Compare commits

...

362 Commits

Author SHA1 Message Date
Miriam Baglioni ed560dacc0 [bulktag] align type to community api 2024-10-29 15:49:48 +01:00
Miriam Baglioni 07a1f2b31c [TransformativeAgreement] fix to remove the file downloaded from a previous run of the workflow 2024-10-28 12:23:18 +01:00
Claudio Atzori 80d7b842e4 [graph provision] added JSON payload to the SolrInputDocuments 2024-10-12 16:23:27 +02:00
Claudio Atzori dd397d107d Merge pull request 'Revert the changes for IgnoreUndefined management in tree evaluation' (#491) from fix_decision_tree into main
Reviewed-on: #491
2024-10-11 10:33:42 +02:00
Giambattista Bloisi 3152382ae8 Revert the changes for IgnoreUndefined management in tree evaluation 2024-10-09 23:00:13 +02:00
Claudio Atzori a50e04154e Merge pull request 'PidCleaner used pervasively' (#490) from pid_cleaning into main
Reviewed-on: #490
2024-10-08 15:08:13 +02:00
Claudio Atzori c4e8aaca1f PidCleaner used pervasively 2024-10-08 14:58:28 +02:00
Claudio Atzori 1596d70224 [bipAffiliations] fix: added publisherInputPath to the spark action parameter specifications 2024-10-02 10:02:10 +02:00
Claudio Atzori 5d030d1118 [graph provision] fixed serialisation of the usage counts as measures in the XML records 2024-10-02 09:45:30 +02:00
Claudio Atzori 6e0b6a886f code formatting 2024-09-30 15:13:23 +02:00
Claudio Atzori 3854fcc5e0 Merge pull request 'New Model from affRo' (#487) from affRoModelModificationOnmain into main
Reviewed-on: #487
2024-09-30 14:33:31 +02:00
Miriam Baglioni 371154d74f [OpenAireAffiliations] changed the code to handle mixed model in input. To be able to update some links for as many datasources as possible. So far crossref and openapc 2024-09-30 14:29:49 +02:00
Claudio Atzori 4e9f64e01a merged from the osfPreprints_plugin branch 2024-09-30 11:24:17 +02:00
Giambattista Bloisi d175a9745f Fix: invert the "natural" order when ordering by id lexicographically 2024-09-26 17:07:31 +02:00
Michele De Bonis fe70caa33c fixed dedup test classes 2024-09-26 11:28:51 +02:00
Claudio Atzori 81bfe3fe32 WIP merged beta into main 2024-09-26 09:23:44 +02:00
Miriam Baglioni 0765641979 [AffRo] used the collectedfrom openaire for all the relations imported as affRo output 2024-09-25 17:23:49 +02:00
Miriam Baglioni d0eba032cd [AffRo] removing package 2024-09-25 17:15:17 +02:00
Miriam Baglioni 7cd8171268 [AffRo] refactoring 2024-09-25 17:12:51 +02:00
Miriam Baglioni a54d021c37 merge with main 2024-09-25 17:06:27 +02:00
Miriam Baglioni 6eea075324 [AffRo] changed the creation of the action set against the new model of provision of the matchings. Changed the test calss and the resources accordingly 2024-09-25 17:04:37 +02:00
Claudio Atzori 2ba67f08d3 [OpenCitations] move the extracted contents under a backup path to avoid needing to re-download it in case of errors 2024-09-25 15:39:22 +02:00
Miriam Baglioni df39360822 [AffRo] changed the creation of the action set agaisnt the nen model of provision of the matchings 2024-09-25 12:32:53 +02:00
Claudio Atzori c1a309df75 Merge pull request 'retry on UnknownHostException' (#469) from retry_on_UnknownHostException into main
Reviewed-on: #469
2024-09-25 11:35:14 +02:00
Claudio Atzori 5fdc286eb9 Merge pull request 'ticket #9525: Update Crosserf Mapping' (#479) from ticket#9525 into main
Reviewed-on: #479
2024-09-25 11:32:20 +02:00
Claudio Atzori e7f6eb82df Merge pull request 'fixed a bug with topic ENRICH/MORE/SUBJECT/ARXIV' (#481) from enrich_more_subject_bug into main
Reviewed-on: #481
2024-09-24 08:56:50 +02:00
Claudio Atzori 9c7711310e Merge pull request '[broker] fixed calculation of events for ENRICH/[MISSING|MORE]/PROJECT' (#483) from fix_missing_project_rels into main
Reviewed-on: #483
2024-09-23 15:26:54 +02:00
Michele Artini 0c66b8589d removed the deletedByInference=true filter 2024-09-23 13:01:45 +02:00
Michele Artini 758d4acd05 fixed a bug with topic ENRICH/MORE/SUBJECT/ARXIV 2024-09-23 09:47:29 +02:00
Sandro La Bruzzo 890190b7ae as described on ticket #9525
1. Changed the mapping applied to Crossref records: anything that has a relationship "is-review-of" must be mapped as publication of type "Review".
2. Force the hostedby of Crossref records with DOI prefix 10.3410 and 10.12703 to the H1 Connect data source.
2024-09-18 17:16:53 +02:00
Claudio Atzori 24b5dc97c6 Merge pull request 'mergeResultsOfDifferentTypes only when checkDelegatedAuthority is true' (#478) from merge_by_id_fix into main
Reviewed-on: #478
2024-09-17 10:48:46 +02:00
Claudio Atzori c648531ccb run mergeResultsOfDifferentTypes only when checkDelegatedAuthority is true 2024-09-16 16:16:23 +02:00
Giambattista Bloisi 10cad80d4d Merge pull request 'Fixes for RestIterator' (#473) from fix_pagination into main
Reviewed-on: #473
2024-09-05 16:59:16 +02:00
Giambattista Bloisi 37b9bdc10c Fix: next returned a null value at end of stream 2024-09-05 16:52:57 +02:00
Giambattista Bloisi e7150eea7b Fix for paginationStart parameter management 2024-09-05 16:52:57 +02:00
Giambattista Bloisi 23477f3e80 Fixes for pagination strategy looping at end of download 2024-09-05 16:52:57 +02:00
Claudio Atzori ce78752aa3 BIPAffiliations to include also input data from publisher websites 2024-08-07 15:46:44 +02:00
Claudio Atzori 152cb47375 Merge pull request 'AffiliationFromPublisher' (#470) from AffiliationFromPublisher into main
Reviewed-on: #470
2024-08-07 14:49:28 +02:00
Miriam Baglioni f1dc0050c7 [AffiliationFromPublisher]extention of test 2024-08-07 11:27:11 +02:00
Miriam Baglioni 42531afc3e [AffiliationFromPublisher]refactoring after compilation 2024-08-07 11:17:56 +02:00
Miriam Baglioni 907eeadce8 [AffiliationFromPublisher]Adding to the creation of the ActrionSet also the links got from the publishers 2024-08-07 11:08:50 +02:00
Claudio Atzori 6b4fa7b8b9 the metadata collection plugins using the HttpConnector2 class shall now retry instead of failing in case of UnknownHostException 2024-08-05 16:55:07 +02:00
Claudio Atzori b8bc237079 [bip affiliations] considers only DOI based records 2024-08-05 12:14:06 +02:00
Claudio Atzori ed6d71fc70 code formatting 2024-08-05 12:12:29 +02:00
Miriam Baglioni cbe877b73c [WebCrawlAffiliation]remove from the creation of the action set the relations for pmc and pmid. Only doi are allowed 2024-08-05 11:44:38 +02:00
Claudio Atzori 5fc413a5df Merge pull request '[main] Rest collector plugin on hadoop supports a new param to pass request headers' (#467) from rest-collector-request-header-map2 into main
Reviewed-on: #467
2024-08-05 09:34:24 +02:00
Claudio Atzori 97c9706469 minors 2024-08-02 15:47:56 +02:00
Claudio Atzori 07e7b9315c code formatting 2024-08-02 14:42:24 +02:00
Alessia 39810c6e7e Rest collector plugin on hadoop supports a new param to pass request headers 2024-08-02 14:41:43 +02:00
Claudio Atzori e0f58afd30 [graph provision] include only FoS L1..L2 in the record serialization 2024-08-02 10:58:57 +02:00
Claudio Atzori 60cf7d86a1 [graph provision] include only FoS L1..L2 in the record serialization 2024-08-02 10:58:47 +02:00
Miriam Baglioni 8f11dfe554 [UnpayWall]added othe : in the identifier construction 2024-07-16 18:18:38 +02:00
Claudio Atzori d20a5e020a [graph provision] log the Solr admin application operations for alias deletion and creation 2024-07-15 16:31:04 +02:00
Claudio Atzori 3d1d8e6036 renamed workflow to better reflect its purpose 2024-07-15 15:24:18 +02:00
Claudio Atzori 0b1c58358b Merge pull request '[broker] fixing the mapping of ORCID for the identification of the enrichments' (#458) from broker_orcid into main
Reviewed-on: #458
2024-07-15 11:34:01 +02:00
Claudio Atzori b70a440aca renamed class, updated criteria to consider the ORCIDs used in the matchers 2024-07-12 17:09:01 +02:00
Michele Artini 36c3df1652 tests 2024-07-12 15:29:45 +02:00
Claudio Atzori 2f13683285 [broker] fine tuned the workflow memory settings 2024-07-12 10:27:24 +02:00
Claudio Atzori 5ab409dcab [metadata collection] added -Dcom.sun.security.enableAIAcaIssuers=true as a default for metadata collection 2024-07-12 10:26:32 +02:00
Claudio Atzori b756cfeb85 Merge pull request 'set JAVA_HOME and JAVA_OPTS in metadata collection' (#457) from metadata_collection_java_upgrade into main
Reviewed-on: #457
2024-07-11 15:32:11 +02:00
Claudio Atzori 51d6a541bd [metadata collection] added the possibility to specify the JAVA_HOME and the JAVA_OPTS parameters 2024-07-11 15:24:29 +02:00
Claudio Atzori 07ce92cef2 [OAI-PMH] fixed node name 2024-07-11 11:00:23 +02:00
Miriam Baglioni f043b7b096 [Irish Tender]changed the irish.json file according to comments #26, #29, and #34 for 9635 2024-07-04 12:22:56 +02:00
Claudio Atzori 153b56eeff make entity level pids unique by pidType:pidValue 2024-07-04 09:41:39 +02:00
Claudio Atzori ed97ba4565 Merge pull request '[prod] Openaire Affiliation Inference' (#453) from affRoFromRawStringmain into main
Reviewed-on: #453
2024-07-03 12:32:26 +02:00
Claudio Atzori 7b398a6d0b updated import of organization types from OpenOrgs 2024-07-03 11:11:35 +02:00
Claudio Atzori 13f6506ce5 Change the selection criteria for the pivot record of a group so that by best pid type becomes the first criteria. This will have the effect to slowly converge to records having DOI 2024-07-03 10:44:01 +02:00
Claudio Atzori 3d9ddaa23a importing organization types from OpenOrgs 2024-07-03 10:15:37 +02:00
Claudio Atzori c06dfdfd86 ignore dates containing 'null's 2024-07-02 15:43:11 +02:00
Claudio Atzori b822b34abe code formatting 2024-07-01 09:22:35 +02:00
Michele De Bonis ea1841fbd2 implementation of countryMatch and addition of workflow parameters 2024-07-01 09:14:32 +02:00
Miriam Baglioni 4dbce39237 [AffiliationInference]Extended the affiliation ingestion from OpenAIRE to include also the links derived from web crawl. Changed the provenance from BIP! to OpenAIRE 2024-06-29 18:51:06 +02:00
Miriam Baglioni 3ee8a7d18a [WebCrawl]moved to Constants web crawl name and id 2024-06-29 18:47:23 +02:00
Claudio Atzori ee7deb3f60 [graph provision] publicFormat worfklow parameter defined as optional 2024-06-28 14:52:43 +02:00
Claudio Atzori 157cc8be87 [graph provision] fixed serialization of the instancetypes 2024-06-28 14:21:12 +02:00
Claudio Atzori 023099a921 imported from beta 2024-06-26 11:40:16 +02:00
Claudio Atzori 786c217085 Using the updated Solr JSON payload model classes 2024-06-26 11:11:33 +02:00
Lampros Smyrnaios c858c02111 - Fix not using the "export HADOOP_USER_NAME" statement in "createPDFsAggregated.sh", which caused permission-issues when creating tables with Impala.
- Remove unused "--user" parameter in "impala-shell" calls.
- Code polishing.
2024-06-26 10:11:21 +02:00
Claudio Atzori 8220e27110 Merge pull request 'Align Solr JSON records to the explore portal requirements' (#448) from json_payload into beta_to_master_may2024
Reviewed-on: #448
2024-06-25 09:57:40 +02:00
Claudio Atzori bc993d49c1 Update pom.xml
depend on released schema version
2024-06-25 09:57:06 +02:00
Claudio Atzori 1dc7458de2 added JSON payload to the SolrInputDocument, updated unit tests 2024-06-24 14:48:09 +02:00
Claudio Atzori a7a54aab47 WIP: align Solr JSON records to the explore portal requirements 2024-06-20 15:48:45 +02:00
Miriam Baglioni eaa00a4199 [IrishFunderList]make changed according to 9635 comment 20, 21, 22 and 23 2024-06-20 12:32:57 +02:00
Claudio Atzori fb731b6d46 WIP: align Solr JSON records to the explore portal requirements 2024-06-19 15:38:43 +02:00
Miriam Baglioni b6da35e736 [IrishFunderList]make changed according to 9635 comment 14, 15 and 16 2024-06-19 11:06:58 +02:00
Lampros Smyrnaios 3c9b8de892 Miscellaneous updates to the copying operation to Impala Cluster:
- Fix not breaking out of the VIEWS-infinite-loop when the "SHOULD_EXIT_WHOLE_SCRIPT_UPON_ERROR" is set to "false".
- Exit the script when no HDFS-active-node was found, independently of the "SHOULD_EXIT_WHOLE_SCRIPT_UPON_ERROR".
- Fix view_name-recognition in a log-message, by using the more advanced "Perl-Compatible Regular Expressions" in "grep".
- Add error-handling for "compute stats" errors.
2024-06-18 15:59:34 +02:00
Antonis Lempesis c67ef157d3 filtering out deletedbyinference and invinsible results from accessroute 2024-06-18 15:59:00 +02:00
Lampros Smyrnaios c23f3031ed Miscellaneous updates to the copying operation to Impala Cluster:
- Show some counts and the elapsed time for various sub-tasks.
- Code polishing.
2024-06-18 15:58:46 +02:00
Claudio Atzori 8ec151aa3d [graph indexing] comment out setting the JSON payload from the SolrInputDocuments 2024-06-18 15:53:24 +02:00
Claudio Atzori 2636936162 [IE OAI-PMH] fixed oozie wf definition 2024-06-14 11:47:37 +02:00
Miriam Baglioni ef437a8cdf [Provision]temporarily removed Json paylod from indexed records (Shadow cannot support it) 2024-06-13 16:48:03 +02:00
Miriam Baglioni 86088ef26e Merge remote-tracking branch 'origin/beta_to_master_may2024' into beta_to_master_may2024 2024-06-11 17:04:07 +02:00
Miriam Baglioni 143c525343 [WebCrawl]remove relations for pid not doi 2024-06-11 17:03:59 +02:00
Claudio Atzori c371513d43 [graph resolution] use sparkExecutorMemory to define also the memoryOverhead 2024-06-11 14:21:01 +02:00
Claudio Atzori 71927ca818 avoid NPEs 2024-06-11 12:40:50 +02:00
Giambattista Bloisi 46018dc804 Fix OperationUnsupportedException while merging two Result's contexts due to modification of an immutable collection 2024-06-11 10:39:48 +02:00
Miriam Baglioni 3efd5b1308 [SDGActionSet]remove datainfo for the result. It is not needed (qualifier.classid = UPDATE) useless since subject do not go at the level of the instance 2024-06-11 10:35:57 +02:00
Miriam Baglioni 196fa55774 Merge remote-tracking branch 'origin/beta_to_master_may2024' into beta_to_master_may2024 2024-06-11 10:26:24 +02:00
Miriam Baglioni 50805e3fc1 [FoSActionSet]remove datainfo for the result. It is not needed (qualifier.classid = UPDATE) useless since subject do not go at the level of the instance 2024-06-11 10:25:46 +02:00
Claudio Atzori d39a1054b8 [actionset promotion] use sparkExecutorMemory to define also the memoryOverhead 2024-06-10 16:15:07 +02:00
Claudio Atzori 576efc1857 hostedby patching to work with the updated Crossref contents 2024-06-10 15:22:33 +02:00
Claudio Atzori efc1632e16 code formatting 2024-06-06 09:25:26 +02:00
Claudio Atzori 91b49366c6 [graph provision] align serialisation of the usage count measures to the agrred specifications 2024-06-05 16:34:40 +02:00
Claudio Atzori 5e05385d35 minor 2024-06-05 16:31:58 +02:00
Miriam Baglioni c4d9b5b9d2 [downloadsAndViews]update the test file to consider the new serialization for downloads and views 2024-06-05 16:30:15 +02:00
Miriam Baglioni bf9a5e6314 [downloadsAndViews]changed the test file to check the indicators are not there if their value is 0 2024-06-05 16:29:40 +02:00
Miriam Baglioni 9d79ddb3dd [bulkTag] fixed issue that made project disappear in graph_10_enriched 2024-06-05 16:20:40 +02:00
Miriam Baglioni 907aa28c6c [downloadsAndViews] fixed issue 2024-06-05 16:19:29 +02:00
Miriam Baglioni 3955ceaa76 [downloadsAndViews] changed the serialization for downloads and views 2024-06-05 16:18:46 +02:00
Miriam Baglioni 128c143394 {downloadsAndViews] extended test file with measures for downloads and views 2024-06-05 16:17:59 +02:00
Claudio Atzori 5133993ee5 Merge branch 'beta_to_master_may2024' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta_to_master_may2024 2024-06-05 12:17:48 +02:00
Claudio Atzori 5cf259a851 [graph2hive] use sparkExecutorMemory to define also the memoryOverhead 2024-06-05 12:17:16 +02:00
Claudio Atzori e1828fc60e Merge pull request '[PROD] Irish oaipmh exporter' (#444) from irish-oaipmh-exporter into beta_to_master_may2024
Reviewed-on: #444
2024-06-05 10:56:20 +02:00
Claudio Atzori 56920b447d Merge pull request 'Fix for missing collectedfrom after dedup' (#442) from fix_mergedcliquesort into beta_to_master_may2024
Reviewed-on: #442
2024-06-03 15:34:01 +02:00
Giambattista Bloisi 3feab5d92d Fix MergeUtils.mergeGroup: it could get rid of some records and did not consider all PID authorities whilke sorting records.
ResultTypeComparator is now renamed in MergeEntitiesComparator and can be used as a general comparator for merging groups of records
2024-06-03 15:13:40 +02:00
Claudio Atzori 6be783caec [graph cleaning] use sparkExecutorMemory to define also the memoryOverhead 2024-05-29 14:36:49 +02:00
Claudio Atzori b703f94f09 Merge pull request 'changes in copy script - beta2master' (#439) from antonis.lempesis/dnet-hadoop:beta into beta_to_master_may2024
Reviewed-on: #439
2024-05-29 14:29:26 +02:00
Miriam Baglioni 14f275ffaf [NOAMI] removed Ireland funder id 501100011103. ticket 9635 2024-05-29 11:54:17 +02:00
Claudio Atzori a428e7be7e graph cleaning to implement ugly hardcoded rules, avoid NPEs 2024-05-29 09:26:12 +02:00
Claudio Atzori 8e45c5baa8 graph cleaning to implement ugly hardcoded rules 2024-05-28 15:28:42 +02:00
Claudio Atzori db5e18c784 hostedby patching to work with the updated Crossref contents 2024-05-28 15:28:13 +02:00
Claudio Atzori fb266efbcb [org dedup] avoid NPEs in SparkPrepareNewOrgs 2024-05-26 21:23:30 +02:00
Claudio Atzori d7daf54333 [org dedup] avoid NPEs in SparkPrepareOrgRels 2024-05-26 16:48:11 +02:00
Claudio Atzori f99eaa0376 Merge branch 'beta_to_master_may2024' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta_to_master_may2024 2024-05-26 15:45:41 +02:00
Claudio Atzori 23312fcc1e [org dedup] avoid NPEs in SparkPrepareOrgRels 2024-05-26 15:43:24 +02:00
Miriam Baglioni b864f0adcf Update to include a blackList that filters out the results we know are wrongly associated to IE - update workflow definition - the blacklist parameter 2024-05-24 16:01:19 +02:00
Miriam Baglioni 7a44869d87 Update to include a blackList that filters out the results we know are wrongly associated to IE - refactoring 2024-05-24 15:23:42 +02:00
Miriam Baglioni 12ffde023f Update to include a blackList that filters out the results we know are wrongly associated to IE 2024-05-24 12:28:24 +02:00
Claudio Atzori c3fe59bc78 fixed conflicts merging from beta, code formatting 2024-05-21 14:50:40 +02:00
Claudio Atzori 795e1b2629 Merge pull request '[graph indexing] sets spark memoryOverhead in the join operations to the same value used for the memory executor' (#426) from provision_memoryOverhead into master
Reviewed-on: #426
2024-04-19 16:59:45 +02:00
Claudio Atzori 0c05abe50b [graph indexing] sets spark memoryOverhead in the join operations to the same value used for the memory executor 2024-04-19 16:57:55 +02:00
Claudio Atzori 8fdd0244ad Merge pull request 'Various fixes for the stats DB update workflow, step16-createIndicatorsTables.sql' (#425) from stats_step16_fix into master
Reviewed-on: #425
2024-04-18 11:25:24 +02:00
Claudio Atzori 18fdaaf548 integrating suggestion from #9699 to improve the result_country table construction 2024-04-18 11:23:43 +02:00
Claudio Atzori 43e123c624 added column alias 2024-04-17 16:40:29 +02:00
Claudio Atzori 62a07b7add added missing end of statement /*EOS*/ 2024-04-17 15:13:28 +02:00
Claudio Atzori 96bddcc921 revised query implementation for indi_pub_gold_oa 2024-04-17 15:06:50 +02:00
Miriam Baglioni 0486cea4c4 removed the funder id : 100011062 Asian Spinal Cord Network, wrongly associated to Ireland 2024-04-16 15:36:40 +02:00
Claudio Atzori 013935c593 Merge pull request 'Improvements to copying data from ocean to impala' (#420) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #420
2024-04-16 14:17:47 +02:00
Claudio Atzori 6132bd028e Merge pull request 'Extend Crossref-funders mapping and datacite hostedbymap' (#417) from CrossrefFundersMap into master
Reviewed-on: #417
2024-04-09 10:30:53 +02:00
Miriam Baglioni 519db1ddef Extended mapping of funder from crossref (#9169, #9277) and change the correspondece files for the irish fundrs (#9635). Extended the datacite map to include the association between metadata and the EBRAINS datasource (SciLake) 2024-04-09 09:33:09 +02:00
Claudio Atzori 5add51f38c Merge pull request 'fixed the result_country definition and updated the stats DB copy procedure' (#412) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #412
2024-04-03 12:34:17 +02:00
Claudio Atzori f01390702e Merge pull request 'fixed typo in indicator query' (#410) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #410
2024-03-27 13:42:07 +01:00
Claudio Atzori 5592ccc37a Merge pull request 'added missing EOS, Generate tables with parquet-files, instead of csv in the contexts.sh script' (#408) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #408
2024-03-27 12:02:57 +01:00
Claudio Atzori d16c15da8d adjusted pom files 2024-03-26 14:00:44 +01:00
Claudio Atzori 09a6d17059 Merge pull request '[Stats wf] #372, #405 to production' (#406) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #406
2024-03-26 12:18:26 +01:00
Claudio Atzori d70793847d resolving conflicts on step16-createIndicatorsTables.sql 2024-03-26 12:17:52 +01:00
Michele De Bonis f6601ea7d1 default parameters for openorgs updated 2024-03-25 13:07:04 +01:00
Michele De Bonis cd4c3c934d openorgs wf updated 2024-03-22 15:42:37 +01:00
Michele Artini a99942f7cf filter by base types 2024-03-13 12:12:42 +01:00
Michele Artini 7f7083f53e updated sql query for filtering BASE records 2024-03-13 11:57:26 +01:00
Michele Artini d9b23a76c5 comments 2024-03-12 14:53:34 +01:00
Michele Artini 841ca92246 Merge pull request 'new plugin to collect from a dump of BASE' (#400) from base-collector-plugin into master
Reviewed-on: #400
2024-03-12 12:22:42 +01:00
Michele Artini 3bcfc40293 new plugin to collect from a dump of BASE 2024-03-12 12:17:58 +01:00
Giambattista Bloisi 3067ea390d Use SparkSQL in place of Hive for executing step16-createIndicatorsTables.sql of stats update wf 2024-03-04 11:13:34 +01:00
Miriam Baglioni c94d94035c [BulkTagging] added check to verify if field is present in the pathMap 2024-02-28 09:41:42 +01:00
Michele Artini 4374d7449e mapping of project PIDs 2024-02-22 14:44:35 +01:00
Claudio Atzori 07d009007b Merge pull request 'Fixed problem on missing author in crossref Mapping' (#384) from crossref_missing_author_fix_master into master
Reviewed-on: #384
2024-02-15 15:06:17 +01:00
Claudio Atzori 071d044971 Merge branch 'master' into crossref_missing_author_fix_master 2024-02-15 15:04:19 +01:00
Claudio Atzori b3ddbaed58 fixed import of ORPs stored on HDFS in the internal graph format (e.g. Datacite) 2024-02-15 15:02:48 +01:00
Claudio Atzori 1416f16b35 [graph raw] fixed mapping of the original resource type from the Datacite format 2024-02-09 10:19:53 +01:00
Giambattista Bloisi ba1a0e7b4f Merge pull request 'Set deletedbyinference =true to dedup aliases, created when a dedup in a previous build has been merged in a new dedup' (#392) from fix_dedupaliases_deletedbyinference into master
Reviewed-on: #392
2024-02-08 15:29:29 +01:00
Giambattista Bloisi 079085286c Merge branch 'master' into fix_dedupaliases_deletedbyinference 2024-02-08 15:29:13 +01:00
Giambattista Bloisi 8dd666aedd Dedup aliases, created when a dedup in a previous build has been merged in a new dedup, need to be marked as "deletedbyinference", since they are "merged" in the new dedup 2024-02-08 15:27:57 +01:00
Claudio Atzori f21133229a Merge pull request 'Support for the PromoteAction strategy [master]' (#391) from promote_actions_join_type_master into master
Reviewed-on: #391
2024-02-08 15:12:16 +01:00
Claudio Atzori d86b909db2 [actiosets] fixed join type 2024-02-08 15:10:55 +01:00
Claudio Atzori 08162902ab [actiosets] introduced support for the PromoteAction strategy 2024-02-08 15:10:40 +01:00
Claudio Atzori e8630a6d03 [graph cleaning] rule out datasources without an officialname 2024-02-05 14:59:06 +02:00
Claudio Atzori f28c63d5ef [orcid enrichment] fixed directory cleanup before distcp 2024-02-05 09:44:56 +02:00
Claudio Atzori 1a8b609ed2 code formatting 2024-01-30 11:34:16 +01:00
Miriam Baglioni 4c8706efee [orcid-enrichment] change the value of parameters. 2024-01-29 18:21:36 +01:00
