From 8535b30cd3347e56d9b28255f4806f604ff668db Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Mon, 5 Dec 2022 10:03:06 +0100
Subject: [PATCH 01/62] remove forgot variables

---
 bin/ncbo_ontology_pull | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/bin/ncbo_ontology_pull b/bin/ncbo_ontology_pull
index 131ef543..a017e4d7 100755
--- a/bin/ncbo_ontology_pull
+++ b/bin/ncbo_ontology_pull
@@ -33,11 +33,7 @@ logger.info "Starting ncbo pull"; logger.flush
 puller = NcboCron::Models::OntologyPull.new
 begin
   puller.do_ontology_pull(ontology_acronym, logger: logger , enable_pull_umls:true )
-rescue NcboCron::Models::OntologyPull::RemoteFileException => e
-  logger.error "RemoteFileException: No submission file at pull location #{last.pullLocation.to_s} for ontology #{ont.acronym}."
-  logger.flush
 rescue StandardError => e
-  e.backtrace
   logger.error e.message
   logger.flush
 end

From f7aa1beafbe13b31d0bd6fe62f88b77e2dbf5866 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Wed, 21 Dec 2022 16:38:55 -0800
Subject: [PATCH 02/62] fix for #61

- create contact instance if it doesn't exist
- changed --from-api to --from-apikey
- minor linting
---
 bin/ncbo_ontology_import | 50 ++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 22 deletions(-)

diff --git a/bin/ncbo_ontology_import b/bin/ncbo_ontology_import
index db2e90c5..3dfb7d57 100755
--- a/bin/ncbo_ontology_import
+++ b/bin/ncbo_ontology_import
@@ -20,11 +20,11 @@ require 'net/http'
 require 'optparse'
 ontologies_acronyms = ''
 ontology_source = ''
-source_api = ''
+source_apikey = ''
 username = ''
 opt_parser = OptionParser.new do |opts|
   opts.banner = 'Usage: ncbo_ontology_import [options]'
-  opts.on('-o', '--ontology ACRONYM', 'Ontologies acronyms which we want to import (separated by comma)') do |acronym|
+  opts.on('-o', '--ontologies ACRONYM1,ACRONYM2', 'Comma-separated list of ontologies to import') do |acronym|
     ontologies_acronyms = acronym
   end
 
@@ -32,8 +32,8 @@ opt_parser = OptionParser.new do |opts|
     ontology_source = url.to_s
   end
 
-  opts.on('--from-api api', 'An apikey to acces the ontoportal api') do |api|
-    source_api = api.to_s
+  opts.on('--from-apikey apikey', 'An apikey to acces the ontoportal api') do |apikey|
+    source_apikey = apikey.to_s
   end
 
   opts.on('--admin-user username', 'The target admin user that will submit the ontology') do |user|
@@ -46,11 +46,14 @@ opt_parser = OptionParser.new do |opts|
   end
 end
 opt_parser.parse!
+if ontologies_acronyms.empty?
+  puts opts
+  exit(1)
+end
 
 # URL of the API and APIKEY of the Ontoportal  we want to import data FROM
-SOURCE_API =  ontology_source
-SOURCE_APIKEY =  source_api
-
+SOURCE_API = ontology_source
+SOURCE_APIKEY = source_apikey
 
 # The username of the user that will have the administration rights on the ontology on the target portal
 TARGETED_PORTAL_USER = username
@@ -58,17 +61,15 @@ TARGETED_PORTAL_USER = username
 # The list of acronyms of ontologies to import
 ONTOLOGIES_TO_IMPORT = ontologies_acronyms.split(',') || []
 
-
 def get_user(username)
   user = LinkedData::Models::User.find(username).first
   raise "The user #{username} does not exist" if user.nil?
+
   user.bring_remaining
 end
 
-
 # A function to create a new ontology (if already Acronym already existing on the portal it will return HTTPConflict)
 def create_ontology(ont_info)
-
   new_ontology = LinkedData::Models::Ontology.new
 
   new_ontology.acronym = ont_info['acronym']
@@ -97,23 +98,29 @@ def upload_submission(sub_info, ontology)
   # Build the json body
   # hasOntologyLanguage options: OWL, UMLS, SKOS, OBO
   # status: alpha, beta, production, retired
-  attr_to_reject = %w[id submissionStatus hasOntologyLanguage metrics ontology @id @type contact]
-  to_copy = sub_info.select do |k,v|
+  attr_to_reject = %w[id submissionStatus hasOntologyLanguage metrics ontology @id @type contact uploadFilePath diffFilePath]
+  to_copy = sub_info.select do |k, v|
     !v.nil? && !v.is_a?(Hash) && !v.to_s.empty? && !attr_to_reject.include?(k)
   end
   to_copy["ontology"] = ontology
-  to_copy["contact"] =  [LinkedData::Models::Contact.where(email: USER.email).first]
-  to_copy["hasOntologyLanguage"] =  LinkedData::Models::OntologyFormat.where(acronym: sub_info["hasOntologyLanguage"]).first
+
+  unless LinkedData::Models::Contact.where(email: USER.email).to_a[0]
+    LinkedData::Models::Contact.new(name: USER.username, email: USER.email).save
+    puts "created a new contact; name: #{USER.username}, email: #{USER.email}"
+  end
+
+  to_copy["contact"] = [LinkedData::Models::Contact.where(email: USER.email).first]
+  to_copy["hasOntologyLanguage"] = LinkedData::Models::OntologyFormat.where(acronym: sub_info["hasOntologyLanguage"]).first
 
   to_copy.each do |key, value|
     attribute_settings = new_submission.class.attribute_settings(key.to_sym)
 
     if attribute_settings
-      if  attribute_settings[:enforce]&.include?(:date_time)
+      if attribute_settings[:enforce]&.include?(:date_time)
         value = DateTime.parse(value)
       elsif attribute_settings[:enforce]&.include?(:uri) && attribute_settings[:enforce]&.include?(:list)
         value = value.map { |v| RDF::IRI.new(v) }
-      elsif  attribute_settings[:enforce]&.include?(:uri)
+      elsif attribute_settings[:enforce]&.include?(:uri)
         value = RDF::IRI.new(value)
       end
     end
@@ -126,10 +133,10 @@ end
 
 
 USER = get_user username
-#get apikey for admin user
+# get apikey for admin user
 TARGET_APIKEY = USER.apikey
 
-SOURCE_APIKEY == '' && abort('--from-api has to be set')
+SOURCE_APIKEY == '' && abort('--from-apikey has to be set')
 SOURCE_API == '' && abort('--from has to be set')
 
 def result_log(ressource, errors)
@@ -143,10 +150,11 @@ end
 # Go through all ontologies acronym and get their latest_submission informations
 ONTOLOGIES_TO_IMPORT.each do |ont|
   sub_info = JSON.parse(Net::HTTP.get(URI.parse("#{SOURCE_API}/ontologies/#{ont}/latest_submission?apikey=#{SOURCE_APIKEY}&display=all")))
-  puts "Import #{ont} " ,
+  puts "Import #{ont} ",
        "From #{SOURCE_API}"
   # if the ontology is already created then it will return HTTPConflict, no consequences
   raise "The ontology #{ont} does not exist" if sub_info['ontology'].nil?
+
   new_ontology = create_ontology(sub_info['ontology'])
   errors = nil
   if new_ontology.valid?
@@ -159,6 +167,7 @@ ONTOLOGIES_TO_IMPORT.each do |ont|
 
   new_ontology ||= LinkedData::Models::Ontology.where(acronym: ont).first
   new_submission = upload_submission(sub_info, new_ontology)
+
   if new_submission.valid?
     new_submission.save
     errors = nil
@@ -167,6 +176,3 @@ ONTOLOGIES_TO_IMPORT.each do |ont|
   end
   result_log(sub_info["id"], errors)
 end
-
-
-

From f03b2aa3710bb54f7676df5085ccd95168033970 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Mon, 9 Jan 2023 11:05:52 -0800
Subject: [PATCH 03/62] Restore branch specifier to develop

---
 Gemfile      |  8 ++++----
 Gemfile.lock | 14 +++++++-------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/Gemfile b/Gemfile
index 747f3b5d..c552979f 100644
--- a/Gemfile
+++ b/Gemfile
@@ -21,10 +21,10 @@ gem 'sys-proctable'
 gem 'cube-ruby', require: 'cube'
 
 # NCBO
-gem 'goo', github: 'ncbo/goo', branch: 'master'
-gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'master'
-gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'master'
-gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'master'
+gem 'goo', github: 'ncbo/goo', branch: 'develop'
+gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'develop'
+gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'develop'
+gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'develop'
 
 group :test do
   gem 'email_spec'
diff --git a/Gemfile.lock b/Gemfile.lock
index db2885f2..14c9d7f3 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 6fcab82f5abbaf08a4a0104d00ada0b40a322a31
-  branch: master
+  revision: 9a5d60d6937658dbb62690dcb33039ac03fb7556
+  branch: develop
   specs:
     goo (0.0.2)
       addressable (~> 2.8)
@@ -15,8 +15,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 71d41e3afb35dafe29abfb6d9becaadc725bad36
-  branch: master
+  revision: 75d1a8f302c8af4060bf62fc619f230084da521e
+  branch: develop
   specs:
     ncbo_annotator (0.0.1)
       goo
@@ -26,8 +26,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 4f9139d870c3b1771af1127afa17b679bd0f60dc
-  branch: master
+  revision: 8698363f8d20ac715d8c96016197d70f2fe8f4b1
+  branch: develop
   specs:
     ontologies_linked_data (0.0.1)
       activesupport
@@ -47,7 +47,7 @@ GIT
 GIT
   remote: https://github.com/ncbo/sparql-client.git
   revision: fb4a89b420f8eb6dda5190a126b6c62e32c4c0c9
-  branch: master
+  branch: develop
   specs:
     sparql-client (1.0.1)
       json_pure (>= 1.4)

From e383b54e8bba2ca15dbe25563d8f0b341d54dd5d Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Sat, 14 Jan 2023 00:00:58 -0800
Subject: [PATCH 04/62] Optimization - remove repeated query

---
 bin/ncbo_ontology_import | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/bin/ncbo_ontology_import b/bin/ncbo_ontology_import
index 3dfb7d57..09b5a0a7 100755
--- a/bin/ncbo_ontology_import
+++ b/bin/ncbo_ontology_import
@@ -104,12 +104,13 @@ def upload_submission(sub_info, ontology)
   end
   to_copy["ontology"] = ontology
 
-  unless LinkedData::Models::Contact.where(email: USER.email).to_a[0]
-    LinkedData::Models::Contact.new(name: USER.username, email: USER.email).save
+  contact = LinkedData::Models::Contact.where(email: USER.email).first
+  unless contact
+    contact = LinkedData::Models::Contact.new(name: USER.username, email: USER.email).save
     puts "created a new contact; name: #{USER.username}, email: #{USER.email}"
   end
 
-  to_copy["contact"] = [LinkedData::Models::Contact.where(email: USER.email).first]
+  to_copy["contact"] = [contact]
   to_copy["hasOntologyLanguage"] = LinkedData::Models::OntologyFormat.where(acronym: sub_info["hasOntologyLanguage"]).first
 
   to_copy.each do |key, value|

From a0297f2f48bcd44651dd73aad91bf60bf2719ee3 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Mon, 30 Jan 2023 16:09:49 -0800
Subject: [PATCH 05/62] Gemfile.lock update

---
 Gemfile.lock | 44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 221f0abc..adededb9 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 091e0ca001244a7dbaed0644b0b1087a3a24d16a
+  revision: 15023141f6051d4fa6cba6081d082c720327b0c9
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: bad8c646205014b1fc82793fb9c07d7075b4c068
+  revision: 75d1a8f302c8af4060bf62fc619f230084da521e
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: a00dac9a0825697cb7f6ac5e0f4db6ab8f4bae79
+  revision: d7425e581d35b265a0263faba7c32c0fdb51cbba
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -79,7 +79,7 @@ GEM
     bcrypt (3.1.18)
     builder (3.2.4)
     coderay (1.1.3)
-    concurrent-ruby (1.1.10)
+    concurrent-ruby (1.2.0)
     connection_pool (2.3.0)
     cube-ruby (0.0.3)
     dante (0.2.0)
@@ -90,7 +90,7 @@ GEM
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (1.10.2)
+    faraday (1.10.3)
       faraday-em_http (~> 1.0)
       faraday-em_synchrony (~> 1.0)
       faraday-excon (~> 1.1)
@@ -116,7 +116,7 @@ GEM
     ffi (1.15.5)
     google-apis-analytics_v3 (0.12.0)
       google-apis-core (>= 0.9.1, < 2.a)
-    google-apis-core (0.9.1)
+    google-apis-core (0.10.0)
       addressable (~> 2.5, >= 2.5.1)
       googleauth (>= 0.16.2, < 2.a)
       httpclient (>= 2.8.1, < 3.a)
@@ -139,13 +139,13 @@ GEM
     httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
-    json (2.6.2)
-    json_pure (2.6.2)
-    jwt (2.5.0)
-    launchy (2.5.0)
-      addressable (~> 2.7)
-    libxml-ruby (3.2.4)
-    logger (1.5.1)
+    json (2.6.3)
+    json_pure (2.6.3)
+    jwt (2.6.0)
+    launchy (2.5.2)
+      addressable (~> 2.8)
+    libxml-ruby (4.0.0)
+    logger (1.5.3)
     macaddr (1.7.2)
       systemu (~> 2.6.5)
     mail (2.6.6)
@@ -160,7 +160,7 @@ GEM
     mlanett-redis-lock (0.2.7)
       redis
     multi_json (1.15.0)
-    multipart-post (2.2.3)
+    multipart-post (2.3.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
     oj (2.18.5)
@@ -170,19 +170,19 @@ GEM
     parseconfig (1.1.2)
     pony (1.13.1)
       mail (>= 2.0)
-    pry (0.14.1)
+    pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    public_suffix (5.0.0)
-    rack (3.0.0)
+    public_suffix (5.0.1)
+    rack (3.0.4.1)
     rack-test (2.0.2)
       rack (>= 1.3)
     rake (13.0.6)
     rdf (1.0.8)
       addressable (>= 2.2)
-    redis (5.0.5)
+    redis (5.0.6)
       redis-client (>= 0.9.0)
-    redis-client (0.11.0)
+    redis-client (0.12.1)
       connection_pool
     representable (3.2.0)
       declarative (< 0.1.0)
@@ -208,13 +208,13 @@ GEM
       faraday (>= 0.17.5, < 3.a)
       jwt (>= 1.5, < 3.0)
       multi_json (~> 1.10)
-    sys-proctable (1.2.7)
+    sys-proctable (1.3.0)
       ffi (~> 1.1)
     systemu (2.6.5)
     test-unit-minitest (0.9.1)
       minitest (~> 4.7)
     trailblazer-option (0.1.2)
-    tzinfo (2.0.5)
+    tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
     uber (0.1.0)
     unf (0.1.4)
@@ -222,7 +222,7 @@ GEM
     unf_ext (0.0.8.2)
     uuid (2.3.9)
       macaddr (~> 1.0)
-    webrick (1.7.0)
+    webrick (1.8.1)
 
 PLATFORMS
   ruby

From 2dfd9dae49b68c771ccb764a9dabc28355ac71f2 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 31 Jan 2023 11:58:26 -0800
Subject: [PATCH 06/62] Gemfile.lock update

---
 Gemfile.lock | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index d2603d5b..b190ad81 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 75d1a8f302c8af4060bf62fc619f230084da521e
+  revision: 0d5a4d823d9c9df11ba98292f06971bb9a127235
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: d7425e581d35b265a0263faba7c32c0fdb51cbba
+  revision: e6372f193488a69ef0c2015017ace8a48274a326
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)

From 7f0589ea6f20ef798d9228766b5d13ea3b0a75e0 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 1 Feb 2023 09:06:34 -0800
Subject: [PATCH 07/62] Gemfile.lock update

---
 Gemfile.lock | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index b190ad81..d0ca376e 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 0d5a4d823d9c9df11ba98292f06971bb9a127235
+  revision: f5484f7f2003a761812d09ea83c00e248034e0e7
   branch: develop
   specs:
     ncbo_annotator (0.0.1)

From 6db9916caf99cb839fc5996eabae4e48a5ac13f2 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 1 Feb 2023 09:36:36 -0800
Subject: [PATCH 08/62] Gemfile had references to develop branch

---
 Gemfile      |  8 ++++----
 Gemfile.lock | 14 +++++++-------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/Gemfile b/Gemfile
index c552979f..747f3b5d 100644
--- a/Gemfile
+++ b/Gemfile
@@ -21,10 +21,10 @@ gem 'sys-proctable'
 gem 'cube-ruby', require: 'cube'
 
 # NCBO
-gem 'goo', github: 'ncbo/goo', branch: 'develop'
-gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'develop'
-gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'develop'
-gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'develop'
+gem 'goo', github: 'ncbo/goo', branch: 'master'
+gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'master'
+gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'master'
+gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'master'
 
 group :test do
   gem 'email_spec'
diff --git a/Gemfile.lock b/Gemfile.lock
index d0ca376e..ac18938b 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 15023141f6051d4fa6cba6081d082c720327b0c9
-  branch: develop
+  revision: 919c20dec58375eb8a4dd1aed47864e2ad7bacfa
+  branch: master
   specs:
     goo (0.0.2)
       addressable (~> 2.8)
@@ -15,8 +15,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: f5484f7f2003a761812d09ea83c00e248034e0e7
-  branch: develop
+  revision: fa8fc96c7f55b1a37f2677bde3d2d16fa93712be
+  branch: master
   specs:
     ncbo_annotator (0.0.1)
       goo
@@ -26,8 +26,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e6372f193488a69ef0c2015017ace8a48274a326
-  branch: develop
+  revision: b22237dc0753ac3824ad60780ce386162142ebcd
+  branch: master
   specs:
     ontologies_linked_data (0.0.1)
       activesupport
@@ -47,7 +47,7 @@ GIT
 GIT
   remote: https://github.com/ncbo/sparql-client.git
   revision: fb4a89b420f8eb6dda5190a126b6c62e32c4c0c9
-  branch: develop
+  branch: master
   specs:
     sparql-client (1.0.1)
       json_pure (>= 1.4)

From f47a07b7ce284b3397d6a158d5a08c7fd60ef609 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Fri, 10 Feb 2023 15:17:00 -0800
Subject: [PATCH 09/62] implemented #64 - ability to generate labels
 independently of RDF processing (and vise versa)

---
 Gemfile.lock                                | 2 +-
 bin/ncbo_ontology_process                   | 6 +++---
 lib/ncbo_cron/ontology_submission_parser.rb | 1 +
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index d0ca376e..632dabeb 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: f5484f7f2003a761812d09ea83c00e248034e0e7
+  revision: 2ee3915af8aa96be7f5fce825c25c6291c8952e5
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
diff --git a/bin/ncbo_ontology_process b/bin/ncbo_ontology_process
index d96f0d87..c3d5237c 100755
--- a/bin/ncbo_ontology_process
+++ b/bin/ncbo_ontology_process
@@ -31,9 +31,9 @@ opt_parser = OptionParser.new do |opts|
   end
 
   options[:tasks] = NcboCron::Models::OntologySubmissionParser::ACTIONS
-  opts.on('-t', '--tasks process_rdf,index_search,run_metrics', "Optional comma-separated list of processing tasks to perform. Default: #{NcboCron::Models::OntologySubmissionParser::ACTIONS.keys.join(',')}") do |tasks|
-    t = tasks.split(",").map {|t| t.strip.sub(/^:/, '').to_sym}
-    options[:tasks].each {|k, _| options[:tasks][k] = false unless t.include?(k)}
+  opts.on('-t', '--tasks process_rdf,generate_labels=false,index_search,run_metrics', "Optional comma-separated list of processing tasks to perform (or exclude). Default: #{NcboCron::Models::OntologySubmissionParser::ACTIONS.keys.join(',')}") do |tasks|
+    work_tasks = tasks.split(',').map { |t| t.gsub(/\s+/, '').gsub(/^:/, '') }.select { |t| k = t.split('='); k.length <= 1 || k[1].downcase === 'true' }.map { |t| t.gsub(/\=true$/, '').to_sym }
+    options[:tasks].each {|k, _| options[:tasks][k] = false unless work_tasks.include?(k)}
   end
 
   options[:logfile] = STDOUT
diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index fe7a3e06..dfa7b320 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -10,6 +10,7 @@ class OntologySubmissionParser
 
       ACTIONS = {
         :process_rdf => true,
+        :generate_labels => true,
         :index_search => true,
         :index_properties => true,
         :run_metrics => true,

From dbd4060ffe7454c325065f433c91c92e24068a0c Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Fri, 10 Feb 2023 15:17:35 -0800
Subject: [PATCH 10/62] Gemfile.lock update

---
 Gemfile.lock | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 632dabeb..84b4eccf 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -117,7 +117,7 @@ GEM
     ffi (1.15.5)
     google-apis-analytics_v3 (0.12.0)
       google-apis-core (>= 0.9.1, < 2.a)
-    google-apis-core (0.10.0)
+    google-apis-core (0.11.0)
       addressable (~> 2.5, >= 2.5.1)
       googleauth (>= 0.16.2, < 2.a)
       httpclient (>= 2.8.1, < 3.a)
@@ -142,7 +142,7 @@ GEM
       concurrent-ruby (~> 1.0)
     json (2.6.3)
     json_pure (2.6.3)
-    jwt (2.6.0)
+    jwt (2.7.0)
     launchy (2.5.2)
       addressable (~> 2.8)
     libxml-ruby (4.0.0)

From 5c6cf910a95c4c990b9e9135ae0e4db292db1159 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Mon, 13 Feb 2023 18:57:56 -0800
Subject: [PATCH 11/62] fixed a bug in #64

---
 Gemfile.lock              | 2 +-
 bin/ncbo_ontology_process | 9 +++++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 84b4eccf..f230ace8 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e6372f193488a69ef0c2015017ace8a48274a326
+  revision: 297f630ee5a35a78b015adf32fdb1e3af59ca652
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
diff --git a/bin/ncbo_ontology_process b/bin/ncbo_ontology_process
index c3d5237c..879e749d 100755
--- a/bin/ncbo_ontology_process
+++ b/bin/ncbo_ontology_process
@@ -32,8 +32,13 @@ opt_parser = OptionParser.new do |opts|
 
   options[:tasks] = NcboCron::Models::OntologySubmissionParser::ACTIONS
   opts.on('-t', '--tasks process_rdf,generate_labels=false,index_search,run_metrics', "Optional comma-separated list of processing tasks to perform (or exclude). Default: #{NcboCron::Models::OntologySubmissionParser::ACTIONS.keys.join(',')}") do |tasks|
-    work_tasks = tasks.split(',').map { |t| t.gsub(/\s+/, '').gsub(/^:/, '') }.select { |t| k = t.split('='); k.length <= 1 || k[1].downcase === 'true' }.map { |t| t.gsub(/\=true$/, '').to_sym }
-    options[:tasks].each {|k, _| options[:tasks][k] = false unless work_tasks.include?(k)}
+    tasks_obj = {}
+    tasks.split(',').each { |t|
+      t_arr = t.gsub(/\s+/, '').gsub(/^:/, '').split('=')
+      tasks_obj[t_arr[0].to_sym] = (t_arr.length <= 1 || t_arr[1].downcase === 'true')
+    }
+    tasks_obj[:generate_labels] = true if tasks_obj[:process_rdf] && !tasks_obj.has_key?(:generate_labels)
+    options[:tasks].each {|k, _| options[:tasks][k] = false unless tasks_obj[k]}
   end
 
   options[:logfile] = STDOUT

From c09d76eeb131caf422c18ba49580db1b47df86dc Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 14 Feb 2023 16:07:43 -0800
Subject: [PATCH 12/62] Relocate docker-compose file and update default configs

---
 .dockerignore                                 |   8 +-
 .github/workflows/ruby-unit-tests.yml         |   4 +-
 Dockerfile                                    |   2 +
 config/config.rb.sample                       |  75 +++++++++----
 config/config.test.rb                         |  63 +++++++----
 dip.yml                                       |  54 +++++++++
 test/docker-compose.yml => docker-compose.yml | 103 ++++++++++--------
 7 files changed, 211 insertions(+), 98 deletions(-)
 create mode 100644 dip.yml
 rename test/docker-compose.yml => docker-compose.yml (52%)

diff --git a/.dockerignore b/.dockerignore
index c712142f..119eac79 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -1,5 +1,6 @@
 # Git
-#.git
+.git
+.github
 .gitignore
 # Logs
 log/*
@@ -8,3 +9,8 @@ tmp/*
 # Editor temp files
 *.swp
 *.swo
+coverage
+create_permissions.log
+# Ignore generated test data
+test/data/ontology_files/repo/**/*
+test/data/tmp/*
diff --git a/.github/workflows/ruby-unit-tests.yml b/.github/workflows/ruby-unit-tests.yml
index cde331e3..5f0db7e1 100644
--- a/.github/workflows/ruby-unit-tests.yml
+++ b/.github/workflows/ruby-unit-tests.yml
@@ -8,17 +8,15 @@ jobs:
   test:
     strategy:
       matrix:
-        backend: ['ruby', 'ruby-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
+        backend: ['ncbo_cron', 'ncbo_cron-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
     - name: copy config.rb file from template
       run:  cp config/config.test.rb config/config.rb
     - name: Build docker-compose
-      working-directory: ./test
       run: docker-compose build
     - name: Run unit tests
-      working-directory: ./test
       run: |
         ci_env=`bash <(curl -s https://codecov.io/env)`
         docker-compose run $ci_env -e CI --rm ${{ matrix.backend }} bundle exec rake test TESTOPTS='-v'
diff --git a/Dockerfile b/Dockerfile
index cd191621..dfc03492 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -20,4 +20,6 @@ ENV BUNDLE_PATH=/srv/ontoportal/bundle
 RUN bundle install
 
 COPY . /srv/ontoportal/ncbo_cron
+RUN cp /srv/ontoportal/ncbo_cron/config/config.rb.sample /srv/ontoportal/ncbo_cron/config/config.rb
+
 CMD ["/bin/bash"]
diff --git a/config/config.rb.sample b/config/config.rb.sample
index 15125224..8d204311 100644
--- a/config/config.rb.sample
+++ b/config/config.rb.sample
@@ -1,16 +1,42 @@
-LinkedData.config do |config|
-  config.enable_monitoring = false
-  config.cube_host = "localhost"
-  config.goo_host = "localhost"
-  config.goo_port = 8080
-  config.search_server_url = "http://localhost:8983/solr/term_search_core1"
-  config.property_search_server_url = "http://localhost:8983/solr/prop_search_core1"
-  config.repository_folder = "./test/data/ontology_files/repo"
-  config.http_redis_host = "localhost"
-  config.http_redis_port = 6379
-  config.goo_redis_host = "localhost"
-  config.goo_redis_port = 6379
+# This file is designed to be used for unit testing with docker-compose
+
+GOO_BACKEND_NAME      = ENV.include?("GOO_BACKEND_NAME")      ? ENV["GOO_BACKEND_NAME"]      : "4store"
+GOO_HOST              = ENV.include?("GOO_HOST")              ? ENV["GOO_HOST"]              : "localhost"
+GOO_PATH_DATA         = ENV.include?("GOO_PATH_DATA")         ? ENV["GOO_PATH_DATA"]         : "/data/"
+GOO_PATH_QUERY        = ENV.include?("GOO_PATH_QUERY")        ? ENV["GOO_PATH_QUERY"]        : "/sparql/"
+GOO_PATH_UPDATE       = ENV.include?("GOO_PATH_UPDATE")       ? ENV["GOO_PATH_UPDATE"]       : "/update/"
+GOO_PORT              = ENV.include?("GOO_PORT")              ? ENV["GOO_PORT"]              : 9000
+MGREP_HOST            = ENV.include?("MGREP_HOST")            ? ENV["MGREP_HOST"]            : "localhost"
+MGREP_PORT            = ENV.include?("MGREP_PORT")            ? ENV["MGREP_PORT"]            : 55555
+MGREP_DICT_PATH       = ENV.include?("MGREP_DICT_PATH")       ? ENV["MGREP_DICT_PATH"]       : "./test/data/dictionary.txt"
+REDIS_GOO_CACHE_HOST  = ENV.include?("REDIS_GOO_CACHE_HOST")  ? ENV["REDIS_GOO_CACHE_HOST"]  : "localhost"
+REDIS_HTTP_CACHE_HOST = ENV.include?("REDIS_HTTP_CACHE_HOST") ? ENV["REDIS_HTTP_CACHE_HOST"] : "localhost"
+REDIS_PERSISTENT_HOST = ENV.include?("REDIS_PERSISTENT_HOST") ? ENV["REDIS_PERSISTENT_HOST"] : "localhost"
+REDIS_PORT            = ENV.include?("REDIS_PORT")            ? ENV["REDIS_PORT"]            : 6379
+REPORT_PATH           = ENV.include?("REPORT_PATH")           ? ENV["REPORT_PATH"]           : "./test/tmp/ontologies_report.json"
+REPOSITORY_FOLDER     = ENV.include?("REPOSITORY_FOLDER")     ? ENV["REPOSITORY_FOLDER"]     : "./test/data/ontology_files/repo"
+REST_URL_PREFIX       = ENV.include?("REST_URL_PREFIX")       ? ENV["REST_URL_PREFIX"]       : "http://localhost:9393"
+SOLR_PROP_SEARCH_URL  = ENV.include?("SOLR_PROP_SEARCH_URL")  ? ENV["SOLR_PROP_SEARCH_URL"]  : "http://localhost:8983/solr/prop_search_core1"
+SOLR_TERM_SEARCH_URL  = ENV.include?("SOLR_TERM_SEARCH_URL")  ? ENV["SOLR_TERM_SEARCH_URL"]  : "http://localhost:8983/solr/term_search_core1"
 
+LinkedData.config do |config|
+  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
+  config.goo_host                      = GOO_HOST.to_s
+  config.goo_port                      = GOO_PORT.to_i
+  config.goo_path_query                = GOO_PATH_QUERY.to_s
+  config.goo_path_data                 = GOO_PATH_DATA.to_s
+  config.goo_path_update               = GOO_PATH_UPDATE.to_s
+  config.goo_redis_host                = REDIS_GOO_CACHE_HOST.to_s
+  config.goo_redis_port                = REDIS_PORT.to_i
+  config.http_redis_host               = REDIS_HTTP_CACHE_HOST.to_s
+  config.http_redis_port               = REDIS_PORT.to_i
+  config.ontology_analytics_redis_host = REDIS_PERSISTENT_HOST.to_s
+  config.ontology_analytics_redis_port = REDIS_PORT.to_i
+  config.repository_folder             = REPOSITORY_FOLDER.to_s
+  config.search_server_url             = SOLR_TERM_SEARCH_URL.to_s
+  config.property_search_server_url    = SOLR_PROP_SEARCH_URL.to_s
+#  config.replace_url_prefix            = false
+#  config.rest_url_prefix               = REST_URL_PREFIX.to_s
   # Email notifications.
   config.enable_notifications    = true
   config.email_sender            = "sender@domain.com" # Default sender for emails
@@ -19,27 +45,30 @@ LinkedData.config do |config|
   config.smtp_user               = nil
   config.smtp_password           = nil
   config.smtp_auth_type          = :none
-  config.smtp_domain             = "localhost.localhost"  
+  config.smtp_domain             = "localhost.localhost"
 end
 
 Annotator.config do |config|
-  config.mgrep_dictionary_file   ||= "./test/tmp/dict"
-  config.stop_words_default_file ||= "./config/default_stop_words.txt"
   config.mgrep_host              ||= "localhost"
-  config.mgrep_port              ||= 55555
-  config.annotator_redis_host  ||= "localhost"
-  config.annotator_redis_port  ||= 6379
+  config.annotator_redis_host  = REDIS_PERSISTENT_HOST.to_s
+  config.annotator_redis_port  = REDIS_PORT.to_i
+  config.mgrep_host            = MGREP_HOST.to_s
+  config.mgrep_port            = MGREP_PORT.to_i
+  config.mgrep_dictionary_file = MGREP_DICT_PATH.to_s
 end
 
 NcboCron.config do |config|
-  config.redis_host  ||= "localhost"
-  config.redis_port  ||= 6379
+  config.redis_host = REDIS_PERSISTENT_HOST.to_s
+  config.redis_port = REDIS_PORT.to_i
+  # Ontologies Report config
+  config.ontology_report_path = REPORT_PATH
+
+  # do not deaemonize in docker
+  config.daemonize  = false
+
   config.search_index_all_url = "http://localhost:8983/solr/term_search_core2"
   config.property_search_index_all_url = "http://localhost:8983/solr/prop_search_core2"
 
-  # Ontologies Report config
-  config.ontology_report_path = "./test/reports/ontologies_report.json"
-
   # Google Analytics config
   config.analytics_service_account_email_address = "123456789999-sikipho0wk8q0atflrmw62dj4kpwoj3c@developer.gserviceaccount.com"
   config.analytics_path_to_key_file              = "config/bioportal-analytics.p12"
diff --git a/config/config.test.rb b/config/config.test.rb
index 0729a4b0..84a621ac 100644
--- a/config/config.test.rb
+++ b/config/config.test.rb
@@ -1,33 +1,42 @@
 # This file is designed to be used for unit testing with docker-compose
-#
-GOO_PATH_QUERY   = ENV.include?("GOO_PATH_QUERY")   ? ENV["GOO_PATH_QUERY"]   : "/sparql/"
-GOO_PATH_DATA    = ENV.include?("GOO_PATH_DATA")    ? ENV["GOO_PATH_DATA"]    : "/data/"
-GOO_PATH_UPDATE  = ENV.include?("GOO_PATH_UPDATE")  ? ENV["GOO_PATH_UPDATE"]  : "/update/"
-GOO_BACKEND_NAME = ENV.include?("GOO_BACKEND_NAME") ? ENV["GOO_BACKEND_NAME"] : "localhost"
-GOO_PORT         = ENV.include?("GOO_PORT")         ? ENV["GOO_PORT"]         : 9000
-GOO_HOST         = ENV.include?("GOO_HOST")         ? ENV["GOO_HOST"]         : "localhost"
-REDIS_HOST       = ENV.include?("REDIS_HOST")       ? ENV["REDIS_HOST"]       : "localhost"
-REDIS_PORT       = ENV.include?("REDIS_PORT")       ? ENV["REDIS_PORT"]       : 6379
-MGREP_HOST       = ENV.include?("MGREP_HOST")       ? ENV["MGREP_HOST"]       : "localhost"
-MGREP_PORT       = ENV.include?("MGREP_PORT")       ? ENV["MGREP_PORT"]       : 55555
-SOLR_TERM_SEARCH_URL = ENV.include?("SOLR_TERM_SEARCH_URL") ? ENV["SOLR_TERM_SEARCH_URL"] : "http://localhost:8983/solr/term_search_core1"
-SOLR_PROP_SEARCH_URL = ENV.include?("SOLR_PROP_SEARCH_URL") ? ENV["SOLR_PROP_SEARCH_URL"] : "http://localhost:8983/solr/prop_search_core1"
+
+GOO_BACKEND_NAME      = ENV.include?("GOO_BACKEND_NAME")      ? ENV["GOO_BACKEND_NAME"]      : "4store"
+GOO_HOST              = ENV.include?("GOO_HOST")              ? ENV["GOO_HOST"]              : "localhost"
+GOO_PATH_DATA         = ENV.include?("GOO_PATH_DATA")         ? ENV["GOO_PATH_DATA"]         : "/data/"
+GOO_PATH_QUERY        = ENV.include?("GOO_PATH_QUERY")        ? ENV["GOO_PATH_QUERY"]        : "/sparql/"
+GOO_PATH_UPDATE       = ENV.include?("GOO_PATH_UPDATE")       ? ENV["GOO_PATH_UPDATE"]       : "/update/"
+GOO_PORT              = ENV.include?("GOO_PORT")              ? ENV["GOO_PORT"]              : 9000
+MGREP_HOST            = ENV.include?("MGREP_HOST")            ? ENV["MGREP_HOST"]            : "localhost"
+MGREP_PORT            = ENV.include?("MGREP_PORT")            ? ENV["MGREP_PORT"]            : 55555
+MGREP_DICT_PATH       = ENV.include?("MGREP_DICT_PATH")       ? ENV["MGREP_DICT_PATH"]       : "./test/data/dictionary.txt"
+REDIS_GOO_CACHE_HOST  = ENV.include?("REDIS_GOO_CACHE_HOST")  ? ENV["REDIS_GOO_CACHE_HOST"]  : "localhost"
+REDIS_HTTP_CACHE_HOST = ENV.include?("REDIS_HTTP_CACHE_HOST") ? ENV["REDIS_HTTP_CACHE_HOST"] : "localhost"
+REDIS_PERSISTENT_HOST = ENV.include?("REDIS_PERSISTENT_HOST") ? ENV["REDIS_PERSISTENT_HOST"] : "localhost"
+REDIS_PORT            = ENV.include?("REDIS_PORT")            ? ENV["REDIS_PORT"]            : 6379
+REPORT_PATH           = ENV.include?("REPORT_PATH")           ? ENV["REPORT_PATH"]           : "./test/tmp/ontologies_report.json"
+REPOSITORY_FOLDER     = ENV.include?("REPOSITORY_FOLDER")     ? ENV["REPOSITORY_FOLDER"]     : "./test/data/ontology_files/repo"
+REST_URL_PREFIX       = ENV.include?("REST_URL_PREFIX")       ? ENV["REST_URL_PREFIX"]       : "http://localhost:9393"
+SOLR_PROP_SEARCH_URL  = ENV.include?("SOLR_PROP_SEARCH_URL")  ? ENV["SOLR_PROP_SEARCH_URL"]  : "http://localhost:8983/solr/prop_search_core1"
+SOLR_TERM_SEARCH_URL  = ENV.include?("SOLR_TERM_SEARCH_URL")  ? ENV["SOLR_TERM_SEARCH_URL"]  : "http://localhost:8983/solr/term_search_core1"
 
 LinkedData.config do |config|
+  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
   config.goo_host                      = GOO_HOST.to_s
   config.goo_port                      = GOO_PORT.to_i
-  config.goo_backend_name              = GOO_BACKEND_NAME.to_s
   config.goo_path_query                = GOO_PATH_QUERY.to_s
   config.goo_path_data                 = GOO_PATH_DATA.to_s
   config.goo_path_update               = GOO_PATH_UPDATE.to_s
-  config.goo_redis_host                = REDIS_HOST.to_s
+  config.goo_redis_host                = REDIS_GOO_CACHE_HOST.to_s
   config.goo_redis_port                = REDIS_PORT.to_i
-  config.http_redis_host               = REDIS_HOST.to_s
+  config.http_redis_host               = REDIS_HTTP_CACHE_HOST.to_s
   config.http_redis_port               = REDIS_PORT.to_i
-  config.ontology_analytics_redis_host = REDIS_HOST.to_s
+  config.ontology_analytics_redis_host = REDIS_PERSISTENT_HOST.to_s
   config.ontology_analytics_redis_port = REDIS_PORT.to_i
+  config.repository_folder             = REPOSITORY_FOLDER.to_s
   config.search_server_url             = SOLR_TERM_SEARCH_URL.to_s
   config.property_search_server_url    = SOLR_PROP_SEARCH_URL.to_s
+#  config.replace_url_prefix            = false
+#  config.rest_url_prefix               = REST_URL_PREFIX.to_s
   # Email notifications.
   config.enable_notifications    = true
   config.email_sender            = "sender@domain.com" # Default sender for emails
@@ -40,15 +49,21 @@
 end
 
 Annotator.config do |config|
-  config.annotator_redis_host          = REDIS_HOST.to_s
-  config.annotator_redis_port          = REDIS_PORT.to_i
-  config.mgrep_host                    = MGREP_HOST.to_s
-  config.mgrep_port                    = MGREP_PORT.to_i
-  config.mgrep_dictionary_file         = "./test/data/dictionary.txt"
+  config.annotator_redis_host  = REDIS_PERSISTENT_HOST.to_s
+  config.annotator_redis_port  = REDIS_PORT.to_i
+  config.mgrep_host            = MGREP_HOST.to_s
+  config.mgrep_port            = MGREP_PORT.to_i
+  config.mgrep_dictionary_file = MGREP_DICT_PATH.to_s
 end
 
+# LinkedData::OntologiesAPI.config do |config|
+#   config.http_redis_host = REDIS_HTTP_CACHE_HOST.to_s
+#   config.http_redis_port = REDIS_PORT.to_i
+# end
+#
 NcboCron.config do |config|
-  config.redis_host = REDIS_HOST.to_s
+  config.daemonize  = false
+  config.redis_host = REDIS_PERSISTENT_HOST.to_s
   config.redis_port = REDIS_PORT.to_i
-  config.ontology_report_path = "./test/ontologies_report.json"
+  config.ontology_report_path = REPORT_PATH
 end
diff --git a/dip.yml b/dip.yml
new file mode 100644
index 00000000..3bbe4444
--- /dev/null
+++ b/dip.yml
@@ -0,0 +1,54 @@
+version: '7.1'
+
+# Define default environment variables to pass
+# to Docker Compose
+#environment:
+#  RAILS_ENV: development
+
+compose:
+  files:
+    - docker-compose.yml
+    #  project_name: ncbo_cron
+
+interaction:
+  # This command spins up a ncbo_cron container with the required dependencies (solr, 4store, etc),
+  # and opens a terminal within it.
+  runner:
+    description: Open a Bash shell within a ncbo_cron container (with dependencies up)
+    service: ncbo_cron
+    command: /bin/bash
+
+  # Run a container without any dependent services
+  bash:
+    description: Run an arbitrary script within a container (or open a shell without deps)
+    service: ncbo_cron
+    command: /bin/bash
+    compose_run_options: [ no-deps ]
+
+  # A shortcut to run Bundler commands
+  bundle:
+    description: Run Bundler commands within ncbo_cron container (with depencendies up)
+    service: ncbo_cron
+    command: bundle
+
+  # A shortcut to run unit tests
+  test:
+    description: Run unit tests with 4store triplestore
+    service: ncbo_cron
+    command: bundle exec rake test TESTOPTS='-v'
+
+  test-ag:
+    description: Run unit tests with AllegroGraph triplestore
+    service: ncbo_cron-agraph
+    command: bundle exec rake test TESTOPTS='-v'
+
+  'redis-cli':
+    description: Run Redis console
+    service: redis-ut
+    command: redis-cli -h redis-ut
+
+#provision:
+  #- dip compose down --volumes
+  #- dip compose up -d solr 4store
+  #- dip bundle install
+  #- dip bash -c bin/setup
diff --git a/test/docker-compose.yml b/docker-compose.yml
similarity index 52%
rename from test/docker-compose.yml
rename to docker-compose.yml
index db957907..ca54bbce 100644
--- a/test/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,43 +1,47 @@
 x-app: &app
-    build:
-      context: ../.
-      args:
-        RUBY_VERSION: '2.7'
-    # Increase the version number in the image tag every time Dockerfile or its arguments is changed
-    image: ncbo_cron-dev:0.0.1
-    environment: &env
-      # default bundle config resolves to /usr/local/bundle/config inside of the container
-      # we are setting it to local app directory if we need to use 'bundle config local'
-      BUNDLE_APP_CONFIG: /srv/ontoportal/ncbo_cron/.bundle
-      BUNDLE_PATH: /srv/ontoportal/bundle
-      COVERAGE: 'true' # enable simplecov code coverage
-      REDIS_HOST: redis-ut
-      REDIS_PORT: 6379
-      SOLR_TERM_SEARCH_URL: http://solr-ut:8983/solr/term_search_core1
-      SOLR_PROP_SEARCH_URL: http://solr-ut:8983/solr/prop_search_core1
-      MGREP_HOST: mgrep-ut
-      MGREP_PORT: 55555
-    stdin_open: true
-    tty: true
-    command: /bin/bash
-    volumes:
-      # bundle volume for hosting gems installed by bundle; it speeds up gem install in local development
-      - bundle:/srv/ontoportal/bundle
-      - ../.:/srv/ontoportal/ncbo_cron
-      # mount directory containing development version of the gems if you need to use 'bundle config local'
-      #- /Users/alexskr/ontoportal:/Users/alexskr/ontoportal
-    depends_on: &depends_on
-      solr-ut:
-        condition: service_healthy
-      redis-ut:
-        condition: service_healthy
-      mgrep-ut:
-        condition: service_healthy
-
+  build:
+    context: .
+    args:
+      RUBY_VERSION: '2.7'
+  # Increase the version number in the image tag every time Dockerfile or its arguments is changed
+  image: ncbo_cron:0.0.1
+  environment: &env
+    BUNDLE_PATH: /srv/ontoportal/bundle
+    # default bundle config resolves to /usr/local/bundle/config inside of the container
+    # we are setting it to local app directory if we need to use 'bundle config local'
+    BUNDLE_APP_CONFIG: /srv/ontoportal/ncbo_cron/.bundle
+    COVERAGE: 'true'
+    GOO_REDIS_HOST: redis-ut
+    REDIS_GOO_CACHE_HOST: redis-ut
+    REDIS_HTTP_CACHE_HOST: redis-ut
+    REDIS_PERSISTENT_HOST: redis-ut
+    REDIS_PORT: 6379
+    SOLR_TERM_SEARCH_URL: http://solr-ut:8983/solr/term_search_core1
+    SOLR_PROP_SEARCH_URL: http://solr-ut:8983/solr/prop_search_core1
+    MGREP_HOST: mgrep-ut
+    MGREP_PORT: 55555
+  stdin_open: true
+  tty: true
+  command: "bundle exec rackup -o 0.0.0.0 --port 9393"
+  ports:
+    - 9393:9393
+  volumes:
+    # bundle volume for hosting gems installed by bundle; it helps in local development with gem udpates
+    - bundle:/srv/ontoportal/bundle
+    # api code
+    - .:/srv/ontoportal/ontologies_api
+    # mount directory containing development version of the gems if you need to use 'bundle config local'
+    #- /Users/alexskr/ontoportal:/Users/alexskr/ontoportal
+  depends_on: &depends_on
+    solr-ut:
+      condition: service_healthy
+    redis-ut:
+      condition: service_healthy
+    mgrep-ut:
+      condition: service_healthy
 
 services:
-  # environment wtih 4store backend
-  ruby:
+  ncbo_cron:
     <<: *app
     environment:
       <<: *env
@@ -54,8 +58,7 @@ services:
       4store-ut:
         condition: service_started
 
-  # environment with AllegroGraph backend
-  ruby-agraph:
+  ncbo_cron-agraph:
     <<: *app
     environment:
       <<: *env
@@ -65,16 +68,15 @@ services:
       GOO_PATH_QUERY: /repositories/bioportal_test
       GOO_PATH_DATA: /repositories/bioportal_test/statements
       GOO_PATH_UPDATE: /repositories/bioportal_test/statements
-      #    profiles:
-        #- agraph
+    profiles:
+      - agraph
     depends_on:
       <<: *depends_on
       agraph-ut:
-        condition: service_started
+        condition: service_healthy
 
   redis-ut:
     image: redis
-    command: ["redis-server", "--save", "", "--appendonly", "no"]
     healthcheck:
       test: redis-cli ping
       interval: 10s
@@ -83,6 +85,7 @@ services:
 
   4store-ut:
     image: bde2020/4store
+    #volume: fourstore:/var/lib/4store
     command: >
       bash -c "4s-backend-setup --segments 4 ontoportal_kb
       && 4s-backend ontoportal_kb
@@ -100,7 +103,7 @@ services:
       retries: 5
 
   mgrep-ut:
-    image: ontoportal/mgrep-ncbo:0.1
+    image: ontoportal/mgrep:0.0.1
     healthcheck:
       test: ["CMD", "nc", "-z", "-v", "localhost", "55555"]
       start_period: 3s
@@ -109,7 +112,7 @@ services:
       retries: 5
 
   agraph-ut:
-    image: franzinc/agraph:v7.3.0
+    image: franzinc/agraph:v7.3.1
     environment:
       - AGRAPH_SUPER_USER=test
       - AGRAPH_SUPER_PASSWORD=xyzzy
@@ -122,8 +125,14 @@ services:
        ; agtool users add anonymous
        ; agtool users grant anonymous root:bioportal_test:rw
        ; tail -f /agraph/data/agraph.log"
-       #    profiles:
-         #- agraph
+    healthcheck:
+      test: ["CMD-SHELL", "agtool storage-report bioportal_test || exit 1"]
+      start_period: 10s
+      interval: 60s
+      timeout: 5s
+      retries: 3
+    profiles:
+      - agraph
 
 volumes:
   bundle:

From 6c6a5c83ad1a8dcf35bdbb97d95bbda986a9a758 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 14 Feb 2023 17:06:12 -0800
Subject: [PATCH 13/62] Add GH workflow for publishing docker images

---
 .github/workflows/docker-image.yml | 35 ++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 .github/workflows/docker-image.yml

diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml
new file mode 100644
index 00000000..b40cbea1
--- /dev/null
+++ b/.github/workflows/docker-image.yml
@@ -0,0 +1,35 @@
+name: Docker Image CI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: bioportal/ncbo_cron
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          build-args: |
+            RUBY_VERSION=2.7
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

From 19886086df10af1ffe10598c9d90c4a9e2a2a686 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 28 Mar 2023 16:56:27 -0700
Subject: [PATCH 14/62] use ruby native method for listing files instead of a
 git function

Resolves warning messages when we exclude .git directory from docker image
---
 Gemfile           | 3 +--
 ncbo_cron.gemspec | 3 ++-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Gemfile b/Gemfile
index c552979f..aae5ab76 100644
--- a/Gemfile
+++ b/Gemfile
@@ -6,7 +6,6 @@ gem 'faraday', '~> 1.9'
 gem 'ffi'
 gem "google-apis-analytics_v3"
 gem 'mail', '2.6.6'
-gem 'minitest', '< 5.0'
 gem 'multi_json'
 gem 'oj', '~> 2.0'
 gem 'parseconfig'
@@ -28,8 +27,8 @@ gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'develop'
 
 group :test do
   gem 'email_spec'
+  gem 'minitest', '< 5.0'
   gem 'simplecov'
   gem 'simplecov-cobertura' # for codecov.io
   gem 'test-unit-minitest'
 end
-
diff --git a/ncbo_cron.gemspec b/ncbo_cron.gemspec
index 821881d1..b57c1138 100644
--- a/ncbo_cron.gemspec
+++ b/ncbo_cron.gemspec
@@ -8,7 +8,8 @@ Gem::Specification.new do |gem|
   gem.summary       = %q{}
   gem.homepage      = "https://github.com/ncbo/ncbo_cron"
 
-  gem.files         = `git ls-files`.split($\)
+  #gem.files         = `git ls-files`.split($\)
+  gem.files         = Dir['**/*']
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
   gem.name          = "ncbo_cron"

From ed261233f0c9fbfb2d3cb1d24a09345192e395c0 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 28 Mar 2023 17:26:01 -0700
Subject: [PATCH 15/62] remove comment

---
 ncbo_cron.gemspec | 1 -
 1 file changed, 1 deletion(-)

diff --git a/ncbo_cron.gemspec b/ncbo_cron.gemspec
index b57c1138..ef21761f 100644
--- a/ncbo_cron.gemspec
+++ b/ncbo_cron.gemspec
@@ -8,7 +8,6 @@ Gem::Specification.new do |gem|
   gem.summary       = %q{}
   gem.homepage      = "https://github.com/ncbo/ncbo_cron"
 
-  #gem.files         = `git ls-files`.split($\)
   gem.files         = Dir['**/*']
   gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
   gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})

From a3668053f23eb57f44737a44eb7e7f2a936bb2cd Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 28 Mar 2023 17:40:38 -0700
Subject: [PATCH 16/62] capitalize argument in order to be consistent with
 other scripts

---
 bin/ncbo_ontology_import | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/bin/ncbo_ontology_import b/bin/ncbo_ontology_import
index 09b5a0a7..57d63aa1 100755
--- a/bin/ncbo_ontology_import
+++ b/bin/ncbo_ontology_import
@@ -28,28 +28,24 @@ opt_parser = OptionParser.new do |opts|
     ontologies_acronyms = acronym
   end
 
-  opts.on('--from url', 'The ontoportal api url source of the ontology') do |url|
+  opts.on('--from URL', 'The ontoportal api url source of the ontology') do |url|
     ontology_source = url.to_s
   end
 
-  opts.on('--from-apikey apikey', 'An apikey to acces the ontoportal api') do |apikey|
+  opts.on('--from-apikey APIKEY', 'An apikey to acces the ontoportal api') do |apikey|
     source_apikey = apikey.to_s
   end
 
-  opts.on('--admin-user username', 'The target admin user that will submit the ontology') do |user|
+  opts.on('--admin-user USERNAME', 'The target admin user that will submit the ontology') do |user|
     username = user.to_s
   end
   # Display the help screen, all programs are assumed to have this option.
-  opts.on( '-h', '--help', 'Display this screen') do
+  opts.on('-h', '--help', 'Display this screen') do
     puts opts
     exit
   end
 end
 opt_parser.parse!
-if ontologies_acronyms.empty?
-  puts opts
-  exit(1)
-end
 
 # URL of the API and APIKEY of the Ontoportal  we want to import data FROM
 SOURCE_API = ontology_source
@@ -132,7 +128,6 @@ def upload_submission(sub_info, ontology)
   new_submission
 end
 
-
 USER = get_user username
 # get apikey for admin user
 TARGET_APIKEY = USER.apikey

From 6ec117409016b1f417354e6cf8c91efc9a5f7dec Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 28 Mar 2023 17:49:58 -0700
Subject: [PATCH 17/62] add arm/64 platform

---
 .github/workflows/docker-image.yml | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml
index b40cbea1..6105c1d8 100644
--- a/.github/workflows/docker-image.yml
+++ b/.github/workflows/docker-image.yml
@@ -12,6 +12,12 @@ jobs:
       - name: Check out the repo
         uses: actions/checkout@v3
 
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
       - name: Log in to Docker Hub
         uses: docker/login-action@v2
         with:
@@ -28,6 +34,7 @@ jobs:
         uses: docker/build-push-action@v4
         with:
           context: .
+          platforms: linux/amd64,linux/arm64
           build-args: |
             RUBY_VERSION=2.7
           push: true

From a461322bcc5909fbe35eeb5307d2ff9c0fcc20dc Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 6 Apr 2023 13:41:13 -0700
Subject: [PATCH 18/62] additional error handling for SPAM deletion script, #60

---
 lib/ncbo_cron/spam_deletion.rb | 40 +++++++++++++++++++++-------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/lib/ncbo_cron/spam_deletion.rb b/lib/ncbo_cron/spam_deletion.rb
index 8db5568b..819ffa9d 100644
--- a/lib/ncbo_cron/spam_deletion.rb
+++ b/lib/ncbo_cron/spam_deletion.rb
@@ -27,6 +27,16 @@ def initialize(logger=nil)
       def run
         auth_token = Base64.decode64(NcboCron.settings.git_repo_access_token)
         res = `curl --header 'Authorization: token #{auth_token}' --header 'Accept: application/vnd.github.v3.raw' --location #{FULL_FILE_PATH}`
+
+        begin
+          error_json = JSON.parse(res)
+          msg = "\nError while fetching the SPAM user list from #{FULL_FILE_PATH}: #{error_json}"
+          @logger.error(msg)
+          puts msg
+          exit
+        rescue JSON::ParserError
+          @logger.info("Successfully downloaded the SPAM user list from #{FULL_FILE_PATH}")
+        end
         usernames = res.split(",").map(&:strip)
         delete_spam(usernames)
       end
@@ -99,25 +109,25 @@ def delete_spam(usernames)
           @logger.info("Deleting #{delete_prov_classes.length} provisional classes...")
           @logger.info("Deleting #{delete_users.length} users...")
 
-          delete_projects.each {|p| p.delete}
-          delete_notes.each {|n| n.delete}
-          delete_reviews.each {|r| r.delete}
-          delete_ontologies.each {|o| o.delete}
-          delete_prov_classes.each {|pc| pc.delete}
-          delete_users.each {|u| u.delete}
+          # delete_projects.each {|p| p.delete}
+          # delete_notes.each {|n| n.delete}
+          # delete_reviews.each {|r| r.delete}
+          # delete_ontologies.each {|o| o.delete}
+          # delete_prov_classes.each {|pc| pc.delete}
+          # delete_users.each {|u| u.delete}
         end
       end
     end
   end
 end
 
-# require 'ontologies_linked_data'
-# require 'goo'
-# require 'ncbo_annotator'
-# require 'ncbo_cron/config'
-# require_relative '../../config/config'
-#
-# spam_deletion_path = File.join("logs", "spam-deletion.log")
-# spam_deletion_logger = Logger.new(spam_deletion_path)
-# NcboCron::Models::SpamDeletion.new(spam_deletion_logger).run
+require 'ontologies_linked_data'
+require 'goo'
+require 'ncbo_annotator'
+require 'ncbo_cron/config'
+require_relative '../../config/config'
+
+spam_deletion_path = File.join("logs", "spam-deletion.log")
+spam_deletion_logger = Logger.new(spam_deletion_path)
+NcboCron::Models::SpamDeletion.new(spam_deletion_logger).run
 # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontology-analytics true --disable-mapping-counts true --disable-ontologies-report true --spam-deletion '14 * * * *'
\ No newline at end of file

From 3b9fdb0704b19e474ad0642da25b33ef5ea84f40 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 6 Apr 2023 13:57:03 -0700
Subject: [PATCH 19/62] additional error handling for SPAM deletion script, #60

---
 lib/ncbo_cron/spam_deletion.rb | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/lib/ncbo_cron/spam_deletion.rb b/lib/ncbo_cron/spam_deletion.rb
index 819ffa9d..e2ec64f8 100644
--- a/lib/ncbo_cron/spam_deletion.rb
+++ b/lib/ncbo_cron/spam_deletion.rb
@@ -25,7 +25,7 @@ def initialize(logger=nil)
       end
 
       def run
-        auth_token = Base64.decode64(NcboCron.settings.git_repo_access_token)
+        auth_token = NcboCron.settings.git_repo_access_token
         res = `curl --header 'Authorization: token #{auth_token}' --header 'Accept: application/vnd.github.v3.raw' --location #{FULL_FILE_PATH}`
 
         begin
@@ -109,25 +109,25 @@ def delete_spam(usernames)
           @logger.info("Deleting #{delete_prov_classes.length} provisional classes...")
           @logger.info("Deleting #{delete_users.length} users...")
 
-          # delete_projects.each {|p| p.delete}
-          # delete_notes.each {|n| n.delete}
-          # delete_reviews.each {|r| r.delete}
-          # delete_ontologies.each {|o| o.delete}
-          # delete_prov_classes.each {|pc| pc.delete}
-          # delete_users.each {|u| u.delete}
+          delete_projects.each {|p| p.delete}
+          delete_notes.each {|n| n.delete}
+          delete_reviews.each {|r| r.delete}
+          delete_ontologies.each {|o| o.delete}
+          delete_prov_classes.each {|pc| pc.delete}
+          delete_users.each {|u| u.delete}
         end
       end
     end
   end
 end
 
-require 'ontologies_linked_data'
-require 'goo'
-require 'ncbo_annotator'
-require 'ncbo_cron/config'
-require_relative '../../config/config'
-
-spam_deletion_path = File.join("logs", "spam-deletion.log")
-spam_deletion_logger = Logger.new(spam_deletion_path)
-NcboCron::Models::SpamDeletion.new(spam_deletion_logger).run
+# require 'ontologies_linked_data'
+# require 'goo'
+# require 'ncbo_annotator'
+# require 'ncbo_cron/config'
+# require_relative '../../config/config'
+#
+# spam_deletion_path = File.join("logs", "spam-deletion.log")
+# spam_deletion_logger = Logger.new(spam_deletion_path)
+# NcboCron::Models::SpamDeletion.new(spam_deletion_logger).run
 # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontology-analytics true --disable-mapping-counts true --disable-ontologies-report true --spam-deletion '14 * * * *'
\ No newline at end of file

From 030930c658c86af0154bb16b3c13a9b585e6ec91 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 11 Apr 2023 11:14:57 -0700
Subject: [PATCH 20/62] implemented #67 - improved corrupt data and error
 handling

---
 Gemfile.lock                                |   8 +-
 bin/ncbo_ontology_archive_old_submissions   | 108 ++++++++++++++++++--
 lib/ncbo_cron/ontology_submission_parser.rb |   2 +-
 3 files changed, 103 insertions(+), 15 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index f230ace8..599d878b 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 15023141f6051d4fa6cba6081d082c720327b0c9
+  revision: b8c7867450ec6ea2d3167eb9d9b1aed5614a1ce3
   branch: develop
   specs:
     goo (0.0.2)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 297f630ee5a35a78b015adf32fdb1e3af59ca652
+  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -46,7 +46,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/sparql-client.git
-  revision: fb4a89b420f8eb6dda5190a126b6c62e32c4c0c9
+  revision: 55e7dbf858eb571c767bc67868f9af61663859cb
   branch: develop
   specs:
     sparql-client (1.0.1)
@@ -235,9 +235,7 @@ GEM
     webrick (1.8.1)
 
 PLATFORMS
-  ruby
   x86_64-darwin-18
-  x86_64-darwin-21
 
 DEPENDENCIES
   cube-ruby
diff --git a/bin/ncbo_ontology_archive_old_submissions b/bin/ncbo_ontology_archive_old_submissions
index 3dc5c87c..535c129e 100755
--- a/bin/ncbo_ontology_archive_old_submissions
+++ b/bin/ncbo_ontology_archive_old_submissions
@@ -11,31 +11,121 @@ require_relative '../lib/ncbo_cron'
 config_exists = File.exist?(File.expand_path('../../config/config.rb', __FILE__))
 abort("Please create a config/config.rb file using the config/config.rb.sample as a template") unless config_exists
 require_relative '../config/config'
+require 'optparse'
 
-logfile = 'archive_old_submissions.log'
+options = { delete: false }
+opt_parser = OptionParser.new do |opts|
+  # Set a banner, displayed at the top of the help screen.
+  opts.banner = "Usage: #{File.basename(__FILE__)} [options]"
+
+  options[:logfile] = STDOUT
+  opts.on( '-l', '--logfile FILE', "Write log to FILE (default is STDOUT)" ) do |filename|
+    options[:logfile] = filename
+  end
+
+  # Delete submission if it contains bad data
+  opts.on( '-d', '--delete', "Delete submissions that contain bad data" ) do
+    options[:delete] = true
+  end
+
+  # Display the help screen, all programs are assumed to have this option.
+  opts.on( '-h', '--help', 'Display this screen' ) do
+    puts opts
+    exit
+  end
+end
+
+opt_parser.parse!
+logfile = options[:logfile]
 if File.file?(logfile); File.delete(logfile); end
 logger = Logger.new(logfile)
-options = { process_rdf: false, index_search: false, index_commit: false,
-            run_metrics: false, reasoning: false, archive: true }
+process_actions = { process_rdf: false, generate_labels: false, index_search: false, index_commit: false,
+            process_annotator: false, diff: false, run_metrics: false, archive: true }
 onts = LinkedData::Models::Ontology.all
 onts.each { |ont| ont.bring(:acronym, :submissions) }
-onts.sort! { |a,b| a.acronym <=> b.acronym }
+onts.sort! { |a, b| a.acronym <=> b.acronym }
+bad_submissions = {}
 
 onts.each do |ont|
   latest_sub = ont.latest_submission
-  if not latest_sub.nil?
+
+  unless latest_sub.nil?
     id = latest_sub.submissionId
     subs = ont.submissions
-    old_subs = subs.reject { |sub| sub.submissionId >= id }
-    old_subs.sort! { |a,b| a.submissionId <=> b.submissionId }
+
+    old_subs = subs.reject { |sub|
+      begin
+        sub.submissionId >= id
+      rescue => e
+        msg = "Invalid submission ID detected (String instead of Integer): #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+        puts msg
+        logger.error(msg)
+
+        if options[:delete]
+          sub.delete if options[:delete]
+          msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to invalid Submission ID"
+          puts msg
+          logger.error(msg)
+        end
+        bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Invalid Submission ID"
+        true
+      end
+    }
+    old_subs.sort! { |a, b| a.submissionId <=> b.submissionId }
     old_subs.each do |sub|
-      if not sub.archived?
+      unless sub.archived?
         msg = "#{ont.acronym}: found un-archived old submission with ID #{sub.submissionId}."
         puts msg
         logger.info msg
-        NcboCron::Models::OntologySubmissionParser.new.process_submission(logger, sub.id.to_s, options)
+
+        begin
+          NcboCron::Models::OntologySubmissionParser.new.process_submission(logger, sub.id.to_s, process_actions)
+        rescue => e
+          if e.class == Goo::Base::NotValidException
+            if sub.valid?
+              msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+              puts msg
+              logger.error(msg)
+              bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Submission passes valid check but cannot be saved"
+            else
+              msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId}:\n#{JSON.pretty_generate(sub.errors)}"
+              puts msg
+              logger.error(msg)
+
+              if options[:delete]
+                sub.delete if options[:delete]
+                msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to invalid data"
+                puts msg
+                logger.error(msg)
+              end
+              bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "Submission is not valid to be saved"
+            end
+          else
+            msg = "Error archiving submission #{ont.acronym}/#{sub.submissionId} - #{e.class}:\n#{e.backtrace.join("\n")}"
+            puts msg
+            logger.error(msg)
+
+            if options[:delete] && (e.class == Net::HTTPBadResponse || e.class == Errno::ECONNREFUSED)
+              sub.delete
+              msg = "Deleted submission #{ont.acronym}/#{sub.submissionId} due to a non-working pull URL"
+              puts msg
+              logger.error(msg)
+            end
+            bad_submissions["#{ont.acronym}/#{sub.submissionId}"] = "#{e.class} - Runtime error"
+          end
+        end
       end
     end
   end
 end
 
+msg = JSON.pretty_generate(bad_submissions)
+puts
+puts msg
+logger.error(msg)
+
+msg = "Number of errored submissions: #{bad_submissions.length}"
+puts msg
+logger.error(msg)
+
+
diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index dfa7b320..a6512312 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -166,7 +166,7 @@ def process_submission(logger, submission_id, actions=ACTIONS)
 
           # Check to make sure the file has been downloaded
           if sub.pullLocation && (!sub.uploadFilePath || !File.exist?(sub.uploadFilePath))
-            multi_logger.debug "Pull location found, but no file in the upload file path. Retrying download."
+            multi_logger.debug "Pull location found (#{sub.pullLocation}, but no file in the upload file path (#{sub.uploadFilePath}. Retrying download."
             file, filename = sub.download_ontology_file
             file_location = sub.class.copy_file_repository(sub.ontology.acronym, sub.submissionId, file, filename)
             file_location = "../" + file_location if file_location.start_with?(".") # relative path fix

From 3308da017161b13d9c27c82654cb8aab7455268e Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 11 Apr 2023 11:15:12 -0700
Subject: [PATCH 21/62] Gemfile.lock update

---
 Gemfile.lock | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 599d878b..3e181fd5 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -74,13 +74,13 @@ GEM
     activesupport (3.2.22.5)
       i18n (~> 0.6, >= 0.6.4)
       multi_json (~> 1.0)
-    addressable (2.8.1)
+    addressable (2.8.4)
       public_suffix (>= 2.0.2, < 6.0)
     bcrypt (3.1.18)
     builder (3.2.4)
     coderay (1.1.3)
-    concurrent-ruby (1.2.0)
-    connection_pool (2.3.0)
+    concurrent-ruby (1.2.2)
+    connection_pool (2.4.0)
     cube-ruby (0.0.3)
     dante (0.2.0)
     declarative (0.0.20)
@@ -115,8 +115,8 @@ GEM
     faraday-rack (1.0.0)
     faraday-retry (1.0.3)
     ffi (1.15.5)
-    google-apis-analytics_v3 (0.12.0)
-      google-apis-core (>= 0.9.1, < 2.a)
+    google-apis-analytics_v3 (0.13.0)
+      google-apis-core (>= 0.11.0, < 2.a)
     google-apis-core (0.11.0)
       addressable (~> 2.5, >= 2.5.1)
       googleauth (>= 0.16.2, < 2.a)
@@ -126,7 +126,7 @@ GEM
       retriable (>= 2.0, < 4.a)
       rexml
       webrick
-    googleauth (1.3.0)
+    googleauth (1.5.1)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)
@@ -155,7 +155,7 @@ GEM
     method_source (1.0.0)
     mime-types (3.4.1)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2022.0105)
+    mime-types-data (3.2023.0218.1)
     mini_mime (1.1.2)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
@@ -175,15 +175,15 @@ GEM
       coderay (~> 1.1)
       method_source (~> 1.0)
     public_suffix (5.0.1)
-    rack (3.0.4.1)
-    rack-test (2.0.2)
+    rack (3.0.7)
+    rack-test (2.1.0)
       rack (>= 1.3)
     rake (13.0.6)
     rdf (1.0.8)
       addressable (>= 2.2)
     redis (5.0.6)
       redis-client (>= 0.9.0)
-    redis-client (0.12.1)
+    redis-client (0.14.1)
       connection_pool
     representable (3.2.0)
       declarative (< 0.1.0)

From 873d8292309c0f74f0737934e5ac972e12d2793d Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Fri, 5 May 2023 13:37:48 -0700
Subject: [PATCH 22/62] exclude test/data/dictionary.txt from git commits

---
 .dockerignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.dockerignore b/.dockerignore
index 119eac79..96c8053c 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -12,5 +12,6 @@ tmp/*
 coverage
 create_permissions.log
 # Ignore generated test data
+test/data/dictionary.txt
 test/data/ontology_files/repo/**/*
 test/data/tmp/*

From 419c518adef378b335a595bb4ec762cf06063d7b Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Fri, 5 May 2023 13:39:14 -0700
Subject: [PATCH 23/62] update version of solr-ut

---
 docker-compose.yml | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/docker-compose.yml b/docker-compose.yml
index ca54bbce..009e33c2 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -28,8 +28,8 @@ x-app: &app
   volumes:
     # bundle volume for hosting gems installed by bundle; it helps in local development with gem udpates
     - bundle:/srv/ontoportal/bundle
-    # api code
-    - .:/srv/ontoportal/ontologies_api
+    # ncbo_cron code
+    - .:/srv/ontoportal/ncbo_cron
     # mount directory containing development version of the gems if you need to use 'bundle config local'
     #- /Users/alexskr/ontoportal:/Users/alexskr/ontoportal
   depends_on: &depends_on
@@ -85,6 +85,7 @@ services:
 
   4store-ut:
     image: bde2020/4store
+    platform: linux/amd64
     #volume: fourstore:/var/lib/4store
     command: >
       bash -c "4s-backend-setup --segments 4 ontoportal_kb
@@ -94,7 +95,7 @@ services:
       - 4store
 
   solr-ut:
-    image: ontoportal/solr-ut:0.1
+    image: ontoportal/solr-ut:0.0.2
     healthcheck:
       test: ["CMD-SHELL", "curl -sf http://localhost:8983/solr/term_search_core1/admin/ping?wt=json | grep -iq '\"status\":\"OK\"}' || exit 1"]
       start_period: 3s
@@ -104,6 +105,7 @@ services:
 
   mgrep-ut:
     image: ontoportal/mgrep:0.0.1
+    platform: linux/amd64
     healthcheck:
       test: ["CMD", "nc", "-z", "-v", "localhost", "55555"]
       start_period: 3s
@@ -113,6 +115,7 @@ services:
 
   agraph-ut:
     image: franzinc/agraph:v7.3.1
+    platform: linux/amd64
     environment:
       - AGRAPH_SUPER_USER=test
       - AGRAPH_SUPER_PASSWORD=xyzzy

From 94eed8de9a004a19fe178ef91ede50ec5f40fb8b Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Fri, 5 May 2023 13:40:58 -0700
Subject: [PATCH 24/62] Gemfile.lock update

---
 Gemfile.lock | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 72849d08..e17ffeaa 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: b8c7867450ec6ea2d3167eb9d9b1aed5614a1ce3
+  revision: fb203b0396d03c1df61abfcdbc4070787010f052
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 2ee3915af8aa96be7f5fce825c25c6291c8952e5
+  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
+  revision: 1f535313248f27170f7ecdb3450ae8247be735eb
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -126,7 +126,7 @@ GEM
       retriable (>= 2.0, < 4.a)
       rexml
       webrick
-    googleauth (1.5.1)
+    googleauth (1.5.2)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)
@@ -145,7 +145,7 @@ GEM
     jwt (2.7.0)
     launchy (2.5.2)
       addressable (~> 2.8)
-    libxml-ruby (4.0.0)
+    libxml-ruby (4.1.1)
     logger (1.5.3)
     macaddr (1.7.2)
       systemu (~> 2.6.5)
@@ -235,6 +235,7 @@ GEM
     webrick (1.8.1)
 
 PLATFORMS
+  ruby
   x86_64-darwin-18
   x86_64-darwin-21
   x86_64-linux

From 68dea929b9de90855b360f41b8d3a6d8c550c9c3 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Fri, 5 May 2023 14:08:03 -0700
Subject: [PATCH 25/62] Restore branch specifier to master

---
 Gemfile      |  8 ++++----
 Gemfile.lock | 18 +++++++++---------
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/Gemfile b/Gemfile
index aae5ab76..e2696023 100644
--- a/Gemfile
+++ b/Gemfile
@@ -20,10 +20,10 @@ gem 'sys-proctable'
 gem 'cube-ruby', require: 'cube'
 
 # NCBO
-gem 'goo', github: 'ncbo/goo', branch: 'develop'
-gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'develop'
-gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'develop'
-gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'develop'
+gem 'goo', github: 'ncbo/goo', branch: 'master'
+gem 'ncbo_annotator', github: 'ncbo/ncbo_annotator', branch: 'master'
+gem 'ontologies_linked_data', github: 'ncbo/ontologies_linked_data', branch: 'master'
+gem 'sparql-client', github: 'ncbo/sparql-client', branch: 'master'
 
 group :test do
   gem 'email_spec'
diff --git a/Gemfile.lock b/Gemfile.lock
index e17ffeaa..324c5a71 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: fb203b0396d03c1df61abfcdbc4070787010f052
-  branch: develop
+  revision: e8816b06244c26088ef0596ddc0623562a75a284
+  branch: master
   specs:
     goo (0.0.2)
       addressable (~> 2.8)
@@ -15,8 +15,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
-  branch: develop
+  revision: 964f0680799421ab24eddc974d9f2995c6c88734
+  branch: master
   specs:
     ncbo_annotator (0.0.1)
       goo
@@ -26,8 +26,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 1f535313248f27170f7ecdb3450ae8247be735eb
-  branch: develop
+  revision: d858e2e29e5da84c9741b7508efa235919642e46
+  branch: master
   specs:
     ontologies_linked_data (0.0.1)
       activesupport
@@ -46,8 +46,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/sparql-client.git
-  revision: 55e7dbf858eb571c767bc67868f9af61663859cb
-  branch: develop
+  revision: fb4a89b420f8eb6dda5190a126b6c62e32c4c0c9
+  branch: master
   specs:
     sparql-client (1.0.1)
       json_pure (>= 1.4)
@@ -267,4 +267,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.4.9

From 07a1d6540474e6d52d077173c7fcb71748da5aa9 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 9 May 2023 09:20:56 -0700
Subject: [PATCH 26/62] fixed configuration for the analytics module

---
 Gemfile.lock                              | 2 +-
 bin/ncbo_ontology_annotate_generate_cache | 2 +-
 lib/ncbo_cron/ontology_analytics.rb       | 7 ++++---
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 72849d08..761ee725 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 2ee3915af8aa96be7f5fce825c25c6291c8952e5
+  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
diff --git a/bin/ncbo_ontology_annotate_generate_cache b/bin/ncbo_ontology_annotate_generate_cache
index 07286e7c..18399bea 100755
--- a/bin/ncbo_ontology_annotate_generate_cache
+++ b/bin/ncbo_ontology_annotate_generate_cache
@@ -49,7 +49,7 @@ opt_parser = OptionParser.new do |opts|
     options[:generate_dictionary] = true
   end
 
-  options[:logfile] = "logs/annotator_cache.log"
+  options[:logfile] = STDOUT
   opts.on('-l', '--logfile FILE', "Write log to FILE (default is 'logs/annotator_cache.log').") do |filename|
     options[:logfile] = filename
   end
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
index e06fcd77..3e4076b4 100644
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ b/lib/ncbo_cron/ontology_analytics.rb
@@ -13,7 +13,7 @@ def initialize(logger)
       end
 
       def run
-        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
+        redis = Redis.new(:host => NcboCron.settings.ontology_analytics_redis_host, :port => NcboCron.settings.ontology_analytics_redis_port)
         ontology_analytics = fetch_ontology_analytics
         redis.set(ONTOLOGY_ANALYTICS_REDIS_FIELD, Marshal.dump(ontology_analytics))
       end
@@ -120,7 +120,8 @@ def authenticate_google
 # require 'ncbo_annotator'
 # require 'ncbo_cron/config'
 # require_relative '../../config/config'
-# ontology_analytics_log_path = File.join("logs", "ontology-analytics.log")
-# ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
+# # ontology_analytics_log_path = File.join("logs", "ontology-analytics.log")
+# # ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
+# ontology_analytics_logger = Logger.new(STDOUT)
 # NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
 # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'

From 8e11202c948fd413b4227e993ab838008ab49a33 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 9 May 2023 09:21:45 -0700
Subject: [PATCH 27/62] Gemfile.lock update

---
 Gemfile.lock | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index e17ffeaa..c0ec0478 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: fb203b0396d03c1df61abfcdbc4070787010f052
+  revision: b8c7867450ec6ea2d3167eb9d9b1aed5614a1ce3
   branch: develop
   specs:
     goo (0.0.2)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 1f535313248f27170f7ecdb3450ae8247be735eb
+  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)

From 0b9b785320242f727e7222b0632145fcc4584ddf Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 22 Jun 2023 15:44:08 -0700
Subject: [PATCH 28/62] implemented #69 - scheduled annotator dictionary file
 generation should be a configurable option instead of the default

---
 Gemfile.lock                                |  2 +-
 bin/ncbo_cron                               | 71 ++++-----------------
 lib/ncbo_cron/config.rb                     | 20 +-----
 lib/ncbo_cron/ontology_submission_parser.rb |  7 +-
 4 files changed, 19 insertions(+), 81 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index c0ec0478..fad566d7 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: b8c7867450ec6ea2d3167eb9d9b1aed5614a1ce3
+  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
   branch: develop
   specs:
     goo (0.0.2)
diff --git a/bin/ncbo_cron b/bin/ncbo_cron
index 8d212382..3b7aa063 100755
--- a/bin/ncbo_cron
+++ b/bin/ncbo_cron
@@ -111,19 +111,9 @@ opt_parser = OptionParser.new do |opts|
   opts.on("--disable-update-check", "disable check for updated version of Ontoportal (for VMs)", "(default: #{options[:enable_update_check]})") do |v|
     options[:enable_update_check] = false
   end
-
-
-
-
-  opts.on("--disable-dictionary-generation", "disable mgrep dictionary generation job", "(default: #{options[:enable_dictionary_generation]})") do |v|
-    options[:enable_dictionary_generation] = false
+  opts.on("--enable-dictionary-generation-cron-job", "ENABLE mgrep dictionary generation JOB and DISABLE dictionary generation during ontology processing. If this is not passed in, dictionary is generated every time an ontology is processed.", "(default: Dictionary is generated on every ontology processing, CRON job is DISABLED)") do |v|
+    options[:enable_dictionary_generation_cron_job] = true
   end
-
-
-
-
-
-
   opts.on("--disable-obofoundry_sync", "disable OBO Foundry synchronization report", "(default: #{options[:enable_obofoundry_sync]})") do |v|
     options[:enable_obofoundry_sync] = false
   end
@@ -160,18 +150,10 @@ opt_parser = OptionParser.new do |opts|
   opts.on("--obofoundry_sync SCHED", String, "cron schedule to run OBO Foundry synchronization report", "(default: #{options[:cron_obofoundry_sync]})") do |c|
     options[:cron_obofoundry_sync] = c
   end
-
-
-
-
-  opts.on("--dictionary-generation SCHED", String, "cron schedule to run mgrep dictionary generation job", "(default: #{options[:cron_dictionary_generation]})") do |c|
-    options[:cron_dictionary_generation] = c
+  opts.on("--dictionary-generation-cron-job SCHED", String, "cron schedule to run mgrep dictionary generation job (if enabled)", "(default: #{options[:cron_dictionary_generation_cron_job]})") do |c|
+    options[:cron_dictionary_generation_cron_job] = c
   end
 
-
-
-
-
   # Display the help screen, all programs are assumed to have this option.
   opts.on_tail('--help', 'Display this screen') do
     puts opts
@@ -484,49 +466,27 @@ runner.execute do |opts|
     end
   end
 
-
-
-
-
-
-
-
-  # temporary job to generate mgrep dictionary file
+  # optional job to generate mgrep dictionary file
   # separate from ontology processing due to
   # https://github.com/ncbo/ncbo_cron/issues/45
-
-  if options[:enable_dictionary_generation]
+  if options[:enable_dictionary_generation_cron_job]
     dictionary_generation_thread = Thread.new do
       dictionary_generation_options = options.dup
-      dictionary_generation_options[:job_name] = "ncbo_cron_dictionary_generation"
+      dictionary_generation_options[:job_name] = "ncbo_cron_dictionary_generation_cron_job"
       dictionary_generation_options[:scheduler_type] = :cron
-      dictionary_generation_options[:cron_schedule] = dictionary_generation_options[:cron_dictionary_generation]
-      logger.info "Setting up mgrep dictionary generation job with #{dictionary_generation_options[:cron_dictionary_generation]}"; logger.flush
+      dictionary_generation_options[:cron_schedule] = dictionary_generation_options[:cron_dictionary_generation_cron_job]
+      logger.info "Setting up mgrep dictionary generation job with #{dictionary_generation_options[:cron_dictionary_generation_cron_job]}"; logger.flush
       NcboCron::Scheduler.scheduled_locking_job(dictionary_generation_options) do
-        logger.info "Starting mgrep dictionary generation..."; logger.flush
+        logger.info "Starting mgrep dictionary generation CRON job..."; logger.flush
         t0 = Time.now
         annotator = Annotator::Models::NcboAnnotator.new
         annotator.generate_dictionary_file()
-        logger.info "mgrep dictionary generation job completed in #{Time.now - t0} sec."; logger.flush
-        logger.info "Finished mgrep dictionary generation"; logger.flush
+        logger.info "mgrep dictionary generation CRON job completed in #{Time.now - t0} sec."; logger.flush
+        logger.info "Finished mgrep dictionary generation CRON job"; logger.flush
       end
     end
   end
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
   # Print running child processes
   require 'sys/proctable'
   at_exit do
@@ -549,12 +509,5 @@ runner.execute do |opts|
   mapping_counts_thread.join if mapping_counts_thread
   update_check_thread.join if update_check_thread
   obofoundry_sync_thread.join if obofoundry_sync_thread
-
-
-
-
   dictionary_generation_thread.join if dictionary_generation_thread
-
-
-
 end
diff --git a/lib/ncbo_cron/config.rb b/lib/ncbo_cron/config.rb
index 49db0fb4..6d3db51e 100644
--- a/lib/ncbo_cron/config.rb
+++ b/lib/ncbo_cron/config.rb
@@ -40,16 +40,8 @@ def config(&block)
     @settings.enable_spam_deletion ||= true
     # enable update check (vor VMs)
     @settings.enable_update_check ||= true
-
-
-
-
     # enable mgrep dictionary generation job
-    @settings.enable_dictionary_generation ||= true
-
-
-
-
+    @settings.enable_dictionary_generation_cron_job ||= false
 
     # UMLS auto-pull
     @settings.pull_umls_url ||= ""
@@ -85,17 +77,9 @@ def config(&block)
     @settings.cron_obofoundry_sync ||= "0 8 * * 1,2,3,4,5"
     # 00 3 * * * - run daily at 3:00AM
     @settings.cron_update_check ||= "00 3 * * *"
-
-
-
-
     # mgrep dictionary generation schedule
     # 30 3 * * * - run daily at 3:30AM
-    @settings.cron_dictionary_generation ||= "30 3 * * *"
-
-
-
-
+    @settings.cron_dictionary_generation_cron_job ||= "30 3 * * *"
 
     @settings.log_level ||= :info
     unless (@settings.log_path && File.exists?(@settings.log_path))
diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index a6512312..34c53930 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -220,10 +220,11 @@ def process_annotator(logger, sub)
           begin
             annotator = Annotator::Models::NcboAnnotator.new
             annotator.create_term_cache_for_submission(logger, sub)
-            # commenting this action out for now due to a problem with hgetall in redis
+            # this action only occurs if the CRON dictionary generation job is disabled
+            # if the CRON dictionary generation job is running,
+            # the dictionary will NOT be generated on each ontology parsing
             # see https://github.com/ncbo/ncbo_cron/issues/45 for details
-            # mgrep dictionary generation will occur as a separate CRON task
-            # annotator.generate_dictionary_file()
+            annotator.generate_dictionary_file() unless NcboCron.settings.enable_dictionary_generation_cron_job
           rescue Exception => e
             logger.error(e.message + "\n" + e.backtrace.join("\n\t"))
             logger.flush()

From 139494e7d02e3d9d808a7f9f302b5499f8a65c60 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 22 Jun 2023 15:44:53 -0700
Subject: [PATCH 29/62] Gemfile.lock update

---
 Gemfile.lock | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index fad566d7..e8cc5d80 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -76,11 +76,11 @@ GEM
       multi_json (~> 1.0)
     addressable (2.8.4)
       public_suffix (>= 2.0.2, < 6.0)
-    bcrypt (3.1.18)
+    bcrypt (3.1.19)
     builder (3.2.4)
     coderay (1.1.3)
     concurrent-ruby (1.2.2)
-    connection_pool (2.4.0)
+    connection_pool (2.4.1)
     cube-ruby (0.0.3)
     dante (0.2.0)
     declarative (0.0.20)
@@ -142,7 +142,7 @@ GEM
       concurrent-ruby (~> 1.0)
     json (2.6.3)
     json_pure (2.6.3)
-    jwt (2.7.0)
+    jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
     libxml-ruby (4.1.1)
@@ -175,7 +175,7 @@ GEM
       coderay (~> 1.1)
       method_source (~> 1.0)
     public_suffix (5.0.1)
-    rack (3.0.7)
+    rack (3.0.8)
     rack-test (2.1.0)
       rack (>= 1.3)
     rake (13.0.6)

From 23794ff32f7e36aa7be09707e5d2031a9c2082af Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Fri, 23 Jun 2023 13:46:23 -0700
Subject: [PATCH 30/62] gem update

---
 Gemfile.lock | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index e8cc5d80..44c33f1b 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
+  revision: fb203b0396d03c1df61abfcdbc4070787010f052
   branch: develop
   specs:
     goo (0.0.2)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
+  revision: 1f535313248f27170f7ecdb3450ae8247be735eb
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -126,7 +126,7 @@ GEM
       retriable (>= 2.0, < 4.a)
       rexml
       webrick
-    googleauth (1.5.2)
+    googleauth (1.6.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)

From 44dec8c31a66ac360e02f295dc6eccd68e3a112a Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Mon, 10 Jul 2023 11:23:35 -0700
Subject: [PATCH 31/62] create new rake taks for updating purls for all
 ontologies

moved from ontologies_api/fix_purls.rb
---
 rakelib/purl_management.rake | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 rakelib/purl_management.rake

diff --git a/rakelib/purl_management.rake b/rakelib/purl_management.rake
new file mode 100644
index 00000000..58cfadd7
--- /dev/null
+++ b/rakelib/purl_management.rake
@@ -0,0 +1,28 @@
+# Task for updating and adding missing purl for all ontologies
+#
+desc 'Purl Utilities'
+namespace :purl do
+  require 'bundler/setup'
+  # Configure the process for the current cron configuration.
+  require_relative '../lib/ncbo_cron'
+  config_exists = File.exist?(File.expand_path('../../config/config.rb', __FILE__))
+  abort('Please create a config/config.rb file using the config/config.rb.sample as a template') unless config_exists
+  require_relative '../config/config'
+
+  desc 'update purl for all ontologies'
+  task :update_all do
+    purl_client = LinkedData::Purl::Client.new
+    LinkedData::Models::Ontology.all.each do |ont|
+      ont.bring(:acronym)
+      acronym = ont.acronym
+
+      if purl_client.purl_exists(acronym)
+        puts "#{acronym} exists"
+        purl_client.fix_purl(acronym)
+      else
+        puts "#{acronym} DOES NOT exist"
+        purl_client.create_purl(acronym)
+      end
+    end
+  end
+end

From f5399c5b4e4df4ff6033460ebea231cbb1ed23ee Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 12 Jul 2023 17:32:08 -0700
Subject: [PATCH 32/62] initial implementation of #70 - Google Analytics v4
 Update Compatibility Issue

