Compare commits

...

367 Commits

Author SHA1 Message Date
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 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
Lampros Smyrnaios e3f28338c1 Miscellaneous updates to the copying operation to Impala Cluster:
- Assign the WRITE and EXECUTE permissions to the DBs' HDFS-directories, in order to be able to create tables on top of them, in the Impala Cluster.
- Make sure the "copydb" function returns early, when it encounters a fatal error, while respecting the "SHOULD_EXIT_WHOLE_SCRIPT_UPON_ERROR" config.
2024-05-28 17:51:45 +03:00
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
Antonis Lempesis 15b54a345a added fos lvl4 2024-05-24 13:21:28 +03:00
Lampros Smyrnaios b48ed6e617 Change configuration in the copy-operation to Impala Cluster:
Set the "SHOULD_EXIT_WHOLE_SCRIPT_UPON_ERROR" parameter to "false".
2024-05-23 16:58:12 +03:00
Lampros Smyrnaios 68322843e2 Small updates to the copy-operation to Impala Cluster:
- Add a configuration-"switch" to control whether the script exits upon an error or not.
- Allow the script to exit when a table could not be created.
- Show the elapsed time for processing each database.
2024-05-23 15:07:49 +03:00
Lampros Smyrnaios c7b32bbacc Update CopyDataToImpalaCluster:
Update the code of acquiring the entities from Ocean cluster, through hive, in order to optimize the process and account for additional reserved keywords in Impala.

Co-authored-by: Antonis Lempesis <antleb@di.uoa.gr>
2024-05-23 13:00:19 +03:00
Claudio Atzori c3fe59bc78 fixed conflicts merging from beta, code formatting 2024-05-21 14:50:40 +02:00
Claudio Atzori 1ea67eba82 Merge branch 'beta' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta 2024-05-21 13:48:48 +02:00
Claudio Atzori f9fb2fef6e Merge pull request 'Modification of Microsoft Academic Graph Mapping' (#435) from mag_only_doi into beta
Reviewed-on: #435
2024-05-21 13:48:42 +02:00
Claudio Atzori 834461ba26 [graph provision]fixed wf definition, revised serialization of the usage counts measures 2024-05-21 13:48:06 +02:00
Sandro La Bruzzo 032bcc8279 since last beta workflow we decide to introduce in the graph only MAG item with DOI and set them invisible ( this should be the same behaviour of the previous DOIBoost mapping).
This commit apply this type of mapping
2024-05-20 09:24:15 +02:00
Claudio Atzori 92f018d196 [graph provision] fixed path pointing to an intermediate data store in the working directory 2024-05-15 15:39:18 +02:00
Claudio Atzori 0611c81a2f [graph provision] using Qualifier.classNames to populate the correponsing fields in the JSON payload 2024-05-15 15:33:10 +02:00
Claudio Atzori 1efe7f7e39 [graph provision] upgrade to dhp-schema:6.1.2, included project.oamandatepublications in the JSON payload mapping, fixed serialisation of the usageCounts measures 2024-05-14 12:39:31 +02:00
Claudio Atzori 53e7bb4336 Merge pull request 'rest-collector-plugin-with-retry' (#432) from rest-collector-plugin-with-retry into beta
Reviewed-on: #432
2024-05-10 09:02:33 +02:00
Claudio Atzori f7d56e2ef2 Merge branch 'beta' into rest-collector-plugin-with-retry 2024-05-10 09:02:21 +02:00
Claudio Atzori c1237ab39e Merge pull request 'Fixes in Graph Provision' (#434) from beta_provision_relation into beta
Reviewed-on: #434
2024-05-09 14:15:05 +02:00
Claudio Atzori dc3a5858f7 Merge branch 'beta' into beta_provision_relation 2024-05-09 14:14:43 +02:00
Claudio Atzori 55f39f7850 [graph provision] adds the possibility to validate the XML records before storing them via the validateXML parameter 2024-05-09 14:06:04 +02:00
Claudio Atzori 39a2afe8b5 [graph provision] fixed XML serialization of the usage counts measures, renamed workflow actions to better reflect their role 2024-05-09 13:54:42 +02:00
Claudio Atzori 908ed9da7a Merge pull request 'Various fixes in the stats wf' (#430) from antonis.lempesis/dnet-hadoop:beta into beta
Reviewed-on: #430
2024-05-08 13:41:02 +02:00
Antonis Lempesis 0cada3cc8f every step is run in the analytics queue. Hardcoded for now, will make a parameter later 2024-05-08 13:42:53 +03:00
Antonis Lempesis 90a4fb3547 fixed typos 2024-05-08 13:17:58 +03:00
Claudio Atzori 18aa323ee9 cleanup unused classes, adjustments in the oozie wf definition 2024-05-08 11:36:46 +02:00
Claudio Atzori b4e3389432 fixed property mapping creating the RelatedEntity transient objects. spark cores & memory adjustments. Code formatting 2024-05-07 16:25:17 +02:00
Giambattista Bloisi 711048ceed PrepareRelationsJob rewritten to use Spark Dataframe API and Windowing functions 2024-05-07 15:44:33 +02:00
Michele Artini f4068de298 code reindent + tests 2024-05-02 09:51:33 +02:00
Michele Artini 2615136efc added a retry mechanism 2024-04-30 11:58:42 +02:00
Lampros Smyrnaios 49af2e5740 Miscellaneous updates to the copying operation to Impala Cluster:
- Update the algorithm for creating views that depend on other views; overcome some bash-instabilities.
- Upon any error, fail the whole process, not just the current DB-creation, as those errors usually indicate a bug in the initial DB-creation, that should be fixed immediately.
- Enhance parallel-copy of large files by "hadoop distcp" command.
- Reduce the "invalidate metadata" commands to just the current DB's tables, in order to eliminate the general overhead on Impala.
- Show the number of tables and views in the logs.
- Fix some log-messages.
2024-04-23 17:15:04 +03:00
Antonis Lempesis d2649a1429 increased the jvm ram 2024-04-23 16:03:16 +03:00
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
Antonis Lempesis b52a5a753b Merge remote-tracking branch 'upstream/beta' into beta 2024-04-19 15:28:28 +03:00
Antonis Lempesis c3fe9662b2 all indicator tables are now stored as parquet 2024-04-19 12:45:36 +03:00
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
Antonis Lempesis 0c71c58df6 fixed the definition of gold_oa 2024-04-18 12:01:27 +03:00
Antonis Lempesis 43d05dbebb fixed the definition of result_country 2024-04-18 11:53:50 +03:00
Antonis Lempesis e728a0897c fixed the definition of indi_pub_bronze_oa 2024-04-18 11:07:55 +03:00
Antonis Lempesis 308ae580a9 slight optimization in indi_pub_gold_oa definition 2024-04-18 10:57:52 +03:00
Antonis Lempesis 27d22bd8f9 slight optimization in indi_pub_gold_oa definition 2024-04-17 23:59:52 +03:00
Antonis Lempesis 1f5aba12fa slight optimization in indi_pub_gold_oa definition 2024-04-17 23:54:23 +03:00
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
168 changed files with 4899 additions and 2997 deletions