Claudio Atzori 4d0c59669b merged changes from beta 2024-01-26 16:08:54 +01:00
Sandro La Bruzzo 3c8c88bdd3 Fixed problem on missing author in crossref Mapping 2024-01-26 12:29:30 +01:00
Claudio Atzori 106968adaa Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-12-21 12:26:29 +01:00
Claudio Atzori a8a4db96f0 added metaresourcetype to the result hive DB view 2023-12-21 12:26:19 +01:00
Sandro La Bruzzo 37e36baf76 updated workflow for generation of Scholix Datasource's to use mdstore transactions 2023-12-18 16:05:35 +01:00
Sandro La Bruzzo 9d39845d1f uploaded input parameters on CreateBaseline WF 2023-12-18 12:23:12 +01:00
Sandro La Bruzzo 1fbd4325f5 Merge branch 'master' of code-repo.d4science.org:D-Net/dnet-hadoop 2023-12-18 11:47:17 +01:00
Sandro La Bruzzo 1f1a6a5f5f updated the transformation Baseline workflow to include mdstore rollback/commit action 2023-12-18 11:47:00 +01:00
Claudio Atzori c4ec35b6cd Merge pull request 'Master branch updates from beta December 2023' (#369) from beta_to_master_dicember2023 into master
Reviewed-on: #369
2023-12-15 11:18:30 +01:00
Claudio Atzori 1726f49790 code formatting 2023-12-15 10:37:02 +01:00
Claudio Atzori 1763d377ad code formatting 2023-11-23 16:33:24 +01:00
Claudio Atzori a0311e8a90 Merge pull request 'Clear working dir in bipranker workflow' (#360) from 9120_bipranker_clean_working_dir into master
Reviewed-on: #360
2023-11-22 14:10:39 +01:00
Claudio Atzori 8fb05888fd Merge branch 'master' into 9120_bipranker_clean_working_dir 2023-11-22 14:10:30 +01:00
Claudio Atzori 2b626815ff Merge pull request 'Project propagation via communityAPI instead of using IS via IIS' (#362) from projectPropagation into master
Reviewed-on: #362
2023-11-14 16:37:53 +01:00
Miriam Baglioni b177cd5a0a Project propagation via communityAPI instead of using IS via IIS 2023-11-14 16:25:09 +01:00
Serafeim Chatzopoulos 671ba8a5a7 Clear working dir in bipranker workflow 2023-11-07 18:35:05 +02:00
Claudio Atzori 5f1ed61c1f merging from bulkTag branch 2023-11-03 12:51:37 +01:00
Claudio Atzori 8c03c41d5d applying changes from beta 2023-11-03 12:08:39 +01:00
Claudio Atzori 97454e9594 Merge pull request '9117_pubmed_affiliations_prod' (#357) from 9117_pubmed_affiliations_prod into master
Reviewed-on: #357
2023-11-03 11:45:34 +01:00
Serafeim Chatzopoulos 7e34dde774 Renaming input param for crossref input path 2023-11-02 17:47:04 +02:00
Serafeim Chatzopoulos 24c3f92d87 Change the description of the workflow 2023-11-02 17:46:51 +02:00
Serafeim Chatzopoulos 6ce9b600c1 Add actionset creation for pubmed affiliations 2023-11-02 17:46:39 +02:00
Serafeim Chatzopoulos 94089878fd Adjust tests to new WF input params 2023-11-02 17:46:13 +02:00
Miriam Baglioni 0097f4e64b Removed Query community testing. Removed package from common related to the interaction with Zenodo since it was moved to the dump-project 2023-10-26 09:38:09 +02:00
Miriam Baglioni 5c5a195e97 refactoring and fixing issue on property name 2023-10-23 11:26:17 +02:00
Miriam Baglioni 70b78a40c7 removed file from different propagation 2023-10-20 15:50:49 +02:00
Miriam Baglioni f206ff42d6 modified code to use the the API. Removing not needed parameters. Rewritten the code to exploit the parallel stream on the entity types 2023-10-20 15:49:41 +02:00
Miriam Baglioni 34358afe75 modified resource file, workflow anf default-config. Add 3g of memory Overhead and specified the shuffle partition in the wf confiduration. Removed the multiple instantiation in the wf because of different implementation of the spark job 2023-10-20 15:48:27 +02:00
Miriam Baglioni 18bfff8af3 adding test classes and modifying test for bulktag 2023-10-20 15:47:03 +02:00
Miriam Baglioni 69dac91659 adding the new code to use the API instead of the Information Service 2023-10-20 15:45:52 +02:00
Miriam Baglioni a9ede1e989 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-10-20 10:14:43 +02:00
Claudio Atzori 242d647146 cleanup & docs 2023-10-12 12:23:44 +02:00
Claudio Atzori af3ffad6c4 [AMF] docs 2023-10-12 10:07:52 +02:00
Claudio Atzori ba5475ed4c Merge pull request 'Fix cleaning of Pmid where parsing of numbers stopped at first not leading 0 (zero) character' (#345) from fix_truncated_pmid into master
Reviewed-on: #345
2023-10-06 14:19:49 +02:00
Giambattista Bloisi 2c235e82ad Fix cleaning of Pmid where parsing of numbers stopped at first not leading 0' character 2023-10-06 12:35:54 +02:00
Claudio Atzori 4ac06c9e37 Merge pull request 'Fix bug in conversion from dedup json model to Spark Dataset of Rows (instanceTypeMatch no longer working)' (#339) from fix_dedupfailsonmatchinginstances into master
Reviewed-on: #339
2023-10-02 11:34:20 +02:00
Claudio Atzori fa692b3629 Merge branch 'master' into fix_dedupfailsonmatchinginstances 2023-10-02 11:28:16 +02:00
Claudio Atzori ef02648399 Merge pull request 'fixed dedup configuration management in the Broker workflow' (#341) from fix_8997 into master
Reviewed-on: #341
2023-10-02 11:03:50 +02:00
Claudio Atzori d13bb534f0 Merge branch 'master' into fix_8997 2023-10-02 11:03:18 +02:00
Giambattista Bloisi 775c3f704a Fix bug in conversion from dedup json model to Spark Dataset of Rows: list of strings contained the json escaped representation of the value instead of the plain value, this caused instanceTypeMatch failures because of the leading and trailing double quotes 2023-09-27 22:30:47 +02:00
Sandro La Bruzzo 9c3ab11d5b Merge branch 'master' of code-repo.d4science.org:D-Net/dnet-hadoop 2023-09-25 15:29:19 +02:00
Sandro La Bruzzo 423ef30676 minor fix on the aggregation of uniprot and pdb 2023-09-25 15:28:58 +02:00
Giambattista Bloisi 7152d47f84 Use asScala to convert java List to Scala Sequence 2023-09-20 16:14:27 +02:00
Claudio Atzori 4853c19b5e code formatting 2023-09-20 15:53:21 +02:00
Giambattista Bloisi 1f226d1dce Fix defect #8997: GenerateEventsJob is generating huge amounts of logs because broker entity similarity calculation consistently failed 2023-09-20 15:42:00 +02:00
Alessia Bardi 6186cdc2cc Use v5 of the UNIBI Gold ISSN list in test 2023-09-19 14:47:01 +02:00
Alessia Bardi d94b9bebf7 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-09-19 13:38:45 +02:00
Alessia Bardi 19abba8fa7 tests for d4science catalog 2023-09-19 13:38:25 +02:00
Claudio Atzori c2f179800c Merge pull request 'Run CC and RAM sequentieally in dhp-impact-indicators WF' (#338) from run_cc_and_ram_sequentially into master
Reviewed-on: #338
2023-09-13 08:52:53 +02:00
Serafeim Chatzopoulos 2aed5a74be Run CC and RAM sequentieally in dhp-impact-indicators WF 2023-09-12 22:31:50 +03:00
Claudio Atzori 4dc4862011 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-09-12 14:34:34 +02:00
Claudio Atzori dc80ab14d3 [graph dedup] consistency wf should not remove the relations while dispatching the entities 2023-09-12 14:34:28 +02:00
Alessia Bardi 77a2199837 updated test for EOSC comunity 2023-09-08 11:05:49 +02:00
Claudio Atzori 265180bfd2 added Archive ouverte UNIGE (ETHZ.UNIGENF, opendoar____::1400) to the Datacite hostedBy_map 2023-09-07 11:20:35 +02:00
Claudio Atzori da0e9828f7 resolved conflicts for PR#337 2023-09-06 11:28:46 +02:00
Miriam Baglioni 599828ce35 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-08-09 13:07:13 +02:00
Claudio Atzori 0bc74e2000 code formatting 2023-08-02 11:52:10 +02:00
Claudio Atzori 7180911ded [graph cleaning] fixed regex behaviour for cleaning ROR and GRID identifiers, added tests 2023-08-02 11:44:14 +02:00
Claudio Atzori da1727f93f rule out records with NULL dataInfo, except for Relations 2023-07-31 17:52:56 +02:00
Claudio Atzori ccac6a7f75 rule out records with NULL dataInfo 2023-07-31 12:35:05 +02:00
Claudio Atzori d512df8612 code formatting 2023-07-26 09:14:08 +02:00
Claudio Atzori 59764145bb cherry picked & fixed commit 270df939c4 2023-07-25 17:39:00 +02:00
Miriam Baglioni 9e8e39f78a - 2023-07-19 11:35:58 +02:00
Claudio Atzori 373a5f2c83 Merge pull request 'Master branch updates from beta July 2023' (#317) from master_july23 into master
Reviewed-on: #317
2023-07-18 18:22:04 +02:00
Claudio Atzori 8af129b0c7 merged stats promotion step from antonis/promotion-prod-only 2023-07-13 15:03:28 +02:00
dimitrispie 706092bc19 Update updateProductionViews.sh 2023-07-13 15:48:12 +03:00
dimitrispie aedd279f78 Updates Promotion DBs
- Add a step for promoting the splitted monitor DBs
2023-07-13 15:35:46 +03:00
Miriam Baglioni 8dcd028eed [UsageCount] fixed typo in attribute name for datasource table 2023-07-01 16:07:22 +02:00
Miriam Baglioni 8621377917 [UsageCount] fixed typo in attribute name for datasource table 2023-06-30 19:02:44 +02:00
Miriam Baglioni ef2dd7a980 resolved conflicts 2023-06-30 18:59:47 +02:00
Claudio Atzori f3a85e224b merged from branch beta the bulk tagging (single step, negative constraints), the cleanig worflow (single step, pid type based cleaning), instance level fulltext 2023-06-28 13:33:57 +02:00
Claudio Atzori 4ef0f2ec26 added dependency commons-validator:commons-validator:1.7 2023-06-28 13:32:01 +02:00
Claudio Atzori 288ec0b7d6 [doiboost] merged workflow from branch beta 2023-06-28 09:15:37 +02:00
Claudio Atzori 5f32edd9bf adopting dhp-schema:3.17.1 2023-06-27 16:57:17 +02:00
Claudio Atzori e10ce92fe5 [stats wf] merged workflows from branch beta 2023-06-27 14:32:48 +02:00
Claudio Atzori b93e1541aa Merge pull request 'update sql query to return distinct pids' (#301) from distinct_pids_from_openorgs into master
Reviewed-on: #301
2023-06-27 12:24:47 +02:00
Claudio Atzori d029bf0b94 Merge branch 'master' into distinct_pids_from_openorgs 2023-06-27 12:24:35 +02:00
Michele Artini 009d7f312f fixed a datasource Id 2023-06-21 16:17:34 +02:00
Miriam Baglioni e4b27182d0 [master] refactoring 2023-06-21 11:15:53 +02:00
Giambattista Bloisi 758e662ab8 Revert "REmove duplicated code and ensure that load and initialization is done through "DedupConfig.load" method"
This reverts commit 485f9d18cb.
2023-06-19 13:08:10 +02:00
Giambattista Bloisi 485f9d18cb REmove duplicated code and ensure that load and initialization is done through "DedupConfig.load" method 2023-06-19 13:00:02 +02:00
Michele Artini a92206dab5 re-added the name of a column (pid) 2023-06-13 11:43:10 +02:00
Miriam Baglioni d9506035e4 [ZenodoApi] gone back to okhttp3 to send the payload. 2023-06-09 12:05:02 +02:00
Alessia Bardi 118e72d7db Updated officialnmae of pangaea in hostedbymap for Datacite to avoid duplicate entries in the source filter of the portal 2023-06-06 14:39:12 +02:00
Alessia Bardi 5befd93d7d test records for Solr indexing 2023-06-06 14:34:33 +02:00
Michele Artini cae92cf811 update sql query to return distinct pids 2023-06-06 14:06:06 +02:00
Miriam Baglioni b64a5eb4a5 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-05-24 15:21:58 +02:00
Claudio Atzori 654ffcba60 Merge pull request '[UsageCount] addition of usagecount for Projects and datasources' (#296) from master_datasource_project_usagecounts into master
Reviewed-on: #296
2023-05-22 16:13:24 +02:00
Claudio Atzori db625e548d [UsageCount] addition of usagecount for Projects and datasources 2023-05-22 15:00:46 +02:00
Alessia Bardi 04141fe259 tests for records from D4Science catalogues 2023-05-19 14:28:24 +02:00
Alessia Bardi b88f009d9f combined level 4 and 6 for the demo 2023-04-24 12:10:33 +02:00
Alessia Bardi 5ffe82ffd8 aligned to current DMF index layout on production 2023-04-24 12:09:55 +02:00
Alessia Bardi 1c173642f0 removed level5 from test records 2023-04-24 09:32:32 +02:00
Alessia Bardi 382f46a8e4 tests to generate the XML records for the index for the EDITH demo on digital twins, integrating output from the FoS classifier 2023-04-21 16:46:30 +02:00
Miriam Baglioni 9fc8ebe98b refactoring 2023-04-19 09:32:13 +02:00
Miriam Baglioni 24c41806ac [ZenodoApiClienttest] change test to mirror change in the omplementation 2023-04-18 09:08:09 +02:00
Miriam Baglioni 087b5a7973 [ZenodiAPIClient] new version of the API to connect to Zenodo (change the http client 2023-04-17 18:59:22 +02:00
Claudio Atzori 688e3b7936 added eoscifguidelines in the result view; removed compute statistics statements 2023-04-11 11:45:56 +02:00
Claudio Atzori 2e465915b4 [graph to Solr] using dedicated sparkExecutorCores, sparkExecutorMemory, sparkDriverMemory in convert_to_xml 2023-04-11 10:43:44 +02:00
Claudio Atzori 4a4ca634f0 Merge pull request 'advConstraintsInBeta' (#288) from advConstraintsInBeta into master
Reviewed-on: #288
2023-04-06 15:24:23 +02:00
Miriam Baglioni c6a7602b3e refactoring after compilation 2023-04-06 14:45:01 +02:00
Miriam Baglioni 831055a1fc change of the property for test purposes, addition of two new verbs, and fix of issue for advanced constraints 2023-04-06 14:41:32 +02:00
Miriam Baglioni cf3d0f4f83 fixed issue on bulktagging for the advanced constraints 2023-04-06 12:17:35 +02:00
Claudio Atzori 4f67225fbc Merge pull request 'doiboostMappingExtention' (#286) from doiboostMappingExtention into master
Reviewed-on: #286
2023-04-06 09:25:08 +02:00
Claudio Atzori e093f04874 Merge pull request 'AdvancedConstraint' (#285) from advConstraintsInBeta into master
Reviewed-on: #285
2023-04-06 09:24:54 +02:00
Miriam Baglioni c5a9f39141 Extended the association project - result in the mapping from CrossRef 2023-04-05 16:48:36 +02:00
Miriam Baglioni ecc05fe0f3 Added the code for the advancedConstraint implementation during the bulkTagging 2023-04-05 16:40:29 +02:00
Claudio Atzori 42442ccd39 Merge pull request 'updated the order of the compatibilities' (#275) from compatibility_order into master
Reviewed-on: #275
2023-04-05 12:44:14 +02:00
Miriam Baglioni 9a9cc6a1dd changed the way the tar archive is build to support renaming in case we need to change .tt.gz into .json.gz 2023-04-04 11:40:58 +02:00
Michele Artini 200098b683 updated the order of the compatibilities 2023-02-22 11:52:59 +01:00
Michele Artini 9c1df15071 null values in date range conditions 2023-02-13 16:05:58 +01:00
Miriam Baglioni 32870339f5 refactoring after compile 2023-02-13 13:06:48 +01:00
Miriam Baglioni 7184cc0804 [FoS] added check for null on level1 subject 2023-02-13 13:03:49 +01:00
Miriam Baglioni 7473093c84 [FoS] changed the default separator from comma to tab to solve the issue in subject value split 2023-02-10 15:34:52 +01:00
Miriam Baglioni 5f0906be60 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-02-02 17:13:14 +01:00
Claudio Atzori 1b37516578 [bulk tagging] better node naming 2023-01-20 16:11:26 +01:00
Claudio Atzori c1e2460293 [cleaning] the datasource master-duplicate fixup should not be brought to production yet 2023-01-20 09:20:26 +01:00
Claudio Atzori 3800361033 [country propagation] fixes error 'cannot resolve countrySet given input columns: []' when there is no prepared information driving the propagation process for a given result type 2023-01-19 15:57:43 +01:00
Michele Artini 699736addc NPE prevention 2023-01-11 13:14:44 +01:00
Claudio Atzori f86e19b282 code formatting 2023-01-11 09:53:19 +01:00
Michele Artini d40e20f437 Considering instance pids and alteternative identifiers 2023-01-11 09:37:34 +01:00
Michele Artini 4953ae5649 fixed an invalid char 2023-01-11 08:35:53 +01:00
Miriam Baglioni c60d3a2b46 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2023-01-09 17:28:27 +01:00
Claudio Atzori 7becdaf31d Merge pull request 'Workaround to use new version of intellij on Master' (#266) from master_intellij into master
Reviewed-on: #266
2022-12-23 10:32:21 +01:00
Miriam Baglioni b713132db7 [Cleaning] adding missing classes 2022-12-21 12:49:08 +01:00
Miriam Baglioni 11f2b470d3 [Cleaning] adding missing classes 2022-12-21 12:42:19 +01:00
Sandro La Bruzzo 91c70b15a5 updated lines function to it's implementation linesWithSeparators.map(l => l.stripLineEnd) in this way we force scala plugin compiler to consider this pipeline scala code and not java.string.lines() pipeline 2022-12-21 11:14:42 +01:00
Claudio Atzori f910b7379d [cleaning] recovering missing resources from #265 2022-12-21 09:26:34 +01:00
Claudio Atzori 33bdad104e [cleaning] align parameter names 2022-12-20 21:43:59 +01:00
Claudio Atzori 5816ded93f code formatting 2022-12-20 10:41:40 +01:00
Claudio Atzori 46972f8393 [orcid propagation] skip empty directory 2022-12-20 10:28:22 +01:00
Claudio Atzori da85ca697d Merge pull request 'cleanCountryOnMaster' (#265) from cleanCountryOnMaster into master
Reviewed-on: #265
2022-12-16 15:58:44 +01:00
Miriam Baglioni 059e100ec7 [Clean Country] moving other resources for testing purposes 2022-12-16 15:48:21 +01:00
Miriam Baglioni fc95a550c3 [Clean Country] moving other resources for testing purposes 2022-12-16 15:46:32 +01:00
Miriam Baglioni 6901ac91b1 [Clean Country] moving source and resources to master 2022-12-16 15:42:49 +01:00
Claudio Atzori 08c4588d47 Merge pull request 'Changes from beta stats wf to prod' (#264) from antonis.lempesis/dnet-hadoop:beta into master
Reviewed-on: #264
2022-12-07 15:56:22 +01:00
Miriam Baglioni 29d3da85f1 [EOSC DUMP] added resources needed for the review as test 2022-11-25 17:16:20 +01:00
Miriam Baglioni 33a2b1b5dc [Bulk Tag] fixed typo in test configuration 2022-11-23 11:31:17 +01:00
Miriam Baglioni c6df8327b3 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2022-11-23 11:26:57 +01:00
Miriam Baglioni 935aa367d8 [BulkTag] removed commented code 2022-11-23 11:16:39 +01:00
Miriam Baglioni 43aedbdfe5 [BulkTag] changed verb name in configuration 2022-11-23 11:14:23 +01:00
Miriam Baglioni b6da9b67ff [BulkTag] fixed typo in annotation for verb name 2022-11-23 11:13:58 +01:00
Claudio Atzori a34c8b6f81 Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop 2022-11-22 10:22:31 +01:00
Miriam Baglioni 122e75aa17 fixed conflicts 2022-11-21 18:13:12 +01:00
Miriam Baglioni cee7a45b1d [Bulk Tag Datasource] fixed issue with verb name and add new test for neanias selection for orcid 2022-11-21 18:10:20 +01:00
Claudio Atzori ed64618235 increased spark.sql.shuffle.partitions in the last join phase of the result (publication) to community through semantic relation propagation 2022-11-18 16:06:51 +01:00
Claudio Atzori 8742934843 added spark.sql.shuffle.partitions in the last join phase of the result to community through semantic relation propagation 2022-11-18 11:32:22 +01:00
Claudio Atzori 13cc592f39 code formatting 2022-11-15 09:37:57 +01:00
Claudio Atzori af15b1e48d [eosc tag] extending criteria for Jupyter Notebook (adding to ORP the same constraint) 2022-11-14 18:30:43 +01:00
Claudio Atzori eb45ba7af0 extended mapping from ODF relations (PR#251) 2022-11-14 18:26:13 +01:00
Claudio Atzori a929dc5fee integrated changes for mapping ROHub contents in the Graph 2022-11-14 18:15:35 +01:00
Miriam Baglioni 5f9383b2d9 [EOSC TAG] remove reduntant check for jupyter notebook 2022-11-11 14:06:19 +01:00
Miriam Baglioni b18bbca8af [EOSC TAG] adding search in orp for jupyter notebook criteria 2022-11-11 12:42:58 +01:00
dimitrispie 55fa3b2a17 Hive memory parameters 2022-11-03 15:21:04 +01:00
Claudio Atzori 80c5e0f637 code formatting 2022-09-27 12:51:51 +02:00
Claudio Atzori c01d528ab2 suppressing hyper verbose spark logs during unit test execution 2022-09-23 15:19:50 +02:00
Claudio Atzori e6d788d27a [stats wf] adding missing changes lost in PR#248 2022-09-23 14:38:42 +02:00
Claudio Atzori 930f118673 fixed semantic (subreltype) for ServiceOrganization relations 2022-09-22 16:24:44 +02:00
Claudio Atzori b2c3071e72 Merge branch 'master' into beta2master_sept_2022 2022-09-22 14:39:15 +02:00
Claudio Atzori 10ec074f79 Merge remote-tracking branch 'antonis.lempesis/beta' into beta2master_sept_2022 2022-09-22 14:12:19 +02:00
Claudio Atzori 7225fe9cbe integrated changes from discard-non-wellformed 2022-09-22 10:06:07 +02:00
Miriam Baglioni 869e129288 [EOSC BulkTag] refactoring 2022-09-20 16:13:18 +02:00
Miriam Baglioni 840465958b [EOSC BulkTag] filtering aout the datasources registered in the eosc with compatibility different from 3.0, 4.0 for literature, data and CRIS to add the context eosc to the results 2022-09-20 10:30:41 +02:00
Claudio Atzori bdc8f993d0 [Patch Hosted By] check also the presence of datasource.officialname.value 2022-09-19 15:28:03 +02:00
Miriam Baglioni ec87149cb3 [Patch Hosted By] added fix to avoi NPE error when datasource official name is not provided. Removing datasources if no officialname has been provided 2022-09-19 14:06:52 +02:00
Miriam Baglioni b42e2c9df6 [Patch Hosted By] added fix to avoi NPE error when datasource official name is not provided 2022-09-19 12:30:32 +02:00
Miriam Baglioni 1329aa8479 [EOSC BulkTag] modified test to remove association of result to eosc when eoscifguidelines are set 2022-09-19 11:59:48 +02:00
Miriam Baglioni a0ee1a8640 [EOSC BulkTag] remove addition of eosc context for result with eosc if guidelines set 2022-09-19 11:44:10 +02:00
Claudio Atzori 96062164f9 Merge pull request '[Aggregator graph|master] Discard invalid records' (#245) from discard-non-wellformed into master
Reviewed-on: #245
2022-09-19 09:48:16 +02:00
Claudio Atzori 35bb7c423f updated dhp-schemas version to 2.12.1 2022-09-16 16:13:15 +02:00
Claudio Atzori fd87571506 code formatting 2022-09-16 16:05:03 +02:00
Claudio Atzori c527112e33 Merge commit 'ff6f789b6d9be0567b6ad72f8a0e75fe3f52726a' into beta2master_sept_2022 2022-09-16 15:59:10 +02:00
Claudio Atzori 65209359bc Merge commit 'b5f7bd30be7f7adaaa28170740da0484b50a77ed' into beta2master_sept_2022 2022-09-16 15:58:11 +02:00
Claudio Atzori d72a64ded3 Merge commit '690be4482fc84327dc7617acbc8d976d559df512' into beta2master_sept_2022 2022-09-16 15:57:44 +02:00
Claudio Atzori 3e8499ce47 Merge commit '71b069ca90a2f7ec09d64241c60917d3636fc81e' into beta2master_sept_2022 2022-09-16 15:57:20 +02:00
Claudio Atzori 61aacb3271 Merge commit '1203378441dc6d8e8435cacd42e76e11746f6d1b' into beta2master_sept_2022 2022-09-16 15:56:55 +02:00
Claudio Atzori dbb567251a merged 853c996fa2 2022-09-16 15:56:28 +02:00
Claudio Atzori c7e8ad853e Merge commit '2b5f8c9c9a3611c57ee5febfe262a455a39ad801' into beta2master_sept_2022 2022-09-16 15:55:04 +02:00
Claudio Atzori 0849ebfd80 merged a11eb38065 2022-09-16 15:54:32 +02:00
Claudio Atzori 281239249e Merge commit 'b7c387c21f946adbc9da90ded95166205195edb0' into beta2master_sept_2022 2022-09-16 15:49:20 +02:00
Claudio Atzori 45fc5e12be Merge commit 'cb7c07c54e59675e8dffe42b7f2a13f16c956068' into beta2master_sept_2022 2022-09-16 15:48:55 +02:00
Claudio Atzori 1c05aaaa2e Merge commit '3418ce50ac9b28fed4fa949919e6c8208738cdcf' into beta2master_sept_2022 2022-09-16 15:48:36 +02:00
Claudio Atzori 01d5ad6361 Merge commit 'd85ba3c1a9d7f0e80565742161ff6c9ecffd52b7' into beta2master_sept_2022 2022-09-16 15:48:16 +02:00
Claudio Atzori d872d1cdd9 Merge commit 'a4815f6bec87f05be8cd740d236707949a0f746e' into beta2master_sept_2022 2022-09-16 15:47:49 +02:00
Claudio Atzori ab0efecab4 Merge commit '84598c75356cf580de6c81653a9351e9b8173639' into beta2master_sept_2022 2022-09-16 15:47:05 +02:00
Claudio Atzori 725c3c68d0 Merge commit '844f6eb46533cdd4be3210401b10401322079640' into beta2master_sept_2022 2022-09-16 15:46:40 +02:00
Claudio Atzori 300ae6221c Merge commit '32cee1f619eb30d2e2ac6083435b76b1aba7db09' into beta2master_sept_2022 2022-09-16 15:45:57 +02:00
Claudio Atzori 0ec2eaba35 Merge commit 'c1f2ffc53dc41f1fac3855b2d2df7d6a5ea15e3e' into beta2master_sept_2022 2022-09-16 15:45:27 +02:00
Claudio Atzori a387807d43 Merge commit 'b78889a0ce27a79c7ab2d8da05b118ee4f1bcb36' into beta2master_sept_2022 2022-09-16 15:44:17 +02:00
Claudio Atzori 2abe2bc137 Merge commit '08ce2cadc2d84aa982726e429c280a905536a715' into beta2master_sept_2022 2022-09-16 15:43:49 +02:00
Claudio Atzori a07c876922 Merge commit '27a91841e7fa2a1b615b4d1e161d606db5bead96' into beta2master_sept_2022 2022-09-16 15:43:02 +02:00
Claudio Atzori cbd48bc645 Merge commit 'efd96e7e664e4139321e35e8d172b884ba4b61a1' into beta2master_sept_2022 2022-09-16 15:38:56 +02:00
104 changed files with 2775 additions and 1663 deletions