---
 .gitignore                          |   1 +
 Gemfile                             |   2 +-
 Gemfile.lock                        |  58 ++++---
 config/config.rb.sample             |  16 +-
 lib/ncbo_cron/ontology_analytics.rb | 259 +++++++++++++++++++---------
 ncbo_cron.gemspec                   |   2 +-
 6 files changed, 222 insertions(+), 116 deletions(-)

diff --git a/.gitignore b/.gitignore
index 9170162c..f9401dc1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -3,6 +3,7 @@
 config/config.rb
 config/config_*.rb
 config/*.p12
+config/*.json
 projectFilesBackup/
 .ruby-version
 repo*
diff --git a/Gemfile b/Gemfile
index aae5ab76..d680bef0 100644
--- a/Gemfile
+++ b/Gemfile
@@ -4,7 +4,7 @@ gemspec
 
 gem 'faraday', '~> 1.9'
 gem 'ffi'
-gem "google-apis-analytics_v3"
+gem 'google-analytics-data'
 gem 'mail', '2.6.6'
 gem 'multi_json'
 gem 'oj', '~> 2.0'
diff --git a/Gemfile.lock b/Gemfile.lock
index e8cc5d80..514e3b0c 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -60,7 +60,7 @@ PATH
     ncbo_cron (0.0.1)
       dante
       goo
-      google-apis-analytics_v3
+      google-analytics-data
       mlanett-redis-lock
       multi_json
       ncbo_annotator
@@ -83,7 +83,6 @@ GEM
     connection_pool (2.4.1)
     cube-ruby (0.0.3)
     dante (0.2.0)
-    declarative (0.0.20)
     docile (1.4.0)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
@@ -115,29 +114,47 @@ GEM
     faraday-rack (1.0.0)
     faraday-retry (1.0.3)
     ffi (1.15.5)
-    google-apis-analytics_v3 (0.13.0)
-      google-apis-core (>= 0.11.0, < 2.a)
-    google-apis-core (0.11.0)
-      addressable (~> 2.5, >= 2.5.1)
-      googleauth (>= 0.16.2, < 2.a)
-      httpclient (>= 2.8.1, < 3.a)
-      mini_mime (~> 1.0)
-      representable (~> 3.0)
-      retriable (>= 2.0, < 4.a)
-      rexml
-      webrick
-    googleauth (1.5.2)
+    gapic-common (0.19.1)
+      faraday (>= 1.9, < 3.a)
+      faraday-retry (>= 1.0, < 3.a)
+      google-protobuf (~> 3.14)
+      googleapis-common-protos (>= 1.3.12, < 2.a)
+      googleapis-common-protos-types (>= 1.3.1, < 2.a)
+      googleauth (~> 1.0)
+      grpc (~> 1.36)
+    google-analytics-data (0.4.0)
+      google-analytics-data-v1beta (>= 0.7, < 2.a)
+      google-cloud-core (~> 1.6)
+    google-analytics-data-v1beta (0.8.0)
+      gapic-common (>= 0.19.1, < 2.a)
+      google-cloud-errors (~> 1.0)
+    google-cloud-core (1.6.0)
+      google-cloud-env (~> 1.0)
+      google-cloud-errors (~> 1.0)
+    google-cloud-env (1.6.0)
+      faraday (>= 0.17.3, < 3.0)
+    google-cloud-errors (1.3.1)
+    google-protobuf (3.23.4-x86_64-darwin)
+    googleapis-common-protos (1.4.0)
+      google-protobuf (~> 3.14)
+      googleapis-common-protos-types (~> 1.2)
+      grpc (~> 1.27)
+    googleapis-common-protos-types (1.6.0)
+      google-protobuf (~> 3.14)
+    googleauth (1.6.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
+    grpc (1.56.0-x86_64-darwin)
+      google-protobuf (~> 3.23)
+      googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
     http-cookie (1.0.5)
       domain_name (~> 0.5)
-    httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
     json (2.6.3)
@@ -156,7 +173,6 @@ GEM
     mime-types (3.4.1)
       mime-types-data (~> 3.2015)
     mime-types-data (3.2023.0218.1)
-    mini_mime (1.1.2)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
       redis
@@ -185,16 +201,11 @@ GEM
       redis-client (>= 0.9.0)
     redis-client (0.14.1)
       connection_pool
-    representable (3.2.0)
-      declarative (< 0.1.0)
-      trailblazer-option (>= 0.1.1, < 0.2.0)
-      uber (< 0.2.0)
     rest-client (2.1.0)
       http-accept (>= 1.7.0, < 2.0)
       http-cookie (>= 1.0.2, < 2.0)
       mime-types (>= 1.16, < 4.0)
       netrc (~> 0.8)
-    retriable (3.1.2)
     rexml (3.2.5)
     rsolr (2.5.0)
       builder (>= 2.1.2)
@@ -223,16 +234,13 @@ GEM
     systemu (2.6.5)
     test-unit-minitest (0.9.1)
       minitest (~> 4.7)
-    trailblazer-option (0.1.2)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
-    uber (0.1.0)
     unf (0.1.4)
       unf_ext
     unf_ext (0.0.8.2)
     uuid (2.3.9)
       macaddr (~> 1.0)
-    webrick (1.8.1)
 
 PLATFORMS
   ruby
@@ -246,7 +254,7 @@ DEPENDENCIES
   faraday (~> 1.9)
   ffi
   goo!
-  google-apis-analytics_v3
+  google-analytics-data
   mail (= 2.6.6)
   minitest (< 5.0)
   multi_json
diff --git a/config/config.rb.sample b/config/config.rb.sample
index 8d204311..668c7a0c 100644
--- a/config/config.rb.sample
+++ b/config/config.rb.sample
@@ -69,14 +69,14 @@ NcboCron.config do |config|
   config.search_index_all_url = "http://localhost:8983/solr/term_search_core2"
   config.property_search_index_all_url = "http://localhost:8983/solr/prop_search_core2"
 
-  # Google Analytics config
-  config.analytics_service_account_email_address = "123456789999-sikipho0wk8q0atflrmw62dj4kpwoj3c@developer.gserviceaccount.com"
-  config.analytics_path_to_key_file              = "config/bioportal-analytics.p12"
-  config.analytics_profile_id                    = "ga:1234567"
-  config.analytics_app_name                      = "BioPortal"
-  config.analytics_app_version                   = "1.0.0"
-  config.analytics_start_date                    = "2013-10-01"
-  config.analytics_filter_str                    = "ga:networkLocation!@stanford;ga:networkLocation!@amazon"
+  # Google Analytics GA4 config
+  config.analytics_path_to_key_file     = "config/your_analytics_key.json"
+  config.analytics_property_id          = "123456789"
+  # path to the Universal Analytics data, which stopped collecting on June 1st, 2023
+  config.analytics_path_to_ua_data_file = "data/your_ua_data.json"
+  # path to the file that will hold your Google Analytics data
+  # this is in addition to storing it in Redis
+  config.analytics_path_to_ga_data_file = "data/your_ga_data.json"
 
   # this is a Base64.encode64 encoded personal access token
   # you need to run Base64.decode64 on it before using it in your code
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
index 3e4076b4..334da43e 100644
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ b/lib/ncbo_cron/ontology_analytics.rb
@@ -1,12 +1,16 @@
 require 'logger'
-require 'google/apis/analytics_v3'
-require 'google/api_client/auth/key_utils'
+require 'json'
+require 'benchmark'
+require 'google/analytics/data'
+
 
 module NcboCron
   module Models
 
     class OntologyAnalytics
-      ONTOLOGY_ANALYTICS_REDIS_FIELD = "ontology_analytics"
+      ONTOLOGY_ANALYTICS_REDIS_FIELD = 'ontology_analytics'
+      UA_START_DATE = '2013-10-01'
+      GA4_START_DATE = '2023-06-01'
 
       def initialize(logger)
         @logger = logger
@@ -15,103 +19,196 @@ def initialize(logger)
       def run
         redis = Redis.new(:host => NcboCron.settings.ontology_analytics_redis_host, :port => NcboCron.settings.ontology_analytics_redis_port)
         ontology_analytics = fetch_ontology_analytics
+        File.open(NcboCron.settings.analytics_path_to_ga_data_file, 'w') do |f|
+          f.write(ontology_analytics.to_json)
+        end
         redis.set(ONTOLOGY_ANALYTICS_REDIS_FIELD, Marshal.dump(ontology_analytics))
       end
 
       def fetch_ontology_analytics
-        google_client = authenticate_google
-        aggregated_results = Hash.new
-        start_year = Date.parse(NcboCron.settings.analytics_start_date).year || 2013
-        ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
-        # ont_acronyms = ["NCIT", "ONTOMA", "CMPO", "AEO", "SNOMEDCT"]
-        filter_str = (NcboCron.settings.analytics_filter_str.nil? || NcboCron.settings.analytics_filter_str.empty?) ? "" : ";#{NcboCron.settings.analytics_filter_str}"
-
-        ont_acronyms.each do |acronym|
+        @logger.info "Starting Google Analytics refresh..."
+        @logger.flush
+        full_data = nil
+
+        time = Benchmark.realtime do
           max_results = 10000
-          num_results = 10000
-          start_index = 1
-          results = nil
-
-          loop do
-            results = google_client.get_ga_data(
-              ids          = NcboCron.settings.analytics_profile_id,
-              start_date   = NcboCron.settings.analytics_start_date,
-              end_date     = Date.today.to_s,
-              metrics      = 'ga:pageviews',
-              {
-                dimensions:  'ga:pagePath,ga:year,ga:month',
-                filters:     "ga:pagePath=~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}",
-                start_index: start_index,
-                max_results: max_results
-              }
-            )
-            results.rows ||= []
-            start_index += max_results
-            num_results = results.rows.length
-            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
-            @logger.flush
-
-            results.rows.each do |row|
-              if aggregated_results.has_key?(acronym)
-                # year
-                if aggregated_results[acronym].has_key?(row[1].to_i)
-                  # month
-                  if aggregated_results[acronym][row[1].to_i].has_key?(row[2].to_i)
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] += row[3].to_i
+          aggregated_results = Hash.new
+
+          @logger.info "Fetching all ontology acronyms from backend..."
+          @logger.flush
+          ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
+          # ont_acronyms = ["NCIT", "SNOMEDCT", "MEDDRA"]
+
+          @logger.info "Authenticating with the Google Analytics Endpoint..."
+          @logger.flush
+          google_client = authenticate_google
+
+          date_range = Google::Analytics::Data::V1beta::DateRange.new(
+            start_date: GA4_START_DATE,
+            end_date: Date.today.to_s
+          )
+          metrics_page_views = Google::Analytics::Data::V1beta::Metric.new(
+            name: "screenPageViews"
+          )
+          dimension_path = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "pagePath"
+          )
+          dimension_year = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "year"
+          )
+          dimension_month = Google::Analytics::Data::V1beta::Dimension.new(
+            name: "month"
+          )
+          string_filter = Google::Analytics::Data::V1beta::Filter::StringFilter.new(
+            match_type: Google::Analytics::Data::V1beta::Filter::StringFilter::MatchType::FULL_REGEXP
+          )
+          filter = Google::Analytics::Data::V1beta::Filter.new(
+            field_name: "pagePath",
+            string_filter: string_filter
+          )
+          filter_expression = Google::Analytics::Data::V1beta::FilterExpression.new(
+            filter: filter
+          )
+          order_year = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
+            dimension_name: "year"
+          )
+          orderby_year = Google::Analytics::Data::V1beta::OrderBy.new(
+            desc: false,
+            dimension: order_year
+          )
+          order_month = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
+            dimension_name: "month"
+          )
+          orderby_month = Google::Analytics::Data::V1beta::OrderBy.new(
+            desc: false,
+            dimension: order_month
+          )
+          @logger.info "Fetching GA4 analytics for all ontologies..."
+          @logger.flush
+
+          ont_acronyms.each do |acronym|
+            start_index = 0
+            string_filter.value = "^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$"
+
+            loop do
+              request = Google::Analytics::Data::V1beta::RunReportRequest.new(
+                property: "properties/#{NcboCron.settings.analytics_property_id}",
+                metrics: [metrics_page_views],
+                dimension_filter: filter_expression,
+                dimensions: [dimension_path, dimension_year, dimension_month],
+                date_ranges: [date_range],
+                order_bys: [orderby_year, orderby_month],
+                offset: start_index,
+                limit: max_results
+              )
+              response = google_client.run_report request
+
+              response.rows ||= []
+              start_index += max_results
+              num_results = response.rows.length
+              @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+              @logger.flush
+
+              response.rows.each do |row|
+                row_h = row.to_h
+                year_month_hits =  row_h[:dimension_values].map.with_index {
+                  |v, i| i > 0 ? v[:value].to_i.to_s : row_h[:metric_values][0][:value].to_i
+                }.rotate(1)
+
+                if aggregated_results.has_key?(acronym)
+                  # year
+                  if aggregated_results[acronym].has_key?(year_month_hits[0])
+                    # month
+                    if aggregated_results[acronym][year_month_hits[0]].has_key?(year_month_hits[1])
+                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] += year_month_hits[2]
+                    else
+                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
+                    end
                   else
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                    aggregated_results[acronym][year_month_hits[0]] = Hash.new
+                    aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
                   end
                 else
-                  aggregated_results[acronym][row[1].to_i] = Hash.new
-                  aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                  aggregated_results[acronym] = Hash.new
+                  aggregated_results[acronym][year_month_hits[0]] = Hash.new
+                  aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
                 end
-              else
-                aggregated_results[acronym] = Hash.new
-                aggregated_results[acronym][row[1].to_i] = Hash.new
-                aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
               end
-            end
+              break if num_results < max_results
+            end # loop
+          end # ont_acronyms
+          @logger.info "Refresh complete, merging GA4 and UA data..."
+          @logger.flush
+          full_data = merge_ga4_ua_data(aggregated_results)
+          @logger.info "Merged"
+          @logger.flush
+        end # Benchmark.realtime
+        @logger.info "Completed Google Analytics refresh in #{(time/60).round(1)} minutes."
+        @logger.flush
+        full_data
+      end
 
-            if num_results < max_results
-              # fill up non existent years
-              (start_year..Date.today.year).each do |y|
-                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
-                aggregated_results[acronym][y] = Hash.new unless aggregated_results[acronym].has_key?(y)
-              end
-              # fill up non existent months with zeros
-              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n] = 0 unless v.has_key?(n) } }
-              break
+      def merge_ga4_ua_data(ga4_data)
+        ua_data_file = File.read(NcboCron.settings.analytics_path_to_ua_data_file)
+        ua_data = JSON.parse(ua_data_file)
+        ua_ga4_intersecting_year = Date.parse(GA4_START_DATE).year.to_s
+        ua_ga4_intersecting_month = Date.parse(GA4_START_DATE).month.to_s
+
+        # add up hits for June of 2023 (the only intersecting month between UA and GA4)
+        ua_data.each do |acronym, _|
+          if ga4_data.has_key?(acronym)
+            if ga4_data[acronym][ua_ga4_intersecting_year].has_key?(ua_ga4_intersecting_month)
+              ua_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month] +=
+                  ga4_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month]
+              # delete data for June of 2023 from ga4_data to avoid overwriting when merging
+              ga4_data[acronym][ua_ga4_intersecting_year].delete(ua_ga4_intersecting_month)
             end
           end
         end
+        # merge ua and ga4 data
+        merged_data = ua_data.deep_merge(ga4_data)
+        # fill missing years and months
+        fill_missing_data(merged_data)
+        # sort acronyms, years and months
+        sort_ga_data(merged_data)
+      end
 
-        @logger.info "Completed ontology analytics refresh..."
-        @logger.flush
+      def fill_missing_data(ga_data)
+        # fill up non existent years
+        start_year = Date.parse(UA_START_DATE).year
+
+        ga_data.each do |acronym, _|
+          (start_year..Date.today.year).each do |y|
+            ga_data[acronym] = Hash.new if ga_data[acronym].nil?
+            ga_data[acronym][y.to_s] = Hash.new unless ga_data[acronym].has_key?(y.to_s)
+          end
+          # fill up non existent months with zeros
+          (1..12).each { |n| ga_data[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+        end
+      end
 
-        aggregated_results
+      def sort_ga_data(ga_data)
+        ga_data.transform_values { |value|
+          value.transform_values { |val|
+            val.sort_by { |key, _| key.to_i }.to_h
+          }.sort_by { |k, _| k.to_i }.to_h
+        }.sort.to_h
       end
 
       def authenticate_google
-        Google::Apis::ClientOptions.default.application_name = NcboCron.settings.analytics_app_name
-        Google::Apis::ClientOptions.default.application_version = NcboCron.settings.analytics_app_version
-        # enable google api call retries in order to
-        # minigate analytics processing failure due to ocasional google api timeouts and other outages
-        Google::Apis::RequestOptions.default.retries = 5
-        # uncoment to enable logging for debugging purposes
-        # Google::Apis.logger.level = Logger::DEBUG
-        # Google::Apis.logger = @logger
-        client = Google::Apis::AnalyticsV3::AnalyticsService.new
-        key = Google::APIClient::KeyUtils::load_from_pkcs12(NcboCron.settings.analytics_path_to_key_file, 'notasecret')
-        client.authorization = Signet::OAuth2::Client.new(
-            :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
-            :audience             => 'https://accounts.google.com/o/oauth2/token',
-            :scope                => 'https://www.googleapis.com/auth/analytics.readonly',
-            :issuer               => NcboCron.settings.analytics_service_account_email_address,
-            :signing_key          => key
-        ).tap { |auth| auth.fetch_access_token! }
-        client
+        Google::Analytics::Data.analytics_data do |config|
+          config.credentials = NcboCron.settings.analytics_path_to_key_file
+        end
       end
-    end
+    end # class
+
+  end
+end
+
+class ::Hash
+  def deep_merge(second)
+    merger = proc { |key, v1, v2| Hash === v1 && Hash === v2 ? v1.merge(v2, &merger) : v2 }
+    self.merge(second, &merger)
   end
 end
 
@@ -124,4 +221,4 @@ def authenticate_google
 # # ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
 # ontology_analytics_logger = Logger.new(STDOUT)
 # NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
-# ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'
+# # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'
diff --git a/ncbo_cron.gemspec b/ncbo_cron.gemspec
index ef21761f..c8faa03d 100644
--- a/ncbo_cron.gemspec
+++ b/ncbo_cron.gemspec
@@ -16,7 +16,7 @@ Gem::Specification.new do |gem|
 
   gem.add_dependency("dante")
   gem.add_dependency("goo")
-  gem.add_dependency("google-apis-analytics_v3")
+  gem.add_dependency("google-analytics-data")
   gem.add_dependency("mlanett-redis-lock")
   gem.add_dependency("multi_json")
   gem.add_dependency("ncbo_annotator")

From 6bb0c23ed9b116c458fdfda6017011698c66d587 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 13 Jul 2023 08:59:11 -0700
Subject: [PATCH 33/62] added the /data folder to ignore

---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitignore b/.gitignore
index f9401dc1..ccf97ea0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,6 +4,7 @@ config/config.rb
 config/config_*.rb
 config/*.p12
 config/*.json
+data/
 projectFilesBackup/
 .ruby-version
 repo*

From 8c8ddb6c7f9f1d2584a5fb3220f1d2aa37b66cb2 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Thu, 20 Jul 2023 14:16:42 -0700
Subject: [PATCH 34/62] update gems

---
 Gemfile.lock | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index b00ea5d6..b495b471 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
+  revision: fb203b0396d03c1df61abfcdbc4070787010f052
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
+  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
+  revision: 13bb138aa40ca72bfafc91a1a7416c162ba8d325
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -141,22 +141,22 @@ GEM
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.6.0)
+    googleapis-common-protos-types (1.7.0)
       google-protobuf (~> 3.14)
-    googleauth (1.6.0)
+    googleauth (1.7.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.56.0)
+    grpc (1.56.2)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.0-x86_64-darwin)
+    grpc (1.56.2-x86_64-darwin)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.0-x86_64-linux)
+    grpc (1.56.2-x86_64-linux)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
@@ -283,4 +283,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.4.17

From dad8832e5f650bb06ae9dd0ff7ce1cc285d34cfa Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 26 Jul 2023 15:20:43 -0700
Subject: [PATCH 35/62] Gemfile.lock update

---
 Gemfile.lock | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index b00ea5d6..6922cbd9 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 79527b94fbb59081ba58281a5cd51ec3448fadb0
+  revision: 13bb138aa40ca72bfafc91a1a7416c162ba8d325
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -141,22 +141,22 @@ GEM
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.6.0)
+    googleapis-common-protos-types (1.7.0)
       google-protobuf (~> 3.14)
-    googleauth (1.6.0)
+    googleauth (1.7.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       memoist (~> 0.16)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.56.0)
+    grpc (1.56.2)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.0-x86_64-darwin)
+    grpc (1.56.2-x86_64-darwin)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.0-x86_64-linux)
+    grpc (1.56.2-x86_64-linux)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)

From 29dc7618a672c42f1476304a3cde8115acc83236 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 26 Jul 2023 15:21:31 -0700
Subject: [PATCH 36/62] Gemfile.lock update

---
 Gemfile.lock | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index b495b471..6922cbd9 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: fb203b0396d03c1df61abfcdbc4070787010f052
+  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
+  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -283,4 +283,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.4.17
+   2.3.15

From 758f199d1536b40c0725bf44f2db0151b14305c7 Mon Sep 17 00:00:00 2001
From: Jennifer Vendetti <vendetti@stanford.edu>
Date: Mon, 31 Jul 2023 15:08:06 -0700
Subject: [PATCH 37/62] Gemfile.lock update

---
 Gemfile.lock | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 6922cbd9..e5e8fcab 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
+  revision: 8e80a4f842331e874055aec6a507ca5e3be4e3a4
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
+  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 13bb138aa40ca72bfafc91a1a7416c162ba8d325
+  revision: afda3aacfdd0e5e33e5e5beae1dffd79d4980a30
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -214,7 +214,7 @@ GEM
       http-cookie (>= 1.0.2, < 2.0)
       mime-types (>= 1.16, < 4.0)
       netrc (~> 0.8)
-    rexml (3.2.5)
+    rexml (3.2.6)
     rsolr (2.5.0)
       builder (>= 2.1.2)
       faraday (>= 0.9, < 3, != 2.0.0)
@@ -283,4 +283,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.3.26

From 5e6a8f4c69470fc0155a8149c3dbf281b1e679d2 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Mon, 31 Jul 2023 21:59:17 -0700
Subject: [PATCH 38/62] use patched version of agraph v7.3.1

---
 .github/workflows/ruby-unit-tests.yml | 1 +
 Gemfile.lock                          | 4 ++--
 docker-compose.yml                    | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/ruby-unit-tests.yml b/.github/workflows/ruby-unit-tests.yml
index 5f0db7e1..b61ce745 100644
--- a/.github/workflows/ruby-unit-tests.yml
+++ b/.github/workflows/ruby-unit-tests.yml
@@ -7,6 +7,7 @@ on:
 jobs:
   test:
     strategy:
+      fail-fast: false
       matrix:
         backend: ['ncbo_cron', 'ncbo_cron-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
     runs-on: ubuntu-latest
diff --git a/Gemfile.lock b/Gemfile.lock
index e5e8fcab..04ed607b 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: afda3aacfdd0e5e33e5e5beae1dffd79d4980a30
+  revision: df675c44c81332a0f894b86338561b51c7f721b7
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -283,4 +283,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.26
+   2.4.17
diff --git a/docker-compose.yml b/docker-compose.yml
index 009e33c2..0045ce12 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -114,7 +114,8 @@ services:
       retries: 5
 
   agraph-ut:
-    image: franzinc/agraph:v7.3.1
+    #image: franzinc/agraph:v7.3.1
+    image: ontoportal/agraph:v7.3.1-patch1
     platform: linux/amd64
     environment:
       - AGRAPH_SUPER_USER=test

From 1f81bdba54351e990047cbd6d1294c96ff0a8c6c Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Mon, 31 Jul 2023 22:11:47 -0700
Subject: [PATCH 39/62] unpin faraday gem

---
 Gemfile      |  3 +--
 Gemfile.lock | 33 +++++++--------------------------
 2 files changed, 8 insertions(+), 28 deletions(-)

diff --git a/Gemfile b/Gemfile
index d680bef0..a2c93e43 100644
--- a/Gemfile
+++ b/Gemfile
@@ -2,12 +2,11 @@ source 'https://rubygems.org'
 
 gemspec
 
-gem 'faraday', '~> 1.9'
 gem 'ffi'
 gem 'google-analytics-data'
 gem 'mail', '2.6.6'
 gem 'multi_json'
-gem 'oj', '~> 2.0'
+gem 'oj', '~> 3.0'
 gem 'parseconfig'
 gem 'pony'
 gem 'pry'
diff --git a/Gemfile.lock b/Gemfile.lock
index 04ed607b..b1921b85 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -90,29 +90,12 @@ GEM
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (1.10.3)
-      faraday-em_http (~> 1.0)
-      faraday-em_synchrony (~> 1.0)
-      faraday-excon (~> 1.1)
-      faraday-httpclient (~> 1.0)
-      faraday-multipart (~> 1.0)
-      faraday-net_http (~> 1.0)
-      faraday-net_http_persistent (~> 1.0)
-      faraday-patron (~> 1.0)
-      faraday-rack (~> 1.0)
-      faraday-retry (~> 1.0)
+    faraday (2.7.10)
+      faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
-    faraday-em_http (1.0.0)
-    faraday-em_synchrony (1.0.0)
-    faraday-excon (1.1.0)
-    faraday-httpclient (1.0.1)
-    faraday-multipart (1.0.4)
-      multipart-post (~> 2)
-    faraday-net_http (1.0.1)
-    faraday-net_http_persistent (1.2.0)
-    faraday-patron (1.0.0)
-    faraday-rack (1.0.0)
-    faraday-retry (1.0.3)
+    faraday-net_http (3.0.2)
+    faraday-retry (2.2.0)
+      faraday (~> 2.0)
     ffi (1.15.5)
     gapic-common (0.19.1)
       faraday (>= 1.9, < 3.a)
@@ -185,10 +168,9 @@ GEM
     mlanett-redis-lock (0.2.7)
       redis
     multi_json (1.15.0)
-    multipart-post (2.3.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
-    oj (2.18.5)
+    oj (3.15.1)
     omni_logger (0.1.4)
       logger
     os (1.1.4)
@@ -259,7 +241,6 @@ PLATFORMS
 DEPENDENCIES
   cube-ruby
   email_spec
-  faraday (~> 1.9)
   ffi
   goo!
   google-analytics-data
@@ -268,7 +249,7 @@ DEPENDENCIES
   multi_json
   ncbo_annotator!
   ncbo_cron!
-  oj (~> 2.0)
+  oj (~> 3.0)
   ontologies_linked_data!
   parseconfig
   pony

From 79104ab2d0de31a8b2612e0eec09749cb9335a26 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Mon, 7 Aug 2023 13:34:35 -0700
Subject: [PATCH 40/62] A chnage to reference Analytics Redis from LinkedData
 block

---
 Gemfile.lock                        | 2 +-
 lib/ncbo_cron/ontology_analytics.rb | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 6922cbd9..dbd979f0 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 8a0c14a6e6942b20749894806f1f1f512f9afcfa
+  revision: a3a5f20a75482b4d9e5ffe31d66831855422867a
   branch: develop
   specs:
     goo (0.0.2)
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
index 334da43e..3a91b813 100644
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ b/lib/ncbo_cron/ontology_analytics.rb
@@ -17,7 +17,7 @@ def initialize(logger)
       end
 
       def run
-        redis = Redis.new(:host => NcboCron.settings.ontology_analytics_redis_host, :port => NcboCron.settings.ontology_analytics_redis_port)
+        redis = Redis.new(:host => LinkedData.settings.ontology_analytics_redis_host, :port => LinkedData.settings.ontology_analytics_redis_port)
         ontology_analytics = fetch_ontology_analytics
         File.open(NcboCron.settings.analytics_path_to_ga_data_file, 'w') do |f|
           f.write(ontology_analytics.to_json)

From 656b3ac6ae66c5bc60cb9d97d5ed0009b1b703e0 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 8 Aug 2023 10:49:09 -0700
Subject: [PATCH 41/62] Gemfile.lock update

---
 Gemfile.lock | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 3a21d8ce..d8205040 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: a3a5f20a75482b4d9e5ffe31d66831855422867a
+  revision: 20801d66769854e254ec85ef5c14b5d87833e210
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 9fd2649b66d3bd6ef7666729d9f91087aa406266
+  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 13bb138aa40ca72bfafc91a1a7416c162ba8d325
+  revision: 98bb4f71a0714a31c13de99646145bb6af5d898c
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -124,8 +124,8 @@ GEM
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.7.0)
-      google-protobuf (~> 3.14)
+    googleapis-common-protos-types (1.8.0)
+      google-protobuf (~> 3.18)
     googleauth (1.7.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
@@ -163,7 +163,7 @@ GEM
     method_source (1.0.0)
     mime-types (3.5.0)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.0218.1)
+    mime-types-data (3.2023.0808)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
       redis
@@ -264,4 +264,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.4.17

From ed14911ccb28375298c63e7ca1b388ed0c638abb Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 7 Sep 2023 16:46:06 -0700
Subject: [PATCH 42/62] Gemfile.lock update

---
 Gemfile.lock | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index d8205040..92164456 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 20801d66769854e254ec85ef5c14b5d87833e210
+  revision: 911d71aefe433314d11398445e3856fca503b9c1
   branch: develop
   specs:
     goo (0.0.2)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 98bb4f71a0714a31c13de99646145bb6af5d898c
+  revision: e33a0e451f8a8226d98291168e45b46d7065e670
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -97,7 +97,7 @@ GEM
     faraday-retry (2.2.0)
       faraday (~> 2.0)
     ffi (1.15.5)
-    gapic-common (0.19.1)
+    gapic-common (0.20.0)
       faraday (>= 1.9, < 3.a)
       faraday-retry (>= 1.0, < 3.a)
       google-protobuf (~> 3.14)
@@ -108,7 +108,7 @@ GEM
     google-analytics-data (0.4.0)
       google-analytics-data-v1beta (>= 0.7, < 2.a)
       google-cloud-core (~> 1.6)
-    google-analytics-data-v1beta (0.8.0)
+    google-analytics-data-v1beta (0.8.1)
       gapic-common (>= 0.19.1, < 2.a)
       google-cloud-errors (~> 1.0)
     google-cloud-core (1.6.0)
@@ -117,9 +117,9 @@ GEM
     google-cloud-env (1.6.0)
       faraday (>= 0.17.3, < 3.0)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.23.4)
-    google-protobuf (3.23.4-x86_64-darwin)
-    google-protobuf (3.23.4-x86_64-linux)
+    google-protobuf (3.24.3)
+    google-protobuf (3.24.3-x86_64-darwin)
+    google-protobuf (3.24.3-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
@@ -133,13 +133,13 @@ GEM
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.56.2)
+    grpc (1.57.0)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.2-x86_64-darwin)
+    grpc (1.57.0-x86_64-darwin)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.56.2-x86_64-linux)
+    grpc (1.57.0-x86_64-linux)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
@@ -161,7 +161,7 @@ GEM
       mime-types (>= 1.16, < 4)
     memoist (0.16.2)
     method_source (1.0.0)
-    mime-types (3.5.0)
+    mime-types (3.5.1)
       mime-types-data (~> 3.2015)
     mime-types-data (3.2023.0808)
     minitest (4.7.5)
@@ -170,7 +170,7 @@ GEM
     multi_json (1.15.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
-    oj (3.15.1)
+    oj (3.16.1)
     omni_logger (0.1.4)
       logger
     os (1.1.4)
@@ -187,9 +187,9 @@ GEM
     rake (13.0.6)
     rdf (1.0.8)
       addressable (>= 2.2)
-    redis (5.0.6)
+    redis (5.0.7)
       redis-client (>= 0.9.0)
-    redis-client (0.15.0)
+    redis-client (0.17.0)
       connection_pool
     rest-client (2.1.0)
       http-accept (>= 1.7.0, < 2.0)
@@ -205,7 +205,7 @@ GEM
     rubyzip (2.3.2)
     rufus-scheduler (2.0.24)
       tzinfo (>= 0.3.22)
-    signet (0.17.0)
+    signet (0.18.0)
       addressable (~> 2.8)
       faraday (>= 0.17.5, < 3.a)
       jwt (>= 1.5, < 3.0)
@@ -264,4 +264,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.4.17
+   2.3.15

From 55ac1cad6a14dd7cb5264d4f53801a05537d9cb8 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Thu, 7 Sep 2023 17:00:35 -0700
Subject: [PATCH 43/62] Gemfile.lock update

---
 Gemfile.lock | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index c849962b..776ef5d1 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 911d71aefe433314d11398445e3856fca503b9c1
-  branch: develop
+  revision: cd477a1c71d8c2b2c26c3ea92c9457643a9cc70a
+  branch: master
   specs:
     goo (0.0.2)
       addressable (~> 2.8)
@@ -15,8 +15,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
-  branch: develop
+  revision: ac11b22596b87a6eecbcd70787b2370c18ff4770
+  branch: master
   specs:
     ncbo_annotator (0.0.1)
       goo
@@ -26,8 +26,8 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e33a0e451f8a8226d98291168e45b46d7065e670
-  branch: develop
+  revision: 89474face62004ab70430ef718556fe50720e038
+  branch: master
   specs:
     ontologies_linked_data (0.0.1)
       activesupport
@@ -46,7 +46,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/sparql-client.git
-  revision: fb4a89b420f8eb6dda5190a126b6c62e32c4c0c9
+  revision: d418d56a6c9ff5692f925b45739a2a1c66bca851
   branch: master
   specs:
     sparql-client (1.0.1)
@@ -264,4 +264,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.4.17
+   2.3.15

From 020ca5d47d76c286da6c24a3fd7a8532dd757e78 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Wed, 13 Sep 2023 09:09:01 -0700
Subject: [PATCH 44/62] Gemfile.lock update

---
 Gemfile.lock | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 92164456..1413c3bf 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 911d71aefe433314d11398445e3856fca503b9c1
+  revision: 83425ba6c05d051d86c6f5775540727ce4238443
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
+  revision: 067104ae94c0e9d058cfbf419364fbf03f34de43
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e33a0e451f8a8226d98291168e45b46d7065e670
+  revision: 711ebf27722355a25a0e53a8204b4ae472902bd0
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -76,6 +76,7 @@ GEM
       multi_json (~> 1.0)
     addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
+    base64 (0.1.1)
     bcrypt (3.1.19)
     builder (3.2.4)
     coderay (1.1.3)
@@ -90,7 +91,8 @@ GEM
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (2.7.10)
+    faraday (2.7.11)
+      base64
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
     faraday-net_http (3.0.2)
@@ -108,8 +110,8 @@ GEM
     google-analytics-data (0.4.0)
       google-analytics-data-v1beta (>= 0.7, < 2.a)
       google-cloud-core (~> 1.6)
-    google-analytics-data-v1beta (0.8.1)
-      gapic-common (>= 0.19.1, < 2.a)
+    google-analytics-data-v1beta (0.9.0)
+      gapic-common (>= 0.20.0, < 2.a)
       google-cloud-errors (~> 1.0)
     google-cloud-core (1.6.0)
       google-cloud-env (~> 1.0)
@@ -126,20 +128,19 @@ GEM
       grpc (~> 1.27)
     googleapis-common-protos-types (1.8.0)
       google-protobuf (~> 3.18)
-    googleauth (1.7.0)
+    googleauth (1.8.0)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
-      memoist (~> 0.16)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.57.0)
+    grpc (1.58.0)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.57.0-x86_64-darwin)
+    grpc (1.58.0-x86_64-darwin)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.57.0-x86_64-linux)
+    grpc (1.58.0-x86_64-linux)
       google-protobuf (~> 3.23)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
@@ -159,7 +160,6 @@ GEM
       systemu (~> 2.6.5)
     mail (2.6.6)
       mime-types (>= 1.16, < 4)
-    memoist (0.16.2)
     method_source (1.0.0)
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)

From ac798aaf30ccac41860edf0df45e9caedaabbdcb Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Wed, 13 Sep 2023 11:18:55 -0700
Subject: [PATCH 45/62] use assert_operator instead of assert

minitest style guide adherence.
encountered an intermittent unit test failure so assert_operator will provide
better failure feedback than assert
---
 test/test_scheduler.rb | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/test/test_scheduler.rb b/test/test_scheduler.rb
index bac2f842..58808ea5 100644
--- a/test/test_scheduler.rb
+++ b/test/test_scheduler.rb
@@ -39,7 +39,7 @@ def test_scheduler
       sleep(5)
       finished_array = listen_string.split("\n")
 
-      assert finished_array.length >= 4
+      assert_operator 4, :<=, finished_array.length
 
       assert job1_thread.alive?
       job1_thread.kill

From c626d5c6e6d74da9a2c243ea8c94b51e34d60579 Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Tue, 10 Oct 2023 20:09:53 +0200
Subject: [PATCH 46/62] use local solr to pass the tests

---
 .github/workflows/ruby-unit-tests.yml         |    2 +-
 config/solr/property_search/enumsconfig.xml   |   12 +
 .../mapping-ISOLatin1Accent.txt               |  246 +++
 config/solr/property_search/schema.xml        | 1179 ++++++++++++
 config/solr/property_search/solrconfig.xml    | 1299 +++++++++++++
 config/solr/solr.xml                          |   60 +
 config/solr/term_search/enumsconfig.xml       |   12 +
 .../term_search/mapping-ISOLatin1Accent.txt   |  246 +++
 config/solr/term_search/schema.xml            | 1222 +++++++++++++
 config/solr/term_search/solrconfig.xml        | 1299 +++++++++++++
 docker-compose.yml                            |   30 +-
 test/solr/README                              |    5 +
 .../_default/conf/lang/contractions_ca.txt    |    8 +
 .../_default/conf/lang/contractions_fr.txt    |   15 +
 .../_default/conf/lang/contractions_ga.txt    |    5 +
 .../_default/conf/lang/contractions_it.txt    |   23 +
 .../_default/conf/lang/hyphenations_ga.txt    |    5 +
 .../_default/conf/lang/stemdict_nl.txt        |    6 +
 .../_default/conf/lang/stoptags_ja.txt        |  420 +++++
 .../_default/conf/lang/stopwords_ar.txt       |  125 ++
 .../_default/conf/lang/stopwords_bg.txt       |  193 ++
 .../_default/conf/lang/stopwords_ca.txt       |  220 +++
 .../_default/conf/lang/stopwords_cz.txt       |  172 ++
 .../_default/conf/lang/stopwords_da.txt       |  110 ++
 .../_default/conf/lang/stopwords_de.txt       |  294 +++
 .../_default/conf/lang/stopwords_el.txt       |   78 +
 .../_default/conf/lang/stopwords_en.txt       |   54 +
 .../_default/conf/lang/stopwords_es.txt       |  356 ++++
 .../_default/conf/lang/stopwords_et.txt       | 1603 +++++++++++++++++
 .../_default/conf/lang/stopwords_eu.txt       |   99 +
 .../_default/conf/lang/stopwords_fa.txt       |  313 ++++
 .../_default/conf/lang/stopwords_fi.txt       |   97 +
 .../_default/conf/lang/stopwords_fr.txt       |  186 ++
 .../_default/conf/lang/stopwords_ga.txt       |  110 ++
 .../_default/conf/lang/stopwords_gl.txt       |  161 ++
 .../_default/conf/lang/stopwords_hi.txt       |  235 +++
 .../_default/conf/lang/stopwords_hu.txt       |  211 +++
 .../_default/conf/lang/stopwords_hy.txt       |   46 +
 .../_default/conf/lang/stopwords_id.txt       |  359 ++++
 .../_default/conf/lang/stopwords_it.txt       |  303 ++++
 .../_default/conf/lang/stopwords_ja.txt       |  127 ++
 .../_default/conf/lang/stopwords_lv.txt       |  172 ++
 .../_default/conf/lang/stopwords_nl.txt       |  119 ++
 .../_default/conf/lang/stopwords_no.txt       |  194 ++
 .../_default/conf/lang/stopwords_pt.txt       |  253 +++
 .../_default/conf/lang/stopwords_ro.txt       |  233 +++
 .../_default/conf/lang/stopwords_ru.txt       |  243 +++
 .../_default/conf/lang/stopwords_sv.txt       |  133 ++
 .../_default/conf/lang/stopwords_th.txt       |  119 ++
 .../_default/conf/lang/stopwords_tr.txt       |  212 +++
 .../_default/conf/lang/userdict_ja.txt        |   29 +
 .../configsets/_default/conf/managed-schema   | 1031 +++++++++++
 .../configsets/_default/conf/protwords.txt    |   21 +
 .../configsets/_default/conf/solrconfig.xml   | 1295 +++++++++++++
 .../configsets/_default/conf/stopwords.txt    |   14 +
 .../configsets/_default/conf/synonyms.txt     |   29 +
 .../property_search/conf/enumsconfig.xml      |   12 +
 .../conf/lang/contractions_ca.txt             |    8 +
 .../conf/lang/contractions_fr.txt             |   15 +
 .../conf/lang/contractions_ga.txt             |    5 +
 .../conf/lang/contractions_it.txt             |   23 +
 .../conf/lang/hyphenations_ga.txt             |    5 +
 .../property_search/conf/lang/stemdict_nl.txt |    6 +
 .../property_search/conf/lang/stoptags_ja.txt |  420 +++++
 .../conf/lang/stopwords_ar.txt                |  125 ++
 .../conf/lang/stopwords_bg.txt                |  193 ++
 .../conf/lang/stopwords_ca.txt                |  220 +++
 .../conf/lang/stopwords_cz.txt                |  172 ++
 .../conf/lang/stopwords_da.txt                |  110 ++
 .../conf/lang/stopwords_de.txt                |  294 +++
 .../conf/lang/stopwords_el.txt                |   78 +
 .../conf/lang/stopwords_en.txt                |   54 +
 .../conf/lang/stopwords_es.txt                |  356 ++++
 .../conf/lang/stopwords_et.txt                | 1603 +++++++++++++++++
 .../conf/lang/stopwords_eu.txt                |   99 +
 .../conf/lang/stopwords_fa.txt                |  313 ++++
 .../conf/lang/stopwords_fi.txt                |   97 +
 .../conf/lang/stopwords_fr.txt                |  186 ++
 .../conf/lang/stopwords_ga.txt                |  110 ++
 .../conf/lang/stopwords_gl.txt                |  161 ++
 .../conf/lang/stopwords_hi.txt                |  235 +++
 .../conf/lang/stopwords_hu.txt                |  211 +++
 .../conf/lang/stopwords_hy.txt                |   46 +
 .../conf/lang/stopwords_id.txt                |  359 ++++
 .../conf/lang/stopwords_it.txt                |  303 ++++
 .../conf/lang/stopwords_ja.txt                |  127 ++
 .../conf/lang/stopwords_lv.txt                |  172 ++
 .../conf/lang/stopwords_nl.txt                |  119 ++
 .../conf/lang/stopwords_no.txt                |  194 ++
 .../conf/lang/stopwords_pt.txt                |  253 +++
 .../conf/lang/stopwords_ro.txt                |  233 +++
 .../conf/lang/stopwords_ru.txt                |  243 +++
 .../conf/lang/stopwords_sv.txt                |  133 ++
 .../conf/lang/stopwords_th.txt                |  119 ++
 .../conf/lang/stopwords_tr.txt                |  212 +++
 .../property_search/conf/lang/userdict_ja.txt |   29 +
 .../property_search/conf/managed-schema       | 1031 +++++++++++
 .../conf/mapping-ISOLatin1Accent.txt          |  246 +++
 .../property_search/conf/protwords.txt        |   21 +
 .../property_search/conf/schema.xml           | 1179 ++++++++++++
 .../property_search/conf/solrconfig.xml       | 1299 +++++++++++++
 .../property_search/conf/stopwords.txt        |   14 +
 .../property_search/conf/synonyms.txt         |   29 +
 .../term_search/conf/enumsconfig.xml          |   12 +
 .../term_search/conf/lang/contractions_ca.txt |    8 +
 .../term_search/conf/lang/contractions_fr.txt |   15 +
 .../term_search/conf/lang/contractions_ga.txt |    5 +
 .../term_search/conf/lang/contractions_it.txt |   23 +
 .../term_search/conf/lang/hyphenations_ga.txt |    5 +
 .../term_search/conf/lang/stemdict_nl.txt     |    6 +
 .../term_search/conf/lang/stoptags_ja.txt     |  420 +++++
 .../term_search/conf/lang/stopwords_ar.txt    |  125 ++
 .../term_search/conf/lang/stopwords_bg.txt    |  193 ++
 .../term_search/conf/lang/stopwords_ca.txt    |  220 +++
 .../term_search/conf/lang/stopwords_cz.txt    |  172 ++
 .../term_search/conf/lang/stopwords_da.txt    |  110 ++
 .../term_search/conf/lang/stopwords_de.txt    |  294 +++
 .../term_search/conf/lang/stopwords_el.txt    |   78 +
 .../term_search/conf/lang/stopwords_en.txt    |   54 +
 .../term_search/conf/lang/stopwords_es.txt    |  356 ++++
 .../term_search/conf/lang/stopwords_et.txt    | 1603 +++++++++++++++++
 .../term_search/conf/lang/stopwords_eu.txt    |   99 +
 .../term_search/conf/lang/stopwords_fa.txt    |  313 ++++
 .../term_search/conf/lang/stopwords_fi.txt    |   97 +
 .../term_search/conf/lang/stopwords_fr.txt    |  186 ++
 .../term_search/conf/lang/stopwords_ga.txt    |  110 ++
 .../term_search/conf/lang/stopwords_gl.txt    |  161 ++
 .../term_search/conf/lang/stopwords_hi.txt    |  235 +++
 .../term_search/conf/lang/stopwords_hu.txt    |  211 +++
 .../term_search/conf/lang/stopwords_hy.txt    |   46 +
 .../term_search/conf/lang/stopwords_id.txt    |  359 ++++
 .../term_search/conf/lang/stopwords_it.txt    |  303 ++++
 .../term_search/conf/lang/stopwords_ja.txt    |  127 ++
 .../term_search/conf/lang/stopwords_lv.txt    |  172 ++
 .../term_search/conf/lang/stopwords_nl.txt    |  119 ++
 .../term_search/conf/lang/stopwords_no.txt    |  194 ++
 .../term_search/conf/lang/stopwords_pt.txt    |  253 +++
 .../term_search/conf/lang/stopwords_ro.txt    |  233 +++
 .../term_search/conf/lang/stopwords_ru.txt    |  243 +++
 .../term_search/conf/lang/stopwords_sv.txt    |  133 ++
 .../term_search/conf/lang/stopwords_th.txt    |  119 ++
 .../term_search/conf/lang/stopwords_tr.txt    |  212 +++
 .../term_search/conf/lang/userdict_ja.txt     |   29 +
 .../term_search/conf/managed-schema           | 1031 +++++++++++
 .../conf/mapping-ISOLatin1Accent.txt          |  246 +++
 .../configsets/term_search/conf/protwords.txt |   21 +
 .../configsets/term_search/conf/schema.xml    | 1222 +++++++++++++
 .../term_search/conf/solrconfig.xml           | 1299 +++++++++++++
 .../configsets/term_search/conf/stopwords.txt |   14 +
 .../configsets/term_search/conf/synonyms.txt  |   29 +
 test/solr/docker-compose.yml                  |   13 +
 test/solr/generate_ncbo_configsets.sh         |   24 +
 152 files changed, 38657 insertions(+), 10 deletions(-)
 create mode 100644 config/solr/property_search/enumsconfig.xml
 create mode 100644 config/solr/property_search/mapping-ISOLatin1Accent.txt
 create mode 100644 config/solr/property_search/schema.xml
 create mode 100644 config/solr/property_search/solrconfig.xml
 create mode 100644 config/solr/solr.xml
 create mode 100644 config/solr/term_search/enumsconfig.xml
 create mode 100644 config/solr/term_search/mapping-ISOLatin1Accent.txt
 create mode 100644 config/solr/term_search/schema.xml
 create mode 100644 config/solr/term_search/solrconfig.xml
 create mode 100644 test/solr/README
 create mode 100644 test/solr/configsets/_default/conf/lang/contractions_ca.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/contractions_fr.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/contractions_ga.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/contractions_it.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/hyphenations_ga.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stemdict_nl.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stoptags_ja.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ar.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_bg.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ca.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_cz.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_da.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_de.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_el.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_en.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_es.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_et.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_eu.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_fa.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_fi.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_fr.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ga.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_gl.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_hi.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_hu.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_hy.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_id.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_it.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ja.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_lv.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_nl.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_no.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_pt.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ro.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_ru.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_sv.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_th.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/stopwords_tr.txt
 create mode 100644 test/solr/configsets/_default/conf/lang/userdict_ja.txt
 create mode 100644 test/solr/configsets/_default/conf/managed-schema
 create mode 100644 test/solr/configsets/_default/conf/protwords.txt
 create mode 100644 test/solr/configsets/_default/conf/solrconfig.xml
 create mode 100644 test/solr/configsets/_default/conf/stopwords.txt
 create mode 100644 test/solr/configsets/_default/conf/synonyms.txt
 create mode 100644 test/solr/configsets/property_search/conf/enumsconfig.xml
 create mode 100644 test/solr/configsets/property_search/conf/lang/contractions_ca.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/contractions_fr.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/contractions_ga.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/contractions_it.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/hyphenations_ga.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stemdict_nl.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stoptags_ja.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ar.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_bg.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ca.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_cz.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_da.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_de.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_el.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_en.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_es.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_et.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_eu.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_fa.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_fi.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_fr.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ga.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_gl.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_hi.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_hu.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_hy.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_id.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_it.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ja.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_lv.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_nl.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_no.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_pt.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ro.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_ru.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_sv.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_th.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/stopwords_tr.txt
 create mode 100644 test/solr/configsets/property_search/conf/lang/userdict_ja.txt
 create mode 100644 test/solr/configsets/property_search/conf/managed-schema
 create mode 100644 test/solr/configsets/property_search/conf/mapping-ISOLatin1Accent.txt
 create mode 100644 test/solr/configsets/property_search/conf/protwords.txt
 create mode 100644 test/solr/configsets/property_search/conf/schema.xml
 create mode 100644 test/solr/configsets/property_search/conf/solrconfig.xml
 create mode 100644 test/solr/configsets/property_search/conf/stopwords.txt
 create mode 100644 test/solr/configsets/property_search/conf/synonyms.txt
 create mode 100644 test/solr/configsets/term_search/conf/enumsconfig.xml
 create mode 100644 test/solr/configsets/term_search/conf/lang/contractions_ca.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/contractions_fr.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/contractions_ga.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/contractions_it.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/hyphenations_ga.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stemdict_nl.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stoptags_ja.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ar.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_bg.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ca.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_cz.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_da.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_de.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_el.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_en.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_es.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_et.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_eu.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_fa.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_fi.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_fr.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ga.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_gl.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_hi.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_hu.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_hy.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_id.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_it.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ja.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_lv.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_nl.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_no.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_pt.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ro.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_ru.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_sv.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_th.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/stopwords_tr.txt
 create mode 100644 test/solr/configsets/term_search/conf/lang/userdict_ja.txt
 create mode 100644 test/solr/configsets/term_search/conf/managed-schema
 create mode 100644 test/solr/configsets/term_search/conf/mapping-ISOLatin1Accent.txt
 create mode 100644 test/solr/configsets/term_search/conf/protwords.txt
 create mode 100644 test/solr/configsets/term_search/conf/schema.xml
 create mode 100644 test/solr/configsets/term_search/conf/solrconfig.xml
 create mode 100644 test/solr/configsets/term_search/conf/stopwords.txt
 create mode 100644 test/solr/configsets/term_search/conf/synonyms.txt
 create mode 100644 test/solr/docker-compose.yml
 create mode 100755 test/solr/generate_ncbo_configsets.sh

