cms-2016-pileup-dataset: add file information and fix usage links

Adds documentation, adds file information, fixes usage links and other
minor metadata information such as publishing year.

.gitignore

@@ -74,3 +74,8 @@ cms-2016-collision-datasets/inputs/hlt-config-store
 cms-2016-collision-datasets/inputs/das-json-store
 cms-2016-collision-datasets/inputs/das-json-config-store
 cms-2016-collision-datasets/outputs/*.json
+cms-2015-pileup-dataset/inputs/config-store
+cms-2015-pileup-dataset/inputs/das-json-store
+cms-2015-pileup-dataset/inputs/mcm-store
+cms-2015-pileup-dataset/outputs/
+cms-2015-pileup-dataset/cookies.txt

README.rst

@@ -50,6 +50,7 @@ Specific data ingestion and curation campaigns:
 - `cms-2015-collision-datasets-hi-ppref <cms-2015-collision-datasets-hi-ppref>`_ - helper scripts for CMS 2015 heavy ion release (proton-proton reference collision datasets)
 - `cms-2015-simulated-datasets <cms-2015-simulated-datasets>`_ -- helper scripts for the CMS 2015 open data release (simulated datasets)
 - `cms-2016-collision-datasets <cms-2016-collision-datasets>`_ -- helper scripts for the CMS 2016 open data release (collision datasets)
+- `cms-2016-pileup-dataset <cms-2016-pileup-dataset>`_ -- helper scripts for the CMS 2016 open data release (pileup dataset)
 - `cms-2016-simulated-datasets <cms-2016-simulated-datasets>`_ -- helper scripts for the CMS 2016 open data release (simulated datasets)
 - `cms-YYYY-luminosity <cms-YYYY-luminosity>`_ -- helper scripts for the CMS luminosity information records (any year)
 - `cms-YYYY-run-numbers <cms-YYYY-run-numbers>`_ -- helper scripts for enriching CMS dataset run numbers (any year)

cms-2016-pileup-dataset/README.md

@@ -0,0 +1,73 @@
+# cms-2016-pileup-dataset
+
+This directory contains helper scripts used to prepare CMS 2016 open data
+release regarding pile-up dataset.
+
+- `code/` folder contains the python code;
+- `inputs/` folder contains input text files with the list of datasets for each
+  year and input files;
+- `outputs/` folder contains generated JSON records to be included as the CERN
+  Open Data portal fixtures.
+
+Every step necessary to produce the final `*.json` files is handled by the
+`code/interface.py` script. Details about it can be queried with the command:
+
+```console
+$ python3 code/interface.py --help
+```
+
+Please make sure to get the VOMS proxy file before running these scripts:
+
+```console
+$ voms-proxy-init --voms cms --rfc --valid 190:00
+```
+
+Please make sure to set the EOS instance to EOSPUBLIC before running these scripts:
+
+```console
+$ export EOS_MGM_URL=root://eospublic.cern.ch
+```
+Please make sure to have a valid `userkey.nodes.pem` certificate present in
+`$HOME/.globus`. If not, you have to run the following on top of the regular
+CMS certificate documentation:
+
+```console
+$ cd $HOME/.globus
+$ ls userkey.nodes.pem
+$ openssl pkcs12 -in myCert.p12 -nocerts -nodes -out userkey.nodes.pem  # if not present
+$ cd -
+```
+
+First step is to create EOS file index cache:
+
+```console
+$ python3 ./code/interface.py --create-eos-indexes inputs/CMS-2016-premix.txt
+```
+
+This requires the index data files to be placed in their final location. However, for
+early testing on LXPLUS, all steps can be run without the EOS file index cache
+by means of adding the command-line option `--ignore-eos-store` to the commands below.
+
+We can now build sample records by doing:
+
+```console
+$ python3 ./code/interface.py --create-das-json-store --ignore-eos-store inputs/CMS-2016-pileup-dataset.txt
+
+$ auth-get-sso-cookie -u  https://cms-pdmv.cern.ch/mcm -o cookies.txt
+$ python3 ./code/interface.py --create-mcm-store --ignore-eos-store inputs/CMS-2016-pileup-dataset.txt
+
+$ python3 ./code/interface.py --get-conf-files --ignore-eos-store inputs/CMS-2016-pileup-dataset.txt
+
+$ python3 ./code/interface.py --create-records --ignore-eos-store inputs/CMS-2016-premix.txt
+```
+
+Each step builds a subdirectory with a cache (`das-json-store`, `mcm-store` and
+`config-store`). They are large, do not upload them to the repository, respect
+the `.gitignore`.
+
+The output JSON files for the dataset records will be generated in the
+`outputs` directory.
+
+The three configuration files from `./inputs/config-store` are to be copied to
+`/eos/opendata/cms/configuration-files/MonteCarlo2016/`. Don't forget to add
+the `*.py` extension.

cms-2016-pileup-dataset/code/dataset_records.py

@@ -43,7 +43,7 @@
 recommended_cmssw = "CMSSW_10_6_30"
 collision_energy = "13TeV"
 collision_type = "pp"
-year_published = "2023"
+year_published = "2024"
 