View File

@ -7,12 +7,12 @@ import java.sql.*;
import java.util.function.Consumer;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class DbClient implements Closeable {
private static final Log log = LogFactory.getLog(DbClient.class);
private static final Logger log = LoggerFactory.getLogger(DbClient.class);
private final Connection connection;
@ -37,6 +37,8 @@ public class DbClient implements Closeable {
try (final Statement stmt = connection.createStatement()) {
stmt.setFetchSize(100);
log.info("running SQL:\n\n{}\n\n", sql);
try (final ResultSet rs = stmt.executeQuery(sql)) {
while (rs.next()) {
consumer.accept(rs);

View File

@ -1,53 +0,0 @@
package eu.dnetlib.dhp.common.api;
import java.io.IOException;
import java.io.InputStream;
import okhttp3.MediaType;
import okhttp3.RequestBody;
import okhttp3.internal.Util;
import okio.BufferedSink;
import okio.Okio;
import okio.Source;
public class InputStreamRequestBody extends RequestBody {
private final InputStream inputStream;
private final MediaType mediaType;
private final long lenght;
public static RequestBody create(final MediaType mediaType, final InputStream inputStream, final long len) {
return new InputStreamRequestBody(inputStream, mediaType, len);
}
private InputStreamRequestBody(InputStream inputStream, MediaType mediaType, long len) {
this.inputStream = inputStream;
this.mediaType = mediaType;
this.lenght = len;
}
@Override
public MediaType contentType() {
return mediaType;
}
@Override
public long contentLength() {
return lenght;
}
@Override
public void writeTo(BufferedSink sink) throws IOException {
Source source = null;
try {
source = Okio.source(inputStream);
sink.writeAll(source);
} finally {
Util.closeQuietly(source);
}
}
}

View File

@ -1,8 +0,0 @@
package eu.dnetlib.dhp.common.api;
public class MissingConceptDoiException extends Throwable {
public MissingConceptDoiException(String message) {
super(message);
}
}

View File

@ -1,363 +0,0 @@
package eu.dnetlib.dhp.common.api;
import java.io.*;
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.concurrent.TimeUnit;
import org.apache.http.HttpHeaders;
import org.apache.http.entity.ContentType;
import org.jetbrains.annotations.NotNull;
import com.google.gson.Gson;
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModel;
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModelList;
import okhttp3.*;
public class ZenodoAPIClient implements Serializable {
String urlString;
String bucket;
String deposition_id;
String access_token;
public static final MediaType MEDIA_TYPE_JSON = MediaType.parse("application/json; charset=utf-8");
private static final MediaType MEDIA_TYPE_ZIP = MediaType.parse("application/zip");
public String getUrlString() {
return urlString;
}
public void setUrlString(String urlString) {
this.urlString = urlString;
}
public String getBucket() {
return bucket;
}
public void setBucket(String bucket) {
this.bucket = bucket;
}
public void setDeposition_id(String deposition_id) {
this.deposition_id = deposition_id;
}
public ZenodoAPIClient(String urlString, String access_token) {
this.urlString = urlString;
this.access_token = access_token;
}
/**
* Brand new deposition in Zenodo. It sets the deposition_id and the bucket where to store the files to upload
*
* @return response code
* @throws IOException
*/
public int newDeposition() throws IOException {
String json = "{}";
URL url = new URL(urlString);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setRequestMethod("POST");
conn.setDoOutput(true);
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel newSubmission = new Gson().fromJson(body, ZenodoModel.class);
this.bucket = newSubmission.getLinks().getBucket();
this.deposition_id = newSubmission.getId();
return responseCode;
}
/**
* Upload files in Zenodo.
*
* @param is the inputStream for the file to upload
* @param file_name the name of the file as it will appear on Zenodo
* @return the response code
*/
public int uploadIS(InputStream is, String file_name) throws IOException {
URL url = new URL(bucket + "/" + file_name);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, "application/zip");
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("PUT");
byte[] buf = new byte[8192];
int length;
try (OutputStream os = conn.getOutputStream()) {
while ((length = is.read(buf)) != -1) {
os.write(buf, 0, length);
}
}
int responseCode = conn.getResponseCode();
if (!checkOKStatus(responseCode)) {
throw new IOException("Unexpected code " + responseCode + getBody(conn));
}
return responseCode;
}
@NotNull
private String getBody(HttpURLConnection conn) throws IOException {
String body = "{}";
try (BufferedReader br = new BufferedReader(
new InputStreamReader(conn.getInputStream(), "utf-8"))) {
StringBuilder response = new StringBuilder();
String responseLine = null;
while ((responseLine = br.readLine()) != null) {
response.append(responseLine.trim());
}
body = response.toString();
}
return body;
}
/**
* Associates metadata information to the current deposition
*
* @param metadata the metadata
* @return response code
* @throws IOException
*/
public int sendMretadata(String metadata) throws IOException {
URL url = new URL(urlString + "/" + deposition_id);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("PUT");
try (OutputStream os = conn.getOutputStream()) {
byte[] input = metadata.getBytes("utf-8");
os.write(input, 0, input.length);
}
final int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + getBody(conn));
return responseCode;
}
private boolean checkOKStatus(int responseCode) {
if (HttpURLConnection.HTTP_OK != responseCode ||
HttpURLConnection.HTTP_CREATED != responseCode)
return true;
return false;
}
/**
* To publish the current deposition. It works for both new deposition or new version of an old deposition
*
* @return response code
* @throws IOException
*/
@Deprecated
public int publish() throws IOException {
String json = "{}";
OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
RequestBody body = RequestBody.create(json, MEDIA_TYPE_JSON);
Request request = new Request.Builder()
.url(urlString + "/" + deposition_id + "/actions/publish")
.addHeader("Authorization", "Bearer " + access_token)
.post(body)
.build();
try (Response response = httpClient.newCall(request).execute()) {
if (!response.isSuccessful())
throw new IOException("Unexpected code " + response + response.body().string());
return response.code();
}
}
/**
* To create a new version of an already published deposition. It sets the deposition_id and the bucket to be used
* for the new version.
*
* @param concept_rec_id the concept record id of the deposition for which to create a new version. It is the last
* part of the url for the DOI Zenodo suggests to use to cite all versions: DOI: 10.xxx/zenodo.656930
* concept_rec_id = 656930
* @return response code
*/
public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
setDepositionId(concept_rec_id, 1);
String json = "{}";
URL url = new URL(urlString + "/" + deposition_id + "/actions/newversion");
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("POST");
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
String latest_draft = zenodoModel.getLinks().getLatest_draft();
deposition_id = latest_draft.substring(latest_draft.lastIndexOf("/") + 1);
bucket = getBucket(latest_draft);
return responseCode;
}
/**
* To finish uploading a version or new deposition not published
* It sets the deposition_id and the bucket to be used
*
*
* @param deposition_id the deposition id of the not yet published upload
* concept_rec_id = 656930
* @return response code
* @throws IOException
* @throws MissingConceptDoiException
*/
public int uploadOpenDeposition(String deposition_id) throws IOException, MissingConceptDoiException {
this.deposition_id = deposition_id;
String json = "{}";
URL url = new URL(urlString + "/" + deposition_id);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setRequestMethod("POST");
conn.setDoOutput(true);
try (OutputStream os = conn.getOutputStream()) {
byte[] input = json.getBytes("utf-8");
os.write(input, 0, input.length);
}
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
bucket = zenodoModel.getLinks().getBucket();
return responseCode;
}
private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
ZenodoModelList zenodoModelList = new Gson()
.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
for (ZenodoModel zm : zenodoModelList) {
if (zm.getConceptrecid().equals(concept_rec_id)) {
deposition_id = zm.getId();
return;
}
}
if (zenodoModelList.size() == 0)
throw new MissingConceptDoiException(
"The concept record id specified was missing in the list of depositions");
setDepositionId(concept_rec_id, page + 1);
}
private String getPrevDepositions(String page) throws IOException {
HttpUrl.Builder urlBuilder = HttpUrl.parse(urlString).newBuilder();
urlBuilder.addQueryParameter("page", page);
URL url = new URL(urlBuilder.build().toString());
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("GET");
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
return body;
}
private String getBucket(String inputUurl) throws IOException {
URL url = new URL(inputUurl);
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
conn.setDoOutput(true);
conn.setRequestMethod("GET");
String body = getBody(conn);
int responseCode = conn.getResponseCode();
conn.disconnect();
if (!checkOKStatus(responseCode))
throw new IOException("Unexpected code " + responseCode + body);
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
return zenodoModel.getLinks().getBucket();
}
}

View File

@ -1,14 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
public class Community {
private String identifier;
public String getIdentifier() {
return identifier;
}
public void setIdentifier(String identifier) {
this.identifier = identifier;
}
}

View File

@ -1,47 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
public class Creator {
private String affiliation;
private String name;
private String orcid;
public String getAffiliation() {
return affiliation;
}
public void setAffiliation(String affiliation) {
this.affiliation = affiliation;
}
public String getName() {
return name;
}
public void setName(String name) {
this.name = name;
}
public String getOrcid() {
return orcid;
}
public void setOrcid(String orcid) {
this.orcid = orcid;
}
public static Creator newInstance(String name, String affiliation, String orcid) {
Creator c = new Creator();
if (name != null) {
c.name = name;
}
if (affiliation != null) {
c.affiliation = affiliation;
}
if (orcid != null) {
c.orcid = orcid;
}
return c;
}
}

View File

@ -1,44 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class File implements Serializable {
private String checksum;
private String filename;
private long filesize;
private String id;
public String getChecksum() {
return checksum;
}
public void setChecksum(String checksum) {
this.checksum = checksum;
}
public String getFilename() {
return filename;
}
public void setFilename(String filename) {
this.filename = filename;
}
public long getFilesize() {
return filesize;
}
public void setFilesize(long filesize) {
this.filesize = filesize;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
}

View File

@ -1,23 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class Grant implements Serializable {
private String id;
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public static Grant newInstance(String id) {
Grant g = new Grant();
g.id = id;
return g;
}
}

View File

@ -1,92 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class Links implements Serializable {
private String bucket;
private String discard;
private String edit;
private String files;
private String html;
private String latest_draft;
private String latest_draft_html;
private String publish;
private String self;
public String getBucket() {
return bucket;
}
public void setBucket(String bucket) {
this.bucket = bucket;
}
public String getDiscard() {
return discard;
}
public void setDiscard(String discard) {
this.discard = discard;
}
public String getEdit() {
return edit;
}
public void setEdit(String edit) {
this.edit = edit;
}
public String getFiles() {
return files;
}
public void setFiles(String files) {
this.files = files;
}
public String getHtml() {
return html;
}
public void setHtml(String html) {
this.html = html;
}
public String getLatest_draft() {
return latest_draft;
}
public void setLatest_draft(String latest_draft) {
this.latest_draft = latest_draft;
}
public String getLatest_draft_html() {
return latest_draft_html;
}
public void setLatest_draft_html(String latest_draft_html) {
this.latest_draft_html = latest_draft_html;
}
public String getPublish() {
return publish;
}
public void setPublish(String publish) {
this.publish = publish;
}
public String getSelf() {
return self;
}
public void setSelf(String self) {
this.self = self;
}
}

View File

@ -1,153 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
import java.util.List;
public class Metadata implements Serializable {
private String access_right;
private List<Community> communities;
private List<Creator> creators;
private String description;
private String doi;
private List<Grant> grants;
private List<String> keywords;
private String language;
private String license;
private PrereserveDoi prereserve_doi;
private String publication_date;
private List<String> references;
private List<RelatedIdentifier> related_identifiers;
private String title;
private String upload_type;
private String version;
public String getUpload_type() {
return upload_type;
}
public void setUpload_type(String upload_type) {
this.upload_type = upload_type;
}
public String getVersion() {
return version;
}
public void setVersion(String version) {
this.version = version;
}
public String getAccess_right() {
return access_right;
}
public void setAccess_right(String access_right) {
this.access_right = access_right;
}
public List<Community> getCommunities() {
return communities;
}
public void setCommunities(List<Community> communities) {
this.communities = communities;
}
public List<Creator> getCreators() {
return creators;
}
public void setCreators(List<Creator> creators) {
this.creators = creators;
}
public String getDescription() {
return description;
}
public void setDescription(String description) {
this.description = description;
}
public String getDoi() {
return doi;
}
public void setDoi(String doi) {
this.doi = doi;
}
public List<Grant> getGrants() {
return grants;
}
public void setGrants(List<Grant> grants) {
this.grants = grants;
}
public List<String> getKeywords() {
return keywords;
}
public void setKeywords(List<String> keywords) {
this.keywords = keywords;
}
public String getLanguage() {
return language;
}
public void setLanguage(String language) {
this.language = language;
}
public String getLicense() {
return license;
}
public void setLicense(String license) {
this.license = license;
}
public PrereserveDoi getPrereserve_doi() {
return prereserve_doi;
}
public void setPrereserve_doi(PrereserveDoi prereserve_doi) {
this.prereserve_doi = prereserve_doi;
}
public String getPublication_date() {
return publication_date;
}
public void setPublication_date(String publication_date) {
this.publication_date = publication_date;
}
public List<String> getReferences() {
return references;
}
public void setReferences(List<String> references) {
this.references = references;
}
public List<RelatedIdentifier> getRelated_identifiers() {
return related_identifiers;
}
public void setRelated_identifiers(List<RelatedIdentifier> related_identifiers) {
this.related_identifiers = related_identifiers;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
}

View File

@ -1,25 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class PrereserveDoi implements Serializable {
private String doi;
private String recid;
public String getDoi() {
return doi;
}
public void setDoi(String doi) {
this.doi = doi;
}
public String getRecid() {
return recid;
}
public void setRecid(String recid) {
this.recid = recid;
}
}

View File

@ -1,43 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
public class RelatedIdentifier implements Serializable {
private String identifier;
private String relation;
private String resource_type;
private String scheme;
public String getIdentifier() {
return identifier;
}
public void setIdentifier(String identifier) {
this.identifier = identifier;
}
public String getRelation() {
return relation;
}
public void setRelation(String relation) {
this.relation = relation;
}
public String getResource_type() {
return resource_type;
}
public void setResource_type(String resource_type) {
this.resource_type = resource_type;
}
public String getScheme() {
return scheme;
}
public void setScheme(String scheme) {
this.scheme = scheme;
}
}

View File

@ -1,118 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.io.Serializable;
import java.util.List;
public class ZenodoModel implements Serializable {
private String conceptrecid;
private String created;
private List<File> files;
private String id;
private Links links;
private Metadata metadata;
private String modified;
private String owner;
private String record_id;
private String state;
private boolean submitted;
private String title;
public String getConceptrecid() {
return conceptrecid;
}
public void setConceptrecid(String conceptrecid) {
this.conceptrecid = conceptrecid;
}
public String getCreated() {
return created;
}
public void setCreated(String created) {
this.created = created;
}
public List<File> getFiles() {
return files;
}
public void setFiles(List<File> files) {
this.files = files;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public Links getLinks() {
return links;
}
public void setLinks(Links links) {
this.links = links;
}
public Metadata getMetadata() {
return metadata;
}
public void setMetadata(Metadata metadata) {
this.metadata = metadata;
}
public String getModified() {
return modified;
}
public void setModified(String modified) {
this.modified = modified;
}
public String getOwner() {
return owner;
}
public void setOwner(String owner) {
this.owner = owner;
}
public String getRecord_id() {
return record_id;
}
public void setRecord_id(String record_id) {
this.record_id = record_id;
}
public String getState() {
return state;
}
public void setState(String state) {
this.state = state;
}
public boolean isSubmitted() {
return submitted;
}
public void setSubmitted(boolean submitted) {
this.submitted = submitted;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
}

View File

@ -1,7 +0,0 @@
package eu.dnetlib.dhp.common.api.zenodo;
import java.util.ArrayList;
public class ZenodoModelList extends ArrayList<ZenodoModel> {
}

View File

@ -212,11 +212,11 @@ public class HttpConnector2 {
.format(
"Unexpected status code: %s errors: %s", urlConn.getResponseCode(),
MAPPER.writeValueAsString(report)));
} catch (MalformedURLException | UnknownHostException e) {
} catch (MalformedURLException e) {
log.error(e.getMessage(), e);
report.put(e.getClass().getName(), e.getMessage());
throw new CollectorException(e.getMessage(), e);
} catch (SocketTimeoutException | SocketException e) {
} catch (SocketTimeoutException | SocketException | UnknownHostException e) {
log.error(e.getMessage(), e);
report.put(e.getClass().getName(), e.getMessage());
backoffAndSleep(getClientParams().getRetryDelay() * retryNumber * 1000);