diff --git a/.github/workflows/ruby-unit-tests.yml b/.github/workflows/ruby-unit-tests.yml
index b61ce745..ce431e48 100644
--- a/.github/workflows/ruby-unit-tests.yml
+++ b/.github/workflows/ruby-unit-tests.yml
@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        backend: ['ncbo_cron', 'ncbo_cron-agraph'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
+        backend: ['ncbo_cron'] # ruby runs tests with 4store backend and ruby-agraph runs with AllegroGraph backend
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
diff --git a/config/solr/property_search/enumsconfig.xml b/config/solr/property_search/enumsconfig.xml
new file mode 100644
index 00000000..72e7b7d3
--- /dev/null
+++ b/config/solr/property_search/enumsconfig.xml
@@ -0,0 +1,12 @@
+<?xml version="1.0" ?>
+<enumsConfig>
+  <enum name="ontologyType">
+    <value>ONTOLOGY</value>
+    <value>VALUE_SET_COLLECTION</value>
+  </enum>
+  <enum name="propertyType">
+    <value>ANNOTATION</value>
+    <value>DATATYPE</value>
+    <value>OBJECT</value>
+  </enum>
+</enumsConfig>
\ No newline at end of file
diff --git a/config/solr/property_search/mapping-ISOLatin1Accent.txt b/config/solr/property_search/mapping-ISOLatin1Accent.txt
new file mode 100644
index 00000000..ede77425
--- /dev/null
+++ b/config/solr/property_search/mapping-ISOLatin1Accent.txt
@@ -0,0 +1,246 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Syntax:
+#   "source" => "target"
+#     "source".length() > 0 (source cannot be empty.)
+#     "target".length() >= 0 (target can be empty.)
+
+# example:
+#   "À" => "A"
+#   "\u00C0" => "A"
+#   "\u00C0" => "\u0041"
+#   "ß" => "ss"
+#   "\t" => " "
+#   "\n" => ""
+
+# À => A
+"\u00C0" => "A"
+
+# Á => A
+"\u00C1" => "A"
+
+# Â => A
+"\u00C2" => "A"
+
+# Ã => A
+"\u00C3" => "A"
+
+# Ä => A
+"\u00C4" => "A"
+
+# Å => A
+"\u00C5" => "A"
+
+# Æ => AE
+"\u00C6" => "AE"
+
+# Ç => C
+"\u00C7" => "C"
+
+# È => E
+"\u00C8" => "E"
+
+# É => E
+"\u00C9" => "E"
+
+# Ê => E
+"\u00CA" => "E"
+
+# Ë => E
+"\u00CB" => "E"
+
+# Ì => I
+"\u00CC" => "I"
+
+# Í => I
+"\u00CD" => "I"
+
+# Î => I
+"\u00CE" => "I"
+
+# Ï => I
+"\u00CF" => "I"
+
+# IJ => IJ
+"\u0132" => "IJ"
+
+# Ð => D
+"\u00D0" => "D"
+
+# Ñ => N
+"\u00D1" => "N"
+
+# Ò => O
+"\u00D2" => "O"
+
+# Ó => O
+"\u00D3" => "O"
+
+# Ô => O
+"\u00D4" => "O"
+
+# Õ => O
+"\u00D5" => "O"
+
+# Ö => O
+"\u00D6" => "O"
+
+# Ø => O
+"\u00D8" => "O"
+
+# Π=> OE
+"\u0152" => "OE"
+
+# Þ
+"\u00DE" => "TH"
+
+# Ù => U
+"\u00D9" => "U"
+
+# Ú => U
+"\u00DA" => "U"
+
+# Û => U
+"\u00DB" => "U"
+
+# Ü => U
+"\u00DC" => "U"
+
+# Ý => Y
+"\u00DD" => "Y"
+
+# Ÿ => Y
+"\u0178" => "Y"
+
+# à => a
+"\u00E0" => "a"
+
+# á => a
+"\u00E1" => "a"
+
+# â => a
+"\u00E2" => "a"
+
+# ã => a
+"\u00E3" => "a"
+
+# ä => a
+"\u00E4" => "a"
+
+# å => a
+"\u00E5" => "a"
+
+# æ => ae
+"\u00E6" => "ae"
+
+# ç => c
+"\u00E7" => "c"
+
+# è => e
+"\u00E8" => "e"
+
+# é => e
+"\u00E9" => "e"
+
+# ê => e
+"\u00EA" => "e"
+
+# ë => e
+"\u00EB" => "e"
+
+# ì => i
+"\u00EC" => "i"
+
+# í => i
+"\u00ED" => "i"
+
+# î => i
+"\u00EE" => "i"
+
+# ï => i
+"\u00EF" => "i"
+
+# ij => ij
+"\u0133" => "ij"
+
+# ð => d
+"\u00F0" => "d"
+
+# ñ => n
+"\u00F1" => "n"
+
+# ò => o
+"\u00F2" => "o"
+
+# ó => o
+"\u00F3" => "o"
+
+# ô => o
+"\u00F4" => "o"
+
+# õ => o
+"\u00F5" => "o"
+
+# ö => o
+"\u00F6" => "o"
+
+# ø => o
+"\u00F8" => "o"
+
+# œ => oe
+"\u0153" => "oe"
+
+# ß => ss
+"\u00DF" => "ss"
+
+# þ => th
+"\u00FE" => "th"
+
+# ù => u
+"\u00F9" => "u"
+
+# ú => u
+"\u00FA" => "u"
+
+# û => u
+"\u00FB" => "u"
+
+# ü => u
+"\u00FC" => "u"
+
+# ý => y
+"\u00FD" => "y"
+
+# ÿ => y
+"\u00FF" => "y"
+
+# ff => ff
+"\uFB00" => "ff"
+
+# fi => fi
+"\uFB01" => "fi"
+
+# fl => fl
+"\uFB02" => "fl"
+
+# ffi => ffi
+"\uFB03" => "ffi"
+
+# ffl => ffl
+"\uFB04" => "ffl"
+
+# ſt => ft
+"\uFB05" => "ft"
+
+# st => st
+"\uFB06" => "st"
diff --git a/config/solr/property_search/schema.xml b/config/solr/property_search/schema.xml
new file mode 100644
index 00000000..20824ea6
--- /dev/null
+++ b/config/solr/property_search/schema.xml
@@ -0,0 +1,1179 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
+-->
+
+<schema name="ncbo_property" version="1.7">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued
+            by nature
+       1.1: multiValued attribute introduced, false by default
+       1.2: omitTermFreqAndPositions attribute introduced, true by default
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandat ory - the name for the field
+     type: mandatory - the name of a field type from the
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc values are
+       useful (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc values will make the index
+       faster to load, more NRT-friendly and more memory-efficient.
+       They however come with some limitations: they are currently only
+       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+       and depending on the field type, they might require the field to be
+       single-valued, be required or have a default value (check the
+       documentation of the field type you're interested in for more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+         id, _version_, and _text_.  All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared
+         in solrconfig.xml.
+
+         Note that many dynamic fields are also defined - you can use them to specify a
+         field's type via field naming conventions - see below.
+
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
+    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+
+    <!-- NCBO specific fields -->
+    <field name="resource_id"                type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
+
+    <!-- searchable fields -->
+    <field name="label"                      type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelExact"                 type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelSuggest"               type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="labelSuggestEdge"           type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelSuggestNgram"          type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <field name="labelGenerated"             type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedExact"        type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedSuggest"      type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="labelGeneratedSuggestEdge"  type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedSuggestNgram" type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <field name="definition"                 type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="submissionAcronym"          type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="parents"                    type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="ontologyType"               type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="propertyType"               type="propertyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="ontologyId"                 type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"               type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <!-- END: NCBO specific fields -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have
+       a "*" only at the start or the end.  -->
+
+    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
+
+    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- KD-tree (point) numerics -->
+    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
+
+    <!-- some trie-coded dynamic fields -->
+    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <dynamicField name="random_*" type="random" />
+
+    <!-- uncomment the following to ignore any fields that don't already match an existing
+        field name or dynamic field, rather than reporting them as an error.
+        alternately, change the type="ignored" to some other type e.g. "text" if you want
+        unknown fields indexed and/or stored by default
+
+        NB: use of "*" dynamic fields will disable field type guessing and adding
+        unknown fields to the schema. -->
+    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching. -->
+
+    <copyField source="label" dest="_text_"/>
+    <copyField source="label" dest="labelExact"/>
+    <copyField source="label" dest="labelSuggest" />
+    <copyField source="label" dest="labelSuggestEdge" />
+    <copyField source="label" dest="labelSuggestNgram" />
+
+    <copyField source="labelGenerated" dest="_text_"/>
+    <copyField source="labelGenerated" dest="labelGeneratedExact"/>
+    <copyField source="labelGenerated" dest="labelGeneratedSuggest" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestEdge" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestNgram" />
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
+    <fieldType name="propertyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="propertyType"/>
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+       It supports doc values but in that case the field needs to be
+       single-valued and either required or have a default value.
+      -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	     This includes "string","boolean", "int", "float", "long", "date", "double",
+	     including the "Trie" and "Point" variants.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!--
+      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+      search time and at index time, but some features are still not supported.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+    <!--
+      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+      tint/tfloat/tlong/tdouble types.
+    -->
+    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+    <!--
+     Numeric field types that index each value at various levels of precision
+     to accelerate range queries when the number of values between the range
+     endpoints is large. See the javadoc for NumericRangeQuery for internal
+     implementation details.
+
+     Smaller precisionStep values (specified in bits) will lead to more tokens
+     indexed per value, slightly larger index size, and faster range queries.
+     A precisionStep of 0 disables indexing at different precision levels.
+
+     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+    -->
+    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+
+         Consult the TrieDateField javadocs for more information.
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+
+    <!-- The "RandomSortField" is not used to store or search any
+         data.  You can declare fields of this type it in your schema
+         to generate pseudo-random orderings of your docs for sorting
+         or function purposes.  The ordering is generated based on the field
+         name and the version of the index. As long as the index version
+         remains unchanged, and the same field name is reused,
+         the ordering of the docs will be consistent.
+         If you want different psuedo-random orderings of documents,
+         for the same version of the index, use a dynamicField and
+         change the field name in the request.
+     -->
+    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+        wild card phrases bypass the query analyzer and will not be lowercased before matching
+        against the index. This means that the characters in wildcard phrases must be lowercase in
+        order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it
+         tokenizes with StandardTokenizer, removes English stop words
+         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer
+         also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
+      For more information about this and other Spatial fields new to Solr 4, see:
+      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+        <filter class="solr.BulgarianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+
+           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but
+       the default is fine for most applications.
+       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/config/solr/property_search/solrconfig.xml b/config/solr/property_search/solrconfig.xml
new file mode 100644
index 00000000..771a0f32
--- /dev/null
+++ b/config/solr/property_search/solrconfig.xml
@@ -0,0 +1,1299 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+     For more details about configurations options that may appear in
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+  <!-- In all configuration below, a prefix of "solr." for class names
+       is an alias that causes solr to search appropriate packages,
+       including org.apache.solr.(search|update|request|core|analysis)
+
+       You may also specify a fully qualified Java classname if you
+       have your own custom plugins.
+    -->
+
+  <!-- Controls what version of Lucene various components of Solr
+       adhere to.  Generally, you want to use the latest version to
+       get all bug fixes and improvements. It is highly recommended
+       that you fully re-index after changing this setting as it can
+       affect both how text is indexed and queried.
+  -->
+  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+
+  <!-- <lib/> directives can be used to instruct Solr to load any Jars
+       identified and use them to resolve any "plugins" specified in
+       your solrconfig.xml or schema.xml (ie: Analyzers, Request
+       Handlers, etc...).
+
+       All directories and paths are resolved relative to the
+       instanceDir.
+
+       Please note that <lib/> directives are processed in the order
+       that they appear in your solrconfig.xml file, and are "stacked"
+       on top of each other when building a ClassLoader - so if you have
+       plugin jars with dependencies on other jars, the "lower level"
+       dependency jars should be loaded first.
+
+       If a "./lib" directory exists in your instanceDir, all files
+       found in it are included as if you had used the following
+       syntax...
+
+              <lib dir="./lib" />
+    -->
+
+  <!-- A 'dir' option by itself adds any files found in the directory
+       to the classpath, this is useful for including all jars in a
+       directory.
+
+       When a 'regex' is specified in addition to a 'dir', only the
+       files in that directory which completely match the regex
+       (anchored on both ends) will be included.
+
+       If a 'dir' option (with or without a regex) is used and nothing
+       is found that matches, a warning will be logged.
+
+       The example below can be used to load a solr-contrib along
+       with their external dependencies.
+    -->
+    <!-- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
+
+  <!-- an exact 'path' can be used instead of a 'dir' to specify a
+       specific jar file.  This will cause a serious error to be logged
+       if it can't be loaded.
+    -->
+  <!--
+     <lib path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
+    -->
+  <dataDir>${solr.data.dir:}</dataDir>
+
+
+  <!-- The DirectoryFactory to use for indexes.
+
+       solr.StandardDirectoryFactory is filesystem
+       based and tries to pick the best implementation for the current
+       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
+       wraps solr.StandardDirectoryFactory and caches small files in memory
+       for better NRT performance.
+
+       One can force a particular implementation via solr.MMapDirectoryFactory,
+       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+       solr.RAMDirectoryFactory is memory based and not persistent.
+    -->
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+       A "compressionMode" string element can be added to <codecFactory> to choose
+       between the existing compression modes in the default codec: "BEST_SPEED" (default)
+       or "BEST_COMPRESSION".
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <!-- NCBO: for now using the unmanaged schema (user-defined) -->
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Index Config - These settings control low-level behavior of indexing
+       Most example settings here show the default value, but are commented
+       out, to more easily see where customizations have been made.
+
+       Note: This replaces <indexDefaults> and <mainIndex> from older versions
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <indexConfig>
+    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+         LimitTokenCountFilterFactory in your fieldType definition. E.g.
+     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+    -->
+    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
+
+    <!-- Expert: Enabling compound file will use less files for the index,
+         using fewer file descriptors on the expense of performance decrease.
+         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+    <!-- <useCompoundFile>false</useCompoundFile> -->
+
+    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+         indexing for buffering added documents and deletions before they are
+         flushed to the Directory.
+         maxBufferedDocs sets a limit on the number of documents buffered
+         before flushing.
+         If both ramBufferSizeMB and maxBufferedDocs is set, then
+         Lucene will flush based on whichever limit is hit first.  -->
+    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+    <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+         per thread before they are flushed. When limit is exceeded, this triggers a forced
+         flush even if ramBufferSizeMB has not been exceeded.
+         This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+         exhaustion due to its internal 32 bit signed integer based memory addressing.
+         The specified value should be greater than 0 and less than 2048MB. When not specified,
+         Solr uses Lucene's default value 1945. -->
+    <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+    <!-- Expert: Merge Policy
+         The Merge Policy in Lucene controls how merging of segments is done.
+         The default since Solr/Lucene 3.3 is TieredMergePolicy.
+         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+         Even older versions of Lucene used LogDocMergePolicy.
+      -->
+    <!--
+        <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+          <int name="maxMergeAtOnce">10</int>
+          <int name="segmentsPerTier">10</int>
+          <double name="noCFSRatio">0.1</double>
+        </mergePolicyFactory>
+      -->
+
+    <!-- Expert: Merge Scheduler
+         The Merge Scheduler in Lucene controls how merges are
+         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+         can perform merges in the background using separate threads.
+         The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--
+       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+       -->
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
+    -->
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Commit Deletion Policy
+         Custom deletion policies can be specified here. The class must
+         implement org.apache.lucene.index.IndexDeletionPolicy.
+
+         The default Solr IndexDeletionPolicy implementation supports
+         deleting index commit points on number of commits, age of
+         commit point and optimized status.
+
+         The latest commit point should always be preserved regardless
+         of the criteria.
+    -->
+    <!--
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+    -->
+    <!-- The number of commit points to be kept -->
+    <!-- <str name="maxCommitsToKeep">1</str> -->
+    <!-- The number of optimized commit points to be kept -->
+    <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+    <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g.
+      -->
+    <!--
+       <str name="maxCommitAge">30MINUTES</str>
+       <str name="maxCommitAge">1DAY</str>
+    -->
+    <!--
+    </deletionPolicy>
+    -->
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting The value to true will instruct the underlying Lucene
+         IndexWriter to write its debugging info the specified file
+      -->
+    <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+  </indexConfig>
+
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.
+         "numVersionBuckets" - sets the number of buckets used to keep
+                track of max version values when checking for re-ordered
+                updates; increase this value to reduce the cost of
+                synchronizing access to version buckets during high-volume
+                indexing, this requires 8 bytes (long) * numVersionBuckets
+                of heap space per Solr core.
+    -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+    </updateLog>
+
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+    <autoCommit>
+      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+      <openSearcher>false</openSearcher>
+    </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+    <autoSoftCommit>
+      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+    </autoSoftCommit>
+
+    <!-- Update Related Event Listeners
+
+         Various IndexWriter related events can trigger Listeners to
+         take actions.
+
+         postCommit - fired after every commit or optimize command
+         postOptimize - fired after every optimize command
+      -->
+
+  </updateHandler>
+
+  <!-- IndexReaderFactory
+
+       Use the following format to specify a custom IndexReaderFactory,
+       which allows for alternate IndexReader implementations.
+
+       ** Experimental Feature **
+
+       Please note - Using a custom IndexReaderFactory may prevent
+       certain other features from working. The API to
+       IndexReaderFactory may change without warning or may even be
+       removed from future releases if the problems cannot be
+       resolved.
+
+
+       ** Features that may not work with custom IndexReaderFactory **
+
+       The ReplicationHandler assumes a disk-resident index. Using a
+       custom IndexReader implementation may cause incompatibility
+       with ReplicationHandler and may cause replication to not work
+       correctly. See SOLR-1366 for details.
+
+    -->
+  <!--
+  <indexReaderFactory name="IndexReaderFactory" class="package.class">
+    <str name="someArg">Some Value</str>
+  </indexReaderFactory >
+  -->
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <query>
+
+    <!-- Maximum number of clauses allowed when parsing a boolean query string.
+         
+         This limit only impacts boolean queries specified by a user as part of a query string,
+         and provides per-collection controls on how complex user specified boolean queries can
+         be.  Query strings that specify more clauses then this will result in an error.
+         
+         If this per-collection limit is greater then the global `maxBooleanClauses` limit
+         specified in `solr.xml`, it will have no effect, as that setting also limits the size
+         of user specified boolean queries.
+      -->
+    <maxBooleanClauses>${solr.max.booleanClauses:500000}</maxBooleanClauses>
+
+    <!-- Solr Internal Query Caches
+
+         There are four implementations of cache available for Solr:
+         LRUCache, based on a synchronized LinkedHashMap, 
+         LFUCache and FastLRUCache, based on a ConcurrentHashMap, and CaffeineCache -
+         a modern and robust cache implementation. Note that in Solr 9.0
+         only CaffeineCache will be available, other implementations are now
+         deprecated.
+
+         FastLRUCache has faster gets and slower puts in single
+         threaded operation and thus is generally faster than LRUCache
+         when the hit ratio of the cache is high (> 75%), and may be
+         faster under other scenarios on multi-cpu systems.
+         Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
+    -->
+
+    <!-- Filter Cache
+
+         Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.  When a
+         new searcher is opened, its caches may be prepopulated or
+         "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For
+         LRUCache, the autowarmed items will be the most recently
+         accessed items.
+
+         Parameters:
+           class - the SolrCache implementation LRUCache or
+               (LRUCache or FastLRUCache)
+           size - the maximum number of entries in the cache
+           initialSize - the initial capacity (number of entries) of
+               the cache.  (see java.util.HashMap)
+           autowarmCount - the number of entries to prepopulate from
+               an old cache.
+           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                      to occupy. Note that when this option is specified, the size
+                      and initialSize parameters are ignored.
+      -->
+    <filterCache size="512"
+                 initialSize="512"
+                 autowarmCount="0"/>
+
+    <!-- Query Result Cache
+
+         Caches results of searches - ordered lists of document ids
+         (DocList) based on a query, a sort, and the range of documents requested.
+         Additional supported parameter by LRUCache:
+            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                       to occupy
+      -->
+    <queryResultCache size="512"
+                      initialSize="512"
+                      autowarmCount="0"/>
+
+    <!-- Document Cache
+
+         Caches Lucene Document objects (the stored fields for each
+         document).  Since Lucene internal document ids are transient,
+         this cache will not be autowarmed.
+      -->
+    <documentCache size="512"
+                   initialSize="512"
+                   autowarmCount="0"/>
+
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+           size="10"
+           initialSize="0"
+           autowarmCount="10"
+           regenerator="solr.NoOpRegenerator" />
+
+    <!-- Field Value Cache
+
+         Cache used to hold field values that are quickly accessible
+         by document id.  The fieldValueCache is created by default
+         even if not configured here.
+      -->
+    <!--
+       <fieldValueCache size="512"
+                        autowarmCount="128"
+                        showItems="32" />
+      -->
+
+    <!-- Custom Cache
+
+         Example of a generic cache.  These caches may be accessed by
+         name through SolrIndexSearcher.getCache(),cacheLookup(), and
+         cacheInsert().  The purpose is to enable easy caching of
+         user/application level data.  The regenerator argument should
+         be specified as an implementation of solr.CacheRegenerator
+         if autowarming is desired.
+      -->
+    <!--
+       <cache name="myUserCache"
+              size="4096"
+              initialSize="1024"
+              autowarmCount="1024"
+              regenerator="com.mycompany.MyRegenerator"
+              />
+      -->
+
+
+    <!-- Lazy Field Loading
+
+         If true, stored fields that are not requested will be loaded
+         lazily.  This can result in a significant speed improvement
+         if the usual case is to not load all stored fields,
+         especially if the skipped fields are large compressed text
+         fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Use Filter For Sorted Query
+
+         A possible optimization that attempts to use a filter to
+         satisfy a search.  If the requested sort does not include
+         score, then the filterCache will be checked for a filter
+         matching the query. If found, the filter will be used as the
+         source of document ids, and then the sort will be applied to
+         that.
+
+         For most situations, this will not be useful unless you
+         frequently get the same search repeatedly with different sort
+         options, and none of them ever use "score"
+      -->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Result Window Size
+
+         An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 49 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.
+      -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache.
+      -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+  <!-- Use Filter For Sorted Query
+
+   A possible optimization that attempts to use a filter to
+   satisfy a search.  If the requested sort does not include
+   score, then the filterCache will be checked for a filter
+   matching the query. If found, the filter will be used as the
+   source of document ids, and then the sort will be applied to
+   that.
+
+   For most situations, this will not be useful unless you
+   frequently get the same search repeatedly with different sort
+   options, and none of them ever use "score"
+-->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Query Related Event Listeners
+
+         Various IndexSearcher related events can trigger Listeners to
+         take actions.
+
+         newSearcher - fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka
+         registered).  It can be used to prime certain caches to
+         prevent long request times for certain requests.
+
+         firstSearcher - fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from.
+
+
+      -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence.
+      -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+          -->
+      </arr>
+    </listener>
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+        <lst>
+          <str name="q">static firstSearcher warming in solrconfig.xml</str>
+        </lst>
+        -->
+      </arr>
+    </listener>
+
+    <!-- Use Cold Searcher
+
+         If a search request comes in and there is no current
+         registered searcher, then immediately register the still
+         warming searcher and use it.  If "false" then all requests
+         will block until the first searcher is done warming.
+      -->
+    <useColdSearcher>false</useColdSearcher>
+
+  </query>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+     Circuit Breaker Section - This section consists of configurations for
+     circuit breakers
+     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+
+    <!-- Circuit Breakers
+
+     Circuit breakers are designed to allow stability and predictable query
+     execution. They prevent operations that can take down the node and cause
+     noisy neighbour issues.
+
+     This flag is the uber control switch which controls the activation/deactivation of all circuit
+     breakers. If a circuit breaker wishes to be independently configurable,
+     they are free to add their specific configuration but need to ensure that this flag is always
+     respected - this should have veto over all independent configuration flags.
+    -->
+    <circuitBreakers enabled="true">
+
+    <!-- Memory Circuit Breaker Configuration
+
+     Specific configuration for max JVM heap usage circuit breaker. This configuration defines whether
+     the circuit breaker is enabled and the threshold percentage of maximum heap allocated beyond which queries will be rejected until the
+     current JVM usage goes below the threshold. The valid value range for this value is 50-95.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+    -->
+    <!--
+   <memBreaker enabled="true" threshold="75"/>
+    -->
+
+      <!-- CPU Circuit Breaker Configuration
+
+     Specific configuration for CPU utilization based circuit breaker. This configuration defines whether the circuit breaker is enabled
+     and the average load over the last minute at which the circuit breaker should start rejecting queries.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+    -->
+
+      <!--
+       <cpuBreaker enabled="true" threshold="75"/>
+      -->
+
+  </circuitBreakers>
+
+
+  <!-- Request Dispatcher
+
+       This section contains instructions for how the SolrDispatchFilter
+       should behave when processing requests for this SolrCore.
+
+    -->
+  <requestDispatcher>
+    <!-- Request Parsing
+
+         These settings indicate how Solr Requests may be parsed, and
+         what restrictions may be placed on the ContentStreams from
+         those requests
+
+         enableRemoteStreaming - enables use of the stream.file
+         and stream.url parameters for specifying remote streams.
+
+         multipartUploadLimitInKB - specifies the max size (in KiB) of
+         Multipart File Uploads that Solr will allow in a Request.
+
+         formdataUploadLimitInKB - specifies the max size (in KiB) of
+         form data (application/x-www-form-urlencoded) sent via
+         POST. You can use POST to pass request parameters not
+         fitting into the URL.
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
+         *** WARNING ***
+         Before enabling remote streaming, you should make sure your
+         system has authentication enabled.
+
+    <requestParsers enableRemoteStreaming="false"
+                    multipartUploadLimitInKB="-1"
+                    formdataUploadLimitInKB="-1"
+                    addHttpRequestToContext="false"/>
+      -->
+
+    <!-- HTTP Caching
+
+         Set HTTP caching related parameters (for proxy caches and clients).
+
+         The options below instruct Solr not to output any HTTP Caching
+         related headers
+      -->
+    <httpCaching never304="true" />
+    <!-- If you include a <cacheControl> directive, it will be used to
+         generate a Cache-Control header (as well as an Expires header
+         if the value contains "max-age=")
+
+         By default, no Cache-Control header is generated.
+
+         You can use the <cacheControl> option even if you have set
+         never304="true"
+      -->
+    <!--
+       <httpCaching never304="true" >
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+    <!-- To enable Solr to respond with automatically generated HTTP
+         Caching headers, and to response to Cache Validation requests
+         correctly, set the value of never304="false"
+
+         This will cause Solr to generate Last-Modified and ETag
+         headers based on the properties of the Index.
+
+         The following options can also be specified to affect the
+         values of these headers...
+
+         lastModFrom - the default value is "openTime" which means the
+         Last-Modified value (and validation against If-Modified-Since
+         requests) will all be relative to when the current Searcher
+         was opened.  You can change it to lastModFrom="dirLastMod" if
+         you want the value to exactly correspond to when the physical
+         index was last modified.
+
+         etagSeed="..." is an option you can change to force the ETag
+         header (and validation against If-None-Match requests) to be
+         different even if the index has not changed (ie: when making
+         significant changes to your config file)
+
+         (lastModifiedFrom and etagSeed are both ignored if you use
+         the never304="true" option)
+      -->
+    <!--
+       <httpCaching lastModifiedFrom="openTime"
+                    etagSeed="Solr">
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+  </requestDispatcher>
+
+  <!-- Request Handlers
+
+       http://wiki.apache.org/solr/SolrRequestHandler
+
+       Incoming queries will be dispatched to a specific handler by name
+       based on the path specified in the request.
+
+       If a Request Handler is declared with startup="lazy", then it will
+       not be initialized until the first request that uses it.
+
+    -->
+  <!-- SearchHandler
+
+       http://wiki.apache.org/solr/SearchHandler
+
+       For processing Search Queries, the primary Request Handler
+       provided with Solr is "SearchHandler" It delegates to a sequent
+       of SearchComponents (see below) and supports distributed
+       queries across multiple shards
+    -->
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <int name="rows">10</int>
+      <!-- Default search field
+         <str name="df">text</str> 
+        -->
+      <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+         <str name="wt">xml</str> 
+        -->
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+      -->
+    <!-- In this example, the param "fq=instock:true" would be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="appends">
+         <str name="fq">inStock:true</str>
+       </lst>
+      -->
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params would
+         be fixed, limiting the facets clients can use.  Faceting is
+         not turned on by default - but if the client does specify
+         facet=true in the request, these are the only facets they
+         will be able to see counts for; regardless of what other
+         facet.field or facet.query params they may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="invariants">
+         <str name="facet.field">cat</str>
+         <str name="facet.field">manu_exact</str>
+         <str name="facet.query">price:[* TO 500]</str>
+         <str name="facet.query">price:[500 TO *]</str>
+       </lst>
+      -->
+    <!-- If the default list of SearchComponents is not desired, that
+         list can either be overridden completely, or components can be
+         prepended or appended to the default list.  (see below)
+      -->
+    <!--
+       <arr name="components">
+         <str>nameOfCustomComponent1</str>
+         <str>nameOfCustomComponent2</str>
+       </arr>
+      -->
+  </requestHandler>
+
+  <!-- A request handler that returns indented JSON by default -->
+  <requestHandler name="/query" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <str name="wt">json</str>
+      <str name="indent">true</str>
+    </lst>
+  </requestHandler>
+
+  <initParams path="/update/**,/query,/select,/spell">
+    <lst name="defaults">
+      <str name="df">_text_</str>
+    </lst>
+  </initParams>
+
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
+
+       Default configuration in a requestHandler would look like:
+
+       <arr name="components">
+         <str>query</str>
+         <str>facet</str>
+         <str>mlt</str>
+         <str>highlight</str>
+         <str>stats</str>
+         <str>debug</str>
+       </arr>
+
+       If you register a searchComponent to one of the standard names,
+       that will be used instead of the default.
+
+       To insert components before or after the 'standard' components, use:
+
+       <arr name="first-components">
+         <str>myFirstComponentName</str>
+       </arr>
+
+       <arr name="last-components">
+         <str>myLastComponentName</str>
+       </arr>
+
+       NOTE: The component registered with the name "debug" will
+       always be executed after the "last-components"
+
+     -->
+
+  <!-- Spell Check
+
+       The spell check component can return a list of alternative spelling
+       suggestions.
+
+       http://wiki.apache.org/solr/SpellCheckComponent
+    -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">text_general</str>
+
+    <!-- Multiple "Spell Checkers" can be declared and used by this
+         component
+      -->
+
+    <!-- a spellchecker built from a field of the main index -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">_text_</str>
+      <str name="classname">solr.DirectSolrSpellChecker</str>
+      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+      <str name="distanceMeasure">internal</str>
+      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+      <float name="accuracy">0.5</float>
+      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+      <int name="maxEdits">2</int>
+      <!-- the minimum shared prefix when enumerating terms -->
+      <int name="minPrefix">1</int>
+      <!-- maximum number of inspections per result. -->
+      <int name="maxInspections">5</int>
+      <!-- minimum length of a query term to be considered for correction -->
+      <int name="minQueryLength">4</int>
+      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+      <float name="maxQueryFrequency">0.01</float>
+      <!-- uncomment this to require suggestions to occur in 1% of the documents
+        <float name="thresholdTokenFrequency">.01</float>
+      -->
+    </lst>
+
+    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
+    <!--
+    <lst name="spellchecker">
+      <str name="name">wordbreak</str>
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
+      <str name="field">name</str>
+      <str name="combineWords">true</str>
+      <str name="breakWords">true</str>
+      <int name="maxChanges">10</int>
+    </lst>
+    -->
+  </searchComponent>
+
+  <!-- A request handler for demonstrating the spellcheck component.
+
+       NOTE: This is purely as an example.  The whole purpose of the
+       SpellCheckComponent is to hook it into the request handler that
+       handles your normal user queries so that a separate request is
+       not needed to get suggestions.
+
+       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+       See http://wiki.apache.org/solr/SpellCheckComponent for details
+       on the request parameters.
+    -->
+  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <!-- Solr will use suggestions from both the 'default' spellchecker
+           and from the 'wordbreak' spellchecker and combine them.
+           collations (re-written queries) can include a combination of
+           corrections from both spellcheckers -->
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck">on</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.count">10</str>
+      <str name="spellcheck.alternativeTermCount">5</str>
+      <str name="spellcheck.maxResultsForSuggest">5</str>
+      <str name="spellcheck.collate">true</str>
+      <str name="spellcheck.collateExtendedResults">true</str>
+      <str name="spellcheck.maxCollationTries">10</str>
+      <str name="spellcheck.maxCollations">5</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
+  <searchComponent name="terms" class="solr.TermsComponent"/>
+
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Highlighting Component
+
+       http://wiki.apache.org/solr/HighlightingParameters
+    -->
+  <searchComponent class="solr.HighlightComponent" name="highlight">
+    <highlighting>
+      <!-- Configure the standard fragmenter -->
+      <!-- This could most likely be commented out in the "default" case -->
+      <fragmenter name="gap"
+                  default="true"
+                  class="solr.highlight.GapFragmenter">
+        <lst name="defaults">
+          <int name="hl.fragsize">100</int>
+        </lst>
+      </fragmenter>
+
+      <!-- A regular-expression-based fragmenter
+           (for sentence extraction)
+        -->
+      <fragmenter name="regex"
+                  class="solr.highlight.RegexFragmenter">
+        <lst name="defaults">
+          <!-- slightly smaller fragsizes work better because of slop -->
+          <int name="hl.fragsize">70</int>
+          <!-- allow 50% slop on fragment sizes -->
+          <float name="hl.regex.slop">0.5</float>
+          <!-- a basic sentence pattern -->
+          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
+        </lst>
+      </fragmenter>
+
+      <!-- Configure the standard formatter -->
+      <formatter name="html"
+                 default="true"
+                 class="solr.highlight.HtmlFormatter">
+        <lst name="defaults">
+          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+          <str name="hl.simple.post"><![CDATA[</em>]]></str>
+        </lst>
+      </formatter>
+
+      <!-- Configure the standard encoder -->
+      <encoder name="html"
+               class="solr.highlight.HtmlEncoder" />
+
+      <!-- Configure the standard fragListBuilder -->
+      <fragListBuilder name="simple"
+                       class="solr.highlight.SimpleFragListBuilder"/>
+
+      <!-- Configure the single fragListBuilder -->
+      <fragListBuilder name="single"
+                       class="solr.highlight.SingleFragListBuilder"/>
+
+      <!-- Configure the weighted fragListBuilder -->
+      <fragListBuilder name="weighted"
+                       default="true"
+                       class="solr.highlight.WeightedFragListBuilder"/>
+
+      <!-- default tag FragmentsBuilder -->
+      <fragmentsBuilder name="default"
+                        default="true"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <!--
+        <lst name="defaults">
+          <str name="hl.multiValuedSeparatorChar">/</str>
+        </lst>
+        -->
+      </fragmentsBuilder>
+
+      <!-- multi-colored tag FragmentsBuilder -->
+      <fragmentsBuilder name="colored"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <lst name="defaults">
+          <str name="hl.tag.pre"><![CDATA[
+               <b style="background:yellow">,<b style="background:lawgreen">,
+               <b style="background:aquamarine">,<b style="background:magenta">,
+               <b style="background:palegreen">,<b style="background:coral">,
+               <b style="background:wheat">,<b style="background:khaki">,
+               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+          <str name="hl.tag.post"><![CDATA[</b>]]></str>
+        </lst>
+      </fragmentsBuilder>
+
+      <boundaryScanner name="default"
+                       default="true"
+                       class="solr.highlight.SimpleBoundaryScanner">
+        <lst name="defaults">
+          <str name="hl.bs.maxScan">10</str>
+          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
+        </lst>
+      </boundaryScanner>
+
+      <boundaryScanner name="breakIterator"
+                       class="solr.highlight.BreakIteratorBoundaryScanner">
+        <lst name="defaults">
+          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+          <str name="hl.bs.type">WORD</str>
+          <!-- language and country are used when constructing Locale object.  -->
+          <!-- And the Locale object will be used when getting instance of BreakIterator -->
+          <str name="hl.bs.language">en</str>
+          <str name="hl.bs.country">US</str>
+        </lst>
+      </boundaryScanner>
+    </highlighting>
+  </searchComponent>
+
+  <!-- Update Processors
+
+       Chains of Update Processor Factories for dealing with Update
+       Requests can be declared, and then used by name in Update
+       Request Processors
+
+       http://wiki.apache.org/solr/UpdateRequestProcessor
+
+    -->
+
+  <!-- Add unknown fields to the schema
+
+       Field type guessing update processors that will
+       attempt to parse string-typed field values as Booleans, Longs,
+       Doubles, or Dates, and then add schema fields with the guessed
+       field types. Text content will be indexed as "text_general" as
+       well as a copy to a plain string version in *_str.
+
+       These require that the schema is both managed and mutable, by
+       declaring schemaFactory as ManagedIndexSchemaFactory, with
+       mutable specified as true.
+
+       See http://wiki.apache.org/solr/GuessingFieldTypes
+    -->
+  <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+  <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+  <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+    <str name="pattern">[^\w-\.]</str>
+    <str name="replacement">_</str>
+  </updateProcessor>
+  <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+  <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+  <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+  <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+    <arr name="format">
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+      <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+      <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+      <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+    </arr>
+  </updateProcessor>
+  <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.String</str>
+      <str name="fieldType">text_general</str>
+      <lst name="copyField">
+        <str name="dest">*_str</str>
+        <int name="maxChars">256</int>
+      </lst>
+      <!-- Use as default mapping instead of defaultFieldType -->
+      <bool name="default">true</bool>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Boolean</str>
+      <str name="fieldType">booleans</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.util.Date</str>
+      <str name="fieldType">pdates</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Long</str>
+      <str name="valueClass">java.lang.Integer</str>
+      <str name="fieldType">plongs</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Number</str>
+      <str name="fieldType">pdoubles</str>
+    </lst>
+  </updateProcessor>
+
+  <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+  <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:false}"
+           processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+    <processor class="solr.LogUpdateProcessorFactory"/>
+    <processor class="solr.DistributedUpdateProcessorFactory"/>
+    <processor class="solr.RunUpdateProcessorFactory"/>
+  </updateRequestProcessorChain>
+
+  <!-- Deduplication
+
+       An example dedup update processor that creates the "id" field
+       on the fly based on the hash code of some other fields.  This
+       example has overwriteDupes set to false since we are using the
+       id field as the signatureField and Solr will maintain
+       uniqueness based on that anyway.
+
+    -->
+  <!--
+     <updateRequestProcessorChain name="dedupe">
+       <processor class="solr.processor.SignatureUpdateProcessorFactory">
+         <bool name="enabled">true</bool>
+         <str name="signatureField">id</str>
+         <bool name="overwriteDupes">false</bool>
+         <str name="fields">name,features,cat</str>
+         <str name="signatureClass">solr.processor.Lookup3Signature</str>
+       </processor>
+       <processor class="solr.LogUpdateProcessorFactory" />
+       <processor class="solr.RunUpdateProcessorFactory" />
+     </updateRequestProcessorChain>
+    -->
+
+  <!-- Response Writers
+
+       http://wiki.apache.org/solr/QueryResponseWriter
+
+       Request responses will be written using the writer specified by
+       the 'wt' request parameter matching the name of a registered
+       writer.
+
+       The "default" writer is the default and will be used if 'wt' is
+       not specified in the request.
+    -->
+  <!-- The following response writers are implicitly configured unless
+       overridden...
+    -->
+  <!--
+     <queryResponseWriter name="xml"
+                          default="true"
+                          class="solr.XMLResponseWriter" />
+     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+    -->
+
+  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+    <!-- For the purposes of the tutorial, JSON responses are written as
+     plain text so that they are easy to read in *any* browser.
+     If you expect a MIME type of "application/json" just remove this override.
+    -->
+    <str name="content-type">text/plain; charset=UTF-8</str>
+  </queryResponseWriter>
+
+  <!-- Query Parsers
+
+       https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
+
+       Multiple QParserPlugins can be registered by name, and then
+       used in either the "defType" param for the QueryComponent (used
+       by SearchHandler) or in LocalParams
+    -->
+  <!-- example of registering a query parser -->
+  <!--
+     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+    -->
+
+  <!-- Function Parsers
+
+       http://wiki.apache.org/solr/FunctionQuery
+
+       Multiple ValueSourceParsers can be registered by name, and then
+       used as function names when using the "func" QParser.
+    -->
+  <!-- example of registering a custom function parser  -->
+  <!--
+     <valueSourceParser name="myfunc"
+                        class="com.mycompany.MyValueSourceParser" />
+    -->
+
+
+  <!-- Document Transformers
+       http://wiki.apache.org/solr/DocTransformers
+    -->
+  <!--
+     Could be something like:
+     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+       <int name="connection">jdbc://....</int>
+     </transformer>
+
+     To add a constant value to all docs, use:
+     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <int name="value">5</int>
+     </transformer>
+
+     If you want the user to still be able to change it with _value:something_ use this:
+     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <double name="defaultValue">5</double>
+     </transformer>
+
+      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
+      EditorialMarkerFactory will do exactly that:
+     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+    -->
+</config>
diff --git a/config/solr/solr.xml b/config/solr/solr.xml
new file mode 100644
index 00000000..d9d089e4
--- /dev/null
+++ b/config/solr/solr.xml
@@ -0,0 +1,60 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+   This is an example of a simple "solr.xml" file for configuring one or
+   more Solr Cores, as well as allowing Cores to be added, removed, and
+   reloaded via HTTP requests.
+
+   More information about options available in this configuration file,
+   and Solr Core administration can be found online:
+   https://lucene.apache.org/solr/guide/format-of-solr-xml.html
+-->
+
+<solr>
+
+  <int name="maxBooleanClauses">${solr.max.booleanClauses:500000}</int>
+  <str name="sharedLib">${solr.sharedLib:}</str>
+  <str name="allowPaths">${solr.allowPaths:}</str>
+
+  <solrcloud>
+
+    <str name="host">${host:}</str>
+    <int name="hostPort">${solr.port.advertise:0}</int>
+    <str name="hostContext">${hostContext:solr}</str>
+
+    <bool name="genericCoreNodeNames">${genericCoreNodeNames:true}</bool>
+
+    <int name="zkClientTimeout">${zkClientTimeout:30000}</int>
+    <int name="distribUpdateSoTimeout">${distribUpdateSoTimeout:600000}</int>
+    <int name="distribUpdateConnTimeout">${distribUpdateConnTimeout:60000}</int>
+    <str name="zkCredentialsProvider">${zkCredentialsProvider:org.apache.solr.common.cloud.DefaultZkCredentialsProvider}</str>
+    <str name="zkACLProvider">${zkACLProvider:org.apache.solr.common.cloud.DefaultZkACLProvider}</str>
+
+  </solrcloud>
+
+  <shardHandlerFactory name="shardHandlerFactory"
+    class="HttpShardHandlerFactory">
+    <int name="socketTimeout">${socketTimeout:600000}</int>
+    <int name="connTimeout">${connTimeout:60000}</int>
+    <str name="shardsWhitelist">${solr.shardsWhitelist:}</str>
+  </shardHandlerFactory>
+
+  <metrics enabled="${metricsEnabled:true}"/>
+
+</solr>
diff --git a/config/solr/term_search/enumsconfig.xml b/config/solr/term_search/enumsconfig.xml
new file mode 100644
index 00000000..72e7b7d3
--- /dev/null
+++ b/config/solr/term_search/enumsconfig.xml
@@ -0,0 +1,12 @@
+<?xml version="1.0" ?>
+<enumsConfig>
+  <enum name="ontologyType">
+    <value>ONTOLOGY</value>
+    <value>VALUE_SET_COLLECTION</value>
+  </enum>
+  <enum name="propertyType">
+    <value>ANNOTATION</value>
+    <value>DATATYPE</value>
+    <value>OBJECT</value>
+  </enum>
+</enumsConfig>
\ No newline at end of file
diff --git a/config/solr/term_search/mapping-ISOLatin1Accent.txt b/config/solr/term_search/mapping-ISOLatin1Accent.txt
new file mode 100644
index 00000000..ede77425
--- /dev/null
+++ b/config/solr/term_search/mapping-ISOLatin1Accent.txt
@@ -0,0 +1,246 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Syntax:
+#   "source" => "target"
+#     "source".length() > 0 (source cannot be empty.)
+#     "target".length() >= 0 (target can be empty.)
+
+# example:
+#   "À" => "A"
+#   "\u00C0" => "A"
+#   "\u00C0" => "\u0041"
+#   "ß" => "ss"
+#   "\t" => " "
+#   "\n" => ""
+
+# À => A
+"\u00C0" => "A"
+
+# Á => A
+"\u00C1" => "A"
+
+# Â => A
+"\u00C2" => "A"
+
+# Ã => A
+"\u00C3" => "A"
+
+# Ä => A
+"\u00C4" => "A"
+
+# Å => A
+"\u00C5" => "A"
+
+# Æ => AE
+"\u00C6" => "AE"
+
+# Ç => C
+"\u00C7" => "C"
+
+# È => E
+"\u00C8" => "E"
+
+# É => E
+"\u00C9" => "E"
+
+# Ê => E
+"\u00CA" => "E"
+
+# Ë => E
+"\u00CB" => "E"
+
+# Ì => I
+"\u00CC" => "I"
+
+# Í => I
+"\u00CD" => "I"
+
+# Î => I
+"\u00CE" => "I"
+
+# Ï => I
+"\u00CF" => "I"
+
+# IJ => IJ
+"\u0132" => "IJ"
+
+# Ð => D
+"\u00D0" => "D"
+
+# Ñ => N
+"\u00D1" => "N"
+
+# Ò => O
+"\u00D2" => "O"
+
+# Ó => O
+"\u00D3" => "O"
+
+# Ô => O
+"\u00D4" => "O"
+
+# Õ => O
+"\u00D5" => "O"
+
+# Ö => O
+"\u00D6" => "O"
+
+# Ø => O
+"\u00D8" => "O"
+
+# Π=> OE
+"\u0152" => "OE"
+
+# Þ
+"\u00DE" => "TH"
+
+# Ù => U
+"\u00D9" => "U"
+
+# Ú => U
+"\u00DA" => "U"
+
+# Û => U
+"\u00DB" => "U"
+
+# Ü => U
+"\u00DC" => "U"
+
+# Ý => Y
+"\u00DD" => "Y"
+
+# Ÿ => Y
+"\u0178" => "Y"
+
+# à => a
+"\u00E0" => "a"
+
+# á => a
+"\u00E1" => "a"
+
+# â => a
+"\u00E2" => "a"
+
+# ã => a
+"\u00E3" => "a"
+
+# ä => a
+"\u00E4" => "a"
+
+# å => a
+"\u00E5" => "a"
+
+# æ => ae
+"\u00E6" => "ae"
+
+# ç => c
+"\u00E7" => "c"
+
+# è => e
+"\u00E8" => "e"
+
+# é => e
+"\u00E9" => "e"
+
+# ê => e
+"\u00EA" => "e"
+
+# ë => e
+"\u00EB" => "e"
+
+# ì => i
+"\u00EC" => "i"
+
+# í => i
+"\u00ED" => "i"
+
+# î => i
+"\u00EE" => "i"
+
+# ï => i
+"\u00EF" => "i"
+
+# ij => ij
+"\u0133" => "ij"
+
+# ð => d
+"\u00F0" => "d"
+
+# ñ => n
+"\u00F1" => "n"
+
+# ò => o
+"\u00F2" => "o"
+
+# ó => o
+"\u00F3" => "o"
+
+# ô => o
+"\u00F4" => "o"
+
+# õ => o
+"\u00F5" => "o"
+
+# ö => o
+"\u00F6" => "o"
+
+# ø => o
+"\u00F8" => "o"
+
+# œ => oe
+"\u0153" => "oe"
+
+# ß => ss
+"\u00DF" => "ss"
+
+# þ => th
+"\u00FE" => "th"
+
+# ù => u
+"\u00F9" => "u"
+
+# ú => u
+"\u00FA" => "u"
+
+# û => u
+"\u00FB" => "u"
+
+# ü => u
+"\u00FC" => "u"
+
+# ý => y
+"\u00FD" => "y"
+
+# ÿ => y
+"\u00FF" => "y"
+
+# ff => ff
+"\uFB00" => "ff"
+
+# fi => fi
+"\uFB01" => "fi"
+
+# fl => fl
+"\uFB02" => "fl"
+
+# ffi => ffi
+"\uFB03" => "ffi"
+
+# ffl => ffl
+"\uFB04" => "ffl"
+
+# ſt => ft
+"\uFB05" => "ft"
+
+# st => st
+"\uFB06" => "st"
diff --git a/config/solr/term_search/schema.xml b/config/solr/term_search/schema.xml
new file mode 100644
index 00000000..fa95e127
--- /dev/null
+++ b/config/solr/term_search/schema.xml
@@ -0,0 +1,1222 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
+-->
+
+<schema name="ncbo_class" version="1.7">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued
+            by nature
+       1.1: multiValued attribute introduced, false by default
+       1.2: omitTermFreqAndPositions attribute introduced, true by default
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandat ory - the name for the field
+     type: mandatory - the name of a field type from the
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc values are
+       useful (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc values will make the index
+       faster to load, more NRT-friendly and more memory-efficient.
+       They however come with some limitations: they are currently only
+       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+       and depending on the field type, they might require the field to be
+       single-valued, be required or have a default value (check the
+       documentation of the field type you're interested in for more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+         id, _version_, and _text_.  All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared
+         in solrconfig.xml.
+
+         Note that many dynamic fields are also defined - you can use them to specify a
+         field's type via field naming conventions - see below.
+
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
+    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+
+    <!-- NCBO specific fields -->
+    <field name="resource_id"           type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
+
+    <!-- searchable fields -->
+    <!-- all languages fields -->
+    <field name="prefLabel"             type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="prefLabelExact"        type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="prefLabelSuggest"      type="text_suggest"       indexed="true"  stored="true"  multiValued="true"  omitNorms="true" />
+    <field name="prefLabelSuggestEdge"  type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true"  />
+    <field name="prefLabelSuggestNgram" type="text_suggest_ngram" indexed="true"  stored="true"  multiValued="true"  omitNorms="true" />
+
+    <!--  language specific fields  (e.g prefLabel_en or prefLabel_fr) -->
+    <dynamicField name="prefLabel_*" type="text_general" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelExact_*" type="string_ci" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggest_*" type="text_suggest" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggestEdge_*" type="text_suggest_edge" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggestNgram_*" type="text_suggest_ngram" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+
+
+    <field name="synonym"               type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymExact"          type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymSuggest"        type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="synonymSuggestEdge"    type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymSuggestNgram"   type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <dynamicField name="synonym_*" type="text_general" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymExact_*" type="string_ci" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymSuggest_*" type="text_suggest" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+    <dynamicField name="synonymSuggestEdge_*" type="text_suggest_edge" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymSuggestNgram_*" type="text_suggest_ngram" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+
+
+    <field name="notation"              type="text_general"       indexed="true"  stored="true"  multiValued="false" />
+
+    <field name="definition" type="string" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="definition_*" type="string" indexed="true" stored="true" multiValued="true" />
+
+    <field name="submissionAcronym"     type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="parents"               type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="ontologyType"          type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="ontologyId"            type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"          type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <field name="childCount"            type="int"                indexed="true"  stored="true"  multiValued="false" />
+
+    <!-- Added cui and tui (semanticType) - NCBO-695 -->
+    <field name="cui"                   type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="semanticType"          type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+
+    <field name="property"              type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="propertyRaw"           type="text_general"       indexed="false" stored="true"  multiValued="false" />
+
+    <field name="obsolete"              type="boolean"            indexed="true"  stored="true"  multiValued="false" default="false"/>
+    <field name="provisional"           type="boolean"            indexed="true"  stored="true"  multiValued="false" default="false"/>
+    <!-- END: NCBO specific fields -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have
+       a "*" only at the start or the end.  -->
+
+    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
+
+    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- KD-tree (point) numerics -->
+    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
+
+    <!-- some trie-coded dynamic fields -->
+    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <dynamicField name="random_*" type="random" />
+
+    <!-- uncomment the following to ignore any fields that don't already match an existing
+        field name or dynamic field, rather than reporting them as an error.
+        alternately, change the type="ignored" to some other type e.g. "text" if you want
+        unknown fields indexed and/or stored by default
+
+        NB: use of "*" dynamic fields will disable field type guessing and adding
+        unknown fields to the schema. -->
+    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching. -->
+
+    <copyField source="prefLabel" dest="_text_"/>
+    <copyField source="prefLabel" dest="prefLabelExact"/>
+    <copyField source="prefLabel" dest="prefLabelSuggest" />
+    <copyField source="prefLabel" dest="prefLabelSuggestEdge" />
+    <copyField source="prefLabel" dest="prefLabelSuggestNgram" />
+
+    <copyField source="synonym" dest="_text_"/>
+    <copyField source="synonym" dest="synonymExact"/>
+    <copyField source="synonym" dest="synonymSuggest" />
+    <copyField source="synonym" dest="synonymSuggestEdge" />
+    <copyField source="synonym" dest="synonymSuggestNgram" />
+
+    <copyField source="prefLabel_*" dest="prefLabelExact_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggest_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggestEdge_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggestNgram_*" />
+
+
+    <copyField source="synonym_*" dest="synonymExact_*" />
+    <copyField source="synonym_*" dest="synonymSuggest_*" />
+    <copyField source="synonym_*" dest="synonymSuggestEdge_*" />
+    <copyField source="synonym_*" dest="synonymSuggestNgram_*" />
+
+    <copyField source="notation" dest="_text_"/>
+
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+       It supports doc values but in that case the field needs to be
+       single-valued and either required or have a default value.
+      -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	     This includes "string","boolean", "int", "float", "long", "date", "double",
+	     including the "Trie" and "Point" variants.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!--
+      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+      search time and at index time, but some features are still not supported.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+    <!--
+      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+      tint/tfloat/tlong/tdouble types.
+    -->
+    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+    <!--
+     Numeric field types that index each value at various levels of precision
+     to accelerate range queries when the number of values between the range
+     endpoints is large. See the javadoc for NumericRangeQuery for internal
+     implementation details.
+
+     Smaller precisionStep values (specified in bits) will lead to more tokens
+     indexed per value, slightly larger index size, and faster range queries.
+     A precisionStep of 0 disables indexing at different precision levels.
+
+     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+    -->
+    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+
+         Consult the TrieDateField javadocs for more information.
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+
+    <!-- The "RandomSortField" is not used to store or search any
+         data.  You can declare fields of this type it in your schema
+         to generate pseudo-random orderings of your docs for sorting
+         or function purposes.  The ordering is generated based on the field
+         name and the version of the index. As long as the index version
+         remains unchanged, and the same field name is reused,
+         the ordering of the docs will be consistent.
+         If you want different psuedo-random orderings of documents,
+         for the same version of the index, use a dynamicField and
+         change the field name in the request.
+     -->
+    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+        wild card phrases bypass the query analyzer and will not be lowercased before matching
+        against the index. This means that the characters in wildcard phrases must be lowercase in
+        order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it
+         tokenizes with StandardTokenizer, removes English stop words
+         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer
+         also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
+      For more information about this and other Spatial fields new to Solr 4, see:
+      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+        <filter class="solr.BulgarianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+
+           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but
+       the default is fine for most applications.
+       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/config/solr/term_search/solrconfig.xml b/config/solr/term_search/solrconfig.xml
new file mode 100644
index 00000000..771a0f32
--- /dev/null
+++ b/config/solr/term_search/solrconfig.xml
@@ -0,0 +1,1299 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+     For more details about configurations options that may appear in
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+  <!-- In all configuration below, a prefix of "solr." for class names
+       is an alias that causes solr to search appropriate packages,
+       including org.apache.solr.(search|update|request|core|analysis)
+
+       You may also specify a fully qualified Java classname if you
+       have your own custom plugins.
+    -->
+
+  <!-- Controls what version of Lucene various components of Solr
+       adhere to.  Generally, you want to use the latest version to
+       get all bug fixes and improvements. It is highly recommended
+       that you fully re-index after changing this setting as it can
+       affect both how text is indexed and queried.
+  -->
+  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+
+  <!-- <lib/> directives can be used to instruct Solr to load any Jars
+       identified and use them to resolve any "plugins" specified in
+       your solrconfig.xml or schema.xml (ie: Analyzers, Request
+       Handlers, etc...).
+
+       All directories and paths are resolved relative to the
+       instanceDir.
+
+       Please note that <lib/> directives are processed in the order
+       that they appear in your solrconfig.xml file, and are "stacked"
+       on top of each other when building a ClassLoader - so if you have
+       plugin jars with dependencies on other jars, the "lower level"
+       dependency jars should be loaded first.
+
+       If a "./lib" directory exists in your instanceDir, all files
+       found in it are included as if you had used the following
+       syntax...
+
+              <lib dir="./lib" />
+    -->
+
+  <!-- A 'dir' option by itself adds any files found in the directory
+       to the classpath, this is useful for including all jars in a
+       directory.
+
+       When a 'regex' is specified in addition to a 'dir', only the
+       files in that directory which completely match the regex
+       (anchored on both ends) will be included.
+
+       If a 'dir' option (with or without a regex) is used and nothing
+       is found that matches, a warning will be logged.
+
+       The example below can be used to load a solr-contrib along
+       with their external dependencies.
+    -->
+    <!-- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
+
+  <!-- an exact 'path' can be used instead of a 'dir' to specify a
+       specific jar file.  This will cause a serious error to be logged
+       if it can't be loaded.
+    -->
+  <!--
+     <lib path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
+    -->
+  <dataDir>${solr.data.dir:}</dataDir>
+
+
+  <!-- The DirectoryFactory to use for indexes.
+
+       solr.StandardDirectoryFactory is filesystem
+       based and tries to pick the best implementation for the current
+       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
+       wraps solr.StandardDirectoryFactory and caches small files in memory
+       for better NRT performance.
+
+       One can force a particular implementation via solr.MMapDirectoryFactory,
+       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+       solr.RAMDirectoryFactory is memory based and not persistent.
+    -->
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+       A "compressionMode" string element can be added to <codecFactory> to choose
+       between the existing compression modes in the default codec: "BEST_SPEED" (default)
+       or "BEST_COMPRESSION".
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <!-- NCBO: for now using the unmanaged schema (user-defined) -->
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Index Config - These settings control low-level behavior of indexing
+       Most example settings here show the default value, but are commented
+       out, to more easily see where customizations have been made.
+
+       Note: This replaces <indexDefaults> and <mainIndex> from older versions
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <indexConfig>
+    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+         LimitTokenCountFilterFactory in your fieldType definition. E.g.
+     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+    -->
+    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
+
+    <!-- Expert: Enabling compound file will use less files for the index,
+         using fewer file descriptors on the expense of performance decrease.
+         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+    <!-- <useCompoundFile>false</useCompoundFile> -->
+
+    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+         indexing for buffering added documents and deletions before they are
+         flushed to the Directory.
+         maxBufferedDocs sets a limit on the number of documents buffered
+         before flushing.
+         If both ramBufferSizeMB and maxBufferedDocs is set, then
+         Lucene will flush based on whichever limit is hit first.  -->
+    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+    <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+         per thread before they are flushed. When limit is exceeded, this triggers a forced
+         flush even if ramBufferSizeMB has not been exceeded.
+         This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+         exhaustion due to its internal 32 bit signed integer based memory addressing.
+         The specified value should be greater than 0 and less than 2048MB. When not specified,
+         Solr uses Lucene's default value 1945. -->
+    <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+    <!-- Expert: Merge Policy
+         The Merge Policy in Lucene controls how merging of segments is done.
+         The default since Solr/Lucene 3.3 is TieredMergePolicy.
+         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+         Even older versions of Lucene used LogDocMergePolicy.
+      -->
+    <!--
+        <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+          <int name="maxMergeAtOnce">10</int>
+          <int name="segmentsPerTier">10</int>
+          <double name="noCFSRatio">0.1</double>
+        </mergePolicyFactory>
+      -->
+
+    <!-- Expert: Merge Scheduler
+         The Merge Scheduler in Lucene controls how merges are
+         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+         can perform merges in the background using separate threads.
+         The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--
+       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+       -->
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
+    -->
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Commit Deletion Policy
+         Custom deletion policies can be specified here. The class must
+         implement org.apache.lucene.index.IndexDeletionPolicy.
+
+         The default Solr IndexDeletionPolicy implementation supports
+         deleting index commit points on number of commits, age of
+         commit point and optimized status.
+
+         The latest commit point should always be preserved regardless
+         of the criteria.
+    -->
+    <!--
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+    -->
+    <!-- The number of commit points to be kept -->
+    <!-- <str name="maxCommitsToKeep">1</str> -->
+    <!-- The number of optimized commit points to be kept -->
+    <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+    <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g.
+      -->
+    <!--
+       <str name="maxCommitAge">30MINUTES</str>
+       <str name="maxCommitAge">1DAY</str>
+    -->
+    <!--
+    </deletionPolicy>
+    -->
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting The value to true will instruct the underlying Lucene
+         IndexWriter to write its debugging info the specified file
+      -->
+    <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+  </indexConfig>
+
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.
+         "numVersionBuckets" - sets the number of buckets used to keep
+                track of max version values when checking for re-ordered
+                updates; increase this value to reduce the cost of
+                synchronizing access to version buckets during high-volume
+                indexing, this requires 8 bytes (long) * numVersionBuckets
+                of heap space per Solr core.
+    -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+    </updateLog>
+
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+    <autoCommit>
+      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+      <openSearcher>false</openSearcher>
+    </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+    <autoSoftCommit>
+      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+    </autoSoftCommit>
+
+    <!-- Update Related Event Listeners
+
+         Various IndexWriter related events can trigger Listeners to
+         take actions.
+
+         postCommit - fired after every commit or optimize command
+         postOptimize - fired after every optimize command
+      -->
+
+  </updateHandler>
+
+  <!-- IndexReaderFactory
+
+       Use the following format to specify a custom IndexReaderFactory,
+       which allows for alternate IndexReader implementations.
+
+       ** Experimental Feature **
+
+       Please note - Using a custom IndexReaderFactory may prevent
+       certain other features from working. The API to
+       IndexReaderFactory may change without warning or may even be
+       removed from future releases if the problems cannot be
+       resolved.
+
+
+       ** Features that may not work with custom IndexReaderFactory **
+
+       The ReplicationHandler assumes a disk-resident index. Using a
+       custom IndexReader implementation may cause incompatibility
+       with ReplicationHandler and may cause replication to not work
+       correctly. See SOLR-1366 for details.
+
+    -->
+  <!--
+  <indexReaderFactory name="IndexReaderFactory" class="package.class">
+    <str name="someArg">Some Value</str>
+  </indexReaderFactory >
+  -->
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <query>
+
+    <!-- Maximum number of clauses allowed when parsing a boolean query string.
+         
+         This limit only impacts boolean queries specified by a user as part of a query string,
+         and provides per-collection controls on how complex user specified boolean queries can
+         be.  Query strings that specify more clauses then this will result in an error.
+         
+         If this per-collection limit is greater then the global `maxBooleanClauses` limit
+         specified in `solr.xml`, it will have no effect, as that setting also limits the size
+         of user specified boolean queries.
+      -->
+    <maxBooleanClauses>${solr.max.booleanClauses:500000}</maxBooleanClauses>
+
+    <!-- Solr Internal Query Caches
+
+         There are four implementations of cache available for Solr:
+         LRUCache, based on a synchronized LinkedHashMap, 
+         LFUCache and FastLRUCache, based on a ConcurrentHashMap, and CaffeineCache -
+         a modern and robust cache implementation. Note that in Solr 9.0
+         only CaffeineCache will be available, other implementations are now
+         deprecated.
+
+         FastLRUCache has faster gets and slower puts in single
+         threaded operation and thus is generally faster than LRUCache
+         when the hit ratio of the cache is high (> 75%), and may be
+         faster under other scenarios on multi-cpu systems.
+         Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
+    -->
+
+    <!-- Filter Cache
+
+         Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.  When a
+         new searcher is opened, its caches may be prepopulated or
+         "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For
+         LRUCache, the autowarmed items will be the most recently
+         accessed items.
+
+         Parameters:
+           class - the SolrCache implementation LRUCache or
+               (LRUCache or FastLRUCache)
+           size - the maximum number of entries in the cache
+           initialSize - the initial capacity (number of entries) of
+               the cache.  (see java.util.HashMap)
+           autowarmCount - the number of entries to prepopulate from
+               an old cache.
+           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                      to occupy. Note that when this option is specified, the size
+                      and initialSize parameters are ignored.
+      -->
+    <filterCache size="512"
+                 initialSize="512"
+                 autowarmCount="0"/>
+
+    <!-- Query Result Cache
+
+         Caches results of searches - ordered lists of document ids
+         (DocList) based on a query, a sort, and the range of documents requested.
+         Additional supported parameter by LRUCache:
+            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                       to occupy
+      -->
+    <queryResultCache size="512"
+                      initialSize="512"
+                      autowarmCount="0"/>
+
+    <!-- Document Cache
+
+         Caches Lucene Document objects (the stored fields for each
+         document).  Since Lucene internal document ids are transient,
+         this cache will not be autowarmed.
+      -->
+    <documentCache size="512"
+                   initialSize="512"
+                   autowarmCount="0"/>
+
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+           size="10"
+           initialSize="0"
+           autowarmCount="10"
+           regenerator="solr.NoOpRegenerator" />
+
+    <!-- Field Value Cache
+
+         Cache used to hold field values that are quickly accessible
+         by document id.  The fieldValueCache is created by default
+         even if not configured here.
+      -->
+    <!--
+       <fieldValueCache size="512"
+                        autowarmCount="128"
+                        showItems="32" />
+      -->
+
+    <!-- Custom Cache
+
+         Example of a generic cache.  These caches may be accessed by
+         name through SolrIndexSearcher.getCache(),cacheLookup(), and
+         cacheInsert().  The purpose is to enable easy caching of
+         user/application level data.  The regenerator argument should
+         be specified as an implementation of solr.CacheRegenerator
+         if autowarming is desired.
+      -->
+    <!--
+       <cache name="myUserCache"
+              size="4096"
+              initialSize="1024"
+              autowarmCount="1024"
+              regenerator="com.mycompany.MyRegenerator"
+              />
+      -->
+
+
+    <!-- Lazy Field Loading
+
+         If true, stored fields that are not requested will be loaded
+         lazily.  This can result in a significant speed improvement
+         if the usual case is to not load all stored fields,
+         especially if the skipped fields are large compressed text
+         fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Use Filter For Sorted Query
+
+         A possible optimization that attempts to use a filter to
+         satisfy a search.  If the requested sort does not include
+         score, then the filterCache will be checked for a filter
+         matching the query. If found, the filter will be used as the
+         source of document ids, and then the sort will be applied to
+         that.
+
+         For most situations, this will not be useful unless you
+         frequently get the same search repeatedly with different sort
+         options, and none of them ever use "score"
+      -->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Result Window Size
+
+         An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 49 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.
+      -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache.
+      -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+  <!-- Use Filter For Sorted Query
+
+   A possible optimization that attempts to use a filter to
+   satisfy a search.  If the requested sort does not include
+   score, then the filterCache will be checked for a filter
+   matching the query. If found, the filter will be used as the
+   source of document ids, and then the sort will be applied to
+   that.
+
+   For most situations, this will not be useful unless you
+   frequently get the same search repeatedly with different sort
+   options, and none of them ever use "score"
+-->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Query Related Event Listeners
+
+         Various IndexSearcher related events can trigger Listeners to
+         take actions.
+
+         newSearcher - fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka
+         registered).  It can be used to prime certain caches to
+         prevent long request times for certain requests.
+
+         firstSearcher - fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from.
+
+
+      -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence.
+      -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+          -->
+      </arr>
+    </listener>
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+        <lst>
+          <str name="q">static firstSearcher warming in solrconfig.xml</str>
+        </lst>
+        -->
+      </arr>
+    </listener>
+
+    <!-- Use Cold Searcher
+
+         If a search request comes in and there is no current
+         registered searcher, then immediately register the still
+         warming searcher and use it.  If "false" then all requests
+         will block until the first searcher is done warming.
+      -->
+    <useColdSearcher>false</useColdSearcher>
+
+  </query>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+     Circuit Breaker Section - This section consists of configurations for
+     circuit breakers
+     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+
+    <!-- Circuit Breakers
+
+     Circuit breakers are designed to allow stability and predictable query
+     execution. They prevent operations that can take down the node and cause
+     noisy neighbour issues.
+
+     This flag is the uber control switch which controls the activation/deactivation of all circuit
+     breakers. If a circuit breaker wishes to be independently configurable,
+     they are free to add their specific configuration but need to ensure that this flag is always
+     respected - this should have veto over all independent configuration flags.
+    -->
+    <circuitBreakers enabled="true">
+
+    <!-- Memory Circuit Breaker Configuration
+
+     Specific configuration for max JVM heap usage circuit breaker. This configuration defines whether
+     the circuit breaker is enabled and the threshold percentage of maximum heap allocated beyond which queries will be rejected until the
+     current JVM usage goes below the threshold. The valid value range for this value is 50-95.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+    -->
+    <!--
+   <memBreaker enabled="true" threshold="75"/>
+    -->
+
+      <!-- CPU Circuit Breaker Configuration
+
+     Specific configuration for CPU utilization based circuit breaker. This configuration defines whether the circuit breaker is enabled
+     and the average load over the last minute at which the circuit breaker should start rejecting queries.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+    -->
+
+      <!--
+       <cpuBreaker enabled="true" threshold="75"/>
+      -->
+
+  </circuitBreakers>
+
+
+  <!-- Request Dispatcher
+
+       This section contains instructions for how the SolrDispatchFilter
+       should behave when processing requests for this SolrCore.
+
+    -->
+  <requestDispatcher>
+    <!-- Request Parsing
+
+         These settings indicate how Solr Requests may be parsed, and
+         what restrictions may be placed on the ContentStreams from
+         those requests
+
+         enableRemoteStreaming - enables use of the stream.file
+         and stream.url parameters for specifying remote streams.
+
+         multipartUploadLimitInKB - specifies the max size (in KiB) of
+         Multipart File Uploads that Solr will allow in a Request.
+
+         formdataUploadLimitInKB - specifies the max size (in KiB) of
+         form data (application/x-www-form-urlencoded) sent via
+         POST. You can use POST to pass request parameters not
+         fitting into the URL.
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
+         *** WARNING ***
+         Before enabling remote streaming, you should make sure your
+         system has authentication enabled.
+
+    <requestParsers enableRemoteStreaming="false"
+                    multipartUploadLimitInKB="-1"
+                    formdataUploadLimitInKB="-1"
+                    addHttpRequestToContext="false"/>
+      -->
+
+    <!-- HTTP Caching
+
+         Set HTTP caching related parameters (for proxy caches and clients).
+
+         The options below instruct Solr not to output any HTTP Caching
+         related headers
+      -->
+    <httpCaching never304="true" />
+    <!-- If you include a <cacheControl> directive, it will be used to
+         generate a Cache-Control header (as well as an Expires header
+         if the value contains "max-age=")
+
+         By default, no Cache-Control header is generated.
+
+         You can use the <cacheControl> option even if you have set
+         never304="true"
+      -->
+    <!--
+       <httpCaching never304="true" >
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+    <!-- To enable Solr to respond with automatically generated HTTP
+         Caching headers, and to response to Cache Validation requests
+         correctly, set the value of never304="false"
+
+         This will cause Solr to generate Last-Modified and ETag
+         headers based on the properties of the Index.
+
+         The following options can also be specified to affect the
+         values of these headers...
+
+         lastModFrom - the default value is "openTime" which means the
+         Last-Modified value (and validation against If-Modified-Since
+         requests) will all be relative to when the current Searcher
+         was opened.  You can change it to lastModFrom="dirLastMod" if
+         you want the value to exactly correspond to when the physical
+         index was last modified.
+
+         etagSeed="..." is an option you can change to force the ETag
+         header (and validation against If-None-Match requests) to be
+         different even if the index has not changed (ie: when making
+         significant changes to your config file)
+
+         (lastModifiedFrom and etagSeed are both ignored if you use
+         the never304="true" option)
+      -->
+    <!--
+       <httpCaching lastModifiedFrom="openTime"
+                    etagSeed="Solr">
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+  </requestDispatcher>
+
+  <!-- Request Handlers
+
+       http://wiki.apache.org/solr/SolrRequestHandler
+
+       Incoming queries will be dispatched to a specific handler by name
+       based on the path specified in the request.
+
+       If a Request Handler is declared with startup="lazy", then it will
+       not be initialized until the first request that uses it.
+
+    -->
+  <!-- SearchHandler
+
+       http://wiki.apache.org/solr/SearchHandler
+
+       For processing Search Queries, the primary Request Handler
+       provided with Solr is "SearchHandler" It delegates to a sequent
+       of SearchComponents (see below) and supports distributed
+       queries across multiple shards
+    -->
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <int name="rows">10</int>
+      <!-- Default search field
+         <str name="df">text</str> 
+        -->
+      <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+         <str name="wt">xml</str> 
+        -->
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+      -->
+    <!-- In this example, the param "fq=instock:true" would be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="appends">
+         <str name="fq">inStock:true</str>
+       </lst>
+      -->
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params would
+         be fixed, limiting the facets clients can use.  Faceting is
+         not turned on by default - but if the client does specify
+         facet=true in the request, these are the only facets they
+         will be able to see counts for; regardless of what other
+         facet.field or facet.query params they may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="invariants">
+         <str name="facet.field">cat</str>
+         <str name="facet.field">manu_exact</str>
+         <str name="facet.query">price:[* TO 500]</str>
+         <str name="facet.query">price:[500 TO *]</str>
+       </lst>
+      -->
+    <!-- If the default list of SearchComponents is not desired, that
+         list can either be overridden completely, or components can be
+         prepended or appended to the default list.  (see below)
+      -->
+    <!--
+       <arr name="components">
+         <str>nameOfCustomComponent1</str>
+         <str>nameOfCustomComponent2</str>
+       </arr>
+      -->
+  </requestHandler>
+
+  <!-- A request handler that returns indented JSON by default -->
+  <requestHandler name="/query" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <str name="wt">json</str>
+      <str name="indent">true</str>
+    </lst>
+  </requestHandler>
+
+  <initParams path="/update/**,/query,/select,/spell">
+    <lst name="defaults">
+      <str name="df">_text_</str>
+    </lst>
+  </initParams>
+
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
+
+       Default configuration in a requestHandler would look like:
+
+       <arr name="components">
+         <str>query</str>
+         <str>facet</str>
+         <str>mlt</str>
+         <str>highlight</str>
+         <str>stats</str>
+         <str>debug</str>
+       </arr>
+
+       If you register a searchComponent to one of the standard names,
+       that will be used instead of the default.
+
+       To insert components before or after the 'standard' components, use:
+
+       <arr name="first-components">
+         <str>myFirstComponentName</str>
+       </arr>
+
+       <arr name="last-components">
+         <str>myLastComponentName</str>
+       </arr>
+
+       NOTE: The component registered with the name "debug" will
+       always be executed after the "last-components"
+
+     -->
+
+  <!-- Spell Check
+
+       The spell check component can return a list of alternative spelling
+       suggestions.
+
+       http://wiki.apache.org/solr/SpellCheckComponent
+    -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">text_general</str>
+
+    <!-- Multiple "Spell Checkers" can be declared and used by this
+         component
+      -->
+
+    <!-- a spellchecker built from a field of the main index -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">_text_</str>
+      <str name="classname">solr.DirectSolrSpellChecker</str>
+      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+      <str name="distanceMeasure">internal</str>
+      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+      <float name="accuracy">0.5</float>
+      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+      <int name="maxEdits">2</int>
+      <!-- the minimum shared prefix when enumerating terms -->
+      <int name="minPrefix">1</int>
+      <!-- maximum number of inspections per result. -->
+      <int name="maxInspections">5</int>
+      <!-- minimum length of a query term to be considered for correction -->
+      <int name="minQueryLength">4</int>
+      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+      <float name="maxQueryFrequency">0.01</float>
+      <!-- uncomment this to require suggestions to occur in 1% of the documents
+        <float name="thresholdTokenFrequency">.01</float>
+      -->
+    </lst>
+
+    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
+    <!--
+    <lst name="spellchecker">
+      <str name="name">wordbreak</str>
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
+      <str name="field">name</str>
+      <str name="combineWords">true</str>
+      <str name="breakWords">true</str>
+      <int name="maxChanges">10</int>
+    </lst>
+    -->
+  </searchComponent>
+
+  <!-- A request handler for demonstrating the spellcheck component.
+
+       NOTE: This is purely as an example.  The whole purpose of the
+       SpellCheckComponent is to hook it into the request handler that
+       handles your normal user queries so that a separate request is
+       not needed to get suggestions.
+
+       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+       See http://wiki.apache.org/solr/SpellCheckComponent for details
+       on the request parameters.
+    -->
+  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <!-- Solr will use suggestions from both the 'default' spellchecker
+           and from the 'wordbreak' spellchecker and combine them.
+           collations (re-written queries) can include a combination of
+           corrections from both spellcheckers -->
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck">on</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.count">10</str>
+      <str name="spellcheck.alternativeTermCount">5</str>
+      <str name="spellcheck.maxResultsForSuggest">5</str>
+      <str name="spellcheck.collate">true</str>
+      <str name="spellcheck.collateExtendedResults">true</str>
+      <str name="spellcheck.maxCollationTries">10</str>
+      <str name="spellcheck.maxCollations">5</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
+  <searchComponent name="terms" class="solr.TermsComponent"/>
+
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Highlighting Component
+
+       http://wiki.apache.org/solr/HighlightingParameters
+    -->
+  <searchComponent class="solr.HighlightComponent" name="highlight">
+    <highlighting>
+      <!-- Configure the standard fragmenter -->
+      <!-- This could most likely be commented out in the "default" case -->
+      <fragmenter name="gap"
+                  default="true"
+                  class="solr.highlight.GapFragmenter">
+        <lst name="defaults">
+          <int name="hl.fragsize">100</int>
+        </lst>
+      </fragmenter>
+
+      <!-- A regular-expression-based fragmenter
+           (for sentence extraction)
+        -->
+      <fragmenter name="regex"
+                  class="solr.highlight.RegexFragmenter">
+        <lst name="defaults">
+          <!-- slightly smaller fragsizes work better because of slop -->
+          <int name="hl.fragsize">70</int>
+          <!-- allow 50% slop on fragment sizes -->
+          <float name="hl.regex.slop">0.5</float>
+          <!-- a basic sentence pattern -->
+          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
+        </lst>
+      </fragmenter>
+
+      <!-- Configure the standard formatter -->
+      <formatter name="html"
+                 default="true"
+                 class="solr.highlight.HtmlFormatter">
+        <lst name="defaults">
+          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+          <str name="hl.simple.post"><![CDATA[</em>]]></str>
+        </lst>
+      </formatter>
+
+      <!-- Configure the standard encoder -->
+      <encoder name="html"
+               class="solr.highlight.HtmlEncoder" />
+
+      <!-- Configure the standard fragListBuilder -->
+      <fragListBuilder name="simple"
+                       class="solr.highlight.SimpleFragListBuilder"/>
+
+      <!-- Configure the single fragListBuilder -->
+      <fragListBuilder name="single"
+                       class="solr.highlight.SingleFragListBuilder"/>
+
+      <!-- Configure the weighted fragListBuilder -->
+      <fragListBuilder name="weighted"
+                       default="true"
+                       class="solr.highlight.WeightedFragListBuilder"/>
+
+      <!-- default tag FragmentsBuilder -->
+      <fragmentsBuilder name="default"
+                        default="true"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <!--
+        <lst name="defaults">
+          <str name="hl.multiValuedSeparatorChar">/</str>
+        </lst>
+        -->
+      </fragmentsBuilder>
+
+      <!-- multi-colored tag FragmentsBuilder -->
+      <fragmentsBuilder name="colored"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <lst name="defaults">
+          <str name="hl.tag.pre"><![CDATA[
+               <b style="background:yellow">,<b style="background:lawgreen">,
+               <b style="background:aquamarine">,<b style="background:magenta">,
+               <b style="background:palegreen">,<b style="background:coral">,
+               <b style="background:wheat">,<b style="background:khaki">,
+               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+          <str name="hl.tag.post"><![CDATA[</b>]]></str>
+        </lst>
+      </fragmentsBuilder>
+
+      <boundaryScanner name="default"
+                       default="true"
+                       class="solr.highlight.SimpleBoundaryScanner">
+        <lst name="defaults">
+          <str name="hl.bs.maxScan">10</str>
+          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
+        </lst>
+      </boundaryScanner>
+
+      <boundaryScanner name="breakIterator"
+                       class="solr.highlight.BreakIteratorBoundaryScanner">
+        <lst name="defaults">
+          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+          <str name="hl.bs.type">WORD</str>
+          <!-- language and country are used when constructing Locale object.  -->
+          <!-- And the Locale object will be used when getting instance of BreakIterator -->
+          <str name="hl.bs.language">en</str>
+          <str name="hl.bs.country">US</str>
+        </lst>
+      </boundaryScanner>
+    </highlighting>
+  </searchComponent>
+
+  <!-- Update Processors
+
+       Chains of Update Processor Factories for dealing with Update
+       Requests can be declared, and then used by name in Update
+       Request Processors
+
+       http://wiki.apache.org/solr/UpdateRequestProcessor
+
+    -->
+
+  <!-- Add unknown fields to the schema
+
+       Field type guessing update processors that will
+       attempt to parse string-typed field values as Booleans, Longs,
+       Doubles, or Dates, and then add schema fields with the guessed
+       field types. Text content will be indexed as "text_general" as
+       well as a copy to a plain string version in *_str.
+
+       These require that the schema is both managed and mutable, by
+       declaring schemaFactory as ManagedIndexSchemaFactory, with
+       mutable specified as true.
+
+       See http://wiki.apache.org/solr/GuessingFieldTypes
+    -->
+  <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+  <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+  <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+    <str name="pattern">[^\w-\.]</str>
+    <str name="replacement">_</str>
+  </updateProcessor>
+  <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+  <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+  <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+  <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+    <arr name="format">
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+      <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+      <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+      <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+    </arr>
+  </updateProcessor>
+  <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.String</str>
+      <str name="fieldType">text_general</str>
+      <lst name="copyField">
+        <str name="dest">*_str</str>
+        <int name="maxChars">256</int>
+      </lst>
+      <!-- Use as default mapping instead of defaultFieldType -->
+      <bool name="default">true</bool>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Boolean</str>
+      <str name="fieldType">booleans</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.util.Date</str>
+      <str name="fieldType">pdates</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Long</str>
+      <str name="valueClass">java.lang.Integer</str>
+      <str name="fieldType">plongs</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Number</str>
+      <str name="fieldType">pdoubles</str>
+    </lst>
+  </updateProcessor>
+
+  <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+  <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:false}"
+           processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+    <processor class="solr.LogUpdateProcessorFactory"/>
+    <processor class="solr.DistributedUpdateProcessorFactory"/>
+    <processor class="solr.RunUpdateProcessorFactory"/>
+  </updateRequestProcessorChain>
+
+  <!-- Deduplication
+
+       An example dedup update processor that creates the "id" field
+       on the fly based on the hash code of some other fields.  This
+       example has overwriteDupes set to false since we are using the
+       id field as the signatureField and Solr will maintain
+       uniqueness based on that anyway.
+
+    -->
+  <!--
+     <updateRequestProcessorChain name="dedupe">
+       <processor class="solr.processor.SignatureUpdateProcessorFactory">
+         <bool name="enabled">true</bool>
+         <str name="signatureField">id</str>
+         <bool name="overwriteDupes">false</bool>
+         <str name="fields">name,features,cat</str>
+         <str name="signatureClass">solr.processor.Lookup3Signature</str>
+       </processor>
+       <processor class="solr.LogUpdateProcessorFactory" />
+       <processor class="solr.RunUpdateProcessorFactory" />
+     </updateRequestProcessorChain>
+    -->
+
+  <!-- Response Writers
+
+       http://wiki.apache.org/solr/QueryResponseWriter
+
+       Request responses will be written using the writer specified by
+       the 'wt' request parameter matching the name of a registered
+       writer.
+
+       The "default" writer is the default and will be used if 'wt' is
+       not specified in the request.
+    -->
+  <!-- The following response writers are implicitly configured unless
+       overridden...
+    -->
+  <!--
+     <queryResponseWriter name="xml"
+                          default="true"
+                          class="solr.XMLResponseWriter" />
+     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+    -->
+
+  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+    <!-- For the purposes of the tutorial, JSON responses are written as
+     plain text so that they are easy to read in *any* browser.
+     If you expect a MIME type of "application/json" just remove this override.
+    -->
+    <str name="content-type">text/plain; charset=UTF-8</str>
+  </queryResponseWriter>
+
+  <!-- Query Parsers
+
+       https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
+
+       Multiple QParserPlugins can be registered by name, and then
+       used in either the "defType" param for the QueryComponent (used
+       by SearchHandler) or in LocalParams
+    -->
+  <!-- example of registering a query parser -->
+  <!--
+     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+    -->
+
+  <!-- Function Parsers
+
+       http://wiki.apache.org/solr/FunctionQuery
+
+       Multiple ValueSourceParsers can be registered by name, and then
+       used as function names when using the "func" QParser.
+    -->
+  <!-- example of registering a custom function parser  -->
+  <!--
+     <valueSourceParser name="myfunc"
+                        class="com.mycompany.MyValueSourceParser" />
+    -->
+
+
+  <!-- Document Transformers
+       http://wiki.apache.org/solr/DocTransformers
+    -->
+  <!--
+     Could be something like:
+     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+       <int name="connection">jdbc://....</int>
+     </transformer>
+
+     To add a constant value to all docs, use:
+     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <int name="value">5</int>
+     </transformer>
+
+     If you want the user to still be able to change it with _value:something_ use this:
+     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <double name="defaultValue">5</double>
+     </transformer>
+
+      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
+      EditorialMarkerFactory will do exactly that:
+     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+    -->
+</config>
diff --git a/docker-compose.yml b/docker-compose.yml
index 0045ce12..7d4a4a56 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -58,6 +58,7 @@ services:
       4store-ut:
         condition: service_started
 
+
   ncbo_cron-agraph:
     <<: *app
     environment:
@@ -75,8 +76,11 @@ services:
       agraph-ut:
         condition: service_healthy
 
+
   redis-ut:
     image: redis
+    ports:
+      - 6379:6379
     healthcheck:
       test: redis-cli ping
       interval: 10s
@@ -95,9 +99,17 @@ services:
       - 4store
 