 LINK_INFO = {}
 
@@ -191,7 +191,7 @@ def get_all_generator_text(dataset, das_dir, mcm_dir, conf_dir, recid_info):
         step = {}
         process = ''
         output_dataset = get_output_dataset_from_mcm(dataset, mcm_step_dir)
-        if output_dataset:        
+        if output_dataset:
             step['output_dataset'] = output_dataset[0]
         release = get_cmssw_version_from_mcm(dataset, mcm_step_dir)
         if release:
@@ -213,7 +213,7 @@ def get_all_generator_text(dataset, das_dir, mcm_dir, conf_dir, recid_info):
         generator_names = get_generator_name(dataset, mcm_step_dir)
         if generator_names:
             step['generators'] = generator_names
-        
+
         m = re.search('-(.+?)-', step_dir)
         if m:
             step_name = m.group(1)
@@ -243,8 +243,8 @@ def get_all_generator_text(dataset, das_dir, mcm_dir, conf_dir, recid_info):
 
         step['type'] = process
 
-        # Extend LHE steps 
-        if step_name.endswith('LHEGEN'):        
+        # Extend LHE steps
+        if step_name.endswith('LHEGEN'):
             step['type'] = "LHE GEN"
             for i, configuration_files in enumerate(step['configuration_files']):
                 if configuration_files['title'] == 'Generator parameters':
@@ -265,7 +265,7 @@ def get_all_generator_text(dataset, das_dir, mcm_dir, conf_dir, recid_info):
         else:
             if 'generators' in step:
                 generators_present = True
-                    
+
     return info
 
 def populate_containerimages_cache():
@@ -283,7 +283,7 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
     dataset = get_dataset(dataset_full_name)
     dataset_format = get_dataset_format(dataset_full_name)
     year_created = '2016'
-    year_published = '2023'  # 
+    year_published = '2024'  #
     run_period = ['Run2016G', 'Run2016H']  #
 
     additional_title = 'Simulated dataset ' + dataset + ' in ' + dataset_format + ' format for ' + year_created + ' collision data'
@@ -324,7 +324,7 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
     rec['distribution']['formats'] = [dataset_format.lower(), 'root']
     rec['distribution']['number_events'] = 27646400 #  this is computed from the number of files (17279 * 1600 = 27646400) was: get_number_events(dataset_full_name, das_dir)
     rec['distribution']['number_files'] = 17279 # known but maybe get from eos - was: get_number_files(dataset_full_name, das_dir)
-    rec['distribution']['size'] = 0 # FIXME: check from eos - was: get_size(dataset_full_name, das_dir)
+    rec['distribution']['size'] = 55600743325296 # known via grep '"size"' inputs/eos-file-indexes/*.json | awk '{print $NF}' | tr ',' ' ' | paste -s -d+ | bc
 
     doi = get_doi(dataset_full_name, doi_info)
     if doi:
@@ -334,7 +334,7 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
 
     rec_files = get_dataset_index_files(dataset_full_name, eos_dir)
     if rec_files:
-        rec['files'] = [] 
+        rec['files'] = []
         for index_type in ['.json', '.txt']:
             index_files = [f for f in rec_files if f[0].endswith(index_type)]
             for file_number, (file_uri, file_size, file_checksum) in enumerate(index_files):
@@ -373,7 +373,7 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
         rec['pileup'] = {}
         if pileup_dataset_recid:
             rec['pileup']['description'] = "<p>To make these simulated data comparable with the collision data, <a href=\"/docs/cms-guide-pileup-simulation\">pile-up events</a> are added to the simulated event in the DIGI2RAW step.</p>"
-            rec['pileup']['links'] = [ 
+            rec['pileup']['links'] = [
                 {
                     "recid": str(pileup_dataset_recid),
                     "title": pileup_dataset_name
@@ -400,7 +400,7 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
     # recomended global tag and cmssw release recommended for analysis
     rec['system_details'] = {}
     rec['system_details']['global_tag'] = recommended_gt
-    rec['system_details']['release'] = recommended_cmssw 
+    rec['system_details']['release'] = recommended_cmssw
     if recommended_cmssw in CONTAINERIMAGES_CACHE.keys():
         rec["system_details"]["container_images"] = CONTAINERIMAGES_CACHE[recommended_cmssw]
 