View File

@ -0,0 +1,70 @@
/*
* Copyright (c) 2024.
* SPDX-FileCopyrightText: © 2023 Consiglio Nazionale delle Ricerche
* SPDX-License-Identifier: AGPL-3.0-or-later
*/
package eu.dnetlib.dhp.schema.oaf;
import org.apache.commons.lang3.builder.EqualsBuilder;
import org.apache.commons.lang3.builder.HashCodeBuilder;
public class HashableStructuredProperty extends StructuredProperty {
private static final long serialVersionUID = 8371670185221126045L;
public static HashableStructuredProperty newInstance(String value, Qualifier qualifier, DataInfo dataInfo) {
if (value == null) {
return null;
}
final HashableStructuredProperty sp = new HashableStructuredProperty();
sp.setValue(value);
sp.setQualifier(qualifier);
sp.setDataInfo(dataInfo);
return sp;
}
public static HashableStructuredProperty newInstance(StructuredProperty sp) {
HashableStructuredProperty hsp = new HashableStructuredProperty();
hsp.setQualifier(sp.getQualifier());
hsp.setValue(sp.getValue());
hsp.setQualifier(sp.getQualifier());
return hsp;
}
public static StructuredProperty toStructuredProperty(HashableStructuredProperty hsp) {
StructuredProperty sp = new StructuredProperty();
sp.setQualifier(hsp.getQualifier());
sp.setValue(hsp.getValue());
sp.setQualifier(hsp.getQualifier());
return sp;
}
@Override
public int hashCode() {
return new HashCodeBuilder(11, 91)
.append(getQualifier().getClassid())
.append(getQualifier().getSchemeid())
.append(getValue())
.hashCode();
}
@Override
public boolean equals(Object obj) {
if (obj == null) {
return false;
}
if (obj == this) {
return true;
}
if (obj.getClass() != getClass()) {
return false;
}
final HashableStructuredProperty rhs = (HashableStructuredProperty) obj;
return new EqualsBuilder()
.append(getQualifier().getClassid(), rhs.getQualifier().getClassid())
.append(getQualifier().getSchemeid(), rhs.getQualifier().getSchemeid())
.append(getValue(), rhs.getValue())
.isEquals();
}
}

View File

@ -43,34 +43,4 @@ public class CleaningFunctions {
return !PidBlacklistProvider.getBlacklist(s.getQualifier().getClassid()).contains(pidValue);
}
/**
* Utility method that normalises PID values on a per-type basis.
* @param pid the PID whose value will be normalised.
* @return the PID containing the normalised value.
*/
public static StructuredProperty normalizePidValue(StructuredProperty pid) {
pid
.setValue(
normalizePidValue(
pid.getQualifier().getClassid(),
pid.getValue()));
return pid;
}
public static String normalizePidValue(String pidType, String pidValue) {
String value = Optional
.ofNullable(pidValue)
.map(String::trim)
.orElseThrow(() -> new IllegalArgumentException("PID value cannot be empty"));
switch (pidType) {
// TODO add cleaning for more PID types as needed
case "doi":
return value.toLowerCase().replaceFirst(DOI_PREFIX_REGEX, DOI_PREFIX);
}
return value;
}
}

View File

@ -6,18 +6,11 @@ import org.apache.commons.lang3.StringUtils;
public class DoiCleaningRule {
public static String clean(final String doi) {
return doi
.toLowerCase()
.replaceAll("\\s", "")
.replaceAll("^doi:", "")
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
}
public static String normalizeDoi(final String input) {
if (input == null)
if (doi == null)
return null;
final String replaced = input
final String replaced = doi
.replaceAll("\\n|\\r|\\t|\\s", "")
.replaceAll("^doi:", "")
.toLowerCase()
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
if (StringUtils.isEmpty(replaced))
@ -32,7 +25,6 @@ public class DoiCleaningRule {
return null;
return ret;
}
}

View File

@ -119,7 +119,7 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.getContext()
.stream()
.filter(c -> !StringUtils.startsWith(c.getId().toLowerCase(), contextId))
.collect(Collectors.toList()));
.collect(Collectors.toCollection(ArrayList::new)));
}
return (T) res;
} else {
@ -563,12 +563,24 @@ public class GraphCleaningFunctions extends CleaningFunctions {
Optional
.ofNullable(i.getPid())
.ifPresent(pid -> {
final Set<StructuredProperty> pids = Sets.newHashSet(pid);
final Set<HashableStructuredProperty> pids = pid
.stream()
.map(HashableStructuredProperty::newInstance)
.collect(Collectors.toCollection(HashSet::new));
Optional
.ofNullable(i.getAlternateIdentifier())
.ifPresent(altId -> {
final Set<StructuredProperty> altIds = Sets.newHashSet(altId);
i.setAlternateIdentifier(Lists.newArrayList(Sets.difference(altIds, pids)));
final Set<HashableStructuredProperty> altIds = altId
.stream()
.map(HashableStructuredProperty::newInstance)
.collect(Collectors.toCollection(HashSet::new));
i
.setAlternateIdentifier(
Sets
.difference(altIds, pids)
.stream()
.map(HashableStructuredProperty::toStructuredProperty)
.collect(Collectors.toList()));
});
});
@ -1003,4 +1015,41 @@ public class GraphCleaningFunctions extends CleaningFunctions {
.orElse(null);
}
/**
* Implements bad and ugly things that we should get rid of ASAP.
*
* @param value
* @return
* @param <T>
*/
public static <T extends Oaf> T dedicatedUglyHacks(T value) {
if (value instanceof OafEntity) {
if (value instanceof Result) {
final Result r = (Result) value;
// Fix for AMS Acta
Optional
.ofNullable(r.getInstance())
.map(
instance -> instance
.stream()
.filter(
i -> Optional
.ofNullable(i.getHostedby())
.map(KeyValue::getKey)
.map(dsId -> dsId.equals("10|re3data_____::4cc76bed7ce2fb95fd8e7a2dfde16016"))
.orElse(false)))
.ifPresent(instance -> instance.forEach(i -> {
if (Optional
.ofNullable(i.getPid())
.map(pid -> pid.stream().noneMatch(p -> p.getValue().startsWith("10.6092/unibo/amsacta")))
.orElse(false)) {
i.setHostedby(UNKNOWN_REPOSITORY);
}
}));
}
}
return value;
}
}

View File

@ -175,7 +175,7 @@ public class IdentifierFactory implements Serializable {
return entity
.getPid()
.stream()
.map(CleaningFunctions::normalizePidValue)
.map(PidCleaner::normalizePidValue)
.filter(CleaningFunctions::pidFilter)
.collect(
Collectors
@ -207,7 +207,7 @@ public class IdentifierFactory implements Serializable {
// filter away PIDs provided by a DS that is not considered an authority for the
// given PID Type
.filter(p -> shouldFilterPidByCriteria(collectedFrom, p, mapHandles))
.map(CleaningFunctions::normalizePidValue)
.map(PidCleaner::normalizePidValue)
.filter(p -> isNotFromDelegatedAuthority(collectedFrom, p))
.filter(CleaningFunctions::pidFilter))
.orElse(Stream.empty());

View File

@ -96,7 +96,7 @@ public class MergeEntitiesComparator implements Comparator<Oaf> {
// id
if (res == 0) {
if (left instanceof OafEntity && right instanceof OafEntity) {
res = ((OafEntity) left).getId().compareTo(((OafEntity) right).getId());
res = ((OafEntity) right).getId().compareTo(((OafEntity) left).getId());
}
}

View File

@ -433,7 +433,10 @@ public class MergeUtils {
// merge datainfo for same context id
merge.setContext(mergeLists(merge.getContext(), enrich.getContext(), trust, Context::getId, (r, l) -> {
r.getDataInfo().addAll(l.getDataInfo());
ArrayList<DataInfo> di = new ArrayList<>();
di.addAll(r.getDataInfo());
di.addAll(l.getDataInfo());
r.setDataInfo(di);
return r;
}));
@ -972,7 +975,7 @@ public class MergeUtils {
private static String extractKeyFromPid(final StructuredProperty pid) {
if (pid == null)
return null;
final StructuredProperty normalizedPid = CleaningFunctions.normalizePidValue(pid);
final StructuredProperty normalizedPid = PidCleaner.normalizePidValue(pid);
return String.format("%s::%s", normalizedPid.getQualifier().getClassid(), normalizedPid.getValue());
}

View File

@ -18,8 +18,8 @@ public class PidValueComparator implements Comparator<StructuredProperty> {
if (right == null)
return -1;
StructuredProperty l = CleaningFunctions.normalizePidValue(left);
StructuredProperty r = CleaningFunctions.normalizePidValue(right);
StructuredProperty l = PidCleaner.normalizePidValue(left);
StructuredProperty r = PidCleaner.normalizePidValue(right);
return Optional
.ofNullable(l.getValue())

View File

@ -28,6 +28,7 @@ import com.jayway.jsonpath.JsonPath;
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
import net.minidev.json.JSONArray;
import scala.collection.JavaConverters;
import scala.collection.Seq;
@ -104,7 +105,7 @@ public class DHPUtils {
public static String generateUnresolvedIdentifier(final String pid, final String pidType) {
final String cleanedPid = CleaningFunctions.normalizePidValue(pidType, pid);
final String cleanedPid = PidCleaner.normalizePidValue(pidType, pid);
return String.format("unresolved::%s::%s", cleanedPid, pidType.toLowerCase().trim());
}

View File

@ -1,109 +0,0 @@
package eu.dnetlib.dhp.common.api;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
@Disabled
class ZenodoAPIClientTest {
private final String URL_STRING = "https://sandbox.zenodo.org/api/deposit/depositions";
private final String ACCESS_TOKEN = "";
private final String CONCEPT_REC_ID = "657113";
private final String depositionId = "674915";
@Test
void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(200, client.uploadOpenDeposition(depositionId));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
Assertions.assertEquals(200, client.sendMretadata(metadata));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewDeposition() throws IOException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newDeposition());
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
Assertions.assertEquals(200, client.sendMretadata(metadata));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewVersionNewName() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/newVersion")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
Assertions.assertEquals(202, client.publish());
}
@Test
void testNewVersionOldName() throws IOException, MissingConceptDoiException {
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
ACCESS_TOKEN);
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
File file = new File(getClass()
.getResource("/eu/dnetlib/dhp/common/api/newVersion2")
.getPath());
InputStream is = new FileInputStream(file);
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
Assertions.assertEquals(202, client.publish());
}
}

View File

@ -29,7 +29,7 @@ class IdentifierFactoryTest {
"publication_doi2.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
verifyIdentifier(
"publication_doi3.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
"publication_doi3.json", "50|pmc_________::e2a339e0e11bfbf55462e14a07f1b304", true);
verifyIdentifier(
"publication_doi4.json", "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66", true);
@ -41,7 +41,7 @@ class IdentifierFactoryTest {
"publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", true);
verifyIdentifier(
"publication_pmc2.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
"publication_pmc2.json", "50|pmc_________::e2a339e0e11bfbf55462e14a07f1b304", true);
verifyIdentifier(
"publication_openapc.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);

View File

@ -177,7 +177,7 @@ class OafMapperUtilsTest {
assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
assertEquals(
ModelConstants.DATASET_RESULTTYPE_CLASSID,
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
((Result) MergeUtils
.merge(p2, d1))
.getResulttype()

View File

@ -29,7 +29,7 @@
},
{
"qualifier": {"classid": "pmc"},
"value": "21459329"
"value": "PMC21459329"
}
]
}

View File

@ -13,7 +13,7 @@
},
{
"qualifier":{"classid":"pmc"},
"value":"21459329"
"value":"PMC21459329"
}
]
}

View File

@ -48,7 +48,7 @@ public class TreeNodeDef implements Serializable {
// function for the evaluation of the node
public TreeNodeStats evaluate(Row doc1, Row doc2, Config conf) {
TreeNodeStats stats = new TreeNodeStats(ignoreUndefined);
TreeNodeStats stats = new TreeNodeStats();
// for each field in the node, it computes the
for (FieldConf fieldConf : fields) {

View File

@ -9,11 +9,8 @@ public class TreeNodeStats implements Serializable {
private Map<String, FieldStats> results; // this is an accumulator for the results of the node
private final boolean ignoreUndefined;
public TreeNodeStats(boolean ignoreUndefined) {
public TreeNodeStats() {
this.results = new HashMap<>();
this.ignoreUndefined = ignoreUndefined;
}
public Map<String, FieldStats> getResults() {
@ -25,10 +22,7 @@ public class TreeNodeStats implements Serializable {
}
public int fieldsCount() {
if (ignoreUndefined)
return this.results.size();
else
return this.results.size() - undefinedCount(); // do not count undefined
}
public int undefinedCount() {
@ -84,23 +78,12 @@ public class TreeNodeStats implements Serializable {
double min = 100.0; // random high value
for (FieldStats fs : this.results.values()) {
if (fs.getResult() < min) {
if (fs.getResult() == -1) {
if (fs.isCountIfUndefined()) {
min = 0.0;
} else {
min = -1;
}
} else {
if (fs.getResult() >= 0.0 || (fs.getResult() == -1 && fs.isCountIfUndefined()))
min = fs.getResult();
}
}
}
if (ignoreUndefined) {
return min == -1.0 ? 0.0 : min;
} else {
return min;
}
}
// if at least one is true, return 1.0
public double or() {
@ -108,12 +91,8 @@ public class TreeNodeStats implements Serializable {
if (fieldStats.getResult() >= fieldStats.getThreshold())
return 1.0;
}
if (!ignoreUndefined && undefinedCount() > 0) {
return -1.0;
} else {
return 0.0;
}
}
// if at least one is false, return 0.0
public double and() {
@ -121,7 +100,7 @@ public class TreeNodeStats implements Serializable {
if (fieldStats.getResult() == -1) {
if (fieldStats.isCountIfUndefined())
return ignoreUndefined ? 0.0 : -1.0;
return 0.0;
} else {
if (fieldStats.getResult() < fieldStats.getThreshold())
return 0.0;

View File

@ -44,10 +44,12 @@ public class TreeProcessor {
TreeNodeStats stats = currentNode.evaluate(doc1, doc2, config);
treeStats.addNodeStats(nextNodeName, stats);
double finalScore = stats.getFinalScore(currentNode.getAggregation());
if (finalScore == -1.0)
// if ignoreUndefined=false the miss is considered as undefined
if (!currentNode.isIgnoreUndefined() && stats.undefinedCount() > 0) {
nextNodeName = currentNode.getUndefined();
else if (finalScore >= currentNode.getThreshold()) {
}
// if ignoreUndefined=true the miss is ignored and the score computed anyway
else if (stats.getFinalScore(currentNode.getAggregation()) >= currentNode.getThreshold()) {
nextNodeName = currentNode.getPositive();
} else {
nextNodeName = currentNode.getNegative();

View File

@ -10,7 +10,6 @@ import java.util.List;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
@ -29,6 +28,7 @@ import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.DoiCleaningRule;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
@ -44,6 +44,10 @@ public class PrepareAffiliationRelations implements Serializable {
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:openaireinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by OpenAIRE";
public static final String BIP_INFERENCE_PROVENANCE = "openaire:affiliation";
public static final String OPENAIRE_DATASOURCE_ID = "10|infrastruct_::f66f1bd369679b5b077dcdf006089556";
public static final String OPENAIRE_DATASOURCE_NAME = "OpenAIRE";
public static final String DOI_URL_PREFIX = "https://doi.org/";
public static final int DOI_URL_PREFIX_LENGTH = 16;
public static <I extends Result> void main(String[] args) throws Exception {
@ -74,6 +78,9 @@ public class PrepareAffiliationRelations implements Serializable {
final String webcrawlInputPath = parser.get("webCrawlInputPath");
log.info("webcrawlInputPath: {}", webcrawlInputPath);
final String publisherInputPath = parser.get("publisherInputPath");
log.info("publisherInputPath: {}", publisherInputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
@ -84,41 +91,72 @@ public class PrepareAffiliationRelations implements Serializable {
isSparkSessionManaged,
spark -> {
Constants.removeOutputDir(spark, outputPath);
createActionSet(
spark, crossrefInputPath, pubmedInputPath, openapcInputPath, dataciteInputPath, webcrawlInputPath,
publisherInputPath, outputPath);
});
}
List<KeyValue> collectedFromCrossref = OafMapperUtils
.listKeyValues(ModelConstants.CROSSREF_ID, "Crossref");
JavaPairRDD<Text, Text> crossrefRelations = prepareAffiliationRelations(
spark, crossrefInputPath, collectedFromCrossref);
private static void createActionSet(SparkSession spark, String crossrefInputPath, String pubmedInputPath,
String openapcInputPath, String dataciteInputPath, String webcrawlInputPath, String publisherlInputPath,
String outputPath) {
List<KeyValue> collectedfromOpenAIRE = OafMapperUtils
.listKeyValues(OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME);
JavaPairRDD<Text, Text> crossrefRelations = prepareAffiliationRelationsNewModel(
spark, crossrefInputPath, collectedfromOpenAIRE);
List<KeyValue> collectedFromPubmed = OafMapperUtils
.listKeyValues(ModelConstants.PUBMED_CENTRAL_ID, "Pubmed");
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
spark, pubmedInputPath, collectedFromPubmed);
spark, pubmedInputPath, collectedfromOpenAIRE);
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
spark, openapcInputPath, collectedFromOpenAPC);
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelationsNewModel(
spark, openapcInputPath, collectedfromOpenAIRE);
List<KeyValue> collectedFromDatacite = OafMapperUtils
.listKeyValues(ModelConstants.DATACITE_ID, "Datacite");
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
spark, dataciteInputPath, collectedFromDatacite);
spark, dataciteInputPath, collectedfromOpenAIRE);
List<KeyValue> collectedFromWebCrawl = OafMapperUtils
.listKeyValues(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME);
JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelations(
spark, webcrawlInputPath, collectedFromWebCrawl);
spark, webcrawlInputPath, collectedfromOpenAIRE);
JavaPairRDD<Text, Text> publisherRelations = prepareAffiliationRelationFromPublisher(
spark, publisherlInputPath, collectedfromOpenAIRE);
crossrefRelations
.union(pubmedRelations)
.union(openAPCRelations)
.union(dataciteRelations)
.union(webCrawlRelations)
.union(publisherRelations)
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
}
private static JavaPairRDD<Text, Text> prepareAffiliationRelationFromPublisherNewModel(SparkSession spark,
String inputPath,
List<KeyValue> collectedfrom) {
Dataset<Row> df = spark
.read()
.schema(
"`DOI` STRING, `Organizations` ARRAY<STRUCT<`PID`:STRING, `Value`:STRING,`Confidence`:DOUBLE, `Status`:STRING>>")
.json(inputPath)
.where("DOI is not null");
return getTextTextJavaPairRDD(collectedfrom, df.selectExpr("DOI", "Organizations as Matchings"));
}
private static JavaPairRDD<Text, Text> prepareAffiliationRelationFromPublisher(SparkSession spark, String inputPath,
List<KeyValue> collectedfrom) {
Dataset<Row> df = spark
.read()
.schema("`DOI` STRING, `Organizations` ARRAY<STRUCT<`RORid`:STRING,`Confidence`:DOUBLE>>")
.json(inputPath)
.where("DOI is not null");
return getTextTextJavaPairRDD(collectedfrom, df.selectExpr("DOI", "Organizations as Matchings"));
});
}
private static <I extends Result> JavaPairRDD<Text, Text> prepareAffiliationRelations(SparkSession spark,
@ -132,6 +170,24 @@ public class PrepareAffiliationRelations implements Serializable {
.json(inputPath)
.where("DOI is not null");
return getTextTextJavaPairRDD(collectedfrom, df);
}
private static <I extends Result> JavaPairRDD<Text, Text> prepareAffiliationRelationsNewModel(SparkSession spark,
String inputPath,
List<KeyValue> collectedfrom) {
// load and parse affiliation relations from HDFS
Dataset<Row> df = spark
.read()
.schema(
"`DOI` STRING, `Matchings` ARRAY<STRUCT<`PID`:STRING, `Value`:STRING,`Confidence`:DOUBLE, `Status`:STRING>>")
.json(inputPath)
.where("DOI is not null");
return getTextTextJavaPairRDDNew(collectedfrom, df);
}
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(List<KeyValue> collectedfrom, Dataset<Row> df) {
// unroll nested arrays
df = df
.withColumn("matching", functions.explode(new Column("Matchings")))
@ -147,7 +203,7 @@ public class PrepareAffiliationRelations implements Serializable {
// DOI to OpenAIRE id
final String paperId = ID_PREFIX
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", row.getAs("doi")));
+ IdentifierFactory.md5(DoiCleaningRule.clean(removePrefix(row.getAs("doi"))));
// ROR id to OpenAIRE id
final String affId = GenerateRorActionSetJob.calculateOpenaireId(row.getAs("rorid"));
@ -179,6 +235,69 @@ public class PrepareAffiliationRelations implements Serializable {
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDDNew(List<KeyValue> collectedfrom, Dataset<Row> df) {
// unroll nested arrays
df = df
.withColumn("matching", functions.explode(new Column("Matchings")))
.select(
new Column("DOI").as("doi"),
new Column("matching.PID").as("pidtype"),
new Column("matching.Value").as("pidvalue"),
new Column("matching.Confidence").as("confidence"),
new Column("matching.Status").as("status"))
.where("status = 'active'");
// prepare action sets for affiliation relations
return df
.toJavaRDD()
.flatMap((FlatMapFunction<Row, Relation>) row -> {
// DOI to OpenAIRE id
final String paperId = ID_PREFIX
+ IdentifierFactory.md5(DoiCleaningRule.clean(removePrefix(row.getAs("doi"))));
// Organization to OpenAIRE identifier
String affId = null;
if (row.getAs("pidtype").equals("ROR"))
// ROR id to OpenIARE id
affId = GenerateRorActionSetJob.calculateOpenaireId(row.getAs("pidvalue"));
else
// getting the OpenOrgs identifier for the organization
affId = row.getAs("pidvalue");
Qualifier qualifier = OafMapperUtils
.qualifier(
BIP_AFFILIATIONS_CLASSID,
BIP_AFFILIATIONS_CLASSNAME,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS);
// format data info; setting `confidence` into relation's `trust`
DataInfo dataInfo = OafMapperUtils
.dataInfo(
false,
BIP_INFERENCE_PROVENANCE,
true,
false,
qualifier,
Double.toString(row.getAs("confidence")));
// return bi-directional relations
return getAffiliationRelationPair(paperId, affId, collectedfrom, dataInfo).iterator();
})
.map(p -> new AtomicAction(Relation.class, p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
}
private static String removePrefix(String doi) {
if (doi.startsWith(DOI_URL_PREFIX))
return doi.substring(DOI_URL_PREFIX_LENGTH);
return doi;
}
private static List<Relation> getAffiliationRelationPair(String paperId, String affId, List<KeyValue> collectedfrom,
DataInfo dataInfo) {
return Arrays

View File

@ -49,6 +49,9 @@ public class ReadCOCI implements Serializable {
final String workingPath = parser.get("inputPath");
log.info("workingPath {}", workingPath);
final String backupPath = parser.get("backupPath");
log.info("backupPath {}", backupPath);
SparkConf sconf = new SparkConf();
Configuration conf = new Configuration();
@ -68,12 +71,14 @@ public class ReadCOCI implements Serializable {
workingPath,
fileSystem,
outputPath,
backupPath,
delimiter);
});
}
private static void doRead(SparkSession spark, String workingPath, FileSystem fileSystem,
String outputPath,
String backupPath,
String delimiter) throws IOException {
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
.listFiles(
@ -107,7 +112,8 @@ public class ReadCOCI implements Serializable {
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
fileSystem.rename(fileStatus.getPath(), new Path("/tmp/miriam/OC/DONE"));
fileSystem.rename(fileStatus.getPath(), new Path(backupPath));
}
}

View File

@ -69,9 +69,12 @@ public class CollectorWorker extends ReportingJob {
scheduleReport(counter);
try (SequenceFile.Writer writer = SequenceFile
.createWriter(this.fileSystem.getConf(), SequenceFile.Writer.file(new Path(outputPath)), SequenceFile.Writer
.keyClass(IntWritable.class), SequenceFile.Writer
.valueClass(Text.class), SequenceFile.Writer.compression(SequenceFile.CompressionType.BLOCK, new DeflateCodec()))) {
.createWriter(
this.fileSystem.getConf(), SequenceFile.Writer.file(new Path(outputPath)), SequenceFile.Writer
.keyClass(IntWritable.class),
SequenceFile.Writer
.valueClass(Text.class),
SequenceFile.Writer.compression(SequenceFile.CompressionType.BLOCK, new DeflateCodec()))) {
final IntWritable key = new IntWritable(counter.get());
final Text value = new Text();
plugin

View File

@ -36,7 +36,9 @@ public class OsfPreprintsCollectorPlugin implements CollectorPlugin {
.map(s -> NumberUtils.toInt(s, PAGE_SIZE_VALUE_DEFAULT))
.orElse(PAGE_SIZE_VALUE_DEFAULT);
if (StringUtils.isBlank(baseUrl)) { throw new CollectorException("Param 'baseUrl' is null or empty"); }
if (StringUtils.isBlank(baseUrl)) {
throw new CollectorException("Param 'baseUrl' is null or empty");
}
final OsfPreprintsIterator it = new OsfPreprintsIterator(baseUrl, pageSize, getClientParams());