   solr-ut:
-    image: ontoportal/solr-ut:0.0.2
+    image: solr:8
+    volumes:
+      - ./test/solr/configsets:/configsets:ro
+    ports:
+      - "8983:8983"
+    command: >
+      bash -c "precreate-core term_search_core1 /configsets/term_search
+      && precreate-core prop_search_core1 /configsets/property_search
+      && solr-foreground"
     healthcheck:
-      test: ["CMD-SHELL", "curl -sf http://localhost:8983/solr/term_search_core1/admin/ping?wt=json | grep -iq '\"status\":\"OK\"}' || exit 1"]
+      test: [ "CMD-SHELL", "curl -sf http://localhost:8983/solr/term_search_core1/admin/ping?wt=json | grep -iq '\"status\":\"OK\"}' || exit 1" ]
       start_period: 3s
       interval: 10s
       timeout: 5s
@@ -107,7 +119,7 @@ services:
     image: ontoportal/mgrep:0.0.1
     platform: linux/amd64
     healthcheck:
-      test: ["CMD", "nc", "-z", "-v", "localhost", "55555"]
+      test: [ "CMD", "nc", "-z", "-v", "localhost", "55555" ]
       start_period: 3s
       interval: 10s
       timeout: 5s
@@ -124,13 +136,13 @@ services:
     # ports:
     #  - 10035:10035
     command: >
-       bash -c "/agraph/bin/agraph-control --config /agraph/etc/agraph.cfg start
-       ; agtool repos create bioportal_test
-       ; agtool users add anonymous
-       ; agtool users grant anonymous root:bioportal_test:rw
-       ; tail -f /agraph/data/agraph.log"
+      bash -c "/agraph/bin/agraph-control --config /agraph/etc/agraph.cfg start
+      ; agtool repos create bioportal_test
+      ; agtool users add anonymous
+      ; agtool users grant anonymous root:bioportal_test:rw
+      ; tail -f /agraph/data/agraph.log"
     healthcheck:
-      test: ["CMD-SHELL", "agtool storage-report bioportal_test || exit 1"]
+      test: [ "CMD-SHELL", "agtool storage-report bioportal_test || exit 1" ]
       start_period: 10s
       interval: 60s
       timeout: 5s
diff --git a/test/solr/README b/test/solr/README
new file mode 100644
index 00000000..b73bea53
--- /dev/null
+++ b/test/solr/README
@@ -0,0 +1,5 @@
+Solr configsets consists of solr config files from config/solr merged with the _default configsets
+provided by solr distribution.
+These solr configsets are used for staring up docker containers for unit testing and are in place
+until solr Schema API and Config API is adoped for configuing solr.
+
diff --git a/test/solr/configsets/_default/conf/lang/contractions_ca.txt b/test/solr/configsets/_default/conf/lang/contractions_ca.txt
new file mode 100644
index 00000000..307a85f9
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
diff --git a/test/solr/configsets/_default/conf/lang/contractions_fr.txt b/test/solr/configsets/_default/conf/lang/contractions_fr.txt
new file mode 100644
index 00000000..f1bba51b
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
diff --git a/test/solr/configsets/_default/conf/lang/contractions_ga.txt b/test/solr/configsets/_default/conf/lang/contractions_ga.txt
new file mode 100644
index 00000000..9ebe7fa3
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
diff --git a/test/solr/configsets/_default/conf/lang/contractions_it.txt b/test/solr/configsets/_default/conf/lang/contractions_it.txt
new file mode 100644
index 00000000..cac04095
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l 
+all 
+dall 
+dell 
+nell 
+sull 
+coll 
+pell 
+gl 
+agl 
+dagl 
+degl 
+negl 
+sugl 
+un 
+m 
+t 
+s 
+v 
+d
diff --git a/test/solr/configsets/_default/conf/lang/hyphenations_ga.txt b/test/solr/configsets/_default/conf/lang/hyphenations_ga.txt
new file mode 100644
index 00000000..4d2642cc
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
diff --git a/test/solr/configsets/_default/conf/lang/stemdict_nl.txt b/test/solr/configsets/_default/conf/lang/stemdict_nl.txt
new file mode 100644
index 00000000..44107297
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets	fiets
+bromfiets	bromfiets
+ei	eier
+kind	kinder
diff --git a/test/solr/configsets/_default/conf/lang/stoptags_ja.txt b/test/solr/configsets/_default/conf/lang/stoptags_ja.txt
new file mode 100644
index 00000000..71b75084
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below.  Note that comments are
+# not allowed on the same line as a stoptag.  See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+#  noun: unclassified nouns
+#名詞
+#
+#  noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+#  noun-proper: Proper nouns where the sub-classification is undefined 
+#名詞-固有名詞
+#
+#  noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+#  noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+#  noun-proper-person-misc: names that cannot be divided into surname and 
+#  given name; foreign names; names where the surname or given name is unknown.
+#  e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+#  noun-proper-person-surname: Mainly Japanese surnames.
+#  e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+#  noun-proper-person-given_name: Mainly Japanese given names.
+#  e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+#  noun-proper-organization: Names representing organizations.
+#  e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+#  noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+#  noun-proper-place-misc: Place names excluding countries.
+#  e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+#  noun-proper-place-country: Country names. 
+#  e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+#  noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+#  noun-pronoun-misc: miscellaneous pronouns: 
+#  e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+#  noun-pronoun-contraction: Spoken language contraction made by combining a 
+#  pronoun and the particle 'wa'.
+#  e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ 
+#名詞-代名詞-縮約
+#
+#  noun-adverbial: Temporal nouns such as names of days or months that behave 
+#  like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+#  e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+#  noun-verbal: Nouns that take arguments with case and can appear followed by 
+#  'suru' and related verbs (する, できる, なさる, くださる)
+#  e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+#  noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+#  e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+#  noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+#  e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+#  noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+#  noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that 
+#  attach to the base form of inflectional words, words that cannot be classified 
+#  into any of the other categories below. This category includes indefinite nouns.
+#  e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第, 
+#       順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み, 
+#       拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+#       わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+#  noun-affix-adverbial: noun affixes that that can behave as adverbs.
+#  e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ, 
+#       上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか, 
+#       最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所, 
+#       とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま, 
+#       儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+#  noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars 
+#  with the stem よう(だ) ("you(da)").
+#  e.g.  よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#  
+#  noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+#  connection form な (aux "da").
+#  e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+#  noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+#  noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is 
+#  treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base 
+#  form of inflectional words.
+#  e.g. そう
+#名詞-特殊-助動詞語幹
+#
+#  noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+#  noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect 
+#  to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+#  any of the other categories below. In general, this category is more inclusive than 
+#  接尾語 ("suffix") and is usually the last element in a compound noun.
+#  e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+#       よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+#  noun-suffix-person: Suffixes that form nouns and attach to person names more often
+#  than other nouns.
+#  e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+#  noun-suffix-place: Suffixes that form nouns and attach to place names more often 
+#  than other nouns.
+#  e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+#  noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that 
+#  can appear before スル ("suru").
+#  e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+#  noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions, 
+#  is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the 
+#  conjunctive form of inflectional words.
+#  e.g. そう
+#名詞-接尾-助動詞語幹
+#
+#  noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive 
+#  form of inflectional words and appear before the copula だ ("da").
+#  e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+#  noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+#  e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+#  noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category 
+#  is more inclusive than 助数詞 ("classifier") and includes common nouns that attach 
+#  to numbers.
+#  e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+#  noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+#  e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+#  noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words 
+#  together.
+#  e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+#  noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are 
+#  semantically verb-like.
+#  e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+#  noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry, 
+#  dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation") 
+#  is いわく ("iwaku").
+#名詞-引用文字列
+#
+#  noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+#  behave like an adjective.
+#  e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+#  prefix: unclassified prefixes
+#接頭詞
+#
+#  prefix-nominal: Prefixes that attach to nouns (including adjective stem forms) 
+#  excluding numerical expressions.
+#  e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+#  prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+#  in conjunctive form followed by なる/なさる/くださる.
+#  e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+#  prefix-adjectival: Prefixes that attach to adjectives.
+#  e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+#  prefix-numerical: Prefixes that attach to numerical expressions.
+#  e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+#  verb: unclassified verbs
+#動詞
+#
+#  verb-main:
+#動詞-自立
+#
+#  verb-auxiliary:
+#動詞-非自立
+#
+#  verb-suffix:
+#動詞-接尾
+#
+#####
+#  adjective: unclassified adjectives
+#形容詞
+#
+#  adjective-main:
+#形容詞-自立
+#
+#  adjective-auxiliary:
+#形容詞-非自立
+#
+#  adjective-suffix:
+#形容詞-接尾
+#
+#####
+#  adverb: unclassified adverbs
+#副詞
+#
+#  adverb-misc: Words that can be segmented into one unit and where adnominal 
+#  modification is not possible.
+#  e.g. あいかわらず, 多分
+#副詞-一般
+#
+#  adverb-particle_conjunction: Adverbs that can be followed by の, は, に, 
+#  な, する, だ, etc.
+#  e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+#  adnominal: Words that only have noun-modifying forms.
+#  e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう, 
+#       どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした, 
+#       「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+#  conjunction: Conjunctions that can occur independently.
+#  e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+#  particle: unclassified particles.
+助詞
+#
+#  particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+#  particle-case-misc: Case particles.
+#  e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+#  particle-case-quote: the "to" that appears after nouns, a person’s speech, 
+#  quotation marks, expressions of decisions from a meeting, reasons, judgements,
+#  conjectures, etc.
+#  e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+#  particle-case-compound: Compounds of particles and verbs that mainly behave 
+#  like case particles.
+#  e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+#       にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける, 
+#       にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し, 
+#       に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして, 
+#       に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+#       にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る, 
+#       にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+#       って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+#  particle-conjunctive:
+#  e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども, 
+#       ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/, 
+#       (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+#  particle-dependency:
+#  e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+#  particle-adverbial:
+#  e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/, 
+#       (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+#       (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに, 
+#       (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+#       ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+#  particle-interjective: particles with interjective grammatical roles.
+#  e.g. (松島) や
+助詞-間投助詞
+#
+#  particle-coordinate:
+#  e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+#  particle-final:
+#  e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ, 
+#       ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+#  particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is 
+#  adverbial, conjunctive, or sentence final. For example:
+#       (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+#       (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+#           「(祈りが届いたせい) か (, 試験に合格した.)」
+#       (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+#  e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+#  particle-adnominalizer: The "no" that attaches to nouns and modifies 
+#  non-inflectional words.
+助詞-連体化
+#
+#  particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs 
+#  that are giongo, giseigo, or gitaigo.
+#  e.g. に, と
+助詞-副詞化
+#
+#  particle-special: A particle that does not fit into one of the above classifications. 
+#  This includes particles that are used in Tanka, Haiku, and other poetry.
+#  e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+#  auxiliary-verb:
+助動詞
+#
+#####
+#  interjection: Greetings and other exclamations.
+#  e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます, 
+#       いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+#  symbol: unclassified Symbols.
+記号
+#
+#  symbol-misc: A general symbol not in one of the categories below.
+#  e.g. [○◎@$〒→+]
+記号-一般
+#
+#  symbol-comma: Commas
+#  e.g. [,、]
+記号-読点
+#
+#  symbol-period: Periods and full stops.
+#  e.g. [.．。]
+記号-句点
+#
+#  symbol-space: Full-width whitespace.
+記号-空白
+#
+#  symbol-open_bracket:
+#  e.g. [({‘“『【]
+記号-括弧開
+#
+#  symbol-close_bracket:
+#  e.g. [)}’”』」】]
+記号-括弧閉
+#
+#  symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+#  other: unclassified other
+#その他
+#
+#  other-interjection: Words that are hard to classify as noun-suffixes or 
+#  sentence-final particles.
+#  e.g. (だ)ァ
+その他-間投
+#
+#####
+#  filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+#  e.g. あの, うんと, えと
+フィラー
+#
+#####
+#  non-verbal: non-verbal sound.
+非言語音
+#
+#####
+#  fragment:
+#語断片
+#
+#####
+#  unknown: unknown part of speech.
+#未知語
+#
+##### End of file
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ar.txt b/test/solr/configsets/_default/conf/lang/stopwords_ar.txt
new file mode 100644
index 00000000..046829db
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some 
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_bg.txt b/test/solr/configsets/_default/conf/lang/stopwords_bg.txt
new file mode 100644
index 00000000..1ae4ba2a
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ca.txt b/test/solr/configsets/_default/conf/lang/stopwords_ca.txt
new file mode 100644
index 00000000..3da65dea
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi 
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc 
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant 
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu 
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son 
+són
+sons 
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_cz.txt b/test/solr/configsets/_default/conf/lang/stopwords_cz.txt
new file mode 100644
index 00000000..53c6097d
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_da.txt b/test/solr/configsets/_default/conf/lang/stopwords_da.txt
new file mode 100644
index 00000000..42e6145b
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og           | and
+i            | in
+jeg          | I
+det          | that (dem. pronoun)/it (pers. pronoun)
+at           | that (in front of a sentence)/to (with infinitive)
+en           | a/an
+den          | it (pers. pronoun)/that (dem. pronoun)
+til          | to/at/for/until/against/by/of/into, more
+er           | present tense of "to be"
+som          | who, as
+på           | on/upon/in/on/at/to/after/of/with/for, on
+de           | they
+med          | with/by/in, along
+han          | he
+af           | of/by/from/off/for/in/with/on, off
+for          | at/for/to/from/by/of/ago, in front/before, because
+ikke         | not
+der          | who/which, there/those
+var          | past tense of "to be"
+mig          | me/myself
+sig          | oneself/himself/herself/itself/themselves
+men          | but
+et           | a/an/one, one (number), someone/somebody/one
+har          | present tense of "to have"
+om           | round/about/for/in/a, about/around/down, if
+vi           | we
+min          | my
+havde        | past tense of "to have"
+ham          | him
+hun          | she
+nu           | now
+over         | over/above/across/by/beyond/past/on/about, over/past
+da           | then, when/as/since
+fra          | from/off/since, off, since
+du           | you
+ud           | out
+sin          | his/her/its/one's
+dem          | them
+os           | us/ourselves
+op           | up
+man          | you/one
+hans         | his
+hvor         | where
+eller        | or
+hvad         | what
+skal         | must/shall etc.
+selv         | myself/youself/herself/ourselves etc., even
+her          | here
+alle         | all/everyone/everybody etc.
+vil          | will (verb)
+blev         | past tense of "to stay/to remain/to get/to become"
+kunne        | could
+ind          | in
+når          | when
+være         | present tense of "to be"
+dog          | however/yet/after all
+noget        | something
+ville        | would
+jo           | you know/you see (adv), yes
+deres        | their/theirs
+efter        | after/behind/according to/for/by/from, later/afterwards
+ned          | down
+skulle       | should
+denne        | this
+end          | than
+dette        | this
+mit          | my/mine
+også         | also
+under        | under/beneath/below/during, below/underneath
+have         | have
+dig          | you
+anden        | other
+hende        | her
+mine         | my
+alt          | everything
+meget        | much/very, plenty of
+sit          | his, her, its, one's
+sine         | his, her, its, one's
+vor          | our
+mod          | against
+disse        | these
+hvis         | if
+din          | your/yours
+nogle        | some
+hos          | by/at
+blive        | be/become
+mange        | many
+ad           | by/through
+bliver       | present tense of "to be/to become"
+hendes       | her/hers
+været        | be
+thi          | for (conj)
+jer          | you
+sådan        | such, like this/like that
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_de.txt b/test/solr/configsets/_default/conf/lang/stopwords_de.txt
new file mode 100644
index 00000000..86525e7a
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber           |  but
+
+alle           |  all
+allem
+allen
+aller
+alles
+
+als            |  than, as
+also           |  so
+am             |  an + dem
+an             |  at
+
+ander          |  other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch           |  also
+auf            |  on
+aus            |  out of
+bei            |  by
+bin            |  am
+bis            |  until
+bist           |  art
+da             |  there
+damit          |  with it
+dann           |  then
+
+der            |  the
+den
+des
+dem
+die
+das
+
+daß            |  that
+
+derselbe       |  the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu           |  to that
+
+dein           |  thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn           |  because
+
+derer          |  of those
+dessen         |  of him
+
+dich           |  thee
+dir            |  to thee
+du             |  thou
+
+dies           |  this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch           |  (several meanings)
+dort           |  (over) there
+
+
+durch          |  through
+
+ein            |  a
+eine
+einem
+einen
+einer
+eines
+
+einig          |  some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal         |  once
+
+er             |  he
+ihn            |  him
+ihm            |  to him
+
+es             |  it
+etwas          |  something
+
+euer           |  your
+eure
+eurem
+euren
+eurer
+eures
+
+für            |  for
+gegen          |  towards
+gewesen        |  p.p. of sein
+hab            |  have
+habe           |  have
+haben          |  have
+hat            |  has
+hatte          |  had
+hatten         |  had
+hier           |  here
+hin            |  there
+hinter         |  behind
+
+ich            |  I
+mich           |  me
+mir            |  to me
+
+
+ihr            |  you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch           |  to you
+
+im             |  in + dem
+in             |  in
+indem          |  while
+ins            |  in + das
+ist            |  is
+
+jede           |  each, every
+jedem
+jeden
+jeder
+jedes
+
+jene           |  that
+jenem
+jenen
+jener
+jenes
+
+jetzt          |  now
+kann           |  can
+
+kein           |  no
+keine
+keinem
+keinen
+keiner
+keines
+
+können         |  can
+könnte         |  could
+machen         |  do
+man            |  one
+
+manche         |  some, many a
+manchem
+manchen
+mancher
+manches
+
+mein           |  my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit            |  with
+muss           |  must
+musste         |  had to
+nach           |  to(wards)
+nicht          |  not
+nichts         |  nothing
+noch           |  still, yet
+nun            |  now
+nur            |  only
+ob             |  whether
+oder           |  or
+ohne           |  without
+sehr           |  very
+
+sein           |  his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst         |  self
+sich           |  herself
+
+sie            |  they, she
+ihnen          |  to them
+
+sind           |  are
+so             |  so
+
+solche         |  such
+solchem
+solchen
+solcher
+solches
+
+soll           |  shall
+sollte         |  should
+sondern        |  but
+sonst          |  else
+über           |  over
+um             |  about, around
+und            |  and
+
+uns            |  us
+unse
+unsem
+unsen
+unser
+unses
+
+unter          |  under
+viel           |  much
+vom            |  von + dem
+von            |  from
+vor            |  before
+während        |  while
+war            |  was
+waren          |  were
+warst          |  wast
+was            |  what
+weg            |  away, off
+weil           |  because
+weiter         |  further
+
+welche         |  which
+welchem
+welchen
+welcher
+welches
+
+wenn           |  when
+werde          |  will
+werden         |  will
+wie            |  how
+wieder         |  again
+will           |  want
+wir            |  we
+wird           |  will
+wirst          |  willst
+wo             |  where
+wollen         |  want
+wollte         |  wanted
+würde          |  would
+würden         |  would
+zu             |  to
+zum            |  zu + dem
+zur            |  zu + der
+zwar           |  indeed
+zwischen       |  between
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_el.txt b/test/solr/configsets/_default/conf/lang/stopwords_el.txt
new file mode 100644
index 00000000..232681f5
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς' 
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και 
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_en.txt b/test/solr/configsets/_default/conf/lang/stopwords_en.txt
new file mode 100644
index 00000000..2c164c0b
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_es.txt b/test/solr/configsets/_default/conf/lang/stopwords_es.txt
new file mode 100644
index 00000000..487d78c8
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  from, of
+la             |  the, her
+que            |  who, that
+el             |  the
+en             |  in
+y              |  and
+a              |  to
+los            |  the, them
+del            |  de + el
+se             |  himself, from him etc
+las            |  the, them
+por            |  for, by, etc
+un             |  a
+para           |  for
+con            |  with
+no             |  no
+una            |  a
+su             |  his, her
+al             |  a + el
+  | es         from SER
+lo             |  him
+como           |  how
+más            |  more
+pero           |  pero
+sus            |  su plural
+le             |  to him, her
+ya             |  already
+o              |  or
+  | fue        from SER
+este           |  this
+  | ha         from HABER
+sí             |  himself etc
+porque         |  because
+esta           |  this
+  | son        from SER
+entre          |  between
+  | está     from ESTAR
+cuando         |  when
+muy            |  very
+sin            |  without
+sobre          |  on
+  | ser        from SER
+  | tiene      from TENER
+también        |  also
+me             |  me
+hasta          |  until
+hay            |  there is/are
+donde          |  where
+  | han        from HABER
+quien          |  whom, that
+  | están      from ESTAR
+  | estado     from ESTAR
+desde          |  from
+todo           |  all
+nos            |  us
+durante        |  during
+  | estados    from ESTAR
+todos          |  all
+uno            |  a
+les            |  to them
+ni             |  nor
+contra         |  against
+otros          |  other
+  | fueron     from SER
+ese            |  that
+eso            |  that
+  | había      from HABER
+ante           |  before
+ellos          |  they
+e              |  and (variant of y)
+esto           |  this
+mí             |  me
+antes          |  before
+algunos        |  some
+qué            |  what?
+unos           |  a
+yo             |  I
+otro           |  other
+otras          |  other
+otra           |  other
+él             |  he
+tanto          |  so much, many
+esa            |  that
+estos          |  these
+mucho          |  much, many
+quienes        |  who
+nada           |  nothing
+muchos         |  many
+cual           |  who
+  | sea        from SER
+poco           |  few
+ella           |  she
+estar          |  to be
+  | haber      from HABER
+estas          |  these
+  | estaba     from ESTAR
+  | estamos    from ESTAR
+algunas        |  some
+algo           |  something
+nosotros       |  we
+
+      | other forms
+
+mi             |  me
+mis            |  mi plural
+tú             |  thou
+te             |  thee
+ti             |  thee
+tu             |  thy
+tus            |  tu plural
+ellas          |  they
+nosotras       |  we
+vosotros       |  you
+vosotras       |  you
+os             |  you
+mío            |  mine
+mía            |
+míos           |
+mías           |
+tuyo           |  thine
+tuya           |
+tuyos          |
+tuyas          |
+suyo           |  his, hers, theirs
+suya           |
+suyos          |
+suyas          |
+nuestro        |  ours
+nuestra        |
+nuestros       |
+nuestras       |
+vuestro        |  yours
+vuestra        |
+vuestros       |
+vuestras       |
+esos           |  those
+esas           |  those
+
+               | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+               | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+               | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+  |  sed also means 'thirst'
+
+               | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_et.txt b/test/solr/configsets/_default/conf/lang/stopwords_et.txt
new file mode 100644
index 00000000..1b06a134
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_et.txt
@@ -0,0 +1,1603 @@
+# Estonian stopwords list
+all
+alla
+allapoole
+allpool
+alt
+altpoolt
+eel
+eespool
+enne
+hommikupoole
+hoolimata
+ilma
+kaudu
+keset
+kesk
+kohe
+koos
+kuhupoole
+kuni
+kuspool
+kustpoolt
+kõige
+käsikäes
+lappi
+ligi
+läbi
+mööda
+paitsi
+peale
+pealepoole
+pealpool
+pealt
+pealtpoolt
+piki
+pikku
+piku
+pikuti
+põiki
+pärast
+päri
+risti
+sealpool
+sealtpoolt
+seespool
+seltsis
+siiapoole
+siinpool
+siitpoolt
+sinnapoole
+sissepoole
+taga
+tagantpoolt
+tagapidi
+tagapool
+taha
+tahapoole
+teispool
+teispoole
+tänu
+tükkis
+vaatamata
+vastu
+väljapoole
+väljaspool
+väljastpoolt
+õhtupoole
+ühes
+ühestükis
+ühestükkis
+ülalpool
+ülaltpoolt
+üle
+ülespoole
+ülevalpool
+ülevaltpoolt
+ümber
+ümbert
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+lool
+läbi
+lähedal
+lähedale
+lähedalt
+man
+mant
+manu
+meelest
+mööda
+nahas
+nahka
+nahkas
+najal
+najale
+najalt
+nõjal
+nõjale
+otsa
+otsas
+otsast
+paigale
+paigu
+paiku
+peal
+peale
+pealt
+perra
+perrä
+pidi
+pihta
+piki
+pikku
+pool
+poole
+poolest
+poolt
+puhul
+puksiiris
+pähe
+päralt
+päras
+pärast
+päri
+ringi
+ringis
+risust
+saadetusel
+saadik
+saatel
+saati
+seas
+seast
+sees
+seest
+sekka
+seljataga
+seltsi
+seltsis
+seltsist
+sisse
+slepis
+suhtes
+šlepis
+taga
+tagant
+tagantotsast
+tagaotsas
+tagaselja
+tagasi
+tagast
+tagutsi
+taha
+tahaotsa
+takka
+tarvis
+tasa
+tuuri
+tuuris
+tõttu
+tükkis
+uhal
+vaatamata
+vahel
+vahele
+vahelt
+vahepeal
+vahepeale
+vahepealt
+vahetsi
+varal
+varale
+varul
+vastas
+vastast
+vastu
+veerde
+veeres
+viisi
+võidu
+võrd
+võrdki
+võrra
+võrragi
+väel
+väele
+vältel
+väärt
+väärtki
+äärde
+ääre
+ääres
+äärest
+ühes
+üle
+ümber
+ümbert
+a
+abil
+aina
+ainult
+alalt
+alates
+alati
+alles
+b
+c
+d
+e
+eales
+ealeski
+edasi
+edaspidi
+eelkõige
+eemal
+ei
+eks
+end
+enda
+enese
+ennem
+esialgu
+f
+g
+h
+hoopis
+i
+iganes
+igatahes
+igati
+iial
+iialgi
+ikka
+ikkagi
+ilmaski
+iseenda
+iseenese
+iseenesest
+isegi
+j
+jah
+ju
+juba
+juhul
+just
+järelikult
+k
+ka
+kah
+kas
+kasvõi
+keda
+kestahes
+kogu
+koguni
+kohati
+kokku
+kuhu
+kuhugi
+kuidagi
+kuidas
+kunagi
+kus
+kusagil
+kusjuures
+kuskil
+kust
+kõigepealt
+küll
+l
+liiga
+lisaks
+m
+miks
+mil
+millal
+millalgi
+mispärast
+mistahes
+mistõttu
+mitte
+muide
+muidu
+muidugi
+muist
+mujal
+mujale
+mujalt
+mõlemad
+mõnda
+mõne
+mõnikord
+n
+nii
+niikaua
+niimoodi
+niipaljuke
+niisama
+niisiis
+niivõrd
+nõnda
+nüüd
+o
+omaette
+omakorda
+omavahel
+ometi
+p
+palju
+paljuke
+palju-palju
+peaaegu
+peagi
+peamiselt
+pigem
+pisut
+praegu
+päris
+r
+rohkem
+s
+samas
+samuti
+seal
+sealt
+sedakorda
+sedapuhku
+seega
+seejuures
+seejärel
+seekord
+seepärast
+seetõttu
+sellepärast
+seni
+sestap
+siia
+siiani
+siin
+siinkohal
+siis
+siiski
+siit
+sinna
+suht
+š
+z
+ž
+t
+teel
+teineteise
+tõesti
+täiesti
+u
+umbes
+v
+w
+veel
+veelgi
+vist
+võibolla
+võib-olla
+väga
+vähemalt
+välja
+väljas
+väljast
+õ
+ä
+ära
+ö
+ü
+ühtlasi
+üksi
+ükskõik
+ülal
+ülale
+ülalt
+üles
+ülesse
+üleval
+ülevalt
+ülimalt
+üsna
+x
+y
+aga
+ega
+ehk
+ehkki
+elik
+ellik
+enge
+ennegu
+ent
+et
+ja
+justkui
+kui
+kuid
+kuigi
+kuivõrd
+kuna
+kuni
+kut
+mistab
+muudkui
+nagu
+nigu
+ning
+olgugi
+otsekui
+otsenagu
+selmet
+sest
+sestab
+vaid
+või
+aa
+adaa
+adjöö
+ae
+ah
+ahaa
+ahah
+ah-ah-ah
+ah-haa
+ahoi
+ai
+aidaa
+aidu-raidu
+aih
+aijeh
+aituma
+aitäh
+aitüma
+ammuu
+amps
+ampsti
+aptsih
+ass
+at
+ata
+at-at-at
+atsih
+atsihh
+auh
+bai-bai
+bingo
+braavo
+brr
+ee
+eeh
+eh
+ehee
+eheh
+eh-eh-hee
+eh-eh-ee
+ehei
+ehh
+ehhee
+einoh
+ena
+ennäe
+ennäh
+fuh
+fui
+fuih
+haa
+hah
+hahaa
+hah-hah-hah
+halleluuja
+hallo
+halloo
+hass
+hee
+heh
+he-he-hee
+hei
+heldeke(ne)
+heureka
+hihii
+hip-hip-hurraa
+hmh
+hmjah
+hoh-hoh-hoo
+hohoo
+hoi
+hollallaa
+hoo
+hoplaa
+hopp
+hops
+hopsassaa
+hopsti
+hosianna
+huh
+huidii
+huist
+hurjah
+hurjeh
+hurjoh
+hurjuh
+hurraa
+huu
+hõhõh
+hõi
+hõissa
+hõissassa
+hõk
+hõkk
+häh
+hä-hä-hää
+hüvasti
+ih-ah-haa
+ih-ih-hii
+ii-ha-ha
+issake
+issakene
+isver
+jaa-ah
+ja-ah
+jaah
+janäe
+jeeh
+jeerum
+jeever
+jessas
+jestas
+juhhei
+jumalaga
+jumalime
+jumaluke
+jumalukene
+jutas
+kaaps
+kaapsti
+kaasike
+kae
+kalps
+kalpsti
+kannäe
+kanäe
+kappadi
+kaps
+kapsti
+karkõmm
+karkäuh
+karkääks
+karkääksti
+karmauh
+karmauhti
+karnaps
+karnapsti
+karniuhti
+karpartsaki
+karpauh
+karpauhti
+karplauh
+karplauhti
+karprauh
+karprauhti
+karsumdi
+karsumm
+kartsumdi
+kartsumm
+karviuh
+karviuhti
+kaske
+kassa
+kauh
+kauhti
+keh
+keksti
+kepsti
+khe
+khm
+kih
+kiiks
+kiiksti
+kiis
+kiiss
+kikerii
+kikerikii
+kili
+kilk
+kilk-kõlk
+kilks
+kilks-kolks
+kilks-kõlks
+kill
+killadi
+killadi|-kolladi
+killadi-kõlladi
+killa-kolla
+killa-kõlla
+kill-kõll
+kimps-komps
+kipp
+kips-kõps
+kiriküüt
+kirra-kõrra
+kirr-kõrr
+kirts
+klaps
+klapsti
+klirdi
+klirr
+klonks
+klops
+klopsti
+kluk
+klu-kluu
+klõks
+klõksti
+klõmdi
+klõmm
+klõmpsti
+klõnks
+klõnksti
+klõps
+klõpsti
+kläu
+kohva-kohva
+kok
+koks
+koksti
+kolaki
+kolk
+kolks
+kolksti
+koll
+kolladi
+komp
+komps
+kompsti
+kop
+kopp
+koppadi
+kops
+kopsti
+kossu
+kotsu
+kraa
+kraak
+kraaks
+kraaps
+kraapsti
+krahh
+kraks
+kraksti
+kraps
+krapsti
+krauh
+krauhti
+kriiks
+kriiksti
+kriips
+kriips-kraaps
+kripa-krõpa
+krips-kraps
+kriuh
+kriuks
+kriuksti
+kromps
+kronk
+kronks
+krooks
+kruu
+krõks
+krõksti
+krõpa
+krõps
+krõpsti
+krõuh
+kräu
+kräuh
+kräuhti
+kräuks
+kss
+kukeleegu
+kukku
+kuku
+kulu
+kurluu
+kurnäu
+kuss
+kussu
+kõks
+kõksti
+kõldi
+kõlks
+kõlksti
+kõll
+kõmaki
+kõmdi
+kõmm
+kõmps
+kõpp
+kõps
+kõpsadi
+kõpsat
+kõpsti
+kõrr
+kõrra-kõrra
+kõss
+kõtt
+kõõksti
+kärr
+kärts
+kärtsti
+käuks
+käuksti
+kääga
+kääks
+kääksti
+köh
+köki-möki
+köksti
+laks
+laksti
+lampsti
+larts
+lartsti
+lats
+latsti
+leelo
+legoo
+lehva
+liiri-lõõri
+lika-lõka
+likat-lõkat
+limpsti
+lips
+lipsti
+lirts
+lirtsaki
+lirtsti
+lonksti
+lops
+lopsti
+lorts
+lortsti
+luks
+lups
+lupsti
+lurts
+lurtsti
+lõks
+lõksti
+lõmps
+lõmpsti
+lõnks
+lõnksti
+lärts
+lärtsti
+läts
+lätsti
+lörts
+lörtsti
+lötsti
+lööps
+lööpsti
+marss
+mats
+matsti
+mauh
+mauhti
+mh
+mhh
+mhmh
+miau
+mjaa
+mkm
+m-mh
+mnjaa
+mnjah
+moens
+mulks
+mulksti
+mull-mull
+mull-mull-mull
+muu
+muuh
+mõh
+mõmm
+mäh
+mäts
+mäu
+mää
+möh
+möh-öh-ää
+möö
+müh-müh
+mühüh
+müks
+müksti
+müraki
+mürr
+mürts
+mürtsaki
+mürtsti
+mütaku
+müta-mäta
+müta-müta
+müt-müt
+müt-müt-müt
+müts
+mütsti
+mütt
+naa
+naah
+nah
+naks
+naksti
+nanuu
+naps
+napsti
+nilpsti
+nipsti
+nirr
+niuh
+niuh-näuh
+niuhti
+noh
+noksti
+nolpsti
+nonoh
+nonoo
+nonäh
+noo
+nooh
+nooks
+norr
+nurr
+nuuts
+nõh
+nõhh
+nõka-nõka
+nõks
+nõksat-nõksat
+nõks-nõks
+nõksti
+nõõ
+nõõh
+näeh
+näh
+nälpsti
+nämm-nämm
+näpsti
+näts
+nätsti
+näu
+näuh
+näuhti
+näuks
+näuksti
+nääh
+nääks
+nühkat-nühkat
+oeh
+oh
+ohh
+ohhh
+oh-hoi
+oh-hoo
+ohoh
+oh-oh-oo
+oh-oh-hoo
+ohoi
+ohoo
+oi
+oih
+oijee
+oijeh
+oo
+ooh
+oo-oh
+oo-ohh
+oot
+ossa
+ot
+paa
+pah
+pahh
+pakaa
+pamm
+pantsti
+pardon
+pardonks
+parlartsti
+parts
+partsti
+partsumdi
+partsumm
+pastoi
+pats
+patst
+patsti
+pau
+pauh
+pauhti
+pele
+pfui
+phuh
+phuuh
+phäh
+phähh
+piiks
+piip
+piiri-pääri
+pimm
+pimm-pamm
+pimm-pomm
+pimm-põmm
+piraki
+piuks
+piu-pau
+plaks
+plaksti
+plarts
+plartsti
+plats
+platsti
+plauh
+plauhh
+plauhti
+pliks
+pliks-plaks
+plinn
+pliraki
+plirts
+plirtsti
+pliu
+pliuh
+ploks
+plotsti
+plumps
+plumpsti
+plõks
+plõksti
+plõmdi
+plõmm
+plõnn
+plärr
+plärts
+plärtsat
+plärtsti
+pläu
+pläuh
+plää
+plörtsat
+pomm
+popp
+pops
+popsti
+ports
+pot
+pots
+potsti
+pott
+praks
+praksti
+prants
+prantsaki
+prantsti
+prassai
+prauh
+prauhh
+prauhti
+priks
+priuh
+priuhh
+priuh-prauh
+proosit
+proost
+prr
+prrr
+prõks
+prõksti
+prõmdi
+prõmm
+prõntsti
+prääk
+prääks
+pst
+psst
+ptrr
+ptruu
+ptüi
+puh
+puhh
+puksti
+pumm
+pumps
+pup-pup-pup
+purts
+puuh
+põks
+põksti
+põmdi
+põmm
+põmmadi
+põnks
+põnn
+põnnadi
+põnt
+põnts
+põntsti
+põraki
+põrr
+põrra-põrra
+päh
+pähh
+päntsti
+pää
+pöörd
+püh
+raks
+raksti
+raps
+rapsti
+ratataa
+rauh
+riips
+riipsti
+riks
+riks-raks
+rips-raps
+rivitult
+robaki
+rops
+ropsaki
+ropsti
+ruik
+räntsti
+räts
+röh
+röhh
+sah
+sahh
+sahkat
+saps
+sapsti
+sauh
+sauhti
+servus
+sihkadi-sahkadi
+sihka-sahka
+sihkat-sahkat
+silks
+silk-solk
+sips
+sipsti
+sirr
+sirr-sorr
+sirts
+sirtsti
+siu
+siuh
+siuh-sauh
+siuh-säuh
+siuhti
+siuks
+siuts
+skool
+so
+soh
+solks
+solksti
+solpsti
+soo
+sooh
+so-oh
+soo-oh
+sopp
+sops
+sopsti
+sorr
+sorts
+sortsti
+so-soo
+soss
+soss-soss
+ss
+sss
+sst
+stopp
+suhkat-sahkat
+sulk
+sulks
+sulksti
+sull
+sulla-sulla
+sulpa-sulpa
+sulps
+sulpsti
+sumaki
+sumdi
+summ
+summat-summat
+sups
+supsaku
+supsti
+surts
+surtsti
+suss
+susti
+suts
+sutsti
+säh
+sähke
+särts
+särtsti
+säu
+säuh
+säuhti
+taevake
+taevakene
+takk
+tere
+terekest
+tibi-tibi
+tikk-takk
+tiks
+tilk
+tilks
+till
+tilla-talla
+till-tall
+tilulii
+tinn
+tip
+tip-tap
+tirr
+tirtsti
+tiu
+tjaa
+tjah
+tohhoh
+tohhoo
+tohoh
+tohoo
+tok
+tokk
+toks
+toksti
+tonks
+tonksti
+tota
+totsti
+tot-tot
+tprr
+tpruu
+trah
+trahh
+trallallaa
+trill
+trillallaa
+trr
+trrr
+tsah
+tsahh
+tsilk
+tsilk-tsolk
+tsirr
+tsiuh
+tskae
+tsolk
+tss
+tst
+tsst
+tsuhh
+tsuk
+tsumm
+tsurr
+tsäuh
+tšao
+tšš
+tššš
+tuk
+tuks
+turts
+turtsti
+tutki
+tutkit
+tutu-lutu
+tutulutu
+tuut
+tuutu-luutu
+tõks
+tötsti
+tümps
+uh
+uhh
+uh-huu
+uhtsa
+uhtsaa
+uhuh
+uhuu
+ui
+uih
+uih-aih
+uijah
+uijeh
+uist
+uit
+uka
+upsti
+uraa
+urjah
+urjeh
+urjoh
+urjuh
+urr
+urraa
+ust
+utu
+uu
+uuh
+vaak
+vaat
+vae
+vaeh
+vai
+vat
+vau
+vhüüt
+vidiit
+viiks
+vilks
+vilksti
+vinki-vinki
+virdi
+virr
+viu
+viudi
+viuh
+viuhti
+voeh
+voh
+vohh
+volks
+volksti
+vooh
+vops
+vopsti
+vot
+vuh
+vuhti
+vuih
+vulks
+vulksti
+vull
+vulpsti
+vups
+vupsaki
+vupsaku
+vupsti
+vurdi
+vurr
+vurra-vurra
+vurts
+vurtsti
+vutt
+võe
+võeh
+või
+võih
+võrr
+võts
+võtt
+vääks
+õe
+õits
+õk
+õkk
+õrr
+õss
+õuh
+äh
+ähh
+ähhähhää
+äh-hää
+äh-äh-hää
+äiu
+äiu-ää
+äss
+ää
+ääh
+äähh
+öh
+öhh
+ök
+üh
+eelmine
+eikeegi
+eimiski
+emb-kumb
+enam
+enim
+iga
+igasugune
+igaüks
+ise
+isesugune
+järgmine
+keegi
+kes
+kumb
+kumbki
+kõik
+meiesugune
+meietaoline
+midagi
+mihuke
+mihukene
+milletaoline
+milline
+mina
+minake
+mingi
+mingisugune
+minusugune
+minutaoline
+mis
+miski
+miskisugune
+missugune
+misuke
+mitmes
+mitmesugune
+mitu
+mitu-mitu
+mitu-setu
+muu
+mõlema
+mõnesugune
+mõni
+mõningane
+mõningas
+mäherdune
+määrane
+naasugune
+need
+nemad
+nendesugune
+nendetaoline
+nihuke
+nihukene
+niimitu
+niisamasugune
+niisugune
+nisuke
+nisukene
+oma
+omaenese
+omasugune
+omataoline
+pool
+praegune
+sama
+samasugune
+samataoline
+see
+seesama
+seesamane
+seesamune
+seesinane
+seesugune
+selline
+sihuke
+sihukene
+sina
+sinusugune
+sinutaoline
+siuke
+siukene
+säherdune
+säärane
+taoline
+teiesugune
+teine
+teistsugune
+tema
+temake
+temakene
+temasugune
+temataoline
+too
+toosama
+toosamane
+üks
+üksteise
+hakkama
+minema
+olema
+pidama
+saama
+tegema
+tulema
+võima
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_eu.txt b/test/solr/configsets/_default/conf/lang/stopwords_eu.txt
new file mode 100644
index 00000000..25f1db93
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_fa.txt b/test/solr/configsets/_default/conf/lang/stopwords_fa.txt
new file mode 100644
index 00000000..723641c6
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_fi.txt b/test/solr/configsets/_default/conf/lang/stopwords_fi.txt
new file mode 100644
index 00000000..4372c9a0
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole        | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en         | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom   Gen    Acc    Part   Iness   Elat    Illat  Adess   Ablat   Allat   Ess    Trans
+minä   minun  minut  minua  minussa minusta minuun minulla minulta minulle               | I
+sinä   sinun  sinut  sinua  sinussa sinusta sinuun sinulla sinulta sinulle               | you
+hän    hänen  hänet  häntä  hänessä hänestä häneen hänellä häneltä hänelle               | he she
+me     meidän meidät meitä  meissä  meistä  meihin meillä  meiltä  meille                | we
+te     teidän teidät teitä  teissä  teistä  teihin teillä  teiltä  teille                | you
+he     heidän heidät heitä  heissä  heistä  heihin heillä  heiltä  heille                | they
+
+tämä   tämän         tätä   tässä   tästä   tähän  tallä   tältä   tälle   tänä   täksi  | this
+tuo    tuon          tuotä  tuossa  tuosta  tuohon tuolla  tuolta  tuolle  tuona  tuoksi | that
+se     sen           sitä   siinä   siitä   siihen sillä   siltä   sille   sinä   siksi  | it
+nämä   näiden        näitä  näissä  näistä  näihin näillä  näiltä  näille  näinä  näiksi | these
+nuo    noiden        noita  noissa  noista  noihin noilla  noilta  noille  noina  noiksi | those
+ne     niiden        niitä  niissä  niistä  niihin niillä  niiltä  niille  niinä  niiksi | they
+
+kuka   kenen kenet   ketä   kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä  keiden ketkä  keitä  keissä  keistä  keihin keillä  keiltä  keille  keinä  keiksi | (pl)
+mikä   minkä minkä   mitä   missä   mistä   mihin  millä   miltä   mille   minä   miksi  | which what
+mitkä                                                                                    | (pl)
+
+joka   jonka         jota   jossa   josta   johon  jolla   jolta   jolle   jona   joksi  | who which
+jotka  joiden        joita  joissa  joista  joihin joilla  joilta  joille  joina  joiksi | (pl)
+
+| conjunctions
+
+että   | that
+ja     | and
+jos    | if
+koska  | because
+kuin   | than
+mutta  | but
+niin   | so
+sekä   | and
+sillä  | for
+tai    | or
+vaan   | but
+vai    | or
+vaikka | although
+
+
+| prepositions
+
+kanssa  | with
+mukaan  | according to
+noin    | about
+poikki  | across
+yli     | over, across
+
+| other
+
+kun    | when
+niin   | so
+nyt    | now
+itse   | self
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_fr.txt b/test/solr/configsets/_default/conf/lang/stopwords_fr.txt
new file mode 100644
index 00000000..749abae6
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au             |  a + le
+aux            |  a + les
+avec           |  with
+ce             |  this
+ces            |  these
+dans           |  with
+de             |  of
+des            |  de + les
+du             |  de + le
+elle           |  she
+en             |  `of them' etc
+et             |  and
+eux            |  them
+il             |  he
+je             |  I
+la             |  the
+le             |  the
+leur           |  their
+lui            |  him
+ma             |  my (fem)
+mais           |  but
+me             |  me
+même           |  same; as in moi-même (myself) etc
+mes            |  me (pl)
+moi            |  me
+mon            |  my (masc)
+ne             |  not
+nos            |  our (pl)
+notre          |  our
+nous           |  we
+on             |  one
+ou             |  where
+par            |  by
+pas            |  not
+pour           |  for
+qu             |  que before vowel
+que            |  that
+qui            |  who
+sa             |  his, her (fem)
+se             |  oneself
+ses            |  his (pl)
+son            |  his, her (masc)
+sur            |  on
+ta             |  thy (fem)
+te             |  thee
+tes            |  thy (pl)
+toi            |  thee
+ton            |  thy (masc)
+tu             |  thou
+un             |  a
+une            |  a
+vos            |  your (pl)
+votre          |  your
+vous           |  you
+
+               |  single letter forms
+
+c              |  c'
+d              |  d'
+j              |  j'
+l              |  l'
+à              |  to, at
+m              |  m'
+n              |  n'
+s              |  s'
+t              |  t'
+y              |  there
+
+               | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+               | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+               | Later additions (from Jean-Christophe Deschamps)
+ceci           |  this
+cela           |  that
+celà           |  that
+cet            |  this
+cette          |  this
+ici            |  here
+ils            |  they
+les            |  the (pl)
+leurs          |  their (pl)
+quel           |  which
+quels          |  which
+quelle         |  which
+quelles        |  which
+sans           |  without
+soi            |  oneself
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ga.txt b/test/solr/configsets/_default/conf/lang/stopwords_ga.txt
new file mode 100644
index 00000000..9ff88d74
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_gl.txt b/test/solr/configsets/_default/conf/lang/stopwords_gl.txt
new file mode 100644
index 00000000..d8760b12
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_hi.txt b/test/solr/configsets/_default/conf/lang/stopwords_hi.txt
new file mode 100644
index 00000000..86286bb0
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer 
+# for spelling variation (see section below), such that it can be used whether or 
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well. 
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन 
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर  
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह 
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह 
+वहाँ
+वहीं
+वाले
+वुह 
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_hu.txt b/test/solr/configsets/_default/conf/lang/stopwords_hu.txt
new file mode 100644
index 00000000..37526da8
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_hy.txt b/test/solr/configsets/_default/conf/lang/stopwords_hy.txt
new file mode 100644
index 00000000..60c1c50f
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_id.txt b/test/solr/configsets/_default/conf/lang/stopwords_id.txt
new file mode 100644
index 00000000..4617f83a
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_it.txt b/test/solr/configsets/_default/conf/lang/stopwords_it.txt
new file mode 100644
index 00000000..1219cc77
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad             |  a (to) before vowel
+al             |  a + il
+allo           |  a + lo
+ai             |  a + i
+agli           |  a + gli
+all            |  a + l'
+agl            |  a + gl'
+alla           |  a + la
+alle           |  a + le
+con            |  with
+col            |  con + il
+coi            |  con + i (forms collo, cogli etc are now very rare)
+da             |  from
+dal            |  da + il
+dallo          |  da + lo
+dai            |  da + i
+dagli          |  da + gli
+dall           |  da + l'
+dagl           |  da + gll'
+dalla          |  da + la
+dalle          |  da + le
+di             |  of
+del            |  di + il
+dello          |  di + lo
+dei            |  di + i
+degli          |  di + gli
+dell           |  di + l'
+degl           |  di + gl'
+della          |  di + la
+delle          |  di + le
+in             |  in
+nel            |  in + el
+nello          |  in + lo
+nei            |  in + i
+negli          |  in + gli
+nell           |  in + l'
+negl           |  in + gl'
+nella          |  in + la
+nelle          |  in + le
+su             |  on
+sul            |  su + il
+sullo          |  su + lo
+sui            |  su + i
+sugli          |  su + gli
+sull           |  su + l'
+sugl           |  su + gl'
+sulla          |  su + la
+sulle          |  su + le
+per            |  through, by
+tra            |  among
+contro         |  against
+io             |  I
+tu             |  thou
+lui            |  he
+lei            |  she
+noi            |  we
+voi            |  you
+loro           |  they
+mio            |  my
+mia            |
+miei           |
+mie            |
+tuo            |
+tua            |
+tuoi           |  thy
+tue            |
+suo            |
+sua            |
+suoi           |  his, her
+sue            |
+nostro         |  our
+nostra         |
+nostri         |
+nostre         |
+vostro         |  your
+vostra         |
+vostri         |
+vostre         |
+mi             |  me
+ti             |  thee
+ci             |  us, there
+vi             |  you, there
+lo             |  him, the
+la             |  her, the
+li             |  them
+le             |  them, the
+gli            |  to him, the
+ne             |  from there etc
+il             |  the
+un             |  a
+uno            |  a
+una            |  a
+ma             |  but
+ed             |  and
+se             |  if
+perché         |  why, because
+anche          |  also
+come           |  how
+dov            |  where (as dov')
+dove           |  where
+che            |  who, that
+chi            |  who
+cui            |  whom
+non            |  not
+più            |  more
+quale          |  who, that
+quanto         |  how much
+quanti         |
+quanta         |
+quante         |
+quello         |  that
+quelli         |
+quella         |
+quelle         |
+questo         |  this
+questi         |
+questa         |
+queste         |
+si             |  yes
+tutto          |  all
+tutti          |  all
+
+               |  single letter forms:
+
+a              |  at
+c              |  as c' for ce or ci
+e              |  and
+i              |  the
+l              |  as l'
+o              |  or
+
+               | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+               | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+               | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+               | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ja.txt b/test/solr/configsets/_default/conf/lang/stopwords_ja.txt
new file mode 100644
index 00000000..d4321be6
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out.  See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter.  When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner.  Change your StopFilter
+# configuration if you need case-sensitive stopping.  Lastly, note that stopping is done
+# using the same character width as the entries in this file.  Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_lv.txt b/test/solr/configsets/_default/conf/lang/stopwords_lv.txt
new file mode 100644
index 00000000..e21a23c0
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined: 
+#   pronouns, adverbs, interjections were removed
+# 
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt  
+biju 
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat 
+būšu     
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_nl.txt b/test/solr/configsets/_default/conf/lang/stopwords_nl.txt
new file mode 100644
index 00000000..47a2aeac
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de             |  the
+en             |  and
+van            |  of, from
+ik             |  I, the ego
+te             |  (1) chez, at etc, (2) to, (3) too
+dat            |  that, which
+die            |  that, those, who, which
+in             |  in, inside
+een            |  a, an, one
+hij            |  he
+het            |  the, it
+niet           |  not, nothing, naught
+zijn           |  (1) to be, being, (2) his, one's, its
+is             |  is
+was            |  (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op             |  on, upon, at, in, up, used up
+aan            |  on, upon, to (as dative)
+met            |  with, by
+als            |  like, such as, when
+voor           |  (1) before, in front of, (2) furrow
+had            |  had, past tense all persons sing. of 'hebben' (have)
+er             |  there
+maar           |  but, only
+om             |  round, about, for etc
+hem            |  him
+dan            |  then
+zou            |  should/would, past tense all persons sing. of 'zullen'
+of             |  or, whether, if
+wat            |  what, something, anything
+mijn           |  possessive and noun 'mine'
+men            |  people, 'one'
+dit            |  this
+zo             |  so, thus, in this way
+door           |  through by
+over           |  over, across
+ze             |  she, her, they, them
+zich           |  oneself
+bij            |  (1) a bee, (2) by, near, at
+ook            |  also, too
+tot            |  till, until
+je             |  you
+mij            |  me
+uit            |  out of, from
+der            |  Old Dutch form of 'van der' still found in surnames
+daar           |  (1) there, (2) because
+haar           |  (1) her, their, them, (2) hair
+naar           |  (1) unpleasant, unwell etc, (2) towards, (3) as
+heb            |  present first person sing. of 'to have'
+hoe            |  how, why
+heeft          |  present third person sing. of 'to have'
+hebben         |  'to have' and various parts thereof
+deze           |  this
+u              |  you
+want           |  (1) for, (2) mitten, (3) rigging
+nog            |  yet, still
+zal            |  'shall', first and third person sing. of verb 'zullen' (will)
+me             |  me
+zij            |  she, they
+nu             |  now
+ge             |  'thou', still used in Belgium and south Netherlands
+geen           |  none
+omdat          |  because
+iets           |  something, somewhat
+worden         |  to become, grow, get
+toch           |  yet, still
+al             |  all, every, each
+waren          |  (1) 'were' (2) to wander, (3) wares, (3)
+veel           |  much, many
+meer           |  (1) more, (2) lake
+doen           |  to do, to make
+toen           |  then, when
+moet           |  noun 'spot/mote' and present form of 'to must'
+ben            |  (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder         |  without
+kan            |  noun 'can' and present form of 'to be able'
+hun            |  their, them
+dus            |  so, consequently
+alles          |  all, everything, anything
+onder          |  under, beneath
+ja             |  yes, of course
+eens           |  once, one day
+hier           |  here
+wie            |  who
+werd           |  imperfect third person sing. of 'become'
+altijd         |  always
+doch           |  yet, but etc
+wordt          |  present third person sing. of 'become'
+wezen          |  (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen         |  to be able
+ons            |  us/our
+zelf           |  self
+tegen          |  against, towards, at
+na             |  after, near
+reeds          |  already
+wil            |  (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon            |  could; past tense of 'to be able'
+niets          |  nothing
+uw             |  your
+iemand         |  somebody
+geweest        |  been; past participle of 'be'
+andere         |  other
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_no.txt b/test/solr/configsets/_default/conf/lang/stopwords_no.txt
new file mode 100644
index 00000000..a7a2c28b
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
+
+og             | and
+i              | in
+jeg            | I
+det            | it/this/that
+at             | to (w. inf.)
+en             | a/an
+et             | a/an
+den            | it/this/that
+til            | to
+er             | is/am/are
+som            | who/that
+på             | on
+de             | they / you(formal)
+med            | with
+han            | he
+av             | of
+ikke           | not
+ikkje          | not *
+der            | there
+så             | so
+var            | was/were
+meg            | me
+seg            | you
+men            | but
+ett            | one
+har            | have
+om             | about
+vi             | we
+min            | my
+mitt           | my
+ha             | have
+hadde          | had
+hun            | she
+nå             | now
+over           | over
+da             | when/as
+ved            | by/know
+fra            | from
+du             | you
+ut             | out
+sin            | your
+dem            | them
+oss            | us
+opp            | up
+man            | you/one
+kan            | can
+hans           | his
+hvor           | where
+eller          | or
+hva            | what
+skal           | shall/must
+selv           | self (reflective)
+sjøl           | self (reflective)
+her            | here
+alle           | all
+vil            | will
+bli            | become
+ble            | became
+blei           | became *
+blitt          | have become
+kunne          | could
+inn            | in
+når            | when
+være           | be
+kom            | come
+noen           | some
+noe            | some
+ville          | would
+dere           | you
+som            | who/which/that
+deres          | their/theirs
+kun            | only/just
+ja             | yes
+etter          | after
+ned            | down
+skulle         | should
+denne          | this
+for            | for/because
+deg            | you
+si             | hers/his
+sine           | hers/his
+sitt           | hers/his
+mot            | against
+å              | to
+meget          | much
+hvorfor        | why
+dette          | this
+disse          | these/those
+uten           | without
+hvordan        | how
+ingen          | none
+din            | your
+ditt           | your
+blir           | become
+samme          | same
+hvilken        | which
+hvilke         | which (plural)
+sånn           | such a
+inni           | inside/within
+mellom         | between
+vår            | our
+hver           | each
+hvem           | who
+vors           | us/ours
+hvis           | whose
+både           | both
+bare           | only/just
+enn            | than
+fordi          | as/because
+før            | before
+mange          | many
+også           | also
+slik           | just
+vært           | been
+være           | to be
+båe            | both *
+begge          | both
+siden          | since
+dykk           | your *
+dykkar         | yours *
+dei            | they *
+deira          | them *
+deires         | theirs *
+deim           | them *
+di             | your (fem.) *
+då             | as/when *
+eg             | I *
+ein            | a/an *
+eit            | a/an *
+eitt           | a/an *
+elles          | or *
+honom          | he *
+hjå            | at *
+ho             | she *
+hoe            | she *
+henne          | her
+hennar         | her/hers
+hennes         | hers
+hoss           | how *
+hossen         | how *
+ikkje          | not *
+ingi           | noone *
+inkje          | noone *
+korleis        | how *
+korso          | how *
+kva            | what/which *
+kvar           | where *
+kvarhelst      | where *
+kven           | who/whom *
+kvi            | why *
+kvifor         | why *
+me             | we *
+medan          | while *
+mi             | my *
+mine           | my *
+mykje          | much *
+no             | now *
+nokon          | some (masc./neut.) *
+noka           | some (fem.) *
+nokor          | some *
+noko           | some *
+nokre          | some *
+si             | his/hers *
+sia            | since *
+sidan          | since *
+so             | so *
+somt           | some *
+somme          | some *
+um             | about*
+upp            | up *
+vere           | be *
+vore           | was *
+verte          | become *
+vort           | become *
+varte          | became *
+vart           | became *
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_pt.txt b/test/solr/configsets/_default/conf/lang/stopwords_pt.txt
new file mode 100644
index 00000000..acfeb01a
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  of, from
+a              |  the; to, at; her
+o              |  the; him
+que            |  who, that
+e              |  and
+do             |  de + o
+da             |  de + a
+em             |  in
+um             |  a
+para           |  for
+  | é          from SER
+com            |  with
+não            |  not, no
+uma            |  a
+os             |  the; them
+no             |  em + o
+se             |  himself etc
+na             |  em + a
+por            |  for
+mais           |  more
+as             |  the; them
+dos            |  de + os
+como           |  as, like
+mas            |  but
+  | foi        from SER
+ao             |  a + o
+ele            |  he
+das            |  de + as
+  | tem        from TER
+à              |  a + a
+seu            |  his
+sua            |  her
+ou             |  or
+  | ser        from SER
+quando         |  when
+muito          |  much
+  | há         from HAV
+nos            |  em + os; us
+já             |  already, now
+  | está       from EST
+eu             |  I
+também         |  also
+só             |  only, just
+pelo           |  per + o
+pela           |  per + a
+até            |  up to
+isso           |  that
+ela            |  he
+entre          |  between
+  | era        from SER
+depois         |  after
+sem            |  without
+mesmo          |  same
+aos            |  a + os
+  | ter        from TER
+seus           |  his
+quem           |  whom
+nas            |  em + as
+me             |  me
+esse           |  that
+eles           |  they
+  | estão      from EST
+você           |  you
+  | tinha      from TER
+  | foram      from SER
+essa           |  that
+num            |  em + um
+nem            |  nor
+suas           |  her
+meu            |  my
+às             |  a + as
+minha          |  my
+  | têm        from TER
+numa           |  em + uma
+pelos          |  per + os
+elas           |  they
+  | havia      from HAV
+  | seja       from SER
+qual           |  which
+  | será       from SER
+nós            |  we
+  | tenho      from TER
+lhe            |  to him, her
+deles          |  of them
+essas          |  those
+esses          |  those
+pelas          |  per + as
+este           |  this
+  | fosse      from SER
+dele           |  of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu             |  thou
+te             |  thee
+vocês          |  you (plural)
+vos            |  you
+lhes           |  to them
+meus           |  my
+minhas
+teu            |  thy
+tua
+teus
+tuas
+nosso          | our
+nossa
+nossos
+nossas
+
+dela           |  of her
+delas          |  of them
+
+esta           |  this
+estes          |  these
+estas          |  these
+aquele         |  that
+aquela         |  that
+aqueles        |  those
+aquelas        |  those
+isto           |  this
+aquilo         |  that
+
+               | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+               | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+               | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+               | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ro.txt b/test/solr/configsets/_default/conf/lang/stopwords_ro.txt
new file mode 100644
index 00000000..4fdee90a
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în 
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_ru.txt b/test/solr/configsets/_default/conf/lang/stopwords_ru.txt
new file mode 100644
index 00000000..55271400
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и              | and
+в              | in/into
+во             | alternative form
+не             | not
+что            | what/that
+он             | he
+на             | on/onto
+я              | i
+с              | from
+со             | alternative form
+как            | how
+а              | milder form of `no' (but)
+то             | conjunction and form of `that'
+все            | all
+она            | she
+так            | so, thus
+его            | him
+но             | but
+да             | yes/and
+ты             | thou
+к              | towards, by
+у              | around, chez
+же             | intensifier particle
+вы             | you
+за             | beyond, behind
+бы             | conditional/subj. particle
+по             | up to, along
+только         | only
+ее             | her
+мне            | to me
+было           | it was
+вот            | here is/are, particle
+от             | away from
+меня           | me
+еще            | still, yet, more
+нет            | no, there isnt/arent
+о              | about
+из             | out of
+ему            | to him
+теперь         | now
+когда          | when
+даже           | even
+ну             | so, well
+вдруг          | suddenly
+ли             | interrogative particle
+если           | if
+уже            | already, but homonym of `narrower'
+или            | or
+ни             | neither
+быть           | to be
+был            | he was
+него           | prepositional form of его
+до             | up to
+вас            | you accusative
+нибудь         | indef. suffix preceded by hyphen
+опять          | again
+уж             | already, but homonym of `adder'
+вам            | to you
+сказал         | he said
+ведь           | particle `after all'
+там            | there
+потом          | then
+себя           | oneself
+ничего         | nothing
+ей             | to her
+может          | usually with `быть' as `maybe'
+они            | they
+тут            | here
+где            | where
+есть           | there is/are
+надо           | got to, must
+ней            | prepositional form of  ей
+для            | for
+мы             | we
+тебя           | thee
+их             | them, their
+чем            | than
+была           | she was
+сам            | self
+чтоб           | in order to
+без            | without
+будто          | as if
+человек        | man, person, one
+чего           | genitive form of `what'
+раз            | once
+тоже           | also
+себе           | to oneself
+под            | beneath
+жизнь          | life
+будет          | will be
+ж              | short form of intensifer particle `же'
+тогда          | then
+кто            | who
+этот           | this
+говорил        | was saying
+того           | genitive form of `that'
+потому         | for that reason
+этого          | genitive form of `this'
+какой          | which
+совсем         | altogether
+ним            | prepositional form of `его', `они'
+здесь          | here
+этом           | prepositional form of `этот'
+один           | one
+почти          | almost
+мой            | my
+тем            | instrumental/dative plural of `тот', `то'
+чтобы          | full form of `in order that'
+нее            | her (acc.)
+кажется        | it seems
+сейчас         | now
+были           | they were
+куда           | where to
+зачем          | why
+сказать        | to say
+всех           | all (acc., gen. preposn. plural)
+никогда        | never
+сегодня        | today
+можно          | possible, one can
+при            | by
+наконец        | finally
+два            | two
+об             | alternative form of `о', about
+другой         | another
+хоть           | even
+после          | after
+над            | above
+больше         | more
+тот            | that one (masc.)
+через          | across, in
+эти            | these
+нас            | us
+про            | about
+всего          | in all, only, of all
+них            | prepositional form of `они' (they)
+какая          | which, feminine
+много          | lots
+разве          | interrogative particle
+сказала        | she said
+три            | three
+эту            | this, acc. fem. sing.
+моя            | my, feminine
+впрочем        | moreover, besides
+хорошо         | good
+свою           | ones own, acc. fem. sing.
+этой           | oblique form of `эта', fem. `this'
+перед          | in front of
+иногда         | sometimes
+лучше          | better
+чуть           | a little
+том            | preposn. form of `that one'
+нельзя         | one must not
+такой          | such a one
+им             | to them
+более          | more
+всегда         | always
+конечно        | of course
+всю            | acc. fem. sing of `all'
+между          | between
+
+
+  | b: some paradigms
+  |
+  | personal pronouns
+  |
+  | я  меня  мне  мной  [мною]
+  | ты  тебя  тебе  тобой  [тобою]
+  | он  его  ему  им  [него, нему, ним]
+  | она  ее  эи  ею  [нее, нэи, нею]
+  | оно  его  ему  им  [него, нему, ним]
+  |
+  | мы  нас  нам  нами
+  | вы  вас  вам  вами
+  | они  их  им  ими  [них, ним, ними]
+  |
+  |   себя  себе  собой   [собою]
+  |
+  | demonstrative pronouns: этот (this), тот (that)
+  |
+  | этот  эта  это  эти
+  | этого  эты  это  эти
+  | этого  этой  этого  этих
+  | этому  этой  этому  этим
+  | этим  этой  этим  [этою]  этими
+  | этом  этой  этом  этих
+  |
+  | тот  та  то  те
+  | того  ту  то  те
+  | того  той  того  тех
+  | тому  той  тому  тем
+  | тем  той  тем  [тою]  теми
+  | том  той  том  тех
+  |
+  | determinative pronouns
+  |
+  | (a) весь (all)
+  |
+  | весь  вся  все  все
+  | всего  всю  все  все
+  | всего  всей  всего  всех
+  | всему  всей  всему  всем
+  | всем  всей  всем  [всею]  всеми
+  | всем  всей  всем  всех
+  |
+  | (b) сам (himself etc)
+  |
+  | сам  сама  само  сами
+  | самого саму  само  самих
+  | самого самой самого  самих
+  | самому самой самому  самим
+  | самим  самой  самим  [самою]  самими
+  | самом самой самом  самих
+  |
+  | stems of verbs `to be', `to have', `to do' and modal
+  |
+  | быть  бы  буд  быв  есть  суть
+  | име
+  | дел
+  | мог   мож  мочь
+  | уме
+  | хоч  хот
+  | долж
+  | можн
+  | нужн
+  | нельзя
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_sv.txt b/test/solr/configsets/_default/conf/lang/stopwords_sv.txt
new file mode 100644
index 00000000..096f87f6
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ |  så = so, but also seed. These are indicated clearly below.
+
+och            | and
+det            | it, this/that
+att            | to (with infinitive)
+i              | in, at
+en             | a
+jag            | I
+hon            | she
+som            | who, that
+han            | he
+på             | on
+den            | it, this/that
+med            | with
+var            | where, each
+sig            | him(self) etc
+för            | for
+så             | so (also: seed)
+till           | to
+är             | is
+men            | but
+ett            | a
+om             | if; around, about
+hade           | had
+de             | they, these/those
+av             | of
+icke           | not, no
+mig            | me
+du             | you
+henne          | her
+då             | then, when
+sin            | his
+nu             | now
+har            | have
+inte           | inte någon = no one
+hans           | his
+honom          | him
+skulle         | 'sake'
+hennes         | her
+där            | there
+min            | my
+man            | one (pronoun)
+ej             | nor
+vid            | at, by, on (also: vast)
+kunde          | could
+något          | some etc
+från           | from, off
+ut             | out
+när            | when
+efter          | after, behind
+upp            | up
+vi             | we
+dem            | them
+vara           | be
+vad            | what
+över           | over
+än             | than
+dig            | you
+kan            | can
+sina           | his
+här            | here
+ha             | have
+mot            | towards
+alla           | all
+under          | under (also: wonder)
+någon          | some etc
+eller          | or (else)
+allt           | all
+mycket         | much
+sedan          | since
+ju             | why
+denna          | this/that
+själv          | myself, yourself etc
+detta          | this/that
+åt             | to
+utan           | without
+varit          | was
+hur            | how
+ingen          | no
+mitt           | my
+ni             | you
+bli            | to be, become
+blev           | from bli
+oss            | us
+din            | thy
+dessa          | these/those
+några          | some etc
+deras          | their
+blir           | from bli
+mina           | my
+samma          | (the) same
+vilken         | who, that
+er             | you, your
+sådan          | such a
+vår            | our
+blivit         | from bli
+dess           | its
+inom           | within
+mellan         | between
+sådant         | such a
+varför         | why
+varje          | each
+vilka          | who, that
+ditt           | thy
+vem            | who
+vilket         | who, that
+sitta          | his
+sådana         | such a
+vart           | each
+dina           | thy
+vars           | whose
+vårt           | our
+våra           | our
+ert            | your
+era            | your
+vilkas         | whose
+
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_th.txt b/test/solr/configsets/_default/conf/lang/stopwords_th.txt
new file mode 100644
index 00000000..07f0fabe
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
diff --git a/test/solr/configsets/_default/conf/lang/stopwords_tr.txt b/test/solr/configsets/_default/conf/lang/stopwords_tr.txt
new file mode 100644
index 00000000..84d9408d
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+#   (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
diff --git a/test/solr/configsets/_default/conf/lang/userdict_ja.txt b/test/solr/configsets/_default/conf/lang/userdict_ja.txt
new file mode 100644
index 00000000..6f0368e4
--- /dev/null
+++ b/test/solr/configsets/_default/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags.  Notice that entries do
+# not have weights since they are always used when found.  This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+#  <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored.  Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
diff --git a/test/solr/configsets/_default/conf/managed-schema b/test/solr/configsets/_default/conf/managed-schema
new file mode 100644
index 00000000..e99e27e9
--- /dev/null
+++ b/test/solr/configsets/_default/conf/managed-schema
@@ -0,0 +1,1031 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+
+ For more information, on how to customize this file, please see
+ http://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+-->
+
+<schema name="default-config" version="1.6">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and 
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued 
+            by nature
+       1.1: multiValued attribute introduced, false by default 
+       1.2: omitTermFreqAndPositions attribute introduced, true by default 
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults 
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types 
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a field type from the 
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc Values is
+       recommended (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc Values will make the index
+       faster to load, more NRT-friendly and more memory-efficient. 
+       They are currently only supported by StrField, UUIDField, all 
+       *PointFields, and depending on the field type, they might require
+       the field to be single-valued, be required or have a default value
+       (check the documentation of the field type you're interested in for
+       more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.  
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This 
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this _default configset, only four fields are pre-declared:
+         id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
+         
+         Note that many dynamic fields are also defined - you can use them to specify a 
+         field's type via field naming conventions - see below.
+  
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- docValues are enabled by default for long type so we don't need to index the version field  -->
+    <field name="_version_" type="plong" indexed="false" stored="false"/>
+
+    <!-- If you don't use child/nested documents, then you should remove the next two fields:  -->
+    <!-- for nested documents (minimal; points to root document) -->
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <!-- for nested documents (relationship tracking) -->
+    <field name="_nest_path_" type="_nest_path_" /><fieldType name="_nest_path_" class="solr.NestPathField" />
+
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+    <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+         because it's very expensive to index everything twice. -->
+    <!-- <copyField source="*" dest="_text_"/> -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end.  -->
+   
+    <dynamicField name="*_i"  type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="random_*" type="random"/>
+    <dynamicField name="ignored_*" type="ignored"/>
+
+    <!-- Type used for data-driven schema, to add a string copy for each text field -->
+    <dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
+
+    <dynamicField name="*_dt"  type="pdate"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="pdate"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching.
+
+    <copyField source="sourceFieldName" dest="destinationFieldName"/>
+    -->
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+       This includes "string", "boolean", "pint", "pfloat", "plong", "pdate", "pdouble".
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!--
+      Numeric field types that index values using KD-trees.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+
+    <!-- since fields of this type are by default not stored or indexed,
+       any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+                      
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+    
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+    
+    <!-- 
+    RankFields can be used to store scoring factors to improve document ranking. They should be used
+    in combination with RankQParserPlugin.
+    (experimental)
+    --> 
+    <fieldType name="rank" class="solr.RankField"/>
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    
+    <!-- SortableTextField generaly functions exactly like TextField,
+         except that it supports, and by default uses, docValues for sorting (or faceting)
+         on the first 1024 characters of the original field values (which is configurable).
+         
+         This makes it a bit more useful then TextField in many situations, but the trade-off
+         is that it takes up more space on disk; which is why it's not used in place of TextField
+         for every fieldType in this _default schema.
+	  -->
+    <dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
+    <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
+         removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- 
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if 
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- A geospatial field type that supports multiValued and polygon shapes.
+      For more information about this and other spatial fields see:
+      http://lucene.apache.org/solr/guide/spatial-search.html
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/> 
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
+        <filter class="solr.BulgarianStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Estonian -->
+    <dynamicField name="*_txt_et" type="text_et"  indexed="true"  stored="true"/>
+    <fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
+      </analyzer>
+    </fieldType>
+    
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Korean morphological analysis -->
+    <dynamicField name="*_txt_ko" type="text_ko"  indexed="true"  stored="true"/>
+    <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
+          The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
+          It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
+
+          This dictionary was built with MeCab, it defines a format for the features adapted
+          for the Korean language.
+          
+          Nori also has a convenient user dictionary feature that allows overriding the statistical
+          model with your own entries for segmentation, part-of-speech tags and readings without a need
+          to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+          The tokenizer supports multiple schema attributes:
+            * userDictionary: User dictionary path.
+            * userDictionaryEncoding: User dictionary encoding.
+            * decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
+            * outputUnknownUnigrams: If true outputs unigrams for unknown words.
+        -->
+        <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
+        <!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
+          listing the tags to remove. By default it removes: 
+          E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
+          This is basically an equivalent to stemming.
+        -->
+        <filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
+        <!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
+        <filter class="solr.KoreanReadingFormFilterFactory" />
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but 
+       the default is fine for most applications.  
+       For more info: http://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/test/solr/configsets/_default/conf/protwords.txt b/test/solr/configsets/_default/conf/protwords.txt
new file mode 100644
index 00000000..1dfc0abe
--- /dev/null
+++ b/test/solr/configsets/_default/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
diff --git a/test/solr/configsets/_default/conf/solrconfig.xml b/test/solr/configsets/_default/conf/solrconfig.xml
new file mode 100644
index 00000000..165544a2
--- /dev/null
+++ b/test/solr/configsets/_default/conf/solrconfig.xml
@@ -0,0 +1,1295 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+     For more details about configurations options that may appear in
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+  <!-- In all configuration below, a prefix of "solr." for class names
+       is an alias that causes solr to search appropriate packages,
+       including org.apache.solr.(search|update|request|core|analysis)
+
+       You may also specify a fully qualified Java classname if you
+       have your own custom plugins.
+    -->
+
+  <!-- Controls what version of Lucene various components of Solr
+       adhere to.  Generally, you want to use the latest version to
+       get all bug fixes and improvements. It is highly recommended
+       that you fully re-index after changing this setting as it can
+       affect both how text is indexed and queried.
+  -->
+  <luceneMatchVersion>8.10.1</luceneMatchVersion>
+
+  <!-- <lib/> directives can be used to instruct Solr to load any Jars
+       identified and use them to resolve any "plugins" specified in
+       your solrconfig.xml or schema.xml (ie: Analyzers, Request
+       Handlers, etc...).
+
+       All directories and paths are resolved relative to the
+       instanceDir.
+
+       Please note that <lib/> directives are processed in the order
+       that they appear in your solrconfig.xml file, and are "stacked"
+       on top of each other when building a ClassLoader - so if you have
+       plugin jars with dependencies on other jars, the "lower level"
+       dependency jars should be loaded first.
+
+       If a "./lib" directory exists in your instanceDir, all files
+       found in it are included as if you had used the following
+       syntax...
+
+              <lib dir="./lib" />
+    -->
+
+  <!-- A 'dir' option by itself adds any files found in the directory
+       to the classpath, this is useful for including all jars in a
+       directory.
+
+       When a 'regex' is specified in addition to a 'dir', only the
+       files in that directory which completely match the regex
+       (anchored on both ends) will be included.
+
+       If a 'dir' option (with or without a regex) is used and nothing
+       is found that matches, a warning will be logged.
+
+       The example below can be used to load a solr-contrib along
+       with their external dependencies.
+    -->
+    <!-- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
+
+  <!-- an exact 'path' can be used instead of a 'dir' to specify a
+       specific jar file.  This will cause a serious error to be logged
+       if it can't be loaded.
+    -->
+  <!--
+     <lib path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
+    -->
+  <dataDir>${solr.data.dir:}</dataDir>
+
+
+  <!-- The DirectoryFactory to use for indexes.
+
+       solr.StandardDirectoryFactory is filesystem
+       based and tries to pick the best implementation for the current
+       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
+       wraps solr.StandardDirectoryFactory and caches small files in memory
+       for better NRT performance.
+
+       One can force a particular implementation via solr.MMapDirectoryFactory,
+       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+       solr.RAMDirectoryFactory is memory based and not persistent.
+    -->
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+       A "compressionMode" string element can be added to <codecFactory> to choose
+       between the existing compression modes in the default codec: "BEST_SPEED" (default)
+       or "BEST_COMPRESSION".
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Index Config - These settings control low-level behavior of indexing
+       Most example settings here show the default value, but are commented
+       out, to more easily see where customizations have been made.
+
+       Note: This replaces <indexDefaults> and <mainIndex> from older versions
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <indexConfig>
+    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+         LimitTokenCountFilterFactory in your fieldType definition. E.g.
+     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+    -->
+    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
+
+    <!-- Expert: Enabling compound file will use less files for the index,
+         using fewer file descriptors on the expense of performance decrease.
+         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+    <!-- <useCompoundFile>false</useCompoundFile> -->
+
+    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+         indexing for buffering added documents and deletions before they are
+         flushed to the Directory.
+         maxBufferedDocs sets a limit on the number of documents buffered
+         before flushing.
+         If both ramBufferSizeMB and maxBufferedDocs is set, then
+         Lucene will flush based on whichever limit is hit first.  -->
+    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+    <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+         per thread before they are flushed. When limit is exceeded, this triggers a forced
+         flush even if ramBufferSizeMB has not been exceeded.
+         This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+         exhaustion due to its internal 32 bit signed integer based memory addressing.
+         The specified value should be greater than 0 and less than 2048MB. When not specified,
+         Solr uses Lucene's default value 1945. -->
+    <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+    <!-- Expert: Merge Policy
+         The Merge Policy in Lucene controls how merging of segments is done.
+         The default since Solr/Lucene 3.3 is TieredMergePolicy.
+         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+         Even older versions of Lucene used LogDocMergePolicy.
+      -->
+    <!--
+        <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+          <int name="maxMergeAtOnce">10</int>
+          <int name="segmentsPerTier">10</int>
+          <double name="noCFSRatio">0.1</double>
+        </mergePolicyFactory>
+      -->
+
+    <!-- Expert: Merge Scheduler
+         The Merge Scheduler in Lucene controls how merges are
+         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+         can perform merges in the background using separate threads.
+         The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--
+       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+       -->
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
+    -->
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Commit Deletion Policy
+         Custom deletion policies can be specified here. The class must
+         implement org.apache.lucene.index.IndexDeletionPolicy.
+
+         The default Solr IndexDeletionPolicy implementation supports
+         deleting index commit points on number of commits, age of
+         commit point and optimized status.
+
+         The latest commit point should always be preserved regardless
+         of the criteria.
+    -->
+    <!--
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+    -->
+    <!-- The number of commit points to be kept -->
+    <!-- <str name="maxCommitsToKeep">1</str> -->
+    <!-- The number of optimized commit points to be kept -->
+    <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+    <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g.
+      -->
+    <!--
+       <str name="maxCommitAge">30MINUTES</str>
+       <str name="maxCommitAge">1DAY</str>
+    -->
+    <!--
+    </deletionPolicy>
+    -->
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting The value to true will instruct the underlying Lucene
+         IndexWriter to write its debugging info the specified file
+      -->
+    <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+  </indexConfig>
+
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.
+         "numVersionBuckets" - sets the number of buckets used to keep
+                track of max version values when checking for re-ordered
+                updates; increase this value to reduce the cost of
+                synchronizing access to version buckets during high-volume
+                indexing, this requires 8 bytes (long) * numVersionBuckets
+                of heap space per Solr core.
+    -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+    </updateLog>
+
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+    <autoCommit>
+      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+      <openSearcher>false</openSearcher>
+    </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+    <autoSoftCommit>
+      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+    </autoSoftCommit>
+
+    <!-- Update Related Event Listeners
+
+         Various IndexWriter related events can trigger Listeners to
+         take actions.
+
+         postCommit - fired after every commit or optimize command
+         postOptimize - fired after every optimize command
+      -->
+
+  </updateHandler>
+
+  <!-- IndexReaderFactory
+
+       Use the following format to specify a custom IndexReaderFactory,
+       which allows for alternate IndexReader implementations.
+
+       ** Experimental Feature **
+
+       Please note - Using a custom IndexReaderFactory may prevent
+       certain other features from working. The API to
+       IndexReaderFactory may change without warning or may even be
+       removed from future releases if the problems cannot be
+       resolved.
+
+
+       ** Features that may not work with custom IndexReaderFactory **
+
+       The ReplicationHandler assumes a disk-resident index. Using a
+       custom IndexReader implementation may cause incompatibility
+       with ReplicationHandler and may cause replication to not work
+       correctly. See SOLR-1366 for details.
+
+    -->
+  <!--
+  <indexReaderFactory name="IndexReaderFactory" class="package.class">
+    <str name="someArg">Some Value</str>
+  </indexReaderFactory >
+  -->
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <query>
+
+    <!-- Maximum number of clauses allowed when parsing a boolean query string.
+         
+         This limit only impacts boolean queries specified by a user as part of a query string,
+         and provides per-collection controls on how complex user specified boolean queries can
+         be.  Query strings that specify more clauses then this will result in an error.
+         
+         If this per-collection limit is greater then the global `maxBooleanClauses` limit
+         specified in `solr.xml`, it will have no effect, as that setting also limits the size
+         of user specified boolean queries.
+      -->
+    <maxBooleanClauses>${solr.max.booleanClauses:1024}</maxBooleanClauses>
+
+    <!-- Solr Internal Query Caches
+
+         There are four implementations of cache available for Solr:
+         LRUCache, based on a synchronized LinkedHashMap, 
+         LFUCache and FastLRUCache, based on a ConcurrentHashMap, and CaffeineCache -
+         a modern and robust cache implementation. Note that in Solr 9.0
+         only CaffeineCache will be available, other implementations are now
+         deprecated.
+
+         FastLRUCache has faster gets and slower puts in single
+         threaded operation and thus is generally faster than LRUCache
+         when the hit ratio of the cache is high (> 75%), and may be
+         faster under other scenarios on multi-cpu systems.
+         Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
+    -->
+
+    <!-- Filter Cache
+
+         Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.  When a
+         new searcher is opened, its caches may be prepopulated or
+         "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For
+         LRUCache, the autowarmed items will be the most recently
+         accessed items.
+
+         Parameters:
+           class - the SolrCache implementation LRUCache or
+               (LRUCache or FastLRUCache)
+           size - the maximum number of entries in the cache
+           initialSize - the initial capacity (number of entries) of
+               the cache.  (see java.util.HashMap)
+           autowarmCount - the number of entries to prepopulate from
+               an old cache.
+           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                      to occupy. Note that when this option is specified, the size
+                      and initialSize parameters are ignored.
+      -->
+    <filterCache size="512"
+                 initialSize="512"
+                 autowarmCount="0"/>
+
+    <!-- Query Result Cache
+
+         Caches results of searches - ordered lists of document ids
+         (DocList) based on a query, a sort, and the range of documents requested.
+         Additional supported parameter by LRUCache:
+            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                       to occupy
+      -->
+    <queryResultCache size="512"
+                      initialSize="512"
+                      autowarmCount="0"/>
+
+    <!-- Document Cache
+
+         Caches Lucene Document objects (the stored fields for each
+         document).  Since Lucene internal document ids are transient,
+         this cache will not be autowarmed.
+      -->
+    <documentCache size="512"
+                   initialSize="512"
+                   autowarmCount="0"/>
+
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+           size="10"
+           initialSize="0"
+           autowarmCount="10"
+           regenerator="solr.NoOpRegenerator" />
+
+    <!-- Field Value Cache
+
+         Cache used to hold field values that are quickly accessible
+         by document id.  The fieldValueCache is created by default
+         even if not configured here.
+      -->
+    <!--
+       <fieldValueCache size="512"
+                        autowarmCount="128"
+                        showItems="32" />
+      -->
+
+    <!-- Custom Cache
+
+         Example of a generic cache.  These caches may be accessed by
+         name through SolrIndexSearcher.getCache(),cacheLookup(), and
+         cacheInsert().  The purpose is to enable easy caching of
+         user/application level data.  The regenerator argument should
+         be specified as an implementation of solr.CacheRegenerator
+         if autowarming is desired.
+      -->
+    <!--
+       <cache name="myUserCache"
+              size="4096"
+              initialSize="1024"
+              autowarmCount="1024"
+              regenerator="com.mycompany.MyRegenerator"
+              />
+      -->
+
+
+    <!-- Lazy Field Loading
+
+         If true, stored fields that are not requested will be loaded
+         lazily.  This can result in a significant speed improvement
+         if the usual case is to not load all stored fields,
+         especially if the skipped fields are large compressed text
+         fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Use Filter For Sorted Query
+
+         A possible optimization that attempts to use a filter to
+         satisfy a search.  If the requested sort does not include
+         score, then the filterCache will be checked for a filter
+         matching the query. If found, the filter will be used as the
+         source of document ids, and then the sort will be applied to
+         that.
+
+         For most situations, this will not be useful unless you
+         frequently get the same search repeatedly with different sort
+         options, and none of them ever use "score"
+      -->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Result Window Size
+
+         An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 49 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.
+      -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache.
+      -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+  <!-- Use Filter For Sorted Query
+
+   A possible optimization that attempts to use a filter to
+   satisfy a search.  If the requested sort does not include
+   score, then the filterCache will be checked for a filter
+   matching the query. If found, the filter will be used as the
+   source of document ids, and then the sort will be applied to
+   that.
+
+   For most situations, this will not be useful unless you
+   frequently get the same search repeatedly with different sort
+   options, and none of them ever use "score"
+-->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Query Related Event Listeners
+
+         Various IndexSearcher related events can trigger Listeners to
+         take actions.
+
+         newSearcher - fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka
+         registered).  It can be used to prime certain caches to
+         prevent long request times for certain requests.
+
+         firstSearcher - fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from.
+
+
+      -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence.
+      -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+          -->
+      </arr>
+    </listener>
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+        <lst>
+          <str name="q">static firstSearcher warming in solrconfig.xml</str>
+        </lst>
+        -->
+      </arr>
+    </listener>
+
+    <!-- Use Cold Searcher
+
+         If a search request comes in and there is no current
+         registered searcher, then immediately register the still
+         warming searcher and use it.  If "false" then all requests
+         will block until the first searcher is done warming.
+      -->
+    <useColdSearcher>false</useColdSearcher>
+
+  </query>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+     Circuit Breaker Section - This section consists of configurations for
+     circuit breakers
+     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+
+    <!-- Circuit Breakers
+
+     Circuit breakers are designed to allow stability and predictable query
+     execution. They prevent operations that can take down the node and cause
+     noisy neighbour issues.
+
+     This flag is the uber control switch which controls the activation/deactivation of all circuit
+     breakers. If a circuit breaker wishes to be independently configurable,
+     they are free to add their specific configuration but need to ensure that this flag is always
+     respected - this should have veto over all independent configuration flags.
+    -->
+    <circuitBreakers enabled="true">
+
+    <!-- Memory Circuit Breaker Configuration
+
+     Specific configuration for max JVM heap usage circuit breaker. This configuration defines whether
+     the circuit breaker is enabled and the threshold percentage of maximum heap allocated beyond which queries will be rejected until the
+     current JVM usage goes below the threshold. The valid value range for this value is 50-95.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+    -->
+    <!--
+   <memBreaker enabled="true" threshold="75"/>
+    -->
+
+      <!-- CPU Circuit Breaker Configuration
+
+     Specific configuration for CPU utilization based circuit breaker. This configuration defines whether the circuit breaker is enabled
+     and the average load over the last minute at which the circuit breaker should start rejecting queries.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+    -->
+
+      <!--
+       <cpuBreaker enabled="true" threshold="75"/>
+      -->
+
+  </circuitBreakers>
+
+
+  <!-- Request Dispatcher
+
+       This section contains instructions for how the SolrDispatchFilter
+       should behave when processing requests for this SolrCore.
+
+    -->
+  <requestDispatcher>
+    <!-- Request Parsing
+
+         These settings indicate how Solr Requests may be parsed, and
+         what restrictions may be placed on the ContentStreams from
+         those requests
+
+         enableRemoteStreaming - enables use of the stream.file
+         and stream.url parameters for specifying remote streams.
+
+         multipartUploadLimitInKB - specifies the max size (in KiB) of
+         Multipart File Uploads that Solr will allow in a Request.
+
+         formdataUploadLimitInKB - specifies the max size (in KiB) of
+         form data (application/x-www-form-urlencoded) sent via
+         POST. You can use POST to pass request parameters not
+         fitting into the URL.
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
+         *** WARNING ***
+         Before enabling remote streaming, you should make sure your
+         system has authentication enabled.
+
+    <requestParsers enableRemoteStreaming="false"
+                    multipartUploadLimitInKB="-1"
+                    formdataUploadLimitInKB="-1"
+                    addHttpRequestToContext="false"/>
+      -->
+
+    <!-- HTTP Caching
+
+         Set HTTP caching related parameters (for proxy caches and clients).
+
+         The options below instruct Solr not to output any HTTP Caching
+         related headers
+      -->
+    <httpCaching never304="true" />
+    <!-- If you include a <cacheControl> directive, it will be used to
+         generate a Cache-Control header (as well as an Expires header
+         if the value contains "max-age=")
+
+         By default, no Cache-Control header is generated.
+
+         You can use the <cacheControl> option even if you have set
+         never304="true"
+      -->
+    <!--
+       <httpCaching never304="true" >
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+    <!-- To enable Solr to respond with automatically generated HTTP
+         Caching headers, and to response to Cache Validation requests
+         correctly, set the value of never304="false"
+
+         This will cause Solr to generate Last-Modified and ETag
+         headers based on the properties of the Index.
+
+         The following options can also be specified to affect the
+         values of these headers...
+
+         lastModFrom - the default value is "openTime" which means the
+         Last-Modified value (and validation against If-Modified-Since
+         requests) will all be relative to when the current Searcher
+         was opened.  You can change it to lastModFrom="dirLastMod" if
+         you want the value to exactly correspond to when the physical
+         index was last modified.
+
+         etagSeed="..." is an option you can change to force the ETag
+         header (and validation against If-None-Match requests) to be
+         different even if the index has not changed (ie: when making
+         significant changes to your config file)
+
+         (lastModifiedFrom and etagSeed are both ignored if you use
+         the never304="true" option)
+      -->
+    <!--
+       <httpCaching lastModifiedFrom="openTime"
+                    etagSeed="Solr">
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+  </requestDispatcher>
+
+  <!-- Request Handlers
+
+       http://wiki.apache.org/solr/SolrRequestHandler
+
+       Incoming queries will be dispatched to a specific handler by name
+       based on the path specified in the request.
+
+       If a Request Handler is declared with startup="lazy", then it will
+       not be initialized until the first request that uses it.
+
+    -->
+  <!-- SearchHandler
+
+       http://wiki.apache.org/solr/SearchHandler
+
+       For processing Search Queries, the primary Request Handler
+       provided with Solr is "SearchHandler" It delegates to a sequent
+       of SearchComponents (see below) and supports distributed
+       queries across multiple shards
+    -->
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <int name="rows">10</int>
+      <!-- Default search field
+         <str name="df">text</str> 
+        -->
+      <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+         <str name="wt">xml</str> 
+        -->
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+      -->
+    <!-- In this example, the param "fq=instock:true" would be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="appends">
+         <str name="fq">inStock:true</str>
+       </lst>
+      -->
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params would
+         be fixed, limiting the facets clients can use.  Faceting is
+         not turned on by default - but if the client does specify
+         facet=true in the request, these are the only facets they
+         will be able to see counts for; regardless of what other
+         facet.field or facet.query params they may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="invariants">
+         <str name="facet.field">cat</str>
+         <str name="facet.field">manu_exact</str>
+         <str name="facet.query">price:[* TO 500]</str>
+         <str name="facet.query">price:[500 TO *]</str>
+       </lst>
+      -->
+    <!-- If the default list of SearchComponents is not desired, that
+         list can either be overridden completely, or components can be
+         prepended or appended to the default list.  (see below)
+      -->
+    <!--
+       <arr name="components">
+         <str>nameOfCustomComponent1</str>
+         <str>nameOfCustomComponent2</str>
+       </arr>
+      -->
+  </requestHandler>
+
+  <!-- A request handler that returns indented JSON by default -->
+  <requestHandler name="/query" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <str name="wt">json</str>
+      <str name="indent">true</str>
+    </lst>
+  </requestHandler>
+
+  <initParams path="/update/**,/query,/select,/spell">
+    <lst name="defaults">
+      <str name="df">_text_</str>
+    </lst>
+  </initParams>
+
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
+
+       Default configuration in a requestHandler would look like:
+
+       <arr name="components">
+         <str>query</str>
+         <str>facet</str>
+         <str>mlt</str>
+         <str>highlight</str>
+         <str>stats</str>
+         <str>debug</str>
+       </arr>
+
+       If you register a searchComponent to one of the standard names,
+       that will be used instead of the default.
+
+       To insert components before or after the 'standard' components, use:
+
+       <arr name="first-components">
+         <str>myFirstComponentName</str>
+       </arr>
+
+       <arr name="last-components">
+         <str>myLastComponentName</str>
+       </arr>
+
+       NOTE: The component registered with the name "debug" will
+       always be executed after the "last-components"
+
+     -->
+
+  <!-- Spell Check
+
+       The spell check component can return a list of alternative spelling
+       suggestions.
+
+       http://wiki.apache.org/solr/SpellCheckComponent
+    -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">text_general</str>
+
+    <!-- Multiple "Spell Checkers" can be declared and used by this
+         component
+      -->
+
+    <!-- a spellchecker built from a field of the main index -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">_text_</str>
+      <str name="classname">solr.DirectSolrSpellChecker</str>
+      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+      <str name="distanceMeasure">internal</str>
+      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+      <float name="accuracy">0.5</float>
+      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+      <int name="maxEdits">2</int>
+      <!-- the minimum shared prefix when enumerating terms -->
+      <int name="minPrefix">1</int>
+      <!-- maximum number of inspections per result. -->
+      <int name="maxInspections">5</int>
+      <!-- minimum length of a query term to be considered for correction -->
+      <int name="minQueryLength">4</int>
+      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+      <float name="maxQueryFrequency">0.01</float>
+      <!-- uncomment this to require suggestions to occur in 1% of the documents
+        <float name="thresholdTokenFrequency">.01</float>
+      -->
+    </lst>
+
+    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
+    <!--
+    <lst name="spellchecker">
+      <str name="name">wordbreak</str>
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
+      <str name="field">name</str>
+      <str name="combineWords">true</str>
+      <str name="breakWords">true</str>
+      <int name="maxChanges">10</int>
+    </lst>
+    -->
+  </searchComponent>
+
+  <!-- A request handler for demonstrating the spellcheck component.
+
+       NOTE: This is purely as an example.  The whole purpose of the
+       SpellCheckComponent is to hook it into the request handler that
+       handles your normal user queries so that a separate request is
+       not needed to get suggestions.
+
+       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+       See http://wiki.apache.org/solr/SpellCheckComponent for details
+       on the request parameters.
+    -->
+  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <!-- Solr will use suggestions from both the 'default' spellchecker
+           and from the 'wordbreak' spellchecker and combine them.
+           collations (re-written queries) can include a combination of
+           corrections from both spellcheckers -->
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck">on</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.count">10</str>
+      <str name="spellcheck.alternativeTermCount">5</str>
+      <str name="spellcheck.maxResultsForSuggest">5</str>
+      <str name="spellcheck.collate">true</str>
+      <str name="spellcheck.collateExtendedResults">true</str>
+      <str name="spellcheck.maxCollationTries">10</str>
+      <str name="spellcheck.maxCollations">5</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
+  <searchComponent name="terms" class="solr.TermsComponent"/>
+
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Highlighting Component
+
+       http://wiki.apache.org/solr/HighlightingParameters
+    -->
+  <searchComponent class="solr.HighlightComponent" name="highlight">
+    <highlighting>
+      <!-- Configure the standard fragmenter -->
+      <!-- This could most likely be commented out in the "default" case -->
+      <fragmenter name="gap"
+                  default="true"
+                  class="solr.highlight.GapFragmenter">
+        <lst name="defaults">
+          <int name="hl.fragsize">100</int>
+        </lst>
+      </fragmenter>
+
+      <!-- A regular-expression-based fragmenter
+           (for sentence extraction)
+        -->
+      <fragmenter name="regex"
+                  class="solr.highlight.RegexFragmenter">
+        <lst name="defaults">
+          <!-- slightly smaller fragsizes work better because of slop -->
+          <int name="hl.fragsize">70</int>
+          <!-- allow 50% slop on fragment sizes -->
+          <float name="hl.regex.slop">0.5</float>
+          <!-- a basic sentence pattern -->
+          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
+        </lst>
+      </fragmenter>
+
+      <!-- Configure the standard formatter -->
+      <formatter name="html"
+                 default="true"
+                 class="solr.highlight.HtmlFormatter">
+        <lst name="defaults">
+          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+          <str name="hl.simple.post"><![CDATA[</em>]]></str>
+        </lst>
+      </formatter>
+
+      <!-- Configure the standard encoder -->
+      <encoder name="html"
+               class="solr.highlight.HtmlEncoder" />
+
+      <!-- Configure the standard fragListBuilder -->
+      <fragListBuilder name="simple"
+                       class="solr.highlight.SimpleFragListBuilder"/>
+
+      <!-- Configure the single fragListBuilder -->
+      <fragListBuilder name="single"
+                       class="solr.highlight.SingleFragListBuilder"/>
+
+      <!-- Configure the weighted fragListBuilder -->
+      <fragListBuilder name="weighted"
+                       default="true"
+                       class="solr.highlight.WeightedFragListBuilder"/>
+
+      <!-- default tag FragmentsBuilder -->
+      <fragmentsBuilder name="default"
+                        default="true"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <!--
+        <lst name="defaults">
+          <str name="hl.multiValuedSeparatorChar">/</str>
+        </lst>
+        -->
+      </fragmentsBuilder>
+
+      <!-- multi-colored tag FragmentsBuilder -->
+      <fragmentsBuilder name="colored"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <lst name="defaults">
+          <str name="hl.tag.pre"><![CDATA[
+               <b style="background:yellow">,<b style="background:lawgreen">,
+               <b style="background:aquamarine">,<b style="background:magenta">,
+               <b style="background:palegreen">,<b style="background:coral">,
+               <b style="background:wheat">,<b style="background:khaki">,
+               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+          <str name="hl.tag.post"><![CDATA[</b>]]></str>
+        </lst>
+      </fragmentsBuilder>
+
+      <boundaryScanner name="default"
+                       default="true"
+                       class="solr.highlight.SimpleBoundaryScanner">
+        <lst name="defaults">
+          <str name="hl.bs.maxScan">10</str>
+          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
+        </lst>
+      </boundaryScanner>
+
+      <boundaryScanner name="breakIterator"
+                       class="solr.highlight.BreakIteratorBoundaryScanner">
+        <lst name="defaults">
+          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+          <str name="hl.bs.type">WORD</str>
+          <!-- language and country are used when constructing Locale object.  -->
+          <!-- And the Locale object will be used when getting instance of BreakIterator -->
+          <str name="hl.bs.language">en</str>
+          <str name="hl.bs.country">US</str>
+        </lst>
+      </boundaryScanner>
+    </highlighting>
+  </searchComponent>
+
+  <!-- Update Processors
+
+       Chains of Update Processor Factories for dealing with Update
+       Requests can be declared, and then used by name in Update
+       Request Processors
+
+       http://wiki.apache.org/solr/UpdateRequestProcessor
+
+    -->
+
+  <!-- Add unknown fields to the schema
+
+       Field type guessing update processors that will
+       attempt to parse string-typed field values as Booleans, Longs,
+       Doubles, or Dates, and then add schema fields with the guessed
+       field types. Text content will be indexed as "text_general" as
+       well as a copy to a plain string version in *_str.
+
+       These require that the schema is both managed and mutable, by
+       declaring schemaFactory as ManagedIndexSchemaFactory, with
+       mutable specified as true.
+
+       See http://wiki.apache.org/solr/GuessingFieldTypes
+    -->
+  <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+  <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+  <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+    <str name="pattern">[^\w-\.]</str>
+    <str name="replacement">_</str>
+  </updateProcessor>
+  <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+  <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+  <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+  <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+    <arr name="format">
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+      <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+      <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+      <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+    </arr>
+  </updateProcessor>
+  <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.String</str>
+      <str name="fieldType">text_general</str>
+      <lst name="copyField">
+        <str name="dest">*_str</str>
+        <int name="maxChars">256</int>
+      </lst>
+      <!-- Use as default mapping instead of defaultFieldType -->
+      <bool name="default">true</bool>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Boolean</str>
+      <str name="fieldType">booleans</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.util.Date</str>
+      <str name="fieldType">pdates</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Long</str>
+      <str name="valueClass">java.lang.Integer</str>
+      <str name="fieldType">plongs</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Number</str>
+      <str name="fieldType">pdoubles</str>
+    </lst>
+  </updateProcessor>
+
+  <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+  <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
+           processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+    <processor class="solr.LogUpdateProcessorFactory"/>
+    <processor class="solr.DistributedUpdateProcessorFactory"/>
+    <processor class="solr.RunUpdateProcessorFactory"/>
+  </updateRequestProcessorChain>
+
+  <!-- Deduplication
+
+       An example dedup update processor that creates the "id" field
+       on the fly based on the hash code of some other fields.  This
+       example has overwriteDupes set to false since we are using the
+       id field as the signatureField and Solr will maintain
+       uniqueness based on that anyway.
+
+    -->
+  <!--
+     <updateRequestProcessorChain name="dedupe">
+       <processor class="solr.processor.SignatureUpdateProcessorFactory">
+         <bool name="enabled">true</bool>
+         <str name="signatureField">id</str>
+         <str name="fields">name,features,cat</str>
+         <str name="signatureClass">solr.processor.Lookup3Signature</str>
+       </processor>
+       <processor class="solr.LogUpdateProcessorFactory" />
+       <processor class="solr.RunUpdateProcessorFactory" />
+     </updateRequestProcessorChain>
+    -->
+
+  <!-- Response Writers
+
+       http://wiki.apache.org/solr/QueryResponseWriter
+
+       Request responses will be written using the writer specified by
+       the 'wt' request parameter matching the name of a registered
+       writer.
+
+       The "default" writer is the default and will be used if 'wt' is
+       not specified in the request.
+    -->
+  <!-- The following response writers are implicitly configured unless
+       overridden...
+    -->
+  <!--
+     <queryResponseWriter name="xml"
+                          default="true"
+                          class="solr.XMLResponseWriter" />
+     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+    -->
+
+  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+    <!-- For the purposes of the tutorial, JSON responses are written as
+     plain text so that they are easy to read in *any* browser.
+     If you expect a MIME type of "application/json" just remove this override.
+    -->
+    <str name="content-type">text/plain; charset=UTF-8</str>
+  </queryResponseWriter>
+
+  <!-- Query Parsers
+
+       https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
+
+       Multiple QParserPlugins can be registered by name, and then
+       used in either the "defType" param for the QueryComponent (used
+       by SearchHandler) or in LocalParams
+    -->
+  <!-- example of registering a query parser -->
+  <!--
+     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+    -->
+
+  <!-- Function Parsers
+
+       http://wiki.apache.org/solr/FunctionQuery
+
+       Multiple ValueSourceParsers can be registered by name, and then
+       used as function names when using the "func" QParser.
+    -->
+  <!-- example of registering a custom function parser  -->
+  <!--
+     <valueSourceParser name="myfunc"
+                        class="com.mycompany.MyValueSourceParser" />
+    -->
+
+
+  <!-- Document Transformers
+       http://wiki.apache.org/solr/DocTransformers
+    -->
+  <!--
+     Could be something like:
+     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+       <int name="connection">jdbc://....</int>
+     </transformer>
+
+     To add a constant value to all docs, use:
+     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <int name="value">5</int>
+     </transformer>
+
+     If you want the user to still be able to change it with _value:something_ use this:
+     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <double name="defaultValue">5</double>
+     </transformer>
+
+      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
+      EditorialMarkerFactory will do exactly that:
+     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+    -->
+</config>
diff --git a/test/solr/configsets/_default/conf/stopwords.txt b/test/solr/configsets/_default/conf/stopwords.txt
new file mode 100644
index 00000000..ae1e83ee
--- /dev/null
+++ b/test/solr/configsets/_default/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
diff --git a/test/solr/configsets/_default/conf/synonyms.txt b/test/solr/configsets/_default/conf/synonyms.txt
new file mode 100644
index 00000000..eab4ee87
--- /dev/null
+++ b/test/solr/configsets/_default/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
diff --git a/test/solr/configsets/property_search/conf/enumsconfig.xml b/test/solr/configsets/property_search/conf/enumsconfig.xml
new file mode 100644
index 00000000..72e7b7d3
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/enumsconfig.xml
@@ -0,0 +1,12 @@
+<?xml version="1.0" ?>
+<enumsConfig>
+  <enum name="ontologyType">
+    <value>ONTOLOGY</value>
+    <value>VALUE_SET_COLLECTION</value>
+  </enum>
+  <enum name="propertyType">
+    <value>ANNOTATION</value>
+    <value>DATATYPE</value>
+    <value>OBJECT</value>
+  </enum>
+</enumsConfig>
\ No newline at end of file
diff --git a/test/solr/configsets/property_search/conf/lang/contractions_ca.txt b/test/solr/configsets/property_search/conf/lang/contractions_ca.txt
new file mode 100644
index 00000000..307a85f9
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
diff --git a/test/solr/configsets/property_search/conf/lang/contractions_fr.txt b/test/solr/configsets/property_search/conf/lang/contractions_fr.txt
new file mode 100644
index 00000000..f1bba51b
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
diff --git a/test/solr/configsets/property_search/conf/lang/contractions_ga.txt b/test/solr/configsets/property_search/conf/lang/contractions_ga.txt
new file mode 100644
index 00000000..9ebe7fa3
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
diff --git a/test/solr/configsets/property_search/conf/lang/contractions_it.txt b/test/solr/configsets/property_search/conf/lang/contractions_it.txt
new file mode 100644
index 00000000..cac04095
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l 
+all 
+dall 
+dell 
+nell 
+sull 
+coll 
+pell 
+gl 
+agl 
+dagl 
+degl 
+negl 
+sugl 
+un 
+m 
+t 
+s 
+v 
+d
diff --git a/test/solr/configsets/property_search/conf/lang/hyphenations_ga.txt b/test/solr/configsets/property_search/conf/lang/hyphenations_ga.txt
new file mode 100644
index 00000000..4d2642cc
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
diff --git a/test/solr/configsets/property_search/conf/lang/stemdict_nl.txt b/test/solr/configsets/property_search/conf/lang/stemdict_nl.txt
new file mode 100644
index 00000000..44107297
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets	fiets
+bromfiets	bromfiets
+ei	eier
+kind	kinder
diff --git a/test/solr/configsets/property_search/conf/lang/stoptags_ja.txt b/test/solr/configsets/property_search/conf/lang/stoptags_ja.txt
new file mode 100644
index 00000000..71b75084
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below.  Note that comments are
+# not allowed on the same line as a stoptag.  See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+#  noun: unclassified nouns
+#名詞
+#
+#  noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+#  noun-proper: Proper nouns where the sub-classification is undefined 
+#名詞-固有名詞
+#
+#  noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+#  noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+#  noun-proper-person-misc: names that cannot be divided into surname and 
+#  given name; foreign names; names where the surname or given name is unknown.
+#  e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+#  noun-proper-person-surname: Mainly Japanese surnames.
+#  e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+#  noun-proper-person-given_name: Mainly Japanese given names.
+#  e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+#  noun-proper-organization: Names representing organizations.
+#  e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+#  noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+#  noun-proper-place-misc: Place names excluding countries.
+#  e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+#  noun-proper-place-country: Country names. 
+#  e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+#  noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+#  noun-pronoun-misc: miscellaneous pronouns: 
+#  e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+#  noun-pronoun-contraction: Spoken language contraction made by combining a 
+#  pronoun and the particle 'wa'.
+#  e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ 
+#名詞-代名詞-縮約
+#
+#  noun-adverbial: Temporal nouns such as names of days or months that behave 
+#  like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+#  e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+#  noun-verbal: Nouns that take arguments with case and can appear followed by 
+#  'suru' and related verbs (する, できる, なさる, くださる)
+#  e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+#  noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+#  e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+#  noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+#  e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+#  noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+#  noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that 
+#  attach to the base form of inflectional words, words that cannot be classified 
+#  into any of the other categories below. This category includes indefinite nouns.
+#  e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第, 
+#       順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み, 
+#       拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+#       わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+#  noun-affix-adverbial: noun affixes that that can behave as adverbs.
+#  e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ, 
+#       上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか, 
+#       最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所, 
+#       とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま, 
+#       儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+#  noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars 
+#  with the stem よう(だ) ("you(da)").
+#  e.g.  よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#  
+#  noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+#  connection form な (aux "da").
+#  e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+#  noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+#  noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is 
+#  treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base 
+#  form of inflectional words.
+#  e.g. そう
+#名詞-特殊-助動詞語幹
+#
+#  noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+#  noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect 
+#  to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+#  any of the other categories below. In general, this category is more inclusive than 
+#  接尾語 ("suffix") and is usually the last element in a compound noun.
+#  e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+#       よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+#  noun-suffix-person: Suffixes that form nouns and attach to person names more often
+#  than other nouns.
+#  e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+#  noun-suffix-place: Suffixes that form nouns and attach to place names more often 
+#  than other nouns.
+#  e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+#  noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that 
+#  can appear before スル ("suru").
+#  e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+#  noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions, 
+#  is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the 
+#  conjunctive form of inflectional words.
+#  e.g. そう
+#名詞-接尾-助動詞語幹
+#
+#  noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive 
+#  form of inflectional words and appear before the copula だ ("da").
+#  e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+#  noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+#  e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+#  noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category 
+#  is more inclusive than 助数詞 ("classifier") and includes common nouns that attach 
+#  to numbers.
+#  e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+#  noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+#  e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+#  noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words 
+#  together.
+#  e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+#  noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are 
+#  semantically verb-like.
+#  e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+#  noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry, 
+#  dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation") 
+#  is いわく ("iwaku").
+#名詞-引用文字列
+#
+#  noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+#  behave like an adjective.
+#  e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+#  prefix: unclassified prefixes
+#接頭詞
+#
+#  prefix-nominal: Prefixes that attach to nouns (including adjective stem forms) 
+#  excluding numerical expressions.
+#  e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+#  prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+#  in conjunctive form followed by なる/なさる/くださる.
+#  e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+#  prefix-adjectival: Prefixes that attach to adjectives.
+#  e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+#  prefix-numerical: Prefixes that attach to numerical expressions.
+#  e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+#  verb: unclassified verbs
+#動詞
+#
+#  verb-main:
+#動詞-自立
+#
+#  verb-auxiliary:
+#動詞-非自立
+#
+#  verb-suffix:
+#動詞-接尾
+#
+#####
+#  adjective: unclassified adjectives
+#形容詞
+#
+#  adjective-main:
+#形容詞-自立
+#
+#  adjective-auxiliary:
+#形容詞-非自立
+#
+#  adjective-suffix:
+#形容詞-接尾
+#
+#####
+#  adverb: unclassified adverbs
+#副詞
+#
+#  adverb-misc: Words that can be segmented into one unit and where adnominal 
+#  modification is not possible.
+#  e.g. あいかわらず, 多分
+#副詞-一般
+#
+#  adverb-particle_conjunction: Adverbs that can be followed by の, は, に, 
+#  な, する, だ, etc.
+#  e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+#  adnominal: Words that only have noun-modifying forms.
+#  e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう, 
+#       どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした, 
+#       「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+#  conjunction: Conjunctions that can occur independently.
+#  e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+#  particle: unclassified particles.
+助詞
+#
+#  particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+#  particle-case-misc: Case particles.
+#  e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+#  particle-case-quote: the "to" that appears after nouns, a person’s speech, 
+#  quotation marks, expressions of decisions from a meeting, reasons, judgements,
+#  conjectures, etc.
+#  e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+#  particle-case-compound: Compounds of particles and verbs that mainly behave 
+#  like case particles.
+#  e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+#       にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける, 
+#       にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し, 
+#       に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして, 
+#       に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+#       にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る, 
+#       にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+#       って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+#  particle-conjunctive:
+#  e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども, 
+#       ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/, 
+#       (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+#  particle-dependency:
+#  e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+#  particle-adverbial:
+#  e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/, 
+#       (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+#       (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに, 
+#       (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+#       ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+#  particle-interjective: particles with interjective grammatical roles.
+#  e.g. (松島) や
+助詞-間投助詞
+#
+#  particle-coordinate:
+#  e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+#  particle-final:
+#  e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ, 
+#       ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+#  particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is 
+#  adverbial, conjunctive, or sentence final. For example:
+#       (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+#       (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+#           「(祈りが届いたせい) か (, 試験に合格した.)」
+#       (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+#  e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+#  particle-adnominalizer: The "no" that attaches to nouns and modifies 
+#  non-inflectional words.
+助詞-連体化
+#
+#  particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs 
+#  that are giongo, giseigo, or gitaigo.
+#  e.g. に, と
+助詞-副詞化
+#
+#  particle-special: A particle that does not fit into one of the above classifications. 
+#  This includes particles that are used in Tanka, Haiku, and other poetry.
+#  e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+#  auxiliary-verb:
+助動詞
+#
+#####
+#  interjection: Greetings and other exclamations.
+#  e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます, 
+#       いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+#  symbol: unclassified Symbols.
+記号
+#
+#  symbol-misc: A general symbol not in one of the categories below.
+#  e.g. [○◎@$〒→+]
+記号-一般
+#
+#  symbol-comma: Commas
+#  e.g. [,、]
+記号-読点
+#
+#  symbol-period: Periods and full stops.
+#  e.g. [.．。]
+記号-句点
+#
+#  symbol-space: Full-width whitespace.
+記号-空白
+#
+#  symbol-open_bracket:
+#  e.g. [({‘“『【]
+記号-括弧開
+#
+#  symbol-close_bracket:
+#  e.g. [)}’”』」】]
+記号-括弧閉
+#
+#  symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+#  other: unclassified other
+#その他
+#
+#  other-interjection: Words that are hard to classify as noun-suffixes or 
+#  sentence-final particles.
+#  e.g. (だ)ァ
+その他-間投
+#
+#####
+#  filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+#  e.g. あの, うんと, えと
+フィラー
+#
+#####
+#  non-verbal: non-verbal sound.
+非言語音
+#
+#####
+#  fragment:
+#語断片
+#
+#####
+#  unknown: unknown part of speech.
+#未知語
+#
+##### End of file
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ar.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ar.txt
new file mode 100644
index 00000000..046829db
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some 
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_bg.txt b/test/solr/configsets/property_search/conf/lang/stopwords_bg.txt
new file mode 100644
index 00000000..1ae4ba2a
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ca.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ca.txt
new file mode 100644
index 00000000..3da65dea
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi 
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc 
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant 
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu 
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son 
+són
+sons 
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_cz.txt b/test/solr/configsets/property_search/conf/lang/stopwords_cz.txt
new file mode 100644
index 00000000..53c6097d
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_da.txt b/test/solr/configsets/property_search/conf/lang/stopwords_da.txt
new file mode 100644
index 00000000..42e6145b
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og           | and
+i            | in
+jeg          | I
+det          | that (dem. pronoun)/it (pers. pronoun)
+at           | that (in front of a sentence)/to (with infinitive)
+en           | a/an
+den          | it (pers. pronoun)/that (dem. pronoun)
+til          | to/at/for/until/against/by/of/into, more
+er           | present tense of "to be"
+som          | who, as
+på           | on/upon/in/on/at/to/after/of/with/for, on
+de           | they
+med          | with/by/in, along
+han          | he
+af           | of/by/from/off/for/in/with/on, off
+for          | at/for/to/from/by/of/ago, in front/before, because
+ikke         | not
+der          | who/which, there/those
+var          | past tense of "to be"
+mig          | me/myself
+sig          | oneself/himself/herself/itself/themselves
+men          | but
+et           | a/an/one, one (number), someone/somebody/one
+har          | present tense of "to have"
+om           | round/about/for/in/a, about/around/down, if
+vi           | we
+min          | my
+havde        | past tense of "to have"
+ham          | him
+hun          | she
+nu           | now
+over         | over/above/across/by/beyond/past/on/about, over/past
+da           | then, when/as/since
+fra          | from/off/since, off, since
+du           | you
+ud           | out
+sin          | his/her/its/one's
+dem          | them
+os           | us/ourselves
+op           | up
+man          | you/one
+hans         | his
+hvor         | where
+eller        | or
+hvad         | what
+skal         | must/shall etc.
+selv         | myself/youself/herself/ourselves etc., even
+her          | here
+alle         | all/everyone/everybody etc.
+vil          | will (verb)
+blev         | past tense of "to stay/to remain/to get/to become"
+kunne        | could
+ind          | in
+når          | when
+være         | present tense of "to be"
+dog          | however/yet/after all
+noget        | something
+ville        | would
+jo           | you know/you see (adv), yes
+deres        | their/theirs
+efter        | after/behind/according to/for/by/from, later/afterwards
+ned          | down
+skulle       | should
+denne        | this
+end          | than
+dette        | this
+mit          | my/mine
+også         | also
+under        | under/beneath/below/during, below/underneath
+have         | have
+dig          | you
+anden        | other
+hende        | her
+mine         | my
+alt          | everything
+meget        | much/very, plenty of
+sit          | his, her, its, one's
+sine         | his, her, its, one's
+vor          | our
+mod          | against
+disse        | these
+hvis         | if
+din          | your/yours
+nogle        | some
+hos          | by/at
+blive        | be/become
+mange        | many
+ad           | by/through
+bliver       | present tense of "to be/to become"