@@ -431,15 +431,15 @@ def create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm
     rec['usage']['description'] = "These simulated data are not meant to be analysed on their own. The dataset can be used to add pile-up events to newly simulated event samples using CMS experiment software, available through the CMS Open Data container or the CMS Virtual Machine. See the instructions for setting up one of the two alternative environments and getting started in"
     rec['usage']['links'] = [
         {
-          "description": "Running CMS analysis code using Docker", 
-          "url": "/docs/cms-guide-docker"
-        }, 
+          "description": "Running CMS analysis code using Docker",
+          "url": "/docs/cms-guide-docker#images"
+        },
         {
-          "description": "How to install the CMS Virtual Machine", 
-          "url": "/docs/cms-virtual-machine-2016-2018"
-        }, 
+          "description": "How to install the CMS Virtual Machine",
+          "url": "/docs/cms-virtual-machine-cc7"
+        },
         {
-          "description": "Getting started with CMS open data", 
+          "description": "Getting started with CMS open data",
           "url": "/docs/cms-getting-started-miniaod"
         }
     ]
@@ -455,7 +455,7 @@ def create(dataset, doi_info, recid_info, eos_dir, das_dir, mcm_dir, conffiles_d
     if os.path.exists(filepath) and os.stat(filepath).st_size != 0:
         print("==> " + dataset + "\n==> Already exist. Skipping...\n")
         return
-        
+
     Record= create_record(dataset, doi_info, recid_info, eos_dir, das_dir, mcm_dir, conffiles_dir)
 
     with open(filepath, 'w') as file:
@@ -478,7 +478,7 @@ def create_records(dataset_full_names, doi_file, recid_file, eos_dir, das_dir, m
     #build the record only for the PREMIX dataset
         if 'PREMIX' in dataset_full_name:
             create(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm_dir, conffiles_dir, records_dir)
-            
+
         #records.append(create_record(dataset_full_name, doi_info, recid_info, eos_dir, das_dir, mcm_dir, conffiles_dir))
     #return records
 
@@ -517,10 +517,10 @@ def get_step_generator_parameters(dataset, mcm_dir, recid, force_lhe=0):
         if mcdb_id > 1:
             print("Got mcdb > 1: " + str(mcdb_id))
             configuration_files['title'] = 'Generator parameters'
-            configuration_files['url'] = "/eos/opendata/cms/lhe_generators/2015-sim/mcdb/{mcdb_id}_header.txt".format(mcdb_id=mcdb_id)    
-            return [configuration_files]        
-        else:       
-            dir='./lhe_generators/2016-sim/gridpacks/' + str(recid) + '/' 
+            configuration_files['url'] = "/eos/opendata/cms/lhe_generators/2015-sim/mcdb/{mcdb_id}_header.txt".format(mcdb_id=mcdb_id)
+            return [configuration_files]
+        else:
+            dir='./lhe_generators/2016-sim/gridpacks/' + str(recid) + '/'
             files = []
             files = [f for f in os.listdir(dir) if os.path.isfile(os.path.join(dir, f))]
             confarr=[]
@@ -543,4 +543,3 @@ def get_step_generator_parameters(dataset, mcm_dir, recid, force_lhe=0):
                         return [configuration_files]
                 except:
                     pass
-

cms-2016-pileup-dataset/code/eos_store.py

@@ -90,7 +90,7 @@ def get_dataset_volume_files(dataset, volume):
     "Return file list with information about name, size, location for the given dataset and volume."
     files = []
     dataset_location = get_dataset_location(dataset)
-    output = subprocess.check_output('eos find --size --checksum ' + dataset_location + '/' + volume, shell=True)
+    output = subprocess.check_output('eos oldfind --size --checksum ' + dataset_location + '/' + volume, shell=True)
     output = str(output.decode("utf-8"))
     for line in output.split('\n'):
         if line and line != 'file-indexes':
@@ -141,7 +141,7 @@ def create_index_files(dataset, volume, eos_dir):
     copy_index_file(dataset, volume, filename, eos_dir)
 
 
-def main(datasets = [], eos_dir = './inputs/eos-file-indexes'):
+def main(datasets = [], eos_dir = './inputs/eos-file-indexes/'):
     "Do the job."
 
     if not os.path.exists(eos_dir):

cms-2016-pileup-dataset/code/interface.py

@@ -15,7 +15,7 @@
 @click.option('--create-eos-indexes/--no-create-eos-indexes', default=False,
               show_default=True,
               help="Create EOS rich index files")
-@click.option('--eos-dir', default='./inputs/eos-file-indexes',
+@click.option('--eos-dir', default='./inputs/eos-file-indexes/',
               show_default=True,
               help='Output directory for the EOS file indexes')
 @click.option('--ignore-eos-store/--no-ignore-eos-store',

cms-2016-pileup-dataset/inputs/doi-sim.txt

@@ -0,0 +1 @@
+/Neutrino_E-10_gun/RunIISummer20ULPrePremix-UL16_106X_mcRun2_asymptotic_v13-v1/PREMIX 10.7483/OPENDATA.CMS.VWUA.G7SB

cms-2016-pileup-dataset/inputs/recid_info.py

@@ -1,3 +1,3 @@
 RECID_INFO = {
-    "/Neutrino_E-10_gun/RunIISummer20ULPrePremix-UL16_106X_mcRun2_asymptotic_v13-v1/PREMIX": 30566,
+    "/Neutrino_E-10_gun/RunIISummer20ULPrePremix-UL16_106X_mcRun2_asymptotic_v13-v1/PREMIX": 30595,
 }