View File

@ -54,7 +54,8 @@ public class OsfPreprintsIterator implements Iterator<String> {
@Override
public boolean hasNext() {
synchronized (this.recordQueue) {
while (this.recordQueue.isEmpty() && StringUtils.isNotBlank(this.currentUrl) && this.currentUrl.startsWith("http")) {
while (this.recordQueue.isEmpty() && StringUtils.isNotBlank(this.currentUrl)
&& this.currentUrl.startsWith("http")) {
try {
this.currentUrl = downloadPage(this.currentUrl);
} catch (final CollectorException e) {
@ -63,7 +64,9 @@ public class OsfPreprintsIterator implements Iterator<String> {
}
}
if (!this.recordQueue.isEmpty()) { return true; }
if (!this.recordQueue.isEmpty()) {
return true;
}
return false;
}
@ -112,7 +115,9 @@ public class OsfPreprintsIterator implements Iterator<String> {
}
private Document downloadUrl(final String url, final int attempt) throws CollectorException {
if (attempt > MAX_ATTEMPTS) { throw new CollectorException("Max Number of attempts reached, url:" + url); }
if (attempt > MAX_ATTEMPTS) {
throw new CollectorException("Max Number of attempts reached, url:" + url);
}
if (attempt > 0) {
final int delay = (attempt * 5000);

View File

@ -28,13 +28,19 @@
"paramLongName": "dataciteInputPath",
"paramDescription": "the path to get the input data from Datacite",
"paramRequired": true
},{
},
{
"paramName": "wip",
"paramLongName": "webCrawlInputPath",
"paramDescription": "the path to get the input data from Web Crawl",
"paramRequired": true
}
,
},
{
"paramName": "pub",
"paramLongName": "publisherInputPath",
"paramDescription": "the path to get the input data from publishers",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",

View File

@ -35,5 +35,6 @@ crossrefInputPath=/data/bip-affiliations/crossref-data.json
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
openapcInputPath=/data/bip-affiliations/openapc-data.json
dataciteInputPath=/data/bip-affiliations/datacite-data.json
webCrawlInputPath=/data/bip-affiliations/webCrawl/
outputPath=/tmp/crossref-affiliations-output-v5

View File

@ -21,6 +21,10 @@
<name>webCrawlInputPath</name>
<description>the path where to find the inferred affiliation relations from webCrawl</description>
</property>
<property>
<name>publisherInputPath</name>
<description>the path where to find the inferred affiliation relations from publisher websites</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</description>
@ -117,6 +121,7 @@
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
<arg>--dataciteInputPath</arg><arg>${dataciteInputPath}</arg>
<arg>--webCrawlInputPath</arg><arg>${webCrawlInputPath}</arg>
<arg>--publisherInputPath</arg><arg>${publisherInputPath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>

View File

@ -24,12 +24,19 @@
"paramLongName": "outputPath",
"paramDescription": "the hdfs name node",
"paramRequired": true
}, {
},
{
"paramName": "nn",
"paramLongName": "hdfsNameNode",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
},
{
"paramName": "bp",
"paramLongName": "backupPath",
"paramDescription": "the hdfs path to move the OC data after the extraction",
"paramRequired": true
}
]

View File

@ -129,6 +129,7 @@
</spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/Extracted</arg>
<arg>--outputPath</arg><arg>${inputPath}/JSON</arg>
<arg>--backupPath</arg><arg>${inputPath}/backup</arg>
<arg>--delimiter</arg><arg>${delimiter}</arg>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
</spark>

View File

@ -16,10 +16,11 @@
"paramLongName": "isSparkSessionManged",
"paramDescription": "the hdfs name node",
"paramRequired": false
},{
},
{
"paramName": "nn",
"paramLongName": "nameNode",
"paramDescription": "the hdfs name node",
"paramRequired": true
}
}
]

View File

@ -24,7 +24,7 @@
<decision name="resume_from">
<switch>
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
<case to="reset_workingDir">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
</switch>
</decision>
@ -33,6 +33,14 @@
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="reset_workingDir">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="download"/>
<error to="Kill"/>
</action>
<action name="download">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>

View File

@ -1,4 +1,4 @@
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
@ -8,19 +8,40 @@
<name>database</name>
<description>the PDB Database Working Path</description>
</property>
<property>
<name>targetPath</name>
<description>the Target Working dir path</description>
<name>mdStoreOutputId</name>
<description>the identifier of the cleaned MDStore</description>
</property>
<property>
<name>mdStoreManagerURI</name>
<description>the path of the cleaned mdstore</description>
</property>
</parameters>
<start to="ConvertDB"/>
<start to="StartTransaction"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="StartTransaction">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>NEW_VERSION</arg>
<arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
<capture-output/>
</java>
<ok to="ConvertDB"/>
<error to="RollBack"/>
</action>
<action name="ConvertDB">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -41,11 +62,48 @@
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${sourcePath}</arg>
<arg>--database</arg><arg>${database}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
</spark>
<ok to="CommitVersion"/>
<error to="RollBack"/>
</action>
<action name="CommitVersion">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>COMMIT</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="RollBack">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>ROLLBACK</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="Kill"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -2,5 +2,5 @@
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
{"paramName":"db", "paramLongName":"database", "paramDescription": "should be PDB or UNIPROT", "paramRequired": true},
{"paramName":"p", "paramLongName":"dbPath", "paramDescription": "the path of the database to transform", "paramRequired": true},
{"paramName":"t", "paramLongName":"targetPath", "paramDescription": "the OAF target path ", "paramRequired": true}
{"paramName":"mo", "paramLongName":"mdstoreOutputVersion", "paramDescription": "the oaf path ", "paramRequired": true}
]

View File

@ -1,5 +1,20 @@
[
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
{"paramName":"s", "paramLongName":"sourcePath","paramDescription": "the source Path", "paramRequired": true},
{"paramName":"t", "paramLongName":"targetPath","paramDescription": "the oaf path ", "paramRequired": true}
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the source Path",
"paramRequired": true
},
{
"paramName": "mo",
"paramLongName": "mdstoreOutputVersion",
"paramDescription": "the oaf path ",
"paramRequired": true
}
]

View File

@ -9,34 +9,26 @@
<description>the Working Path</description>
</property>
<property>
<name>targetPath</name>
<description>the OAF MDStore Path</description>
<name>mdStoreOutputId</name>
<description>the identifier of the cleaned MDStore</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
<name>mdStoreManagerURI</name>
<description>the path of the cleaned mdstore</description>
</property>
<property>
<name>resumeFrom</name>
<value>DownloadEBILinks</value>
<value>CreateEBIDataSet</value>
<description>node to start</description>
</property>
</parameters>
<start to="resume_from"/>
<start to="StartTransaction"/>
<decision name="resume_from">
<switch>
<case to="DownloadEBILinks">${wf:conf('resumeFrom') eq 'DownloadEBILinks'}</case>
<case to="CreateEBIDataSet">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
<case to="StartTransaction">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
<default to="DownloadEBILinks"/>
</switch>
</decision>
@ -77,9 +69,29 @@
<move source="${sourcePath}/ebi_links_dataset" target="${sourcePath}/ebi_links_dataset_old"/>
<move source="${workingPath}/links_final" target="${sourcePath}/ebi_links_dataset"/>
</fs>
<ok to="CreateEBIDataSet"/>
<ok to="StartTransaction"/>
<error to="Kill"/>
</action>
<action name="StartTransaction">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>NEW_VERSION</arg>
<arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
<capture-output/>
</java>
<ok to="CreateEBIDataSet"/>
<error to="RollBack"/>
</action>
<action name="CreateEBIDataSet">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
@ -95,11 +107,49 @@
${sparkExtraOPT}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/ebi_links_dataset</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="CommitVersion">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>COMMIT</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="RollBack">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>ROLLBACK</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="Kill"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -332,7 +332,7 @@ case object Crossref2Oaf {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
//MAPPING Crossref DOI into PID
val doi: String = DoiCleaningRule.normalizeDoi((json \ "DOI").extract[String])
val doi: String = DoiCleaningRule.clean((json \ "DOI").extract[String])
result.setPid(
List(
structuredProperty(
@ -504,6 +504,24 @@ case object Crossref2Oaf {
)
}
val is_review = json \ "relation" \ "is-review-of" \ "id"
if (is_review != JNothing) {
instance.setInstancetype(
OafMapperUtils.qualifier(
"0015",
"peerReviewed",
ModelConstants.DNET_REVIEW_LEVELS,
ModelConstants.DNET_REVIEW_LEVELS
)
)
}
if (doi.startsWith("10.3410") || doi.startsWith("10.12703"))
instance.setHostedby(
OafMapperUtils.keyValue(OafMapperUtils.createOpenaireId(10, "openaire____::H1Connect", true), "H1Connect")
)
instance.setAccessright(
decideAccessRight(instance.getLicense, result.getDateofacceptance.getValue)
)
@ -655,7 +673,7 @@ case object Crossref2Oaf {
val doi = input.getString(0)
val rorId = input.getString(1)
val pubId = s"50|${PidType.doi.toString.padTo(12, "_")}::${DoiCleaningRule.normalizeDoi(doi)}"
val pubId = s"50|${PidType.doi.toString.padTo(12, "_")}::${DoiCleaningRule.clean(doi)}"
val affId = GenerateRorActionSetJob.calculateOpenaireId(rorId)
val r: Relation = new Relation

View File

@ -231,7 +231,7 @@ object BioDBToOAF {
def uniprotToOAF(input: String): List[Oaf] = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json = parse(input)
val pid = (json \ "pid").extract[String]
val pid = (json \ "pid").extract[String].trim()
val d = new Dataset

View File

@ -2,12 +2,15 @@ package eu.dnetlib.dhp.sx.bio
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.collection.CollectionUtils
import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
object SparkTransformBioDatabaseToOAF {
@ -25,8 +28,13 @@ object SparkTransformBioDatabaseToOAF {
val dbPath: String = parser.get("dbPath")
log.info("dbPath: {}", database)
val targetPath: String = parser.get("targetPath")
log.info("targetPath: {}", database)
val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
val outputBasePath = cleanedMdStoreVersion.getHdfsPath
log.info("outputBasePath: {}", outputBasePath)
val spark: SparkSession =
SparkSession
@ -43,24 +51,28 @@ object SparkTransformBioDatabaseToOAF {
case "UNIPROT" =>
CollectionUtils.saveDataset(
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.uniprotToOAF(i))),
targetPath
s"$outputBasePath/$MDSTORE_DATA_PATH"
)
case "PDB" =>
CollectionUtils.saveDataset(
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.pdbTOOaf(i))),
targetPath
s"$outputBasePath/$MDSTORE_DATA_PATH"
)
case "SCHOLIX" =>
CollectionUtils.saveDataset(
spark.read.load(dbPath).as[ScholixResolved].map(i => BioDBToOAF.scholixResolvedToOAF(i)),
targetPath
s"$outputBasePath/$MDSTORE_DATA_PATH"
)
case "CROSSREF_LINKS" =>
CollectionUtils.saveDataset(
spark.createDataset(sc.textFile(dbPath).map(i => BioDBToOAF.crossrefLinksToOaf(i))),
targetPath
s"$outputBasePath/$MDSTORE_DATA_PATH"
)
}
val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
val mdStoreSize = df.count
writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
}
}

View File

@ -9,6 +9,9 @@ import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
object SparkEBILinksToOaf {
@ -32,8 +35,13 @@ object SparkEBILinksToOaf {
import spark.implicits._
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val targetPath = parser.get("targetPath")
log.info(s"targetPath -> $targetPath")
val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
val outputBasePath = cleanedMdStoreVersion.getHdfsPath
log.info("outputBasePath: {}", outputBasePath)
implicit val PMEncoder: Encoder[Oaf] = Encoders.kryo(classOf[Oaf])
val ebLinks: Dataset[EBILinkItem] = spark.read
@ -46,7 +54,10 @@ object SparkEBILinksToOaf {
.flatMap(j => BioDBToOAF.parse_ebi_links(j.links))
.filter(p => BioDBToOAF.EBITargetLinksFilter(p))
.flatMap(p => BioDBToOAF.convertEBILinksToOaf(p)),
targetPath
s"$outputBasePath/$MDSTORE_DATA_PATH"
)
val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
val mdStoreSize = df.count
writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
}
}

View File

@ -30,6 +30,7 @@ import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
public class PrepareAffiliationRelationsTest {
@ -74,21 +75,34 @@ public class PrepareAffiliationRelationsTest {
@Test
void testMatch() throws Exception {
String crossrefAffiliationRelationPath = getClass()
String crossrefAffiliationRelationPathNew = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
String crossrefAffiliationRelationPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror_old.json")
.getPath();
String publisherAffiliationRelationPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/publishers")
.getPath();
String publisherAffiliationRelationOldPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/publichers_old")
.getPath();
String outputPath = workingDir.toString() + "/actionSet";
PrepareAffiliationRelations
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-crossrefInputPath", crossrefAffiliationRelationPath,
"-crossrefInputPath", crossrefAffiliationRelationPathNew,
"-pubmedInputPath", crossrefAffiliationRelationPath,
"-openapcInputPath", crossrefAffiliationRelationPath,
"-openapcInputPath", crossrefAffiliationRelationPathNew,
"-dataciteInputPath", crossrefAffiliationRelationPath,
"-webCrawlInputPath", crossrefAffiliationRelationPath,
"-publisherInputPath", publisherAffiliationRelationOldPath,
"-outputPath", outputPath
});
@ -99,13 +113,8 @@ public class PrepareAffiliationRelationsTest {
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
// for (Relation r : tmp.collect()) {
// System.out.println(
// r.getSource() + "\t" + r.getTarget() + "\t" + r.getRelType() + "\t" + r.getRelClass() + "\t" + r.getSubRelType() + "\t" + r.getValidationDate() + "\t" + r.getDataInfo().getTrust() + "\t" + r.getDataInfo().getInferred()
// );
// }
// count the number of relations
assertEquals(120, tmp.count());
assertEquals(150, tmp.count());// 18 + 24 *3 + 30 * 2 =
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
dataset.createOrReplaceTempView("result");
@ -116,7 +125,7 @@ public class PrepareAffiliationRelationsTest {
// verify that we have equal number of bi-directional relations
Assertions
.assertEquals(
60, execVerification
75, execVerification
.filter(
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
.collectAsList()
@ -124,26 +133,56 @@ public class PrepareAffiliationRelationsTest {
Assertions
.assertEquals(
60, execVerification
75, execVerification
.filter(
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
.collectAsList()
.size());
// check confidence value of a specific relation
String sourceDOI = "10.1061/(asce)0733-9399(2002)128:7(759)";
String sourceDOI = "10.1089/10872910260066679";
final String sourceOpenaireId = ID_PREFIX
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", sourceDOI));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", sourceDOI));
Assertions
.assertEquals(
"0.7071067812", execVerification
"1.0", execVerification
.filter(
"source='" + sourceOpenaireId + "'")
.collectAsList()
.get(0)
.getString(4));
final String publisherid = ID_PREFIX
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1089/10872910260066679"));
final String rorId = "20|ror_________::" + IdentifierFactory.md5("https://ror.org/05cf8a891");
Assertions
.assertEquals(
2, execVerification.filter("source = '" + publisherid + "' and target = '" + rorId + "'").count());
Assertions
.assertEquals(
1, execVerification
.filter(
"source = '" + ID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue("doi", "10.1007/s00217-010-1268-9"))
+ "' and target = '" + "20|ror_________::"
+ IdentifierFactory.md5("https://ror.org/03265fv13") + "'")
.count());
Assertions
.assertEquals(
3, execVerification
.filter(
"source = '" + ID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue("doi", "10.1007/3-540-47984-8_14"))
+ "' and target = '" + "20|ror_________::"
+ IdentifierFactory.md5("https://ror.org/00a0n9e72") + "'")
.count());
}
}

View File

@ -31,6 +31,7 @@ import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
public class CreateOpenCitationsASTest {
@ -280,17 +281,17 @@ public class CreateOpenCitationsASTest {
@Test
void testRelationsSourceTargetCouple() throws Exception {
final String doi1 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
final String doi2 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
final String doi3 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
final String doi4 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
final String doi5 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
final String doi6 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
String inputPath = getClass()
.getResource(

View File

@ -77,13 +77,13 @@ public class RemapTest {
MapOCIdsInPids
.main(
new String[] {
"-isSparkSessionManged",
"--isSparkSessionManged",
Boolean.FALSE.toString(),
"-inputPath",
"--inputPath",
inputPath,
"-outputPath",
"--outputPath",
workingDir.toString() + "/out/",
"-nameNode", "input1;input2;input3;input4;input5"
"--nameNode", "hdfs://localhost"
});
}

View File

@ -28,6 +28,7 @@ import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
/**
* @author miriam.baglioni
@ -270,17 +271,17 @@ public class CreateTAActionSetTest {
@Test
void testRelationsSourceTargetCouple() throws Exception {
final String doi1 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
final String doi2 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
final String doi3 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
final String doi4 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
final String doi5 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
final String doi6 = "50|doi_________::"
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
String inputPath = getClass()
.getResource(

View File

@ -50,7 +50,8 @@ public class OsfPreprintsCollectorPluginTest {
@Test
@Disabled
void test_one() throws CollectorException {
this.plugin.collect(this.api, new AggregatorReport())
this.plugin
.collect(this.api, new AggregatorReport())
.limit(1)
.forEach(log::info);
}
@ -95,7 +96,8 @@ public class OsfPreprintsCollectorPluginTest {
final HttpConnector2 connector = new HttpConnector2();
try {
final String res = connector.getInputSource("https://api.osf.io/v2/preprints/ydtzx/contributors/?format=json");
final String res = connector
.getInputSource("https://api.osf.io/v2/preprints/ydtzx/contributors/?format=json");
System.out.println(res);
fail();
} catch (final Throwable e) {

View File

@ -1,9 +1,10 @@
{"DOI":"10.1061\/(asce)0733-9399(2002)128:7(759)","Matchings":[{"RORid":"https:\/\/ror.org\/03yxnpp24","Confidence":0.7071067812},{"RORid":"https:\/\/ror.org\/01teme464","Confidence":0.89}]}
{"DOI":"10.1105\/tpc.8.3.343","Matchings":[{"RORid":"https:\/\/ror.org\/02k40bc56","Confidence":0.7071067812}]}
{"DOI":"10.1161\/01.cir.0000013305.01850.37","Matchings":[{"RORid":"https:\/\/ror.org\/00qjgza05","Confidence":1}]}
{"DOI":"10.1142\/s021821650200186x","Matchings":[{"RORid":"https:\/\/ror.org\/035xkbk20","Confidence":1},{"RORid":"https:\/\/ror.org\/05apxxy63","Confidence":1}]}
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(575)","Matchings":[{"RORid":"https:\/\/ror.org\/04j198w64","Confidence":0.82}]}
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(588)","Matchings":[{"RORid":"https:\/\/ror.org\/03m8km719","Confidence":0.8660254038},{"RORid":"https:\/\/ror.org\/02aze4h65","Confidence":0.87}]}
{"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]}
{"DOI": "10.1080/13669877.2015.1042504", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/03265fv13"}]}
{"DOI": "10.1007/3-540-47984-8_14", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/00a0n9e72"}]}
{"DOI":"10.1021\/ac020069k","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/01f5ytq51","Status":"active","Confidence":1}]}
{"DOI":"10.1161\/01.cir.0000013846.72805.7e","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/02pttbw34","Status":"active","Confidence":1}]}
{"DOI":"10.1161\/hy02t2.102992","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/00qqv6244","Status":"active","Confidence":1},{"PID":"ROR","Value":"https:\/\/ror.org\/00p991c53","Status":"active","Confidence":1}]}
{"DOI":"10.1126\/science.1073633","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/03xez1567","Status":"active","Confidence":1},{"PID":"ROR","Value":"https:\/\/ror.org\/006w34k90","Status":"active","Confidence":1}]}
{"DOI":"10.1089\/10872910260066679","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/05cf8a891","Status":"active","Confidence":1}]}
{"DOI":"10.1108\/02656719610116117","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/03mnm0t94","Status":"active","Confidence":1},{"PID":"ROR","Value":"https:\/\/ror.org\/007tn5k56","Status":"active","Confidence":1}]}
{"DOI":"10.1080\/01443610050111986","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/001x4vz59","Status":"active","Confidence":1},{"PID":"ROR","Value":"https:\/\/ror.org\/01tmqtf75","Status":"active","Confidence":1}]}
{"DOI":"10.1021\/cm020118+","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/02cf1je33","Confidence":1,"Status":"inactive"},{"PID":"ROR","Value":"https:\/\/ror.org\/01hvx5h04","Confidence":1,"Status":"active"}]}
{"DOI":"10.1161\/hc1202.104524","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/040r8fr65","Status":"active","Confidence":1},{"PID":"ROR","Value":"https:\/\/ror.org\/04fctr677","Status":"active","Confidence":1}]}
{"DOI":"10.1021\/ma011134f","Matchings":[{"PID":"ROR","Value":"https:\/\/ror.org\/04tj63d06","Status":"active","Confidence":1}]}

View File

@ -0,0 +1,9 @@
{"DOI":"10.1061\/(asce)0733-9399(2002)128:7(759)","Matchings":[{"RORid":"https:\/\/ror.org\/03yxnpp24","Confidence":0.7071067812},{"RORid":"https:\/\/ror.org\/01teme464","Confidence":0.89}]}
{"DOI":"10.1105\/tpc.8.3.343","Matchings":[{"RORid":"https:\/\/ror.org\/02k40bc56","Confidence":0.7071067812}]}
{"DOI":"10.1161\/01.cir.0000013305.01850.37","Matchings":[{"RORid":"https:\/\/ror.org\/00qjgza05","Confidence":1}]}
{"DOI":"10.1142\/s021821650200186x","Matchings":[{"RORid":"https:\/\/ror.org\/035xkbk20","Confidence":1},{"RORid":"https:\/\/ror.org\/05apxxy63","Confidence":1}]}
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(575)","Matchings":[{"RORid":"https:\/\/ror.org\/04j198w64","Confidence":0.82}]}
{"DOI":"10.1061\/(asce)0733-9372(2002)128:7(588)","Matchings":[{"RORid":"https:\/\/ror.org\/03m8km719","Confidence":0.8660254038},{"RORid":"https:\/\/ror.org\/02aze4h65","Confidence":0.87}]}
{"DOI":"10.1161\/hy0202.103001","Matchings":[{"RORid":"https:\/\/ror.org\/057xtrt18","Confidence":0.7071067812}]}
{"DOI": "10.1080/13669877.2015.1042504", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/03265fv13"}]}
{"DOI": "https://doi.org/10.1007/3-540-47984-8_14", "Matchings": [{"Confidence": 1.0, "RORid": "https://ror.org/00a0n9e72"}]}