+hendes       | her/hers
+været        | be
+thi          | for (conj)
+jer          | you
+sådan        | such, like this/like that
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_de.txt b/test/solr/configsets/property_search/conf/lang/stopwords_de.txt
new file mode 100644
index 00000000..86525e7a
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber           |  but
+
+alle           |  all
+allem
+allen
+aller
+alles
+
+als            |  than, as
+also           |  so
+am             |  an + dem
+an             |  at
+
+ander          |  other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch           |  also
+auf            |  on
+aus            |  out of
+bei            |  by
+bin            |  am
+bis            |  until
+bist           |  art
+da             |  there
+damit          |  with it
+dann           |  then
+
+der            |  the
+den
+des
+dem
+die
+das
+
+daß            |  that
+
+derselbe       |  the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu           |  to that
+
+dein           |  thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn           |  because
+
+derer          |  of those
+dessen         |  of him
+
+dich           |  thee
+dir            |  to thee
+du             |  thou
+
+dies           |  this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch           |  (several meanings)
+dort           |  (over) there
+
+
+durch          |  through
+
+ein            |  a
+eine
+einem
+einen
+einer
+eines
+
+einig          |  some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal         |  once
+
+er             |  he
+ihn            |  him
+ihm            |  to him
+
+es             |  it
+etwas          |  something
+
+euer           |  your
+eure
+eurem
+euren
+eurer
+eures
+
+für            |  for
+gegen          |  towards
+gewesen        |  p.p. of sein
+hab            |  have
+habe           |  have
+haben          |  have
+hat            |  has
+hatte          |  had
+hatten         |  had
+hier           |  here
+hin            |  there
+hinter         |  behind
+
+ich            |  I
+mich           |  me
+mir            |  to me
+
+
+ihr            |  you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch           |  to you
+
+im             |  in + dem
+in             |  in
+indem          |  while
+ins            |  in + das
+ist            |  is
+
+jede           |  each, every
+jedem
+jeden
+jeder
+jedes
+
+jene           |  that
+jenem
+jenen
+jener
+jenes
+
+jetzt          |  now
+kann           |  can
+
+kein           |  no
+keine
+keinem
+keinen
+keiner
+keines
+
+können         |  can
+könnte         |  could
+machen         |  do
+man            |  one
+
+manche         |  some, many a
+manchem
+manchen
+mancher
+manches
+
+mein           |  my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit            |  with
+muss           |  must
+musste         |  had to
+nach           |  to(wards)
+nicht          |  not
+nichts         |  nothing
+noch           |  still, yet
+nun            |  now
+nur            |  only
+ob             |  whether
+oder           |  or
+ohne           |  without
+sehr           |  very
+
+sein           |  his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst         |  self
+sich           |  herself
+
+sie            |  they, she
+ihnen          |  to them
+
+sind           |  are
+so             |  so
+
+solche         |  such
+solchem
+solchen
+solcher
+solches
+
+soll           |  shall
+sollte         |  should
+sondern        |  but
+sonst          |  else
+über           |  over
+um             |  about, around
+und            |  and
+
+uns            |  us
+unse
+unsem
+unsen
+unser
+unses
+
+unter          |  under
+viel           |  much
+vom            |  von + dem
+von            |  from
+vor            |  before
+während        |  while
+war            |  was
+waren          |  were
+warst          |  wast
+was            |  what
+weg            |  away, off
+weil           |  because
+weiter         |  further
+
+welche         |  which
+welchem
+welchen
+welcher
+welches
+
+wenn           |  when
+werde          |  will
+werden         |  will
+wie            |  how
+wieder         |  again
+will           |  want
+wir            |  we
+wird           |  will
+wirst          |  willst
+wo             |  where
+wollen         |  want
+wollte         |  wanted
+würde          |  would
+würden         |  would
+zu             |  to
+zum            |  zu + dem
+zur            |  zu + der
+zwar           |  indeed
+zwischen       |  between
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_el.txt b/test/solr/configsets/property_search/conf/lang/stopwords_el.txt
new file mode 100644
index 00000000..232681f5
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς' 
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και 
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_en.txt b/test/solr/configsets/property_search/conf/lang/stopwords_en.txt
new file mode 100644
index 00000000..2c164c0b
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_es.txt b/test/solr/configsets/property_search/conf/lang/stopwords_es.txt
new file mode 100644
index 00000000..487d78c8
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  from, of
+la             |  the, her
+que            |  who, that
+el             |  the
+en             |  in
+y              |  and
+a              |  to
+los            |  the, them
+del            |  de + el
+se             |  himself, from him etc
+las            |  the, them
+por            |  for, by, etc
+un             |  a
+para           |  for
+con            |  with
+no             |  no
+una            |  a
+su             |  his, her
+al             |  a + el
+  | es         from SER
+lo             |  him
+como           |  how
+más            |  more
+pero           |  pero
+sus            |  su plural
+le             |  to him, her
+ya             |  already
+o              |  or
+  | fue        from SER
+este           |  this
+  | ha         from HABER
+sí             |  himself etc
+porque         |  because
+esta           |  this
+  | son        from SER
+entre          |  between
+  | está     from ESTAR
+cuando         |  when
+muy            |  very
+sin            |  without
+sobre          |  on
+  | ser        from SER
+  | tiene      from TENER
+también        |  also
+me             |  me
+hasta          |  until
+hay            |  there is/are
+donde          |  where
+  | han        from HABER
+quien          |  whom, that
+  | están      from ESTAR
+  | estado     from ESTAR
+desde          |  from
+todo           |  all
+nos            |  us
+durante        |  during
+  | estados    from ESTAR
+todos          |  all
+uno            |  a
+les            |  to them
+ni             |  nor
+contra         |  against
+otros          |  other
+  | fueron     from SER
+ese            |  that
+eso            |  that
+  | había      from HABER
+ante           |  before
+ellos          |  they
+e              |  and (variant of y)
+esto           |  this
+mí             |  me
+antes          |  before
+algunos        |  some
+qué            |  what?
+unos           |  a
+yo             |  I
+otro           |  other
+otras          |  other
+otra           |  other
+él             |  he
+tanto          |  so much, many
+esa            |  that
+estos          |  these
+mucho          |  much, many
+quienes        |  who
+nada           |  nothing
+muchos         |  many
+cual           |  who
+  | sea        from SER
+poco           |  few
+ella           |  she
+estar          |  to be
+  | haber      from HABER
+estas          |  these
+  | estaba     from ESTAR
+  | estamos    from ESTAR
+algunas        |  some
+algo           |  something
+nosotros       |  we
+
+      | other forms
+
+mi             |  me
+mis            |  mi plural
+tú             |  thou
+te             |  thee
+ti             |  thee
+tu             |  thy
+tus            |  tu plural
+ellas          |  they
+nosotras       |  we
+vosotros       |  you
+vosotras       |  you
+os             |  you
+mío            |  mine
+mía            |
+míos           |
+mías           |
+tuyo           |  thine
+tuya           |
+tuyos          |
+tuyas          |
+suyo           |  his, hers, theirs
+suya           |
+suyos          |
+suyas          |
+nuestro        |  ours
+nuestra        |
+nuestros       |
+nuestras       |
+vuestro        |  yours
+vuestra        |
+vuestros       |
+vuestras       |
+esos           |  those
+esas           |  those
+
+               | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+               | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+               | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+  |  sed also means 'thirst'
+
+               | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_et.txt b/test/solr/configsets/property_search/conf/lang/stopwords_et.txt
new file mode 100644
index 00000000..1b06a134
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_et.txt
@@ -0,0 +1,1603 @@
+# Estonian stopwords list
+all
+alla
+allapoole
+allpool
+alt
+altpoolt
+eel
+eespool
+enne
+hommikupoole
+hoolimata
+ilma
+kaudu
+keset
+kesk
+kohe
+koos
+kuhupoole
+kuni
+kuspool
+kustpoolt
+kõige
+käsikäes
+lappi
+ligi
+läbi
+mööda
+paitsi
+peale
+pealepoole
+pealpool
+pealt
+pealtpoolt
+piki
+pikku
+piku
+pikuti
+põiki
+pärast
+päri
+risti
+sealpool
+sealtpoolt
+seespool
+seltsis
+siiapoole
+siinpool
+siitpoolt
+sinnapoole
+sissepoole
+taga
+tagantpoolt
+tagapidi
+tagapool
+taha
+tahapoole
+teispool
+teispoole
+tänu
+tükkis
+vaatamata
+vastu
+väljapoole
+väljaspool
+väljastpoolt
+õhtupoole
+ühes
+ühestükis
+ühestükkis
+ülalpool
+ülaltpoolt
+üle
+ülespoole
+ülevalpool
+ülevaltpoolt
+ümber
+ümbert
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+lool
+läbi
+lähedal
+lähedale
+lähedalt
+man
+mant
+manu
+meelest
+mööda
+nahas
+nahka
+nahkas
+najal
+najale
+najalt
+nõjal
+nõjale
+otsa
+otsas
+otsast
+paigale
+paigu
+paiku
+peal
+peale
+pealt
+perra
+perrä
+pidi
+pihta
+piki
+pikku
+pool
+poole
+poolest
+poolt
+puhul
+puksiiris
+pähe
+päralt
+päras
+pärast
+päri
+ringi
+ringis
+risust
+saadetusel
+saadik
+saatel
+saati
+seas
+seast
+sees
+seest
+sekka
+seljataga
+seltsi
+seltsis
+seltsist
+sisse
+slepis
+suhtes
+šlepis
+taga
+tagant
+tagantotsast
+tagaotsas
+tagaselja
+tagasi
+tagast
+tagutsi
+taha
+tahaotsa
+takka
+tarvis
+tasa
+tuuri
+tuuris
+tõttu
+tükkis
+uhal
+vaatamata
+vahel
+vahele
+vahelt
+vahepeal
+vahepeale
+vahepealt
+vahetsi
+varal
+varale
+varul
+vastas
+vastast
+vastu
+veerde
+veeres
+viisi
+võidu
+võrd
+võrdki
+võrra
+võrragi
+väel
+väele
+vältel
+väärt
+väärtki
+äärde
+ääre
+ääres
+äärest
+ühes
+üle
+ümber
+ümbert
+a
+abil
+aina
+ainult
+alalt
+alates
+alati
+alles
+b
+c
+d
+e
+eales
+ealeski
+edasi
+edaspidi
+eelkõige
+eemal
+ei
+eks
+end
+enda
+enese
+ennem
+esialgu
+f
+g
+h
+hoopis
+i
+iganes
+igatahes
+igati
+iial
+iialgi
+ikka
+ikkagi
+ilmaski
+iseenda
+iseenese
+iseenesest
+isegi
+j
+jah
+ju
+juba
+juhul
+just
+järelikult
+k
+ka
+kah
+kas
+kasvõi
+keda
+kestahes
+kogu
+koguni
+kohati
+kokku
+kuhu
+kuhugi
+kuidagi
+kuidas
+kunagi
+kus
+kusagil
+kusjuures
+kuskil
+kust
+kõigepealt
+küll
+l
+liiga
+lisaks
+m
+miks
+mil
+millal
+millalgi
+mispärast
+mistahes
+mistõttu
+mitte
+muide
+muidu
+muidugi
+muist
+mujal
+mujale
+mujalt
+mõlemad
+mõnda
+mõne
+mõnikord
+n
+nii
+niikaua
+niimoodi
+niipaljuke
+niisama
+niisiis
+niivõrd
+nõnda
+nüüd
+o
+omaette
+omakorda
+omavahel
+ometi
+p
+palju
+paljuke
+palju-palju
+peaaegu
+peagi
+peamiselt
+pigem
+pisut
+praegu
+päris
+r
+rohkem
+s
+samas
+samuti
+seal
+sealt
+sedakorda
+sedapuhku
+seega
+seejuures
+seejärel
+seekord
+seepärast
+seetõttu
+sellepärast
+seni
+sestap
+siia
+siiani
+siin
+siinkohal
+siis
+siiski
+siit
+sinna
+suht
+š
+z
+ž
+t
+teel
+teineteise
+tõesti
+täiesti
+u
+umbes
+v
+w
+veel
+veelgi
+vist
+võibolla
+võib-olla
+väga
+vähemalt
+välja
+väljas
+väljast
+õ
+ä
+ära
+ö
+ü
+ühtlasi
+üksi
+ükskõik
+ülal
+ülale
+ülalt
+üles
+ülesse
+üleval
+ülevalt
+ülimalt
+üsna
+x
+y
+aga
+ega
+ehk
+ehkki
+elik
+ellik
+enge
+ennegu
+ent
+et
+ja
+justkui
+kui
+kuid
+kuigi
+kuivõrd
+kuna
+kuni
+kut
+mistab
+muudkui
+nagu
+nigu
+ning
+olgugi
+otsekui
+otsenagu
+selmet
+sest
+sestab
+vaid
+või
+aa
+adaa
+adjöö
+ae
+ah
+ahaa
+ahah
+ah-ah-ah
+ah-haa
+ahoi
+ai
+aidaa
+aidu-raidu
+aih
+aijeh
+aituma
+aitäh
+aitüma
+ammuu
+amps
+ampsti
+aptsih
+ass
+at
+ata
+at-at-at
+atsih
+atsihh
+auh
+bai-bai
+bingo
+braavo
+brr
+ee
+eeh
+eh
+ehee
+eheh
+eh-eh-hee
+eh-eh-ee
+ehei
+ehh
+ehhee
+einoh
+ena
+ennäe
+ennäh
+fuh
+fui
+fuih
+haa
+hah
+hahaa
+hah-hah-hah
+halleluuja
+hallo
+halloo
+hass
+hee
+heh
+he-he-hee
+hei
+heldeke(ne)
+heureka
+hihii
+hip-hip-hurraa
+hmh
+hmjah
+hoh-hoh-hoo
+hohoo
+hoi
+hollallaa
+hoo
+hoplaa
+hopp
+hops
+hopsassaa
+hopsti
+hosianna
+huh
+huidii
+huist
+hurjah
+hurjeh
+hurjoh
+hurjuh
+hurraa
+huu
+hõhõh
+hõi
+hõissa
+hõissassa
+hõk
+hõkk
+häh
+hä-hä-hää
+hüvasti
+ih-ah-haa
+ih-ih-hii
+ii-ha-ha
+issake
+issakene
+isver
+jaa-ah
+ja-ah
+jaah
+janäe
+jeeh
+jeerum
+jeever
+jessas
+jestas
+juhhei
+jumalaga
+jumalime
+jumaluke
+jumalukene
+jutas
+kaaps
+kaapsti
+kaasike
+kae
+kalps
+kalpsti
+kannäe
+kanäe
+kappadi
+kaps
+kapsti
+karkõmm
+karkäuh
+karkääks
+karkääksti
+karmauh
+karmauhti
+karnaps
+karnapsti
+karniuhti
+karpartsaki
+karpauh
+karpauhti
+karplauh
+karplauhti
+karprauh
+karprauhti
+karsumdi
+karsumm
+kartsumdi
+kartsumm
+karviuh
+karviuhti
+kaske
+kassa
+kauh
+kauhti
+keh
+keksti
+kepsti
+khe
+khm
+kih
+kiiks
+kiiksti
+kiis
+kiiss
+kikerii
+kikerikii
+kili
+kilk
+kilk-kõlk
+kilks
+kilks-kolks
+kilks-kõlks
+kill
+killadi
+killadi|-kolladi
+killadi-kõlladi
+killa-kolla
+killa-kõlla
+kill-kõll
+kimps-komps
+kipp
+kips-kõps
+kiriküüt
+kirra-kõrra
+kirr-kõrr
+kirts
+klaps
+klapsti
+klirdi
+klirr
+klonks
+klops
+klopsti
+kluk
+klu-kluu
+klõks
+klõksti
+klõmdi
+klõmm
+klõmpsti
+klõnks
+klõnksti
+klõps
+klõpsti
+kläu
+kohva-kohva
+kok
+koks
+koksti
+kolaki
+kolk
+kolks
+kolksti
+koll
+kolladi
+komp
+komps
+kompsti
+kop
+kopp
+koppadi
+kops
+kopsti
+kossu
+kotsu
+kraa
+kraak
+kraaks
+kraaps
+kraapsti
+krahh
+kraks
+kraksti
+kraps
+krapsti
+krauh
+krauhti
+kriiks
+kriiksti
+kriips
+kriips-kraaps
+kripa-krõpa
+krips-kraps
+kriuh
+kriuks
+kriuksti
+kromps
+kronk
+kronks
+krooks
+kruu
+krõks
+krõksti
+krõpa
+krõps
+krõpsti
+krõuh
+kräu
+kräuh
+kräuhti
+kräuks
+kss
+kukeleegu
+kukku
+kuku
+kulu
+kurluu
+kurnäu
+kuss
+kussu
+kõks
+kõksti
+kõldi
+kõlks
+kõlksti
+kõll
+kõmaki
+kõmdi
+kõmm
+kõmps
+kõpp
+kõps
+kõpsadi
+kõpsat
+kõpsti
+kõrr
+kõrra-kõrra
+kõss
+kõtt
+kõõksti
+kärr
+kärts
+kärtsti
+käuks
+käuksti
+kääga
+kääks
+kääksti
+köh
+köki-möki
+köksti
+laks
+laksti
+lampsti
+larts
+lartsti
+lats
+latsti
+leelo
+legoo
+lehva
+liiri-lõõri
+lika-lõka
+likat-lõkat
+limpsti
+lips
+lipsti
+lirts
+lirtsaki
+lirtsti
+lonksti
+lops
+lopsti
+lorts
+lortsti
+luks
+lups
+lupsti
+lurts
+lurtsti
+lõks
+lõksti
+lõmps
+lõmpsti
+lõnks
+lõnksti
+lärts
+lärtsti
+läts
+lätsti
+lörts
+lörtsti
+lötsti
+lööps
+lööpsti
+marss
+mats
+matsti
+mauh
+mauhti
+mh
+mhh
+mhmh
+miau
+mjaa
+mkm
+m-mh
+mnjaa
+mnjah
+moens
+mulks
+mulksti
+mull-mull
+mull-mull-mull
+muu
+muuh
+mõh
+mõmm
+mäh
+mäts
+mäu
+mää
+möh
+möh-öh-ää
+möö
+müh-müh
+mühüh
+müks
+müksti
+müraki
+mürr
+mürts
+mürtsaki
+mürtsti
+mütaku
+müta-mäta
+müta-müta
+müt-müt
+müt-müt-müt
+müts
+mütsti
+mütt
+naa
+naah
+nah
+naks
+naksti
+nanuu
+naps
+napsti
+nilpsti
+nipsti
+nirr
+niuh
+niuh-näuh
+niuhti
+noh
+noksti
+nolpsti
+nonoh
+nonoo
+nonäh
+noo
+nooh
+nooks
+norr
+nurr
+nuuts
+nõh
+nõhh
+nõka-nõka
+nõks
+nõksat-nõksat
+nõks-nõks
+nõksti
+nõõ
+nõõh
+näeh
+näh
+nälpsti
+nämm-nämm
+näpsti
+näts
+nätsti
+näu
+näuh
+näuhti
+näuks
+näuksti
+nääh
+nääks
+nühkat-nühkat
+oeh
+oh
+ohh
+ohhh
+oh-hoi
+oh-hoo
+ohoh
+oh-oh-oo
+oh-oh-hoo
+ohoi
+ohoo
+oi
+oih
+oijee
+oijeh
+oo
+ooh
+oo-oh
+oo-ohh
+oot
+ossa
+ot
+paa
+pah
+pahh
+pakaa
+pamm
+pantsti
+pardon
+pardonks
+parlartsti
+parts
+partsti
+partsumdi
+partsumm
+pastoi
+pats
+patst
+patsti
+pau
+pauh
+pauhti
+pele
+pfui
+phuh
+phuuh
+phäh
+phähh
+piiks
+piip
+piiri-pääri
+pimm
+pimm-pamm
+pimm-pomm
+pimm-põmm
+piraki
+piuks
+piu-pau
+plaks
+plaksti
+plarts
+plartsti
+plats
+platsti
+plauh
+plauhh
+plauhti
+pliks
+pliks-plaks
+plinn
+pliraki
+plirts
+plirtsti
+pliu
+pliuh
+ploks
+plotsti
+plumps
+plumpsti
+plõks
+plõksti
+plõmdi
+plõmm
+plõnn
+plärr
+plärts
+plärtsat
+plärtsti
+pläu
+pläuh
+plää
+plörtsat
+pomm
+popp
+pops
+popsti
+ports
+pot
+pots
+potsti
+pott
+praks
+praksti
+prants
+prantsaki
+prantsti
+prassai
+prauh
+prauhh
+prauhti
+priks
+priuh
+priuhh
+priuh-prauh
+proosit
+proost
+prr
+prrr
+prõks
+prõksti
+prõmdi
+prõmm
+prõntsti
+prääk
+prääks
+pst
+psst
+ptrr
+ptruu
+ptüi
+puh
+puhh
+puksti
+pumm
+pumps
+pup-pup-pup
+purts
+puuh
+põks
+põksti
+põmdi
+põmm
+põmmadi
+põnks
+põnn
+põnnadi
+põnt
+põnts
+põntsti
+põraki
+põrr
+põrra-põrra
+päh
+pähh
+päntsti
+pää
+pöörd
+püh
+raks
+raksti
+raps
+rapsti
+ratataa
+rauh
+riips
+riipsti
+riks
+riks-raks
+rips-raps
+rivitult
+robaki
+rops
+ropsaki
+ropsti
+ruik
+räntsti
+räts
+röh
+röhh
+sah
+sahh
+sahkat
+saps
+sapsti
+sauh
+sauhti
+servus
+sihkadi-sahkadi
+sihka-sahka
+sihkat-sahkat
+silks
+silk-solk
+sips
+sipsti
+sirr
+sirr-sorr
+sirts
+sirtsti
+siu
+siuh
+siuh-sauh
+siuh-säuh
+siuhti
+siuks
+siuts
+skool
+so
+soh
+solks
+solksti
+solpsti
+soo
+sooh
+so-oh
+soo-oh
+sopp
+sops
+sopsti
+sorr
+sorts
+sortsti
+so-soo
+soss
+soss-soss
+ss
+sss
+sst
+stopp
+suhkat-sahkat
+sulk
+sulks
+sulksti
+sull
+sulla-sulla
+sulpa-sulpa
+sulps
+sulpsti
+sumaki
+sumdi
+summ
+summat-summat
+sups
+supsaku
+supsti
+surts
+surtsti
+suss
+susti
+suts
+sutsti
+säh
+sähke
+särts
+särtsti
+säu
+säuh
+säuhti
+taevake
+taevakene
+takk
+tere
+terekest
+tibi-tibi
+tikk-takk
+tiks
+tilk
+tilks
+till
+tilla-talla
+till-tall
+tilulii
+tinn
+tip
+tip-tap
+tirr
+tirtsti
+tiu
+tjaa
+tjah
+tohhoh
+tohhoo
+tohoh
+tohoo
+tok
+tokk
+toks
+toksti
+tonks
+tonksti
+tota
+totsti
+tot-tot
+tprr
+tpruu
+trah
+trahh
+trallallaa
+trill
+trillallaa
+trr
+trrr
+tsah
+tsahh
+tsilk
+tsilk-tsolk
+tsirr
+tsiuh
+tskae
+tsolk
+tss
+tst
+tsst
+tsuhh
+tsuk
+tsumm
+tsurr
+tsäuh
+tšao
+tšš
+tššš
+tuk
+tuks
+turts
+turtsti
+tutki
+tutkit
+tutu-lutu
+tutulutu
+tuut
+tuutu-luutu
+tõks
+tötsti
+tümps
+uh
+uhh
+uh-huu
+uhtsa
+uhtsaa
+uhuh
+uhuu
+ui
+uih
+uih-aih
+uijah
+uijeh
+uist
+uit
+uka
+upsti
+uraa
+urjah
+urjeh
+urjoh
+urjuh
+urr
+urraa
+ust
+utu
+uu
+uuh
+vaak
+vaat
+vae
+vaeh
+vai
+vat
+vau
+vhüüt
+vidiit
+viiks
+vilks
+vilksti
+vinki-vinki
+virdi
+virr
+viu
+viudi
+viuh
+viuhti
+voeh
+voh
+vohh
+volks
+volksti
+vooh
+vops
+vopsti
+vot
+vuh
+vuhti
+vuih
+vulks
+vulksti
+vull
+vulpsti
+vups
+vupsaki
+vupsaku
+vupsti
+vurdi
+vurr
+vurra-vurra
+vurts
+vurtsti
+vutt
+võe
+võeh
+või
+võih
+võrr
+võts
+võtt
+vääks
+õe
+õits
+õk
+õkk
+õrr
+õss
+õuh
+äh
+ähh
+ähhähhää
+äh-hää
+äh-äh-hää
+äiu
+äiu-ää
+äss
+ää
+ääh
+äähh
+öh
+öhh
+ök
+üh
+eelmine
+eikeegi
+eimiski
+emb-kumb
+enam
+enim
+iga
+igasugune
+igaüks
+ise
+isesugune
+järgmine
+keegi
+kes
+kumb
+kumbki
+kõik
+meiesugune
+meietaoline
+midagi
+mihuke
+mihukene
+milletaoline
+milline
+mina
+minake
+mingi
+mingisugune
+minusugune
+minutaoline
+mis
+miski
+miskisugune
+missugune
+misuke
+mitmes
+mitmesugune
+mitu
+mitu-mitu
+mitu-setu
+muu
+mõlema
+mõnesugune
+mõni
+mõningane
+mõningas
+mäherdune
+määrane
+naasugune
+need
+nemad
+nendesugune
+nendetaoline
+nihuke
+nihukene
+niimitu
+niisamasugune
+niisugune
+nisuke
+nisukene
+oma
+omaenese
+omasugune
+omataoline
+pool
+praegune
+sama
+samasugune
+samataoline
+see
+seesama
+seesamane
+seesamune
+seesinane
+seesugune
+selline
+sihuke
+sihukene
+sina
+sinusugune
+sinutaoline
+siuke
+siukene
+säherdune
+säärane
+taoline
+teiesugune
+teine
+teistsugune
+tema
+temake
+temakene
+temasugune
+temataoline
+too
+toosama
+toosamane
+üks
+üksteise
+hakkama
+minema
+olema
+pidama
+saama
+tegema
+tulema
+võima
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_eu.txt b/test/solr/configsets/property_search/conf/lang/stopwords_eu.txt
new file mode 100644
index 00000000..25f1db93
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_fa.txt b/test/solr/configsets/property_search/conf/lang/stopwords_fa.txt
new file mode 100644
index 00000000..723641c6
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_fi.txt b/test/solr/configsets/property_search/conf/lang/stopwords_fi.txt
new file mode 100644
index 00000000..4372c9a0
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole        | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en         | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom   Gen    Acc    Part   Iness   Elat    Illat  Adess   Ablat   Allat   Ess    Trans
+minä   minun  minut  minua  minussa minusta minuun minulla minulta minulle               | I
+sinä   sinun  sinut  sinua  sinussa sinusta sinuun sinulla sinulta sinulle               | you
+hän    hänen  hänet  häntä  hänessä hänestä häneen hänellä häneltä hänelle               | he she
+me     meidän meidät meitä  meissä  meistä  meihin meillä  meiltä  meille                | we
+te     teidän teidät teitä  teissä  teistä  teihin teillä  teiltä  teille                | you
+he     heidän heidät heitä  heissä  heistä  heihin heillä  heiltä  heille                | they
+
+tämä   tämän         tätä   tässä   tästä   tähän  tallä   tältä   tälle   tänä   täksi  | this
+tuo    tuon          tuotä  tuossa  tuosta  tuohon tuolla  tuolta  tuolle  tuona  tuoksi | that
+se     sen           sitä   siinä   siitä   siihen sillä   siltä   sille   sinä   siksi  | it
+nämä   näiden        näitä  näissä  näistä  näihin näillä  näiltä  näille  näinä  näiksi | these
+nuo    noiden        noita  noissa  noista  noihin noilla  noilta  noille  noina  noiksi | those
+ne     niiden        niitä  niissä  niistä  niihin niillä  niiltä  niille  niinä  niiksi | they
+
+kuka   kenen kenet   ketä   kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä  keiden ketkä  keitä  keissä  keistä  keihin keillä  keiltä  keille  keinä  keiksi | (pl)
+mikä   minkä minkä   mitä   missä   mistä   mihin  millä   miltä   mille   minä   miksi  | which what
+mitkä                                                                                    | (pl)
+
+joka   jonka         jota   jossa   josta   johon  jolla   jolta   jolle   jona   joksi  | who which
+jotka  joiden        joita  joissa  joista  joihin joilla  joilta  joille  joina  joiksi | (pl)
+
+| conjunctions
+
+että   | that
+ja     | and
+jos    | if
+koska  | because
+kuin   | than
+mutta  | but
+niin   | so
+sekä   | and
+sillä  | for
+tai    | or
+vaan   | but
+vai    | or
+vaikka | although
+
+
+| prepositions
+
+kanssa  | with
+mukaan  | according to
+noin    | about
+poikki  | across
+yli     | over, across
+
+| other
+
+kun    | when
+niin   | so
+nyt    | now
+itse   | self
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_fr.txt b/test/solr/configsets/property_search/conf/lang/stopwords_fr.txt
new file mode 100644
index 00000000..749abae6
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au             |  a + le
+aux            |  a + les
+avec           |  with
+ce             |  this
+ces            |  these
+dans           |  with
+de             |  of
+des            |  de + les
+du             |  de + le
+elle           |  she
+en             |  `of them' etc
+et             |  and
+eux            |  them
+il             |  he
+je             |  I
+la             |  the
+le             |  the
+leur           |  their
+lui            |  him
+ma             |  my (fem)
+mais           |  but
+me             |  me
+même           |  same; as in moi-même (myself) etc
+mes            |  me (pl)
+moi            |  me
+mon            |  my (masc)
+ne             |  not
+nos            |  our (pl)
+notre          |  our
+nous           |  we
+on             |  one
+ou             |  where
+par            |  by
+pas            |  not
+pour           |  for
+qu             |  que before vowel
+que            |  that
+qui            |  who
+sa             |  his, her (fem)
+se             |  oneself
+ses            |  his (pl)
+son            |  his, her (masc)
+sur            |  on
+ta             |  thy (fem)
+te             |  thee
+tes            |  thy (pl)
+toi            |  thee
+ton            |  thy (masc)
+tu             |  thou
+un             |  a
+une            |  a
+vos            |  your (pl)
+votre          |  your
+vous           |  you
+
+               |  single letter forms
+
+c              |  c'
+d              |  d'
+j              |  j'
+l              |  l'
+à              |  to, at
+m              |  m'
+n              |  n'
+s              |  s'
+t              |  t'
+y              |  there
+
+               | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+               | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+               | Later additions (from Jean-Christophe Deschamps)
+ceci           |  this
+cela           |  that
+celà           |  that
+cet            |  this
+cette          |  this
+ici            |  here
+ils            |  they
+les            |  the (pl)
+leurs          |  their (pl)
+quel           |  which
+quels          |  which
+quelle         |  which
+quelles        |  which
+sans           |  without
+soi            |  oneself
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ga.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ga.txt
new file mode 100644
index 00000000..9ff88d74
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_gl.txt b/test/solr/configsets/property_search/conf/lang/stopwords_gl.txt
new file mode 100644
index 00000000..d8760b12
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_hi.txt b/test/solr/configsets/property_search/conf/lang/stopwords_hi.txt
new file mode 100644
index 00000000..86286bb0
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer 
+# for spelling variation (see section below), such that it can be used whether or 
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well. 
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन 
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर  
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह 
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह 
+वहाँ
+वहीं
+वाले
+वुह 
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_hu.txt b/test/solr/configsets/property_search/conf/lang/stopwords_hu.txt
new file mode 100644
index 00000000..37526da8
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_hy.txt b/test/solr/configsets/property_search/conf/lang/stopwords_hy.txt
new file mode 100644
index 00000000..60c1c50f
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_id.txt b/test/solr/configsets/property_search/conf/lang/stopwords_id.txt
new file mode 100644
index 00000000..4617f83a
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_it.txt b/test/solr/configsets/property_search/conf/lang/stopwords_it.txt
new file mode 100644
index 00000000..1219cc77
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad             |  a (to) before vowel
+al             |  a + il
+allo           |  a + lo
+ai             |  a + i
+agli           |  a + gli
+all            |  a + l'
+agl            |  a + gl'
+alla           |  a + la
+alle           |  a + le
+con            |  with
+col            |  con + il
+coi            |  con + i (forms collo, cogli etc are now very rare)
+da             |  from
+dal            |  da + il
+dallo          |  da + lo
+dai            |  da + i
+dagli          |  da + gli
+dall           |  da + l'
+dagl           |  da + gll'
+dalla          |  da + la
+dalle          |  da + le
+di             |  of
+del            |  di + il
+dello          |  di + lo
+dei            |  di + i
+degli          |  di + gli
+dell           |  di + l'
+degl           |  di + gl'
+della          |  di + la
+delle          |  di + le
+in             |  in
+nel            |  in + el
+nello          |  in + lo
+nei            |  in + i
+negli          |  in + gli
+nell           |  in + l'
+negl           |  in + gl'
+nella          |  in + la
+nelle          |  in + le
+su             |  on
+sul            |  su + il
+sullo          |  su + lo
+sui            |  su + i
+sugli          |  su + gli
+sull           |  su + l'
+sugl           |  su + gl'
+sulla          |  su + la
+sulle          |  su + le
+per            |  through, by
+tra            |  among
+contro         |  against
+io             |  I
+tu             |  thou
+lui            |  he
+lei            |  she
+noi            |  we
+voi            |  you
+loro           |  they
+mio            |  my
+mia            |
+miei           |
+mie            |
+tuo            |
+tua            |
+tuoi           |  thy
+tue            |
+suo            |
+sua            |
+suoi           |  his, her
+sue            |
+nostro         |  our
+nostra         |
+nostri         |
+nostre         |
+vostro         |  your
+vostra         |
+vostri         |
+vostre         |
+mi             |  me
+ti             |  thee
+ci             |  us, there
+vi             |  you, there
+lo             |  him, the
+la             |  her, the
+li             |  them
+le             |  them, the
+gli            |  to him, the
+ne             |  from there etc
+il             |  the
+un             |  a
+uno            |  a
+una            |  a
+ma             |  but
+ed             |  and
+se             |  if
+perché         |  why, because
+anche          |  also
+come           |  how
+dov            |  where (as dov')
+dove           |  where
+che            |  who, that
+chi            |  who
+cui            |  whom
+non            |  not
+più            |  more
+quale          |  who, that
+quanto         |  how much
+quanti         |
+quanta         |
+quante         |
+quello         |  that
+quelli         |
+quella         |
+quelle         |
+questo         |  this
+questi         |
+questa         |
+queste         |
+si             |  yes
+tutto          |  all
+tutti          |  all
+
+               |  single letter forms:
+
+a              |  at
+c              |  as c' for ce or ci
+e              |  and
+i              |  the
+l              |  as l'
+o              |  or
+
+               | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+               | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+               | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+               | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ja.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ja.txt
new file mode 100644
index 00000000..d4321be6
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out.  See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter.  When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner.  Change your StopFilter
+# configuration if you need case-sensitive stopping.  Lastly, note that stopping is done
+# using the same character width as the entries in this file.  Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_lv.txt b/test/solr/configsets/property_search/conf/lang/stopwords_lv.txt
new file mode 100644
index 00000000..e21a23c0
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined: 
+#   pronouns, adverbs, interjections were removed
+# 
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt  
+biju 
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat 
+būšu     
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_nl.txt b/test/solr/configsets/property_search/conf/lang/stopwords_nl.txt
new file mode 100644
index 00000000..47a2aeac
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de             |  the
+en             |  and
+van            |  of, from
+ik             |  I, the ego
+te             |  (1) chez, at etc, (2) to, (3) too
+dat            |  that, which
+die            |  that, those, who, which
+in             |  in, inside
+een            |  a, an, one
+hij            |  he
+het            |  the, it
+niet           |  not, nothing, naught
+zijn           |  (1) to be, being, (2) his, one's, its
+is             |  is
+was            |  (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op             |  on, upon, at, in, up, used up
+aan            |  on, upon, to (as dative)
+met            |  with, by
+als            |  like, such as, when
+voor           |  (1) before, in front of, (2) furrow
+had            |  had, past tense all persons sing. of 'hebben' (have)
+er             |  there
+maar           |  but, only
+om             |  round, about, for etc
+hem            |  him
+dan            |  then
+zou            |  should/would, past tense all persons sing. of 'zullen'
+of             |  or, whether, if
+wat            |  what, something, anything
+mijn           |  possessive and noun 'mine'
+men            |  people, 'one'
+dit            |  this
+zo             |  so, thus, in this way
+door           |  through by
+over           |  over, across
+ze             |  she, her, they, them
+zich           |  oneself
+bij            |  (1) a bee, (2) by, near, at
+ook            |  also, too
+tot            |  till, until
+je             |  you
+mij            |  me
+uit            |  out of, from
+der            |  Old Dutch form of 'van der' still found in surnames
+daar           |  (1) there, (2) because
+haar           |  (1) her, their, them, (2) hair
+naar           |  (1) unpleasant, unwell etc, (2) towards, (3) as
+heb            |  present first person sing. of 'to have'
+hoe            |  how, why
+heeft          |  present third person sing. of 'to have'
+hebben         |  'to have' and various parts thereof
+deze           |  this
+u              |  you
+want           |  (1) for, (2) mitten, (3) rigging
+nog            |  yet, still
+zal            |  'shall', first and third person sing. of verb 'zullen' (will)
+me             |  me
+zij            |  she, they
+nu             |  now
+ge             |  'thou', still used in Belgium and south Netherlands
+geen           |  none
+omdat          |  because
+iets           |  something, somewhat
+worden         |  to become, grow, get
+toch           |  yet, still
+al             |  all, every, each
+waren          |  (1) 'were' (2) to wander, (3) wares, (3)
+veel           |  much, many
+meer           |  (1) more, (2) lake
+doen           |  to do, to make
+toen           |  then, when
+moet           |  noun 'spot/mote' and present form of 'to must'
+ben            |  (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder         |  without
+kan            |  noun 'can' and present form of 'to be able'
+hun            |  their, them
+dus            |  so, consequently
+alles          |  all, everything, anything
+onder          |  under, beneath
+ja             |  yes, of course
+eens           |  once, one day
+hier           |  here
+wie            |  who
+werd           |  imperfect third person sing. of 'become'
+altijd         |  always
+doch           |  yet, but etc
+wordt          |  present third person sing. of 'become'
+wezen          |  (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen         |  to be able
+ons            |  us/our
+zelf           |  self
+tegen          |  against, towards, at
+na             |  after, near
+reeds          |  already
+wil            |  (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon            |  could; past tense of 'to be able'
+niets          |  nothing
+uw             |  your
+iemand         |  somebody
+geweest        |  been; past participle of 'be'
+andere         |  other
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_no.txt b/test/solr/configsets/property_search/conf/lang/stopwords_no.txt
new file mode 100644
index 00000000..a7a2c28b
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
+
+og             | and
+i              | in
+jeg            | I
+det            | it/this/that
+at             | to (w. inf.)
+en             | a/an
+et             | a/an
+den            | it/this/that
+til            | to
+er             | is/am/are
+som            | who/that
+på             | on
+de             | they / you(formal)
+med            | with
+han            | he
+av             | of
+ikke           | not
+ikkje          | not *
+der            | there
+så             | so
+var            | was/were
+meg            | me
+seg            | you
+men            | but
+ett            | one
+har            | have
+om             | about
+vi             | we
+min            | my
+mitt           | my
+ha             | have
+hadde          | had
+hun            | she
+nå             | now
+over           | over
+da             | when/as
+ved            | by/know
+fra            | from
+du             | you
+ut             | out
+sin            | your
+dem            | them
+oss            | us
+opp            | up
+man            | you/one
+kan            | can
+hans           | his
+hvor           | where
+eller          | or
+hva            | what
+skal           | shall/must
+selv           | self (reflective)
+sjøl           | self (reflective)
+her            | here
+alle           | all
+vil            | will
+bli            | become
+ble            | became
+blei           | became *
+blitt          | have become
+kunne          | could
+inn            | in
+når            | when
+være           | be
+kom            | come
+noen           | some
+noe            | some
+ville          | would
+dere           | you
+som            | who/which/that
+deres          | their/theirs
+kun            | only/just
+ja             | yes
+etter          | after
+ned            | down
+skulle         | should
+denne          | this
+for            | for/because
+deg            | you
+si             | hers/his
+sine           | hers/his
+sitt           | hers/his
+mot            | against
+å              | to
+meget          | much
+hvorfor        | why
+dette          | this
+disse          | these/those
+uten           | without
+hvordan        | how
+ingen          | none
+din            | your
+ditt           | your
+blir           | become
+samme          | same
+hvilken        | which
+hvilke         | which (plural)
+sånn           | such a
+inni           | inside/within
+mellom         | between
+vår            | our
+hver           | each
+hvem           | who
+vors           | us/ours
+hvis           | whose
+både           | both
+bare           | only/just
+enn            | than
+fordi          | as/because
+før            | before
+mange          | many
+også           | also
+slik           | just
+vært           | been
+være           | to be
+båe            | both *
+begge          | both
+siden          | since
+dykk           | your *
+dykkar         | yours *
+dei            | they *
+deira          | them *
+deires         | theirs *
+deim           | them *
+di             | your (fem.) *
+då             | as/when *
+eg             | I *
+ein            | a/an *
+eit            | a/an *
+eitt           | a/an *
+elles          | or *
+honom          | he *
+hjå            | at *
+ho             | she *
+hoe            | she *
+henne          | her
+hennar         | her/hers
+hennes         | hers
+hoss           | how *
+hossen         | how *
+ikkje          | not *
+ingi           | noone *
+inkje          | noone *
+korleis        | how *
+korso          | how *
+kva            | what/which *
+kvar           | where *
+kvarhelst      | where *
+kven           | who/whom *
+kvi            | why *
+kvifor         | why *
+me             | we *
+medan          | while *
+mi             | my *
+mine           | my *
+mykje          | much *
+no             | now *
+nokon          | some (masc./neut.) *
+noka           | some (fem.) *
+nokor          | some *
+noko           | some *
+nokre          | some *
+si             | his/hers *
+sia            | since *
+sidan          | since *
+so             | so *
+somt           | some *
+somme          | some *
+um             | about*
+upp            | up *
+vere           | be *
+vore           | was *
+verte          | become *
+vort           | become *
+varte          | became *
+vart           | became *
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_pt.txt b/test/solr/configsets/property_search/conf/lang/stopwords_pt.txt
new file mode 100644
index 00000000..acfeb01a
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  of, from
+a              |  the; to, at; her
+o              |  the; him
+que            |  who, that
+e              |  and
+do             |  de + o
+da             |  de + a
+em             |  in
+um             |  a
+para           |  for
+  | é          from SER
+com            |  with
+não            |  not, no
+uma            |  a
+os             |  the; them
+no             |  em + o
+se             |  himself etc
+na             |  em + a
+por            |  for
+mais           |  more
+as             |  the; them
+dos            |  de + os
+como           |  as, like
+mas            |  but
+  | foi        from SER
+ao             |  a + o
+ele            |  he
+das            |  de + as
+  | tem        from TER
+à              |  a + a
+seu            |  his
+sua            |  her
+ou             |  or
+  | ser        from SER
+quando         |  when
+muito          |  much
+  | há         from HAV
+nos            |  em + os; us
+já             |  already, now
+  | está       from EST
+eu             |  I
+também         |  also
+só             |  only, just
+pelo           |  per + o
+pela           |  per + a
+até            |  up to
+isso           |  that
+ela            |  he
+entre          |  between
+  | era        from SER
+depois         |  after
+sem            |  without
+mesmo          |  same
+aos            |  a + os
+  | ter        from TER
+seus           |  his
+quem           |  whom
+nas            |  em + as
+me             |  me
+esse           |  that
+eles           |  they
+  | estão      from EST
+você           |  you
+  | tinha      from TER
+  | foram      from SER
+essa           |  that
+num            |  em + um
+nem            |  nor
+suas           |  her
+meu            |  my
+às             |  a + as
+minha          |  my
+  | têm        from TER
+numa           |  em + uma
+pelos          |  per + os
+elas           |  they
+  | havia      from HAV
+  | seja       from SER
+qual           |  which
+  | será       from SER
+nós            |  we
+  | tenho      from TER
+lhe            |  to him, her
+deles          |  of them
+essas          |  those
+esses          |  those
+pelas          |  per + as
+este           |  this
+  | fosse      from SER
+dele           |  of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu             |  thou
+te             |  thee
+vocês          |  you (plural)
+vos            |  you
+lhes           |  to them
+meus           |  my
+minhas
+teu            |  thy
+tua
+teus
+tuas
+nosso          | our
+nossa
+nossos
+nossas
+
+dela           |  of her
+delas          |  of them
+
+esta           |  this
+estes          |  these
+estas          |  these
+aquele         |  that
+aquela         |  that
+aqueles        |  those
+aquelas        |  those
+isto           |  this
+aquilo         |  that
+
+               | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+               | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+               | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+               | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ro.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ro.txt
new file mode 100644
index 00000000..4fdee90a
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în 
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_ru.txt b/test/solr/configsets/property_search/conf/lang/stopwords_ru.txt
new file mode 100644
index 00000000..55271400
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и              | and
+в              | in/into
+во             | alternative form
+не             | not
+что            | what/that
+он             | he
+на             | on/onto
+я              | i
+с              | from
+со             | alternative form
+как            | how
+а              | milder form of `no' (but)
+то             | conjunction and form of `that'
+все            | all
+она            | she
+так            | so, thus
+его            | him
+но             | but
+да             | yes/and
+ты             | thou
+к              | towards, by
+у              | around, chez
+же             | intensifier particle
+вы             | you
+за             | beyond, behind
+бы             | conditional/subj. particle
+по             | up to, along
+только         | only
+ее             | her
+мне            | to me
+было           | it was
+вот            | here is/are, particle
+от             | away from
+меня           | me
+еще            | still, yet, more
+нет            | no, there isnt/arent
+о              | about
+из             | out of
+ему            | to him
+теперь         | now
+когда          | when
+даже           | even
+ну             | so, well
+вдруг          | suddenly
+ли             | interrogative particle
+если           | if
+уже            | already, but homonym of `narrower'
+или            | or
+ни             | neither
+быть           | to be
+был            | he was
+него           | prepositional form of его
+до             | up to
+вас            | you accusative
+нибудь         | indef. suffix preceded by hyphen
+опять          | again
+уж             | already, but homonym of `adder'
+вам            | to you
+сказал         | he said
+ведь           | particle `after all'
+там            | there
+потом          | then
+себя           | oneself
+ничего         | nothing
+ей             | to her
+может          | usually with `быть' as `maybe'
+они            | they
+тут            | here
+где            | where
+есть           | there is/are
+надо           | got to, must
+ней            | prepositional form of  ей
+для            | for
+мы             | we
+тебя           | thee
+их             | them, their
+чем            | than
+была           | she was
+сам            | self
+чтоб           | in order to
+без            | without
+будто          | as if
+человек        | man, person, one
+чего           | genitive form of `what'
+раз            | once
+тоже           | also
+себе           | to oneself
+под            | beneath
+жизнь          | life
+будет          | will be
+ж              | short form of intensifer particle `же'
+тогда          | then
+кто            | who
+этот           | this
+говорил        | was saying
+того           | genitive form of `that'
+потому         | for that reason
+этого          | genitive form of `this'
+какой          | which
+совсем         | altogether
+ним            | prepositional form of `его', `они'
+здесь          | here
+этом           | prepositional form of `этот'
+один           | one
+почти          | almost
+мой            | my
+тем            | instrumental/dative plural of `тот', `то'
+чтобы          | full form of `in order that'
+нее            | her (acc.)
+кажется        | it seems
+сейчас         | now
+были           | they were
+куда           | where to
+зачем          | why
+сказать        | to say
+всех           | all (acc., gen. preposn. plural)
+никогда        | never
+сегодня        | today
+можно          | possible, one can
+при            | by
+наконец        | finally
+два            | two
+об             | alternative form of `о', about
+другой         | another
+хоть           | even
+после          | after
+над            | above
+больше         | more
+тот            | that one (masc.)
+через          | across, in
+эти            | these
+нас            | us
+про            | about
+всего          | in all, only, of all
+них            | prepositional form of `они' (they)
+какая          | which, feminine
+много          | lots
+разве          | interrogative particle
+сказала        | she said
+три            | three
+эту            | this, acc. fem. sing.
+моя            | my, feminine
+впрочем        | moreover, besides
+хорошо         | good
+свою           | ones own, acc. fem. sing.
+этой           | oblique form of `эта', fem. `this'
+перед          | in front of
+иногда         | sometimes
+лучше          | better
+чуть           | a little
+том            | preposn. form of `that one'
+нельзя         | one must not
+такой          | such a one
+им             | to them
+более          | more
+всегда         | always
+конечно        | of course
+всю            | acc. fem. sing of `all'
+между          | between
+
+
+  | b: some paradigms
+  |
+  | personal pronouns
+  |
+  | я  меня  мне  мной  [мною]
+  | ты  тебя  тебе  тобой  [тобою]
+  | он  его  ему  им  [него, нему, ним]
+  | она  ее  эи  ею  [нее, нэи, нею]
+  | оно  его  ему  им  [него, нему, ним]
+  |
+  | мы  нас  нам  нами
+  | вы  вас  вам  вами
+  | они  их  им  ими  [них, ним, ними]
+  |
+  |   себя  себе  собой   [собою]
+  |
+  | demonstrative pronouns: этот (this), тот (that)
+  |
+  | этот  эта  это  эти
+  | этого  эты  это  эти
+  | этого  этой  этого  этих
+  | этому  этой  этому  этим
+  | этим  этой  этим  [этою]  этими
+  | этом  этой  этом  этих
+  |
+  | тот  та  то  те
+  | того  ту  то  те
+  | того  той  того  тех
+  | тому  той  тому  тем
+  | тем  той  тем  [тою]  теми
+  | том  той  том  тех
+  |
+  | determinative pronouns
+  |
+  | (a) весь (all)
+  |
+  | весь  вся  все  все
+  | всего  всю  все  все
+  | всего  всей  всего  всех
+  | всему  всей  всему  всем
+  | всем  всей  всем  [всею]  всеми
+  | всем  всей  всем  всех
+  |
+  | (b) сам (himself etc)
+  |
+  | сам  сама  само  сами
+  | самого саму  само  самих
+  | самого самой самого  самих
+  | самому самой самому  самим
+  | самим  самой  самим  [самою]  самими
+  | самом самой самом  самих
+  |
+  | stems of verbs `to be', `to have', `to do' and modal
+  |
+  | быть  бы  буд  быв  есть  суть
+  | име
+  | дел
+  | мог   мож  мочь
+  | уме
+  | хоч  хот
+  | долж
+  | можн
+  | нужн
+  | нельзя
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_sv.txt b/test/solr/configsets/property_search/conf/lang/stopwords_sv.txt
new file mode 100644
index 00000000..096f87f6
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ |  så = so, but also seed. These are indicated clearly below.
+
+och            | and
+det            | it, this/that
+att            | to (with infinitive)
+i              | in, at
+en             | a
+jag            | I
+hon            | she
+som            | who, that
+han            | he
+på             | on
+den            | it, this/that
+med            | with
+var            | where, each
+sig            | him(self) etc
+för            | for
+så             | so (also: seed)
+till           | to
+är             | is
+men            | but
+ett            | a
+om             | if; around, about
+hade           | had
+de             | they, these/those
+av             | of
+icke           | not, no
+mig            | me
+du             | you
+henne          | her
+då             | then, when
+sin            | his
+nu             | now
+har            | have
+inte           | inte någon = no one
+hans           | his
+honom          | him
+skulle         | 'sake'
+hennes         | her
+där            | there
+min            | my
+man            | one (pronoun)
+ej             | nor
+vid            | at, by, on (also: vast)
+kunde          | could
+något          | some etc
+från           | from, off
+ut             | out
+när            | when
+efter          | after, behind
+upp            | up
+vi             | we
+dem            | them
+vara           | be
+vad            | what
+över           | over
+än             | than
+dig            | you
+kan            | can
+sina           | his
+här            | here
+ha             | have
+mot            | towards
+alla           | all
+under          | under (also: wonder)
+någon          | some etc
+eller          | or (else)
+allt           | all
+mycket         | much
+sedan          | since
+ju             | why
+denna          | this/that
+själv          | myself, yourself etc
+detta          | this/that
+åt             | to
+utan           | without
+varit          | was
+hur            | how
+ingen          | no
+mitt           | my
+ni             | you
+bli            | to be, become
+blev           | from bli
+oss            | us
+din            | thy
+dessa          | these/those
+några          | some etc
+deras          | their
+blir           | from bli
+mina           | my
+samma          | (the) same
+vilken         | who, that
+er             | you, your
+sådan          | such a
+vår            | our
+blivit         | from bli
+dess           | its
+inom           | within
+mellan         | between
+sådant         | such a
+varför         | why
+varje          | each
+vilka          | who, that
+ditt           | thy
+vem            | who
+vilket         | who, that
+sitta          | his
+sådana         | such a
+vart           | each
+dina           | thy
+vars           | whose
+vårt           | our
+våra           | our
+ert            | your
+era            | your
+vilkas         | whose
+
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_th.txt b/test/solr/configsets/property_search/conf/lang/stopwords_th.txt
new file mode 100644
index 00000000..07f0fabe
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
diff --git a/test/solr/configsets/property_search/conf/lang/stopwords_tr.txt b/test/solr/configsets/property_search/conf/lang/stopwords_tr.txt
new file mode 100644
index 00000000..84d9408d
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+#   (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
diff --git a/test/solr/configsets/property_search/conf/lang/userdict_ja.txt b/test/solr/configsets/property_search/conf/lang/userdict_ja.txt
new file mode 100644
index 00000000..6f0368e4
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags.  Notice that entries do
+# not have weights since they are always used when found.  This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+#  <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored.  Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
diff --git a/test/solr/configsets/property_search/conf/managed-schema b/test/solr/configsets/property_search/conf/managed-schema
new file mode 100644
index 00000000..e99e27e9
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/managed-schema
@@ -0,0 +1,1031 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+
+ For more information, on how to customize this file, please see
+ http://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+-->
+
+<schema name="default-config" version="1.6">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and 
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued 
+            by nature
+       1.1: multiValued attribute introduced, false by default 
+       1.2: omitTermFreqAndPositions attribute introduced, true by default 
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults 
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types 
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a field type from the 
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc Values is
+       recommended (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc Values will make the index
+       faster to load, more NRT-friendly and more memory-efficient. 
+       They are currently only supported by StrField, UUIDField, all 
+       *PointFields, and depending on the field type, they might require
+       the field to be single-valued, be required or have a default value
+       (check the documentation of the field type you're interested in for
+       more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.  
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This 
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this _default configset, only four fields are pre-declared:
+         id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
+         
+         Note that many dynamic fields are also defined - you can use them to specify a 
+         field's type via field naming conventions - see below.
+  
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- docValues are enabled by default for long type so we don't need to index the version field  -->
+    <field name="_version_" type="plong" indexed="false" stored="false"/>
+
+    <!-- If you don't use child/nested documents, then you should remove the next two fields:  -->
+    <!-- for nested documents (minimal; points to root document) -->
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <!-- for nested documents (relationship tracking) -->
+    <field name="_nest_path_" type="_nest_path_" /><fieldType name="_nest_path_" class="solr.NestPathField" />
+
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+    <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+         because it's very expensive to index everything twice. -->
+    <!-- <copyField source="*" dest="_text_"/> -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end.  -->
+   
+    <dynamicField name="*_i"  type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="random_*" type="random"/>
+    <dynamicField name="ignored_*" type="ignored"/>
+
+    <!-- Type used for data-driven schema, to add a string copy for each text field -->
+    <dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
+
+    <dynamicField name="*_dt"  type="pdate"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="pdate"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching.
+
+    <copyField source="sourceFieldName" dest="destinationFieldName"/>
+    -->
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+       This includes "string", "boolean", "pint", "pfloat", "plong", "pdate", "pdouble".
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!--
+      Numeric field types that index values using KD-trees.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+
+    <!-- since fields of this type are by default not stored or indexed,
+       any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+                      
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+    
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+    
+    <!-- 
+    RankFields can be used to store scoring factors to improve document ranking. They should be used
+    in combination with RankQParserPlugin.
+    (experimental)
+    --> 
+    <fieldType name="rank" class="solr.RankField"/>
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    
+    <!-- SortableTextField generaly functions exactly like TextField,
+         except that it supports, and by default uses, docValues for sorting (or faceting)
+         on the first 1024 characters of the original field values (which is configurable).
+         
+         This makes it a bit more useful then TextField in many situations, but the trade-off
+         is that it takes up more space on disk; which is why it's not used in place of TextField
+         for every fieldType in this _default schema.
+	  -->
+    <dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
+    <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
+         removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- 
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if 
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- A geospatial field type that supports multiValued and polygon shapes.
+      For more information about this and other spatial fields see:
+      http://lucene.apache.org/solr/guide/spatial-search.html
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/> 
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
+        <filter class="solr.BulgarianStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Estonian -->
+    <dynamicField name="*_txt_et" type="text_et"  indexed="true"  stored="true"/>
+    <fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
+      </analyzer>
+    </fieldType>
+    
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Korean morphological analysis -->
+    <dynamicField name="*_txt_ko" type="text_ko"  indexed="true"  stored="true"/>
+    <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
+          The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
+          It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
+
+          This dictionary was built with MeCab, it defines a format for the features adapted
+          for the Korean language.
+          
+          Nori also has a convenient user dictionary feature that allows overriding the statistical
+          model with your own entries for segmentation, part-of-speech tags and readings without a need
+          to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+          The tokenizer supports multiple schema attributes:
+            * userDictionary: User dictionary path.
+            * userDictionaryEncoding: User dictionary encoding.
+            * decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
+            * outputUnknownUnigrams: If true outputs unigrams for unknown words.
+        -->
+        <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
+        <!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
+          listing the tags to remove. By default it removes: 
+          E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
+          This is basically an equivalent to stemming.
+        -->
+        <filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
+        <!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
+        <filter class="solr.KoreanReadingFormFilterFactory" />
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but 
+       the default is fine for most applications.  
+       For more info: http://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/test/solr/configsets/property_search/conf/mapping-ISOLatin1Accent.txt b/test/solr/configsets/property_search/conf/mapping-ISOLatin1Accent.txt
new file mode 100644
index 00000000..ede77425
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/mapping-ISOLatin1Accent.txt
@@ -0,0 +1,246 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Syntax:
+#   "source" => "target"
+#     "source".length() > 0 (source cannot be empty.)
+#     "target".length() >= 0 (target can be empty.)
+
+# example:
+#   "À" => "A"
+#   "\u00C0" => "A"
+#   "\u00C0" => "\u0041"
+#   "ß" => "ss"
+#   "\t" => " "
+#   "\n" => ""
+
+# À => A
+"\u00C0" => "A"
+
+# Á => A
+"\u00C1" => "A"
+
+# Â => A
+"\u00C2" => "A"
+
+# Ã => A
+"\u00C3" => "A"
+
+# Ä => A
+"\u00C4" => "A"
+
+# Å => A
+"\u00C5" => "A"
+
+# Æ => AE
+"\u00C6" => "AE"
+
+# Ç => C
+"\u00C7" => "C"
+
+# È => E
+"\u00C8" => "E"
+
+# É => E
+"\u00C9" => "E"
+
+# Ê => E
+"\u00CA" => "E"
+
+# Ë => E
+"\u00CB" => "E"
+
+# Ì => I
+"\u00CC" => "I"
+
+# Í => I
+"\u00CD" => "I"
+
+# Î => I
+"\u00CE" => "I"
+
+# Ï => I
+"\u00CF" => "I"
+
+# IJ => IJ
+"\u0132" => "IJ"
+
+# Ð => D
+"\u00D0" => "D"
+
+# Ñ => N
+"\u00D1" => "N"
+
+# Ò => O
+"\u00D2" => "O"
+
+# Ó => O
+"\u00D3" => "O"
+
+# Ô => O
+"\u00D4" => "O"
+
+# Õ => O
+"\u00D5" => "O"
+
+# Ö => O
+"\u00D6" => "O"
+
+# Ø => O
+"\u00D8" => "O"
+
+# Π=> OE
+"\u0152" => "OE"
+
+# Þ
+"\u00DE" => "TH"
+
+# Ù => U
+"\u00D9" => "U"
+
+# Ú => U
+"\u00DA" => "U"
+
+# Û => U
+"\u00DB" => "U"
+
+# Ü => U
+"\u00DC" => "U"
+
+# Ý => Y
+"\u00DD" => "Y"
+
+# Ÿ => Y
+"\u0178" => "Y"
+
+# à => a
+"\u00E0" => "a"
+
+# á => a
+"\u00E1" => "a"
+
+# â => a
+"\u00E2" => "a"
+
+# ã => a
+"\u00E3" => "a"
+
+# ä => a
+"\u00E4" => "a"
+
+# å => a
+"\u00E5" => "a"
+
+# æ => ae
+"\u00E6" => "ae"
+
+# ç => c
+"\u00E7" => "c"
+
+# è => e
+"\u00E8" => "e"
+
+# é => e
+"\u00E9" => "e"
+
+# ê => e
+"\u00EA" => "e"
+
+# ë => e
+"\u00EB" => "e"
+
+# ì => i
+"\u00EC" => "i"
+
+# í => i
+"\u00ED" => "i"
+
+# î => i
+"\u00EE" => "i"
+
+# ï => i
+"\u00EF" => "i"
+
+# ij => ij
+"\u0133" => "ij"
+
+# ð => d
+"\u00F0" => "d"
+
+# ñ => n
+"\u00F1" => "n"
+
+# ò => o
+"\u00F2" => "o"
+
+# ó => o
+"\u00F3" => "o"
+
+# ô => o
+"\u00F4" => "o"
+
+# õ => o
+"\u00F5" => "o"
+
+# ö => o
+"\u00F6" => "o"
+
+# ø => o
+"\u00F8" => "o"
+
+# œ => oe
+"\u0153" => "oe"
+
+# ß => ss
+"\u00DF" => "ss"
+
+# þ => th
+"\u00FE" => "th"
+
+# ù => u
+"\u00F9" => "u"
+
+# ú => u
+"\u00FA" => "u"
+
+# û => u
+"\u00FB" => "u"
+
+# ü => u
+"\u00FC" => "u"
+
+# ý => y
+"\u00FD" => "y"
+
+# ÿ => y
+"\u00FF" => "y"
+
+# ff => ff
+"\uFB00" => "ff"
+
+# fi => fi
+"\uFB01" => "fi"
+
+# fl => fl
+"\uFB02" => "fl"
+
+# ffi => ffi
+"\uFB03" => "ffi"
+
+# ffl => ffl
+"\uFB04" => "ffl"
+
+# ſt => ft
+"\uFB05" => "ft"
+
+# st => st
+"\uFB06" => "st"
diff --git a/test/solr/configsets/property_search/conf/protwords.txt b/test/solr/configsets/property_search/conf/protwords.txt
new file mode 100644
index 00000000..1dfc0abe
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
diff --git a/test/solr/configsets/property_search/conf/schema.xml b/test/solr/configsets/property_search/conf/schema.xml
new file mode 100644
index 00000000..20824ea6
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/schema.xml
@@ -0,0 +1,1179 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
+-->
+
+<schema name="ncbo_property" version="1.7">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued
+            by nature
+       1.1: multiValued attribute introduced, false by default
+       1.2: omitTermFreqAndPositions attribute introduced, true by default
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandat ory - the name for the field
+     type: mandatory - the name of a field type from the
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc values are
+       useful (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc values will make the index
+       faster to load, more NRT-friendly and more memory-efficient.
+       They however come with some limitations: they are currently only
+       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+       and depending on the field type, they might require the field to be
+       single-valued, be required or have a default value (check the
+       documentation of the field type you're interested in for more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+         id, _version_, and _text_.  All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared
+         in solrconfig.xml.
+
+         Note that many dynamic fields are also defined - you can use them to specify a
+         field's type via field naming conventions - see below.
+
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
+    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+
+    <!-- NCBO specific fields -->
+    <field name="resource_id"                type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
+
+    <!-- searchable fields -->
+    <field name="label"                      type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelExact"                 type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelSuggest"               type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="labelSuggestEdge"           type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelSuggestNgram"          type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <field name="labelGenerated"             type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedExact"        type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedSuggest"      type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="labelGeneratedSuggestEdge"  type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="labelGeneratedSuggestNgram" type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <field name="definition"                 type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="submissionAcronym"          type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="parents"                    type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="ontologyType"               type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="propertyType"               type="propertyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="ontologyId"                 type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"               type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <!-- END: NCBO specific fields -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have
+       a "*" only at the start or the end.  -->
+
+    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
+
+    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- KD-tree (point) numerics -->
+    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
+
+    <!-- some trie-coded dynamic fields -->
+    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <dynamicField name="random_*" type="random" />
+
+    <!-- uncomment the following to ignore any fields that don't already match an existing
+        field name or dynamic field, rather than reporting them as an error.
+        alternately, change the type="ignored" to some other type e.g. "text" if you want
+        unknown fields indexed and/or stored by default
+
+        NB: use of "*" dynamic fields will disable field type guessing and adding
+        unknown fields to the schema. -->
+    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching. -->
+
+    <copyField source="label" dest="_text_"/>
+    <copyField source="label" dest="labelExact"/>
+    <copyField source="label" dest="labelSuggest" />
+    <copyField source="label" dest="labelSuggestEdge" />
+    <copyField source="label" dest="labelSuggestNgram" />
+
+    <copyField source="labelGenerated" dest="_text_"/>
+    <copyField source="labelGenerated" dest="labelGeneratedExact"/>
+    <copyField source="labelGenerated" dest="labelGeneratedSuggest" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestEdge" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestNgram" />
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
+    <fieldType name="propertyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="propertyType"/>
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+       It supports doc values but in that case the field needs to be
+       single-valued and either required or have a default value.
+      -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	     This includes "string","boolean", "int", "float", "long", "date", "double",
+	     including the "Trie" and "Point" variants.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!--
+      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+      search time and at index time, but some features are still not supported.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+    <!--
+      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+      tint/tfloat/tlong/tdouble types.
+    -->
+    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+    <!--
+     Numeric field types that index each value at various levels of precision
+     to accelerate range queries when the number of values between the range
+     endpoints is large. See the javadoc for NumericRangeQuery for internal
+     implementation details.
+
+     Smaller precisionStep values (specified in bits) will lead to more tokens
+     indexed per value, slightly larger index size, and faster range queries.
+     A precisionStep of 0 disables indexing at different precision levels.
+
+     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+    -->
+    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+
+         Consult the TrieDateField javadocs for more information.
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+
+    <!-- The "RandomSortField" is not used to store or search any
+         data.  You can declare fields of this type it in your schema
+         to generate pseudo-random orderings of your docs for sorting
+         or function purposes.  The ordering is generated based on the field
+         name and the version of the index. As long as the index version
+         remains unchanged, and the same field name is reused,
+         the ordering of the docs will be consistent.
+         If you want different psuedo-random orderings of documents,
+         for the same version of the index, use a dynamicField and
+         change the field name in the request.
+     -->
+    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+        wild card phrases bypass the query analyzer and will not be lowercased before matching
+        against the index. This means that the characters in wildcard phrases must be lowercase in
+        order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it
+         tokenizes with StandardTokenizer, removes English stop words
+         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer
+         also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
+      For more information about this and other Spatial fields new to Solr 4, see:
+      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+        <filter class="solr.BulgarianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+
+           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but
+       the default is fine for most applications.
+       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/test/solr/configsets/property_search/conf/solrconfig.xml b/test/solr/configsets/property_search/conf/solrconfig.xml
new file mode 100644
index 00000000..771a0f32
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/solrconfig.xml
@@ -0,0 +1,1299 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+     For more details about configurations options that may appear in
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+  <!-- In all configuration below, a prefix of "solr." for class names
+       is an alias that causes solr to search appropriate packages,
+       including org.apache.solr.(search|update|request|core|analysis)
+
+       You may also specify a fully qualified Java classname if you
+       have your own custom plugins.
+    -->
+
+  <!-- Controls what version of Lucene various components of Solr
+       adhere to.  Generally, you want to use the latest version to
+       get all bug fixes and improvements. It is highly recommended
+       that you fully re-index after changing this setting as it can
+       affect both how text is indexed and queried.
+  -->
+  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+
+  <!-- <lib/> directives can be used to instruct Solr to load any Jars
+       identified and use them to resolve any "plugins" specified in
+       your solrconfig.xml or schema.xml (ie: Analyzers, Request
+       Handlers, etc...).
+
+       All directories and paths are resolved relative to the
+       instanceDir.
+
+       Please note that <lib/> directives are processed in the order
+       that they appear in your solrconfig.xml file, and are "stacked"
+       on top of each other when building a ClassLoader - so if you have
+       plugin jars with dependencies on other jars, the "lower level"
+       dependency jars should be loaded first.
+
+       If a "./lib" directory exists in your instanceDir, all files
+       found in it are included as if you had used the following
+       syntax...
+
+              <lib dir="./lib" />
+    -->
+
+  <!-- A 'dir' option by itself adds any files found in the directory
+       to the classpath, this is useful for including all jars in a
+       directory.
+
+       When a 'regex' is specified in addition to a 'dir', only the
+       files in that directory which completely match the regex
+       (anchored on both ends) will be included.
+
+       If a 'dir' option (with or without a regex) is used and nothing
+       is found that matches, a warning will be logged.
+
+       The example below can be used to load a solr-contrib along
+       with their external dependencies.
+    -->
+    <!-- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
+
+  <!-- an exact 'path' can be used instead of a 'dir' to specify a
+       specific jar file.  This will cause a serious error to be logged
+       if it can't be loaded.
+    -->
+  <!--
+     <lib path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
+    -->
+  <dataDir>${solr.data.dir:}</dataDir>
+
+
+  <!-- The DirectoryFactory to use for indexes.
+
+       solr.StandardDirectoryFactory is filesystem
+       based and tries to pick the best implementation for the current
+       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
+       wraps solr.StandardDirectoryFactory and caches small files in memory
+       for better NRT performance.
+
+       One can force a particular implementation via solr.MMapDirectoryFactory,
+       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+       solr.RAMDirectoryFactory is memory based and not persistent.
+    -->
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+       A "compressionMode" string element can be added to <codecFactory> to choose
+       between the existing compression modes in the default codec: "BEST_SPEED" (default)
+       or "BEST_COMPRESSION".
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <!-- NCBO: for now using the unmanaged schema (user-defined) -->
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Index Config - These settings control low-level behavior of indexing
+       Most example settings here show the default value, but are commented
+       out, to more easily see where customizations have been made.
+
+       Note: This replaces <indexDefaults> and <mainIndex> from older versions
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <indexConfig>
+    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+         LimitTokenCountFilterFactory in your fieldType definition. E.g.
+     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+    -->
+    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
+
+    <!-- Expert: Enabling compound file will use less files for the index,
+         using fewer file descriptors on the expense of performance decrease.
+         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+    <!-- <useCompoundFile>false</useCompoundFile> -->
+
+    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+         indexing for buffering added documents and deletions before they are
+         flushed to the Directory.
+         maxBufferedDocs sets a limit on the number of documents buffered
+         before flushing.
+         If both ramBufferSizeMB and maxBufferedDocs is set, then
+         Lucene will flush based on whichever limit is hit first.  -->
+    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+    <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+         per thread before they are flushed. When limit is exceeded, this triggers a forced
+         flush even if ramBufferSizeMB has not been exceeded.
+         This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+         exhaustion due to its internal 32 bit signed integer based memory addressing.
+         The specified value should be greater than 0 and less than 2048MB. When not specified,
+         Solr uses Lucene's default value 1945. -->
+    <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+    <!-- Expert: Merge Policy
+         The Merge Policy in Lucene controls how merging of segments is done.
+         The default since Solr/Lucene 3.3 is TieredMergePolicy.
+         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+         Even older versions of Lucene used LogDocMergePolicy.
+      -->
+    <!--
+        <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+          <int name="maxMergeAtOnce">10</int>
+          <int name="segmentsPerTier">10</int>
+          <double name="noCFSRatio">0.1</double>
+        </mergePolicyFactory>
+      -->
+
+    <!-- Expert: Merge Scheduler
+         The Merge Scheduler in Lucene controls how merges are
+         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+         can perform merges in the background using separate threads.
+         The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--
+       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+       -->
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
+    -->
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Commit Deletion Policy
+         Custom deletion policies can be specified here. The class must
+         implement org.apache.lucene.index.IndexDeletionPolicy.
+
+         The default Solr IndexDeletionPolicy implementation supports
+         deleting index commit points on number of commits, age of
+         commit point and optimized status.
+
+         The latest commit point should always be preserved regardless
+         of the criteria.
+    -->
+    <!--
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+    -->
+    <!-- The number of commit points to be kept -->
+    <!-- <str name="maxCommitsToKeep">1</str> -->
+    <!-- The number of optimized commit points to be kept -->
+    <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+    <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g.
+      -->
+    <!--
+       <str name="maxCommitAge">30MINUTES</str>
+       <str name="maxCommitAge">1DAY</str>
+    -->
+    <!--
+    </deletionPolicy>
+    -->
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting The value to true will instruct the underlying Lucene
+         IndexWriter to write its debugging info the specified file
+      -->
+    <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+  </indexConfig>
+
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.
+         "numVersionBuckets" - sets the number of buckets used to keep
+                track of max version values when checking for re-ordered
+                updates; increase this value to reduce the cost of
+                synchronizing access to version buckets during high-volume
+                indexing, this requires 8 bytes (long) * numVersionBuckets
+                of heap space per Solr core.
+    -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+    </updateLog>
+
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+    <autoCommit>
+      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+      <openSearcher>false</openSearcher>
+    </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+    <autoSoftCommit>
+      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+    </autoSoftCommit>
+
+    <!-- Update Related Event Listeners
+
+         Various IndexWriter related events can trigger Listeners to
+         take actions.
+
+         postCommit - fired after every commit or optimize command
+         postOptimize - fired after every optimize command
+      -->
+
+  </updateHandler>
+
+  <!-- IndexReaderFactory
+
+       Use the following format to specify a custom IndexReaderFactory,
+       which allows for alternate IndexReader implementations.
+
+       ** Experimental Feature **
+
+       Please note - Using a custom IndexReaderFactory may prevent
+       certain other features from working. The API to
+       IndexReaderFactory may change without warning or may even be
+       removed from future releases if the problems cannot be
+       resolved.
+
+
+       ** Features that may not work with custom IndexReaderFactory **
+
+       The ReplicationHandler assumes a disk-resident index. Using a
+       custom IndexReader implementation may cause incompatibility
+       with ReplicationHandler and may cause replication to not work
+       correctly. See SOLR-1366 for details.
+
+    -->
+  <!--
+  <indexReaderFactory name="IndexReaderFactory" class="package.class">
+    <str name="someArg">Some Value</str>
+  </indexReaderFactory >
+  -->
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <query>
+
+    <!-- Maximum number of clauses allowed when parsing a boolean query string.
+         
+         This limit only impacts boolean queries specified by a user as part of a query string,
+         and provides per-collection controls on how complex user specified boolean queries can
+         be.  Query strings that specify more clauses then this will result in an error.
+         
+         If this per-collection limit is greater then the global `maxBooleanClauses` limit
+         specified in `solr.xml`, it will have no effect, as that setting also limits the size
+         of user specified boolean queries.
+      -->
+    <maxBooleanClauses>${solr.max.booleanClauses:500000}</maxBooleanClauses>
+
+    <!-- Solr Internal Query Caches
+
+         There are four implementations of cache available for Solr:
+         LRUCache, based on a synchronized LinkedHashMap, 
+         LFUCache and FastLRUCache, based on a ConcurrentHashMap, and CaffeineCache -
+         a modern and robust cache implementation. Note that in Solr 9.0
+         only CaffeineCache will be available, other implementations are now
+         deprecated.
+
+         FastLRUCache has faster gets and slower puts in single
+         threaded operation and thus is generally faster than LRUCache
+         when the hit ratio of the cache is high (> 75%), and may be
+         faster under other scenarios on multi-cpu systems.
+         Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
+    -->
+
+    <!-- Filter Cache
+
+         Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.  When a
+         new searcher is opened, its caches may be prepopulated or
+         "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For
+         LRUCache, the autowarmed items will be the most recently
+         accessed items.
+
+         Parameters:
+           class - the SolrCache implementation LRUCache or
+               (LRUCache or FastLRUCache)
+           size - the maximum number of entries in the cache
+           initialSize - the initial capacity (number of entries) of
+               the cache.  (see java.util.HashMap)
+           autowarmCount - the number of entries to prepopulate from
+               an old cache.
+           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                      to occupy. Note that when this option is specified, the size
+                      and initialSize parameters are ignored.
+      -->
+    <filterCache size="512"
+                 initialSize="512"
+                 autowarmCount="0"/>
+
+    <!-- Query Result Cache
+
+         Caches results of searches - ordered lists of document ids
+         (DocList) based on a query, a sort, and the range of documents requested.
+         Additional supported parameter by LRUCache:
+            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                       to occupy
+      -->
+    <queryResultCache size="512"
+                      initialSize="512"
+                      autowarmCount="0"/>
+
+    <!-- Document Cache
+
+         Caches Lucene Document objects (the stored fields for each
+         document).  Since Lucene internal document ids are transient,
+         this cache will not be autowarmed.
+      -->
+    <documentCache size="512"
+                   initialSize="512"
+                   autowarmCount="0"/>
+
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+           size="10"
+           initialSize="0"
+           autowarmCount="10"
+           regenerator="solr.NoOpRegenerator" />
+
+    <!-- Field Value Cache
+
+         Cache used to hold field values that are quickly accessible
+         by document id.  The fieldValueCache is created by default
+         even if not configured here.
+      -->
+    <!--
+       <fieldValueCache size="512"
+                        autowarmCount="128"
+                        showItems="32" />
+      -->
+
+    <!-- Custom Cache
+
+         Example of a generic cache.  These caches may be accessed by
+         name through SolrIndexSearcher.getCache(),cacheLookup(), and
+         cacheInsert().  The purpose is to enable easy caching of
+         user/application level data.  The regenerator argument should
+         be specified as an implementation of solr.CacheRegenerator
+         if autowarming is desired.
+      -->
+    <!--
+       <cache name="myUserCache"
+              size="4096"
+              initialSize="1024"
+              autowarmCount="1024"
+              regenerator="com.mycompany.MyRegenerator"
+              />
+      -->
+
+
+    <!-- Lazy Field Loading
+
+         If true, stored fields that are not requested will be loaded
+         lazily.  This can result in a significant speed improvement
+         if the usual case is to not load all stored fields,
+         especially if the skipped fields are large compressed text
+         fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Use Filter For Sorted Query
+
+         A possible optimization that attempts to use a filter to
+         satisfy a search.  If the requested sort does not include
+         score, then the filterCache will be checked for a filter
+         matching the query. If found, the filter will be used as the
+         source of document ids, and then the sort will be applied to
+         that.
+
+         For most situations, this will not be useful unless you
+         frequently get the same search repeatedly with different sort
+         options, and none of them ever use "score"
+      -->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Result Window Size
+
+         An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 49 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.
+      -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache.
+      -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+  <!-- Use Filter For Sorted Query
+
+   A possible optimization that attempts to use a filter to
+   satisfy a search.  If the requested sort does not include
+   score, then the filterCache will be checked for a filter
+   matching the query. If found, the filter will be used as the
+   source of document ids, and then the sort will be applied to
+   that.
+
+   For most situations, this will not be useful unless you
+   frequently get the same search repeatedly with different sort
+   options, and none of them ever use "score"
+-->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Query Related Event Listeners
+
+         Various IndexSearcher related events can trigger Listeners to
+         take actions.
+
+         newSearcher - fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka
+         registered).  It can be used to prime certain caches to
+         prevent long request times for certain requests.
+
+         firstSearcher - fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from.
+
+
+      -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence.
+      -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+          -->
+      </arr>
+    </listener>
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+        <lst>
+          <str name="q">static firstSearcher warming in solrconfig.xml</str>
+        </lst>
+        -->
+      </arr>
+    </listener>
+
+    <!-- Use Cold Searcher
+
+         If a search request comes in and there is no current
+         registered searcher, then immediately register the still
+         warming searcher and use it.  If "false" then all requests
+         will block until the first searcher is done warming.
+      -->
+    <useColdSearcher>false</useColdSearcher>
+
+  </query>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+     Circuit Breaker Section - This section consists of configurations for
+     circuit breakers
+     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+
+    <!-- Circuit Breakers
+
+     Circuit breakers are designed to allow stability and predictable query
+     execution. They prevent operations that can take down the node and cause
+     noisy neighbour issues.
+
+     This flag is the uber control switch which controls the activation/deactivation of all circuit
+     breakers. If a circuit breaker wishes to be independently configurable,
+     they are free to add their specific configuration but need to ensure that this flag is always
+     respected - this should have veto over all independent configuration flags.
+    -->
+    <circuitBreakers enabled="true">
+
+    <!-- Memory Circuit Breaker Configuration
+
+     Specific configuration for max JVM heap usage circuit breaker. This configuration defines whether
+     the circuit breaker is enabled and the threshold percentage of maximum heap allocated beyond which queries will be rejected until the
+     current JVM usage goes below the threshold. The valid value range for this value is 50-95.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+    -->
+    <!--
+   <memBreaker enabled="true" threshold="75"/>
+    -->
+
+      <!-- CPU Circuit Breaker Configuration
+
+     Specific configuration for CPU utilization based circuit breaker. This configuration defines whether the circuit breaker is enabled
+     and the average load over the last minute at which the circuit breaker should start rejecting queries.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+    -->
+
+      <!--
+       <cpuBreaker enabled="true" threshold="75"/>
+      -->
+
+  </circuitBreakers>
+
+
+  <!-- Request Dispatcher
+
+       This section contains instructions for how the SolrDispatchFilter
+       should behave when processing requests for this SolrCore.
+
+    -->
+  <requestDispatcher>
+    <!-- Request Parsing
+
+         These settings indicate how Solr Requests may be parsed, and
+         what restrictions may be placed on the ContentStreams from
+         those requests
+
+         enableRemoteStreaming - enables use of the stream.file
+         and stream.url parameters for specifying remote streams.
+
+         multipartUploadLimitInKB - specifies the max size (in KiB) of
+         Multipart File Uploads that Solr will allow in a Request.
+
+         formdataUploadLimitInKB - specifies the max size (in KiB) of
+         form data (application/x-www-form-urlencoded) sent via
+         POST. You can use POST to pass request parameters not
+         fitting into the URL.
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
+         *** WARNING ***
+         Before enabling remote streaming, you should make sure your
+         system has authentication enabled.
+
+    <requestParsers enableRemoteStreaming="false"
+                    multipartUploadLimitInKB="-1"
+                    formdataUploadLimitInKB="-1"
+                    addHttpRequestToContext="false"/>
+      -->
+
+    <!-- HTTP Caching
+
+         Set HTTP caching related parameters (for proxy caches and clients).
+
+         The options below instruct Solr not to output any HTTP Caching
+         related headers
+      -->
+    <httpCaching never304="true" />
+    <!-- If you include a <cacheControl> directive, it will be used to
+         generate a Cache-Control header (as well as an Expires header
+         if the value contains "max-age=")
+
+         By default, no Cache-Control header is generated.
+
+         You can use the <cacheControl> option even if you have set
+         never304="true"
+      -->
+    <!--
+       <httpCaching never304="true" >
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+    <!-- To enable Solr to respond with automatically generated HTTP
+         Caching headers, and to response to Cache Validation requests
+         correctly, set the value of never304="false"
+
+         This will cause Solr to generate Last-Modified and ETag
+         headers based on the properties of the Index.
+
+         The following options can also be specified to affect the
+         values of these headers...
+
+         lastModFrom - the default value is "openTime" which means the
+         Last-Modified value (and validation against If-Modified-Since
+         requests) will all be relative to when the current Searcher
+         was opened.  You can change it to lastModFrom="dirLastMod" if
+         you want the value to exactly correspond to when the physical
+         index was last modified.
+
+         etagSeed="..." is an option you can change to force the ETag
+         header (and validation against If-None-Match requests) to be
+         different even if the index has not changed (ie: when making
+         significant changes to your config file)
+
+         (lastModifiedFrom and etagSeed are both ignored if you use
+         the never304="true" option)
+      -->
+    <!--
+       <httpCaching lastModifiedFrom="openTime"
+                    etagSeed="Solr">
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+  </requestDispatcher>
+
+  <!-- Request Handlers
+
+       http://wiki.apache.org/solr/SolrRequestHandler
+
+       Incoming queries will be dispatched to a specific handler by name
+       based on the path specified in the request.
+
+       If a Request Handler is declared with startup="lazy", then it will
+       not be initialized until the first request that uses it.
+
+    -->
+  <!-- SearchHandler
+
+       http://wiki.apache.org/solr/SearchHandler
+
+       For processing Search Queries, the primary Request Handler
+       provided with Solr is "SearchHandler" It delegates to a sequent
+       of SearchComponents (see below) and supports distributed
+       queries across multiple shards
+    -->
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <int name="rows">10</int>
+      <!-- Default search field
+         <str name="df">text</str> 
+        -->
+      <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+         <str name="wt">xml</str> 
+        -->
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+      -->
+    <!-- In this example, the param "fq=instock:true" would be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="appends">
+         <str name="fq">inStock:true</str>
+       </lst>
+      -->
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params would
+         be fixed, limiting the facets clients can use.  Faceting is
+         not turned on by default - but if the client does specify
+         facet=true in the request, these are the only facets they
+         will be able to see counts for; regardless of what other
+         facet.field or facet.query params they may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="invariants">
+         <str name="facet.field">cat</str>
+         <str name="facet.field">manu_exact</str>
+         <str name="facet.query">price:[* TO 500]</str>
+         <str name="facet.query">price:[500 TO *]</str>
+       </lst>
+      -->
+    <!-- If the default list of SearchComponents is not desired, that
+         list can either be overridden completely, or components can be
+         prepended or appended to the default list.  (see below)
+      -->
+    <!--
+       <arr name="components">
+         <str>nameOfCustomComponent1</str>
+         <str>nameOfCustomComponent2</str>
+       </arr>
+      -->
+  </requestHandler>
+
+  <!-- A request handler that returns indented JSON by default -->
+  <requestHandler name="/query" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <str name="wt">json</str>
+      <str name="indent">true</str>
+    </lst>
+  </requestHandler>
+
+  <initParams path="/update/**,/query,/select,/spell">
+    <lst name="defaults">
+      <str name="df">_text_</str>
+    </lst>
+  </initParams>
+
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
+
+       Default configuration in a requestHandler would look like:
+
+       <arr name="components">
+         <str>query</str>
+         <str>facet</str>
+         <str>mlt</str>
+         <str>highlight</str>
+         <str>stats</str>
+         <str>debug</str>
+       </arr>
+
+       If you register a searchComponent to one of the standard names,
+       that will be used instead of the default.
+
+       To insert components before or after the 'standard' components, use:
+
+       <arr name="first-components">
+         <str>myFirstComponentName</str>
+       </arr>
+
+       <arr name="last-components">
+         <str>myLastComponentName</str>
+       </arr>
+
+       NOTE: The component registered with the name "debug" will
+       always be executed after the "last-components"
+
+     -->
+
+  <!-- Spell Check
+
+       The spell check component can return a list of alternative spelling
+       suggestions.
+
+       http://wiki.apache.org/solr/SpellCheckComponent
+    -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">text_general</str>
+
+    <!-- Multiple "Spell Checkers" can be declared and used by this
+         component
+      -->
+
+    <!-- a spellchecker built from a field of the main index -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">_text_</str>
+      <str name="classname">solr.DirectSolrSpellChecker</str>
+      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+      <str name="distanceMeasure">internal</str>
+      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+      <float name="accuracy">0.5</float>
+      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+      <int name="maxEdits">2</int>
+      <!-- the minimum shared prefix when enumerating terms -->
+      <int name="minPrefix">1</int>
+      <!-- maximum number of inspections per result. -->
+      <int name="maxInspections">5</int>
+      <!-- minimum length of a query term to be considered for correction -->
+      <int name="minQueryLength">4</int>
+      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+      <float name="maxQueryFrequency">0.01</float>
+      <!-- uncomment this to require suggestions to occur in 1% of the documents
+        <float name="thresholdTokenFrequency">.01</float>
+      -->
+    </lst>
+
+    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
+    <!--
+    <lst name="spellchecker">
+      <str name="name">wordbreak</str>
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
+      <str name="field">name</str>
+      <str name="combineWords">true</str>
+      <str name="breakWords">true</str>
+      <int name="maxChanges">10</int>
+    </lst>
+    -->
+  </searchComponent>
+
+  <!-- A request handler for demonstrating the spellcheck component.
+
+       NOTE: This is purely as an example.  The whole purpose of the
+       SpellCheckComponent is to hook it into the request handler that
+       handles your normal user queries so that a separate request is
+       not needed to get suggestions.
+
+       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+       See http://wiki.apache.org/solr/SpellCheckComponent for details
+       on the request parameters.
+    -->
+  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <!-- Solr will use suggestions from both the 'default' spellchecker
+           and from the 'wordbreak' spellchecker and combine them.
+           collations (re-written queries) can include a combination of
+           corrections from both spellcheckers -->
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck">on</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.count">10</str>
+      <str name="spellcheck.alternativeTermCount">5</str>
+      <str name="spellcheck.maxResultsForSuggest">5</str>
+      <str name="spellcheck.collate">true</str>
+      <str name="spellcheck.collateExtendedResults">true</str>
+      <str name="spellcheck.maxCollationTries">10</str>
+      <str name="spellcheck.maxCollations">5</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
+  <searchComponent name="terms" class="solr.TermsComponent"/>
+
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Highlighting Component
+
+       http://wiki.apache.org/solr/HighlightingParameters
+    -->
+  <searchComponent class="solr.HighlightComponent" name="highlight">
+    <highlighting>
+      <!-- Configure the standard fragmenter -->
+      <!-- This could most likely be commented out in the "default" case -->
+      <fragmenter name="gap"
+                  default="true"
+                  class="solr.highlight.GapFragmenter">
+        <lst name="defaults">
+          <int name="hl.fragsize">100</int>
+        </lst>
+      </fragmenter>
+
+      <!-- A regular-expression-based fragmenter
+           (for sentence extraction)
+        -->
+      <fragmenter name="regex"
+                  class="solr.highlight.RegexFragmenter">
+        <lst name="defaults">
+          <!-- slightly smaller fragsizes work better because of slop -->
+          <int name="hl.fragsize">70</int>
+          <!-- allow 50% slop on fragment sizes -->
+          <float name="hl.regex.slop">0.5</float>
+          <!-- a basic sentence pattern -->
+          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
+        </lst>
+      </fragmenter>
+
+      <!-- Configure the standard formatter -->
+      <formatter name="html"
+                 default="true"
+                 class="solr.highlight.HtmlFormatter">
+        <lst name="defaults">
+          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+          <str name="hl.simple.post"><![CDATA[</em>]]></str>
+        </lst>
+      </formatter>
+
+      <!-- Configure the standard encoder -->
+      <encoder name="html"
+               class="solr.highlight.HtmlEncoder" />
+
+      <!-- Configure the standard fragListBuilder -->
+      <fragListBuilder name="simple"
+                       class="solr.highlight.SimpleFragListBuilder"/>
+
+      <!-- Configure the single fragListBuilder -->
+      <fragListBuilder name="single"
+                       class="solr.highlight.SingleFragListBuilder"/>
+
+      <!-- Configure the weighted fragListBuilder -->
+      <fragListBuilder name="weighted"
+                       default="true"
+                       class="solr.highlight.WeightedFragListBuilder"/>
+
+      <!-- default tag FragmentsBuilder -->
+      <fragmentsBuilder name="default"
+                        default="true"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <!--
+        <lst name="defaults">
+          <str name="hl.multiValuedSeparatorChar">/</str>
+        </lst>
+        -->
+      </fragmentsBuilder>
+
+      <!-- multi-colored tag FragmentsBuilder -->
+      <fragmentsBuilder name="colored"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <lst name="defaults">
+          <str name="hl.tag.pre"><![CDATA[
+               <b style="background:yellow">,<b style="background:lawgreen">,
+               <b style="background:aquamarine">,<b style="background:magenta">,
+               <b style="background:palegreen">,<b style="background:coral">,
+               <b style="background:wheat">,<b style="background:khaki">,
+               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+          <str name="hl.tag.post"><![CDATA[</b>]]></str>
+        </lst>
+      </fragmentsBuilder>
+
+      <boundaryScanner name="default"
+                       default="true"
+                       class="solr.highlight.SimpleBoundaryScanner">
+        <lst name="defaults">
+          <str name="hl.bs.maxScan">10</str>
+          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
+        </lst>
+      </boundaryScanner>
+
+      <boundaryScanner name="breakIterator"
+                       class="solr.highlight.BreakIteratorBoundaryScanner">
+        <lst name="defaults">
+          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+          <str name="hl.bs.type">WORD</str>
+          <!-- language and country are used when constructing Locale object.  -->
+          <!-- And the Locale object will be used when getting instance of BreakIterator -->
+          <str name="hl.bs.language">en</str>
+          <str name="hl.bs.country">US</str>
+        </lst>
+      </boundaryScanner>
+    </highlighting>
+  </searchComponent>
+
+  <!-- Update Processors
+
+       Chains of Update Processor Factories for dealing with Update
+       Requests can be declared, and then used by name in Update
+       Request Processors
+
+       http://wiki.apache.org/solr/UpdateRequestProcessor
+
+    -->
+
+  <!-- Add unknown fields to the schema
+
+       Field type guessing update processors that will
+       attempt to parse string-typed field values as Booleans, Longs,
+       Doubles, or Dates, and then add schema fields with the guessed
+       field types. Text content will be indexed as "text_general" as
+       well as a copy to a plain string version in *_str.
+
+       These require that the schema is both managed and mutable, by
+       declaring schemaFactory as ManagedIndexSchemaFactory, with
+       mutable specified as true.
+
+       See http://wiki.apache.org/solr/GuessingFieldTypes
+    -->
+  <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+  <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+  <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+    <str name="pattern">[^\w-\.]</str>
+    <str name="replacement">_</str>
+  </updateProcessor>
+  <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+  <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+  <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+  <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+    <arr name="format">
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+      <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+      <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+      <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+    </arr>
+  </updateProcessor>
+  <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.String</str>
+      <str name="fieldType">text_general</str>
+      <lst name="copyField">
+        <str name="dest">*_str</str>
+        <int name="maxChars">256</int>
+      </lst>
+      <!-- Use as default mapping instead of defaultFieldType -->
+      <bool name="default">true</bool>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Boolean</str>
+      <str name="fieldType">booleans</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.util.Date</str>
+      <str name="fieldType">pdates</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Long</str>
+      <str name="valueClass">java.lang.Integer</str>
+      <str name="fieldType">plongs</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Number</str>
+      <str name="fieldType">pdoubles</str>
+    </lst>
+  </updateProcessor>
+
+  <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+  <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:false}"
+           processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+    <processor class="solr.LogUpdateProcessorFactory"/>
+    <processor class="solr.DistributedUpdateProcessorFactory"/>
+    <processor class="solr.RunUpdateProcessorFactory"/>
+  </updateRequestProcessorChain>
+
+  <!-- Deduplication
+
+       An example dedup update processor that creates the "id" field
+       on the fly based on the hash code of some other fields.  This
+       example has overwriteDupes set to false since we are using the
+       id field as the signatureField and Solr will maintain
+       uniqueness based on that anyway.
+
+    -->
+  <!--
+     <updateRequestProcessorChain name="dedupe">
+       <processor class="solr.processor.SignatureUpdateProcessorFactory">
+         <bool name="enabled">true</bool>
+         <str name="signatureField">id</str>
+         <bool name="overwriteDupes">false</bool>
+         <str name="fields">name,features,cat</str>
+         <str name="signatureClass">solr.processor.Lookup3Signature</str>
+       </processor>
+       <processor class="solr.LogUpdateProcessorFactory" />
+       <processor class="solr.RunUpdateProcessorFactory" />
+     </updateRequestProcessorChain>
+    -->
+
+  <!-- Response Writers
+
+       http://wiki.apache.org/solr/QueryResponseWriter
+
+       Request responses will be written using the writer specified by
+       the 'wt' request parameter matching the name of a registered
+       writer.
+
+       The "default" writer is the default and will be used if 'wt' is
+       not specified in the request.
+    -->
+  <!-- The following response writers are implicitly configured unless
+       overridden...
+    -->
+  <!--
+     <queryResponseWriter name="xml"
+                          default="true"
+                          class="solr.XMLResponseWriter" />
+     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+    -->
+
+  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+    <!-- For the purposes of the tutorial, JSON responses are written as
+     plain text so that they are easy to read in *any* browser.
+     If you expect a MIME type of "application/json" just remove this override.
+    -->
+    <str name="content-type">text/plain; charset=UTF-8</str>
+  </queryResponseWriter>
+
+  <!-- Query Parsers
+
+       https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
+
+       Multiple QParserPlugins can be registered by name, and then
+       used in either the "defType" param for the QueryComponent (used
+       by SearchHandler) or in LocalParams
+    -->
+  <!-- example of registering a query parser -->
+  <!--
+     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+    -->
+
+  <!-- Function Parsers
+
+       http://wiki.apache.org/solr/FunctionQuery
+
+       Multiple ValueSourceParsers can be registered by name, and then
+       used as function names when using the "func" QParser.
+    -->
+  <!-- example of registering a custom function parser  -->
+  <!--
+     <valueSourceParser name="myfunc"
+                        class="com.mycompany.MyValueSourceParser" />
+    -->
+
+
+  <!-- Document Transformers
+       http://wiki.apache.org/solr/DocTransformers
+    -->
+  <!--
+     Could be something like:
+     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+       <int name="connection">jdbc://....</int>
+     </transformer>
+
+     To add a constant value to all docs, use:
+     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <int name="value">5</int>
+     </transformer>
+
+     If you want the user to still be able to change it with _value:something_ use this:
+     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <double name="defaultValue">5</double>
+     </transformer>
+
+      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
+      EditorialMarkerFactory will do exactly that:
+     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+    -->
+</config>
diff --git a/test/solr/configsets/property_search/conf/stopwords.txt b/test/solr/configsets/property_search/conf/stopwords.txt
new file mode 100644
index 00000000..ae1e83ee
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
diff --git a/test/solr/configsets/property_search/conf/synonyms.txt b/test/solr/configsets/property_search/conf/synonyms.txt
new file mode 100644
index 00000000..eab4ee87
--- /dev/null
+++ b/test/solr/configsets/property_search/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
diff --git a/test/solr/configsets/term_search/conf/enumsconfig.xml b/test/solr/configsets/term_search/conf/enumsconfig.xml
new file mode 100644
index 00000000..72e7b7d3
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/enumsconfig.xml
@@ -0,0 +1,12 @@
+<?xml version="1.0" ?>
+<enumsConfig>
+  <enum name="ontologyType">
+    <value>ONTOLOGY</value>
+    <value>VALUE_SET_COLLECTION</value>
+  </enum>
+  <enum name="propertyType">
+    <value>ANNOTATION</value>
+    <value>DATATYPE</value>
+    <value>OBJECT</value>
+  </enum>
+</enumsConfig>
\ No newline at end of file
diff --git a/test/solr/configsets/term_search/conf/lang/contractions_ca.txt b/test/solr/configsets/term_search/conf/lang/contractions_ca.txt
new file mode 100644
index 00000000..307a85f9
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
diff --git a/test/solr/configsets/term_search/conf/lang/contractions_fr.txt b/test/solr/configsets/term_search/conf/lang/contractions_fr.txt
new file mode 100644
index 00000000..f1bba51b
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
diff --git a/test/solr/configsets/term_search/conf/lang/contractions_ga.txt b/test/solr/configsets/term_search/conf/lang/contractions_ga.txt
new file mode 100644
index 00000000..9ebe7fa3
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
diff --git a/test/solr/configsets/term_search/conf/lang/contractions_it.txt b/test/solr/configsets/term_search/conf/lang/contractions_it.txt
new file mode 100644
index 00000000..cac04095
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l 
+all 
+dall 
+dell 
+nell 
+sull 
+coll 
+pell 
+gl 
+agl 
+dagl 
+degl 
+negl 
+sugl 
+un 
+m 
+t 
+s 
+v 
+d
diff --git a/test/solr/configsets/term_search/conf/lang/hyphenations_ga.txt b/test/solr/configsets/term_search/conf/lang/hyphenations_ga.txt
new file mode 100644
index 00000000..4d2642cc
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
diff --git a/test/solr/configsets/term_search/conf/lang/stemdict_nl.txt b/test/solr/configsets/term_search/conf/lang/stemdict_nl.txt
new file mode 100644
index 00000000..44107297
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets	fiets
+bromfiets	bromfiets
+ei	eier
+kind	kinder
diff --git a/test/solr/configsets/term_search/conf/lang/stoptags_ja.txt b/test/solr/configsets/term_search/conf/lang/stoptags_ja.txt
new file mode 100644
index 00000000..71b75084
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below.  Note that comments are
+# not allowed on the same line as a stoptag.  See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+#  noun: unclassified nouns
+#名詞
+#
+#  noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+#  noun-proper: Proper nouns where the sub-classification is undefined 
+#名詞-固有名詞
+#
+#  noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+#  noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+#  noun-proper-person-misc: names that cannot be divided into surname and 
+#  given name; foreign names; names where the surname or given name is unknown.
+#  e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+#  noun-proper-person-surname: Mainly Japanese surnames.
+#  e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+#  noun-proper-person-given_name: Mainly Japanese given names.
+#  e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+#  noun-proper-organization: Names representing organizations.
+#  e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+#  noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+#  noun-proper-place-misc: Place names excluding countries.
+#  e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+#  noun-proper-place-country: Country names. 
+#  e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+#  noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+#  noun-pronoun-misc: miscellaneous pronouns: 
+#  e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+#  noun-pronoun-contraction: Spoken language contraction made by combining a 
+#  pronoun and the particle 'wa'.
+#  e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ 
+#名詞-代名詞-縮約
+#
+#  noun-adverbial: Temporal nouns such as names of days or months that behave 
+#  like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+#  e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+#  noun-verbal: Nouns that take arguments with case and can appear followed by 
+#  'suru' and related verbs (する, できる, なさる, くださる)
+#  e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+#  noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+#  e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+#  noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+#  e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+#  noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+#  noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that 
+#  attach to the base form of inflectional words, words that cannot be classified 
+#  into any of the other categories below. This category includes indefinite nouns.
+#  e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第, 
+#       順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み, 
+#       拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+#       わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+#  noun-affix-adverbial: noun affixes that that can behave as adverbs.
+#  e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ, 
+#       上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか, 
+#       最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所, 
+#       とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま, 
+#       儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+#  noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars 
+#  with the stem よう(だ) ("you(da)").
+#  e.g.  よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#  
+#  noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+#  connection form な (aux "da").
+#  e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+#  noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+#  noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is 
+#  treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base 
+#  form of inflectional words.
+#  e.g. そう
+#名詞-特殊-助動詞語幹
+#
+#  noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+#  noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect 
+#  to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+#  any of the other categories below. In general, this category is more inclusive than 
+#  接尾語 ("suffix") and is usually the last element in a compound noun.
+#  e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+#       よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+#  noun-suffix-person: Suffixes that form nouns and attach to person names more often
+#  than other nouns.
+#  e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+#  noun-suffix-place: Suffixes that form nouns and attach to place names more often 
+#  than other nouns.
+#  e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+#  noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that 
+#  can appear before スル ("suru").
+#  e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+#  noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions, 
+#  is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the 
+#  conjunctive form of inflectional words.
+#  e.g. そう
+#名詞-接尾-助動詞語幹
+#
+#  noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive 
+#  form of inflectional words and appear before the copula だ ("da").
+#  e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+#  noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+#  e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+#  noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category 
+#  is more inclusive than 助数詞 ("classifier") and includes common nouns that attach 
+#  to numbers.
+#  e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+#  noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+#  e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+#  noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words 
+#  together.
+#  e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+#  noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are 
+#  semantically verb-like.
+#  e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+#  noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry, 
+#  dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation") 
+#  is いわく ("iwaku").
+#名詞-引用文字列
+#
+#  noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+#  behave like an adjective.
+#  e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+#  prefix: unclassified prefixes
+#接頭詞
+#
+#  prefix-nominal: Prefixes that attach to nouns (including adjective stem forms) 
+#  excluding numerical expressions.
+#  e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+#  prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+#  in conjunctive form followed by なる/なさる/くださる.
+#  e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+#  prefix-adjectival: Prefixes that attach to adjectives.
+#  e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+#  prefix-numerical: Prefixes that attach to numerical expressions.
+#  e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+#  verb: unclassified verbs
+#動詞
+#
+#  verb-main:
+#動詞-自立
+#
+#  verb-auxiliary:
+#動詞-非自立
+#
+#  verb-suffix:
+#動詞-接尾
+#
+#####
+#  adjective: unclassified adjectives
+#形容詞
+#
+#  adjective-main:
+#形容詞-自立
+#
+#  adjective-auxiliary:
+#形容詞-非自立
+#
+#  adjective-suffix:
+#形容詞-接尾
+#
+#####
+#  adverb: unclassified adverbs
+#副詞
+#
+#  adverb-misc: Words that can be segmented into one unit and where adnominal 
+#  modification is not possible.
+#  e.g. あいかわらず, 多分
+#副詞-一般
+#
+#  adverb-particle_conjunction: Adverbs that can be followed by の, は, に, 
+#  な, する, だ, etc.
+#  e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+#  adnominal: Words that only have noun-modifying forms.
+#  e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう, 
+#       どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした, 
+#       「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+#  conjunction: Conjunctions that can occur independently.
+#  e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+#  particle: unclassified particles.
+助詞
+#
+#  particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+#  particle-case-misc: Case particles.
+#  e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+#  particle-case-quote: the "to" that appears after nouns, a person’s speech, 
+#  quotation marks, expressions of decisions from a meeting, reasons, judgements,
+#  conjectures, etc.
+#  e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+#  particle-case-compound: Compounds of particles and verbs that mainly behave 
+#  like case particles.
+#  e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+#       にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける, 
+#       にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し, 
+#       に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして, 
+#       に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+#       にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る, 
+#       にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+#       って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+#  particle-conjunctive:
+#  e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども, 
+#       ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/, 
+#       (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+#  particle-dependency:
+#  e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+#  particle-adverbial:
+#  e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/, 
+#       (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+#       (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに, 
+#       (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+#       ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+#  particle-interjective: particles with interjective grammatical roles.
+#  e.g. (松島) や
+助詞-間投助詞
+#
+#  particle-coordinate:
+#  e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+#  particle-final:
+#  e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ, 
+#       ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+#  particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is 
+#  adverbial, conjunctive, or sentence final. For example:
+#       (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+#       (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+#           「(祈りが届いたせい) か (, 試験に合格した.)」
+#       (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+#  e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+#  particle-adnominalizer: The "no" that attaches to nouns and modifies 
+#  non-inflectional words.
+助詞-連体化
+#
+#  particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs 
+#  that are giongo, giseigo, or gitaigo.
+#  e.g. に, と
+助詞-副詞化
+#
+#  particle-special: A particle that does not fit into one of the above classifications. 
+#  This includes particles that are used in Tanka, Haiku, and other poetry.
+#  e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+#  auxiliary-verb:
+助動詞
+#
+#####
+#  interjection: Greetings and other exclamations.
+#  e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます, 
+#       いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+#  symbol: unclassified Symbols.
+記号
+#
+#  symbol-misc: A general symbol not in one of the categories below.
+#  e.g. [○◎@$〒→+]
+記号-一般
+#
+#  symbol-comma: Commas
+#  e.g. [,、]
+記号-読点
+#
+#  symbol-period: Periods and full stops.
+#  e.g. [.．。]
+記号-句点
+#
+#  symbol-space: Full-width whitespace.
+記号-空白
+#
+#  symbol-open_bracket:
+#  e.g. [({‘“『【]
+記号-括弧開
+#
+#  symbol-close_bracket:
+#  e.g. [)}’”』」】]
+記号-括弧閉
+#
+#  symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+#  other: unclassified other
+#その他
+#
+#  other-interjection: Words that are hard to classify as noun-suffixes or 
+#  sentence-final particles.
+#  e.g. (だ)ァ
+その他-間投
+#
+#####
+#  filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+#  e.g. あの, うんと, えと
+フィラー
+#
+#####
+#  non-verbal: non-verbal sound.
+非言語音
+#
+#####
+#  fragment:
+#語断片
+#
+#####
+#  unknown: unknown part of speech.
+#未知語
+#
+##### End of file
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ar.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ar.txt
new file mode 100644
index 00000000..046829db
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some 
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_bg.txt b/test/solr/configsets/term_search/conf/lang/stopwords_bg.txt
new file mode 100644
index 00000000..1ae4ba2a
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ca.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ca.txt
new file mode 100644
index 00000000..3da65dea
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi 
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc 
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant 
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu 
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son 
+són
+sons 
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_cz.txt b/test/solr/configsets/term_search/conf/lang/stopwords_cz.txt
new file mode 100644
index 00000000..53c6097d
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_da.txt b/test/solr/configsets/term_search/conf/lang/stopwords_da.txt
new file mode 100644
index 00000000..42e6145b
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og           | and
+i            | in
+jeg          | I
+det          | that (dem. pronoun)/it (pers. pronoun)
+at           | that (in front of a sentence)/to (with infinitive)
+en           | a/an
+den          | it (pers. pronoun)/that (dem. pronoun)
+til          | to/at/for/until/against/by/of/into, more
+er           | present tense of "to be"
+som          | who, as
+på           | on/upon/in/on/at/to/after/of/with/for, on
+de           | they
+med          | with/by/in, along
+han          | he
+af           | of/by/from/off/for/in/with/on, off
+for          | at/for/to/from/by/of/ago, in front/before, because
+ikke         | not
+der          | who/which, there/those
+var          | past tense of "to be"
+mig          | me/myself
+sig          | oneself/himself/herself/itself/themselves
+men          | but
+et           | a/an/one, one (number), someone/somebody/one
+har          | present tense of "to have"
+om           | round/about/for/in/a, about/around/down, if
+vi           | we
+min          | my
+havde        | past tense of "to have"
+ham          | him
+hun          | she
+nu           | now
+over         | over/above/across/by/beyond/past/on/about, over/past
+da           | then, when/as/since
+fra          | from/off/since, off, since
+du           | you
+ud           | out
+sin          | his/her/its/one's
+dem          | them
+os           | us/ourselves
+op           | up
+man          | you/one
+hans         | his
+hvor         | where
+eller        | or
+hvad         | what
+skal         | must/shall etc.
+selv         | myself/youself/herself/ourselves etc., even
+her          | here
+alle         | all/everyone/everybody etc.
+vil          | will (verb)
+blev         | past tense of "to stay/to remain/to get/to become"
+kunne        | could
+ind          | in
+når          | when
+være         | present tense of "to be"
+dog          | however/yet/after all
+noget        | something
+ville        | would
+jo           | you know/you see (adv), yes
+deres        | their/theirs
+efter        | after/behind/according to/for/by/from, later/afterwards
+ned          | down
+skulle       | should
+denne        | this
+end          | than
+dette        | this
+mit          | my/mine
+også         | also
+under        | under/beneath/below/during, below/underneath
+have         | have
+dig          | you
+anden        | other
+hende        | her
+mine         | my
+alt          | everything
+meget        | much/very, plenty of
+sit          | his, her, its, one's
+sine         | his, her, its, one's
+vor          | our
+mod          | against
+disse        | these
+hvis         | if
+din          | your/yours
+nogle        | some
+hos          | by/at
+blive        | be/become
+mange        | many
+ad           | by/through
+bliver       | present tense of "to be/to become"
+hendes       | her/hers
+været        | be
+thi          | for (conj)
+jer          | you
+sådan        | such, like this/like that
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_de.txt b/test/solr/configsets/term_search/conf/lang/stopwords_de.txt
new file mode 100644
index 00000000..86525e7a
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber           |  but
+
+alle           |  all
+allem
+allen
+aller
+alles
+
+als            |  than, as
+also           |  so
+am             |  an + dem
+an             |  at
+
+ander          |  other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch           |  also
+auf            |  on
+aus            |  out of
+bei            |  by
+bin            |  am
+bis            |  until
+bist           |  art
+da             |  there
+damit          |  with it
+dann           |  then
+
+der            |  the
+den
+des
+dem
+die
+das
+
+daß            |  that
+
+derselbe       |  the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu           |  to that
+
+dein           |  thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn           |  because
+
+derer          |  of those
+dessen         |  of him
+
+dich           |  thee
+dir            |  to thee
+du             |  thou
+
+dies           |  this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch           |  (several meanings)
+dort           |  (over) there
+
+
+durch          |  through
+
+ein            |  a
+eine
+einem
+einen
+einer
+eines
+
+einig          |  some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal         |  once
+
+er             |  he
+ihn            |  him
+ihm            |  to him
+
+es             |  it
+etwas          |  something
+
+euer           |  your
+eure
+eurem
+euren
+eurer
+eures
+
+für            |  for
+gegen          |  towards
+gewesen        |  p.p. of sein
+hab            |  have
+habe           |  have
+haben          |  have
+hat            |  has
+hatte          |  had
+hatten         |  had
+hier           |  here
+hin            |  there
+hinter         |  behind
+
+ich            |  I
+mich           |  me
+mir            |  to me
+
+
+ihr            |  you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch           |  to you
+
+im             |  in + dem
+in             |  in
+indem          |  while
+ins            |  in + das
+ist            |  is
+
+jede           |  each, every
+jedem
+jeden
+jeder
+jedes
+
+jene           |  that
+jenem
+jenen
+jener
+jenes
+
+jetzt          |  now
+kann           |  can
+
+kein           |  no
+keine
+keinem
+keinen
+keiner
+keines
+
+können         |  can
+könnte         |  could
+machen         |  do
+man            |  one
+
+manche         |  some, many a
+manchem
+manchen
+mancher
+manches
+
+mein           |  my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit            |  with
+muss           |  must
+musste         |  had to
+nach           |  to(wards)
+nicht          |  not
+nichts         |  nothing
+noch           |  still, yet
+nun            |  now
+nur            |  only
+ob             |  whether
+oder           |  or
+ohne           |  without
+sehr           |  very
+
+sein           |  his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst         |  self
+sich           |  herself
+
+sie            |  they, she
+ihnen          |  to them
+
+sind           |  are
+so             |  so
+
+solche         |  such
+solchem
+solchen
+solcher
+solches
+
+soll           |  shall
+sollte         |  should
+sondern        |  but
+sonst          |  else
+über           |  over
+um             |  about, around
+und            |  and
+
+uns            |  us
+unse
+unsem
+unsen
+unser
+unses
+
+unter          |  under
+viel           |  much
+vom            |  von + dem
+von            |  from
+vor            |  before
+während        |  while
+war            |  was
+waren          |  were
+warst          |  wast
+was            |  what
+weg            |  away, off
+weil           |  because
+weiter         |  further
+
+welche         |  which
+welchem
+welchen
+welcher
+welches
+
+wenn           |  when
+werde          |  will
+werden         |  will
+wie            |  how
+wieder         |  again
+will           |  want
+wir            |  we
+wird           |  will
+wirst          |  willst
+wo             |  where
+wollen         |  want
+wollte         |  wanted
+würde          |  would
+würden         |  would
+zu             |  to
+zum            |  zu + dem
+zur            |  zu + der
+zwar           |  indeed
+zwischen       |  between
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_el.txt b/test/solr/configsets/term_search/conf/lang/stopwords_el.txt
new file mode 100644
index 00000000..232681f5
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς' 
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και 
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_en.txt b/test/solr/configsets/term_search/conf/lang/stopwords_en.txt
new file mode 100644
index 00000000..2c164c0b
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_es.txt b/test/solr/configsets/term_search/conf/lang/stopwords_es.txt
new file mode 100644
index 00000000..487d78c8
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  from, of
+la             |  the, her
+que            |  who, that
+el             |  the
+en             |  in
+y              |  and
+a              |  to
+los            |  the, them
+del            |  de + el
+se             |  himself, from him etc
+las            |  the, them
+por            |  for, by, etc
+un             |  a
+para           |  for
+con            |  with
+no             |  no
+una            |  a
+su             |  his, her
+al             |  a + el
+  | es         from SER
+lo             |  him
+como           |  how
+más            |  more
+pero           |  pero
+sus            |  su plural
+le             |  to him, her
+ya             |  already
+o              |  or
+  | fue        from SER
+este           |  this
+  | ha         from HABER
+sí             |  himself etc
+porque         |  because
+esta           |  this
+  | son        from SER
+entre          |  between
+  | está     from ESTAR
+cuando         |  when
+muy            |  very
+sin            |  without
+sobre          |  on
+  | ser        from SER
+  | tiene      from TENER
+también        |  also
+me             |  me
+hasta          |  until
+hay            |  there is/are
+donde          |  where
+  | han        from HABER
+quien          |  whom, that
+  | están      from ESTAR
+  | estado     from ESTAR
+desde          |  from
+todo           |  all
+nos            |  us
+durante        |  during
+  | estados    from ESTAR
+todos          |  all
+uno            |  a
+les            |  to them
+ni             |  nor
+contra         |  against
+otros          |  other
+  | fueron     from SER
+ese            |  that
+eso            |  that
+  | había      from HABER
+ante           |  before
+ellos          |  they
+e              |  and (variant of y)
+esto           |  this
+mí             |  me
+antes          |  before
+algunos        |  some
+qué            |  what?
+unos           |  a
+yo             |  I
+otro           |  other
+otras          |  other
+otra           |  other
+él             |  he
+tanto          |  so much, many
+esa            |  that
+estos          |  these
+mucho          |  much, many
+quienes        |  who
+nada           |  nothing
+muchos         |  many
+cual           |  who
+  | sea        from SER
+poco           |  few
+ella           |  she
+estar          |  to be
+  | haber      from HABER
+estas          |  these
+  | estaba     from ESTAR
+  | estamos    from ESTAR
+algunas        |  some
+algo           |  something
+nosotros       |  we
+
+      | other forms
+
+mi             |  me
+mis            |  mi plural
+tú             |  thou
+te             |  thee
+ti             |  thee
+tu             |  thy
+tus            |  tu plural
+ellas          |  they
+nosotras       |  we
+vosotros       |  you
+vosotras       |  you
+os             |  you
+mío            |  mine
+mía            |
+míos           |
+mías           |
+tuyo           |  thine
+tuya           |
+tuyos          |
+tuyas          |
+suyo           |  his, hers, theirs
+suya           |
+suyos          |
+suyas          |
+nuestro        |  ours
+nuestra        |
+nuestros       |
+nuestras       |
+vuestro        |  yours
+vuestra        |
+vuestros       |
+vuestras       |
+esos           |  those
+esas           |  those
+
+               | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+               | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+               | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+  |  sed also means 'thirst'
