Skip to content

Commit

Permalink
Solr jump-start config-set change
Browse files Browse the repository at this point in the history
  • Loading branch information
actions-user committed Apr 22, 2024
1 parent 0357aba commit 7960429
Show file tree
Hide file tree
Showing 68 changed files with 2,472 additions and 4 deletions.
185 changes: 185 additions & 0 deletions jump-start/solr6/cloud-config-set/accents_cy.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,185 @@
# À => A
"\u00C0" => "A"
# Á => A
"\u00C1" => "A"
# Â => A
"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Ą => A
"\u0104" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
"\u00C7" => "C"
# Ć => C
"\U0106" => "C"
# È => E
"\u00C8" => "E"
# É => E
"\u00C9" => "E"
# Ê => E
"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ę => E
"\u0118" => "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"
# Ł => L
"\u0141" => "L"
# Ñ => N
"\u00D1" => "N"
# Ń => N
"\u0143" => "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"
# Œ => 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"
# Ś => S
"\u015a" => "S"
# 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"
# Ź => Z
"\u0179" => "Z"
# Ż => Z
"\u017b" => "Z"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => st
"\uFB05" => "st"
# st => st
"\uFB06" => "st"
# Māori macrons.
# Ā => A
"\u0100" => "A"
# Ē => E
"\u0112" => "E"
# Ī => I
"\u012A" => "I"
# Ō => O
"\u014C" => "O"
# Ū => U
"\u016A" => "U"
# ā => a
"\u0101" => "a"
# ē => e
"\u0113" => "e"
# ī => i
"\u012B" => "i"
# ō => o
"\u014D" => "o"
# ū => u
"\u016B" => "u"
Empty file.
Empty file.
7 changes: 7 additions & 0 deletions jump-start/solr6/cloud-config-set/schema_extra_fields.xml
Original file line number Diff line number Diff line change
Expand Up @@ -180,3 +180,10 @@
<dynamicField name="tus_X3b_uk_*" type="text_unstemmed_uk" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tum_X3b_uk_*" type="text_unstemmed_uk" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="sort_X3b_uk_*" type="collated_uk" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
<dynamicField name="ts_X3b_cy_*" type="text_cy" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tm_X3b_cy_*" type="text_cy" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="tos_X3b_cy_*" type="text_cy" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
<dynamicField name="tom_X3b_cy_*" type="text_cy" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
<dynamicField name="tus_X3b_cy_*" type="text_unstemmed_cy" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
<dynamicField name="tum_X3b_cy_*" type="text_unstemmed_cy" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
<dynamicField name="sort_X3b_cy_*" type="collated_cy" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
53 changes: 53 additions & 0 deletions jump-start/solr6/cloud-config-set/schema_extra_types.xml
Original file line number Diff line number Diff line change
Expand Up @@ -929,3 +929,56 @@
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Welsh Text Field
6.0.0
-->
<fieldType name="text_cy" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_cy.txt"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_cy.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cy.txt"/>
<filter class="solr.SnowballPorterFilterFactory" language="Spanish" protected="protwords_cy.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_cy.txt"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_cy.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_cy.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cy.txt"/>
<filter class="solr.SnowballPorterFilterFactory" language="Spanish" protected="protwords_cy.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!--
Welsh Text Field collated
6.0.0
-->
<fieldType name="collated_cy" class="solr.ICUCollationField" locale="cy" strength="primary" caseLevel="false"/>
<!--
Welsh Text Field unstemmed
6.0.0
-->
<fieldType name="text_unstemmed_cy" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_cy.txt"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_cy.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cy.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="accents_cy.txt"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_cy.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_cy.txt" expand="true" ignoreCase="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cy.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
26 changes: 26 additions & 0 deletions jump-start/solr6/cloud-config-set/solrconfig_extra.xml
Original file line number Diff line number Diff line change
Expand Up @@ -237,6 +237,21 @@
<str name="thresholdTokenFrequency">.01</str>
<str name="onlyMorePopular">true</str>
</lst>

<lst name="spellchecker">
<str name="name">cy</str>
<str name="field">spellcheck_cy</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">internal</str>
<str name="accuracy">0.5</str>
<str name="maxEdits">2</str>
<str name="minPrefix">1</str>
<str name="maxInspections">5</str>
<str name="minQueryLength">4</str>
<str name="maxQueryFrequency">0.01</str>
<str name="thresholdTokenFrequency">.01</str>
<str name="onlyMorePopular">true</str>
</lst>
</searchComponent>
<searchComponent name="suggest" class="solr.SuggestComponent">
<lst name="suggester">
Expand Down Expand Up @@ -418,5 +433,16 @@
<str name="buildOnCommit">false</str>
<str name="buildOnStartup">false</str>
</lst>

<lst name="suggester">
<str name="name">cy</str>
<str name="lookupImpl">AnalyzingInfixLookupFactory</str>
<str name="dictionaryImpl">DocumentDictionaryFactory</str>
<str name="field">twm_suggest</str>
<str name="suggestAnalyzerFieldType">text_cy</str>
<str name="contextField">sm_context_tags</str>
<str name="buildOnCommit">false</str>
<str name="buildOnStartup">false</str>
</lst>
</searchComponent>
<statsCache class="org.apache.solr.search.stats.LRUStatsCache" />
35 changes: 35 additions & 0 deletions jump-start/solr6/cloud-config-set/stopwords_cy.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
a
ac
ag
am
an
ar
at
canys
cyfryw
ddim
eu
fel
fod
gan
hyn
hynny
hwn
i
mae
mewn
na
nac
neu
nhw
o
oedd
ond
os
ym
ymlaen
yn
yna
yno
yng
yr
1 change: 1 addition & 0 deletions jump-start/solr6/cloud-config-set/synonyms_cy.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
drupal, durpal
Loading

0 comments on commit 7960429

Please sign in to comment.