View File

@ -0,0 +1,6 @@
{"DOI": "10.1007/s00217-010-1268-9", "Authors": [{"Name": {"Full": "Martin Zarnkow", "First": null, "Last": null}, "Raw_affiliations": ["TU M\u00fcnchen, Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Andrea Faltermaier", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Werner Back", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Technologie der Brauerei I"], "Organization_PIDs": []}, {"Name": {"Full": "Martina Gastl", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Elkek K. Arendt", "First": null, "Last": null}, "Raw_affiliations": ["University College Cork"], "Organization_PIDs": [{"RORid": "https://ror.org/03265fv13", "Confidence": 1}]}], "Organizations": [{"RORid": "https://ror.org/03265fv13", "Confidence": 1}]}
{"DOI": "10.1007/BF01154707", "Authors": [{"Name": {"Full": "Buggy, M.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Materials Science and Technology, University of Limerick, Limerick, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/00a0n9e72", "Confidence": 1}]}, {"Name": {"Full": "Carew, A.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Materials Science and Technology, University of Limerick, Limerick, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/00a0n9e72", "Confidence": 1}]}], "Organizations": [{"RORid": "https://ror.org/00a0n9e72", "Confidence": 1}]}
{"DOI": "10.1007/s10237-017-0974-7", "Authors": [{"Name": {"Full": "Donnacha J. McGrath", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/03bea9k73", "Confidence": 1}]}, {"Name": {"Full": "Anja Lena Thiebes", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"RORid": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"RORid": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Christian G. Cornelissen", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"RORid": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"RORid": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Barry O\u2019Brien", "First": null, "Last": null}, "Raw_affiliations": ["Department for Internal Medicine \u2013 Section for Pneumology, Medical Faculty, RWTH Aachen University, Aachen, Germany"], "Organization_PIDs": [{"RORid": "https://ror.org/04xfq0f34", "Confidence": 1}]}, {"Name": {"Full": "Stefan Jockenhoevel", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/03bea9k73", "Confidence": 1}]}, {"Name": {"Full": "Mark Bruzzi", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"RORid": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"RORid": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Peter E. McHugh", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/03bea9k73", "Confidence": 1}]}], "Organizations": [{"RORid": "https://ror.org/03bea9k73", "Confidence": 1}, {"RORid": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"RORid": "https://ror.org/04xfq0f34", "Confidence": 0.87}, {"RORid": "https://ror.org/04xfq0f34", "Confidence": 1}]}
{"DOI": "10.1007/BF03168973", "Authors": [{"Name": {"Full": "Sheehan, G.", "First": null, "Last": null}, "Raw_affiliations": ["Dept of Infectious Diseases, Mater Misercordiae Hospital, Dublin 7"], "Organization_PIDs": []}, {"Name": {"Full": "Chew, N.", "First": null, "Last": null}, "Raw_affiliations": ["Dept of Infectious Diseases, Mater Misercordiae Hospital, Dublin 7"], "Organization_PIDs": []}], "Organizations": []}
{"DOI": "10.1007/s00338-009-0480-1", "Authors": [{"Name": {"Full": "Gleason, D. F.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biology, Georgia Southern University, Statesboro, USA"], "Organization_PIDs": [{"RORid": "https://ror.org/04agmb972", "Confidence": 1}]}, {"Name": {"Full": "Danilowicz, B. S.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biology, Georgia Southern University, Statesboro, USA"], "Organization_PIDs": [{"RORid": "https://ror.org/04agmb972", "Confidence": 1}]}, {"Name": {"Full": "Nolan, C. J.", "First": null, "Last": null}, "Raw_affiliations": ["School of Biology and Environmental Science, University College Dublin, Dublin 4, Ireland"], "Organization_PIDs": [{"RORid": "https://ror.org/05m7pjf47", "Confidence": 1}]}], "Organizations": [{"RORid": "https://ror.org/04agmb972", "Confidence": 1}, {"RORid": "https://ror.org/05m7pjf47", "Confidence": 1}]}
{"DOI": "10.1007/s10993-010-9187-y", "Authors": [{"Name": {"Full": "Martin Howard", "First": null, "Last": null}, "Raw_affiliations": ["University College Cork"], "Organization_PIDs": [{"RORid": "https://ror.org/03265fv13", "Confidence": 1}]}], "Organizations": [{"RORid": "https://ror.org/03265fv13", "Confidence": 1}]}

View File

@ -0,0 +1,6 @@
{"DOI": "10.1007/s00217-010-1268-9", "Authors": [{"Name": {"Full": "Martin Zarnkow", "First": null, "Last": null}, "Raw_affiliations": ["TU M\u00fcnchen, Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Andrea Faltermaier", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Werner Back", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Technologie der Brauerei I"], "Organization_PIDs": []}, {"Name": {"Full": "Martina Gastl", "First": null, "Last": null}, "Raw_affiliations": ["Lehrstuhl f\u00fcr Brau- und Getr\u00e4nketechnologie"], "Organization_PIDs": []}, {"Name": {"Full": "Elkek K. Arendt", "First": null, "Last": null}, "Raw_affiliations": ["University College Cork"], "Organization_PIDs": [{"Value": "https://ror.org/03265fv13", "Confidence": 1}]}], "Organizations": [{"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/03265fv13", "Confidence": 1}]}
{"DOI": "10.1007/BF01154707", "Authors": [{"Name": {"Full": "Buggy, M.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Materials Science and Technology, University of Limerick, Limerick, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/00a0n9e72", "Confidence": 1}]}, {"Name": {"Full": "Carew, A.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Materials Science and Technology, University of Limerick, Limerick, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/00a0n9e72", "Confidence": 1}]}], "Organizations": [{"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/00a0n9e72", "Confidence": 1}]}
{"DOI": "10.1007/s10237-017-0974-7", "Authors": [{"Name": {"Full": "Donnacha J. McGrath", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/03bea9k73", "Confidence": 1}]}, {"Name": {"Full": "Anja Lena Thiebes", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"Value": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"Value": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Christian G. Cornelissen", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"Value": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"Value": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Barry O\u2019Brien", "First": null, "Last": null}, "Raw_affiliations": ["Department for Internal Medicine \u2013 Section for Pneumology, Medical Faculty, RWTH Aachen University, Aachen, Germany"], "Organization_PIDs": [{"Value": "https://ror.org/04xfq0f34", "Confidence": 1}]}, {"Name": {"Full": "Stefan Jockenhoevel", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/03bea9k73", "Confidence": 1}]}, {"Name": {"Full": "Mark Bruzzi", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biohybrid and Medical Textiles (BioTex), AME-Helmholtz Institute for Biomedical Engineering, ITA-Institut f\u00fcr Textiltechnik, RWTH Aachen University and at AMIBM Maastricht University, Maastricht, The Netherlands, Aachen, Germany"], "Organization_PIDs": [{"Value": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"Value": "https://ror.org/04xfq0f34", "Confidence": 0.87}]}, {"Name": {"Full": "Peter E. McHugh", "First": null, "Last": null}, "Raw_affiliations": ["Biomechanics Research Centre (BMEC), Biomedical Engineering, College of Engineering and Informatics, NUI Galway, Galway, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/03bea9k73", "Confidence": 1}]}], "Organizations": [{"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/03bea9k73", "Confidence": 1}, {"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/02jz4aj89", "Confidence": 0.82}, {"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/04xfq0f34", "Confidence": 0.87}, {"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/04xfq0f34", "Confidence": 1}]}
{"DOI": "10.1007/BF03168973", "Authors": [{"Name": {"Full": "Sheehan, G.", "First": null, "Last": null}, "Raw_affiliations": ["Dept of Infectious Diseases, Mater Misercordiae Hospital, Dublin 7"], "Organization_PIDs": []}, {"Name": {"Full": "Chew, N.", "First": null, "Last": null}, "Raw_affiliations": ["Dept of Infectious Diseases, Mater Misercordiae Hospital, Dublin 7"], "Organization_PIDs": []}], "Organizations": []}
{"DOI": "10.1007/s00338-009-0480-1", "Authors": [{"Name": {"Full": "Gleason, D. F.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biology, Georgia Southern University, Statesboro, USA"], "Organization_PIDs": [{"Value": "https://ror.org/04agmb972", "Confidence": 1}]}, {"Name": {"Full": "Danilowicz, B. S.", "First": null, "Last": null}, "Raw_affiliations": ["Department of Biology, Georgia Southern University, Statesboro, USA"], "Organization_PIDs": [{"Value": "https://ror.org/04agmb972", "Confidence": 1}]}, {"Name": {"Full": "Nolan, C. J.", "First": null, "Last": null}, "Raw_affiliations": ["School of Biology and Environmental Science, University College Dublin, Dublin 4, Ireland"], "Organization_PIDs": [{"Value": "https://ror.org/05m7pjf47", "Confidence": 1}]}], "Organizations": [{"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/04agmb972", "Confidence": 1}, {"Provenance":"AffRo","PID":"ROR","Status":"active","Value": "https://ror.org/05m7pjf47", "Confidence": 1}]}
{"DOI": "10.1007/s10993-010-9187-y", "Authors": [{"Name": {"Full": "Martin Howard", "First": null, "Last": null}, "Raw_affiliations": ["University College Cork"], "Organization_PIDs": [{"Value": "https://ror.org/03265fv13", "Confidence": 1}]}], "Organizations": [{"PID":"ROR","Status":"active","Value": "https://ror.org/03265fv13", "Confidence": 1}]}

View File

@ -1,15 +1,44 @@
{"pdb": "1CW0", "title": "crystal structure analysis of very short patch repair (vsr) endonuclease in complex with a duplex dna", "authors": ["S.E.Tsutakawa", "H.Jingami", "K.Morikawa"], "doi": "10.1016/S0092-8674(00)81550-0", "pmid": "10612397"}
{"pdb": "2CWW", "title": "crystal structure of thermus thermophilus ttha1280, a putative sam- dependent rna methyltransferase, in complex with s-adenosyl-l- homocysteine", "authors": ["A.A.Pioszak", "K.Murayama", "N.Nakagawa", "A.Ebihara", "S.Kuramitsu", "M.Shirouzu", "S.Yokoyama", "Riken Structural Genomics/proteomics Initiative (Rsgi)"], "doi": "10.1107/S1744309105029842", "pmid": "16511182"}
{"pdb": "6CWE", "title": "structure of alpha-gsa[8,6p] bound by cd1d and in complex with the va14vb8.2 tcr", "authors": ["J.Wang", "D.Zajonc"], "doi": null, "pmid": null}
{"pdb": "5CWS", "title": "crystal structure of the intact chaetomium thermophilum nsp1-nup49- nup57 channel nucleoporin heterotrimer bound to its nic96 nuclear pore complex attachment site", "authors": ["C.J.Bley", "S.Petrovic", "M.Paduch", "V.Lu", "A.A.Kossiakoff", "A.Hoelz"], "doi": "10.1126/SCIENCE.AAC9176", "pmid": "26316600"}
{"pdb": "5CWE", "title": "structure of cyp107l2 from streptomyces avermitilis with lauric acid", "authors": ["T.-V.Pham", "S.-H.Han", "J.-H.Kim", "D.-H.Kim", "L.-W.Kang"], "doi": null, "pmid": null}
{"pdb": "7CW4", "title": "acetyl-coa acetyltransferase from bacillus cereus atcc 14579", "authors": ["J.Hong", "K.J.Kim"], "doi": "10.1016/J.BBRC.2020.09.048", "pmid": "32972748"}
{"pdb": "2CWP", "title": "crystal structure of metrs related protein from pyrococcus horikoshii", "authors": ["K.Murayama", "M.Kato-Murayama", "M.Shirouzu", "S.Yokoyama", "Riken StructuralGenomics/proteomics Initiative (Rsgi)"], "doi": null, "pmid": null}
{"pdb": "2CW7", "title": "crystal structure of intein homing endonuclease ii", "authors": ["H.Matsumura", "H.Takahashi", "T.Inoue", "H.Hashimoto", "M.Nishioka", "S.Fujiwara", "M.Takagi", "T.Imanaka", "Y.Kai"], "doi": "10.1002/PROT.20858", "pmid": "16493661"}
{"pdb": "1CWU", "title": "brassica napus enoyl acp reductase a138g mutant complexed with nad+ and thienodiazaborine", "authors": ["A.Roujeinikova", "J.B.Rafferty", "D.W.Rice"], "doi": "10.1074/JBC.274.43.30811", "pmid": "10521472"}
{"pdb": "3CWN", "title": "escherichia coli transaldolase b mutant f178y", "authors": ["T.Sandalova", "G.Schneider", "A.Samland"], "doi": "10.1074/JBC.M803184200", "pmid": "18687684"}
{"pdb": "1CWL", "title": "human cyclophilin a complexed with 4 4-hydroxy-meleu cyclosporin", "authors": ["V.Mikol", "J.Kallen", "P.Taylor", "M.D.Walkinshaw"], "doi": "10.1006/JMBI.1998.2108", "pmid": "9769216"}
{"pdb": "3CW2", "title": "crystal structure of the intact archaeal translation initiation factor 2 from sulfolobus solfataricus .", "authors": ["E.A.Stolboushkina", "S.V.Nikonov", "A.D.Nikulin", "U.Blaesi", "D.J.Manstein", "R.V.Fedorov", "M.B.Garber", "O.S.Nikonov"], "doi": "10.1016/J.JMB.2008.07.039", "pmid": "18675278"}
{"pdb": "3CW9", "title": "4-chlorobenzoyl-coa ligase/synthetase in the thioester-forming conformation, bound to 4-chlorophenacyl-coa", "authors": ["A.S.Reger", "J.Cao", "R.Wu", "D.Dunaway-Mariano", "A.M.Gulick"], "doi": "10.1021/BI800696Y", "pmid": "18620418"}
{"pdb": "3CWU", "title": "crystal structure of an alka host/guest complex 2'-fluoro-2'-deoxy-1, n6-ethenoadenine:thymine base pair", "authors": ["B.R.Bowman", "S.Lee", "S.Wang", "G.L.Verdine"], "doi": "10.1016/J.STR.2008.04.012", "pmid": "18682218"}
{"pdb": "5CWF", "title": "crystal structure of de novo designed helical repeat protein dhr8", "authors": ["G.Bhabha", "D.C.Ekiert"], "doi": "10.1038/NATURE16162", "pmid": "26675729"}
{"classification": "Signaling protein", "pdb": "5NM4", "deposition_date": "2017-04-05", "title": "A2a adenosine receptor room-temperature structure determined by serial Femtosecond crystallography", "Keywords": ["Oom-temperature", " serial crystallography", " signaling protein"], "authors": ["T.weinert", "R.cheng", "D.james", "D.gashi", "P.nogly", "K.jaeger", "M.hennig", "", "J.standfuss"], "pmid": "28912485", "doi": "10.1038/S41467-017-00630-4"}
{"classification": "Oxidoreductase/oxidoreductase inhibitor", "pdb": "4KN3", "deposition_date": "2013-05-08", "title": "Structure of the y34ns91g double mutant of dehaloperoxidase from Amphitrite ornata with 2,4,6-trichlorophenol", "Keywords": ["Lobin", " oxygen storage", " peroxidase", " oxidoreductase", " oxidoreductase-", "Oxidoreductase inhibitor complex"], "authors": ["C.wang", "L.lovelace", "L.lebioda"], "pmid": "23952341", "doi": "10.1021/BI400627W"}
{"classification": "Transport protein", "pdb": "8HKM", "deposition_date": "2022-11-27", "title": "Ion channel", "Keywords": ["On channel", " transport protein"], "authors": ["D.h.jiang", "J.t.zhang"], "pmid": "37494189", "doi": "10.1016/J.CELREP.2023.112858"}
{"classification": "Signaling protein", "pdb": "6JT1", "deposition_date": "2019-04-08", "title": "Structure of human soluble guanylate cyclase in the heme oxidised State", "Keywords": ["Oluble guanylate cyclase", " signaling protein"], "authors": ["L.chen", "Y.kang", "R.liu", "J.-x.wu"], "pmid": "31514202", "doi": "10.1038/S41586-019-1584-6"}
{"classification": "Immune system", "pdb": "7OW6", "deposition_date": "2021-06-16", "title": "Crystal structure of a tcr in complex with hla-a*11:01 bound to kras G12d peptide (vvvgadgvgk)", "Keywords": ["La", " kras", " tcr", " immune system"], "authors": ["V.karuppiah", "R.a.robinson"], "doi": "10.1038/S41467-022-32811-1"}
{"classification": "Biosynthetic protein", "pdb": "5EQ8", "deposition_date": "2015-11-12", "title": "Crystal structure of medicago truncatula histidinol-phosphate Phosphatase (mthpp) in complex with l-histidinol", "Keywords": ["Istidine biosynthesis", " metabolic pathways", " dimer", " plant", "", "Biosynthetic protein"], "authors": ["M.ruszkowski", "Z.dauter"], "pmid": "26994138", "doi": "10.1074/JBC.M115.708727"}
{"classification": "De novo protein", "pdb": "8CWA", "deposition_date": "2022-05-18", "title": "Solution nmr structure of 8-residue rosetta-designed cyclic peptide D8.21 in cdcl3 with cis/trans switching (tc conformation, 53%)", "Keywords": ["Yclic peptide", " non natural amino acids", " cis/trans", " switch peptides", "", "De novo design", "Membrane permeability", "De novo protein"], "authors": ["T.a.ramelot", "R.tejero", "G.t.montelione"], "pmid": "36041435", "doi": "10.1016/J.CELL.2022.07.019"}
{"classification": "Hydrolase", "pdb": "3R6M", "deposition_date": "2011-03-21", "title": "Crystal structure of vibrio parahaemolyticus yeaz", "Keywords": ["Ctin/hsp70 nucleotide-binding fold", " bacterial resuscitation", " viable", "But non-culturable state", "Resuscitation promoting factor", "Ygjd", "", "Yjee", "Vibrio parahaemolyticus", "Hydrolase"], "authors": ["A.roujeinikova", "I.aydin"], "pmid": "21858042", "doi": "10.1371/JOURNAL.PONE.0023245"}
{"classification": "Hydrolase", "pdb": "2W5J", "deposition_date": "2008-12-10", "title": "Structure of the c14-rotor ring of the proton translocating Chloroplast atp synthase", "Keywords": ["Ydrolase", " chloroplast", " atp synthase", " lipid-binding", " cf(0)", " membrane", "", "Transport", "Formylation", "Energy transduction", "Hydrogen ion transport", "", "Ion transport", "Transmembrane", "Membrane protein"], "authors": ["M.vollmar", "D.schlieper", "M.winn", "C.buechner", "G.groth"], "pmid": "19423706", "doi": "10.1074/JBC.M109.006916"}
{"classification": "De novo protein", "pdb": "4GLU", "deposition_date": "2012-08-14", "title": "Crystal structure of the mirror image form of vegf-a", "Keywords": ["-protein", " covalent dimer", " cysteine knot protein", " growth factor", " de", "Novo protein"], "authors": ["K.mandal", "M.uppalapati", "D.ault-riche", "J.kenney", "J.lowitz", "S.sidhu", "", "S.b.h.kent"], "pmid": "22927390", "doi": "10.1073/PNAS.1210483109"}
{"classification": "Hydrolase/hydrolase inhibitor", "pdb": "3WYL", "deposition_date": "2014-09-01", "title": "Crystal structure of the catalytic domain of pde10a complexed with 5- Methoxy-3-(1-phenyl-1h-pyrazol-5-yl)-1-(3-(trifluoromethyl)phenyl) Pyridazin-4(1h)-one", "Keywords": ["Ydrolase-hydrolase inhibitor complex"], "authors": ["H.oki", "Y.hayano"], "pmid": "25384088", "doi": "10.1021/JM5013648"}
{"classification": "Isomerase", "pdb": "5BOR", "deposition_date": "2015-05-27", "title": "Structure of acetobacter aceti pure-s57c, sulfonate form", "Keywords": ["Cidophile", " pure", " purine biosynthesis", " isomerase"], "authors": ["K.l.sullivan", "T.j.kappock"]}
{"classification": "Hydrolase", "pdb": "1X0C", "deposition_date": "2005-03-17", "title": "Improved crystal structure of isopullulanase from aspergillus niger Atcc 9642", "Keywords": ["Ullulan", " glycoside hydrolase family 49", " glycoprotein", " hydrolase"], "authors": ["M.mizuno", "T.tonozuka", "A.yamamura", "Y.miyasaka", "H.akeboshi", "S.kamitori", "", "A.nishikawa", "Y.sakano"], "pmid": "18155243", "doi": "10.1016/J.JMB.2007.11.098"}
{"classification": "Oxidoreductase", "pdb": "7CUP", "deposition_date": "2020-08-23", "title": "Structure of 2,5-dihydroxypridine dioxygenase from pseudomonas putida Kt2440", "Keywords": ["On-heme dioxygenase", " oxidoreductase"], "authors": ["G.q.liu", "H.z.tang"]}
{"classification": "Ligase", "pdb": "1VCN", "deposition_date": "2004-03-10", "title": "Crystal structure of t.th. hb8 ctp synthetase complex with sulfate Anion", "Keywords": ["Etramer", " riken structural genomics/proteomics initiative", " rsgi", "", "Structural genomics", "Ligase"], "authors": ["M.goto", "Riken structural genomics/proteomics initiative (rsgi)"], "pmid": "15296735", "doi": "10.1016/J.STR.2004.05.013"}
{"classification": "Transferase/transferase inhibitor", "pdb": "6C9V", "deposition_date": "2018-01-28", "title": "Mycobacterium tuberculosis adenosine kinase bound to (2r,3s,4r,5r)-2- (hydroxymethyl)-5-(6-(4-phenylpiperazin-1-yl)-9h-purin-9-yl) Tetrahydrofuran-3,4-diol", "Keywords": ["Ucleoside analog", " complex", " inhibitor", " structural genomics", " psi-2", "", "Protein structure initiative", "Tb structural genomics consortium", "", "Tbsgc", "Transferase-transferase inhibitor complex"], "authors": ["R.a.crespo", "Tb structural genomics consortium (tbsgc)"], "pmid": "31002508", "doi": "10.1021/ACS.JMEDCHEM.9B00020"}
{"classification": "De novo protein", "pdb": "4LPY", "deposition_date": "2013-07-16", "title": "Crystal structure of tencon variant g10", "Keywords": ["Ibronectin type iii fold", " alternate scaffold", " de novo protein"], "authors": ["A.teplyakov", "G.obmolova", "G.l.gilliland"], "pmid": "24375666", "doi": "10.1002/PROT.24502"}
{"classification": "Isomerase", "pdb": "2Y88", "deposition_date": "2011-02-03", "title": "Crystal structure of mycobacterium tuberculosis phosphoribosyl Isomerase (variant d11n) with bound prfar", "Keywords": ["Romatic amino acid biosynthesis", " isomerase", " tim-barrel", " histidine", "Biosynthesis", "Tryptophan biosynthesis"], "authors": ["J.kuper", "A.v.due", "A.geerlof", "M.wilmanns"], "pmid": "21321225", "doi": "10.1073/PNAS.1015996108"}
{"classification": "Unknown function", "pdb": "1SR0", "deposition_date": "2004-03-22", "title": "Crystal structure of signalling protein from sheep(sps-40) at 3.0a Resolution using crystal grown in the presence of polysaccharides", "Keywords": ["Ignalling protein", " involution", " unknown function"], "authors": ["D.b.srivastava", "A.s.ethayathulla", "N.singh", "J.kumar", "S.sharma", "T.p.singh"]}
{"classification": "Dna binding protein", "pdb": "3RH2", "deposition_date": "2011-04-11", "title": "Crystal structure of a tetr-like transcriptional regulator (sama_0099) From shewanella amazonensis sb2b at 2.42 a resolution", "Keywords": ["Na/rna-binding 3-helical bundle", " structural genomics", " joint center", "For structural genomics", "Jcsg", "Protein structure initiative", "Psi-", "Biology", "Dna binding protein"], "authors": ["Joint center for structural genomics (jcsg)"]}
{"classification": "Transferase", "pdb": "2WK5", "deposition_date": "2009-06-05", "title": "Structural features of native human thymidine phosphorylase And in complex with 5-iodouracil", "Keywords": ["Lycosyltransferase", " developmental protein", " angiogenesis", "", "5-iodouracil", "Growth factor", "Enzyme kinetics", "", "Differentiation", "Disease mutation", "Thymidine", "Phosphorylase", "Chemotaxis", "Transferase", "Mutagenesis", "", "Polymorphism"], "authors": ["E.mitsiki", "A.c.papageorgiou", "S.iyer", "N.thiyagarajan", "S.h.prior", "", "D.sleep", "C.finnis", "K.r.acharya"], "pmid": "19555658", "doi": "10.1016/J.BBRC.2009.06.104"}
{"classification": "Hydrolase", "pdb": "3P9Y", "deposition_date": "2010-10-18", "title": "Crystal structure of the drosophila melanogaster ssu72-pctd complex", "Keywords": ["Hosphatase", " cis proline", " lmw ptp-like fold", " rna polymerase ii ctd", "", "Hydrolase"], "authors": ["J.w.werner-allen", "P.zhou"], "pmid": "21159777", "doi": "10.1074/JBC.M110.197129"}
{"classification": "Recombination/dna", "pdb": "6OEO", "deposition_date": "2019-03-27", "title": "Cryo-em structure of mouse rag1/2 nfc complex (dna1)", "Keywords": ["(d)j recombination", " dna transposition", " rag", " scid", " recombination", "", "Recombination-dna complex"], "authors": ["X.chen", "Y.cui", "Z.h.zhou", "W.yang", "M.gellert"], "pmid": "32015552", "doi": "10.1038/S41594-019-0363-2"}
{"classification": "Hydrolase", "pdb": "4ECA", "deposition_date": "1997-02-21", "title": "Asparaginase from e. coli, mutant t89v with covalently bound aspartate", "Keywords": ["Ydrolase", " acyl-enzyme intermediate", " threonine amidohydrolase"], "authors": ["G.j.palm", "J.lubkowski", "A.wlodawer"], "pmid": "8706862", "doi": "10.1016/0014-5793(96)00660-6"}
{"classification": "Transcription/protein binding", "pdb": "3UVX", "deposition_date": "2011-11-30", "title": "Crystal structure of the first bromodomain of human brd4 in complex With a diacetylated histone 4 peptide (h4k12ack16ac)", "Keywords": ["Romodomain", " bromodomain containing protein 4", " cap", " hunk1", " mcap", "", "Mitotic chromosome associated protein", "Peptide complex", "Structural", "Genomics consortium", "Sgc", "Transcription-protein binding complex"], "authors": ["P.filippakopoulos", "S.picaud", "T.keates", "E.ugochukwu", "F.von delft", "", "C.h.arrowsmith", "A.m.edwards", "J.weigelt", "C.bountra", "S.knapp", "Structural", "Genomics consortium (sgc)"], "pmid": "22464331", "doi": "10.1016/J.CELL.2012.02.013"}
{"classification": "Membrane protein", "pdb": "1TLZ", "deposition_date": "2004-06-10", "title": "Tsx structure complexed with uridine", "Keywords": ["Ucleoside transporter", " beta barrel", " uridine", " membrane", "Protein"], "authors": ["J.ye", "B.van den berg"], "pmid": "15272310", "doi": "10.1038/SJ.EMBOJ.7600330"}
{"classification": "Dna binding protein", "pdb": "7AZD", "deposition_date": "2020-11-16", "title": "Dna polymerase sliding clamp from escherichia coli with peptide 20 Bound", "Keywords": ["Ntibacterial drug", " dna binding protein"], "authors": ["C.monsarrat", "G.compain", "C.andre", "I.martiel", "S.engilberge", "V.olieric", "", "P.wolff", "K.brillet", "M.landolfo", "C.silva da veiga", "J.wagner", "G.guichard", "", "D.y.burnouf"], "pmid": "34806883", "doi": "10.1021/ACS.JMEDCHEM.1C00918"}
{"classification": "Transferase", "pdb": "5N3K", "deposition_date": "2017-02-08", "title": "Camp-dependent protein kinase a from cricetulus griseus in complex With fragment like molecule o-guanidino-l-homoserine", "Keywords": ["Ragment", " complex", " transferase", " serine threonine kinase", " camp", "", "Kinase", "Pka"], "authors": ["C.siefker", "A.heine", "G.klebe"]}
{"classification": "Biosynthetic protein", "pdb": "8H52", "deposition_date": "2022-10-11", "title": "Crystal structure of helicobacter pylori carboxyspermidine Dehydrogenase in complex with nadp", "Keywords": ["Arboxyspermidine dehydrogenase", " biosynthetic protein"], "authors": ["K.y.ko", "S.c.park", "S.y.cho", "S.i.yoon"], "pmid": "36283333", "doi": "10.1016/J.BBRC.2022.10.049"}
{"classification": "Metal binding protein", "pdb": "6DYC", "deposition_date": "2018-07-01", "title": "Co(ii)-bound structure of the engineered cyt cb562 variant, ch3", "Keywords": ["Esigned protein", " 4-helix bundle", " electron transport", " metal binding", "Protein"], "authors": ["F.a.tezcan", "J.rittle"], "pmid": "30778140", "doi": "10.1038/S41557-019-0218-9"}
{"classification": "Protein fibril", "pdb": "6A6B", "deposition_date": "2018-06-27", "title": "Cryo-em structure of alpha-synuclein fiber", "Keywords": ["Lpha-syn fiber", " parkinson disease", " protein fibril"], "authors": ["Y.w.li", "C.y.zhao", "F.luo", "Z.liu", "X.gui", "Z.luo", "X.zhang", "D.li", "C.liu", "X.li"], "pmid": "30065316", "doi": "10.1038/S41422-018-0075-X"}
{"classification": "Dna", "pdb": "7D5E", "deposition_date": "2020-09-25", "title": "Left-handed g-quadruplex containing two bulges", "Keywords": ["-quadruplex", " bulge", " dna", " left-handed"], "authors": ["P.das", "A.maity", "K.h.ngo", "F.r.winnerdy", "B.bakalar", "Y.mechulam", "E.schmitt", "", "A.t.phan"], "pmid": "33503265", "doi": "10.1093/NAR/GKAA1259"}
{"classification": "Transferase", "pdb": "3RSY", "deposition_date": "2011-05-02", "title": "Cellobiose phosphorylase from cellulomonas uda in complex with sulfate And glycerol", "Keywords": ["H94", " alpha barrel", " cellobiose phosphorylase", " disaccharide", "Phosphorylase", "Transferase"], "authors": ["A.van hoorebeke", "J.stout", "W.soetaert", "J.van beeumen", "T.desmet", "S.savvides"]}
{"classification": "Oxidoreductase", "pdb": "7MCI", "deposition_date": "2021-04-02", "title": "Mofe protein from azotobacter vinelandii with a sulfur-replenished Cofactor", "Keywords": ["Zotobacter vinelandii", " mofe-protein", " nitrogenase", " oxidoreductase"], "authors": ["W.kang", "C.lee", "Y.hu", "M.w.ribbe"], "doi": "10.1038/S41929-022-00782-7"}
{"classification": "Dna", "pdb": "1XUW", "deposition_date": "2004-10-26", "title": "Structural rationalization of a large difference in rna affinity Despite a small difference in chemistry between two 2'-o-modified Nucleic acid analogs", "Keywords": ["Na mimetic methylcarbamate amide analog", " dna"], "authors": ["R.pattanayek", "L.sethaphong", "C.pan", "M.prhavc", "T.p.prakash", "M.manoharan", "", "M.egli"], "pmid": "15547979", "doi": "10.1021/JA044637K"}
{"classification": "Lyase", "pdb": "7C0D", "deposition_date": "2020-05-01", "title": "Crystal structure of azospirillum brasilense l-2-keto-3-deoxyarabonate Dehydratase (hydroxypyruvate-bound form)", "Keywords": ["-2-keto-3-deoxyarabonate dehydratase", " lyase"], "authors": ["Y.watanabe", "S.watanabe"], "pmid": "32697085", "doi": "10.1021/ACS.BIOCHEM.0C00515"}
{"classification": "Signaling protein", "pdb": "5LYK", "deposition_date": "2016-09-28", "title": "Crystal structure of intracellular b30.2 domain of btn3a1 bound to Citrate", "Keywords": ["30.2", " butyrophilin", " signaling protein"], "authors": ["F.mohammed", "A.t.baker", "M.salim", "B.e.willcox"], "pmid": "28862425", "doi": "10.1021/ACSCHEMBIO.7B00694"}
{"classification": "Toxin", "pdb": "4IZL", "deposition_date": "2013-01-30", "title": "Structure of the n248a mutant of the panton-valentine leucocidin s Component from staphylococcus aureus", "Keywords": ["I-component leucotoxin", " staphylococcus aureus", " s component", "Leucocidin", "Beta-barrel pore forming toxin", "Toxin"], "authors": ["L.maveyraud", "B.j.laventie", "G.prevost", "L.mourey"], "pmid": "24643034", "doi": "10.1371/JOURNAL.PONE.0092094"}
{"classification": "Dna", "pdb": "6F3C", "deposition_date": "2017-11-28", "title": "The cytotoxic [pt(h2bapbpy)] platinum complex interacting with the Cgtacg hexamer", "Keywords": ["Rug-dna complex", " four-way junction", " dna"], "authors": ["M.ferraroni", "C.bazzicalupi", "P.gratteri", "F.papi"], "pmid": "31046177", "doi": "10.1002/ANIE.201814532"}
{"classification": "Signaling protein/inhibitor", "pdb": "4L5M", "deposition_date": "2013-06-11", "title": "Complexe of arno sec7 domain with the protein-protein interaction Inhibitor n-(4-hydroxy-2,6-dimethylphenyl)benzenesulfonamide at ph6.5", "Keywords": ["Ec-7domain", " signaling protein-inhibitor complex"], "authors": ["F.hoh", "J.rouhana"], "pmid": "24112024", "doi": "10.1021/JM4009357"}
{"classification": "Signaling protein", "pdb": "5I6J", "deposition_date": "2016-02-16", "title": "Crystal structure of srgap2 f-barx", "Keywords": ["Rgap2", " f-bar", " fx", " signaling protein"], "authors": ["M.sporny", "J.guez-haddad", "M.n.isupov", "Y.opatowsky"], "pmid": "28333212", "doi": "10.1093/MOLBEV/MSX094"}
{"classification": "Metal binding protein", "pdb": "1Q80", "deposition_date": "2003-08-20", "title": "Solution structure and dynamics of nereis sarcoplasmic calcium binding Protein", "Keywords": ["Ll-alpha", " metal binding protein"], "authors": ["G.rabah", "R.popescu", "J.a.cox", "Y.engelborghs", "C.t.craescu"], "pmid": "15819893", "doi": "10.1111/J.1742-4658.2005.04629.X"}
{"classification": "Transferase", "pdb": "1TW1", "deposition_date": "2004-06-30", "title": "Beta-1,4-galactosyltransferase mutant met344his (m344h-gal-t1) complex With udp-galactose and magnesium", "Keywords": ["Et344his mutation; closed conformation; mn binding", " transferase"], "authors": ["B.ramakrishnan", "E.boeggeman", "P.k.qasba"], "pmid": "15449940", "doi": "10.1021/BI049007+"}
{"classification": "Rna", "pdb": "2PN4", "deposition_date": "2007-04-23", "title": "Crystal structure of hepatitis c virus ires subdomain iia", "Keywords": ["Cv", " ires", " subdoamin iia", " rna", " strontium", " hepatitis"], "authors": ["Q.zhao", "Q.han", "C.r.kissinger", "P.a.thompson"], "pmid": "18391410", "doi": "10.1107/S0907444908002011"}