+
+               | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_et.txt b/test/solr/configsets/term_search/conf/lang/stopwords_et.txt
new file mode 100644
index 00000000..1b06a134
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_et.txt
@@ -0,0 +1,1603 @@
+# Estonian stopwords list
+all
+alla
+allapoole
+allpool
+alt
+altpoolt
+eel
+eespool
+enne
+hommikupoole
+hoolimata
+ilma
+kaudu
+keset
+kesk
+kohe
+koos
+kuhupoole
+kuni
+kuspool
+kustpoolt
+kõige
+käsikäes
+lappi
+ligi
+läbi
+mööda
+paitsi
+peale
+pealepoole
+pealpool
+pealt
+pealtpoolt
+piki
+pikku
+piku
+pikuti
+põiki
+pärast
+päri
+risti
+sealpool
+sealtpoolt
+seespool
+seltsis
+siiapoole
+siinpool
+siitpoolt
+sinnapoole
+sissepoole
+taga
+tagantpoolt
+tagapidi
+tagapool
+taha
+tahapoole
+teispool
+teispoole
+tänu
+tükkis
+vaatamata
+vastu
+väljapoole
+väljaspool
+väljastpoolt
+õhtupoole
+ühes
+ühestükis
+ühestükkis
+ülalpool
+ülaltpoolt
+üle
+ülespoole
+ülevalpool
+ülevaltpoolt
+ümber
+ümbert
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+aegu
+aegus
+alguks
+algul
+algule
+algult
+alguni
+all
+alla
+alt
+alul
+alutsi
+arvel
+asemel
+asemele
+eel
+eeli
+ees
+eesotsas
+eest
+eestotsast
+esitsi
+ette
+etteotsa
+haaval
+heaks
+hoolimata
+hulgas
+hulgast
+hulka
+jalgu
+jalus
+jalust
+jaoks
+jooksul
+juurde
+juures
+juurest
+jälil
+jälile
+järel
+järele
+järelt
+järgi
+kaasas
+kallal
+kallale
+kallalt
+kamul
+kannul
+kannule
+kannult
+kaudu
+kaupa
+keskel
+keskele
+keskelt
+keskis
+keskpaiku
+kestel
+kestes
+kilda
+killas
+killast
+kimpu
+kimpus
+kiuste
+kohal
+kohale
+kohalt
+kohaselt
+kohe
+kohta
+koos
+korral
+kukil
+kukile
+kukilt
+kulul
+kõrva
+kõrval
+kõrvale
+kõrvalt
+kõrvas
+kõrvast
+käekõrval
+käekõrvale
+käekõrvalt
+käes
+käest
+kätte
+külge
+küljes
+küljest
+küüsi
+küüsis
+küüsist
+ligi
+ligidal
+ligidale
+ligidalt
+lool
+läbi
+lähedal
+lähedale
+lähedalt
+man
+mant
+manu
+meelest
+mööda
+nahas
+nahka
+nahkas
+najal
+najale
+najalt
+nõjal
+nõjale
+otsa
+otsas
+otsast
+paigale
+paigu
+paiku
+peal
+peale
+pealt
+perra
+perrä
+pidi
+pihta
+piki
+pikku
+pool
+poole
+poolest
+poolt
+puhul
+puksiiris
+pähe
+päralt
+päras
+pärast
+päri
+ringi
+ringis
+risust
+saadetusel
+saadik
+saatel
+saati
+seas
+seast
+sees
+seest
+sekka
+seljataga
+seltsi
+seltsis
+seltsist
+sisse
+slepis
+suhtes
+šlepis
+taga
+tagant
+tagantotsast
+tagaotsas
+tagaselja
+tagasi
+tagast
+tagutsi
+taha
+tahaotsa
+takka
+tarvis
+tasa
+tuuri
+tuuris
+tõttu
+tükkis
+uhal
+vaatamata
+vahel
+vahele
+vahelt
+vahepeal
+vahepeale
+vahepealt
+vahetsi
+varal
+varale
+varul
+vastas
+vastast
+vastu
+veerde
+veeres
+viisi
+võidu
+võrd
+võrdki
+võrra
+võrragi
+väel
+väele
+vältel
+väärt
+väärtki
+äärde
+ääre
+ääres
+äärest
+ühes
+üle
+ümber
+ümbert
+a
+abil
+aina
+ainult
+alalt
+alates
+alati
+alles
+b
+c
+d
+e
+eales
+ealeski
+edasi
+edaspidi
+eelkõige
+eemal
+ei
+eks
+end
+enda
+enese
+ennem
+esialgu
+f
+g
+h
+hoopis
+i
+iganes
+igatahes
+igati
+iial
+iialgi
+ikka
+ikkagi
+ilmaski
+iseenda
+iseenese
+iseenesest
+isegi
+j
+jah
+ju
+juba
+juhul
+just
+järelikult
+k
+ka
+kah
+kas
+kasvõi
+keda
+kestahes
+kogu
+koguni
+kohati
+kokku
+kuhu
+kuhugi
+kuidagi
+kuidas
+kunagi
+kus
+kusagil
+kusjuures
+kuskil
+kust
+kõigepealt
+küll
+l
+liiga
+lisaks
+m
+miks
+mil
+millal
+millalgi
+mispärast
+mistahes
+mistõttu
+mitte
+muide
+muidu
+muidugi
+muist
+mujal
+mujale
+mujalt
+mõlemad
+mõnda
+mõne
+mõnikord
+n
+nii
+niikaua
+niimoodi
+niipaljuke
+niisama
+niisiis
+niivõrd
+nõnda
+nüüd
+o
+omaette
+omakorda
+omavahel
+ometi
+p
+palju
+paljuke
+palju-palju
+peaaegu
+peagi
+peamiselt
+pigem
+pisut
+praegu
+päris
+r
+rohkem
+s
+samas
+samuti
+seal
+sealt
+sedakorda
+sedapuhku
+seega
+seejuures
+seejärel
+seekord
+seepärast
+seetõttu
+sellepärast
+seni
+sestap
+siia
+siiani
+siin
+siinkohal
+siis
+siiski
+siit
+sinna
+suht
+š
+z
+ž
+t
+teel
+teineteise
+tõesti
+täiesti
+u
+umbes
+v
+w
+veel
+veelgi
+vist
+võibolla
+võib-olla
+väga
+vähemalt
+välja
+väljas
+väljast
+õ
+ä
+ära
+ö
+ü
+ühtlasi
+üksi
+ükskõik
+ülal
+ülale
+ülalt
+üles
+ülesse
+üleval
+ülevalt
+ülimalt
+üsna
+x
+y
+aga
+ega
+ehk
+ehkki
+elik
+ellik
+enge
+ennegu
+ent
+et
+ja
+justkui
+kui
+kuid
+kuigi
+kuivõrd
+kuna
+kuni
+kut
+mistab
+muudkui
+nagu
+nigu
+ning
+olgugi
+otsekui
+otsenagu
+selmet
+sest
+sestab
+vaid
+või
+aa
+adaa
+adjöö
+ae
+ah
+ahaa
+ahah
+ah-ah-ah
+ah-haa
+ahoi
+ai
+aidaa
+aidu-raidu
+aih
+aijeh
+aituma
+aitäh
+aitüma
+ammuu
+amps
+ampsti
+aptsih
+ass
+at
+ata
+at-at-at
+atsih
+atsihh
+auh
+bai-bai
+bingo
+braavo
+brr
+ee
+eeh
+eh
+ehee
+eheh
+eh-eh-hee
+eh-eh-ee
+ehei
+ehh
+ehhee
+einoh
+ena
+ennäe
+ennäh
+fuh
+fui
+fuih
+haa
+hah
+hahaa
+hah-hah-hah
+halleluuja
+hallo
+halloo
+hass
+hee
+heh
+he-he-hee
+hei
+heldeke(ne)
+heureka
+hihii
+hip-hip-hurraa
+hmh
+hmjah
+hoh-hoh-hoo
+hohoo
+hoi
+hollallaa
+hoo
+hoplaa
+hopp
+hops
+hopsassaa
+hopsti
+hosianna
+huh
+huidii
+huist
+hurjah
+hurjeh
+hurjoh
+hurjuh
+hurraa
+huu
+hõhõh
+hõi
+hõissa
+hõissassa
+hõk
+hõkk
+häh
+hä-hä-hää
+hüvasti
+ih-ah-haa
+ih-ih-hii
+ii-ha-ha
+issake
+issakene
+isver
+jaa-ah
+ja-ah
+jaah
+janäe
+jeeh
+jeerum
+jeever
+jessas
+jestas
+juhhei
+jumalaga
+jumalime
+jumaluke
+jumalukene
+jutas
+kaaps
+kaapsti
+kaasike
+kae
+kalps
+kalpsti
+kannäe
+kanäe
+kappadi
+kaps
+kapsti
+karkõmm
+karkäuh
+karkääks
+karkääksti
+karmauh
+karmauhti
+karnaps
+karnapsti
+karniuhti
+karpartsaki
+karpauh
+karpauhti
+karplauh
+karplauhti
+karprauh
+karprauhti
+karsumdi
+karsumm
+kartsumdi
+kartsumm
+karviuh
+karviuhti
+kaske
+kassa
+kauh
+kauhti
+keh
+keksti
+kepsti
+khe
+khm
+kih
+kiiks
+kiiksti
+kiis
+kiiss
+kikerii
+kikerikii
+kili
+kilk
+kilk-kõlk
+kilks
+kilks-kolks
+kilks-kõlks
+kill
+killadi
+killadi|-kolladi
+killadi-kõlladi
+killa-kolla
+killa-kõlla
+kill-kõll
+kimps-komps
+kipp
+kips-kõps
+kiriküüt
+kirra-kõrra
+kirr-kõrr
+kirts
+klaps
+klapsti
+klirdi
+klirr
+klonks
+klops
+klopsti
+kluk
+klu-kluu
+klõks
+klõksti
+klõmdi
+klõmm
+klõmpsti
+klõnks
+klõnksti
+klõps
+klõpsti
+kläu
+kohva-kohva
+kok
+koks
+koksti
+kolaki
+kolk
+kolks
+kolksti
+koll
+kolladi
+komp
+komps
+kompsti
+kop
+kopp
+koppadi
+kops
+kopsti
+kossu
+kotsu
+kraa
+kraak
+kraaks
+kraaps
+kraapsti
+krahh
+kraks
+kraksti
+kraps
+krapsti
+krauh
+krauhti
+kriiks
+kriiksti
+kriips
+kriips-kraaps
+kripa-krõpa
+krips-kraps
+kriuh
+kriuks
+kriuksti
+kromps
+kronk
+kronks
+krooks
+kruu
+krõks
+krõksti
+krõpa
+krõps
+krõpsti
+krõuh
+kräu
+kräuh
+kräuhti
+kräuks
+kss
+kukeleegu
+kukku
+kuku
+kulu
+kurluu
+kurnäu
+kuss
+kussu
+kõks
+kõksti
+kõldi
+kõlks
+kõlksti
+kõll
+kõmaki
+kõmdi
+kõmm
+kõmps
+kõpp
+kõps
+kõpsadi
+kõpsat
+kõpsti
+kõrr
+kõrra-kõrra
+kõss
+kõtt
+kõõksti
+kärr
+kärts
+kärtsti
+käuks
+käuksti
+kääga
+kääks
+kääksti
+köh
+köki-möki
+köksti
+laks
+laksti
+lampsti
+larts
+lartsti
+lats
+latsti
+leelo
+legoo
+lehva
+liiri-lõõri
+lika-lõka
+likat-lõkat
+limpsti
+lips
+lipsti
+lirts
+lirtsaki
+lirtsti
+lonksti
+lops
+lopsti
+lorts
+lortsti
+luks
+lups
+lupsti
+lurts
+lurtsti
+lõks
+lõksti
+lõmps
+lõmpsti
+lõnks
+lõnksti
+lärts
+lärtsti
+läts
+lätsti
+lörts
+lörtsti
+lötsti
+lööps
+lööpsti
+marss
+mats
+matsti
+mauh
+mauhti
+mh
+mhh
+mhmh
+miau
+mjaa
+mkm
+m-mh
+mnjaa
+mnjah
+moens
+mulks
+mulksti
+mull-mull
+mull-mull-mull
+muu
+muuh
+mõh
+mõmm
+mäh
+mäts
+mäu
+mää
+möh
+möh-öh-ää
+möö
+müh-müh
+mühüh
+müks
+müksti
+müraki
+mürr
+mürts
+mürtsaki
+mürtsti
+mütaku
+müta-mäta
+müta-müta
+müt-müt
+müt-müt-müt
+müts
+mütsti
+mütt
+naa
+naah
+nah
+naks
+naksti
+nanuu
+naps
+napsti
+nilpsti
+nipsti
+nirr
+niuh
+niuh-näuh
+niuhti
+noh
+noksti
+nolpsti
+nonoh
+nonoo
+nonäh
+noo
+nooh
+nooks
+norr
+nurr
+nuuts
+nõh
+nõhh
+nõka-nõka
+nõks
+nõksat-nõksat
+nõks-nõks
+nõksti
+nõõ
+nõõh
+näeh
+näh
+nälpsti
+nämm-nämm
+näpsti
+näts
+nätsti
+näu
+näuh
+näuhti
+näuks
+näuksti
+nääh
+nääks
+nühkat-nühkat
+oeh
+oh
+ohh
+ohhh
+oh-hoi
+oh-hoo
+ohoh
+oh-oh-oo
+oh-oh-hoo
+ohoi
+ohoo
+oi
+oih
+oijee
+oijeh
+oo
+ooh
+oo-oh
+oo-ohh
+oot
+ossa
+ot
+paa
+pah
+pahh
+pakaa
+pamm
+pantsti
+pardon
+pardonks
+parlartsti
+parts
+partsti
+partsumdi
+partsumm
+pastoi
+pats
+patst
+patsti
+pau
+pauh
+pauhti
+pele
+pfui
+phuh
+phuuh
+phäh
+phähh
+piiks
+piip
+piiri-pääri
+pimm
+pimm-pamm
+pimm-pomm
+pimm-põmm
+piraki
+piuks
+piu-pau
+plaks
+plaksti
+plarts
+plartsti
+plats
+platsti
+plauh
+plauhh
+plauhti
+pliks
+pliks-plaks
+plinn
+pliraki
+plirts
+plirtsti
+pliu
+pliuh
+ploks
+plotsti
+plumps
+plumpsti
+plõks
+plõksti
+plõmdi
+plõmm
+plõnn
+plärr
+plärts
+plärtsat
+plärtsti
+pläu
+pläuh
+plää
+plörtsat
+pomm
+popp
+pops
+popsti
+ports
+pot
+pots
+potsti
+pott
+praks
+praksti
+prants
+prantsaki
+prantsti
+prassai
+prauh
+prauhh
+prauhti
+priks
+priuh
+priuhh
+priuh-prauh
+proosit
+proost
+prr
+prrr
+prõks
+prõksti
+prõmdi
+prõmm
+prõntsti
+prääk
+prääks
+pst
+psst
+ptrr
+ptruu
+ptüi
+puh
+puhh
+puksti
+pumm
+pumps
+pup-pup-pup
+purts
+puuh
+põks
+põksti
+põmdi
+põmm
+põmmadi
+põnks
+põnn
+põnnadi
+põnt
+põnts
+põntsti
+põraki
+põrr
+põrra-põrra
+päh
+pähh
+päntsti
+pää
+pöörd
+püh
+raks
+raksti
+raps
+rapsti
+ratataa
+rauh
+riips
+riipsti
+riks
+riks-raks
+rips-raps
+rivitult
+robaki
+rops
+ropsaki
+ropsti
+ruik
+räntsti
+räts
+röh
+röhh
+sah
+sahh
+sahkat
+saps
+sapsti
+sauh
+sauhti
+servus
+sihkadi-sahkadi
+sihka-sahka
+sihkat-sahkat
+silks
+silk-solk
+sips
+sipsti
+sirr
+sirr-sorr
+sirts
+sirtsti
+siu
+siuh
+siuh-sauh
+siuh-säuh
+siuhti
+siuks
+siuts
+skool
+so
+soh
+solks
+solksti
+solpsti
+soo
+sooh
+so-oh
+soo-oh
+sopp
+sops
+sopsti
+sorr
+sorts
+sortsti
+so-soo
+soss
+soss-soss
+ss
+sss
+sst
+stopp
+suhkat-sahkat
+sulk
+sulks
+sulksti
+sull
+sulla-sulla
+sulpa-sulpa
+sulps
+sulpsti
+sumaki
+sumdi
+summ
+summat-summat
+sups
+supsaku
+supsti
+surts
+surtsti
+suss
+susti
+suts
+sutsti
+säh
+sähke
+särts
+särtsti
+säu
+säuh
+säuhti
+taevake
+taevakene
+takk
+tere
+terekest
+tibi-tibi
+tikk-takk
+tiks
+tilk
+tilks
+till
+tilla-talla
+till-tall
+tilulii
+tinn
+tip
+tip-tap
+tirr
+tirtsti
+tiu
+tjaa
+tjah
+tohhoh
+tohhoo
+tohoh
+tohoo
+tok
+tokk
+toks
+toksti
+tonks
+tonksti
+tota
+totsti
+tot-tot
+tprr
+tpruu
+trah
+trahh
+trallallaa
+trill
+trillallaa
+trr
+trrr
+tsah
+tsahh
+tsilk
+tsilk-tsolk
+tsirr
+tsiuh
+tskae
+tsolk
+tss
+tst
+tsst
+tsuhh
+tsuk
+tsumm
+tsurr
+tsäuh
+tšao
+tšš
+tššš
+tuk
+tuks
+turts
+turtsti
+tutki
+tutkit
+tutu-lutu
+tutulutu
+tuut
+tuutu-luutu
+tõks
+tötsti
+tümps
+uh
+uhh
+uh-huu
+uhtsa
+uhtsaa
+uhuh
+uhuu
+ui
+uih
+uih-aih
+uijah
+uijeh
+uist
+uit
+uka
+upsti
+uraa
+urjah
+urjeh
+urjoh
+urjuh
+urr
+urraa
+ust
+utu
+uu
+uuh
+vaak
+vaat
+vae
+vaeh
+vai
+vat
+vau
+vhüüt
+vidiit
+viiks
+vilks
+vilksti
+vinki-vinki
+virdi
+virr
+viu
+viudi
+viuh
+viuhti
+voeh
+voh
+vohh
+volks
+volksti
+vooh
+vops
+vopsti
+vot
+vuh
+vuhti
+vuih
+vulks
+vulksti
+vull
+vulpsti
+vups
+vupsaki
+vupsaku
+vupsti
+vurdi
+vurr
+vurra-vurra
+vurts
+vurtsti
+vutt
+võe
+võeh
+või
+võih
+võrr
+võts
+võtt
+vääks
+õe
+õits
+õk
+õkk
+õrr
+õss
+õuh
+äh
+ähh
+ähhähhää
+äh-hää
+äh-äh-hää
+äiu
+äiu-ää
+äss
+ää
+ääh
+äähh
+öh
+öhh
+ök
+üh
+eelmine
+eikeegi
+eimiski
+emb-kumb
+enam
+enim
+iga
+igasugune
+igaüks
+ise
+isesugune
+järgmine
+keegi
+kes
+kumb
+kumbki
+kõik
+meiesugune
+meietaoline
+midagi
+mihuke
+mihukene
+milletaoline
+milline
+mina
+minake
+mingi
+mingisugune
+minusugune
+minutaoline
+mis
+miski
+miskisugune
+missugune
+misuke
+mitmes
+mitmesugune
+mitu
+mitu-mitu
+mitu-setu
+muu
+mõlema
+mõnesugune
+mõni
+mõningane
+mõningas
+mäherdune
+määrane
+naasugune
+need
+nemad
+nendesugune
+nendetaoline
+nihuke
+nihukene
+niimitu
+niisamasugune
+niisugune
+nisuke
+nisukene
+oma
+omaenese
+omasugune
+omataoline
+pool
+praegune
+sama
+samasugune
+samataoline
+see
+seesama
+seesamane
+seesamune
+seesinane
+seesugune
+selline
+sihuke
+sihukene
+sina
+sinusugune
+sinutaoline
+siuke
+siukene
+säherdune
+säärane
+taoline
+teiesugune
+teine
+teistsugune
+tema
+temake
+temakene
+temasugune
+temataoline
+too
+toosama
+toosamane
+üks
+üksteise
+hakkama
+minema
+olema
+pidama
+saama
+tegema
+tulema
+võima
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_eu.txt b/test/solr/configsets/term_search/conf/lang/stopwords_eu.txt
new file mode 100644
index 00000000..25f1db93
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_fa.txt b/test/solr/configsets/term_search/conf/lang/stopwords_fa.txt
new file mode 100644
index 00000000..723641c6
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_fi.txt b/test/solr/configsets/term_search/conf/lang/stopwords_fi.txt
new file mode 100644
index 00000000..4372c9a0
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole        | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en         | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom   Gen    Acc    Part   Iness   Elat    Illat  Adess   Ablat   Allat   Ess    Trans
+minä   minun  minut  minua  minussa minusta minuun minulla minulta minulle               | I
+sinä   sinun  sinut  sinua  sinussa sinusta sinuun sinulla sinulta sinulle               | you
+hän    hänen  hänet  häntä  hänessä hänestä häneen hänellä häneltä hänelle               | he she
+me     meidän meidät meitä  meissä  meistä  meihin meillä  meiltä  meille                | we
+te     teidän teidät teitä  teissä  teistä  teihin teillä  teiltä  teille                | you
+he     heidän heidät heitä  heissä  heistä  heihin heillä  heiltä  heille                | they
+
+tämä   tämän         tätä   tässä   tästä   tähän  tallä   tältä   tälle   tänä   täksi  | this
+tuo    tuon          tuotä  tuossa  tuosta  tuohon tuolla  tuolta  tuolle  tuona  tuoksi | that
+se     sen           sitä   siinä   siitä   siihen sillä   siltä   sille   sinä   siksi  | it
+nämä   näiden        näitä  näissä  näistä  näihin näillä  näiltä  näille  näinä  näiksi | these
+nuo    noiden        noita  noissa  noista  noihin noilla  noilta  noille  noina  noiksi | those
+ne     niiden        niitä  niissä  niistä  niihin niillä  niiltä  niille  niinä  niiksi | they
+
+kuka   kenen kenet   ketä   kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä  keiden ketkä  keitä  keissä  keistä  keihin keillä  keiltä  keille  keinä  keiksi | (pl)
+mikä   minkä minkä   mitä   missä   mistä   mihin  millä   miltä   mille   minä   miksi  | which what
+mitkä                                                                                    | (pl)
+
+joka   jonka         jota   jossa   josta   johon  jolla   jolta   jolle   jona   joksi  | who which
+jotka  joiden        joita  joissa  joista  joihin joilla  joilta  joille  joina  joiksi | (pl)
+
+| conjunctions
+
+että   | that
+ja     | and
+jos    | if
+koska  | because
+kuin   | than
+mutta  | but
+niin   | so
+sekä   | and
+sillä  | for
+tai    | or
+vaan   | but
+vai    | or
+vaikka | although
+
+
+| prepositions
+
+kanssa  | with
+mukaan  | according to
+noin    | about
+poikki  | across
+yli     | over, across
+
+| other
+
+kun    | when
+niin   | so
+nyt    | now
+itse   | self
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_fr.txt b/test/solr/configsets/term_search/conf/lang/stopwords_fr.txt
new file mode 100644
index 00000000..749abae6
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au             |  a + le
+aux            |  a + les
+avec           |  with
+ce             |  this
+ces            |  these
+dans           |  with
+de             |  of
+des            |  de + les
+du             |  de + le
+elle           |  she
+en             |  `of them' etc
+et             |  and
+eux            |  them
+il             |  he
+je             |  I
+la             |  the
+le             |  the
+leur           |  their
+lui            |  him
+ma             |  my (fem)
+mais           |  but
+me             |  me
+même           |  same; as in moi-même (myself) etc
+mes            |  me (pl)
+moi            |  me
+mon            |  my (masc)
+ne             |  not
+nos            |  our (pl)
+notre          |  our
+nous           |  we
+on             |  one
+ou             |  where
+par            |  by
+pas            |  not
+pour           |  for
+qu             |  que before vowel
+que            |  that
+qui            |  who
+sa             |  his, her (fem)
+se             |  oneself
+ses            |  his (pl)
+son            |  his, her (masc)
+sur            |  on
+ta             |  thy (fem)
+te             |  thee
+tes            |  thy (pl)
+toi            |  thee
+ton            |  thy (masc)
+tu             |  thou
+un             |  a
+une            |  a
+vos            |  your (pl)
+votre          |  your
+vous           |  you
+
+               |  single letter forms
+
+c              |  c'
+d              |  d'
+j              |  j'
+l              |  l'
+à              |  to, at
+m              |  m'
+n              |  n'
+s              |  s'
+t              |  t'
+y              |  there
+
+               | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+               | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+               | Later additions (from Jean-Christophe Deschamps)
+ceci           |  this
+cela           |  that
+celà           |  that
+cet            |  this
+cette          |  this
+ici            |  here
+ils            |  they
+les            |  the (pl)
+leurs          |  their (pl)
+quel           |  which
+quels          |  which
+quelle         |  which
+quelles        |  which
+sans           |  without
+soi            |  oneself
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ga.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ga.txt
new file mode 100644
index 00000000..9ff88d74
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_gl.txt b/test/solr/configsets/term_search/conf/lang/stopwords_gl.txt
new file mode 100644
index 00000000..d8760b12
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_hi.txt b/test/solr/configsets/term_search/conf/lang/stopwords_hi.txt
new file mode 100644
index 00000000..86286bb0
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer 
+# for spelling variation (see section below), such that it can be used whether or 
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well. 
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन 
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर  
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह 
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह 
+वहाँ
+वहीं
+वाले
+वुह 
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_hu.txt b/test/solr/configsets/term_search/conf/lang/stopwords_hu.txt
new file mode 100644
index 00000000..37526da8
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+ 
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_hy.txt b/test/solr/configsets/term_search/conf/lang/stopwords_hy.txt
new file mode 100644
index 00000000..60c1c50f
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_id.txt b/test/solr/configsets/term_search/conf/lang/stopwords_id.txt
new file mode 100644
index 00000000..4617f83a
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_it.txt b/test/solr/configsets/term_search/conf/lang/stopwords_it.txt
new file mode 100644
index 00000000..1219cc77
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad             |  a (to) before vowel
+al             |  a + il
+allo           |  a + lo
+ai             |  a + i
+agli           |  a + gli
+all            |  a + l'
+agl            |  a + gl'
+alla           |  a + la
+alle           |  a + le
+con            |  with
+col            |  con + il
+coi            |  con + i (forms collo, cogli etc are now very rare)
+da             |  from
+dal            |  da + il
+dallo          |  da + lo
+dai            |  da + i
+dagli          |  da + gli
+dall           |  da + l'
+dagl           |  da + gll'
+dalla          |  da + la
+dalle          |  da + le
+di             |  of
+del            |  di + il
+dello          |  di + lo
+dei            |  di + i
+degli          |  di + gli
+dell           |  di + l'
+degl           |  di + gl'
+della          |  di + la
+delle          |  di + le
+in             |  in
+nel            |  in + el
+nello          |  in + lo
+nei            |  in + i
+negli          |  in + gli
+nell           |  in + l'
+negl           |  in + gl'
+nella          |  in + la
+nelle          |  in + le
+su             |  on
+sul            |  su + il
+sullo          |  su + lo
+sui            |  su + i
+sugli          |  su + gli
+sull           |  su + l'
+sugl           |  su + gl'
+sulla          |  su + la
+sulle          |  su + le
+per            |  through, by
+tra            |  among
+contro         |  against
+io             |  I
+tu             |  thou
+lui            |  he
+lei            |  she
+noi            |  we
+voi            |  you
+loro           |  they
+mio            |  my
+mia            |
+miei           |
+mie            |
+tuo            |
+tua            |
+tuoi           |  thy
+tue            |
+suo            |
+sua            |
+suoi           |  his, her
+sue            |
+nostro         |  our
+nostra         |
+nostri         |
+nostre         |
+vostro         |  your
+vostra         |
+vostri         |
+vostre         |
+mi             |  me
+ti             |  thee
+ci             |  us, there
+vi             |  you, there
+lo             |  him, the
+la             |  her, the
+li             |  them
+le             |  them, the
+gli            |  to him, the
+ne             |  from there etc
+il             |  the
+un             |  a
+uno            |  a
+una            |  a
+ma             |  but
+ed             |  and
+se             |  if
+perché         |  why, because
+anche          |  also
+come           |  how
+dov            |  where (as dov')
+dove           |  where
+che            |  who, that
+chi            |  who
+cui            |  whom
+non            |  not
+più            |  more
+quale          |  who, that
+quanto         |  how much
+quanti         |
+quanta         |
+quante         |
+quello         |  that
+quelli         |
+quella         |
+quelle         |
+questo         |  this
+questi         |
+questa         |
+queste         |
+si             |  yes
+tutto          |  all
+tutti          |  all
+
+               |  single letter forms:
+
+a              |  at
+c              |  as c' for ce or ci
+e              |  and
+i              |  the
+l              |  as l'
+o              |  or
+
+               | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+               | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+               | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+               | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ja.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ja.txt
new file mode 100644
index 00000000..d4321be6
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out.  See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter.  When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner.  Change your StopFilter
+# configuration if you need case-sensitive stopping.  Lastly, note that stopping is done
+# using the same character width as the entries in this file.  Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_lv.txt b/test/solr/configsets/term_search/conf/lang/stopwords_lv.txt
new file mode 100644
index 00000000..e21a23c0
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined: 
+#   pronouns, adverbs, interjections were removed
+# 
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt  
+biju 
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat 
+būšu     
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_nl.txt b/test/solr/configsets/term_search/conf/lang/stopwords_nl.txt
new file mode 100644
index 00000000..47a2aeac
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de             |  the
+en             |  and
+van            |  of, from
+ik             |  I, the ego
+te             |  (1) chez, at etc, (2) to, (3) too
+dat            |  that, which
+die            |  that, those, who, which
+in             |  in, inside
+een            |  a, an, one
+hij            |  he
+het            |  the, it
+niet           |  not, nothing, naught
+zijn           |  (1) to be, being, (2) his, one's, its
+is             |  is
+was            |  (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op             |  on, upon, at, in, up, used up
+aan            |  on, upon, to (as dative)
+met            |  with, by
+als            |  like, such as, when
+voor           |  (1) before, in front of, (2) furrow
+had            |  had, past tense all persons sing. of 'hebben' (have)
+er             |  there
+maar           |  but, only
+om             |  round, about, for etc
+hem            |  him
+dan            |  then
+zou            |  should/would, past tense all persons sing. of 'zullen'
+of             |  or, whether, if
+wat            |  what, something, anything
+mijn           |  possessive and noun 'mine'
+men            |  people, 'one'
+dit            |  this
+zo             |  so, thus, in this way
+door           |  through by
+over           |  over, across
+ze             |  she, her, they, them
+zich           |  oneself
+bij            |  (1) a bee, (2) by, near, at
+ook            |  also, too
+tot            |  till, until
+je             |  you
+mij            |  me
+uit            |  out of, from
+der            |  Old Dutch form of 'van der' still found in surnames
+daar           |  (1) there, (2) because
+haar           |  (1) her, their, them, (2) hair
+naar           |  (1) unpleasant, unwell etc, (2) towards, (3) as
+heb            |  present first person sing. of 'to have'
+hoe            |  how, why
+heeft          |  present third person sing. of 'to have'
+hebben         |  'to have' and various parts thereof
+deze           |  this
+u              |  you
+want           |  (1) for, (2) mitten, (3) rigging
+nog            |  yet, still
+zal            |  'shall', first and third person sing. of verb 'zullen' (will)
+me             |  me
+zij            |  she, they
+nu             |  now
+ge             |  'thou', still used in Belgium and south Netherlands
+geen           |  none
+omdat          |  because
+iets           |  something, somewhat
+worden         |  to become, grow, get
+toch           |  yet, still
+al             |  all, every, each
+waren          |  (1) 'were' (2) to wander, (3) wares, (3)
+veel           |  much, many
+meer           |  (1) more, (2) lake
+doen           |  to do, to make
+toen           |  then, when
+moet           |  noun 'spot/mote' and present form of 'to must'
+ben            |  (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder         |  without
+kan            |  noun 'can' and present form of 'to be able'
+hun            |  their, them
+dus            |  so, consequently
+alles          |  all, everything, anything
+onder          |  under, beneath
+ja             |  yes, of course
+eens           |  once, one day
+hier           |  here
+wie            |  who
+werd           |  imperfect third person sing. of 'become'
+altijd         |  always
+doch           |  yet, but etc
+wordt          |  present third person sing. of 'become'
+wezen          |  (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen         |  to be able
+ons            |  us/our
+zelf           |  self
+tegen          |  against, towards, at
+na             |  after, near
+reeds          |  already
+wil            |  (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon            |  could; past tense of 'to be able'
+niets          |  nothing
+uw             |  your
+iemand         |  somebody
+geweest        |  been; past participle of 'be'
+andere         |  other
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_no.txt b/test/solr/configsets/term_search/conf/lang/stopwords_no.txt
new file mode 100644
index 00000000..a7a2c28b
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005
+
+og             | and
+i              | in
+jeg            | I
+det            | it/this/that
+at             | to (w. inf.)
+en             | a/an
+et             | a/an
+den            | it/this/that
+til            | to
+er             | is/am/are
+som            | who/that
+på             | on
+de             | they / you(formal)
+med            | with
+han            | he
+av             | of
+ikke           | not
+ikkje          | not *
+der            | there
+så             | so
+var            | was/were
+meg            | me
+seg            | you
+men            | but
+ett            | one
+har            | have
+om             | about
+vi             | we
+min            | my
+mitt           | my
+ha             | have
+hadde          | had
+hun            | she
+nå             | now
+over           | over
+da             | when/as
+ved            | by/know
+fra            | from
+du             | you
+ut             | out
+sin            | your
+dem            | them
+oss            | us
+opp            | up
+man            | you/one
+kan            | can
+hans           | his
+hvor           | where
+eller          | or
+hva            | what
+skal           | shall/must
+selv           | self (reflective)
+sjøl           | self (reflective)
+her            | here
+alle           | all
+vil            | will
+bli            | become
+ble            | became
+blei           | became *
+blitt          | have become
+kunne          | could
+inn            | in
+når            | when
+være           | be
+kom            | come
+noen           | some
+noe            | some
+ville          | would
+dere           | you
+som            | who/which/that
+deres          | their/theirs
+kun            | only/just
+ja             | yes
+etter          | after
+ned            | down
+skulle         | should
+denne          | this
+for            | for/because
+deg            | you
+si             | hers/his
+sine           | hers/his
+sitt           | hers/his
+mot            | against
+å              | to
+meget          | much
+hvorfor        | why
+dette          | this
+disse          | these/those
+uten           | without
+hvordan        | how
+ingen          | none
+din            | your
+ditt           | your
+blir           | become
+samme          | same
+hvilken        | which
+hvilke         | which (plural)
+sånn           | such a
+inni           | inside/within
+mellom         | between
+vår            | our
+hver           | each
+hvem           | who
+vors           | us/ours
+hvis           | whose
+både           | both
+bare           | only/just
+enn            | than
+fordi          | as/because
+før            | before
+mange          | many
+også           | also
+slik           | just
+vært           | been
+være           | to be
+båe            | both *
+begge          | both
+siden          | since
+dykk           | your *
+dykkar         | yours *
+dei            | they *
+deira          | them *
+deires         | theirs *
+deim           | them *
+di             | your (fem.) *
+då             | as/when *
+eg             | I *
+ein            | a/an *
+eit            | a/an *
+eitt           | a/an *
+elles          | or *
+honom          | he *
+hjå            | at *
+ho             | she *
+hoe            | she *
+henne          | her
+hennar         | her/hers
+hennes         | hers
+hoss           | how *
+hossen         | how *
+ikkje          | not *
+ingi           | noone *
+inkje          | noone *
+korleis        | how *
+korso          | how *
+kva            | what/which *
+kvar           | where *
+kvarhelst      | where *
+kven           | who/whom *
+kvi            | why *
+kvifor         | why *
+me             | we *
+medan          | while *
+mi             | my *
+mine           | my *
+mykje          | much *
+no             | now *
+nokon          | some (masc./neut.) *
+noka           | some (fem.) *
+nokor          | some *
+noko           | some *
+nokre          | some *
+si             | his/hers *
+sia            | since *
+sidan          | since *
+so             | so *
+somt           | some *
+somme          | some *
+um             | about*
+upp            | up *
+vere           | be *
+vore           | was *
+verte          | become *
+vort           | become *
+varte          | became *
+vart           | became *
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_pt.txt b/test/solr/configsets/term_search/conf/lang/stopwords_pt.txt
new file mode 100644
index 00000000..acfeb01a
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de             |  of, from
+a              |  the; to, at; her
+o              |  the; him
+que            |  who, that
+e              |  and
+do             |  de + o
+da             |  de + a
+em             |  in
+um             |  a
+para           |  for
+  | é          from SER
+com            |  with
+não            |  not, no
+uma            |  a
+os             |  the; them
+no             |  em + o
+se             |  himself etc
+na             |  em + a
+por            |  for
+mais           |  more
+as             |  the; them
+dos            |  de + os
+como           |  as, like
+mas            |  but
+  | foi        from SER
+ao             |  a + o
+ele            |  he
+das            |  de + as
+  | tem        from TER
+à              |  a + a
+seu            |  his
+sua            |  her
+ou             |  or
+  | ser        from SER
+quando         |  when
+muito          |  much
+  | há         from HAV
+nos            |  em + os; us
+já             |  already, now
+  | está       from EST
+eu             |  I
+também         |  also
+só             |  only, just
+pelo           |  per + o
+pela           |  per + a
+até            |  up to
+isso           |  that
+ela            |  he
+entre          |  between
+  | era        from SER
+depois         |  after
+sem            |  without
+mesmo          |  same
+aos            |  a + os
+  | ter        from TER
+seus           |  his
+quem           |  whom
+nas            |  em + as
+me             |  me
+esse           |  that
+eles           |  they
+  | estão      from EST
+você           |  you
+  | tinha      from TER
+  | foram      from SER
+essa           |  that
+num            |  em + um
+nem            |  nor
+suas           |  her
+meu            |  my
+às             |  a + as
+minha          |  my
+  | têm        from TER
+numa           |  em + uma
+pelos          |  per + os
+elas           |  they
+  | havia      from HAV
+  | seja       from SER
+qual           |  which
+  | será       from SER
+nós            |  we
+  | tenho      from TER
+lhe            |  to him, her
+deles          |  of them
+essas          |  those
+esses          |  those
+pelas          |  per + as
+este           |  this
+  | fosse      from SER
+dele           |  of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu             |  thou
+te             |  thee
+vocês          |  you (plural)
+vos            |  you
+lhes           |  to them
+meus           |  my
+minhas
+teu            |  thy
+tua
+teus
+tuas
+nosso          | our
+nossa
+nossos
+nossas
+
+dela           |  of her
+delas          |  of them
+
+esta           |  this
+estes          |  these
+estas          |  these
+aquele         |  that
+aquela         |  that
+aqueles        |  those
+aquelas        |  those
+isto           |  this
+aquilo         |  that
+
+               | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+               | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+               | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+               | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ro.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ro.txt
new file mode 100644
index 00000000..4fdee90a
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în 
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_ru.txt b/test/solr/configsets/term_search/conf/lang/stopwords_ru.txt
new file mode 100644
index 00000000..55271400
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и              | and
+в              | in/into
+во             | alternative form
+не             | not
+что            | what/that
+он             | he
+на             | on/onto
+я              | i
+с              | from
+со             | alternative form
+как            | how
+а              | milder form of `no' (but)
+то             | conjunction and form of `that'
+все            | all
+она            | she
+так            | so, thus
+его            | him
+но             | but
+да             | yes/and
+ты             | thou
+к              | towards, by
+у              | around, chez
+же             | intensifier particle
+вы             | you
+за             | beyond, behind
+бы             | conditional/subj. particle
+по             | up to, along
+только         | only
+ее             | her
+мне            | to me
+было           | it was
+вот            | here is/are, particle
+от             | away from
+меня           | me
+еще            | still, yet, more
+нет            | no, there isnt/arent
+о              | about
+из             | out of
+ему            | to him
+теперь         | now
+когда          | when
+даже           | even
+ну             | so, well
+вдруг          | suddenly
+ли             | interrogative particle
+если           | if
+уже            | already, but homonym of `narrower'
+или            | or
+ни             | neither
+быть           | to be
+был            | he was
+него           | prepositional form of его
+до             | up to
+вас            | you accusative
+нибудь         | indef. suffix preceded by hyphen
+опять          | again
+уж             | already, but homonym of `adder'
+вам            | to you
+сказал         | he said
+ведь           | particle `after all'
+там            | there
+потом          | then
+себя           | oneself
+ничего         | nothing
+ей             | to her
+может          | usually with `быть' as `maybe'
+они            | they
+тут            | here
+где            | where
+есть           | there is/are
+надо           | got to, must
+ней            | prepositional form of  ей
+для            | for
+мы             | we
+тебя           | thee
+их             | them, their
+чем            | than
+была           | she was
+сам            | self
+чтоб           | in order to
+без            | without
+будто          | as if
+человек        | man, person, one
+чего           | genitive form of `what'
+раз            | once
+тоже           | also
+себе           | to oneself
+под            | beneath
+жизнь          | life
+будет          | will be
+ж              | short form of intensifer particle `же'
+тогда          | then
+кто            | who
+этот           | this
+говорил        | was saying
+того           | genitive form of `that'
+потому         | for that reason
+этого          | genitive form of `this'
+какой          | which
+совсем         | altogether
+ним            | prepositional form of `его', `они'
+здесь          | here
+этом           | prepositional form of `этот'
+один           | one
+почти          | almost
+мой            | my
+тем            | instrumental/dative plural of `тот', `то'
+чтобы          | full form of `in order that'
+нее            | her (acc.)
+кажется        | it seems
+сейчас         | now
+были           | they were
+куда           | where to
+зачем          | why
+сказать        | to say
+всех           | all (acc., gen. preposn. plural)
+никогда        | never
+сегодня        | today
+можно          | possible, one can
+при            | by
+наконец        | finally
+два            | two
+об             | alternative form of `о', about
+другой         | another
+хоть           | even
+после          | after
+над            | above
+больше         | more
+тот            | that one (masc.)
+через          | across, in
+эти            | these
+нас            | us
+про            | about
+всего          | in all, only, of all
+них            | prepositional form of `они' (they)
+какая          | which, feminine
+много          | lots
+разве          | interrogative particle
+сказала        | she said
+три            | three
+эту            | this, acc. fem. sing.
+моя            | my, feminine
+впрочем        | moreover, besides
+хорошо         | good
+свою           | ones own, acc. fem. sing.
+этой           | oblique form of `эта', fem. `this'
+перед          | in front of
+иногда         | sometimes
+лучше          | better
+чуть           | a little
+том            | preposn. form of `that one'
+нельзя         | one must not
+такой          | such a one
+им             | to them
+более          | more
+всегда         | always
+конечно        | of course
+всю            | acc. fem. sing of `all'
+между          | between
+
+
+  | b: some paradigms
+  |
+  | personal pronouns
+  |
+  | я  меня  мне  мной  [мною]
+  | ты  тебя  тебе  тобой  [тобою]
+  | он  его  ему  им  [него, нему, ним]
+  | она  ее  эи  ею  [нее, нэи, нею]
+  | оно  его  ему  им  [него, нему, ним]
+  |
+  | мы  нас  нам  нами
+  | вы  вас  вам  вами
+  | они  их  им  ими  [них, ним, ними]
+  |
+  |   себя  себе  собой   [собою]
+  |
+  | demonstrative pronouns: этот (this), тот (that)
+  |
+  | этот  эта  это  эти
+  | этого  эты  это  эти
+  | этого  этой  этого  этих
+  | этому  этой  этому  этим
+  | этим  этой  этим  [этою]  этими
+  | этом  этой  этом  этих
+  |
+  | тот  та  то  те
+  | того  ту  то  те
+  | того  той  того  тех
+  | тому  той  тому  тем
+  | тем  той  тем  [тою]  теми
+  | том  той  том  тех
+  |
+  | determinative pronouns
+  |
+  | (a) весь (all)
+  |
+  | весь  вся  все  все
+  | всего  всю  все  все
+  | всего  всей  всего  всех
+  | всему  всей  всему  всем
+  | всем  всей  всем  [всею]  всеми
+  | всем  всей  всем  всех
+  |
+  | (b) сам (himself etc)
+  |
+  | сам  сама  само  сами
+  | самого саму  само  самих
+  | самого самой самого  самих
+  | самому самой самому  самим
+  | самим  самой  самим  [самою]  самими
+  | самом самой самом  самих
+  |
+  | stems of verbs `to be', `to have', `to do' and modal
+  |
+  | быть  бы  буд  быв  есть  суть
+  | име
+  | дел
+  | мог   мож  мочь
+  | уме
+  | хоч  хот
+  | долж
+  | можн
+  | нужн
+  | нельзя
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_sv.txt b/test/solr/configsets/term_search/conf/lang/stopwords_sv.txt
new file mode 100644
index 00000000..096f87f6
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ |  - Encoding was converted to UTF-8.
+ |  - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ |  så = so, but also seed. These are indicated clearly below.
+
+och            | and
+det            | it, this/that
+att            | to (with infinitive)
+i              | in, at
+en             | a
+jag            | I
+hon            | she
+som            | who, that
+han            | he
+på             | on
+den            | it, this/that
+med            | with
+var            | where, each
+sig            | him(self) etc
+för            | for
+så             | so (also: seed)
+till           | to
+är             | is
+men            | but
+ett            | a
+om             | if; around, about
+hade           | had
+de             | they, these/those
+av             | of
+icke           | not, no
+mig            | me
+du             | you
+henne          | her
+då             | then, when
+sin            | his
+nu             | now
+har            | have
+inte           | inte någon = no one
+hans           | his
+honom          | him
+skulle         | 'sake'
+hennes         | her
+där            | there
+min            | my
+man            | one (pronoun)
+ej             | nor
+vid            | at, by, on (also: vast)
+kunde          | could
+något          | some etc
+från           | from, off
+ut             | out
+när            | when
+efter          | after, behind
+upp            | up
+vi             | we
+dem            | them
+vara           | be
+vad            | what
+över           | over
+än             | than
+dig            | you
+kan            | can
+sina           | his
+här            | here
+ha             | have
+mot            | towards
+alla           | all
+under          | under (also: wonder)
+någon          | some etc
+eller          | or (else)
+allt           | all
+mycket         | much
+sedan          | since
+ju             | why
+denna          | this/that
+själv          | myself, yourself etc
+detta          | this/that
+åt             | to
+utan           | without
+varit          | was
+hur            | how
+ingen          | no
+mitt           | my
+ni             | you
+bli            | to be, become
+blev           | from bli
+oss            | us
+din            | thy
+dessa          | these/those
+några          | some etc
+deras          | their
+blir           | from bli
+mina           | my
+samma          | (the) same
+vilken         | who, that
+er             | you, your
+sådan          | such a
+vår            | our
+blivit         | from bli
+dess           | its
+inom           | within
+mellan         | between
+sådant         | such a
+varför         | why
+varje          | each
+vilka          | who, that
+ditt           | thy
+vem            | who
+vilket         | who, that
+sitta          | his
+sådana         | such a
+vart           | each
+dina           | thy
+vars           | whose
+vårt           | our
+våra           | our
+ert            | your
+era            | your
+vilkas         | whose
+
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_th.txt b/test/solr/configsets/term_search/conf/lang/stopwords_th.txt
new file mode 100644
index 00000000..07f0fabe
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
diff --git a/test/solr/configsets/term_search/conf/lang/stopwords_tr.txt b/test/solr/configsets/term_search/conf/lang/stopwords_tr.txt
new file mode 100644
index 00000000..84d9408d
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+#   (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
diff --git a/test/solr/configsets/term_search/conf/lang/userdict_ja.txt b/test/solr/configsets/term_search/conf/lang/userdict_ja.txt
new file mode 100644
index 00000000..6f0368e4
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags.  Notice that entries do
+# not have weights since they are always used when found.  This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+#  <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored.  Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
diff --git a/test/solr/configsets/term_search/conf/managed-schema b/test/solr/configsets/term_search/conf/managed-schema
new file mode 100644
index 00000000..e99e27e9
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/managed-schema
@@ -0,0 +1,1031 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+
+ For more information, on how to customize this file, please see
+ http://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+-->
+
+<schema name="default-config" version="1.6">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and 
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued 
+            by nature
+       1.1: multiValued attribute introduced, false by default 
+       1.2: omitTermFreqAndPositions attribute introduced, true by default 
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults 
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types 
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a field type from the 
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc Values is
+       recommended (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc Values will make the index
+       faster to load, more NRT-friendly and more memory-efficient. 
+       They are currently only supported by StrField, UUIDField, all 
+       *PointFields, and depending on the field type, they might require
+       the field to be single-valued, be required or have a default value
+       (check the documentation of the field type you're interested in for
+       more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.  
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This 
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this _default configset, only four fields are pre-declared:
+         id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
+         
+         Note that many dynamic fields are also defined - you can use them to specify a 
+         field's type via field naming conventions - see below.
+  
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- docValues are enabled by default for long type so we don't need to index the version field  -->
+    <field name="_version_" type="plong" indexed="false" stored="false"/>
+
+    <!-- If you don't use child/nested documents, then you should remove the next two fields:  -->
+    <!-- for nested documents (minimal; points to root document) -->
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <!-- for nested documents (relationship tracking) -->
+    <field name="_nest_path_" type="_nest_path_" /><fieldType name="_nest_path_" class="solr.NestPathField" />
+
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+    <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+         because it's very expensive to index everything twice. -->
+    <!-- <copyField source="*" dest="_text_"/> -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end.  -->
+   
+    <dynamicField name="*_i"  type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="random_*" type="random"/>
+    <dynamicField name="ignored_*" type="ignored"/>
+
+    <!-- Type used for data-driven schema, to add a string copy for each text field -->
+    <dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
+
+    <dynamicField name="*_dt"  type="pdate"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="pdate"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching.
+
+    <copyField source="sourceFieldName" dest="destinationFieldName"/>
+    -->
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+       This includes "string", "boolean", "pint", "pfloat", "plong", "pdate", "pdouble".
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!--
+      Numeric field types that index values using KD-trees.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+
+    <!-- since fields of this type are by default not stored or indexed,
+       any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime    
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+                      
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+    
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+    
+    <!-- 
+    RankFields can be used to store scoring factors to improve document ranking. They should be used
+    in combination with RankQParserPlugin.
+    (experimental)
+    --> 
+    <fieldType name="rank" class="solr.RankField"/>
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    
+    <!-- SortableTextField generaly functions exactly like TextField,
+         except that it supports, and by default uses, docValues for sorting (or faceting)
+         on the first 1024 characters of the original field values (which is configurable).
+         
+         This makes it a bit more useful then TextField in many situations, but the trade-off
+         is that it takes up more space on disk; which is why it's not used in place of TextField
+         for every fieldType in this _default schema.
+	  -->
+    <dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
+    <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
+         removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- 
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if 
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- A geospatial field type that supports multiValued and polygon shapes.
+      For more information about this and other spatial fields see:
+      http://lucene.apache.org/solr/guide/spatial-search.html
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/> 
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> 
+        <filter class="solr.BulgarianStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>       
+      </analyzer>
+    </fieldType>
+    
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Estonian -->
+    <dynamicField name="*_txt_et" type="text_et"  indexed="true"  stored="true"/>
+    <fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->   
+      </analyzer>
+    </fieldType>
+    
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Korean morphological analysis -->
+    <dynamicField name="*_txt_ko" type="text_ko"  indexed="true"  stored="true"/>
+    <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
+          The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
+          It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
+
+          This dictionary was built with MeCab, it defines a format for the features adapted
+          for the Korean language.
+          
+          Nori also has a convenient user dictionary feature that allows overriding the statistical
+          model with your own entries for segmentation, part-of-speech tags and readings without a need
+          to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+          The tokenizer supports multiple schema attributes:
+            * userDictionary: User dictionary path.
+            * userDictionaryEncoding: User dictionary encoding.
+            * decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
+            * outputUnknownUnigrams: If true outputs unigrams for unknown words.
+        -->
+        <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
+        <!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
+          listing the tags to remove. By default it removes: 
+          E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
+          This is basically an equivalent to stemming.
+        -->
+        <filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
+        <!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
+        <filter class="solr.KoreanReadingFormFilterFactory" />
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+    
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer> 
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but 
+       the default is fine for most applications.  
+       For more info: http://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/test/solr/configsets/term_search/conf/mapping-ISOLatin1Accent.txt b/test/solr/configsets/term_search/conf/mapping-ISOLatin1Accent.txt
new file mode 100644
index 00000000..ede77425
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/mapping-ISOLatin1Accent.txt
@@ -0,0 +1,246 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Syntax:
+#   "source" => "target"
+#     "source".length() > 0 (source cannot be empty.)
+#     "target".length() >= 0 (target can be empty.)
+
+# example:
+#   "À" => "A"
+#   "\u00C0" => "A"
+#   "\u00C0" => "\u0041"
+#   "ß" => "ss"
+#   "\t" => " "
+#   "\n" => ""
+
+# À => A
+"\u00C0" => "A"
+
+# Á => A
+"\u00C1" => "A"
+
+# Â => A
+"\u00C2" => "A"
+
+# Ã => A
+"\u00C3" => "A"
+
+# Ä => A
+"\u00C4" => "A"
+
+# Å => A
+"\u00C5" => "A"
+
+# Æ => AE
+"\u00C6" => "AE"
+
+# Ç => C
+"\u00C7" => "C"
+
+# È => E
+"\u00C8" => "E"
+
+# É => E
+"\u00C9" => "E"
+
+# Ê => E
+"\u00CA" => "E"
+
+# Ë => E
+"\u00CB" => "E"
+
+# Ì => I
+"\u00CC" => "I"
+
+# Í => I
+"\u00CD" => "I"
+
+# Î => I
+"\u00CE" => "I"
+
+# Ï => I
+"\u00CF" => "I"
+
+# IJ => IJ
+"\u0132" => "IJ"
+
+# Ð => D
+"\u00D0" => "D"
+
+# Ñ => N
+"\u00D1" => "N"
+
+# Ò => O
+"\u00D2" => "O"
+
+# Ó => O
+"\u00D3" => "O"
+
+# Ô => O
+"\u00D4" => "O"
+
+# Õ => O
+"\u00D5" => "O"
+
+# Ö => O
+"\u00D6" => "O"
+
+# Ø => O
+"\u00D8" => "O"
+
+# Π=> OE
+"\u0152" => "OE"
+
+# Þ
+"\u00DE" => "TH"
+
+# Ù => U
+"\u00D9" => "U"
+
+# Ú => U
+"\u00DA" => "U"
+
+# Û => U
+"\u00DB" => "U"
+
+# Ü => U
+"\u00DC" => "U"
+
+# Ý => Y
+"\u00DD" => "Y"
+
+# Ÿ => Y
+"\u0178" => "Y"
+
+# à => a
+"\u00E0" => "a"
+
+# á => a
+"\u00E1" => "a"
+
+# â => a
+"\u00E2" => "a"
+
+# ã => a
+"\u00E3" => "a"
+
+# ä => a
+"\u00E4" => "a"
+
+# å => a
+"\u00E5" => "a"
+
+# æ => ae
+"\u00E6" => "ae"
+
+# ç => c
+"\u00E7" => "c"
+
+# è => e
+"\u00E8" => "e"
+
+# é => e
+"\u00E9" => "e"
+
+# ê => e
+"\u00EA" => "e"
+
+# ë => e
+"\u00EB" => "e"
+
+# ì => i
+"\u00EC" => "i"
+
+# í => i
+"\u00ED" => "i"
+
+# î => i
+"\u00EE" => "i"
+
+# ï => i
+"\u00EF" => "i"
+
+# ij => ij
+"\u0133" => "ij"
+
+# ð => d
+"\u00F0" => "d"
+
+# ñ => n
+"\u00F1" => "n"
+
+# ò => o
+"\u00F2" => "o"
+
+# ó => o
+"\u00F3" => "o"
+
+# ô => o
+"\u00F4" => "o"
+
+# õ => o
+"\u00F5" => "o"
+
+# ö => o
+"\u00F6" => "o"
+
+# ø => o
+"\u00F8" => "o"
+
+# œ => oe
+"\u0153" => "oe"
+
+# ß => ss
+"\u00DF" => "ss"
+
+# þ => th
+"\u00FE" => "th"
+
+# ù => u
+"\u00F9" => "u"
+
+# ú => u
+"\u00FA" => "u"
+
+# û => u
+"\u00FB" => "u"
+
+# ü => u
+"\u00FC" => "u"
+
+# ý => y
+"\u00FD" => "y"
+
+# ÿ => y
+"\u00FF" => "y"
+
+# ff => ff
+"\uFB00" => "ff"
+
+# fi => fi
+"\uFB01" => "fi"
+
+# fl => fl
+"\uFB02" => "fl"
+
+# ffi => ffi
+"\uFB03" => "ffi"
+
+# ffl => ffl
+"\uFB04" => "ffl"
+
+# ſt => ft
+"\uFB05" => "ft"
+
+# st => st
+"\uFB06" => "st"
diff --git a/test/solr/configsets/term_search/conf/protwords.txt b/test/solr/configsets/term_search/conf/protwords.txt
new file mode 100644
index 00000000..1dfc0abe
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
diff --git a/test/solr/configsets/term_search/conf/schema.xml b/test/solr/configsets/term_search/conf/schema.xml
new file mode 100644
index 00000000..fa95e127
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/schema.xml
@@ -0,0 +1,1222 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - for best index size and searching performance, set "index" to false
+    for all general text fields, use copyField to copy them to the
+    catchall "text" field, and use that for searching.
+  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
+-->
+
+<schema name="ncbo_class" version="1.7">
+    <!-- attribute "name" is the name of this schema and is only used for display purposes.
+       version="x.y" is Solr's version number for the schema syntax and
+       semantics.  It should not normally be changed by applications.
+
+       1.0: multiValued attribute did not exist, all fields are multiValued
+            by nature
+       1.1: multiValued attribute introduced, false by default
+       1.2: omitTermFreqAndPositions attribute introduced, true by default
+            except for text fields.
+       1.3: removed optional field compress feature
+       1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+            behavior when a single string produces multiple tokens.  Defaults
+            to off for version >= 1.4
+       1.5: omitNorms defaults to true for primitive field types
+            (int, float, boolean, string...)
+       1.6: useDocValuesAsStored defaults to true.
+    -->
+
+    <!-- Valid attributes for fields:
+     name: mandat ory - the name for the field
+     type: mandatory - the name of a field type from the
+       fieldTypes section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     docValues: true if this field should have doc values. Doc values are
+       useful (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc values will make the index
+       faster to load, more NRT-friendly and more memory-efficient.
+       They however come with some limitations: they are currently only
+       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+       and depending on the field type, they might require the field to be
+       single-valued, be required or have a default value (check the
+       documentation of the field type you're interested in for more information)
+     multiValued: true if this field may contain multiple values per document
+     omitNorms: (expert) set to true to omit the norms associated with
+       this field (this disables length normalization and index-time
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+       Norms are omitted for primitive (non-analyzed) types by default.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This
+       will increase storage costs.
+     required: The field is required.  It will throw an error if the
+       value does not exist
+     default: a value that should be used if no value is specified
+       when adding a document.
+    -->
+
+    <!-- field names should consist of alphanumeric or underscore characters only and
+      not start with a digit.  This is not currently strictly enforced,
+      but other field names will not have first class support from all components
+      and back compatibility is not guaranteed.  Names with both leading and
+      trailing underscores (e.g. _version_) are reserved.
+    -->
+
+    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+         id, _version_, and _text_.  All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared
+         in solrconfig.xml.
+
+         Note that many dynamic fields are also defined - you can use them to specify a
+         field's type via field naming conventions - see below.
+
+         WARNING: The _text_ catch-all field will significantly increase your index size.
+         If you don't need it, consider removing it and the corresponding copyField directive.
+    -->
+    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
+    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+
+    <!-- NCBO specific fields -->
+    <field name="resource_id"           type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
+
+    <!-- searchable fields -->
+    <!-- all languages fields -->
+    <field name="prefLabel"             type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="prefLabelExact"        type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="prefLabelSuggest"      type="text_suggest"       indexed="true"  stored="true"  multiValued="true"  omitNorms="true" />
+    <field name="prefLabelSuggestEdge"  type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true"  />
+    <field name="prefLabelSuggestNgram" type="text_suggest_ngram" indexed="true"  stored="true"  multiValued="true"  omitNorms="true" />
+
+    <!--  language specific fields  (e.g prefLabel_en or prefLabel_fr) -->
+    <dynamicField name="prefLabel_*" type="text_general" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelExact_*" type="string_ci" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggest_*" type="text_suggest" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggestEdge_*" type="text_suggest_edge" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="prefLabelSuggestNgram_*" type="text_suggest_ngram" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+
+
+    <field name="synonym"               type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymExact"          type="string_ci"          indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymSuggest"        type="text_suggest"       indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+    <field name="synonymSuggestEdge"    type="text_suggest_edge"  indexed="true"  stored="true"  multiValued="true" />
+    <field name="synonymSuggestNgram"   type="text_suggest_ngram" indexed="true"  stored="true"  omitNorms="true" multiValued="true" />
+
+    <dynamicField name="synonym_*" type="text_general" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymExact_*" type="string_ci" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymSuggest_*" type="text_suggest" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+    <dynamicField name="synonymSuggestEdge_*" type="text_suggest_edge" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="synonymSuggestNgram_*" type="text_suggest_ngram" indexed="true" stored="true" omitNorms="true" multiValued="true" />
+
+
+    <field name="notation"              type="text_general"       indexed="true"  stored="true"  multiValued="false" />
+
+    <field name="definition" type="string" indexed="true" stored="true" multiValued="true" />
+    <dynamicField name="definition_*" type="string" indexed="true" stored="true" multiValued="true" />
+
+    <field name="submissionAcronym"     type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="parents"               type="string"             indexed="true"  stored="true"  multiValued="true" />
+    <field name="ontologyType"          type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
+    <field name="ontologyId"            type="string"             indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"          type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <field name="childCount"            type="int"                indexed="true"  stored="true"  multiValued="false" />
+
+    <!-- Added cui and tui (semanticType) - NCBO-695 -->
+    <field name="cui"                   type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="semanticType"          type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+
+    <field name="property"              type="text_general"       indexed="true"  stored="true"  multiValued="true" />
+    <field name="propertyRaw"           type="text_general"       indexed="false" stored="true"  multiValued="false" />
+
+    <field name="obsolete"              type="boolean"            indexed="true"  stored="true"  multiValued="false" default="false"/>
+    <field name="provisional"           type="boolean"            indexed="true"  stored="true"  multiValued="false" default="false"/>
+    <!-- END: NCBO specific fields -->
+
+    <!-- Dynamic field definitions allow using convention over configuration
+       for fields via the specification of patterns to match field names.
+       EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
+       RESTRICTION: the glob-like pattern in the name attribute must have
+       a "*" only at the start or the end.  -->
+
+    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
+    <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
+    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
+    <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
+
+    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
+    <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
+
+    <!-- KD-tree (point) numerics -->
+    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
+
+    <!-- some trie-coded dynamic fields -->
+    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
+    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
+
+    <!-- payloaded dynamic fields -->
+    <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
+    <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
+    <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
+
+    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+    <dynamicField name="random_*" type="random" />
+
+    <!-- uncomment the following to ignore any fields that don't already match an existing
+        field name or dynamic field, rather than reporting them as an error.
+        alternately, change the type="ignored" to some other type e.g. "text" if you want
+        unknown fields indexed and/or stored by default
+
+        NB: use of "*" dynamic fields will disable field type guessing and adding
+        unknown fields to the schema. -->
+    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+    <!-- Field to use to determine and enforce document uniqueness.
+      Unless this field is marked with required="false", it will be a required field
+    -->
+    <uniqueKey>id</uniqueKey>
+
+    <!-- copyField commands copy one field to another at the time a document
+       is added to the index.  It's used either to index the same field differently,
+       or to add multiple fields to the same field for easier/faster searching. -->
+
+    <copyField source="prefLabel" dest="_text_"/>
+    <copyField source="prefLabel" dest="prefLabelExact"/>
+    <copyField source="prefLabel" dest="prefLabelSuggest" />
+    <copyField source="prefLabel" dest="prefLabelSuggestEdge" />
+    <copyField source="prefLabel" dest="prefLabelSuggestNgram" />
+
+    <copyField source="synonym" dest="_text_"/>
+    <copyField source="synonym" dest="synonymExact"/>
+    <copyField source="synonym" dest="synonymSuggest" />
+    <copyField source="synonym" dest="synonymSuggestEdge" />
+    <copyField source="synonym" dest="synonymSuggestNgram" />
+
+    <copyField source="prefLabel_*" dest="prefLabelExact_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggest_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggestEdge_*" />
+    <copyField source="prefLabel_*" dest="prefLabelSuggestNgram_*" />
+
+
+    <copyField source="synonym_*" dest="synonymExact_*" />
+    <copyField source="synonym_*" dest="synonymSuggest_*" />
+    <copyField source="synonym_*" dest="synonymSuggestEdge_*" />
+    <copyField source="synonym_*" dest="synonymSuggestNgram_*" />
+
+    <copyField source="notation" dest="_text_"/>
+
+
+    <!-- field type definitions. The "name" attribute is
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldType.
+         Class names starting with "solr" refer to java classes in a
+       standard package such as org.apache.solr.analysis
+    -->
+
+    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
+
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+       It supports doc values but in that case the field needs to be
+       single-valued and either required or have a default value.
+      -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+    <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	     This includes "string","boolean", "int", "float", "long", "date", "double",
+	     including the "Trie" and "Point" variants.
+       - If sortMissingLast="true", then a sort on this field will cause documents
+         without the field to come after documents with the field,
+         regardless of the requested sort order (asc or desc).
+       - If sortMissingFirst="true", then a sort on this field will cause documents
+         without the field to come before documents with the field,
+         regardless of the requested sort order.
+       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+         then default lucene sorting will be used which places docs without the
+         field first in an ascending sort and last in a descending sort.
+    -->
+
+    <!--
+      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+      search time and at index time, but some features are still not supported.
+      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+    -->
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+    <!--
+      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+      tint/tfloat/tlong/tdouble types.
+    -->
+    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+    <!--
+     Numeric field types that index each value at various levels of precision
+     to accelerate range queries when the number of values between the range
+     endpoints is large. See the javadoc for NumericRangeQuery for internal
+     implementation details.
+
+     Smaller precisionStep values (specified in bits) will lead to more tokens
+     indexed per value, slightly larger index size, and faster range queries.
+     A precisionStep of 0 disables indexing at different precision levels.
+
+     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+    -->
+    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+         is a more restricted form of the canonical representation of dateTime
+         http://www.w3.org/TR/xmlschema-2/#dateTime
+         The trailing "Z" designates UTC time and is mandatory.
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+         All other components are mandatory.
+
+         Expressions can also be used to denote calculations that should be
+         performed relative to "NOW" to determine the value, ie...
+
+               NOW/HOUR
+                  ... Round to the start of the current hour
+               NOW-1DAY
+                  ... Exactly 1 day prior to now
+               NOW/DAY+6MONTHS+3DAYS
+                  ... 6 months and 3 days in the future from the start of
+                      the current day
+
+         Consult the TrieDateField javadocs for more information.
+      -->
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldType name="binary" class="solr.BinaryField"/>
+
+    <!-- The "RandomSortField" is not used to store or search any
+         data.  You can declare fields of this type it in your schema
+         to generate pseudo-random orderings of your docs for sorting
+         or function purposes.  The ordering is generated based on the field
+         name and the version of the index. As long as the index version
+         remains unchanged, and the same field name is reused,
+         the ordering of the docs will be consistent.
+         If you want different psuedo-random orderings of documents,
+         for the same version of the index, use a dynamicField and
+         change the field name in the request.
+     -->
+    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+    <!-- solr.TextField allows the specification of custom text analyzers
+         specified as a tokenizer and a list of token filters. Different
+         analyzers may be specified for indexing and querying.
+
+         The optional positionIncrementGap puts space between multiple fields of
+         this type on the same document, with the purpose of preventing false phrase
+         matching across fields.
+
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+     -->
+
+    <!-- One can also specify an existing Analyzer class that has a
+         default constructor via the class attribute on the analyzer element.
+         Example:
+    <fieldType name="text_greek" class="solr.TextField">
+      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+    </fieldType>
+    -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <dynamicField name="*_ws" type="text_ws"  indexed="true"  stored="true"/>
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+        wild card phrases bypass the query analyzer and will not be lowercased before matching
+        against the index. This means that the characters in wildcard phrases must be lowercase in
+        order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A general text field that has reasonable, generic
+         cross-language defaults: it tokenizes with StandardTokenizer,
+	       removes stop words from case-insensitive "stopwords.txt"
+	       (empty by default), and down cases.  At query time only, it
+	       also applies synonyms.
+	  -->
+    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it
+         tokenizes with StandardTokenizer, removes English stop words
+         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer
+         also applies synonyms from synonyms.txt. -->
+    <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+            />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+	      -->
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English, plus
+         aggressive word-splitting and autophrase features enabled.
+         This field is just like text_en, except it adds
+         WordDelimiterGraphFilter to enable splitting and matching of
+         words on case-change, alpha numeric boundaries, and
+         non-alphanumeric chars.  This means certain compound word
+         cases will work, for example query "wi fi" will match
+         document "WiFi" or "wi-fi".
+    -->
+    <dynamicField name="*_txt_en_split" type="text_en_splitting"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+        -->
+        <!-- Case insensitive stop word removal.
+        -->
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="lang/stopwords_en.txt"
+        />
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
+         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
+    <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
+    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+      <analyzer type="index">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Just like text_general except it reverses the characters of
+	       each token, to enable more efficient leading wildcard queries.
+    -->
+    <dynamicField name="*_txt_rev" type="text_general_rev"  indexed="true"  stored="true"/>
+    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+                maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
+    <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- lowercases the entire field value, keeping it as a single token.  -->
+    <dynamicField name="*_s_lower" type="lowercase"  indexed="true"  stored="true"/>
+    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at index time, so
+      queries for paths match documents at that path, or in descendent paths
+    -->
+    <dynamicField name="*_descendent_path" type="descendent_path"  indexed="true"  stored="true"/>
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+
+    <!--
+      Example of using PathHierarchyTokenizerFactory at query time, so
+      queries for paths match documents at that path, or in ancestor paths
+    -->
+    <dynamicField name="*_ancestor_path" type="ancestor_path"  indexed="true"  stored="true"/>
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+
+    <!-- since fields of this type are by default not stored or indexed,
+         any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+    <!-- This point type indexes the coordinates as separate fields (subFields)
+      If subFieldType is defined, it references a type, and a dynamic field
+      definition is created matching *___<typename>.  Alternately, if
+      subFieldSuffix is defined, that is used to create the subFields.
+      Example: if subFieldType="double", then the coordinates would be
+        indexed in fields myloc_0___double,myloc_1___double.
+      Example: if subFieldSuffix="_d" then the coordinates would be indexed
+        in fields myloc_0_d,myloc_1_d
+      The subFields are an implementation detail of the fieldType, and end
+      users normally should not need to know about them.
+     -->
+    <dynamicField name="*_point" type="point"  indexed="true"  stored="true"/>
+    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+    <!-- A specialized field for geospatial search filters and distance sorting. -->
+    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
+      For more information about this and other Spatial fields new to Solr 4, see:
+      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+    <!-- Payloaded field types -->
+    <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+      </analyzer>
+    </fieldType>
+    <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- some examples for different languages (generally ordered by ISO code) -->
+
+    <!-- Arabic -->
+    <dynamicField name="*_txt_ar" type="text_ar"  indexed="true"  stored="true"/>
+    <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- for any non-arabic -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+        <!-- normalizes ﻯ to ﻱ, etc -->
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.ArabicStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Bulgarian -->
+    <dynamicField name="*_txt_bg" type="text_bg"  indexed="true"  stored="true"/>
+    <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+        <filter class="solr.BulgarianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Catalan -->
+    <dynamicField name="*_txt_ca" type="text_ca"  indexed="true"  stored="true"/>
+    <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+    <dynamicField name="*_txt_cjk" type="text_cjk"  indexed="true"  stored="true"/>
+    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- for any non-CJK -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.CJKBigramFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Czech -->
+    <dynamicField name="*_txt_cz" type="text_cz"  indexed="true"  stored="true"/>
+    <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+        <filter class="solr.CzechStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Danish -->
+    <dynamicField name="*_txt_da" type="text_da"  indexed="true"  stored="true"/>
+    <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- German -->
+    <dynamicField name="*_txt_de" type="text_de"  indexed="true"  stored="true"/>
+    <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+        <filter class="solr.GermanNormalizationFilterFactory"/>
+        <filter class="solr.GermanLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Greek -->
+    <dynamicField name="*_txt_el" type="text_el"  indexed="true"  stored="true"/>
+    <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- greek specific lowercase for sigma -->
+        <filter class="solr.GreekLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+        <filter class="solr.GreekStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Spanish -->
+    <dynamicField name="*_txt_es" type="text_es"  indexed="true"  stored="true"/>
+    <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+        <filter class="solr.SpanishLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Basque -->
+    <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
+    <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Persian -->
+    <dynamicField name="*_txt_fa" type="text_fa"  indexed="true"  stored="true"/>
+    <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- for ZWNJ -->
+        <charFilter class="solr.PersianCharFilterFactory"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.ArabicNormalizationFilterFactory"/>
+        <filter class="solr.PersianNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Finnish -->
+    <dynamicField name="*_txt_fi" type="text_fi"  indexed="true"  stored="true"/>
+    <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+        <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- French -->
+    <dynamicField name="*_txt_fr" type="text_fr"  indexed="true"  stored="true"/>
+    <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+        <filter class="solr.FrenchLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Irish -->
+    <dynamicField name="*_txt_ga" type="text_ga"  indexed="true"  stored="true"/>
+    <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes d', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+        <!-- removes n-, etc. position increments is intentionally false! -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+        <filter class="solr.IrishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Galician -->
+    <dynamicField name="*_txt_gl" type="text_gl"  indexed="true"  stored="true"/>
+    <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+        <filter class="solr.GalicianStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Hindi -->
+    <dynamicField name="*_txt_hi" type="text_hi"  indexed="true"  stored="true"/>
+    <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <!-- normalizes unicode representation -->
+        <filter class="solr.IndicNormalizationFilterFactory"/>
+        <!-- normalizes variation in spelling -->
+        <filter class="solr.HindiNormalizationFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+        <filter class="solr.HindiStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Hungarian -->
+    <dynamicField name="*_txt_hu" type="text_hu"  indexed="true"  stored="true"/>
+    <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+        <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Armenian -->
+    <dynamicField name="*_txt_hy" type="text_hy"  indexed="true"  stored="true"/>
+    <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Indonesian -->
+    <dynamicField name="*_txt_id" type="text_id"  indexed="true"  stored="true"/>
+    <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+        <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+        <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Italian -->
+  <dynamicField name="*_txt_it" type="text_it"  indexed="true"  stored="true"/>
+  <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <!-- removes l', etc -->
+        <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+        <filter class="solr.ItalianLightStemFilterFactory"/>
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+         NOTE: If you want to optimize search for precision, use default operator AND in your request
+         handler config (q.op) Use OR if you would like to optimize for recall (default).
+    -->
+    <dynamicField name="*_txt_ja" type="text_ja"  indexed="true"  stored="true"/>
+    <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+      <analyzer>
+        <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
+           is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+           Valid values for attribute mode are:
+              normal: regular segmentation
+              search: segmentation useful for search with synonyms compounds (default)
+            extended: same as search mode, but unigrams unknown words (experimental)
+
+           For some applications it might be good to use search mode for indexing and normal mode for
+           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+           model with your own entries for segmentation, part-of-speech tags and readings without a need
+           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
+
+           User dictionary attributes are:
+                     userDictionary: user dictionary filename
+             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+           See lang/userdict_ja.txt for a sample user dictionary file.
+
+           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
+
+           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+        -->
+        <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+        <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+        <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+        <filter class="solr.JapaneseBaseFormFilterFactory"/>
+        <!-- Removes tokens with certain part-of-speech tags -->
+        <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+        <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+        <filter class="solr.CJKWidthFilterFactory"/>
+        <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+        <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+        <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+        <!-- Lower-cases romaji characters -->
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Latvian -->
+    <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
+    <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+        <filter class="solr.LatvianStemFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Dutch -->
+    <dynamicField name="*_txt_nl" type="text_nl"  indexed="true"  stored="true"/>
+    <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+        <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+        <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Norwegian -->
+    <dynamicField name="*_txt_no" type="text_no"  indexed="true"  stored="true"/>
+    <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+        <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+        <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Portuguese -->
+  <dynamicField name="*_txt_pt" type="text_pt"  indexed="true"  stored="true"/>
+  <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+        <filter class="solr.PortugueseLightStemFilterFactory"/>
+        <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+        <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+        <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Romanian -->
+    <dynamicField name="*_txt_ro" type="text_ro"  indexed="true"  stored="true"/>
+    <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Russian -->
+    <dynamicField name="*_txt_ru" type="text_ru"  indexed="true"  stored="true"/>
+    <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+        <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Swedish -->
+    <dynamicField name="*_txt_sv" type="text_sv"  indexed="true"  stored="true"/>
+    <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+        <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+      </analyzer>
+    </fieldType>
+
+    <!-- Thai -->
+    <dynamicField name="*_txt_th" type="text_th"  indexed="true"  stored="true"/>
+    <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ThaiTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+      </analyzer>
+    </fieldType>
+
+    <!-- Turkish -->
+    <dynamicField name="*_txt_tr" type="text_tr"  indexed="true"  stored="true"/>
+    <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.TurkishLowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- Similarity is the scoring routine for each document vs. a query.
+       A custom Similarity or SimilarityFactory may be specified here, but
+       the default is fine for most applications.
+       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+    -->
+    <!--
+     <similarity class="com.example.solr.CustomSimilarityFactory">
+       <str name="paramkey">param value</str>
+     </similarity>
+    -->
+
+</schema>
diff --git a/test/solr/configsets/term_search/conf/solrconfig.xml b/test/solr/configsets/term_search/conf/solrconfig.xml
new file mode 100644
index 00000000..771a0f32
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/solrconfig.xml
@@ -0,0 +1,1299 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements.  See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+     For more details about configurations options that may appear in
+     this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+  <!-- In all configuration below, a prefix of "solr." for class names
+       is an alias that causes solr to search appropriate packages,
+       including org.apache.solr.(search|update|request|core|analysis)
+
+       You may also specify a fully qualified Java classname if you
+       have your own custom plugins.
+    -->
+
+  <!-- Controls what version of Lucene various components of Solr
+       adhere to.  Generally, you want to use the latest version to
+       get all bug fixes and improvements. It is highly recommended
+       that you fully re-index after changing this setting as it can
+       affect both how text is indexed and queried.
+  -->
+  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+
+  <!-- <lib/> directives can be used to instruct Solr to load any Jars
+       identified and use them to resolve any "plugins" specified in
+       your solrconfig.xml or schema.xml (ie: Analyzers, Request
+       Handlers, etc...).
+
+       All directories and paths are resolved relative to the
+       instanceDir.
+
+       Please note that <lib/> directives are processed in the order
+       that they appear in your solrconfig.xml file, and are "stacked"
+       on top of each other when building a ClassLoader - so if you have
+       plugin jars with dependencies on other jars, the "lower level"
+       dependency jars should be loaded first.
+
+       If a "./lib" directory exists in your instanceDir, all files
+       found in it are included as if you had used the following
+       syntax...
+
+              <lib dir="./lib" />
+    -->
+
+  <!-- A 'dir' option by itself adds any files found in the directory
+       to the classpath, this is useful for including all jars in a
+       directory.
+
+       When a 'regex' is specified in addition to a 'dir', only the
+       files in that directory which completely match the regex
+       (anchored on both ends) will be included.
+
+       If a 'dir' option (with or without a regex) is used and nothing
+       is found that matches, a warning will be logged.
+
+       The example below can be used to load a solr-contrib along
+       with their external dependencies.
+    -->
+    <!-- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
+
+  <!-- an exact 'path' can be used instead of a 'dir' to specify a
+       specific jar file.  This will cause a serious error to be logged
+       if it can't be loaded.
+    -->
+  <!--
+     <lib path="../a-jar-that-does-not-exist.jar" />
+  -->
+
+  <!-- Data Directory
+
+       Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.  If
+       replication is in use, this should match the replication
+       configuration.
+    -->
+  <dataDir>${solr.data.dir:}</dataDir>
+
+
+  <!-- The DirectoryFactory to use for indexes.
+
+       solr.StandardDirectoryFactory is filesystem
+       based and tries to pick the best implementation for the current
+       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
+       wraps solr.StandardDirectoryFactory and caches small files in memory
+       for better NRT performance.
+
+       One can force a particular implementation via solr.MMapDirectoryFactory,
+       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+       solr.RAMDirectoryFactory is memory based and not persistent.
+    -->
+  <directoryFactory name="DirectoryFactory"
+                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+  <!-- The CodecFactory for defining the format of the inverted index.
+       The default implementation is SchemaCodecFactory, which is the official Lucene
+       index format, but hooks into the schema to provide per-field customization of
+       the postings lists and per-document values in the fieldType element
+       (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+       are experimental, so if you choose to customize the index format, it's a good
+       idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+       before upgrading to a newer version to avoid unnecessary reindexing.
+       A "compressionMode" string element can be added to <codecFactory> to choose
+       between the existing compression modes in the default codec: "BEST_SPEED" (default)
+       or "BEST_COMPRESSION".
+  -->
+  <codecFactory class="solr.SchemaCodecFactory"/>
+
+  <!-- NCBO: for now using the unmanaged schema (user-defined) -->
+  <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Index Config - These settings control low-level behavior of indexing
+       Most example settings here show the default value, but are commented
+       out, to more easily see where customizations have been made.
+
+       Note: This replaces <indexDefaults> and <mainIndex> from older versions
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <indexConfig>
+    <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+         LimitTokenCountFilterFactory in your fieldType definition. E.g.
+     <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+    -->
+    <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+    <!-- <writeLockTimeout>1000</writeLockTimeout>  -->
+
+    <!-- Expert: Enabling compound file will use less files for the index,
+         using fewer file descriptors on the expense of performance decrease.
+         Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+    <!-- <useCompoundFile>false</useCompoundFile> -->
+
+    <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+         indexing for buffering added documents and deletions before they are
+         flushed to the Directory.
+         maxBufferedDocs sets a limit on the number of documents buffered
+         before flushing.
+         If both ramBufferSizeMB and maxBufferedDocs is set, then
+         Lucene will flush based on whichever limit is hit first.  -->
+    <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+    <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+    <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+         per thread before they are flushed. When limit is exceeded, this triggers a forced
+         flush even if ramBufferSizeMB has not been exceeded.
+         This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+         exhaustion due to its internal 32 bit signed integer based memory addressing.
+         The specified value should be greater than 0 and less than 2048MB. When not specified,
+         Solr uses Lucene's default value 1945. -->
+    <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+    <!-- Expert: Merge Policy
+         The Merge Policy in Lucene controls how merging of segments is done.
+         The default since Solr/Lucene 3.3 is TieredMergePolicy.
+         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+         Even older versions of Lucene used LogDocMergePolicy.
+      -->
+    <!--
+        <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+          <int name="maxMergeAtOnce">10</int>
+          <int name="segmentsPerTier">10</int>
+          <double name="noCFSRatio">0.1</double>
+        </mergePolicyFactory>
+      -->
+
+    <!-- Expert: Merge Scheduler
+         The Merge Scheduler in Lucene controls how merges are
+         performed.  The ConcurrentMergeScheduler (Lucene 2.3 default)
+         can perform merges in the background using separate threads.
+         The SerialMergeScheduler (Lucene 2.2 default) does not.
+     -->
+    <!--
+       <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+       -->
+
+    <!-- LockFactory
+
+         This option specifies which Lucene LockFactory implementation
+         to use.
+
+         single = SingleInstanceLockFactory - suggested for a
+                  read-only index or when there is no possibility of
+                  another process trying to modify the index.
+         native = NativeFSLockFactory - uses OS native file locking.
+                  Do not use when multiple solr webapps in the same
+                  JVM are attempting to share a single index.
+         simple = SimpleFSLockFactory  - uses a plain file for locking
+
+         Defaults: 'native' is default for Solr3.6 and later, otherwise
+                   'simple' is the default
+
+         More details on the nuances of each LockFactory...
+         http://wiki.apache.org/lucene-java/AvailableLockFactories
+    -->
+    <lockType>${solr.lock.type:native}</lockType>
+
+    <!-- Commit Deletion Policy
+         Custom deletion policies can be specified here. The class must
+         implement org.apache.lucene.index.IndexDeletionPolicy.
+
+         The default Solr IndexDeletionPolicy implementation supports
+         deleting index commit points on number of commits, age of
+         commit point and optimized status.
+
+         The latest commit point should always be preserved regardless
+         of the criteria.
+    -->
+    <!--
+    <deletionPolicy class="solr.SolrDeletionPolicy">
+    -->
+    <!-- The number of commit points to be kept -->
+    <!-- <str name="maxCommitsToKeep">1</str> -->
+    <!-- The number of optimized commit points to be kept -->
+    <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+    <!--
+        Delete all commit points once they have reached the given age.
+        Supports DateMathParser syntax e.g.
+      -->
+    <!--
+       <str name="maxCommitAge">30MINUTES</str>
+       <str name="maxCommitAge">1DAY</str>
+    -->
+    <!--
+    </deletionPolicy>
+    -->
+
+    <!-- Lucene Infostream
+
+         To aid in advanced debugging, Lucene provides an "InfoStream"
+         of detailed information when indexing.
+
+         Setting The value to true will instruct the underlying Lucene
+         IndexWriter to write its debugging info the specified file
+      -->
+    <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+  </indexConfig>
+
+
+  <!-- JMX
+
+       This example enables JMX if and only if an existing MBeanServer
+       is found, use this if you want to configure JMX through JVM
+       parameters. Remove this to disable exposing Solr configuration
+       and statistics to JMX.
+
+       For more details see http://wiki.apache.org/solr/SolrJmx
+    -->
+  <jmx />
+  <!-- If you want to connect to a particular server, specify the
+       agentId
+    -->
+  <!-- <jmx agentId="myAgent" /> -->
+  <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+  <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+    -->
+
+  <!-- The default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+
+    <!-- Enables a transaction log, used for real-time get, durability, and
+         and solr cloud replica recovery.  The log can grow as big as
+         uncommitted changes to the index, so use of a hard autoCommit
+         is recommended (see below).
+         "dir" - the target directory for transaction logs, defaults to the
+                solr data directory.
+         "numVersionBuckets" - sets the number of buckets used to keep
+                track of max version values when checking for re-ordered
+                updates; increase this value to reduce the cost of
+                synchronizing access to version buckets during high-volume
+                indexing, this requires 8 bytes (long) * numVersionBuckets
+                of heap space per Solr core.
+    -->
+    <updateLog>
+      <str name="dir">${solr.ulog.dir:}</str>
+      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+    </updateLog>
+
+    <!-- AutoCommit
+
+         Perform a hard commit automatically under certain conditions.
+         Instead of enabling autoCommit, consider using "commitWithin"
+         when adding documents.
+
+         http://wiki.apache.org/solr/UpdateXmlMessages
+
+         maxDocs - Maximum number of documents to add since the last
+                   commit before automatically triggering a new commit.
+
+         maxTime - Maximum amount of time in ms that is allowed to pass
+                   since a document was added before automatically
+                   triggering a new commit.
+         openSearcher - if false, the commit causes recent index changes
+           to be flushed to stable storage, but does not cause a new
+           searcher to be opened to make those changes visible.
+
+         If the updateLog is enabled, then it's highly recommended to
+         have some sort of hard autoCommit to limit the log size.
+      -->
+    <autoCommit>
+      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+      <openSearcher>false</openSearcher>
+    </autoCommit>
+
+    <!-- softAutoCommit is like autoCommit except it causes a
+         'soft' commit which only ensures that changes are visible
+         but does not ensure that data is synced to disk.  This is
+         faster and more near-realtime friendly than a hard commit.
+      -->
+
+    <autoSoftCommit>
+      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+    </autoSoftCommit>
+
+    <!-- Update Related Event Listeners
+
+         Various IndexWriter related events can trigger Listeners to
+         take actions.
+
+         postCommit - fired after every commit or optimize command
+         postOptimize - fired after every optimize command
+      -->
+
+  </updateHandler>
+
+  <!-- IndexReaderFactory
+
+       Use the following format to specify a custom IndexReaderFactory,
+       which allows for alternate IndexReader implementations.
+
+       ** Experimental Feature **
+
+       Please note - Using a custom IndexReaderFactory may prevent
+       certain other features from working. The API to
+       IndexReaderFactory may change without warning or may even be
+       removed from future releases if the problems cannot be
+       resolved.
+
+
+       ** Features that may not work with custom IndexReaderFactory **
+
+       The ReplicationHandler assumes a disk-resident index. Using a
+       custom IndexReader implementation may cause incompatibility
+       with ReplicationHandler and may cause replication to not work
+       correctly. See SOLR-1366 for details.
+
+    -->
+  <!--
+  <indexReaderFactory name="IndexReaderFactory" class="package.class">
+    <str name="someArg">Some Value</str>
+  </indexReaderFactory >
+  -->
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+       Query section - these settings control query time things like caches
+       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+  <query>
+
+    <!-- Maximum number of clauses allowed when parsing a boolean query string.
+         
+         This limit only impacts boolean queries specified by a user as part of a query string,
+         and provides per-collection controls on how complex user specified boolean queries can
+         be.  Query strings that specify more clauses then this will result in an error.
+         
+         If this per-collection limit is greater then the global `maxBooleanClauses` limit
+         specified in `solr.xml`, it will have no effect, as that setting also limits the size
+         of user specified boolean queries.
+      -->
+    <maxBooleanClauses>${solr.max.booleanClauses:500000}</maxBooleanClauses>
+
+    <!-- Solr Internal Query Caches
+
+         There are four implementations of cache available for Solr:
+         LRUCache, based on a synchronized LinkedHashMap, 
+         LFUCache and FastLRUCache, based on a ConcurrentHashMap, and CaffeineCache -
+         a modern and robust cache implementation. Note that in Solr 9.0
+         only CaffeineCache will be available, other implementations are now
+         deprecated.
+
+         FastLRUCache has faster gets and slower puts in single
+         threaded operation and thus is generally faster than LRUCache
+         when the hit ratio of the cache is high (> 75%), and may be
+         faster under other scenarios on multi-cpu systems.
+         Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
+    -->
+
+    <!-- Filter Cache
+
+         Cache used by SolrIndexSearcher for filters (DocSets),
+         unordered sets of *all* documents that match a query.  When a
+         new searcher is opened, its caches may be prepopulated or
+         "autowarmed" using data from caches in the old searcher.
+         autowarmCount is the number of items to prepopulate.  For
+         LRUCache, the autowarmed items will be the most recently
+         accessed items.
+
+         Parameters:
+           class - the SolrCache implementation LRUCache or
+               (LRUCache or FastLRUCache)
+           size - the maximum number of entries in the cache
+           initialSize - the initial capacity (number of entries) of
+               the cache.  (see java.util.HashMap)
+           autowarmCount - the number of entries to prepopulate from
+               an old cache.
+           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                      to occupy. Note that when this option is specified, the size
+                      and initialSize parameters are ignored.
+      -->
+    <filterCache size="512"
+                 initialSize="512"
+                 autowarmCount="0"/>
+
+    <!-- Query Result Cache
+
+         Caches results of searches - ordered lists of document ids
+         (DocList) based on a query, a sort, and the range of documents requested.
+         Additional supported parameter by LRUCache:
+            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+                       to occupy
+      -->
+    <queryResultCache size="512"
+                      initialSize="512"
+                      autowarmCount="0"/>
+
+    <!-- Document Cache
+
+         Caches Lucene Document objects (the stored fields for each
+         document).  Since Lucene internal document ids are transient,
+         this cache will not be autowarmed.
+      -->
+    <documentCache size="512"
+                   initialSize="512"
+                   autowarmCount="0"/>
+
+    <!-- custom cache currently used by block join -->
+    <cache name="perSegFilter"
+           size="10"
+           initialSize="0"
+           autowarmCount="10"
+           regenerator="solr.NoOpRegenerator" />
+
+    <!-- Field Value Cache
+
+         Cache used to hold field values that are quickly accessible
+         by document id.  The fieldValueCache is created by default
+         even if not configured here.
+      -->
+    <!--
+       <fieldValueCache size="512"
+                        autowarmCount="128"
+                        showItems="32" />
+      -->
+
+    <!-- Custom Cache
+
+         Example of a generic cache.  These caches may be accessed by
+         name through SolrIndexSearcher.getCache(),cacheLookup(), and
+         cacheInsert().  The purpose is to enable easy caching of
+         user/application level data.  The regenerator argument should
+         be specified as an implementation of solr.CacheRegenerator
+         if autowarming is desired.
+      -->
+    <!--
+       <cache name="myUserCache"
+              size="4096"
+              initialSize="1024"
+              autowarmCount="1024"
+              regenerator="com.mycompany.MyRegenerator"
+              />
+      -->
+
+
+    <!-- Lazy Field Loading
+
+         If true, stored fields that are not requested will be loaded
+         lazily.  This can result in a significant speed improvement
+         if the usual case is to not load all stored fields,
+         especially if the skipped fields are large compressed text
+         fields.
+    -->
+    <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+    <!-- Use Filter For Sorted Query
+
+         A possible optimization that attempts to use a filter to
+         satisfy a search.  If the requested sort does not include
+         score, then the filterCache will be checked for a filter
+         matching the query. If found, the filter will be used as the
+         source of document ids, and then the sort will be applied to
+         that.
+
+         For most situations, this will not be useful unless you
+         frequently get the same search repeatedly with different sort
+         options, and none of them ever use "score"
+      -->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Result Window Size
+
+         An optimization for use with the queryResultCache.  When a search
+         is requested, a superset of the requested number of document ids
+         are collected.  For example, if a search for a particular query
+         requests matching documents 10 through 19, and queryWindowSize is 50,
+         then documents 0 through 49 will be collected and cached.  Any further
+         requests in that range can be satisfied via the cache.
+      -->
+    <queryResultWindowSize>20</queryResultWindowSize>
+
+    <!-- Maximum number of documents to cache for any entry in the
+         queryResultCache.
+      -->
+    <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+  <!-- Use Filter For Sorted Query
+
+   A possible optimization that attempts to use a filter to
+   satisfy a search.  If the requested sort does not include
+   score, then the filterCache will be checked for a filter
+   matching the query. If found, the filter will be used as the
+   source of document ids, and then the sort will be applied to
+   that.
+
+   For most situations, this will not be useful unless you
+   frequently get the same search repeatedly with different sort
+   options, and none of them ever use "score"
+-->
+    <!--
+       <useFilterForSortedQuery>true</useFilterForSortedQuery>
+      -->
+
+    <!-- Query Related Event Listeners
+
+         Various IndexSearcher related events can trigger Listeners to
+         take actions.
+
+         newSearcher - fired whenever a new searcher is being prepared
+         and there is a current searcher handling requests (aka
+         registered).  It can be used to prime certain caches to
+         prevent long request times for certain requests.
+
+         firstSearcher - fired whenever a new searcher is being
+         prepared but there is no current registered searcher to handle
+         requests or to gain autowarming data from.
+
+
+      -->
+    <!-- QuerySenderListener takes an array of NamedList and executes a
+         local query request for each NamedList in sequence.
+      -->
+    <listener event="newSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+          -->
+      </arr>
+    </listener>
+    <listener event="firstSearcher" class="solr.QuerySenderListener">
+      <arr name="queries">
+        <!--
+        <lst>
+          <str name="q">static firstSearcher warming in solrconfig.xml</str>
+        </lst>
+        -->
+      </arr>
+    </listener>
+
+    <!-- Use Cold Searcher
+
+         If a search request comes in and there is no current
+         registered searcher, then immediately register the still
+         warming searcher and use it.  If "false" then all requests
+         will block until the first searcher is done warming.
+      -->
+    <useColdSearcher>false</useColdSearcher>
+
+  </query>
+
+  <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+     Circuit Breaker Section - This section consists of configurations for
+     circuit breakers
+     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+
+    <!-- Circuit Breakers
+
+     Circuit breakers are designed to allow stability and predictable query
+     execution. They prevent operations that can take down the node and cause
+     noisy neighbour issues.
+
+     This flag is the uber control switch which controls the activation/deactivation of all circuit
+     breakers. If a circuit breaker wishes to be independently configurable,
+     they are free to add their specific configuration but need to ensure that this flag is always
+     respected - this should have veto over all independent configuration flags.
+    -->
+    <circuitBreakers enabled="true">
+
+    <!-- Memory Circuit Breaker Configuration
+
+     Specific configuration for max JVM heap usage circuit breaker. This configuration defines whether
+     the circuit breaker is enabled and the threshold percentage of maximum heap allocated beyond which queries will be rejected until the
+     current JVM usage goes below the threshold. The valid value range for this value is 50-95.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+
+     If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
+     If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
+     in logs and the corresponding error message should tell you what transpired (if the failure
+     was caused by tripped circuit breakers).
+    -->
+    <!--
+   <memBreaker enabled="true" threshold="75"/>
+    -->
+
+      <!-- CPU Circuit Breaker Configuration
+
+     Specific configuration for CPU utilization based circuit breaker. This configuration defines whether the circuit breaker is enabled
+     and the average load over the last minute at which the circuit breaker should start rejecting queries.
+
+     Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThreshold is
+     defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
+     allocated.
+    -->
+
+      <!--
+       <cpuBreaker enabled="true" threshold="75"/>
+      -->
+
+  </circuitBreakers>
+
+
+  <!-- Request Dispatcher
+
+       This section contains instructions for how the SolrDispatchFilter
+       should behave when processing requests for this SolrCore.
+
+    -->
+  <requestDispatcher>
+    <!-- Request Parsing
+
+         These settings indicate how Solr Requests may be parsed, and
+         what restrictions may be placed on the ContentStreams from
+         those requests
+
+         enableRemoteStreaming - enables use of the stream.file
+         and stream.url parameters for specifying remote streams.
+
+         multipartUploadLimitInKB - specifies the max size (in KiB) of
+         Multipart File Uploads that Solr will allow in a Request.
+
+         formdataUploadLimitInKB - specifies the max size (in KiB) of
+         form data (application/x-www-form-urlencoded) sent via
+         POST. You can use POST to pass request parameters not
+         fitting into the URL.
+
+         addHttpRequestToContext - if set to true, it will instruct
+         the requestParsers to include the original HttpServletRequest
+         object in the context map of the SolrQueryRequest under the
+         key "httpRequest". It will not be used by any of the existing
+         Solr components, but may be useful when developing custom
+         plugins.
+
+         *** WARNING ***
+         Before enabling remote streaming, you should make sure your
+         system has authentication enabled.
+
+    <requestParsers enableRemoteStreaming="false"
+                    multipartUploadLimitInKB="-1"
+                    formdataUploadLimitInKB="-1"
+                    addHttpRequestToContext="false"/>
+      -->
+
+    <!-- HTTP Caching
+
+         Set HTTP caching related parameters (for proxy caches and clients).
+
+         The options below instruct Solr not to output any HTTP Caching
+         related headers
+      -->
+    <httpCaching never304="true" />
+    <!-- If you include a <cacheControl> directive, it will be used to
+         generate a Cache-Control header (as well as an Expires header
+         if the value contains "max-age=")
+
+         By default, no Cache-Control header is generated.
+
+         You can use the <cacheControl> option even if you have set
+         never304="true"
+      -->
+    <!--
+       <httpCaching never304="true" >
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+    <!-- To enable Solr to respond with automatically generated HTTP
+         Caching headers, and to response to Cache Validation requests
+         correctly, set the value of never304="false"
+
+         This will cause Solr to generate Last-Modified and ETag
+         headers based on the properties of the Index.
+
+         The following options can also be specified to affect the
+         values of these headers...
+
+         lastModFrom - the default value is "openTime" which means the
+         Last-Modified value (and validation against If-Modified-Since
+         requests) will all be relative to when the current Searcher
+         was opened.  You can change it to lastModFrom="dirLastMod" if
+         you want the value to exactly correspond to when the physical
+         index was last modified.
+
+         etagSeed="..." is an option you can change to force the ETag
+         header (and validation against If-None-Match requests) to be
+         different even if the index has not changed (ie: when making
+         significant changes to your config file)
+
+         (lastModifiedFrom and etagSeed are both ignored if you use
+         the never304="true" option)
+      -->
+    <!--
+       <httpCaching lastModifiedFrom="openTime"
+                    etagSeed="Solr">
+         <cacheControl>max-age=30, public</cacheControl>
+       </httpCaching>
+      -->
+  </requestDispatcher>
+
+  <!-- Request Handlers
+
+       http://wiki.apache.org/solr/SolrRequestHandler
+
+       Incoming queries will be dispatched to a specific handler by name
+       based on the path specified in the request.
+
+       If a Request Handler is declared with startup="lazy", then it will
+       not be initialized until the first request that uses it.
+
+    -->
+  <!-- SearchHandler
+
+       http://wiki.apache.org/solr/SearchHandler
+
+       For processing Search Queries, the primary Request Handler
+       provided with Solr is "SearchHandler" It delegates to a sequent
+       of SearchComponents (see below) and supports distributed
+       queries across multiple shards
+    -->
+  <requestHandler name="/select" class="solr.SearchHandler">
+    <!-- default values for query parameters can be specified, these
+         will be overridden by parameters in the request
+      -->
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <int name="rows">10</int>
+      <!-- Default search field
+         <str name="df">text</str> 
+        -->
+      <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+         <str name="wt">xml</str> 
+        -->
+    </lst>
+    <!-- In addition to defaults, "appends" params can be specified
+         to identify values which should be appended to the list of
+         multi-val params from the query (or the existing "defaults").
+      -->
+    <!-- In this example, the param "fq=instock:true" would be appended to
+         any query time fq params the user may specify, as a mechanism for
+         partitioning the index, independent of any user selected filtering
+         that may also be desired (perhaps as a result of faceted searching).
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "appends" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="appends">
+         <str name="fq">inStock:true</str>
+       </lst>
+      -->
+    <!-- "invariants" are a way of letting the Solr maintainer lock down
+         the options available to Solr clients.  Any params values
+         specified here are used regardless of what values may be specified
+         in either the query, the "defaults", or the "appends" params.
+
+         In this example, the facet.field and facet.query params would
+         be fixed, limiting the facets clients can use.  Faceting is
+         not turned on by default - but if the client does specify
+         facet=true in the request, these are the only facets they
+         will be able to see counts for; regardless of what other
+         facet.field or facet.query params they may specify.
+
+         NOTE: there is *absolutely* nothing a client can do to prevent these
+         "invariants" values from being used, so don't use this mechanism
+         unless you are sure you always want it.
+      -->
+    <!--
+       <lst name="invariants">
+         <str name="facet.field">cat</str>
+         <str name="facet.field">manu_exact</str>
+         <str name="facet.query">price:[* TO 500]</str>
+         <str name="facet.query">price:[500 TO *]</str>
+       </lst>
+      -->
+    <!-- If the default list of SearchComponents is not desired, that
+         list can either be overridden completely, or components can be
+         prepended or appended to the default list.  (see below)
+      -->
+    <!--
+       <arr name="components">
+         <str>nameOfCustomComponent1</str>
+         <str>nameOfCustomComponent2</str>
+       </arr>
+      -->
+  </requestHandler>
+
+  <!-- A request handler that returns indented JSON by default -->
+  <requestHandler name="/query" class="solr.SearchHandler">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+      <str name="wt">json</str>
+      <str name="indent">true</str>
+    </lst>
+  </requestHandler>
+
+  <initParams path="/update/**,/query,/select,/spell">
+    <lst name="defaults">
+      <str name="df">_text_</str>
+    </lst>
+  </initParams>
+
+  <!-- Search Components
+
+       Search components are registered to SolrCore and used by
+       instances of SearchHandler (which can access them by name)
+
+       By default, the following components are available:
+
+       <searchComponent name="query"     class="solr.QueryComponent" />
+       <searchComponent name="facet"     class="solr.FacetComponent" />
+       <searchComponent name="mlt"       class="solr.MoreLikeThisComponent" />
+       <searchComponent name="highlight" class="solr.HighlightComponent" />
+       <searchComponent name="stats"     class="solr.StatsComponent" />
+       <searchComponent name="debug"     class="solr.DebugComponent" />
+
+       Default configuration in a requestHandler would look like:
+
+       <arr name="components">
+         <str>query</str>
+         <str>facet</str>
+         <str>mlt</str>
+         <str>highlight</str>
+         <str>stats</str>
+         <str>debug</str>
+       </arr>
+
+       If you register a searchComponent to one of the standard names,
+       that will be used instead of the default.
+
+       To insert components before or after the 'standard' components, use:
+
+       <arr name="first-components">
+         <str>myFirstComponentName</str>
+       </arr>
+
+       <arr name="last-components">
+         <str>myLastComponentName</str>
+       </arr>
+
+       NOTE: The component registered with the name "debug" will
+       always be executed after the "last-components"
+
+     -->
+
+  <!-- Spell Check
+
+       The spell check component can return a list of alternative spelling
+       suggestions.
+
+       http://wiki.apache.org/solr/SpellCheckComponent
+    -->
+  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+    <str name="queryAnalyzerFieldType">text_general</str>
+
+    <!-- Multiple "Spell Checkers" can be declared and used by this
+         component
+      -->
+
+    <!-- a spellchecker built from a field of the main index -->
+    <lst name="spellchecker">
+      <str name="name">default</str>
+      <str name="field">_text_</str>
+      <str name="classname">solr.DirectSolrSpellChecker</str>
+      <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+      <str name="distanceMeasure">internal</str>
+      <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+      <float name="accuracy">0.5</float>
+      <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+      <int name="maxEdits">2</int>
+      <!-- the minimum shared prefix when enumerating terms -->
+      <int name="minPrefix">1</int>
+      <!-- maximum number of inspections per result. -->
+      <int name="maxInspections">5</int>
+      <!-- minimum length of a query term to be considered for correction -->
+      <int name="minQueryLength">4</int>
+      <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+      <float name="maxQueryFrequency">0.01</float>
+      <!-- uncomment this to require suggestions to occur in 1% of the documents
+        <float name="thresholdTokenFrequency">.01</float>
+      -->
+    </lst>
+
+    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
+    <!--
+    <lst name="spellchecker">
+      <str name="name">wordbreak</str>
+      <str name="classname">solr.WordBreakSolrSpellChecker</str>
+      <str name="field">name</str>
+      <str name="combineWords">true</str>
+      <str name="breakWords">true</str>
+      <int name="maxChanges">10</int>
+    </lst>
+    -->
+  </searchComponent>
+
+  <!-- A request handler for demonstrating the spellcheck component.
+
+       NOTE: This is purely as an example.  The whole purpose of the
+       SpellCheckComponent is to hook it into the request handler that
+       handles your normal user queries so that a separate request is
+       not needed to get suggestions.
+
+       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+       See http://wiki.apache.org/solr/SpellCheckComponent for details
+       on the request parameters.
+    -->
+  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <!-- Solr will use suggestions from both the 'default' spellchecker
+           and from the 'wordbreak' spellchecker and combine them.
+           collations (re-written queries) can include a combination of
+           corrections from both spellcheckers -->
+      <str name="spellcheck.dictionary">default</str>
+      <str name="spellcheck">on</str>
+      <str name="spellcheck.extendedResults">true</str>
+      <str name="spellcheck.count">10</str>
+      <str name="spellcheck.alternativeTermCount">5</str>
+      <str name="spellcheck.maxResultsForSuggest">5</str>
+      <str name="spellcheck.collate">true</str>
+      <str name="spellcheck.collateExtendedResults">true</str>
+      <str name="spellcheck.maxCollationTries">10</str>
+      <str name="spellcheck.maxCollations">5</str>
+    </lst>
+    <arr name="last-components">
+      <str>spellcheck</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Terms Component
+
+       http://wiki.apache.org/solr/TermsComponent
+
+       A component to return terms and document frequency of those
+       terms
+    -->
+  <searchComponent name="terms" class="solr.TermsComponent"/>
+
+  <!-- A request handler for demonstrating the terms component -->
+  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+    <lst name="defaults">
+      <bool name="terms">true</bool>
+      <bool name="distrib">false</bool>
+    </lst>
+    <arr name="components">
+      <str>terms</str>
+    </arr>
+  </requestHandler>
+
+  <!-- Highlighting Component
+
+       http://wiki.apache.org/solr/HighlightingParameters
+    -->
+  <searchComponent class="solr.HighlightComponent" name="highlight">
+    <highlighting>
+      <!-- Configure the standard fragmenter -->
+      <!-- This could most likely be commented out in the "default" case -->
+      <fragmenter name="gap"
+                  default="true"
+                  class="solr.highlight.GapFragmenter">
+        <lst name="defaults">
+          <int name="hl.fragsize">100</int>
+        </lst>
+      </fragmenter>
+
+      <!-- A regular-expression-based fragmenter
+           (for sentence extraction)
+        -->
+      <fragmenter name="regex"
+                  class="solr.highlight.RegexFragmenter">
+        <lst name="defaults">
+          <!-- slightly smaller fragsizes work better because of slop -->
+          <int name="hl.fragsize">70</int>
+          <!-- allow 50% slop on fragment sizes -->
+          <float name="hl.regex.slop">0.5</float>
+          <!-- a basic sentence pattern -->
+          <str name="hl.regex.pattern">[-\w ,/\n\&quot;&apos;]{20,200}</str>
+        </lst>
+      </fragmenter>
+
+      <!-- Configure the standard formatter -->
+      <formatter name="html"
+                 default="true"
+                 class="solr.highlight.HtmlFormatter">
+        <lst name="defaults">
+          <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+          <str name="hl.simple.post"><![CDATA[</em>]]></str>
+        </lst>
+      </formatter>
+
+      <!-- Configure the standard encoder -->
+      <encoder name="html"
+               class="solr.highlight.HtmlEncoder" />
+
+      <!-- Configure the standard fragListBuilder -->
+      <fragListBuilder name="simple"
+                       class="solr.highlight.SimpleFragListBuilder"/>
+
+      <!-- Configure the single fragListBuilder -->
+      <fragListBuilder name="single"
+                       class="solr.highlight.SingleFragListBuilder"/>
+
+      <!-- Configure the weighted fragListBuilder -->
+      <fragListBuilder name="weighted"
+                       default="true"
+                       class="solr.highlight.WeightedFragListBuilder"/>
+
+      <!-- default tag FragmentsBuilder -->
+      <fragmentsBuilder name="default"
+                        default="true"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <!--
+        <lst name="defaults">
+          <str name="hl.multiValuedSeparatorChar">/</str>
+        </lst>
+        -->
+      </fragmentsBuilder>
+
+      <!-- multi-colored tag FragmentsBuilder -->
+      <fragmentsBuilder name="colored"
+                        class="solr.highlight.ScoreOrderFragmentsBuilder">
+        <lst name="defaults">
+          <str name="hl.tag.pre"><![CDATA[
+               <b style="background:yellow">,<b style="background:lawgreen">,
+               <b style="background:aquamarine">,<b style="background:magenta">,
+               <b style="background:palegreen">,<b style="background:coral">,
+               <b style="background:wheat">,<b style="background:khaki">,
+               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+          <str name="hl.tag.post"><![CDATA[</b>]]></str>
+        </lst>
+      </fragmentsBuilder>
+
+      <boundaryScanner name="default"
+                       default="true"
+                       class="solr.highlight.SimpleBoundaryScanner">
+        <lst name="defaults">
+          <str name="hl.bs.maxScan">10</str>
+          <str name="hl.bs.chars">.,!? &#9;&#10;&#13;</str>
+        </lst>
+      </boundaryScanner>
+
+      <boundaryScanner name="breakIterator"
+                       class="solr.highlight.BreakIteratorBoundaryScanner">
+        <lst name="defaults">
+          <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+          <str name="hl.bs.type">WORD</str>
+          <!-- language and country are used when constructing Locale object.  -->
+          <!-- And the Locale object will be used when getting instance of BreakIterator -->
+          <str name="hl.bs.language">en</str>
+          <str name="hl.bs.country">US</str>
+        </lst>
+      </boundaryScanner>
+    </highlighting>
+  </searchComponent>
+
+  <!-- Update Processors
+
+       Chains of Update Processor Factories for dealing with Update
+       Requests can be declared, and then used by name in Update
+       Request Processors
+
+       http://wiki.apache.org/solr/UpdateRequestProcessor
+
+    -->
+
+  <!-- Add unknown fields to the schema
+
+       Field type guessing update processors that will
+       attempt to parse string-typed field values as Booleans, Longs,
+       Doubles, or Dates, and then add schema fields with the guessed
+       field types. Text content will be indexed as "text_general" as
+       well as a copy to a plain string version in *_str.
+
+       These require that the schema is both managed and mutable, by
+       declaring schemaFactory as ManagedIndexSchemaFactory, with
+       mutable specified as true.
+
+       See http://wiki.apache.org/solr/GuessingFieldTypes
+    -->
+  <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+  <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+  <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+    <str name="pattern">[^\w-\.]</str>
+    <str name="replacement">_</str>
+  </updateProcessor>
+  <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+  <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+  <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+  <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+    <arr name="format">
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+      <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+      <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+      <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+      <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+    </arr>
+  </updateProcessor>
+  <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.String</str>
+      <str name="fieldType">text_general</str>
+      <lst name="copyField">
+        <str name="dest">*_str</str>
+        <int name="maxChars">256</int>
+      </lst>
+      <!-- Use as default mapping instead of defaultFieldType -->
+      <bool name="default">true</bool>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Boolean</str>
+      <str name="fieldType">booleans</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.util.Date</str>
+      <str name="fieldType">pdates</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Long</str>
+      <str name="valueClass">java.lang.Integer</str>
+      <str name="fieldType">plongs</str>
+    </lst>
+    <lst name="typeMapping">
+      <str name="valueClass">java.lang.Number</str>
+      <str name="fieldType">pdoubles</str>
+    </lst>
+  </updateProcessor>
+
+  <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+  <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:false}"
+           processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+    <processor class="solr.LogUpdateProcessorFactory"/>
+    <processor class="solr.DistributedUpdateProcessorFactory"/>
+    <processor class="solr.RunUpdateProcessorFactory"/>
+  </updateRequestProcessorChain>
+
+  <!-- Deduplication
+
+       An example dedup update processor that creates the "id" field
+       on the fly based on the hash code of some other fields.  This
+       example has overwriteDupes set to false since we are using the
+       id field as the signatureField and Solr will maintain
+       uniqueness based on that anyway.
+
+    -->
+  <!--
+     <updateRequestProcessorChain name="dedupe">
+       <processor class="solr.processor.SignatureUpdateProcessorFactory">
+         <bool name="enabled">true</bool>
+         <str name="signatureField">id</str>
+         <bool name="overwriteDupes">false</bool>
+         <str name="fields">name,features,cat</str>
+         <str name="signatureClass">solr.processor.Lookup3Signature</str>
+       </processor>
+       <processor class="solr.LogUpdateProcessorFactory" />
+       <processor class="solr.RunUpdateProcessorFactory" />
+     </updateRequestProcessorChain>
+    -->
+
+  <!-- Response Writers
+
+       http://wiki.apache.org/solr/QueryResponseWriter
+
+       Request responses will be written using the writer specified by
+       the 'wt' request parameter matching the name of a registered
+       writer.
+
+       The "default" writer is the default and will be used if 'wt' is
+       not specified in the request.
+    -->
+  <!-- The following response writers are implicitly configured unless
+       overridden...
+    -->
+  <!--
+     <queryResponseWriter name="xml"
+                          default="true"
+                          class="solr.XMLResponseWriter" />
+     <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+     <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+     <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+     <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+     <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+     <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+     <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+    -->
+
+  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+    <!-- For the purposes of the tutorial, JSON responses are written as
+     plain text so that they are easy to read in *any* browser.
+     If you expect a MIME type of "application/json" just remove this override.
+    -->
+    <str name="content-type">text/plain; charset=UTF-8</str>
+  </queryResponseWriter>
+
+  <!-- Query Parsers
+
+       https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
+
+       Multiple QParserPlugins can be registered by name, and then
+       used in either the "defType" param for the QueryComponent (used
+       by SearchHandler) or in LocalParams
+    -->
+  <!-- example of registering a query parser -->
+  <!--
+     <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+    -->
+
+  <!-- Function Parsers
+
+       http://wiki.apache.org/solr/FunctionQuery
+
+       Multiple ValueSourceParsers can be registered by name, and then
+       used as function names when using the "func" QParser.
+    -->
+  <!-- example of registering a custom function parser  -->
+  <!--
+     <valueSourceParser name="myfunc"
+                        class="com.mycompany.MyValueSourceParser" />
+    -->
+
+
+  <!-- Document Transformers
+       http://wiki.apache.org/solr/DocTransformers
+    -->
+  <!--
+     Could be something like:
+     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+       <int name="connection">jdbc://....</int>
+     </transformer>
+
+     To add a constant value to all docs, use:
+     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <int name="value">5</int>
+     </transformer>
+
+     If you want the user to still be able to change it with _value:something_ use this:
+     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+       <double name="defaultValue">5</double>
+     </transformer>
+
+      If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
+      EditorialMarkerFactory will do exactly that:
+     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+    -->
+</config>
diff --git a/test/solr/configsets/term_search/conf/stopwords.txt b/test/solr/configsets/term_search/conf/stopwords.txt
new file mode 100644
index 00000000..ae1e83ee
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
diff --git a/test/solr/configsets/term_search/conf/synonyms.txt b/test/solr/configsets/term_search/conf/synonyms.txt
new file mode 100644
index 00000000..eab4ee87
--- /dev/null
+++ b/test/solr/configsets/term_search/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
diff --git a/test/solr/docker-compose.yml b/test/solr/docker-compose.yml
new file mode 100644
index 00000000..3ddae69c
--- /dev/null
+++ b/test/solr/docker-compose.yml
@@ -0,0 +1,13 @@
+version: '3.8'
+
+services:
+  op_solr:
+    image: solr:8.8
+    volumes:
+      - ./solr_configsets:/configsets:ro
+    ports:
+      - "8983:8983"
+    command: >
+      bash -c "precreate-core term_search_core1 /configsets/term_search
+      && precreate-core prop_search_core1 /configsets/property_search
+      && solr-foreground"
diff --git a/test/solr/generate_ncbo_configsets.sh b/test/solr/generate_ncbo_configsets.sh
new file mode 100755
index 00000000..7b4281f7
--- /dev/null
+++ b/test/solr/generate_ncbo_configsets.sh
@@ -0,0 +1,24 @@
+#!/bin/bash
+# generates solr configsets by merging _default configset with config files in config/solr
+# _default is copied from sorl distribuion solr-8.10.1/server/solr/configsets/_default/
+
+#cd solr/configsets
+ld_config='config/solr'
+configsets='test/solr/configsets'
+[ -d ${configsets}/property_search ] && rm -Rf ${configsets}/property_search
+[ -d ${configsets}/term_search ] && rm -Rf ${configsets}/term_search
+if [[ ! -d ${ld_config}/property_search ]]; then
+  echo 'cant find ld solr config sets'
+  exit 1
+fi
+if [[ ! -d ${configsets}/_default/conf ]]; then
+  echo 'cant find default solr configset' 
+  exit 1
+fi
+mkdir -p ${configsets}/property_search/conf
+mkdir -p ${configsets}/term_search/conf
+cp -a ${configsets}/_default/conf/* ${configsets}/property_search/conf/
+cp -a ${configsets}/_default/conf/* ${configsets}/term_search/conf/
+cp -a $ld_config/property_search/* ${configsets}/property_search/conf
+cp -a $ld_config/term_search/* ${configsets}/term_search/conf
+

From 88e8399f990adc240d37a9e4196a5207720fe011 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 1 Nov 2023 11:08:58 -0700
Subject: [PATCH 47/62] fixed ncbo_ontology_archive_old_submissions error
 output

---
 Gemfile.lock                              |  4 ++--
 bin/ncbo_ontology_archive_old_submissions | 20 ++++++++++++--------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 92164456..825ea3a5 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: 911d71aefe433314d11398445e3856fca503b9c1
+  revision: 6db93bb3d5095a5fe0d017e572c5a04caa34ebc6
   branch: develop
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 3ae6bfb56dc59a670b5bc1a513ff4929f8cf3756
+  revision: 067104ae94c0e9d058cfbf419364fbf03f34de43
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
diff --git a/bin/ncbo_ontology_archive_old_submissions b/bin/ncbo_ontology_archive_old_submissions
index 535c129e..1b2268a5 100755
--- a/bin/ncbo_ontology_archive_old_submissions
+++ b/bin/ncbo_ontology_archive_old_submissions
@@ -119,13 +119,17 @@ onts.each do |ont|
   end
 end
 
-msg = JSON.pretty_generate(bad_submissions)
 puts
-puts msg
-logger.error(msg)
-
-msg = "Number of errored submissions: #{bad_submissions.length}"
-puts msg
-logger.error(msg)
-
 
+if bad_submissions.empty?
+  msg = "No errored submissions found"
+  puts msg
+  logger.info(msg)
+else
+  msg = JSON.pretty_generate(bad_submissions)
+  puts msg
+  logger.error(msg)
+  msg = "Number of errored submissions: #{bad_submissions.length}"
+  puts msg
+  logger.error(msg)
+end
\ No newline at end of file

From 33cc9b491e0d1d36064624d028580cb615e34496 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 1 Nov 2023 20:14:26 -0700
Subject: [PATCH 48/62] Gemfile.lock update

---
 Gemfile.lock | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 1927ea82..13bf6b72 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -98,7 +98,7 @@ GEM
     faraday-net_http (3.0.2)
     faraday-retry (2.2.0)
       faraday (~> 2.0)
-    ffi (1.15.5)
+    ffi (1.16.3)
     gapic-common (0.20.0)
       faraday (>= 1.9, < 3.a)
       faraday-retry (>= 1.0, < 3.a)
@@ -119,29 +119,29 @@ GEM
     google-cloud-env (1.6.0)
       faraday (>= 0.17.3, < 3.0)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.24.3)
-    google-protobuf (3.24.3-x86_64-darwin)
-    google-protobuf (3.24.3-x86_64-linux)
+    google-protobuf (3.25.0)
+    google-protobuf (3.25.0-x86_64-darwin)
+    google-protobuf (3.25.0-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.8.0)
+    googleapis-common-protos-types (1.9.0)
       google-protobuf (~> 3.18)
-    googleauth (1.8.0)
+    googleauth (1.8.1)
       faraday (>= 0.17.3, < 3.a)
       jwt (>= 1.4, < 3.0)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.58.0)
-      google-protobuf (~> 3.23)
+    grpc (1.59.2)
+      google-protobuf (~> 3.24)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.58.0-x86_64-darwin)
-      google-protobuf (~> 3.23)
+    grpc (1.59.2-x86_64-darwin)
+      google-protobuf (~> 3.24)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.58.0-x86_64-linux)
-      google-protobuf (~> 3.23)
+    grpc (1.59.2-x86_64-linux)
+      google-protobuf (~> 3.24)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
@@ -163,7 +163,7 @@ GEM
     method_source (1.0.0)
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.0808)
+    mime-types-data (3.2023.1003)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
       redis
@@ -184,12 +184,12 @@ GEM
     rack (3.0.8)
     rack-test (2.1.0)
       rack (>= 1.3)
-    rake (13.0.6)
+    rake (13.1.0)
     rdf (1.0.8)
       addressable (>= 2.2)
-    redis (5.0.7)
-      redis-client (>= 0.9.0)
-    redis-client (0.17.0)
+    redis (5.0.8)
+      redis-client (>= 0.17.0)
+    redis-client (0.18.0)
       connection_pool
     rest-client (2.1.0)
       http-accept (>= 1.7.0, < 2.0)
@@ -264,4 +264,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.4.17
+   2.3.15

From 7429289a0cf9d48c43191ed3bcaa9ce82a20f6d4 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Wed, 1 Nov 2023 20:16:56 -0700
Subject: [PATCH 49/62] Gemfile.lock update

---
 Gemfile.lock | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index e7a782db..9e47a23c 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e33a0e451f8a8226d98291168e45b46d7065e670
+  revision: ff10e5ff4103431da1aec3cbbaebc57547c0035c
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -119,9 +119,9 @@ GEM
     google-cloud-env (1.6.0)
       faraday (>= 0.17.3, < 3.0)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.24.4)
-    google-protobuf (3.24.4-x86_64-darwin)
-    google-protobuf (3.24.4-x86_64-linux)
+    google-protobuf (3.25.0)
+    google-protobuf (3.25.0-x86_64-darwin)
+    google-protobuf (3.25.0-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)

From bb93561f78522cf6b289afc81b3bf86cdbbb8cfc Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 7 Nov 2023 21:31:46 -0800
Subject: [PATCH 50/62] Gemfile update

---
 Gemfile.lock | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index e7a782db..fab55057 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: e33a0e451f8a8226d98291168e45b46d7065e670
+  revision: 9487c7f73e68abab097af523d42c1d2e106e614b
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -76,7 +76,7 @@ GEM
       multi_json (~> 1.0)
     addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
-    base64 (0.1.1)
+    base64 (0.2.0)
     bcrypt (3.1.19)
     builder (3.2.4)
     coderay (1.1.3)
@@ -119,14 +119,14 @@ GEM
     google-cloud-env (1.6.0)
       faraday (>= 0.17.3, < 3.0)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.24.4)
-    google-protobuf (3.24.4-x86_64-darwin)
-    google-protobuf (3.24.4-x86_64-linux)
+    google-protobuf (3.25.0)
+    google-protobuf (3.25.0-x86_64-darwin)
+    google-protobuf (3.25.0-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.9.0)
+    googleapis-common-protos-types (1.10.0)
       google-protobuf (~> 3.18)
     googleauth (1.8.1)
       faraday (>= 0.17.3, < 3.a)
@@ -154,8 +154,8 @@ GEM
     jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
-    libxml-ruby (4.1.1)
-    logger (1.5.3)
+    libxml-ruby (4.1.2)
+    logger (1.6.0)
     macaddr (1.7.2)
       systemu (~> 2.6.5)
     mail (2.6.6)

From a20827249fe225af6f18e9efea5e1097ab28d86b Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 7 Nov 2023 21:46:34 -0800
Subject: [PATCH 51/62] Gemfile update

---
 Gemfile.lock | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 13bf6b72..617eccb3 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,6 +1,6 @@
 GIT
   remote: https://github.com/ncbo/goo.git
-  revision: daea7822af9e5ca1961d6873a758735133a1b2db
+  revision: 657149d6b33813253fa7440252f69c04e0631190
   branch: master
   specs:
     goo (0.0.2)
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 04226ac5840a328e6f906f15c769ee6ee5723102
+  revision: 4f4361e2c181143bba3876326ecda407a587207e
   branch: master
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: a7ad210e846a390f203457be2459719214d142fe
+  revision: 7783784f9d2ceada9be706cf6c084d272ae653e8
   branch: master
   specs:
     ontologies_linked_data (0.0.1)
@@ -76,7 +76,7 @@ GEM
       multi_json (~> 1.0)
     addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
-    base64 (0.1.1)
+    base64 (0.2.0)
     bcrypt (3.1.19)
     builder (3.2.4)
     coderay (1.1.3)
@@ -126,7 +126,7 @@ GEM
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.9.0)
+    googleapis-common-protos-types (1.10.0)
       google-protobuf (~> 3.18)
     googleauth (1.8.1)
       faraday (>= 0.17.3, < 3.a)
@@ -154,8 +154,8 @@ GEM
     jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
-    libxml-ruby (4.1.1)
-    logger (1.5.3)
+    libxml-ruby (4.1.2)
+    logger (1.6.0)
     macaddr (1.7.2)
       systemu (~> 2.6.5)
     mail (2.6.6)

From e8fa020e75bda0ea228089523e26e065d228eb3b Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Tue, 14 Nov 2023 14:13:06 -0800
Subject: [PATCH 52/62] fixes to the analytics script and a new script to
 generate UA analytics for documentation

---
 Gemfile                             |   6 ++
 Gemfile.lock                        |  35 ++++++--
 bin/generate_ua_analytics_file.rb   | 126 ++++++++++++++++++++++++++++
 lib/ncbo_cron/ontology_analytics.rb |  49 ++++++-----
 4 files changed, 190 insertions(+), 26 deletions(-)
 create mode 100755 bin/generate_ua_analytics_file.rb

diff --git a/Gemfile b/Gemfile
index a2c93e43..ea60eb54 100644
--- a/Gemfile
+++ b/Gemfile
@@ -3,6 +3,12 @@ source 'https://rubygems.org'
 gemspec
 
 gem 'ffi'
+
+# This is needed temporarily to pull the Google Universal Analytics (UA)
+# data and store it in a file. See (bin/generate_ua_analytics_file.rb)
+# The ability to pull this data from Google will cease on July 1, 2024
+gem "google-apis-analytics_v3"
+
 gem 'google-analytics-data'
 gem 'mail', '2.6.6'
 gem 'multi_json'
diff --git a/Gemfile.lock b/Gemfile.lock
index 9e47a23c..de996c17 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: 067104ae94c0e9d058cfbf419364fbf03f34de43
+  revision: ebbb7a3c28ecde49c261290bec34ab082490a271
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: ff10e5ff4103431da1aec3cbbaebc57547c0035c
+  revision: 5600020a8017cb4901e719f577032b0be6a14949
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -76,7 +76,7 @@ GEM
       multi_json (~> 1.0)
     addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
-    base64 (0.1.1)
+    base64 (0.2.0)
     bcrypt (3.1.19)
     builder (3.2.4)
     coderay (1.1.3)
@@ -84,6 +84,7 @@ GEM
     connection_pool (2.4.1)
     cube-ruby (0.0.3)
     dante (0.2.0)
+    declarative (0.0.20)
     docile (1.4.0)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
@@ -113,6 +114,17 @@ GEM
     google-analytics-data-v1beta (0.9.0)
       gapic-common (>= 0.20.0, < 2.a)
       google-cloud-errors (~> 1.0)
+    google-apis-analytics_v3 (0.13.0)
+      google-apis-core (>= 0.11.0, < 2.a)
+    google-apis-core (0.11.2)
+      addressable (~> 2.5, >= 2.5.1)
+      googleauth (>= 0.16.2, < 2.a)
+      httpclient (>= 2.8.1, < 3.a)
+      mini_mime (~> 1.0)
+      representable (~> 3.0)
+      retriable (>= 2.0, < 4.a)
+      rexml
+      webrick
     google-cloud-core (1.6.0)
       google-cloud-env (~> 1.0)
       google-cloud-errors (~> 1.0)
@@ -126,7 +138,7 @@ GEM
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.9.0)
+    googleapis-common-protos-types (1.10.0)
       google-protobuf (~> 3.18)
     googleauth (1.8.1)
       faraday (>= 0.17.3, < 3.a)
@@ -147,6 +159,7 @@ GEM
     http-accept (1.7.0)
     http-cookie (1.0.5)
       domain_name (~> 0.5)
+    httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
     json (2.6.3)
@@ -154,8 +167,8 @@ GEM
     jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
-    libxml-ruby (4.1.1)
-    logger (1.5.3)
+    libxml-ruby (4.1.2)
+    logger (1.6.0)
     macaddr (1.7.2)
       systemu (~> 2.6.5)
     mail (2.6.6)
@@ -164,6 +177,7 @@ GEM
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)
     mime-types-data (3.2023.1003)
+    mini_mime (1.1.5)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
       redis
@@ -191,11 +205,16 @@ GEM
       redis-client (>= 0.17.0)
     redis-client (0.18.0)
       connection_pool
+    representable (3.2.0)
+      declarative (< 0.1.0)
+      trailblazer-option (>= 0.1.1, < 0.2.0)
+      uber (< 0.2.0)
     rest-client (2.1.0)
       http-accept (>= 1.7.0, < 2.0)
       http-cookie (>= 1.0.2, < 2.0)
       mime-types (>= 1.16, < 4.0)
       netrc (~> 0.8)
+    retriable (3.1.2)
     rexml (3.2.6)
     rsolr (2.5.0)
       builder (>= 2.1.2)
@@ -224,13 +243,16 @@ GEM
     systemu (2.6.5)
     test-unit-minitest (0.9.1)
       minitest (~> 4.7)
+    trailblazer-option (0.1.2)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
+    uber (0.1.0)
     unf (0.1.4)
       unf_ext
     unf_ext (0.0.8.2)
     uuid (2.3.9)
       macaddr (~> 1.0)
+    webrick (1.8.1)
 
 PLATFORMS
   ruby
@@ -244,6 +266,7 @@ DEPENDENCIES
   ffi
   goo!
   google-analytics-data
+  google-apis-analytics_v3
   mail (= 2.6.6)
   minitest (< 5.0)
   multi_json
diff --git a/bin/generate_ua_analytics_file.rb b/bin/generate_ua_analytics_file.rb
new file mode 100755
index 00000000..0a432a92
--- /dev/null
+++ b/bin/generate_ua_analytics_file.rb
@@ -0,0 +1,126 @@
+require 'logger'
+require 'google/apis/analytics_v3'
+require 'google/api_client/auth/key_utils'
+
+module NcboCron
+  module Models
+
+    class OntologyAnalyticsUA
+
+      def initialize(logger)
+        @logger = logger
+      end
+
+      def run
+        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
+        ontology_analytics = fetch_ontology_analytics
+        File.open(NcboCron.settings.analytics_path_to_ua_data_file, 'w') do |f|
+          f.write(ontology_analytics.to_json)
+        end
+      end
+
+      def fetch_ontology_analytics
+        google_client = authenticate_google
+        aggregated_results = Hash.new
+        start_year = Date.parse(NcboCron.settings.analytics_start_date).year || 2013
+        ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
+        # ont_acronyms = ["NCIT", "ONTOMA", "CMPO", "AEO", "SNOMEDCT"]
+        filter_str = (NcboCron.settings.analytics_filter_str.nil? || NcboCron.settings.analytics_filter_str.empty?) ? "" : ";#{NcboCron.settings.analytics_filter_str}"
+
+        ont_acronyms.each do |acronym|
+          max_results = 10000
+          num_results = 10000
+          start_index = 1
+          results = nil
+
+          loop do
+            results = google_client.get_ga_data(
+              ids          = NcboCron.settings.analytics_profile_id,
+              start_date   = NcboCron.settings.analytics_start_date,
+              end_date     = Date.today.to_s,
+              metrics      = 'ga:pageviews',
+              {
+                dimensions:  'ga:pagePath,ga:year,ga:month',
+                filters:     "ga:pagePath=~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}",
+                start_index: start_index,
+                max_results: max_results
+              }
+            )
+            results.rows ||= []
+            start_index += max_results
+            num_results = results.rows.length
+            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+            @logger.flush
+
+            results.rows.each do |row|
+              if aggregated_results.has_key?(acronym)
+                # year
+                if aggregated_results[acronym].has_key?(row[1].to_i)
+                  # month
+                  if aggregated_results[acronym][row[1].to_i].has_key?(row[2].to_i)
+                    aggregated_results[acronym][row[1].to_i][row[2].to_i] += row[3].to_i
+                  else
+                    aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                  end
+                else
+                  aggregated_results[acronym][row[1].to_i] = Hash.new
+                  aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+                end
+              else
+                aggregated_results[acronym] = Hash.new
+                aggregated_results[acronym][row[1].to_i] = Hash.new
+                aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
+              end
+            end
+
+            if num_results < max_results
+              # fill up non existent years
+              (start_year..Date.today.year).each do |y|
+                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
+                aggregated_results[acronym][y] = Hash.new unless aggregated_results[acronym].has_key?(y)
+              end
+              # fill up non existent months with zeros
+              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n] = 0 unless v.has_key?(n) } }
+              break
+            end
+          end
+        end
+
+        @logger.info "Completed Universal Analytics pull..."
+        @logger.flush
+
+        aggregated_results
+      end
+
+      def authenticate_google
+        Google::Apis::ClientOptions.default.application_name = NcboCron.settings.analytics_app_name
+        Google::Apis::ClientOptions.default.application_version = NcboCron.settings.analytics_app_version
+        # enable google api call retries in order to
+        # minigate analytics processing failure due to occasional google api timeouts and other outages
+        Google::Apis::RequestOptions.default.retries = 5
+        # uncoment to enable logging for debugging purposes
+        # Google::Apis.logger.level = Logger::DEBUG
+        # Google::Apis.logger = @logger
+        client = Google::Apis::AnalyticsV3::AnalyticsService.new
+        key = Google::APIClient::KeyUtils::load_from_pkcs12(NcboCron.settings.analytics_path_to_ua_key_file, 'notasecret')
+        client.authorization = Signet::OAuth2::Client.new(
+          :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
+          :audience             => 'https://accounts.google.com/o/oauth2/token',
+          :scope                => 'https://www.googleapis.com/auth/analytics.readonly',
+          :issuer               => NcboCron.settings.analytics_service_account_email_address,
+          :signing_key          => key
+        ).tap { |auth| auth.fetch_access_token! }
+        client
+      end
+    end
+  end
+end
+
+require 'ontologies_linked_data'
+require 'goo'
+require 'ncbo_annotator'
+require 'ncbo_cron/config'
+require_relative '../config/config'
+ontology_analytics_log_path = File.join("logs", "ontology-analytics-ua.log")
+ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
+NcboCron::Models::OntologyAnalyticsUA.new(ontology_analytics_logger).run
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
index 3a91b813..c5a4de00 100644
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ b/lib/ncbo_cron/ontology_analytics.rb
@@ -38,7 +38,6 @@ def fetch_ontology_analytics
           @logger.flush
           ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
           # ont_acronyms = ["NCIT", "SNOMEDCT", "MEDDRA"]
-
           @logger.info "Authenticating with the Google Analytics Endpoint..."
           @logger.flush
           google_client = authenticate_google
@@ -137,39 +136,49 @@ def fetch_ontology_analytics
               break if num_results < max_results
             end # loop
           end # ont_acronyms
-          @logger.info "Refresh complete, merging GA4 and UA data..."
-          @logger.flush
-          full_data = merge_ga4_ua_data(aggregated_results)
-          @logger.info "Merged"
+          @logger.info "Refresh complete"
           @logger.flush
+          full_data = merge_and_fill_missing_data(aggregated_results)
         end # Benchmark.realtime
         @logger.info "Completed Google Analytics refresh in #{(time/60).round(1)} minutes."
         @logger.flush
         full_data
       end
 
-      def merge_ga4_ua_data(ga4_data)
-        ua_data_file = File.read(NcboCron.settings.analytics_path_to_ua_data_file)
-        ua_data = JSON.parse(ua_data_file)
-        ua_ga4_intersecting_year = Date.parse(GA4_START_DATE).year.to_s
-        ua_ga4_intersecting_month = Date.parse(GA4_START_DATE).month.to_s
-
-        # add up hits for June of 2023 (the only intersecting month between UA and GA4)
-        ua_data.each do |acronym, _|
-          if ga4_data.has_key?(acronym)
-            if ga4_data[acronym][ua_ga4_intersecting_year].has_key?(ua_ga4_intersecting_month)
-              ua_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month] +=
-                  ga4_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month]
-              # delete data for June of 2023 from ga4_data to avoid overwriting when merging
-              ga4_data[acronym][ua_ga4_intersecting_year].delete(ua_ga4_intersecting_month)
+      def merge_and_fill_missing_data(ga4_data)
+        ua_data = {}
+
+        if File.exists?(NcboCron.settings.analytics_path_to_ua_data_file) &&
+            !File.zero?(NcboCron.settings.analytics_path_to_ua_data_file)
+          @logger.info "Merging GA4 and UA data..."
+          @logger.flush
+          ua_data_file = File.read(NcboCron.settings.analytics_path_to_ua_data_file)
+          ua_data = JSON.parse(ua_data_file)
+          ua_ga4_intersecting_year = Date.parse(GA4_START_DATE).year.to_s
+          ua_ga4_intersecting_month = Date.parse(GA4_START_DATE).month.to_s
+
+          # add up hits for June of 2023 (the only intersecting month between UA and GA4)
+          ua_data.each do |acronym, _|
+            if ga4_data.has_key?(acronym)
+              if ga4_data[acronym][ua_ga4_intersecting_year].has_key?(ua_ga4_intersecting_month)
+                ua_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month] +=
+                    ga4_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month]
+                # delete data for June of 2023 from ga4_data to avoid overwriting when merging
+                ga4_data[acronym][ua_ga4_intersecting_year].delete(ua_ga4_intersecting_month)
+              end
             end
           end
         end
+
         # merge ua and ga4 data
         merged_data = ua_data.deep_merge(ga4_data)
         # fill missing years and months
+        @logger.info "Filling in missing years data..."
+        @logger.flush
         fill_missing_data(merged_data)
         # sort acronyms, years and months
+        @logger.info "Sorting final data..."
+        @logger.flush
         sort_ga_data(merged_data)
       end
 
@@ -221,4 +230,4 @@ def deep_merge(second)
 # # ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
 # ontology_analytics_logger = Logger.new(STDOUT)
 # NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
-# # ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'
+# ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'

From c2a72dbc223cd003c0cbc96f3fb2d910b7b0f57a Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Sun, 10 Dec 2023 09:23:35 -0800
Subject: [PATCH 53/62] Gemfile.lock update

---
 Gemfile.lock | 72 ++++++++++++++++++++++++++++------------------------
 1 file changed, 39 insertions(+), 33 deletions(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 74482dd3..8ca29047 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: ebbb7a3c28ecde49c261290bec34ab082490a271
+  revision: 067104ae94c0e9d058cfbf419364fbf03f34de43
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 5600020a8017cb4901e719f577032b0be6a14949
+  revision: 9487c7f73e68abab097af523d42c1d2e106e614b
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -71,13 +71,17 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (3.2.22.5)
-      i18n (~> 0.6, >= 0.6.4)
-      multi_json (~> 1.0)
-    addressable (2.8.5)
+    activesupport (4.0.13)
+      i18n (~> 0.6, >= 0.6.9)
+      minitest (~> 4.2)
+      multi_json (~> 1.3)
+      thread_safe (~> 0.1)
+      tzinfo (~> 0.3.37)
+    addressable (2.8.6)
       public_suffix (>= 2.0.2, < 6.0)
     base64 (0.2.0)
-    bcrypt (3.1.19)
+    bcrypt (3.1.20)
+    bigdecimal (3.1.4)
     builder (3.2.4)
     coderay (1.1.3)
     concurrent-ruby (1.2.2)
@@ -91,7 +95,7 @@ GEM
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (2.7.11)
+    faraday (2.7.12)
       base64
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
@@ -124,35 +128,36 @@ GEM
       retriable (>= 2.0, < 4.a)
       rexml
       webrick
-    google-cloud-core (1.6.0)
-      google-cloud-env (~> 1.0)
+    google-cloud-core (1.6.1)
+      google-cloud-env (>= 1.0, < 3.a)
       google-cloud-errors (~> 1.0)
-    google-cloud-env (1.6.0)
-      faraday (>= 0.17.3, < 3.0)
+    google-cloud-env (2.0.1)
+      faraday (>= 1.0, < 3.a)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.25.0)
-    google-protobuf (3.25.0-x86_64-darwin)
-    google-protobuf (3.25.0-x86_64-linux)
+    google-protobuf (3.25.1)
+    google-protobuf (3.25.1-x86_64-darwin)
+    google-protobuf (3.25.1-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.10.0)
+    googleapis-common-protos-types (1.11.0)
       google-protobuf (~> 3.18)
-    googleauth (1.8.1)
-      faraday (>= 0.17.3, < 3.a)
+    googleauth (1.9.0)
+      faraday (>= 1.0, < 3.a)
+      google-cloud-env (~> 2.0, >= 2.0.1)
       jwt (>= 1.4, < 3.0)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.59.2)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.59.2-x86_64-darwin)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0-x86_64-darwin)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.59.2-x86_64-linux)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0-x86_64-linux)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
@@ -161,8 +166,8 @@ GEM
     httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
-    json (2.6.3)
-    json_pure (2.6.3)
+    json (2.7.1)
+    json_pure (2.7.1)
     jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
@@ -175,7 +180,7 @@ GEM
     method_source (1.0.0)
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.1003)
+    mime-types-data (3.2023.1205)
     mini_mime (1.1.5)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
@@ -183,7 +188,8 @@ GEM
     multi_json (1.15.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
-    oj (3.16.1)
+    oj (3.16.2)
+      bigdecimal (~> 3.1)
     omni_logger (0.1.4)
       logger
     os (1.1.4)
@@ -193,7 +199,7 @@ GEM
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    public_suffix (5.0.3)
+    public_suffix (5.0.4)
     rack (3.0.8)
     rack-test (2.1.0)
       rack (>= 1.3)
@@ -202,7 +208,7 @@ GEM
       addressable (>= 2.2)
     redis (5.0.8)
       redis-client (>= 0.17.0)
-    redis-client (0.18.0)
+    redis-client (0.19.0)
       connection_pool
     representable (3.2.0)
       declarative (< 0.1.0)
@@ -242,9 +248,9 @@ GEM
     systemu (2.6.5)
     test-unit-minitest (0.9.1)
       minitest (~> 4.7)
+    thread_safe (0.3.6)
     trailblazer-option (0.1.2)
-    tzinfo (2.0.6)
-      concurrent-ruby (~> 1.0)
+    tzinfo (0.3.62)
     uber (0.1.0)
     uuid (2.3.9)
       macaddr (~> 1.0)
@@ -283,4 +289,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.4.22

From ab43cdc82e49e145a759269c7b74d8d61b213176 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Sun, 10 Dec 2023 12:18:32 -0800
Subject: [PATCH 54/62] Gemfile.lock update

---
 Gemfile.lock | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Gemfile.lock b/Gemfile.lock
index 8ca29047..511c10a4 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 9487c7f73e68abab097af523d42c1d2e106e614b
+  revision: 809c54f56b1a4d30d8c2d49e9c005f07c2d6c596
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)

From a659415dd42c0593394aa26982751eb88ad828c7 Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Sat, 16 Dec 2023 17:39:14 -0800
Subject: [PATCH 55/62] implemented the first pass at bmir-radx/radx-project#37

---
 Gemfile.lock                                |  57 +++---
 bin/ncbo_ontology_pull                      |   2 +-
 lib/ncbo_cron/ontology_helper.rb            | 185 ++++++++++++++++++++
 lib/ncbo_cron/ontology_pull.rb              | 147 +---------------
 lib/ncbo_cron/ontology_rank.rb              |   7 +-
 lib/ncbo_cron/ontology_submission_parser.rb |  51 +++---
 test/test_case.rb                           |   6 +-
 test/test_ontology_pull.rb                  |  31 +++-
 8 files changed, 277 insertions(+), 209 deletions(-)
 create mode 100644 lib/ncbo_cron/ontology_helper.rb

diff --git a/Gemfile.lock b/Gemfile.lock
index 74482dd3..ed375af7 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -15,7 +15,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ncbo_annotator.git
-  revision: ebbb7a3c28ecde49c261290bec34ab082490a271
+  revision: d7ee80860a0eab9293af81083a0700d099c50263
   branch: develop
   specs:
     ncbo_annotator (0.0.1)
@@ -26,7 +26,7 @@ GIT
 
 GIT
   remote: https://github.com/ncbo/ontologies_linked_data.git
-  revision: 5600020a8017cb4901e719f577032b0be6a14949
+  revision: 9487c7f73e68abab097af523d42c1d2e106e614b
   branch: develop
   specs:
     ontologies_linked_data (0.0.1)
@@ -74,10 +74,11 @@ GEM
     activesupport (3.2.22.5)
       i18n (~> 0.6, >= 0.6.4)
       multi_json (~> 1.0)
-    addressable (2.8.5)
+    addressable (2.8.6)
       public_suffix (>= 2.0.2, < 6.0)
     base64 (0.2.0)
-    bcrypt (3.1.19)
+    bcrypt (3.1.20)
+    bigdecimal (3.1.4)
     builder (3.2.4)
     coderay (1.1.3)
     concurrent-ruby (1.2.2)
@@ -91,7 +92,7 @@ GEM
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (2.7.11)
+    faraday (2.7.12)
       base64
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
@@ -124,35 +125,36 @@ GEM
       retriable (>= 2.0, < 4.a)
       rexml
       webrick
-    google-cloud-core (1.6.0)
-      google-cloud-env (~> 1.0)
+    google-cloud-core (1.6.1)
+      google-cloud-env (>= 1.0, < 3.a)
       google-cloud-errors (~> 1.0)
-    google-cloud-env (1.6.0)
-      faraday (>= 0.17.3, < 3.0)
+    google-cloud-env (2.1.0)
+      faraday (>= 1.0, < 3.a)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.25.0)
-    google-protobuf (3.25.0-x86_64-darwin)
-    google-protobuf (3.25.0-x86_64-linux)
+    google-protobuf (3.25.1)
+    google-protobuf (3.25.1-x86_64-darwin)
+    google-protobuf (3.25.1-x86_64-linux)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.10.0)
+    googleapis-common-protos-types (1.11.0)
       google-protobuf (~> 3.18)
-    googleauth (1.8.1)
-      faraday (>= 0.17.3, < 3.a)
+    googleauth (1.9.1)
+      faraday (>= 1.0, < 3.a)
+      google-cloud-env (~> 2.1)
       jwt (>= 1.4, < 3.0)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.59.2)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.59.2-x86_64-darwin)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0-x86_64-darwin)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
-    grpc (1.59.2-x86_64-linux)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0-x86_64-linux)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
@@ -161,8 +163,8 @@ GEM
     httpclient (2.8.3)
     i18n (0.9.5)
       concurrent-ruby (~> 1.0)
-    json (2.6.3)
-    json_pure (2.6.3)
+    json (2.7.1)
+    json_pure (2.7.1)
     jwt (2.7.1)
     launchy (2.5.2)
       addressable (~> 2.8)
@@ -175,7 +177,7 @@ GEM
     method_source (1.0.0)
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.1003)
+    mime-types-data (3.2023.1205)
     mini_mime (1.1.5)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
@@ -183,7 +185,8 @@ GEM
     multi_json (1.15.0)
     net-http-persistent (2.9.4)
     netrc (0.11.0)
-    oj (3.16.1)
+    oj (3.16.3)
+      bigdecimal (>= 3.0)
     omni_logger (0.1.4)
       logger
     os (1.1.4)
@@ -193,7 +196,7 @@ GEM
     pry (0.14.2)
       coderay (~> 1.1)
       method_source (~> 1.0)
-    public_suffix (5.0.3)
+    public_suffix (5.0.4)
     rack (3.0.8)
     rack-test (2.1.0)
       rack (>= 1.3)
@@ -202,7 +205,7 @@ GEM
       addressable (>= 2.2)
     redis (5.0.8)
       redis-client (>= 0.17.0)
-    redis-client (0.18.0)
+    redis-client (0.19.0)
       connection_pool
     representable (3.2.0)
       declarative (< 0.1.0)
diff --git a/bin/ncbo_ontology_pull b/bin/ncbo_ontology_pull
index a017e4d7..be3e08de 100755
--- a/bin/ncbo_ontology_pull
+++ b/bin/ncbo_ontology_pull
@@ -32,7 +32,7 @@ logger = Logger.new($stdout)
 logger.info "Starting ncbo pull"; logger.flush
 puller = NcboCron::Models::OntologyPull.new
 begin
-  puller.do_ontology_pull(ontology_acronym, logger: logger , enable_pull_umls:true )
+  puller.do_ontology_pull(ontology_acronym, logger: logger, enable_pull_umls: true)
 rescue StandardError => e
   logger.error e.message
   logger.flush
diff --git a/lib/ncbo_cron/ontology_helper.rb b/lib/ncbo_cron/ontology_helper.rb
new file mode 100644
index 00000000..42534768
--- /dev/null
+++ b/lib/ncbo_cron/ontology_helper.rb
@@ -0,0 +1,185 @@
+require 'logger'
+
+module NcboCron
+  module Helpers
+    module OntologyHelper
+
+      REDIS_SUBMISSION_ID_PREFIX = "sub:"
+      PROCESS_QUEUE_HOLDER = "parseQueue"
+      PROCESS_ACTIONS = {
+        :process_rdf => true,
+        :generate_labels => true,
+        :index_search => true,
+        :index_properties => true,
+        :run_metrics => true,
+        :process_annotator => true,
+        :diff => true,
+        :remote_pull => false
+      }
+
+      class RemoteFileException < StandardError
+        attr_reader :submission
+
+        def initialize(submission)
+          super
+          @submission = submission
+        end
+      end
+
+      def self.do_ontology_pull(ontology_acronym, enable_pull_umls = false, umls_download_url = '', logger = nil,
+                                add_to_queue = true)
+        logger ||= Logger.new($stdout)
+        ont = LinkedData::Models::Ontology.find(ontology_acronym).include(:acronym).first
+        new_submission = nil
+        raise StandardError, "Ontology #{ontology_acronym} not found" if ont.nil?
+
+        last = ont.latest_submission(status: :any)
+        raise StandardError, "No submission found for #{ontology_acronym}" if last.nil?
+
+        last.bring(:hasOntologyLanguage) if last.bring?(:hasOntologyLanguage)
+        if !enable_pull_umls && last.hasOntologyLanguage.umls?
+          raise StandardError, "Pull umls not enabled"
+        end
+
+        last.bring(:pullLocation) if last.bring?(:pullLocation)
+        raise StandardError, "#{ontology_acronym} has no pullLocation" if last.pullLocation.nil?
+
+        last.bring(:uploadFilePath) if last.bring?(:uploadFilePath)
+
+        if last.hasOntologyLanguage.umls? && umls_download_url && !umls_download_url.empty?
+          last.pullLocation = RDF::URI.new(umls_download_url + last.pullLocation.split("/")[-1])
+          logger.info("Using alternative download for umls #{last.pullLocation.to_s}")
+          logger.flush
+        end
+
+        if last.remote_file_exists?(last.pullLocation.to_s)
+          logger.info "Checking download for #{ont.acronym}"
+          logger.info "Location: #{last.pullLocation.to_s}"; logger.flush
+          file, filename = last.download_ontology_file
+          file, md5local, md5remote, new_file_exists = self.new_file_exists?(file, last)
+
+          if new_file_exists
+            logger.info "New file found for #{ont.acronym}\nold: #{md5local}\nnew: #{md5remote}"
+            logger.flush()
+            new_submission = self.create_submission(ont, last, file, filename, logger, add_to_queue)
+          else
+            logger.info "There is no new file found for #{ont.acronym}"
+            logger.flush()
+          end
+
+          file.close
+          new_submission
+        else
+          raise self::RemoteFileException.new(last)
+        end
+      end
+
+      def self.create_submission(ont, sub, file, filename, logger = nil, add_to_queue = true, new_version = nil,
+                                 new_released = nil)
+        logger ||= Kernel.const_defined?("LOGGER") ? Kernel.const_get("LOGGER") : Logger.new(STDOUT)
+        new_sub = LinkedData::Models::OntologySubmission.new
+
+        sub.bring_remaining
+        sub.loaded_attributes.each do |attr|
+          new_sub.send("#{attr}=", sub.send(attr))
+        end
+
+        submission_id = ont.next_submission_id()
+        new_sub.submissionId = submission_id
+        file_location = LinkedData::Models::OntologySubmission.copy_file_repository(ont.acronym, submission_id, file, filename)
+        new_sub.uploadFilePath = file_location
+
+        unless new_version.nil?
+          new_sub.version = new_version
+        end
+
+        if new_released.nil?
+          new_sub.released = DateTime.now
+        else
+          new_sub.released = DateTime.parse(new_released)
+        end
+        new_sub.submissionStatus = nil
+        new_sub.creationDate = nil
+        new_sub.missingImports = nil
+        new_sub.metrics = nil
+        full_file_path = File.expand_path(file_location)
+
+        # check if OWLAPI is able to parse the file before creating a new submission
+        owlapi = LinkedData::Parser::OWLAPICommand.new(
+          full_file_path,
+          File.expand_path(new_sub.data_folder.to_s),
+          logger: logger)
+        owlapi.disable_reasoner
+        parsable = true
+
+        begin
+          owlapi.parse
+        rescue Exception => e
+          logger.error("The new file for ontology #{ont.acronym}, submission id: #{submission_id} did not clear OWLAPI: #{e.class}: #{e.message}\n#{e.backtrace.join("\n\t")}")
+          logger.error("A new submission has NOT been created.")
+          logger.flush
+          parsable = false
+        end
+
+        if parsable
+          if new_sub.valid?
+            new_sub.save()
+
+            if add_to_queue
+              self.queue_submission(new_sub, { all: true })
+              logger.info("OntologyPull created a new submission (#{submission_id}) for ontology #{ont.acronym}")
+            end
+          else
+            logger.error("Unable to create a new submission for ontology #{ont.acronym} with id #{submission_id}: #{new_sub.errors}")
+            logger.flush
+          end
+        else
+          # delete the bad file
+          File.delete full_file_path if File.exist? full_file_path
+        end
+        new_sub
+      end
+
+      def self.queue_submission(submission, actions={:all => true})
+        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
+
+        if actions[:all]
+          actions = PROCESS_ACTIONS.dup
+        else
+          actions.delete_if {|k, v| !PROCESS_ACTIONS.has_key?(k)}
+        end
+        actionStr = MultiJson.dump(actions)
+        redis.hset(PROCESS_QUEUE_HOLDER, get_prefixed_id(submission.id), actionStr) unless actions.empty?
+      end
+
+      def self.get_prefixed_id(id)
+        "#{REDIS_SUBMISSION_ID_PREFIX}#{id}"
+      end
+
+      def self.last_fragment_of_uri(uri)
+        uri.to_s.split("/")[-1]
+      end
+
+      def self.acronym_from_submission_id(submissionID)
+        submissionID.to_s.split("/")[-3]
+      end
+
+      def self.new_file_exists?(file, last)
+        file = File.open(file.path, "rb")
+        remote_contents = file.read
+        md5remote = Digest::MD5.hexdigest(remote_contents)
+
+        if last.uploadFilePath && File.exist?(last.uploadFilePath)
+          file_contents = open(last.uploadFilePath) { |f| f.read }
+          md5local = Digest::MD5.hexdigest(file_contents)
+          new_file_exists = (not md5remote.eql?(md5local))
+        else
+          # There is no existing file, so let's create a submission with the downloaded one
+          new_file_exists = true
+        end
+        return file, md5local, md5remote, new_file_exists
+      end
+
+    end
+  end
+end
\ No newline at end of file
diff --git a/lib/ncbo_cron/ontology_pull.rb b/lib/ncbo_cron/ontology_pull.rb
index 7aa9fc23..c554c95e 100644
--- a/lib/ncbo_cron/ontology_pull.rb
+++ b/lib/ncbo_cron/ontology_pull.rb
@@ -1,22 +1,11 @@
-require 'open-uri'
 require 'logger'
-require_relative 'ontology_submission_parser'
+require_relative 'ontology_helper'
 
 module NcboCron
   module Models
 
     class OntologyPull
 
-      class RemoteFileException < StandardError
-        attr_reader :submission
-
-        def initialize(submission)
-          super
-          @submission = submission
-        end
-      end
-
-
       def do_remote_ontology_pull(options = {})
         logger = options[:logger] || Logger.new($stdout)
         logger.info "UMLS auto-pull #{options[:enable_pull_umls] == true}"
@@ -33,11 +22,11 @@ def do_remote_ontology_pull(options = {})
         ontologies.each do |ont|
           begin
             begin
-              new_submissions << self.do_ontology_pull(ont.acronym,
+              new_submissions << NcboCron::Helpers::OntologyHelper.do_ontology_pull(ont.acronym,
                                                        enable_pull_umls: enable_pull_umls,
                                                        umls_download_url: umls_download_url,
-                                                       logger: logger)
-            rescue RemoteFileException => error
+                                                       logger: logger, add_to_queue: true)
+            rescue NcboCron::Helpers::OntologyHelper::RemoteFileException => error
               logger.info "RemoteFileException: No submission file at pull location #{error.submission.pullLocation.to_s} for ontology #{ont.acronym}."
               logger.flush
               LinkedData::Utils::Notifications.remote_ontology_pull(error.submission)
@@ -58,136 +47,8 @@ def do_remote_ontology_pull(options = {})
         new_submissions
       end
 
-      def do_ontology_pull(ontology_acronym, enable_pull_umls: false, umls_download_url: '', logger: nil)
-        ont = LinkedData::Models::Ontology.find(ontology_acronym).include(:acronym).first
-        new_submission = nil
-        raise StandardError, "Ontology #{ontology_acronym} not found" if ont.nil?
-
-        last = ont.latest_submission(status: :any)
-        raise StandardError, "No submission found for #{ontology_acronym}" if last.nil?
-
-        last.bring(:hasOntologyLanguage) if last.bring?(:hasOntologyLanguage)
-        if !enable_pull_umls && last.hasOntologyLanguage.umls?
-          raise StandardError, "Pull umls not enabled"
-        end
-
-        last.bring(:pullLocation) if last.bring?(:pullLocation)
-        raise StandardError, "#{ontology_acronym} has no pullLocation" if last.pullLocation.nil?
-
-        last.bring(:uploadFilePath) if last.bring?(:uploadFilePath)
-
-        if last.hasOntologyLanguage.umls? && umls_download_url
-          last.pullLocation = RDF::URI.new(umls_download_url + last.pullLocation.split("/")[-1])
-          logger.info("Using alternative download for umls #{last.pullLocation.to_s}")
-          logger.flush
-        end
-
-        if last.remote_file_exists?(last.pullLocation.to_s)
-          logger.info "Checking download for #{ont.acronym}"
-          logger.info "Location: #{last.pullLocation.to_s}"; logger.flush
-          file, filename = last.download_ontology_file
-          file, md5local, md5remote, new_file_exists = new_file_exists?(file, last)
-
-          if new_file_exists
-            logger.info "New file found for #{ont.acronym}\nold: #{md5local}\nnew: #{md5remote}"
-            logger.flush()
-            new_submission = create_submission(ont, last, file, filename, logger)
-          else
-            logger.info "There is no new file found for #{ont.acronym}"
-            logger.flush()
-          end
-
-          file.close
-          new_submission
-        else
-          raise RemoteFileException.new(last)
-        end
-      end
-
-      def create_submission(ont, sub, file, filename, logger = nil,
-                            add_to_pull = true, new_version = nil, new_released = nil)
-        logger ||= Kernel.const_defined?("LOGGER") ? Kernel.const_get("LOGGER") : Logger.new(STDOUT)
-        new_sub = LinkedData::Models::OntologySubmission.new
-
-        sub.bring_remaining
-        sub.loaded_attributes.each do |attr|
-          new_sub.send("#{attr}=", sub.send(attr))
-        end
-
-        submission_id = ont.next_submission_id()
-        new_sub.submissionId = submission_id
-        file_location = LinkedData::Models::OntologySubmission.copy_file_repository(ont.acronym, submission_id, file, filename)
-        new_sub.uploadFilePath = file_location
-        unless new_version.nil?
-          new_sub.version = new_version
-        end
-        if new_released.nil?
-          new_sub.released = DateTime.now
-        else
-          new_sub.released = DateTime.parse(new_released)
-        end
-        new_sub.submissionStatus = nil
-        new_sub.creationDate = nil
-        new_sub.missingImports = nil
-        new_sub.metrics = nil
-        full_file_path = File.expand_path(file_location)
-
-        # check if OWLAPI is able to parse the file before creating a new submission
-        owlapi = LinkedData::Parser::OWLAPICommand.new(
-          full_file_path,
-          File.expand_path(new_sub.data_folder.to_s),
-          logger: logger)
-        owlapi.disable_reasoner
-        parsable = true
-
-        begin
-          owlapi.parse
-        rescue Exception => e
-          logger.error("The new file for ontology #{ont.acronym}, submission id: #{submission_id} did not clear OWLAPI: #{e.class}: #{e.message}\n#{e.backtrace.join("\n\t")}")
-          logger.error("A new submission has NOT been created.")
-          logger.flush
-          parsable = false
-        end
-
-        if parsable
-          if new_sub.valid?
-            new_sub.save()
-
-            if add_to_pull
-              submission_queue = NcboCron::Models::OntologySubmissionParser.new
-              submission_queue.queue_submission(new_sub, { all: true })
-              logger.info("OntologyPull created a new submission (#{submission_id}) for ontology #{ont.acronym}")
-            end
-          else
-            logger.error("Unable to create a new submission in OntologyPull: #{new_sub.errors}")
-            logger.flush
-          end
-        else
-          # delete the bad file
-          File.delete full_file_path if File.exist? full_file_path
-        end
-        new_sub
-      end
-
-
       private
 
-      def new_file_exists?(file, last)
-        file = File.open(file.path, "rb")
-        remote_contents = file.read
-        md5remote = Digest::MD5.hexdigest(remote_contents)
-
-        if last.uploadFilePath && File.exist?(last.uploadFilePath)
-          file_contents = open(last.uploadFilePath) { |f| f.read }
-          md5local = Digest::MD5.hexdigest(file_contents)
-          new_file_exists = (not md5remote.eql?(md5local))
-        else
-          # There is no existing file, so let's create a submission with the downloaded one
-          new_file_exists = true
-        end
-        return file, md5local, md5remote, new_file_exists
-      end
-
       def redis_goo
         Redis.new(host: LinkedData.settings.goo_redis_host, port: LinkedData.settings.goo_redis_port, timeout: 30)
       end
diff --git a/lib/ncbo_cron/ontology_rank.rb b/lib/ncbo_cron/ontology_rank.rb
index b60c2740..64de8844 100644
--- a/lib/ncbo_cron/ontology_rank.rb
+++ b/lib/ncbo_cron/ontology_rank.rb
@@ -1,5 +1,6 @@
 require 'logger'
 require 'benchmark'
+require_relative 'ontology_helper'
 
 module NcboCron
   module Models
@@ -66,7 +67,7 @@ def umls_scores(ontologies)
 
         ontologies.each do |ont|
           if ont.group && !ont.group.empty?
-            umls_gr = ont.group.select {|gr| acronym_from_id(gr.id.to_s).include?('UMLS')}
+            umls_gr = ont.group.select {|gr| NcboCron::Helpers::OntologyHelper.last_fragment_of_uri(gr.id.to_s).include?('UMLS')}
             scores[ont.acronym] = umls_gr.empty? ? 0 : 1
           else
             scores[ont.acronym] = 0
@@ -75,10 +76,6 @@ def umls_scores(ontologies)
         scores
       end
 