View File

@ -1,6 +1,36 @@
{"pid": "Q6GZX4", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 41."}], "title": "Putative transcription factor 001R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q6GZX3", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 42."}], "title": "Uncharacterized protein 002L;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q197F8", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 27."}], "title": "Uncharacterized protein 002R;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
{"pid": "Q197F7", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 23."}], "title": "Uncharacterized protein 003L;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
{"pid": "Q6GZX2", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 36."}], "title": "Uncharacterized protein 3R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": "Q6GZX1", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 34."}], "title": "Uncharacterized protein 004R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZX4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 43"}], "title": "Putative transcription factor 001R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZX3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 45"}], "title": "Uncharacterized protein 002L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197F8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 29"}], "title": "Uncharacterized protein 002R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q197F7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 23"}], "title": "Uncharacterized protein 003L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZX2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 3R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZX1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 38"}], "title": "Uncharacterized protein 004R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197F5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 005L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZX0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 47"}], "title": "Uncharacterized protein 005R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q91G88", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-06-28", "date_info": "entry version 53"}], "title": "Putative KilA-N domain-containing protein 006L", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZW9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 34"}], "title": "Uncharacterized protein 006R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 32"}], "title": "Uncharacterized protein 007R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197F3", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 007R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q197F2", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 22"}], "title": "Uncharacterized protein 008L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 67"}], "title": "Putative helicase 009L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q91G85", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 38"}], "title": "Uncharacterized protein 009R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZW5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 010R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197E9", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 011L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 011R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 012L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197E7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 37"}], "title": "Uncharacterized protein IIV3-013L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZW2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 30"}], "title": "Uncharacterized protein 013R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 014R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZW0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 50"}], "title": "Uncharacterized protein 015R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 017L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV7", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 018L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 87"}], "title": "Putative serine/threonine-protein kinase 019R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 40"}], "title": "Uncharacterized protein 020R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZV4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 021L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-12-14", "date_info": "entry version 35"}], "title": "Transmembrane protein 022L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZV2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 023R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 25"}], "title": "Uncharacterized protein 023R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q6GZV1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 024R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q197D5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 24"}], "title": "Uncharacterized protein 025R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
{"pid": " Q91G70", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 026R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
{"pid": " Q6GZU9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 49"}], "title": "Uncharacterized protein 027R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
{"pid": " Q6GZU8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 55"}], "title": "Uncharacterized protein 028R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}

View File

@ -26,7 +26,7 @@ class MAGMappingTest {
@Test
def mappingMagType(): Unit = {
checkResult[Publication](MagUtility.createResultFromType(null, null), invisible = false, "Other literature type")
checkResult[Publication](MagUtility.createResultFromType(null, null), invisible = true, "Other literature type")
checkResult[Publication](
MagUtility.createResultFromType(Some("BookChapter"), null),
invisible = false,

View File

@ -70,9 +70,8 @@ public class PrepareRelatedProjectsJob {
final Dataset<Relation> rels = ClusterUtils
.loadRelations(graphPath, spark)
.filter((FilterFunction<Relation>) r -> r.getDataInfo().getDeletedbyinference())
.filter((FilterFunction<Relation>) r -> r.getRelType().equals(ModelConstants.RESULT_PROJECT))
.filter((FilterFunction<Relation>) r -> !r.getRelClass().equals(BrokerConstants.IS_MERGED_IN_CLASS))
.filter((FilterFunction<Relation>) r -> ModelConstants.RESULT_PROJECT.equals(r.getRelType()))
.filter((FilterFunction<Relation>) r -> !BrokerConstants.IS_MERGED_IN_CLASS.equals(r.getRelClass()))
.filter((FilterFunction<Relation>) r -> !ClusterUtils.isDedupRoot(r.getSource()))
.filter((FilterFunction<Relation>) r -> !ClusterUtils.isDedupRoot(r.getTarget()));

View File

@ -53,7 +53,7 @@ public class EnrichMoreSubject extends UpdateMatcher<OaBrokerTypedValue> {
.collect(Collectors.toSet());
return source
.getPids()
.getSubjects()
.stream()
.filter(s -> !existingSubjects.contains(subjectAsString(s)))
.collect(Collectors.toList());

View File

@ -0,0 +1,60 @@
package eu.dnetlib.dhp.broker.oa.matchers.simple;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertTrue;
import java.util.Arrays;
import java.util.List;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import eu.dnetlib.broker.objects.OaBrokerMainEntity;
import eu.dnetlib.broker.objects.OaBrokerTypedValue;
public class EnrichMoreSubjectTest {
final EnrichMoreSubject matcher = new EnrichMoreSubject();
@BeforeEach
void setUp() throws Exception {
}
@Test
void testFindDifferences_1() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
final List<OaBrokerTypedValue> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
@Test
void testFindDifferences_2() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
source.setSubjects(Arrays.asList(new OaBrokerTypedValue("arxiv", "subject_01")));
final List<OaBrokerTypedValue> list = this.matcher.findDifferences(source, target);
assertEquals(1, list.size());
}
@Test
void testFindDifferences_3() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
target.setSubjects(Arrays.asList(new OaBrokerTypedValue("arxiv", "subject_01")));
final List<OaBrokerTypedValue> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
@Test
void testFindDifferences_4() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
source.setSubjects(Arrays.asList(new OaBrokerTypedValue("arxiv", "subject_01")));
target.setSubjects(Arrays.asList(new OaBrokerTypedValue("arxiv", "subject_01")));
final List<OaBrokerTypedValue> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
}

View File

@ -17,45 +17,6 @@ import eu.dnetlib.pace.tree.support.TreeStats;
class DecisionTreeTest {
@Test
void testJPath() throws IOException {
DedupConfig conf = DedupConfig
.load(IOUtils.toString(getClass().getResourceAsStream("dedup_conf_organization.json")));
final String org = IOUtils.toString(getClass().getResourceAsStream("organization.json"));
Row row = SparkModel.apply(conf).rowFromJson(org);
System.out.println("row = " + row);
Assertions.assertNotNull(row);
Assertions.assertTrue(StringUtils.isNotBlank(row.getAs("identifier")));
System.out.println("row = " + row.getAs("countrytitle"));
}
@Test
void jsonToModelTest() throws IOException {
DedupConfig conf = DedupConfig
.load(
IOUtils
.toString(
SparkOpenorgsDedupTest.class
.getResourceAsStream(
"/eu/dnetlib/dhp/dedup/conf/org.curr.conf.json")));
final String org = IOUtils.toString(getClass().getResourceAsStream("organization_example1.json"));
Row row = SparkModel.apply(conf).rowFromJson(org);
// to check that the same parsing returns the same row
Row row1 = SparkModel.apply(conf).rowFromJson(org);
Assertions.assertEquals(row, row1);
System.out.println("row = " + row);
Assertions.assertNotNull(row);
Assertions.assertTrue(StringUtils.isNotBlank(row.getAs("identifier")));
}
@Test
void organizationDecisionTreeTest() throws Exception {
DedupConfig conf = DedupConfig

View File

@ -452,18 +452,18 @@ public class SparkDedupTest implements Serializable {
assertEquals(ModelConstants.RESULT_RESULT, r.getRelType());
assertEquals(ModelConstants.DEDUP, r.getSubRelType());
assertEquals(ModelConstants.IS_MERGED_IN, r.getRelClass());
assertTrue(dups.contains(r.getTarget()));
assertFalse(dups.contains(r.getTarget()));
});
final List<Relation> mergedIn = pubs
.filter("target == '50|arXiv_dedup_::c93aeb433eb90ed7a86e29be00791b7c'")
.collectAsList();
assertEquals(3, mergedIn.size());
assertEquals(1, mergedIn.size());
mergedIn.forEach(r -> {
assertEquals(ModelConstants.RESULT_RESULT, r.getRelType());
assertEquals(ModelConstants.DEDUP, r.getSubRelType());
assertEquals(ModelConstants.IS_MERGED_IN, r.getRelClass());
assertTrue(dups.contains(r.getSource()));
assertEquals(ModelConstants.MERGES, r.getRelClass());
assertFalse(dups.contains(r.getSource()));
});
System.out.println("orgs_mergerel = " + orgs_mergerel);
@ -473,8 +473,8 @@ public class SparkDedupTest implements Serializable {
System.out.println("orp_mergerel = " + orp_mergerel);
if (CHECK_CARDINALITIES) {
assertEquals(1268, orgs_mergerel);
assertEquals(1156, pubs.count());
assertEquals(1278, orgs_mergerel);
assertEquals(1158, pubs.count());
assertEquals(292, sw_mergerel);
assertEquals(476, ds_mergerel);
assertEquals(742, orp_mergerel);

View File

@ -241,7 +241,6 @@ public class SparkPublicationRootsTest implements Serializable {
verifyRoot_case_1(roots, pubs);
verifyRoot_case_2(roots, pubs);
verifyRoot_case_3(roots, pubs);
}
private static void verifyRoot_case_1(Dataset<Publication> roots, Dataset<Publication> pubs) {
@ -322,34 +321,6 @@ public class SparkPublicationRootsTest implements Serializable {
assertTrue(Sets.difference(root_cf, dups_cf).isEmpty());
}
private void verifyRoot_case_3(Dataset<Publication> roots, Dataset<Publication> pubs) {
Publication root = roots
.filter("id = '50|dedup_wf_001::31ca734cc22181b704c4aa8fd050062a'")
.first();
assertNotNull(root);
Publication pivot_duplicate = pubs
.filter("id = '50|od_______166::31ca734cc22181b704c4aa8fd050062a'")
.first();
assertEquals(pivot_duplicate.getPublisher().getValue(), root.getPublisher().getValue());
Set<String> dups_cf = pubs
.collectAsList()
.stream()
.flatMap(p -> p.getCollectedfrom().stream())
.map(KeyValue::getValue)
.collect(Collectors.toCollection(HashSet::new));
Set<String> root_cf = root
.getCollectedfrom()
.stream()
.map(KeyValue::getValue)
.collect(Collectors.toCollection(HashSet::new));
assertTrue(Sets.difference(root_cf, dups_cf).isEmpty());
}
@Test
@Order(6)
void updateEntityTest() throws Exception {

View File

@ -143,7 +143,9 @@ public class SparkPublicationRootsTest2 implements Serializable {
"--graphBasePath", graphInputPath,
"--actionSetId", testActionSetId,
"--isLookUpUrl", "lookupurl",
"--workingPath", workingPath
"--workingPath", workingPath,
"--hiveMetastoreUris", "none",
"--pivotHistoryDatabase", ""
}), spark)
.run(isLookUpService);
@ -153,7 +155,7 @@ public class SparkPublicationRootsTest2 implements Serializable {
.as(Encoders.bean(Relation.class));
assertEquals(
3, merges
4, merges
.filter("relclass == 'isMergedIn'")
.map((MapFunction<Relation, String>) Relation::getTarget, Encoders.STRING())
.distinct()
@ -178,7 +180,7 @@ public class SparkPublicationRootsTest2 implements Serializable {
.textFile(workingPath + "/" + testActionSetId + "/publication_deduprecord")
.map(asEntity(Publication.class), Encoders.bean(Publication.class));
assertEquals(3, roots.count());
assertEquals(4, roots.count());
final Dataset<Publication> pubs = spark
.read()
@ -195,7 +197,7 @@ public class SparkPublicationRootsTest2 implements Serializable {
.collectAsList()
.get(0);
assertEquals(crossref_duplicate.getDateofacceptance().getValue(), root.getDateofacceptance().getValue());
assertEquals("2022-01-01", root.getDateofacceptance().getValue());
assertEquals(crossref_duplicate.getJournal().getName(), root.getJournal().getName());
assertEquals(crossref_duplicate.getJournal().getIssnPrinted(), root.getJournal().getIssnPrinted());
assertEquals(crossref_duplicate.getPublisher().getValue(), root.getPublisher().getValue());

View File

@ -168,7 +168,7 @@ public class SparkStatsTest implements Serializable {
.load(testOutputBasePath + "/" + testActionSetId + "/otherresearchproduct_blockstats")
.count();
assertEquals(414, orgs_blocks);
assertEquals(412, orgs_blocks);
assertEquals(221, pubs_blocks);
assertEquals(134, sw_blocks);
assertEquals(196, ds_blocks);

View File

@ -73,12 +73,6 @@
"name": "Irish Nephrology Society",
"synonym": []
},
{
"id": "100011062",
"uri": "http://dx.doi.org/10.13039/100011062",
"name": "Asian Spinal Cord Network",
"synonym": []
},
{
"id": "100011096",
"uri": "http://dx.doi.org/10.13039/100011096",
@ -223,12 +217,6 @@
"name": "Global Brain Health Institute",
"synonym": []
},
{
"id": "100015776",
"uri": "http://dx.doi.org/10.13039/100015776",
"name": "Health and Social Care Board",
"synonym": []
},
{
"id": "100015992",
"uri": "http://dx.doi.org/10.13039/100015992",
@ -403,18 +391,6 @@
"name": "Irish Hospice Foundation",
"synonym": []
},
{
"id": "501100001596",
"uri": "http://dx.doi.org/10.13039/501100001596",
"name": "Irish Research Council for Science, Engineering and Technology",
"synonym": []
},
{
"id": "501100001597",
"uri": "http://dx.doi.org/10.13039/501100001597",
"name": "Irish Research Council for the Humanities and Social Sciences",
"synonym": []
},
{
"id": "501100001598",
"uri": "http://dx.doi.org/10.13039/501100001598",
@ -515,7 +491,7 @@
"id": "501100002081",
"uri": "http://dx.doi.org/10.13039/501100002081",
"name": "Irish Research Council",
"synonym": []
"synonym": ["501100001596", "501100001597"]
},
{
"id": "501100002736",

View File

@ -560,7 +560,15 @@ case object Crossref2Oaf {
"10.13039/501100000266" | "10.13039/501100006041" | "10.13039/501100000265" | "10.13039/501100000270" |
"10.13039/501100013589" | "10.13039/501100000271" =>
generateSimpleRelationFromAward(funder, "ukri________", a => a)
//HFRI
case "10.13039/501100013209" =>
generateSimpleRelationFromAward(funder, "hfri________", a => a)
val targetId = getProjectId("hfri________", "1e5e62235d094afd01cd56e65112fc63")
queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
//ERASMUS+
case "10.13039/501100010790" =>
generateSimpleRelationFromAward(funder, "erasmusplus_", a => a)
case _ => logger.debug("no match for " + funder.DOI.get)
}

View File

@ -13,13 +13,13 @@ public class CommunityContentprovider {
private String openaireId;
private SelectionConstraints selectioncriteria;
private String enabled;
private Boolean enabled;
public String getEnabled() {
public Boolean getEnabled() {
return enabled;
}
public void setEnabled(String enabled) {
public void setEnabled(Boolean enabled) {
this.enabled = enabled;
}

View File

@ -53,6 +53,8 @@ public class Constraints implements Serializable {
for (Constraint sc : constraint) {
boolean verified = false;
if (!param.containsKey(sc.getField()))
return false;
for (String value : param.get(sc.getField())) {
if (sc.verifyCriteria(value.trim())) {
verified = true;