-      def acronym_from_id(id)
-        id.to_s.split("/")[-1]
-      end
-
       def normalize(x, xmin, xmax, ymin, ymax)
         xrange = xmax - xmin
         yrange = ymax - ymin
diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index 34c53930..f493eced 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -1,39 +1,22 @@
 require 'multi_json'
+require_relative 'ontology_helper'
 
 module NcboCron
   module Models
 
     class OntologySubmissionParser
 
-      QUEUE_HOLDER = "parseQueue"
-      IDPREFIX = "sub:"
-
-      ACTIONS = {
-        :process_rdf => true,
-        :generate_labels => true,
-        :index_search => true,
-        :index_properties => true,
-        :run_metrics => true,
-        :process_annotator => true,
-        :diff => true
-      }
+      QUEUE_HOLDER = NcboCron::Helpers::OntologyHelper::PROCESS_QUEUE_HOLDER
+      ACTIONS = NcboCron::Helpers::OntologyHelper::PROCESS_ACTIONS
 
       def initialize()
       end
 
-      def queue_submission(submission, actions={:all => true})
-        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
-
-        if actions[:all]
-          actions = ACTIONS.dup
-        else
-          actions.delete_if {|k, v| !ACTIONS.has_key?(k)}
-        end
-        actionStr = MultiJson.dump(actions)
-        redis.hset(QUEUE_HOLDER, get_prefixed_id(submission.id), actionStr) unless actions.empty?
+      def queue_submission(submission, actions={ :all => true })
+        NcboCron::Helpers::OntologyHelper.queue_submission(submission, actions)
       end
 
-      def process_queue_submissions(options = {})
+      def process_queue_submissions(options={})
         logger = options[:logger]
         logger ||= Kernel.const_defined?("LOGGER") ? Kernel.const_get("LOGGER") : Logger.new(STDOUT)
         redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
@@ -44,6 +27,18 @@ def process_queue_submissions(options = {})
           realKey = process_data[:key]
           key = process_data[:redis_key]
           redis.hdel(QUEUE_HOLDER, key)
+
+          # if :remote_pull is one of the actions, pull the ontology and halt if no new submission is found
+          if actions.key?(:remote_pull) && actions[:remote_pull]
+            acronym = NcboCron::Helpers::OntologyHelper.acronym_from_submission_id(realKey)
+            new_submission = NcboCron::Helpers::OntologyHelper.do_ontology_pull(acronym, enable_pull_umls: false,
+                                                                                umls_download_url: '', logger: logger,
+                                                                                add_to_queue: false)
+            return unless new_submission
+            realKey = new_submission.id.to_s
+            actions.delete(:remote_pull)
+          end
+
           begin
             process_submission(logger, realKey, actions)
           rescue Exception => e
@@ -56,7 +51,7 @@ def process_queue_submissions(options = {})
       def queued_items(redis, logger=nil)
         logger ||= Kernel.const_defined?("LOGGER") ? Kernel.const_get("LOGGER") : Logger.new(STDOUT)
         all = redis.hgetall(QUEUE_HOLDER)
-        prefix_remove = Regexp.new(/^#{IDPREFIX}/)
+        prefix_remove = Regexp.new(/^#{NcboCron::Helpers::OntologyHelper::REDIS_SUBMISSION_ID_PREFIX}/)
         items = []
         all.each do |key, val|
           begin
@@ -76,10 +71,6 @@ def queued_items(redis, logger=nil)
         items
       end
 
-      def get_prefixed_id(id)
-        "#{IDPREFIX}#{id}"
-      end
-
       def zombie_classes_graphs
         query = "SELECT DISTINCT ?g WHERE { GRAPH ?g { ?s ?p ?o }}"
         class_graphs = []
@@ -191,6 +182,10 @@ def process_submission(logger, submission_id, actions=ACTIONS)
         end
       end
 
+      def get_prefixed_id(id)
+        NcboCron::Helpers::OntologyHelper.get_prefixed_id(id)
+      end
+
       private
 
       def archive_old_submissions(logger, sub)
diff --git a/test/test_case.rb b/test/test_case.rb
index 5f164ecd..75bb0454 100644
--- a/test/test_case.rb
+++ b/test/test_case.rb
@@ -56,7 +56,7 @@ def count_pattern(pattern)
     return 0
   end
 
-  def backend_4s_delete
+  def backend_triplestore_delete
     raise StandardError, 'Too many triples in KB, does not seem right to run tests' unless
           count_pattern('?s ?p ?o') < 400000
 
@@ -89,7 +89,7 @@ def _run_suites(suites, type)
   end
 
   def _run_suite(suite, type)
-    backend_4s_delete
+    backend_triplestore_delete
     suite.before_suite if suite.respond_to?(:before_suite)
     super(suite, type)
   rescue Exception => e
@@ -98,7 +98,7 @@ def _run_suite(suite, type)
     puts 'Traced from:'
     raise e
   ensure
-    backend_4s_delete
+    backend_triplestore_delete
     suite.after_suite if suite.respond_to?(:after_suite)
   end
 end
diff --git a/test/test_ontology_pull.rb b/test/test_ontology_pull.rb
index 74923677..ca3c6130 100644
--- a/test/test_ontology_pull.rb
+++ b/test/test_ontology_pull.rb
@@ -76,6 +76,32 @@ def test_remote_ontology_pull
     assert_equal 2, ont.submissions.length
   end
 
+  def test_remote_pull_parsing_action
+    ontologies = init_ontologies(1, process_submissions: true)
+    ont = LinkedData::Models::Ontology.find(ontologies[0].id).first
+    ont.bring(:submissions) if ont.bring?(:submissions)
+    assert_equal 1, ont.submissions.length
+
+    # add this ontology to submission queue with :remote_pull action enabled
+    parser = NcboCron::Models::OntologySubmissionParser.new
+    actions = NcboCron::Models::OntologySubmissionParser::ACTIONS.dup
+    actions[:remote_pull] = true
+    parser.queue_submission(ont.submissions[0], actions)
+    parser.process_queue_submissions
+
+    # make sure there are now 2 submissions present
+    ont = LinkedData::Models::Ontology.find(ontologies[0].id).first
+    ont.bring(:submissions) if ont.bring?(:submissions)
+    assert_equal 2, ont.submissions.length
+
+    # verify that no new submission is created when the file has not changed
+    parser.queue_submission(ont.submissions[0], actions)
+    parser.process_queue_submissions
+    ont = LinkedData::Models::Ontology.find(ontologies[0].id).first
+    ont.bring(:submissions) if ont.bring?(:submissions)
+    assert_equal 2, ont.submissions.length
+  end
+
   def test_pull_error_notification
     server_port = Random.rand(55000..65535)
 
@@ -164,8 +190,9 @@ def test_no_pull_location
 
   private
 
-  def init_ontologies(submission_count)
-    ont_count, acronyms, ontologies = LinkedData::SampleData::Ontology.create_ontologies_and_submissions(ont_count: 1, submission_count: submission_count, process_submission: false)
+  def init_ontologies(submission_count, process_submissions = false)
+    ont_count, acronyms, ontologies = LinkedData::SampleData::Ontology.create_ontologies_and_submissions(
+                            ont_count: 1, submission_count: submission_count, process_submission: process_submissions)
     ontologies[0].bring(:submissions) if ontologies[0].bring?(:submissions)
     ontologies[0].submissions.each do |sub|
       sub.bring_remaining()

From 23316314217ec2e6b5cba8d66f3b8a491f53da4c Mon Sep 17 00:00:00 2001
From: mdorf <mdorf@stanford.edu>
Date: Sat, 16 Dec 2023 17:54:36 -0800
Subject: [PATCH 56/62] implemented the first pass at bmir-radx/radx-project#37

---
 lib/ncbo_cron/ontology_submission_parser.rb | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/lib/ncbo_cron/ontology_submission_parser.rb b/lib/ncbo_cron/ontology_submission_parser.rb
index f493eced..8d33f89d 100644
--- a/lib/ncbo_cron/ontology_submission_parser.rb
+++ b/lib/ncbo_cron/ontology_submission_parser.rb
@@ -29,6 +29,8 @@ def process_queue_submissions(options={})
           redis.hdel(QUEUE_HOLDER, key)
 
           # if :remote_pull is one of the actions, pull the ontology and halt if no new submission is found
+          # if a new submission is found, replace the submission ID with the new one and proceed with
+          # processing the remaining actions on the new submission
           if actions.key?(:remote_pull) && actions[:remote_pull]
             acronym = NcboCron::Helpers::OntologyHelper.acronym_from_submission_id(realKey)
             new_submission = NcboCron::Helpers::OntologyHelper.do_ontology_pull(acronym, enable_pull_umls: false,

From 07107b1aa08e41bb4ce8de311149355de70738e5 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 19 Dec 2023 15:08:28 -0800
Subject: [PATCH 57/62] set bundler version to be comptatible with ruby 2.7

+ AG v8
---
 Dockerfile         |  4 ++++
 docker-compose.yml | 15 ++++++---------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index dfc03492..73e1379c 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -14,6 +14,10 @@ COPY Gemfile* *.gemspec /srv/ontoportal/ncbo_cron/
 
 WORKDIR /srv/ontoportal/ncbo_cron
 
+# set rubygem and bundler to the last version supported by ruby 2.7
+# remove version after ruby v3 upgrade
+RUN gem update --system '3.4.22'
+RUN gem install bundler -v '2.4.22'
 RUN gem update --system
 RUN gem install bundler
 ENV BUNDLE_PATH=/srv/ontoportal/bundle
diff --git a/docker-compose.yml b/docker-compose.yml
index 0045ce12..5f4e9307 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -4,7 +4,7 @@ x-app: &app
     args:
       RUBY_VERSION: '2.7'
   # Increase the version number in the image tag every time Dockerfile or its arguments is changed
-  image: ncbo_cron:0.0.1
+  image: ncbo_cron:0.0.2
   environment: &env
     BUNDLE_PATH: /srv/ontoportal/bundle
     # default bundle config resolves to /usr/local/bundle/config inside of the container
@@ -19,12 +19,10 @@ x-app: &app
     SOLR_TERM_SEARCH_URL: http://solr-ut:8983/solr/term_search_core1
     SOLR_PROP_SEARCH_URL: http://solr-ut:8983/solr/prop_search_core1
     MGREP_HOST: mgrep-ut
-    MGREP_PORT: 55555
+    MGREP_PORT: 55556
   stdin_open: true
   tty: true
   command: "bundle exec rackup -o 0.0.0.0 --port 9393"
-  ports:
-    - 9393:9393
   volumes:
     # bundle volume for hosting gems installed by bundle; it helps in local development with gem udpates
     - bundle:/srv/ontoportal/bundle
@@ -104,18 +102,17 @@ services:
       retries: 5
 
   mgrep-ut:
-    image: ontoportal/mgrep:0.0.1
+    image: ontoportal/mgrep:0.0.2
     platform: linux/amd64
     healthcheck:
-      test: ["CMD", "nc", "-z", "-v", "localhost", "55555"]
+      test: ["CMD", "nc", "-z", "-v", "localhost", "55556"]
       start_period: 3s
       interval: 10s
       timeout: 5s
       retries: 5
 
   agraph-ut:
-    #image: franzinc/agraph:v7.3.1
-    image: ontoportal/agraph:v7.3.1-patch1
+    image: franzinc/agraph:v8.0.0
     platform: linux/amd64
     environment:
       - AGRAPH_SUPER_USER=test
@@ -131,7 +128,7 @@ services:
        ; tail -f /agraph/data/agraph.log"
     healthcheck:
       test: ["CMD-SHELL", "agtool storage-report bioportal_test || exit 1"]
-      start_period: 10s
+      start_period: 20s
       interval: 60s
       timeout: 5s
       retries: 3

From bada7d2a26903cba03d6b881637576275e143f68 Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Wed, 27 Dec 2023 13:31:02 +0100
Subject: [PATCH 58/62] refactor ontologies analytics job to handle the new
 google analytics migration

---
 bin/generate_ua_analytics_file.rb             | 126 --------
 bin/ncbo_cron                                 |   2 +-
 bin/ncbo_ontology_analytics_rebuild           |   2 +-
 lib/ncbo_cron.rb                              |   2 +-
 lib/ncbo_cron/analytics/object_analytics.rb   | 269 ++++++++++++++++++
 .../analytics/object_analytics_job.rb         |  87 ++++++
 .../analytics/ontology_visits_analytics.rb    | 110 +++++++
 lib/ncbo_cron/ontology_analytics.rb           | 233 ---------------
 8 files changed, 469 insertions(+), 362 deletions(-)
 delete mode 100755 bin/generate_ua_analytics_file.rb
 create mode 100644 lib/ncbo_cron/analytics/object_analytics.rb
 create mode 100644 lib/ncbo_cron/analytics/object_analytics_job.rb
 create mode 100644 lib/ncbo_cron/analytics/ontology_visits_analytics.rb
 delete mode 100644 lib/ncbo_cron/ontology_analytics.rb

diff --git a/bin/generate_ua_analytics_file.rb b/bin/generate_ua_analytics_file.rb
deleted file mode 100755
index 0a432a92..00000000
--- a/bin/generate_ua_analytics_file.rb
+++ /dev/null
@@ -1,126 +0,0 @@
-require 'logger'
-require 'google/apis/analytics_v3'
-require 'google/api_client/auth/key_utils'
-
-module NcboCron
-  module Models
-
-    class OntologyAnalyticsUA
-
-      def initialize(logger)
-        @logger = logger
-      end
-
-      def run
-        redis = Redis.new(:host => NcboCron.settings.redis_host, :port => NcboCron.settings.redis_port)
-        ontology_analytics = fetch_ontology_analytics
-        File.open(NcboCron.settings.analytics_path_to_ua_data_file, 'w') do |f|
-          f.write(ontology_analytics.to_json)
-        end
-      end
-
-      def fetch_ontology_analytics
-        google_client = authenticate_google
-        aggregated_results = Hash.new
-        start_year = Date.parse(NcboCron.settings.analytics_start_date).year || 2013
-        ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
-        # ont_acronyms = ["NCIT", "ONTOMA", "CMPO", "AEO", "SNOMEDCT"]
-        filter_str = (NcboCron.settings.analytics_filter_str.nil? || NcboCron.settings.analytics_filter_str.empty?) ? "" : ";#{NcboCron.settings.analytics_filter_str}"
-
-        ont_acronyms.each do |acronym|
-          max_results = 10000
-          num_results = 10000
-          start_index = 1
-          results = nil
-
-          loop do
-            results = google_client.get_ga_data(
-              ids          = NcboCron.settings.analytics_profile_id,
-              start_date   = NcboCron.settings.analytics_start_date,
-              end_date     = Date.today.to_s,
-              metrics      = 'ga:pageviews',
-              {
-                dimensions:  'ga:pagePath,ga:year,ga:month',
-                filters:     "ga:pagePath=~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}",
-                start_index: start_index,
-                max_results: max_results
-              }
-            )
-            results.rows ||= []
-            start_index += max_results
-            num_results = results.rows.length
-            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
-            @logger.flush
-
-            results.rows.each do |row|
-              if aggregated_results.has_key?(acronym)
-                # year
-                if aggregated_results[acronym].has_key?(row[1].to_i)
-                  # month
-                  if aggregated_results[acronym][row[1].to_i].has_key?(row[2].to_i)
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] += row[3].to_i
-                  else
-                    aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
-                  end
-                else
-                  aggregated_results[acronym][row[1].to_i] = Hash.new
-                  aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
-                end
-              else
-                aggregated_results[acronym] = Hash.new
-                aggregated_results[acronym][row[1].to_i] = Hash.new
-                aggregated_results[acronym][row[1].to_i][row[2].to_i] = row[3].to_i
-              end
-            end
-
-            if num_results < max_results
-              # fill up non existent years
-              (start_year..Date.today.year).each do |y|
-                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
-                aggregated_results[acronym][y] = Hash.new unless aggregated_results[acronym].has_key?(y)
-              end
-              # fill up non existent months with zeros
-              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n] = 0 unless v.has_key?(n) } }
-              break
-            end
-          end
-        end
-
-        @logger.info "Completed Universal Analytics pull..."
-        @logger.flush
-
-        aggregated_results
-      end
-
-      def authenticate_google
-        Google::Apis::ClientOptions.default.application_name = NcboCron.settings.analytics_app_name
-        Google::Apis::ClientOptions.default.application_version = NcboCron.settings.analytics_app_version
-        # enable google api call retries in order to
-        # minigate analytics processing failure due to occasional google api timeouts and other outages
-        Google::Apis::RequestOptions.default.retries = 5
-        # uncoment to enable logging for debugging purposes
-        # Google::Apis.logger.level = Logger::DEBUG
-        # Google::Apis.logger = @logger
-        client = Google::Apis::AnalyticsV3::AnalyticsService.new
-        key = Google::APIClient::KeyUtils::load_from_pkcs12(NcboCron.settings.analytics_path_to_ua_key_file, 'notasecret')
-        client.authorization = Signet::OAuth2::Client.new(
-          :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
-          :audience             => 'https://accounts.google.com/o/oauth2/token',
-          :scope                => 'https://www.googleapis.com/auth/analytics.readonly',
-          :issuer               => NcboCron.settings.analytics_service_account_email_address,
-          :signing_key          => key
-        ).tap { |auth| auth.fetch_access_token! }
-        client
-      end
-    end
-  end
-end
-
-require 'ontologies_linked_data'
-require 'goo'
-require 'ncbo_annotator'
-require 'ncbo_cron/config'
-require_relative '../config/config'
-ontology_analytics_log_path = File.join("logs", "ontology-analytics-ua.log")
-ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
-NcboCron::Models::OntologyAnalyticsUA.new(ontology_analytics_logger).run
diff --git a/bin/ncbo_cron b/bin/ncbo_cron
index 397d726d..9073f9a1 100755
--- a/bin/ncbo_cron
+++ b/bin/ncbo_cron
@@ -381,7 +381,7 @@ runner.execute do |opts|
         logger.info "Logging ontology analytics refresh details to #{ontology_analytics_log_path}"; logger.flush
         t0 = Time.now
         # Generate ontology analytics
-        NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
+        NcboCron::Models::ObjectAnalyticsJob.new(logger).run
         # Generate ontology ranking
         NcboCron::Models::OntologyRank.new(ontology_analytics_logger).run
         logger.info "Ontology analytics refresh job completed in #{Time.now - t0} sec."; logger.flush
diff --git a/bin/ncbo_ontology_analytics_rebuild b/bin/ncbo_ontology_analytics_rebuild
index 5dfc082a..b37b8138 100755
--- a/bin/ncbo_ontology_analytics_rebuild
+++ b/bin/ncbo_ontology_analytics_rebuild
@@ -52,7 +52,7 @@ begin
   logger.info(msg)
 
   time = Benchmark.realtime do
-    NcboCron::Models::OntologyAnalytics.new(logger).run
+    NcboCron::Models::ObjectAnalyticsJob.new(logger).run
   end
   msg = "Completed rebuilding ontology analytics repository in #{(time/60).round(1)} minutes."
   puts msg
diff --git a/lib/ncbo_cron.rb b/lib/ncbo_cron.rb
index 884e6b33..83d67caa 100644
--- a/lib/ncbo_cron.rb
+++ b/lib/ncbo_cron.rb
@@ -11,7 +11,7 @@
 require_relative 'ncbo_cron/scheduler'
 require_relative 'ncbo_cron/query_caching'
 require_relative 'ncbo_cron/ontologies_report'
-require_relative 'ncbo_cron/ontology_analytics'
+require_relative 'ncbo_cron/analytics/object_analytics_job'
 require_relative 'ncbo_cron/ontology_rank'
 require_relative 'ncbo_cron/spam_deletion'
 require_relative 'ncbo_cron/mapping_counts'
diff --git a/lib/ncbo_cron/analytics/object_analytics.rb b/lib/ncbo_cron/analytics/object_analytics.rb
new file mode 100644
index 00000000..f5275f82
--- /dev/null
+++ b/lib/ncbo_cron/analytics/object_analytics.rb
@@ -0,0 +1,269 @@
+require 'logger'
+require 'json'
+require 'benchmark'
+require 'google/analytics/data'
+require 'google/apis/analytics_v3'
+require 'google/api_client/auth/key_utils'
+
+module NcboCron
+  module Models
+    UA_START_DATE = '2013-10-01'
+    GA4_START_DATE = '2023-06-01'
+
+    class GoogleAnalyticsConnector
+
+      attr_reader :ga_client
+
+      def initialize
+        @ga_data_file = NcboCron.settings.analytics_path_to_ga_data_file
+        @ua_data_file = NcboCron.settings.analytics_path_to_ua_data_file
+        @app_id = NcboCron.settings.analytics_property_id
+        @app_key_file = NcboCron.settings.analytics_path_to_key_file
+        @ga_client = analytics_data_client
+      end
+
+      def run_request(metrics:, dimensions:, date_ranges:, order_bys:, offset:, limit:, dimension_filter:)
+        request = Google::Analytics::Data::V1beta::RunReportRequest.new(
+          property: "properties/#{@app_id}",
+          metrics: metrics.map { |m| ga_metric(m) },
+          dimension_filter: dimension_filter.empty? ? nil : ga_filter(*dimension_filter),
+          dimensions: dimensions.map { |d| ga_dimension(d) },
+          date_ranges: [ga_date_range(*date_ranges)],
+          order_bys: order_bys.map { |o| ga_order_by(o) },
+          offset: offset,
+          limit: limit
+        )
+
+        @ga_client.run_report request
+      end
+
+      private
+
+      def analytics_data_client
+        Google::Analytics::Data.analytics_data do |config|
+          config.credentials = @app_key_file
+        end
+      end
+
+      def ga_metric(name)
+        Google::Analytics::Data::V1beta::Metric.new(
+          name: name
+        )
+      end
+
+      def ga_date_range(start_date, end_date)
+        Google::Analytics::Data::V1beta::DateRange.new(
+          start_date: start_date,
+          end_date: end_date
+        )
+      end
+
+      def ga_dimension(name)
+        Google::Analytics::Data::V1beta::Dimension.new(
+          name: name
+        )
+      end
+
+      def ga_filter(field_name, value)
+        string_filter = Google::Analytics::Data::V1beta::Filter::StringFilter.new(
+          match_type: Google::Analytics::Data::V1beta::Filter::StringFilter::MatchType::FULL_REGEXP,
+          value: value
+        )
+
+        filter = Google::Analytics::Data::V1beta::Filter.new(
+          field_name: field_name,
+          string_filter: string_filter
+        )
+        Google::Analytics::Data::V1beta::FilterExpression.new(filter: filter)
+      end
+
+      def ga_order_by(dimension_name, desc = false)
+        order = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
+          dimension_name: dimension_name
+        )
+        Google::Analytics::Data::V1beta::OrderBy.new(
+          desc: desc,
+          dimension: order
+        )
+      end
+
+    end
+
+    # Old version of Google Analytics
+    class GoogleAnalyticsUAConnector
+      def initialize
+        @app_id = NcboCron.settings.analytics_profile_id
+        @app_name = NcboCron.settings.analytics_app_name
+        @app_version = NcboCron.settings.analytics_app_version
+        @analytics_key_file = NcboCron.settings.ua_analytics_path_to_key_file
+        @app_user = NcboCron.settings.analytics_service_account_email_address
+        @generated_file_path = NcboCron.settings.analytics_path_to_ua_data_file
+        @start_date = NcboCron.settings.analytics_start_date
+        @analytics_filter = NcboCron.settings.analytics_filter_str
+        @ga_client = authenticate_google
+      end
+
+      def run_request(metrics:, dimensions:, filters:, start_index:, max_results:, dates_ranges:, sort:)
+        @ga_client.get_ga_data(
+          ids = @app_id,
+          start_date = dates_ranges.first,
+          end_date = dates_ranges.last,
+          metrics = metrics.map { |m| "ga:#{m}" }.join(','),
+          {
+            dimensions: dimensions.map { |d| "ga:#{d}" }.join(','),
+            filters: filters.empty? ? nil : filters.map { |f, v| "ga:#{f}=#{v}" }.join(','),
+            start_index: start_index,
+            max_results: max_results,
+            sort: sort.map { |d| "ga:#{d}" }.join(',')
+          }
+        )
+      end
+
+      private
+
+      def authenticate_google
+        Google::Apis::ClientOptions.default.application_name = @app_name
+        Google::Apis::ClientOptions.default.application_version = @app_version
+        # enable google api call retries in order to
+        # minigate analytics processing failure due to occasional google api timeouts and other outages
+        Google::Apis::RequestOptions.default.retries = 5
+        # uncoment to enable logging for debugging purposes
+        # Google::Apis.logger.level = Logger::DEBUG
+        # Google::Apis.logger = @logger
+        client = Google::Apis::AnalyticsV3::AnalyticsService.new
+        key = Google::APIClient::KeyUtils::load_from_pkcs12(@analytics_key_file, 'notasecret')
+        client.authorization = Signet::OAuth2::Client.new(
+          :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
+          :audience => 'https://accounts.google.com/o/oauth2/token',
+          :scope => 'https://www.googleapis.com/auth/analytics.readonly',
+          :issuer => @app_user,
+          :signing_key => key
+        ).tap { |auth| auth.fetch_access_token! }
+        client
+      end
+
+    end
+
+    class ObjectAnalytics
+
+      attr_reader :redis_field
+
+      def initialize(redis_field:, start_date:, old_data: {})
+        @redis_field = redis_field
+        @start_date = Date.parse(start_date) rescue Date.parse(NcboCron.settings.analytics_start_date)
+        @old_data = old_data[@redis_field] || {}
+      end
+
+      def full_data(logger, ga_conn, ua_conn)
+
+        logger.info "Fetching GA4 analytics for all ontologies from #{@start_date} to today..."
+        logger.flush
+        new_ga_data = fetch_object_analytics(logger, ga_conn)
+
+        if @start_date < Date.parse(GA4_START_DATE)
+          @old_data = {}
+          logger.info "Fetching UA analytics for all ontologies from #{@start_date} to today..."
+          logger.flush
+          ua_data = fetch_ua_object_analytics(logger, ua_conn)
+          logger.info "Completed Universal Analytics pull..."
+          logger.flush
+          new_ga_data = merge_and_fill_missing_data(new_ga_data, ua_data, logger)
+        end
+        merge_and_fill_missing_data(new_ga_data, @old_data, logger)
+      end
+
+      # @param ga_conn GoogleAnalyticsConnector
+      def fetch_object_analytics(logger, ga_conn)
+        raise NotImplementedError, "Subclasses must implement this method"
+      end
+
+      # @param ua_conn GoogleAnalyticsUAConnector
+      def fetch_ua_object_analytics(logger, ua_conn)
+        raise NotImplementedError, "Subclasses must implement this method"
+      end
+
+      private
+
+      def merge_and_fill_missing_data(new_data, old_data,logger, start_date = @start_date)
+        if !old_data.empty?
+          logger.info "Merging GA4 and UA data..."
+          logger.flush
+          old_data.keys.each do |acronym|
+            (start_date.year..Date.today.year).each do |year|
+              year = year.to_s
+              # add up hits for June of 2023 (the only intersecting month between UA and GA4)
+              if old_data[acronym].has_key?(year)
+                next unless new_data[acronym].has_key?(year)
+
+                (1..Date.today.month).each do |month|
+                  month = month.to_s
+                  old_data[acronym][year][month] ||= 0
+                  unless old_data[acronym][year][month].eql?(new_data[acronym][year][month])
+                    old_data[acronym][year][month] += (new_data[acronym][year][month] || 0)
+                  end
+                end
+
+              elsif new_data[acronym][year]
+                old_data[acronym][year] = new_data[acronym][year]
+              end
+            end
+          end
+          old_data = fill_missing_data(old_data)
+        else
+          old_data = new_data
+        end
+
+        # fill missing years and months
+        logger.info "Filling in missing years data..."
+        logger.flush
+        old_data
+        # sort_ga_data(old_data)
+      end
+
+      def aggregate_results(aggregated_results, results)
+        results.each do |row|
+
+          year = row[1].to_i.to_s
+          month = row[2].to_i.to_s
+          value = row[3].to_i
+          aggregated = aggregated_results
+          # year
+          if aggregated.has_key?(year)
+            # month
+            if aggregated[year].has_key?(month)
+              aggregated[year][month] += value
+            else
+              aggregated[year][month] = value
+            end
+          else
+            aggregated[year] = Hash.new
+            aggregated[year][month] = value
+          end
+        end
+      end
+
+      def fill_missing_data(ga_data)
+        # fill up non existent years
+        start_year = Date.parse(UA_START_DATE).year
+
+        ga_data.each do |acronym, _|
+          (start_year..Date.today.year).each do |y|
+            ga_data[acronym] = Hash.new if ga_data[acronym].nil?
+            ga_data[acronym][y.to_s] = Hash.new unless ga_data[acronym].has_key?(y.to_s)
+          end
+          # fill up non existent months with zeros
+          (1..12).each { |n| ga_data[acronym].values.each { |v| v[n.to_s] = 0 if v.is_a?(Hash) && !v.has_key?(n.to_s) } }
+        end
+      end
+
+      def sort_ga_data(ga_data)
+        ga_data.transform_values { |value|
+          value.transform_values { |val|
+            val.sort_by { |key, _| key.to_i }.to_h
+          }.sort_by { |k, _| k.to_i }.to_h
+        }.sort.to_h
+      end
+
+    end
+  end
+end
diff --git a/lib/ncbo_cron/analytics/object_analytics_job.rb b/lib/ncbo_cron/analytics/object_analytics_job.rb
new file mode 100644
index 00000000..af2e2885
--- /dev/null
+++ b/lib/ncbo_cron/analytics/object_analytics_job.rb
@@ -0,0 +1,87 @@
+require 'logger'
+require 'json'
+require 'benchmark'
+require 'google/analytics/data'
+require 'google/apis/analytics_v3'
+require 'google/api_client/auth/key_utils'
+
+require_relative 'ontology_visits_analytics'
+require_relative 'user_visits_analytics'
+require_relative 'page_visits_analytics'
+
+module NcboCron
+  module Models
+    class ObjectAnalyticsJob
+      def initialize(logger)
+        @redis_host = LinkedData.settings.ontology_analytics_redis_host
+        @redis_port = LinkedData.settings.ontology_analytics_redis_port
+
+        @data_file =  NcboCron.settings.analytics_path_to_ga_data_file
+        @ua_data_file = NcboCron.settings.analytics_path_to_ua_data_file
+
+        @ga_conn = GoogleAnalyticsConnector.new
+        @ua_conn = GoogleAnalyticsUAConnector.new
+
+        @logger = logger
+        @logger.info "Authenticating with the Google Analytics Endpoint..."
+        @logger.flush
+
+        @analytics_objects = [
+          NcboCron::Models::OntologyVisitsAnalytics,
+          NcboCron::Models::UsersVisitsAnalytics,
+          NcboCron::Models::PageVisitsAnalytics,
+        ]
+      end
+
+      # @param analytics_objects ObjectAnalytics[]
+      def run
+        redis = Redis.new(:host => @redis_host, :port => @redis_port)
+        @logger.info "Starting Google Analytics refresh..."
+        @logger.flush
+        time = Benchmark.realtime do
+          @logger.info "Fetching all ontology acronyms from backend..."
+          @logger.flush
+          save = {}
+          @old_data = read_old_data
+          @analytics_objects.each do |analytic_object|
+            analytic_object = analytic_object.new(start_date: detect_latest_date, old_data: @old_data)
+            new_data = analytic_object.full_data(@logger, @ga_conn, @ua_conn)
+            save[analytic_object.redis_field] = new_data
+            redis.set(analytic_object.redis_field, Marshal.dump(new_data))
+          end
+          save_data(save)
+        end
+        @logger.info "Completed Google Analytics refresh in #{(time / 60).round(1)} minutes."
+        @logger.flush
+      end
+
+      private
+      def read_old_data
+        return {} unless File.exists?(@data_file) && !File.zero?(@data_file)
+        JSON.parse(File.read(@data_file))
+      end
+
+      def detect_latest_date
+        begin
+          input_date = Date.parse(@old_data['latest_date_save']).prev_month(6)
+          start_of_month = Date.new(input_date.year, input_date.month, 1)
+          start_of_month.to_s
+        rescue
+          nil
+        end
+
+      end
+
+      def save_data(new_data)
+        new_data["latest_date_save"] =  Date.today.to_s
+        # Ensure the directory exists before creating the file
+        FileUtils.mkdir_p(File.dirname(@data_file))
+        # Open the file with 'w+' mode to create if not exist and write
+        File.open(@data_file, 'w+') do |f|
+          f.write(new_data.to_json)
+        end
+      end
+    end
+
+  end
+end
diff --git a/lib/ncbo_cron/analytics/ontology_visits_analytics.rb b/lib/ncbo_cron/analytics/ontology_visits_analytics.rb
new file mode 100644
index 00000000..6aa64e79
--- /dev/null
+++ b/lib/ncbo_cron/analytics/ontology_visits_analytics.rb
@@ -0,0 +1,110 @@
+require 'logger'
+require 'json'
+require 'benchmark'
+require_relative 'object_analytics'
+
+module NcboCron
+  module Models
+
+    class OntologyVisitsAnalytics < ObjectAnalytics
+
+      ONTOLOGY_ANALYTICS_REDIS_FIELD = 'ontology_analytics'
+
+      def initialize(start_date: , old_data: {})
+        super(redis_field: ONTOLOGY_ANALYTICS_REDIS_FIELD, start_date: start_date, old_data: old_data)
+        @ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map { |o| o.acronym }
+        @ont_acronyms = ['AGROVOC', 'E-PHY', 'CROPUSAGE']
+      end
+
+
+      def fetch_ua_object_analytics(logger, ua_conn)
+        @logger = logger
+        @ua_conn =  ua_conn
+        aggregated_results = Hash.new
+        start_year = Date.parse(UA_START_DATE).year || 2013
+        filter_str = (@analytics_filter.nil? || @analytics_filter.empty?) ? "" : ";#{@analytics_filter}"
+
+        @ont_acronyms.each do |acronym|
+          max_results = 10000
+          start_index = 1
+          loop do
+            results = @ua_conn.run_request(
+              metrics: ['pageviews'],
+              dimensions: %w[pagePath year month],
+              filters: [['pagePath', "~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}"]],
+              start_index: start_index,
+              max_results: max_results,
+              dates_ranges: [UA_START_DATE, Date.today.to_s],
+              sort: %w[year month]
+            )
+            results.rows ||= []
+            start_index += max_results
+            num_results = results.rows.length
+            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+            @logger.flush
+            aggregated_results[acronym] = Hash.new unless aggregated_results.has_key?(acronym)
+            aggregate_results(aggregated_results[acronym], results.rows)
+
+            if num_results < max_results
+              # fill up non existent years
+              (start_year..Date.today.year).each do |y|
+                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
+                aggregated_results[acronym][y.to_s] = Hash.new unless aggregated_results[acronym].has_key?(y.to_s)
+              end
+              # fill up non existent months with zeros
+              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+              break
+            end
+          end
+        end
+        sort_ga_data(aggregated_results)
+      end
+
+      def fetch_object_analytics(logger, ga_conn)
+        @logger = logger
+        @ga_conn = ga_conn
+
+        aggregated_results = Hash.new
+        max_results = 10000
+
+        @ont_acronyms.each do |acronym|
+          start_index = 0
+          filer_regex = "^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$"
+
+          loop do
+            response = @ga_conn.run_request(
+              date_ranges: [[@start_date, Date.parse(GA4_START_DATE)].max.to_s, Date.today.to_s],
+              metrics: ['screenPageViews'],
+              dimensions: %w[pagePath year month],
+              order_bys: %w[year month],
+              dimension_filter: ['pagePath', filer_regex],
+              offset: start_index,
+              limit: max_results
+            )
+
+            response.rows ||= []
+            num_results = response.rows.length
+            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+            @logger.flush
+            start_index += max_results
+            results = []
+
+            response.rows.each do |row|
+              row_h = row.to_h
+              year_month_hits = row_h[:dimension_values].map.with_index {
+                |v, i| i > 0 ? v[:value].to_s : row_h[:metric_values][0][:value].to_s
+              }.rotate(1)
+              results << ([acronym] + year_month_hits)
+            end
+            aggregated_results[acronym] = Hash.new unless aggregated_results.has_key?(acronym)
+            aggregate_results(aggregated_results[acronym], results)
+            break if num_results < max_results
+          end
+        end
+        aggregated_results
+      end
+
+    end
+
+  end
+end
diff --git a/lib/ncbo_cron/ontology_analytics.rb b/lib/ncbo_cron/ontology_analytics.rb
deleted file mode 100644
index c5a4de00..00000000
--- a/lib/ncbo_cron/ontology_analytics.rb
+++ /dev/null
@@ -1,233 +0,0 @@
-require 'logger'
-require 'json'
-require 'benchmark'
-require 'google/analytics/data'
-
-
-module NcboCron
-  module Models
-
-    class OntologyAnalytics
-      ONTOLOGY_ANALYTICS_REDIS_FIELD = 'ontology_analytics'
-      UA_START_DATE = '2013-10-01'
-      GA4_START_DATE = '2023-06-01'
-
-      def initialize(logger)
-        @logger = logger
-      end
-
-      def run
-        redis = Redis.new(:host => LinkedData.settings.ontology_analytics_redis_host, :port => LinkedData.settings.ontology_analytics_redis_port)
-        ontology_analytics = fetch_ontology_analytics
-        File.open(NcboCron.settings.analytics_path_to_ga_data_file, 'w') do |f|
-          f.write(ontology_analytics.to_json)
-        end
-        redis.set(ONTOLOGY_ANALYTICS_REDIS_FIELD, Marshal.dump(ontology_analytics))
-      end
-
-      def fetch_ontology_analytics
-        @logger.info "Starting Google Analytics refresh..."
-        @logger.flush
-        full_data = nil
-
-        time = Benchmark.realtime do
-          max_results = 10000
-          aggregated_results = Hash.new
-
-          @logger.info "Fetching all ontology acronyms from backend..."
-          @logger.flush
-          ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map {|o| o.acronym}
-          # ont_acronyms = ["NCIT", "SNOMEDCT", "MEDDRA"]
-          @logger.info "Authenticating with the Google Analytics Endpoint..."
-          @logger.flush
-          google_client = authenticate_google
-
-          date_range = Google::Analytics::Data::V1beta::DateRange.new(
-            start_date: GA4_START_DATE,
-            end_date: Date.today.to_s
-          )
-          metrics_page_views = Google::Analytics::Data::V1beta::Metric.new(
-            name: "screenPageViews"
-          )
-          dimension_path = Google::Analytics::Data::V1beta::Dimension.new(
-            name: "pagePath"
-          )
-          dimension_year = Google::Analytics::Data::V1beta::Dimension.new(
-            name: "year"
-          )
-          dimension_month = Google::Analytics::Data::V1beta::Dimension.new(
-            name: "month"
-          )
-          string_filter = Google::Analytics::Data::V1beta::Filter::StringFilter.new(
-            match_type: Google::Analytics::Data::V1beta::Filter::StringFilter::MatchType::FULL_REGEXP
-          )
-          filter = Google::Analytics::Data::V1beta::Filter.new(
-            field_name: "pagePath",
-            string_filter: string_filter
-          )
-          filter_expression = Google::Analytics::Data::V1beta::FilterExpression.new(
-            filter: filter
-          )
-          order_year = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
-            dimension_name: "year"
-          )
-          orderby_year = Google::Analytics::Data::V1beta::OrderBy.new(
-            desc: false,
-            dimension: order_year
-          )
-          order_month = Google::Analytics::Data::V1beta::OrderBy::DimensionOrderBy.new(
-            dimension_name: "month"
-          )
-          orderby_month = Google::Analytics::Data::V1beta::OrderBy.new(
-            desc: false,
-            dimension: order_month
-          )
-          @logger.info "Fetching GA4 analytics for all ontologies..."
-          @logger.flush
-
-          ont_acronyms.each do |acronym|
-            start_index = 0
-            string_filter.value = "^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$"
-
-            loop do
-              request = Google::Analytics::Data::V1beta::RunReportRequest.new(
-                property: "properties/#{NcboCron.settings.analytics_property_id}",
-                metrics: [metrics_page_views],
-                dimension_filter: filter_expression,
-                dimensions: [dimension_path, dimension_year, dimension_month],
-                date_ranges: [date_range],
-                order_bys: [orderby_year, orderby_month],
-                offset: start_index,
-                limit: max_results
-              )
-              response = google_client.run_report request
-
-              response.rows ||= []
-              start_index += max_results
-              num_results = response.rows.length
-              @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
-              @logger.flush
-
-              response.rows.each do |row|
-                row_h = row.to_h
-                year_month_hits =  row_h[:dimension_values].map.with_index {
-                  |v, i| i > 0 ? v[:value].to_i.to_s : row_h[:metric_values][0][:value].to_i
-                }.rotate(1)
-
-                if aggregated_results.has_key?(acronym)
-                  # year
-                  if aggregated_results[acronym].has_key?(year_month_hits[0])
-                    # month
-                    if aggregated_results[acronym][year_month_hits[0]].has_key?(year_month_hits[1])
-                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] += year_month_hits[2]
-                    else
-                      aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
-                    end
-                  else
-                    aggregated_results[acronym][year_month_hits[0]] = Hash.new
-                    aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
-                  end
-                else
-                  aggregated_results[acronym] = Hash.new
-                  aggregated_results[acronym][year_month_hits[0]] = Hash.new
-                  aggregated_results[acronym][year_month_hits[0]][year_month_hits[1]] = year_month_hits[2]
-                end
-              end
-              break if num_results < max_results
-            end # loop
-          end # ont_acronyms
-          @logger.info "Refresh complete"
-          @logger.flush
-          full_data = merge_and_fill_missing_data(aggregated_results)
-        end # Benchmark.realtime
-        @logger.info "Completed Google Analytics refresh in #{(time/60).round(1)} minutes."
-        @logger.flush
-        full_data
-      end
-
-      def merge_and_fill_missing_data(ga4_data)
-        ua_data = {}
-
-        if File.exists?(NcboCron.settings.analytics_path_to_ua_data_file) &&
-            !File.zero?(NcboCron.settings.analytics_path_to_ua_data_file)
-          @logger.info "Merging GA4 and UA data..."
-          @logger.flush
-          ua_data_file = File.read(NcboCron.settings.analytics_path_to_ua_data_file)
-          ua_data = JSON.parse(ua_data_file)
-          ua_ga4_intersecting_year = Date.parse(GA4_START_DATE).year.to_s
-          ua_ga4_intersecting_month = Date.parse(GA4_START_DATE).month.to_s
-
-          # add up hits for June of 2023 (the only intersecting month between UA and GA4)
-          ua_data.each do |acronym, _|
-            if ga4_data.has_key?(acronym)
-              if ga4_data[acronym][ua_ga4_intersecting_year].has_key?(ua_ga4_intersecting_month)
-                ua_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month] +=
-                    ga4_data[acronym][ua_ga4_intersecting_year][ua_ga4_intersecting_month]
-                # delete data for June of 2023 from ga4_data to avoid overwriting when merging
-                ga4_data[acronym][ua_ga4_intersecting_year].delete(ua_ga4_intersecting_month)
-              end
-            end
-          end
-        end
-
-        # merge ua and ga4 data
-        merged_data = ua_data.deep_merge(ga4_data)
-        # fill missing years and months
-        @logger.info "Filling in missing years data..."
-        @logger.flush
-        fill_missing_data(merged_data)
-        # sort acronyms, years and months
-        @logger.info "Sorting final data..."
-        @logger.flush
-        sort_ga_data(merged_data)
-      end
-
-      def fill_missing_data(ga_data)
-        # fill up non existent years
-        start_year = Date.parse(UA_START_DATE).year
-
-        ga_data.each do |acronym, _|
-          (start_year..Date.today.year).each do |y|
-            ga_data[acronym] = Hash.new if ga_data[acronym].nil?
-            ga_data[acronym][y.to_s] = Hash.new unless ga_data[acronym].has_key?(y.to_s)
-          end
-          # fill up non existent months with zeros
-          (1..12).each { |n| ga_data[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
-        end
-      end
-
-      def sort_ga_data(ga_data)
-        ga_data.transform_values { |value|
-          value.transform_values { |val|
-            val.sort_by { |key, _| key.to_i }.to_h
-          }.sort_by { |k, _| k.to_i }.to_h
-        }.sort.to_h
-      end
-
-      def authenticate_google
-        Google::Analytics::Data.analytics_data do |config|
-          config.credentials = NcboCron.settings.analytics_path_to_key_file
-        end
-      end
-    end # class
-
-  end
-end
-
-class ::Hash
-  def deep_merge(second)
-    merger = proc { |key, v1, v2| Hash === v1 && Hash === v2 ? v1.merge(v2, &merger) : v2 }
-    self.merge(second, &merger)
-  end
-end
-
-# require 'ontologies_linked_data'
-# require 'goo'
-# require 'ncbo_annotator'
-# require 'ncbo_cron/config'
-# require_relative '../../config/config'
-# # ontology_analytics_log_path = File.join("logs", "ontology-analytics.log")
-# # ontology_analytics_logger = Logger.new(ontology_analytics_log_path)
-# ontology_analytics_logger = Logger.new(STDOUT)
-# NcboCron::Models::OntologyAnalytics.new(ontology_analytics_logger).run
-# ./bin/ncbo_cron --disable-processing true --disable-pull true --disable-flush true --disable-warmq true --disable-ontologies-report true --disable-mapping-counts true --disable-spam-deletion true --ontology-analytics '14 * * * *'

From 08f5e4228f9f7fbc5bb7a6da020213968e77245a Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Wed, 27 Dec 2023 13:31:51 +0100
Subject: [PATCH 59/62] add user analytics fetching the monthly user visits
 count

---
 .../analytics/user_visits_analytics.rb        | 94 +++++++++++++++++++
 1 file changed, 94 insertions(+)
 create mode 100644 lib/ncbo_cron/analytics/user_visits_analytics.rb

diff --git a/lib/ncbo_cron/analytics/user_visits_analytics.rb b/lib/ncbo_cron/analytics/user_visits_analytics.rb
new file mode 100644
index 00000000..793bf0ca
--- /dev/null
+++ b/lib/ncbo_cron/analytics/user_visits_analytics.rb
@@ -0,0 +1,94 @@
+require 'logger'
+require 'json'
+require 'benchmark'
+require_relative 'object_analytics'
+
+module NcboCron
+  module Models
+    class UsersVisitsAnalytics < ObjectAnalytics
+      def initialize(start_date: , old_data: {})
+        super(redis_field: 'user_analytics', start_date: start_date, old_data: old_data)
+      end
+
+      private
+
+      def fetch_object_analytics(logger, ga_conn)
+        @logger = logger
+        @ga_conn = ga_conn
+
+        aggregated_results = Hash.new
+        max_results = 10000
+
+
+
+        start_index = 0
+        loop do
+          response = @ga_conn.run_request(
+            date_ranges: [[@start_date, Date.parse(GA4_START_DATE)].max.to_s, Date.today.to_s],
+            metrics: ['newUsers'],
+            dimensions: %w[year month],
+            order_bys: %w[year month],
+            dimension_filter: [],
+            offset: start_index,
+            limit: max_results
+          )
+
+          response.rows ||= []
+          num_results = response.rows.length
+          @logger.info "Results: #{num_results}, Start Index: #{start_index}"
+          @logger.flush
+          start_index += max_results
+          results = []
+          response.rows.each do |row|
+            row_h = row.to_h
+            year_month_hits = row_h[:dimension_values].map{ |x| x[:value] } + [row_h[:metric_values].first[:value]]
+            results << ([-1] + year_month_hits)
+          end
+          aggregate_results(aggregated_results, results)
+          break if num_results < max_results
+
+        end
+        {"all_users" => aggregated_results}
+      end
+
+      def fetch_ua_object_analytics(logger, ua_conn)
+
+        aggregated_results = Hash.new
+        start_year = Date.parse(UA_START_DATE).year || 2013
+
+        max_results = 10000
+        start_index = 1
+        loop do
+          results = ua_conn.run_request(
+            metrics: ['newUsers'],
+            dimensions: %w[year month],
+            filters: [],
+            start_index: start_index,
+            max_results: max_results,
+            dates_ranges: [UA_START_DATE, Date.today.to_s],
+            sort: %w[year month]
+          )
+          results.rows ||= []
+          start_index += max_results
+          num_results = results.rows.length
+          logger.info "Results: #{num_results}, Start Index: #{start_index}"
+          logger.flush
+          aggregate_results(aggregated_results, results.rows.map{|row| [-1] + row})
+
+          if num_results < max_results
+            # fill up non existent years
+            (start_year..Date.today.year).each do |y|
+              aggregated_results = Hash.new if aggregated_results.nil?
+              aggregated_results[y.to_s] = Hash.new unless aggregated_results.has_key?(y.to_s)
+            end
+            # fill up non existent months with zeros
+            (1..12).each { |n| aggregated_results.values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+            break
+          end
+        end
+        { "all_users" => aggregated_results}
+      end
+    end
+  end
+end
+

From 6f21df6f2640853617b072f64638a7fea293963c Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Wed, 27 Dec 2023 13:32:50 +0100
Subject: [PATCH 60/62] add page visits analytics  fetching  last month most
 visited pages

---
 Gemfile                                       |  4 +-
 Gemfile.lock                                  | 49 +++++++-------
 docker-compose.yml                            |  4 ++
 .../analytics/page_visits_analytics.rb        | 65 +++++++++++++++++++
 4 files changed, 97 insertions(+), 25 deletions(-)
 create mode 100644 lib/ncbo_cron/analytics/page_visits_analytics.rb

diff --git a/Gemfile b/Gemfile
index 7003d3ac..1d7413db 100644
--- a/Gemfile
+++ b/Gemfile
@@ -25,9 +25,9 @@ gem 'request_store'
 # Monitoring
 gem 'cube-ruby', require: 'cube'
 
-gem 'goo', github: 'ontoportal-lirmm/goo', branch: 'development'
+gem 'goo', github: 'ontoportal-lirmm/goo', branch: 'master'
 gem 'sparql-client', github: 'ontoportal-lirmm/sparql-client', branch: 'master'
-gem 'ontologies_linked_data', github: 'ontoportal-lirmm/ontologies_linked_data', branch: 'development'
+gem 'ontologies_linked_data', github: 'ontoportal-lirmm/ontologies_linked_data', branch: 'master'
 gem 'ncbo_annotator', github: 'ontoportal-lirmm/ncbo_annotator', branch: 'master'
 # Testing
 group :test do
diff --git a/Gemfile.lock b/Gemfile.lock
index ec0671de..d752fe7d 100644
--- a/Gemfile.lock
+++ b/Gemfile.lock
@@ -1,7 +1,7 @@
 GIT
   remote: https://github.com/ontoportal-lirmm/goo.git
-  revision: 69466682c1e9cb2c338539195013dbec9714ca7d
-  branch: development
+  revision: 03da25b671d2ffa515b5dce51c6bd35980ae60c7
+  branch: master
   specs:
     goo (0.0.2)
       addressable (~> 2.8)
@@ -26,8 +26,8 @@ GIT
 
 GIT
   remote: https://github.com/ontoportal-lirmm/ontologies_linked_data.git
-  revision: 1204ede68ed0a5af5e3fb355172496d5e0134544
-  branch: development
+  revision: e98b884999e5ce917a8be5fdc37f7b4797a1559e
+  branch: master
   specs:
     ontologies_linked_data (0.0.1)
       activesupport
@@ -77,7 +77,8 @@ GEM
     addressable (2.8.6)
       public_suffix (>= 2.0.2, < 6.0)
     base64 (0.2.0)
-    bcrypt (3.1.19)
+    bcrypt (3.1.20)
+    bigdecimal (3.1.5)
     binding_of_caller (1.0.0)
       debug_inspector (>= 0.0.1)
     builder (3.2.4)
@@ -86,14 +87,15 @@ GEM
     connection_pool (2.4.1)
     cube-ruby (0.0.3)
     dante (0.2.0)
-    debug_inspector (1.1.0)
+    debug_inspector (1.2.0)
+    declarative (0.0.20)
     docile (1.4.0)
     domain_name (0.6.20231109)
     email_spec (2.1.1)
       htmlentities (~> 4.3.3)
       launchy (~> 2.1)
       mail (~> 2.6)
-    faraday (2.7.12)
+    faraday (2.8.1)
       base64
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
@@ -101,7 +103,7 @@ GEM
     faraday-retry (2.2.0)
       faraday (~> 2.0)
     ffi (1.16.3)
-    gapic-common (0.20.0)
+    gapic-common (0.21.1)
       faraday (>= 1.9, < 3.a)
       faraday-retry (>= 1.0, < 3.a)
       google-protobuf (~> 3.18)
@@ -132,25 +134,22 @@ GEM
     google-cloud-env (2.1.0)
       faraday (>= 1.0, < 3.a)
     google-cloud-errors (1.3.1)
-    google-protobuf (3.24.4-x86_64-darwin)
-    google-protobuf (3.24.4-x86_64-linux)
+    google-protobuf (3.25.1-x86_64-darwin)
     googleapis-common-protos (1.4.0)
       google-protobuf (~> 3.14)
       googleapis-common-protos-types (~> 1.2)
       grpc (~> 1.27)
-    googleapis-common-protos-types (1.9.0)
+    googleapis-common-protos-types (1.11.0)
       google-protobuf (~> 3.18)
-    googleauth (1.8.1)
-      faraday (>= 0.17.3, < 3.a)
+    googleauth (1.9.1)
+      faraday (>= 1.0, < 3.a)
+      google-cloud-env (~> 2.1)
       jwt (>= 1.4, < 3.0)
       multi_json (~> 1.11)
       os (>= 0.9, < 2.0)
       signet (>= 0.16, < 2.a)
-    grpc (1.58.0-x86_64-darwin)
-      google-protobuf (~> 3.23)
-      googleapis-common-protos-types (~> 1.0)
-    grpc (1.59.2-x86_64-linux)
-      google-protobuf (~> 3.24)
+    grpc (1.60.0-x86_64-darwin)
+      google-protobuf (~> 3.25)
       googleapis-common-protos-types (~> 1.0)
     htmlentities (4.3.4)
     http-accept (1.7.0)
@@ -173,7 +172,8 @@ GEM
     method_source (1.0.0)
     mime-types (3.5.1)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.1003)
+    mime-types-data (3.2023.1205)
+    mini_mime (1.1.5)
     minitest (4.7.5)
     mlanett-redis-lock (0.2.7)
       redis
@@ -200,8 +200,12 @@ GEM
       addressable (>= 2.2)
     redis (5.0.8)
       redis-client (>= 0.17.0)
-    redis-client (0.18.0)
+    redis-client (0.19.1)
       connection_pool
+    representable (3.2.0)
+      declarative (< 0.1.0)
+      trailblazer-option (>= 0.1.1, < 0.2.0)
+      uber (< 0.2.0)
     request_store (1.5.1)
       rack (>= 1.4)
     rest-client (2.1.0)
@@ -247,8 +251,7 @@ GEM
     webrick (1.8.1)
 
 PLATFORMS
-  x86_64-darwin-21
-  x86_64-linux
+  x86_64-darwin-23
 
 DEPENDENCIES
   binding_of_caller (~> 1.0)
@@ -279,4 +282,4 @@ DEPENDENCIES
   test-unit-minitest
 
 BUNDLED WITH
-   2.3.15
+   2.4.21
diff --git a/docker-compose.yml b/docker-compose.yml
index 783d33f2..9f5d628d 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -95,6 +95,8 @@ services:
       && 4s-httpd -D -s-1 -p 9000 ontoportal_kb"
     profiles:
       - 4store
+    ports:
+      - 9000:9000
 
   solr-ut:
     image: solr:8
@@ -122,6 +124,8 @@ services:
       interval: 10s
       timeout: 5s
       retries: 5
+    ports:
+      - 55556:55555
 
   agraph-ut:
     image: franzinc/agraph:v8.0.0
diff --git a/lib/ncbo_cron/analytics/page_visits_analytics.rb b/lib/ncbo_cron/analytics/page_visits_analytics.rb
new file mode 100644
index 00000000..8ecd21c0
--- /dev/null
+++ b/lib/ncbo_cron/analytics/page_visits_analytics.rb
@@ -0,0 +1,65 @@
+require 'logger'
+require 'json'
+require 'benchmark'
+require_relative 'object_analytics'
+
+module NcboCron
+  module Models
+    class PageVisitsAnalytics < ObjectAnalytics
+      def initialize(start_date: Date.today.prev_month, old_data: {})
+        super(redis_field: 'pages_analytics', start_date: start_date, old_data: { })
+      end
+
+      private
+
+      def fetch_object_analytics(logger, ga_conn)
+        @logger = logger
+        @ga_conn = ga_conn
+
+        aggregated_results = Hash.new
+        max_results = 10000
+
+        start_index = 0
+        loop do
+          response = @ga_conn.run_request(
+            date_ranges: [[@start_date, Date.parse(GA4_START_DATE)].max.to_s, Date.today.to_s],
+            metrics: ['screenPageViews'],
+            dimensions: %w[pagePathPlusQueryString],
+            order_bys: %w[screenPageViews],
+            dimension_filter: [],
+            offset: start_index,
+            limit: max_results
+          )
+
+          response.rows ||= []
+          num_results = response.rows.length
+          @logger.info "Results: #{num_results}, Start Index: #{start_index}"
+          @logger.flush
+          start_index += max_results
+          results = []
+          aggregated_results = {}
+          response.rows.each do |row|
+            row_h = row.to_h
+            year_month_hits = row_h[:dimension_values].map{ |x| x[:value] } + [row_h[:metric_values].first[:value]]
+            results << year_month_hits
+            page_count = year_month_hits[1].to_i
+            page_path = year_month_hits[0]
+            page_path = year_month_hits[0].chop  if page_path.end_with?('/') && !page_path.eql?('/')
+            if page_count >= 10
+              old_page_count = aggregated_results[page_path] || 0
+              aggregated_results[page_path] = old_page_count + page_count
+            end
+          end
+
+          break if num_results < max_results
+        end
+        {"all_pages" => aggregated_results }
+      end
+
+      def fetch_ua_object_analytics(logger, ua_conn)
+        {"all_pages" => {} } # we fetch only the current month views UA is at least 6 month past
+      end
+    end
+  end
+end
+

From 080629e5a0a0098bb0021260e07b7bc59d2a6735 Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Wed, 27 Dec 2023 15:22:59 +0100
Subject: [PATCH 61/62] extract google analytics UA import code to a script to
 make current code clean of it

---
 Gemfile                                       |   2 +-
 bin/import_google_ua_analytics_data           | 235 ++++++++++++++++++
 bin/ncbo_ontology_analytics_rebuild           |   8 +-
 config/config.rb.sample                       |   5 +-
 lib/ncbo_cron/analytics/object_analytics.rb   | 128 +++-------
 .../analytics/object_analytics_job.rb         |  25 +-
 .../analytics/ontology_visits_analytics.rb    |  46 ----
 .../analytics/page_visits_analytics.rb        |   7 +-
 .../analytics/user_visits_analytics.rb        |  36 ---
 9 files changed, 283 insertions(+), 209 deletions(-)
 create mode 100755 bin/import_google_ua_analytics_data

diff --git a/Gemfile b/Gemfile
index 1d7413db..54646cf4 100644
--- a/Gemfile
+++ b/Gemfile
@@ -5,7 +5,7 @@ gemspec
 gem 'ffi'
 
 # This is needed temporarily to pull the Google Universal Analytics (UA)
-# data and store it in a file. See (bin/generate_ua_analytics_file.rb)
+# data and store it in a file. See (bin/import_google_ua_analytics_data)
 # The ability to pull this data from Google will cease on July 1, 2024
 gem "google-apis-analytics_v3"
 
diff --git a/bin/import_google_ua_analytics_data b/bin/import_google_ua_analytics_data
new file mode 100755
index 00000000..eadfd936
--- /dev/null
+++ b/bin/import_google_ua_analytics_data
@@ -0,0 +1,235 @@
+#!/usr/bin/env ruby
+require 'logger'
+require 'optparse'
+require 'google/apis/analytics_v3'
+require 'google/api_client/auth/key_utils'
+require_relative '../lib/ncbo_cron/analytics/object_analytics_job'
+
+module NcboCron
+  module Models
+
+    class OntologyVisitsAnalytics
+      def fetch_ua_object_analytics(logger, ua_conn)
+        @logger = logger
+        @ua_conn = ua_conn
+        aggregated_results = Hash.new
+        start_year = @start_date.year || 2013
+        filter_str = (@analytics_filter.nil? || @analytics_filter.empty?) ? "" : ";#{@analytics_filter}"
+
+        @ont_acronyms.each do |acronym|
+          max_results = 10000
+          start_index = 1
+          loop do
+            results = @ua_conn.run_request(
+              metrics: ['pageviews'],
+              dimensions: %w[pagePath year month],
+              filters: [['pagePath', "~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}"]],
+              start_index: start_index,
+              max_results: max_results,
+              dates_ranges: [@start_date, Date.today.to_s],
+              sort: %w[year month]
+            )
+            results.rows ||= []
+            start_index += max_results
+            num_results = results.rows.length
+            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
+            aggregated_results[acronym] = Hash.new unless aggregated_results.has_key?(acronym)
+            aggregate_results(aggregated_results[acronym], results.rows)
+
+            if num_results < max_results
+              # fill up non existent years
+              (start_year..Date.today.year).each do |y|
+                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
+                aggregated_results[acronym][y.to_s] = Hash.new unless aggregated_results[acronym].has_key?(y.to_s)
+              end
+              # fill up non existent months with zeros
+              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+              break
+            end
+          end
+        end
+        sort_ga_data(aggregated_results)
+      end
+    end
+
+    class UsersVisitsAnalytics
+      def fetch_ua_object_analytics(logger, ua_conn)
+
+        aggregated_results = Hash.new
+        start_year = @start_date.year || 2013
+
+        max_results = 10000
+        start_index = 1
+        loop do
+          results = ua_conn.run_request(
+            metrics: ['newUsers'],
+            dimensions: %w[year month],
+            filters: [],
+            start_index: start_index,
+            max_results: max_results,
+            dates_ranges: [@start_date.to_s, Date.today.to_s],
+            sort: %w[year month]
+          )
+          results.rows ||= []
+          start_index += max_results
+          num_results = results.rows.length
+          logger.info "Results: #{num_results}, Start Index: #{start_index}"
+
+          aggregate_results(aggregated_results, results.rows.map { |row| [-1] + row })
+
+          if num_results < max_results
+            # fill up non existent years
+            (start_year..Date.today.year).each do |y|
+              aggregated_results = Hash.new if aggregated_results.nil?
+              aggregated_results[y.to_s] = Hash.new unless aggregated_results.has_key?(y.to_s)
+            end
+            # fill up non existent months with zeros
+            (1..12).each { |n| aggregated_results.values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
+            break
+          end
+        end
+        { "all_users" => aggregated_results }
+      end
+    end
+  end
+  module GoogleAnalyticsUAMigrator
+    # Old version of Google Analytics connector
+    class GoogleAnalyticsUAConnector
+      def initialize(app_id:, app_name:, app_version:, analytics_key_file:, app_user:, start_date:, analytics_filter:)
+        @app_id = app_id
+        @app_name = app_name
+        @app_version = app_version
+        @analytics_key_file = analytics_key_file
+        @app_user = app_user
+        @generated_file_path = NcboCron.settings.analytics_path_to_ga_data_file
+        @start_date = start_date
+        @analytics_filter = analytics_filter
+        @ga_client = authenticate_google
+      end
+
+      def run_request(metrics:, dimensions:, filters:, start_index:, max_results:, dates_ranges:, sort:)
+        @ga_client.get_ga_data(
+          ids = @app_id,
+          start_date = dates_ranges.first,
+          end_date = dates_ranges.last,
+          metrics = metrics.map { |m| "ga:#{m}" }.join(','),
+          {
+            dimensions: dimensions.map { |d| "ga:#{d}" }.join(','),
+            filters: filters.empty? ? nil : filters.map { |f, v| "ga:#{f}=#{v}" }.join(','),
+            start_index: start_index,
+            max_results: max_results,
+            sort: sort.map { |d| "ga:#{d}" }.join(',')
+          }
+        )
+      end
+
+      private
+
+      def authenticate_google
+        Google::Apis::ClientOptions.default.application_name = @app_name
+        Google::Apis::ClientOptions.default.application_version = @app_version
+        # enable google api call retries in order to
+        # minigate analytics processing failure due to occasional google api timeouts and other outages
+        Google::Apis::RequestOptions.default.retries = 5
+        # uncoment to enable logging for debugging purposes
+        # Google::Apis.logger.level = Logger::DEBUG
+        # Google::Apis.logger = @logger
+        client = Google::Apis::AnalyticsV3::AnalyticsService.new
+        key = Google::APIClient::KeyUtils::load_from_pkcs12(@analytics_key_file, 'notasecret')
+        client.authorization = Signet::OAuth2::Client.new(
+          :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
+          :audience => 'https://accounts.google.com/o/oauth2/token',
+          :scope => 'https://www.googleapis.com/auth/analytics.readonly',
+          :issuer => @app_user,
+          :signing_key => key
+        ).tap { |auth| auth.fetch_access_token! }
+        client
+      end
+    end
+
+    def self.run(logger, options)
+      @start_date = options[:start_date]
+      @ua_conn = GoogleAnalyticsUAConnector.new(options)
+
+      logger.info "Fetching UA analytics for all ontologies from #{@start_date} to today..."
+      save = {}
+      analytics_to_migrate = [NcboCron::Models::OntologyVisitsAnalytics,
+                              NcboCron::Models::UsersVisitsAnalytics]
+      analytics_to_migrate.each do |analytic_object|
+        analytic_object = analytic_object.new(start_date: @start_date)
+        ua_data = analytic_object.fetch_ua_object_analytics(logger, @ua_conn)
+        save[analytic_object.redis_field] = ua_data
+      end
+      new_ga_start_date = NcboCron::Models::ObjectAnalytics::GA4_START_DATE
+      NcboCron::Models::ObjectAnalyticsJob.new(logger).send(:save_data_in_file, save, new_ga_start_date)
+      logger.info "Completed Universal Analytics pull..."
+      logger.close
+    end
+  end
+end
+require 'bundler/setup'
+require_relative '../lib/ncbo_cron'
+require_relative '../config/config'
+
+
+# # Google Analytics UA config
+options = {
+  app_id: nil,
+  app_name: nil,
+  app_version: nil,
+  analytics_key_file: nil,
+  app_user: nil,
+  start_date: nil,
+  analytics_filter: nil,
+  logfile: nil
+}
+
+help_text = <<EOS
+If you have existing Google Analytics UA data that you have been collecting till end 2023,
+you can import it from Google (available till July 1st, 2024) so it’s merged with
+your Google Analytics Data (GA4) data and displayed in OntoPortal.
+  
+This script needs to be run ONLY ONCE, and the imported data will be used by your Google Analytics
+CRON job to merge the 'old' data with the new data from GA4.
+EOS
+
+opt = OptionParser.new do |opts|
+  opts.banner = "Usage: #{File.basename($PROGRAM_NAME)} [options]\n #{help_text}"
+  opts.on('--app-id APP_ID', 'Application ID') { |v| options[:app_id] = v }
+  opts.on('--app-name APP_NAME', 'Application Name') { |v| options[:app_name] = v }
+  opts.on('--app-version APP_VERSION', 'Application Version') { |v| options[:app_version] = v }
+  opts.on('--analytics-key-file KEY_FILE', 'Path to Analytics Key File') { |v| options[:analytics_key_file] = v }
+  opts.on('--app-user APP_USER', 'Application User') { |v| options[:app_user] = v }
+  opts.on('--start-date START_DATE', 'Start Date') { |v| options[:start_date] = v }
+  opts.on('--analytics-filter FILTER', 'Analytics Filter String') { |v| options[:analytics_filter] = v }
+  opts.on('--logfile LOGFILE', 'Path to Log File') { |v| options[:logfile] = v }
+  opts.on_tail('-h', '--help', 'Show this help message') do
+    puts opts
+    exit
+  end
+end
+
+begin
+  opt.parse!
+rescue OptionParser::MissingArgument, OptionParser::InvalidOption
+  puts "Error: #{$!}"
+  puts opt
+  exit(1)
+end
+
+# Validate required options
+required_options = %i[app_id app_name app_version analytics_key_file app_user start_date analytics_filter]
+missing_options = required_options.select { |opt| options[opt].nil? }
+
+if missing_options.any?
+  puts "Missing required options: #{missing_options.join(', ')}"
+  puts opt
+  exit(1)
+end
+
+# Create a logger that writes to the specified logfile or STDOUT if not provided
+logfile = options.delete(:logfile) || STDOUT
+stdout_logger = Logger.new(logfile)
+
+# Run the migration with the specified logger and options
+NcboCron::GoogleAnalyticsUAMigrator.run(stdout_logger, options)
\ No newline at end of file
diff --git a/bin/ncbo_ontology_analytics_rebuild b/bin/ncbo_ontology_analytics_rebuild
index b37b8138..c20ccfe4 100755
--- a/bin/ncbo_ontology_analytics_rebuild
+++ b/bin/ncbo_ontology_analytics_rebuild
@@ -51,12 +51,8 @@ begin
   puts msg
   logger.info(msg)
 
-  time = Benchmark.realtime do
-    NcboCron::Models::ObjectAnalyticsJob.new(logger).run
-  end
-  msg = "Completed rebuilding ontology analytics repository in #{(time/60).round(1)} minutes."
-  puts msg
-  logger.info(msg)
+  NcboCron::Models::ObjectAnalyticsJob.new(logger).run
+
 rescue Exception => e
   msg = "Failed rebuilding ontology analytics repository with exception: #{e.class}: #{e.message}\n#{e.backtrace.join("\n")}"
   logger.error(msg)
diff --git a/config/config.rb.sample b/config/config.rb.sample
index 79ce75de..10cf7e90 100644
--- a/config/config.rb.sample
+++ b/config/config.rb.sample
@@ -79,12 +79,11 @@ NcboCron.config do |config|
   # Google Analytics GA4 config
   config.analytics_path_to_key_file     = "config/your_analytics_key.json"
   config.analytics_property_id          = "123456789"
-  # path to the Universal Analytics data, which stopped collecting on June 1st, 2023
-  config.analytics_path_to_ua_data_file = "data/your_ua_data.json"
+
   # path to the file that will hold your Google Analytics data
   # this is in addition to storing it in Redis
   config.analytics_path_to_ga_data_file = "data/your_ga_data.json"
-
+  config.analytics_start_date                    = '2015-01-01'
   # this is a Base64.encode64 encoded personal access token
   # you need to run Base64.decode64 on it before using it in your code
   # this is a workaround because Github does not allow storing access tokens in a repo
diff --git a/lib/ncbo_cron/analytics/object_analytics.rb b/lib/ncbo_cron/analytics/object_analytics.rb
index f5275f82..d4a7f3da 100644
--- a/lib/ncbo_cron/analytics/object_analytics.rb
+++ b/lib/ncbo_cron/analytics/object_analytics.rb
@@ -7,16 +7,14 @@
 
 module NcboCron
   module Models
-    UA_START_DATE = '2013-10-01'
-    GA4_START_DATE = '2023-06-01'
+
+
 
     class GoogleAnalyticsConnector
 
       attr_reader :ga_client
 
       def initialize
-        @ga_data_file = NcboCron.settings.analytics_path_to_ga_data_file
-        @ua_data_file = NcboCron.settings.analytics_path_to_ua_data_file
         @app_id = NcboCron.settings.analytics_property_id
         @app_key_file = NcboCron.settings.analytics_path_to_key_file
         @ga_client = analytics_data_client
@@ -89,63 +87,8 @@ def ga_order_by(dimension_name, desc = false)
 
     end
 
-    # Old version of Google Analytics
-    class GoogleAnalyticsUAConnector
-      def initialize
-        @app_id = NcboCron.settings.analytics_profile_id
-        @app_name = NcboCron.settings.analytics_app_name
-        @app_version = NcboCron.settings.analytics_app_version
-        @analytics_key_file = NcboCron.settings.ua_analytics_path_to_key_file
-        @app_user = NcboCron.settings.analytics_service_account_email_address
-        @generated_file_path = NcboCron.settings.analytics_path_to_ua_data_file
-        @start_date = NcboCron.settings.analytics_start_date
-        @analytics_filter = NcboCron.settings.analytics_filter_str
-        @ga_client = authenticate_google
-      end
-
-      def run_request(metrics:, dimensions:, filters:, start_index:, max_results:, dates_ranges:, sort:)
-        @ga_client.get_ga_data(
-          ids = @app_id,
-          start_date = dates_ranges.first,
-          end_date = dates_ranges.last,
-          metrics = metrics.map { |m| "ga:#{m}" }.join(','),
-          {
-            dimensions: dimensions.map { |d| "ga:#{d}" }.join(','),
-            filters: filters.empty? ? nil : filters.map { |f, v| "ga:#{f}=#{v}" }.join(','),
-            start_index: start_index,
-            max_results: max_results,
-            sort: sort.map { |d| "ga:#{d}" }.join(',')
-          }
-        )
-      end
-
-      private
-
-      def authenticate_google
-        Google::Apis::ClientOptions.default.application_name = @app_name
-        Google::Apis::ClientOptions.default.application_version = @app_version
-        # enable google api call retries in order to
-        # minigate analytics processing failure due to occasional google api timeouts and other outages
-        Google::Apis::RequestOptions.default.retries = 5
-        # uncoment to enable logging for debugging purposes
-        # Google::Apis.logger.level = Logger::DEBUG
-        # Google::Apis.logger = @logger
-        client = Google::Apis::AnalyticsV3::AnalyticsService.new
-        key = Google::APIClient::KeyUtils::load_from_pkcs12(@analytics_key_file, 'notasecret')
-        client.authorization = Signet::OAuth2::Client.new(
-          :token_credential_uri => 'https://accounts.google.com/o/oauth2/token',
-          :audience => 'https://accounts.google.com/o/oauth2/token',
-          :scope => 'https://www.googleapis.com/auth/analytics.readonly',
-          :issuer => @app_user,
-          :signing_key => key
-        ).tap { |auth| auth.fetch_access_token! }
-        client
-      end
-
-    end
-
     class ObjectAnalytics
-
+      GA4_START_DATE = '2023-06-01'
       attr_reader :redis_field
 
       def initialize(redis_field:, start_date:, old_data: {})
@@ -154,21 +97,12 @@ def initialize(redis_field:, start_date:, old_data: {})
         @old_data = old_data[@redis_field] || {}
       end
 
-      def full_data(logger, ga_conn, ua_conn)
+      def full_data(logger, ga_conn)
 
-        logger.info "Fetching GA4 analytics for all ontologies from #{@start_date} to today..."
+        logger.info "Fetching GA4 analytics for #{@redis_field} from #{@start_date} to today..."
         logger.flush
         new_ga_data = fetch_object_analytics(logger, ga_conn)
 
-        if @start_date < Date.parse(GA4_START_DATE)
-          @old_data = {}
-          logger.info "Fetching UA analytics for all ontologies from #{@start_date} to today..."
-          logger.flush
-          ua_data = fetch_ua_object_analytics(logger, ua_conn)
-          logger.info "Completed Universal Analytics pull..."
-          logger.flush
-          new_ga_data = merge_and_fill_missing_data(new_ga_data, ua_data, logger)
-        end
         merge_and_fill_missing_data(new_ga_data, @old_data, logger)
       end
 
@@ -177,47 +111,41 @@ def fetch_object_analytics(logger, ga_conn)
         raise NotImplementedError, "Subclasses must implement this method"
       end
 
-      # @param ua_conn GoogleAnalyticsUAConnector
-      def fetch_ua_object_analytics(logger, ua_conn)
-        raise NotImplementedError, "Subclasses must implement this method"
-      end
-
       private
 
       def merge_and_fill_missing_data(new_data, old_data,logger, start_date = @start_date)
-        if !old_data.empty?
-          logger.info "Merging GA4 and UA data..."
+        if !new_data.empty?
+          logger.info "Merging old Google Analytics and the new data..."
           logger.flush
-          old_data.keys.each do |acronym|
-            (start_date.year..Date.today.year).each do |year|
-              year = year.to_s
-              # add up hits for June of 2023 (the only intersecting month between UA and GA4)
-              if old_data[acronym].has_key?(year)
-                next unless new_data[acronym].has_key?(year)
-
-                (1..Date.today.month).each do |month|
-                  month = month.to_s
-                  old_data[acronym][year][month] ||= 0
-                  unless old_data[acronym][year][month].eql?(new_data[acronym][year][month])
-                    old_data[acronym][year][month] += (new_data[acronym][year][month] || 0)
+          new_data.keys.each do |acronym|
+            if old_data.has_key?(acronym)
+              (start_date.year..Date.today.year).each do |year|
+                year = year.to_s
+                if new_data[acronym].has_key?(year)
+                  if old_data[acronym].has_key?(year)
+                    (1..Date.today.month).each do |month|
+                      month = month.to_s
+                      old_data[acronym][year][month] ||= 0
+                      unless old_data[acronym][year][month].eql?(new_data[acronym][year][month])
+                        old_data[acronym][year][month] += (new_data[acronym][year][month] || 0)
+                      end
+                    end
+                  else
+                    old_data[acronym][year] = new_data[acronym][year]
                   end
                 end
-
-              elsif new_data[acronym][year]
-                old_data[acronym][year] = new_data[acronym][year]
               end
+            else
+              old_data[acronym]= new_data[acronym]
             end
           end
+          # fill missing years and months
+          logger.info "Filling in missing years data..."
           old_data = fill_missing_data(old_data)
-        else
-          old_data = new_data
         end
 
-        # fill missing years and months
-        logger.info "Filling in missing years data..."
-        logger.flush
-        old_data
         # sort_ga_data(old_data)
+        old_data
       end
 
       def aggregate_results(aggregated_results, results)
@@ -244,7 +172,7 @@ def aggregate_results(aggregated_results, results)
 
       def fill_missing_data(ga_data)
         # fill up non existent years
-        start_year = Date.parse(UA_START_DATE).year
+        start_year = @start_date.year
 
         ga_data.each do |acronym, _|
           (start_year..Date.today.year).each do |y|
diff --git a/lib/ncbo_cron/analytics/object_analytics_job.rb b/lib/ncbo_cron/analytics/object_analytics_job.rb
index af2e2885..8133aeb0 100644
--- a/lib/ncbo_cron/analytics/object_analytics_job.rb
+++ b/lib/ncbo_cron/analytics/object_analytics_job.rb
@@ -17,14 +17,12 @@ def initialize(logger)
         @redis_port = LinkedData.settings.ontology_analytics_redis_port
 
         @data_file =  NcboCron.settings.analytics_path_to_ga_data_file
-        @ua_data_file = NcboCron.settings.analytics_path_to_ua_data_file
 
-        @ga_conn = GoogleAnalyticsConnector.new
-        @ua_conn = GoogleAnalyticsUAConnector.new
+
 
         @logger = logger
         @logger.info "Authenticating with the Google Analytics Endpoint..."
-        @logger.flush
+        @ga_conn = GoogleAnalyticsConnector.new
 
         @analytics_objects = [
           NcboCron::Models::OntologyVisitsAnalytics,
@@ -33,23 +31,22 @@ def initialize(logger)
         ]
       end
 
-      # @param analytics_objects ObjectAnalytics[]
       def run
         redis = Redis.new(:host => @redis_host, :port => @redis_port)
         @logger.info "Starting Google Analytics refresh..."
-        @logger.flush
         time = Benchmark.realtime do
-          @logger.info "Fetching all ontology acronyms from backend..."
-          @logger.flush
+          @logger.info "Fetching saved analytics data..."
           save = {}
           @old_data = read_old_data
           @analytics_objects.each do |analytic_object|
             analytic_object = analytic_object.new(start_date: detect_latest_date, old_data: @old_data)
-            new_data = analytic_object.full_data(@logger, @ga_conn, @ua_conn)
+            @logger.info "Start fetching new #{analytic_object.redis_field}  data..."
+            new_data = analytic_object.full_data(@logger, @ga_conn)
             save[analytic_object.redis_field] = new_data
             redis.set(analytic_object.redis_field, Marshal.dump(new_data))
+            @logger.info "Completed fetching #{analytic_object.redis_field}  data..."
           end
-          save_data(save)
+          save_data_in_file(save)
         end
         @logger.info "Completed Google Analytics refresh in #{(time / 60).round(1)} minutes."
         @logger.flush
@@ -72,12 +69,12 @@ def detect_latest_date
 
       end
 
-      def save_data(new_data)
-        new_data["latest_date_save"] =  Date.today.to_s
+      def save_data_in_file(new_data, saved_date =  Date.today.to_s, data_file =  @data_file)
+        new_data["latest_date_save"] =  saved_date
         # Ensure the directory exists before creating the file
-        FileUtils.mkdir_p(File.dirname(@data_file))
+        FileUtils.mkdir_p(File.dirname(data_file))
         # Open the file with 'w+' mode to create if not exist and write
-        File.open(@data_file, 'w+') do |f|
+        File.open(data_file, 'w+') do |f|
           f.write(new_data.to_json)
         end
       end
diff --git a/lib/ncbo_cron/analytics/ontology_visits_analytics.rb b/lib/ncbo_cron/analytics/ontology_visits_analytics.rb
index 6aa64e79..41d6edfd 100644
--- a/lib/ncbo_cron/analytics/ontology_visits_analytics.rb
+++ b/lib/ncbo_cron/analytics/ontology_visits_analytics.rb
@@ -13,51 +13,6 @@ class OntologyVisitsAnalytics < ObjectAnalytics
       def initialize(start_date: , old_data: {})
         super(redis_field: ONTOLOGY_ANALYTICS_REDIS_FIELD, start_date: start_date, old_data: old_data)
         @ont_acronyms = LinkedData::Models::Ontology.where.include(:acronym).all.map { |o| o.acronym }
-        @ont_acronyms = ['AGROVOC', 'E-PHY', 'CROPUSAGE']
-      end
-
-
-      def fetch_ua_object_analytics(logger, ua_conn)
-        @logger = logger
-        @ua_conn =  ua_conn
-        aggregated_results = Hash.new
-        start_year = Date.parse(UA_START_DATE).year || 2013
-        filter_str = (@analytics_filter.nil? || @analytics_filter.empty?) ? "" : ";#{@analytics_filter}"
-
-        @ont_acronyms.each do |acronym|
-          max_results = 10000
-          start_index = 1
-          loop do
-            results = @ua_conn.run_request(
-              metrics: ['pageviews'],
-              dimensions: %w[pagePath year month],
-              filters: [['pagePath', "~^(\\/ontologies\\/#{acronym})(\\/?\\?{0}|\\/?\\?{1}.*)$#{filter_str}"]],
-              start_index: start_index,
-              max_results: max_results,
-              dates_ranges: [UA_START_DATE, Date.today.to_s],
-              sort: %w[year month]
-            )
-            results.rows ||= []
-            start_index += max_results
-            num_results = results.rows.length
-            @logger.info "Acronym: #{acronym}, Results: #{num_results}, Start Index: #{start_index}"
-            @logger.flush
-            aggregated_results[acronym] = Hash.new unless aggregated_results.has_key?(acronym)
-            aggregate_results(aggregated_results[acronym], results.rows)
-
-            if num_results < max_results
-              # fill up non existent years
-              (start_year..Date.today.year).each do |y|
-                aggregated_results[acronym] = Hash.new if aggregated_results[acronym].nil?
-                aggregated_results[acronym][y.to_s] = Hash.new unless aggregated_results[acronym].has_key?(y.to_s)
-              end
-              # fill up non existent months with zeros
-              (1..12).each { |n| aggregated_results[acronym].values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
-              break
-            end
-          end
-        end
-        sort_ga_data(aggregated_results)
       end
 
       def fetch_object_analytics(logger, ga_conn)
@@ -103,7 +58,6 @@ def fetch_object_analytics(logger, ga_conn)
         end
         aggregated_results
       end
-
     end
 
   end
diff --git a/lib/ncbo_cron/analytics/page_visits_analytics.rb b/lib/ncbo_cron/analytics/page_visits_analytics.rb
index 8ecd21c0..b2354c00 100644
--- a/lib/ncbo_cron/analytics/page_visits_analytics.rb
+++ b/lib/ncbo_cron/analytics/page_visits_analytics.rb
@@ -7,7 +7,7 @@ module NcboCron
   module Models
     class PageVisitsAnalytics < ObjectAnalytics
       def initialize(start_date: Date.today.prev_month, old_data: {})
-        super(redis_field: 'pages_analytics', start_date: start_date, old_data: { })
+        super(redis_field: 'pages_analytics', start_date: Date.today.prev_month, old_data: { })
       end
 
       private
@@ -56,8 +56,9 @@ def fetch_object_analytics(logger, ga_conn)
         {"all_pages" => aggregated_results }
       end
 
-      def fetch_ua_object_analytics(logger, ua_conn)
-        {"all_pages" => {} } # we fetch only the current month views UA is at least 6 month past
+      # we don't the missing data in this case
+      def fill_missing_data(ga_data)
+        ga_data
       end
     end
   end
diff --git a/lib/ncbo_cron/analytics/user_visits_analytics.rb b/lib/ncbo_cron/analytics/user_visits_analytics.rb
index 793bf0ca..9b2b6631 100644
--- a/lib/ncbo_cron/analytics/user_visits_analytics.rb
+++ b/lib/ncbo_cron/analytics/user_visits_analytics.rb
@@ -51,43 +51,7 @@ def fetch_object_analytics(logger, ga_conn)
         {"all_users" => aggregated_results}
       end
 
-      def fetch_ua_object_analytics(logger, ua_conn)
 
-        aggregated_results = Hash.new
-        start_year = Date.parse(UA_START_DATE).year || 2013
-
-        max_results = 10000
-        start_index = 1
-        loop do
-          results = ua_conn.run_request(
-            metrics: ['newUsers'],
-            dimensions: %w[year month],
-            filters: [],
-            start_index: start_index,
-            max_results: max_results,
-            dates_ranges: [UA_START_DATE, Date.today.to_s],
-            sort: %w[year month]
-          )
-          results.rows ||= []
-          start_index += max_results
-          num_results = results.rows.length
-          logger.info "Results: #{num_results}, Start Index: #{start_index}"
-          logger.flush
-          aggregate_results(aggregated_results, results.rows.map{|row| [-1] + row})
-
-          if num_results < max_results
-            # fill up non existent years
-            (start_year..Date.today.year).each do |y|
-              aggregated_results = Hash.new if aggregated_results.nil?
-              aggregated_results[y.to_s] = Hash.new unless aggregated_results.has_key?(y.to_s)
-            end
-            # fill up non existent months with zeros
-            (1..12).each { |n| aggregated_results.values.each { |v| v[n.to_s] = 0 unless v.has_key?(n.to_s) } }
-            break
-          end
-        end
-        { "all_users" => aggregated_results}
-      end
     end
   end
 end

From 1154c7c8e621bb0edecaa55404f0daa2bae887f4 Mon Sep 17 00:00:00 2001
From: Syphax Bouazzouni <gs_bouazzouni@esi.dz>
Date: Wed, 27 Dec 2023 18:00:46 +0100
Subject: [PATCH 62/62] add option to force submission archiving even if
 already archived

---
 bin/ncbo_ontology_archive_old_submissions | 13 +++++++++----
 lib/ncbo_cron/ontology_helper.rb          |  1 +
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/bin/ncbo_ontology_archive_old_submissions b/bin/ncbo_ontology_archive_old_submissions
index 1b2268a5..34fe073c 100755
--- a/bin/ncbo_ontology_archive_old_submissions
+++ b/bin/ncbo_ontology_archive_old_submissions
@@ -13,11 +13,15 @@ abort("Please create a config/config.rb file using the config/config.rb.sample a
 require_relative '../config/config'
 require 'optparse'
 
-options = { delete: false }
+options = { delete: false , force_archiving: false}
 opt_parser = OptionParser.new do |opts|
   # Set a banner, displayed at the top of the help screen.
   opts.banner = "Usage: #{File.basename(__FILE__)} [options]"
 
+  opts.on('-f', '--force-re-archiving', 'Force to re-archive already archived submissions.') do
+    options[:force_archiving] = true
+  end
+
   options[:logfile] = STDOUT
   opts.on( '-l', '--logfile FILE', "Write log to FILE (default is STDOUT)" ) do |filename|
     options[:logfile] = filename
@@ -40,12 +44,12 @@ logfile = options[:logfile]
 if File.file?(logfile); File.delete(logfile); end
 logger = Logger.new(logfile)
 process_actions = { process_rdf: false, generate_labels: false, index_search: false, index_commit: false,
-            process_annotator: false, diff: false, run_metrics: false, archive: true }
+                    process_annotator: false, diff: false, run_metrics: false, archive: true }
 onts = LinkedData::Models::Ontology.all
 onts.each { |ont| ont.bring(:acronym, :submissions) }
 onts.sort! { |a, b| a.acronym <=> b.acronym }
 bad_submissions = {}
-
+force_archiving = options[:force_archiving]
 onts.each do |ont|
   latest_sub = ont.latest_submission
 
@@ -73,7 +77,7 @@ onts.each do |ont|
     }
     old_subs.sort! { |a, b| a.submissionId <=> b.submissionId }
     old_subs.each do |sub|
-      unless sub.archived?
+      unless sub.archived? || force_archiving
         msg = "#{ont.acronym}: found un-archived old submission with ID #{sub.submissionId}."
         puts msg
         logger.info msg
@@ -119,6 +123,7 @@ onts.each do |ont|
   end
 end
 
+
 puts
 
 if bad_submissions.empty?
diff --git a/lib/ncbo_cron/ontology_helper.rb b/lib/ncbo_cron/ontology_helper.rb
index 42534768..4d1f0716 100644
--- a/lib/ncbo_cron/ontology_helper.rb
+++ b/lib/ncbo_cron/ontology_helper.rb
@@ -9,6 +9,7 @@ module OntologyHelper
       PROCESS_ACTIONS = {
         :process_rdf => true,
         :generate_labels => true,
+        :extract_metadata => true,
         :index_search => true,
         :index_properties => true,
         :run_metrics => true,