View File

@ -14,6 +14,7 @@ import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
@ -84,11 +85,12 @@ public class SparkCountryPropagationJob {
Dataset<R> res = readPath(spark, sourcePath, resultClazz);
log.info("Reading prepared info: {}", preparedInfoPath);
Dataset<ResultCountrySet> prepared = spark
final Dataset<Row> preparedInfoRaw = spark
.read()
.json(preparedInfoPath)
.as(Encoders.bean(ResultCountrySet.class));
.json(preparedInfoPath);
if (!preparedInfoRaw.isEmpty()) {
final Dataset<ResultCountrySet> prepared = preparedInfoRaw.as(Encoders.bean(ResultCountrySet.class));
res
.joinWith(prepared, res.col("id").equalTo(prepared.col("resultId")), "left_outer")
.map(getCountryMergeFn(), Encoders.bean(resultClazz))
@ -96,7 +98,13 @@ public class SparkCountryPropagationJob {
.option("compression", "gzip")
.mode(SaveMode.Overwrite)
.json(outputPath);
} else {
res
.write()
.option("compression", "gzip")
.mode(SaveMode.Overwrite)
.json(outputPath);
}
}
private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() {

View File

@ -147,6 +147,7 @@ public class CleanGraphSparkJob {
.map((MapFunction<T, T>) GraphCleaningFunctions::fixVocabularyNames, Encoders.bean(clazz))
.map((MapFunction<T, T>) value -> OafCleaner.apply(value, mapping), Encoders.bean(clazz))
.map((MapFunction<T, T>) value -> GraphCleaningFunctions.cleanup(value, vocs), Encoders.bean(clazz))
.map((MapFunction<T, T>) GraphCleaningFunctions::dedicatedUglyHacks, Encoders.bean(clazz))
.filter((FilterFunction<T>) GraphCleaningFunctions::filter);
// read the master-duplicate tuples

View File

@ -55,29 +55,7 @@ import eu.dnetlib.dhp.common.Constants;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.AccessRight;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Context;
import eu.dnetlib.dhp.schema.oaf.Country;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.EoscIfGuidelines;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.GeoLocation;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.InstanceTypeMapping;
import eu.dnetlib.dhp.schema.oaf.Journal;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.OAIProvenance;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.Subject;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
@ -667,22 +645,25 @@ public abstract class AbstractMdRecordToOafMapper {
return this.vocs.getTermAsQualifier(schemeId, classId);
}
protected List<StructuredProperty> prepareListStructPropsWithValidQualifier(
protected List<HashableStructuredProperty> prepareListStructPropsWithValidQualifier(
final Node node,
final String xpath,
final String xpathClassId,
final String schemeId,
final DataInfo info) {
final List<StructuredProperty> res = new ArrayList<>();
final Set<HashableStructuredProperty> res = new HashSet<>();
for (final Object o : node.selectNodes(xpath)) {
final Node n = (Node) o;
final String classId = n.valueOf(xpathClassId).trim();
if (this.vocs.termExists(schemeId, classId)) {
res.add(structuredProperty(n.getText(), this.vocs.getTermAsQualifier(schemeId, classId), info));
res
.add(
HashableStructuredProperty
.newInstance(n.getText(), this.vocs.getTermAsQualifier(schemeId, classId), info));
}
}
return res;
return Lists.newArrayList(res);
}
protected List<StructuredProperty> prepareListStructProps(

View File

@ -25,6 +25,7 @@ import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.ModelHardLimits;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
public class OafToOafMapper extends AbstractMdRecordToOafMapper {
@ -380,7 +381,7 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper {
return prepareListStructPropsWithValidQualifier(
doc, "//oaf:identifier", "@identifierType", DNET_PID_TYPES, info)
.stream()
.map(CleaningFunctions::normalizePidValue)
.map(PidCleaner::normalizePidValue)
.collect(Collectors.toList());
}

View File

@ -24,6 +24,7 @@ import eu.dnetlib.dhp.schema.common.RelationInverse;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
import eu.dnetlib.dhp.schema.oaf.utils.PidCleaner;
public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
@ -504,7 +505,7 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
@Override
protected List<StructuredProperty> prepareResultPids(final Document doc, final DataInfo info) {
final Set<StructuredProperty> res = new HashSet<>();
final Set<HashableStructuredProperty> res = new HashSet<>();
res
.addAll(
prepareListStructPropsWithValidQualifier(
@ -524,7 +525,8 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper {
return res
.stream()
.map(CleaningFunctions::normalizePidValue)
.map(PidCleaner::normalizePidValue)
.filter(CleaningFunctions::pidFilter)
.collect(Collectors.toList());
}

View File

@ -223,11 +223,13 @@
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--hostedByMapPath</arg><arg>${hostedByMapPath}</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
@ -253,11 +255,13 @@
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
@ -278,6 +282,7 @@
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

View File

@ -388,7 +388,7 @@ public class CleanGraphSparkJobTest {
.collect(Collectors.toList());
assertNotNull(fos_subjects);
assertEquals(2, fos_subjects.size());
assertEquals(3, fos_subjects.size());
assertTrue(
fos_subjects
@ -396,18 +396,10 @@ public class CleanGraphSparkJobTest {
.anyMatch(
s -> "0101 mathematics".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid()) &
"sysimport:crosswalk:datasetarchive"
.equals(s.getDataInfo().getProvenanceaction().getClassid())));
"subject:fos".equals(s.getDataInfo().getProvenanceaction().getClassid())));
assertTrue(
fos_subjects
.stream()
.anyMatch(
s -> "0102 computer and information sciences".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid())));
verify_keyword(p, "In Situ Hybridization");
verify_keyword(p, "Avicennia");
verify_keyword(p, "FOS: Mathematics");
verify_keyword(p, "FOS: Computer and information sciences");
}
@Test

View File

@ -266,7 +266,7 @@ public class GraphCleaningFunctionsTest {
.collect(Collectors.toList());
assertNotNull(fos_subjects);
assertEquals(2, fos_subjects.size());
assertEquals(3, fos_subjects.size());
assertTrue(
fos_subjects
@ -274,18 +274,18 @@ public class GraphCleaningFunctionsTest {
.anyMatch(
s -> "0101 mathematics".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid()) &
"sysimport:crosswalk:datasetarchive"
.equals(s.getDataInfo().getProvenanceaction().getClassid())));
"subject:fos".equals(s.getDataInfo().getProvenanceaction().getClassid())));
assertTrue(
fos_subjects
.stream()
.anyMatch(
s -> "0102 computer and information sciences".equals(s.getValue()) &
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid())));
ModelConstants.DNET_SUBJECT_FOS_CLASSID.equals(s.getQualifier().getClassid()) &
"subject:fos".equals(s.getDataInfo().getProvenanceaction().getClassid())));
verify_keyword(p_cleaned, "In Situ Hybridization");
verify_keyword(p_cleaned, "Avicennia");
verify_keyword(p_cleaned, "FOS: Computer and information sciences");
verify_keyword(p_cleaned, "FOS: Mathematics");
// TODO add more assertions to verity the cleaned values
System.out.println(MAPPER.writeValueAsString(p_cleaned));

View File

@ -44,7 +44,7 @@ class GenerateEntitiesApplicationTest {
}
@Test
void testMergeResult() throws IOException, DocumentException {
void testMergeResult() throws IOException {
Result publication = getResult("oaf_record.xml", Publication.class);
Result dataset = getResult("odf_dataset.xml", Dataset.class);
Result software = getResult("odf_software.xml", Software.class);
@ -69,15 +69,15 @@ class GenerateEntitiesApplicationTest {
verifyMerge(orp, software, Software.class, ModelConstants.SOFTWARE_RESULTTYPE_CLASSID);
}
protected <T extends Result> void verifyMerge(Result publication, Result dataset, Class<T> clazz,
protected <T extends Result> void verifyMerge(Result r1, Result r2, Class<T> clazz,
String resultType) {
final Result merge = (Result) MergeUtils.merge(publication, dataset);
final Result merge = MergeUtils.checkedMerge(r1, r2, true);
assertTrue(clazz.isAssignableFrom(merge.getClass()));
assertEquals(resultType, merge.getResulttype().getClassid());
}
protected <T extends Result> Result getResult(String xmlFileName, Class<T> clazz)
throws IOException, DocumentException {
throws IOException {
final String xml = IOUtils.toString(getClass().getResourceAsStream(xmlFileName));
return new OdfToOafMapper(vocs, false, true)
.processMdRecord(xml)

View File

@ -216,7 +216,7 @@ class MappersTest {
}
@Test
void testPublication_PubMed() throws IOException, DocumentException {
void testPublication_PubMed() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_record_pubmed.xml")));
@ -264,8 +264,17 @@ class MappersTest {
assertFalse(p.getSubject().isEmpty());
assertFalse(p.getPid().isEmpty());
assertEquals("PMC1517292", p.getPid().get(0).getValue());
assertEquals("pmc", p.getPid().get(0).getQualifier().getClassid());
assertTrue(p.getPid().stream().anyMatch(pi -> "pmc".equals(pi.getQualifier().getClassid())));
assertEquals(
"PMC1517292",
p
.getPid()
.stream()
.filter(pi -> "pmc".equals(pi.getQualifier().getClassid()))
.findFirst()
.get()
.getValue());
assertNotNull(p.getInstance());
assertFalse(p.getInstance().isEmpty());
@ -292,7 +301,7 @@ class MappersTest {
}
@Test
void testPublicationInvisible() throws IOException, DocumentException {
void testPublicationInvisible() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_record.xml")));
@ -307,6 +316,25 @@ class MappersTest {
}
@Test
void testPublicationInvisible_BASE() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_record_base.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, true, true).processMdRecord(xml);
assertFalse(list.isEmpty());
assertTrue(list.get(0) instanceof Publication);
final Publication p = (Publication) list.get(0);
assertTrue(p.getDataInfo().getInvisible());
System.out.println(new ObjectMapper().writeValueAsString(p));
}
@Test
void testOdfFwfEBookLibrary() throws IOException {
final String xml = IOUtils
@ -318,7 +346,7 @@ class MappersTest {
}
@Test
void testDataset() throws IOException, DocumentException {
void testDataset() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_dataset.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -332,19 +360,19 @@ class MappersTest {
final Relation r1 = (Relation) list.get(1);
final Relation r2 = (Relation) list.get(2);
assertEquals(d.getId(), r1.getSource());
assertEquals("40|corda_______::e06332dee33bec6c2ba4c98601053229", r1.getTarget());
assertEquals(d.getId(), r1.getTarget());
assertEquals("40|corda_______::e06332dee33bec6c2ba4c98601053229", r1.getSource());
assertEquals(ModelConstants.RESULT_PROJECT, r1.getRelType());
assertEquals(ModelConstants.OUTCOME, r1.getSubRelType());
assertEquals(ModelConstants.IS_PRODUCED_BY, r1.getRelClass());
assertEquals(ModelConstants.PRODUCES, r1.getRelClass());
assertTrue(r1.getValidated());
assertEquals("2020-01-01", r1.getValidationDate());
assertEquals(d.getId(), r2.getTarget());
assertEquals("40|corda_______::e06332dee33bec6c2ba4c98601053229", r2.getSource());
assertEquals(d.getId(), r2.getSource());
assertEquals("40|corda_______::e06332dee33bec6c2ba4c98601053229", r2.getTarget());
assertEquals(ModelConstants.RESULT_PROJECT, r2.getRelType());
assertEquals(ModelConstants.OUTCOME, r2.getSubRelType());
assertEquals(ModelConstants.PRODUCES, r2.getRelClass());
assertEquals(ModelConstants.IS_PRODUCED_BY, r2.getRelClass());
assertTrue(r2.getValidated());
assertEquals("2020-01-01", r2.getValidationDate());
@ -450,7 +478,7 @@ class MappersTest {
}
@Test
void testOdfBielefeld() throws IOException, DocumentException {
void testOdfBielefeld() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_bielefeld.xml")));
@ -501,7 +529,7 @@ class MappersTest {
}
@Test
void testOpentrial() throws IOException, DocumentException {
void testOpentrial() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_opentrial.xml")));
@ -741,7 +769,7 @@ class MappersTest {
}
@Test
void testSoftware() throws IOException, DocumentException {
void testSoftware() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_software.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -763,22 +791,21 @@ class MappersTest {
final Relation r1 = (Relation) list.get(1);
final Relation r2 = (Relation) list.get(2);
assertEquals(s.getId(), r1.getSource());
assertEquals("50|doi_________::b453e7b4b2130ace57ff0c3db470a982", r1.getTarget());
assertEquals(s.getId(), r1.getTarget());
assertEquals("50|doi_________::b453e7b4b2130ace57ff0c3db470a982", r1.getSource());
assertEquals(ModelConstants.RESULT_RESULT, r1.getRelType());
assertEquals(ModelConstants.RELATIONSHIP, r1.getSubRelType());
assertEquals(ModelConstants.IS_REFERENCED_BY, r1.getRelClass());
assertEquals(ModelConstants.REFERENCES, r1.getRelClass());
assertEquals(s.getId(), r2.getTarget());
assertEquals("50|doi_________::b453e7b4b2130ace57ff0c3db470a982", r2.getSource());
assertEquals(s.getId(), r2.getSource());
assertEquals("50|doi_________::b453e7b4b2130ace57ff0c3db470a982", r2.getTarget());
assertEquals(ModelConstants.RESULT_RESULT, r2.getRelType());
assertEquals(ModelConstants.RELATIONSHIP, r2.getSubRelType());
assertEquals(ModelConstants.REFERENCES, r2.getRelClass());
assertEquals(ModelConstants.IS_REFERENCED_BY, r2.getRelClass());
}
@Test
void testClaimDedup() throws IOException, DocumentException {
void testClaimDedup() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_claim_dedup.xml")));
final List<Oaf> list = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
@ -792,7 +819,7 @@ class MappersTest {
}
@Test
void testNakala() throws IOException, DocumentException {
void testNakala() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_nakala.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -820,7 +847,7 @@ class MappersTest {
}
@Test
void testEnermaps() throws IOException, DocumentException {
void testEnermaps() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("enermaps.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -845,7 +872,7 @@ class MappersTest {
}
@Test
void testClaimFromCrossref() throws IOException, DocumentException {
void testClaimFromCrossref() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_claim_crossref.xml")));
final List<Oaf> list = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
@ -862,7 +889,7 @@ class MappersTest {
}
@Test
void testODFRecord() throws IOException, DocumentException {
void testODFRecord() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_record.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
System.out.println("***************");
@ -882,7 +909,7 @@ class MappersTest {
}
@Test
void testTextGrid() throws IOException, DocumentException {
void testTextGrid() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("textgrid.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -916,7 +943,7 @@ class MappersTest {
}
@Test
void testBologna() throws IOException, DocumentException {
void testBologna() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf-bologna.xml")));
final List<Oaf> list = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
@ -933,7 +960,7 @@ class MappersTest {
}
@Test
void testJairo() throws IOException, DocumentException {
void testJairo() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_jairo.xml")));
final List<Oaf> list = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
@ -971,7 +998,7 @@ class MappersTest {
}
@Test
void testZenodo() throws IOException, DocumentException {
void testZenodo() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_zenodo.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -1016,7 +1043,7 @@ class MappersTest {
}
@Test
void testOdfFromHdfs() throws IOException, DocumentException {
void testOdfFromHdfs() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_from_hdfs.xml")));
@ -1065,7 +1092,7 @@ class MappersTest {
}
@Test
void testXMLEncodedURL() throws IOException, DocumentException {
void testXMLEncodedURL() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("encoded-url.xml")));
final List<Oaf> list = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
@ -1081,7 +1108,7 @@ class MappersTest {
}
@Test
void testXMLEncodedURL_ODF() throws IOException, DocumentException {
void testXMLEncodedURL_ODF() throws IOException {
final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("encoded-url_odf.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
@ -1245,7 +1272,7 @@ class MappersTest {
}
@Test
void testRiunet() throws IOException, DocumentException {
void testRiunet() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("riunet.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
System.out.println("***************");
@ -1291,7 +1318,7 @@ class MappersTest {
}
@Test
void testIRISPub() throws IOException, DocumentException {
void testIRISPub() throws IOException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("iris-odf.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
System.out.println("***************");

View File

@ -794,28 +794,6 @@
},
"value": "FOS: Computer and information sciences"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferenceprovenance": "",
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:datasetarchive",
"classname": "sysimport:crosswalk:datasetarchive",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "0101 mathematics"
},
{
"dataInfo": {
"deletedbyinference": false,
@ -831,8 +809,8 @@
"trust": "0.9"
},
"qualifier": {
"classid": "keyword",
"classname": "keyword",
"classid": "FOS",
"classname": "Fields of Science and Technology classification",
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
@ -910,8 +888,8 @@
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:actionset",
"classname": "Harvested",
"classid": "subject:fos",
"classname": "subject:fos",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
@ -923,7 +901,7 @@
"schemeid": "dnet:subject_classification_typologies",
"schemename": "dnet:subject_classification_typologies"
},
"value": "Avicennia"
"value": "0102 computer and information sciences"
},
{
"dataInfo": {

View File

@ -0,0 +1,129 @@
<?xml version="1.0" encoding="UTF-8"?>
<record xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
xmlns:datacite="http://datacite.org/schema/kernel-4"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:dc="http://purl.org/dc/elements/1.1/">
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<dri:objIdentifier>base_oa_____::7ecf1ef502253efffe203ca9a22bb9f1</dri:objIdentifier>
<identifier>ftunivqespace:oai:espace.library.uq.edu.au:UQ:336902</identifier>
<datestamp>2020-12-22T10:30:27Z</datestamp>
<dr:dateOfTransformation>2024-09-10T17:21:36.972Z</dr:dateOfTransformation>
</header>
<metadata>
<datacite:resource>
<datacite:identifier identifierType="DOI">https://doi.org/10.1016/j.envint.2014.07.004</datacite:identifier>
<datacite:alternateIdentifiers>
<datacite:identifier alternateIdentifierType="url">https://espace.library.uq.edu.au/view/UQ:336902</datacite:identifier>
<datacite:identifier alternateIdentifierType="oai-original">ftunivqespace:oai:espace.library.uq.edu.au:UQ:336902</datacite:identifier>
</datacite:alternateIdentifiers>
<datacite:relatedIdentifiers/>
<datacite:resourceType>Article contribution</datacite:resourceType>
<datacite:titles>
<datacite:title>The role of environmental factors in the spatial distribution of Japanese encephalitis in mainland China</datacite:title>
</datacite:titles>
<datacite:creators>
<datacite:creator>
<datacite:creatorName>Wang, Liya</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Hu, Wenbiao</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Soares Magalhaes, Ricardo J.</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Bi, Peng</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Ding, Fan</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Sun, Hailong</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Li, Shenlong</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Yin, Wenwu</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Wei, Lan</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Liu, Qiyong</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Haque, Ubydul</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Sun, Yansong</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Huang, Liuyu</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Tong, Shilu</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Clements, Archie C.A.</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Zhang, Wenyi</datacite:creatorName>
</datacite:creator>
<datacite:creator>
<datacite:creatorName>Li, Chengyi</datacite:creatorName>
</datacite:creator>
</datacite:creators>
<datacite:contributors/>
<datacite:descriptions>
<datacite:description descriptionType="Abstract">Japanese encephalitis (JE) is the most common cause of viral encephalitis and an important public health concern in the Asia-Pacific region, particularly in China where 50% of global cases are notified. To explore the association between environmental factors and human JE cases and identify the high risk areas for JE transmission in China, we used annual notified data on JE cases at the center of administrative township and environmental variables with a pixel resolution of 1. km. ×. 1. km from 2005 to 2011 to construct models using ecological niche modeling (ENM) approaches based on maximum entropy. These models were then validated by overlaying reported human JE case localities from 2006 to 2012 onto each prediction map. ENMs had good discriminatory ability with the area under the curve (AUC) of the receiver operating curve (ROC) of 0.82-0.91, and low extrinsic omission rate of 5.44-7.42%. Resulting maps showed JE being presented extensively throughout southwestern and central China, with local spatial variations in probability influenced by minimum temperatures, human population density, mean temperatures, and elevation, with contribution of 17.94%-38.37%, 15.47%-21.82%, 3.86%-21.22%, and 12.05%-16.02%, respectively. Approximately 60% of JE cases occurred in predicted high risk areas, which covered less than 6% of areas in mainland China. Our findings will help inform optimal geographical allocation of the limited resources available for JE prevention and control in China, find hidden high-risk areas, and increase the effectiveness of public health interventions against JE transmission.</datacite:description>
</datacite:descriptions>
<datacite:subjects>
<datacite:subject>Japanese encephalitis</datacite:subject>
<datacite:subject>Ecological niche model</datacite:subject>
<datacite:subject>MaxEnt</datacite:subject>
<datacite:subject>China</datacite:subject>
<datacite:subject>2300 Environmental Science</datacite:subject>
<datacite:subject classificationCode="950" subjectScheme="ddc">950</datacite:subject>
</datacite:subjects>
<datacite:publisher>Pergamon Press</datacite:publisher>
<datacite:publicationYear>2014</datacite:publicationYear>
<datacite:formats/>
<datacite:language>eng</datacite:language>
<oaf:accessrights/>
</datacite:resource>
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
<oaf:accessrights>UNKNOWN</oaf:accessrights>
<oaf:identifier identifierType="doi">10.1163/qwerty</oaf:identifier>
<oaf:identifier identifierType="doi">0.1163/18763308-90001038</oaf:identifier>
<oaf:identifier identifierType="doi">https://doi.org/10.1016/j.envint.2014.07.004</oaf:identifier>
<oaf:identifier identifierType="doi">https://doi.org/10.1080/09672567.2013.792375</oaf:identifier>
<oaf:identifier identifierType="doi">http://doi.org/10.1080/08673487.2012.812376</oaf:identifier>
<oaf:identifier identifierType="doi">http://dx.doi.org/10.1090/08673487.2012.812376</oaf:identifier>
<oaf:identifier identifierType="url">https://espace.library.uq.edu.au/view/UQ:336902</oaf:identifier>
<oaf:identifier identifierType="oai-original">ftunivqespace:oai:espace.library.uq.edu.au:UQ:336902</oaf:identifier>
<oaf:hostedBy name="The University of Queensland: UQ eSpace" id="opendoar____::575"/>
<oaf:collectedFrom name="Bielefeld Academic Search Engine (BASE)"
id="openaire____::base_search"/>
<oaf:dateAccepted>2014-12-01</oaf:dateAccepted>
<oaf:relation relClass="hasAuthorInstitution"
relType="resultOrganization"
subRelType="affiliation"
targetType="organization">ror_________::https://ror.org/00rqy9422</oaf:relation>
<oaf:datainfo>
<oaf:inferred>false</oaf:inferred>
<oaf:deletedbyinference>false</oaf:deletedbyinference>
<oaf:trust>0.89</oaf:trust>
<oaf:inferenceprovenance/>
<oaf:provenanceaction classid="sysimport:crosswalk:aggregator"
classname="sysimport:crosswalk:aggregator"
schemeid="dnet:provenanceActions"
schemename="dnet:provenanceActions"/>
</oaf:datainfo>
</metadata>
</record>

View File

@ -130,5 +130,10 @@
"value": [
"Pippo", "Foo"
]
},
{
"field": "typology",
"type": "string",
"value": "Government"
}
]

View File

@ -4,12 +4,13 @@ import eu.dnetlib.dhp.schema.sx.scholix.ScholixResource
import eu.dnetlib.dhp.sx.graph.SparkCreateScholexplorerDump
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.junit.jupiter.api.Test
import org.junit.jupiter.api.{Disabled, Test}
import org.objenesis.strategy.StdInstantiatorStrategy
class ScholixGenerationTest {
@Test
@Disabled
def generateScholix(): Unit = {
val spark: SparkSession = SparkSession.builder().master("local[*]").getOrCreate()

View File

@ -175,7 +175,8 @@ public class XmlSerializationUtils {
.append("<")
.append(name)
.append(" ")
.append(attr(measure.getId(), kv.getValue()))
.append(attr("id", measure.getId()))
.append(attr("score", kv.getValue()))
.append(attr("datasource", kv.getKey()))
.append(" />");
}

View File

@ -69,7 +69,7 @@
</configuration>
</global>
<start to="oaiphm_provision"/>
<start to="irish_oaiphm_provision"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>

Some files were not shown because too many files have changed in this diff Show More