View File

@ -70,10 +70,7 @@
<groupId>com.ibm.icu</groupId>
<artifactId>icu4j</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
</dependency>
<dependency>
<groupId>com.github.sisyphsu</groupId>
<artifactId>dateparser</artifactId>
@ -163,7 +160,7 @@
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>${dhp-schemas.artifact}</artifactId>
<artifactId>dhp-schemas</artifactId>
</dependency>
<dependency>
@ -172,4 +169,23 @@
</dependency>
</dependencies>
<!-- dependencies required on JDK9+ because J2EE has been removed -->
<profiles>
<profile>
<id>spark-34</id>
<dependencies>
<dependency>
<groupId>javax.xml.bind</groupId>
<artifactId>jaxb-api</artifactId>
<version>2.2.11</version>
</dependency>
<dependency>
<groupId>com.sun.xml.ws</groupId>
<artifactId>jaxws-ri</artifactId>
<version>2.3.3</version>
<type>pom</type>
</dependency>
</dependencies>
</profile>
</profiles>
</project>

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

@ -1,365 +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
* @throws IOException
* @throws MissingConceptDoiException
*/
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

@ -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 {
@ -1003,4 +1003,41 @@ 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

@ -0,0 +1,106 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import java.util.*;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
public class MergeEntitiesComparator implements Comparator<Oaf> {
static final List<String> PID_AUTHORITIES = Arrays
.asList(
ModelConstants.ARXIV_ID,
ModelConstants.PUBMED_CENTRAL_ID,
ModelConstants.EUROPE_PUBMED_CENTRAL_ID,
ModelConstants.DATACITE_ID,
ModelConstants.CROSSREF_ID);
static final List<String> RESULT_TYPES = Arrays
.asList(
ModelConstants.ORP_RESULTTYPE_CLASSID,
ModelConstants.SOFTWARE_RESULTTYPE_CLASSID,
ModelConstants.DATASET_RESULTTYPE_CLASSID,
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
public static final Comparator<Oaf> INSTANCE = new MergeEntitiesComparator();
@Override
public int compare(Oaf left, Oaf right) {
if (left == null && right == null)
return 0;
if (left == null)
return -1;
if (right == null)
return 1;
int res = 0;
// pid authority
int cfp1 = Optional
.ofNullable(left.getCollectedfrom())
.map(
cf -> cf
.stream()
.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
.max(Integer::compare)
.orElse(-1))
.orElse(-1);
int cfp2 = Optional
.ofNullable(right.getCollectedfrom())
.map(
cf -> cf
.stream()
.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
.max(Integer::compare)
.orElse(-1))
.orElse(-1);
if (cfp1 >= 0 && cfp1 > cfp2) {
return 1;
} else if (cfp2 >= 0 && cfp2 > cfp1) {
return -1;
}
// trust
if (left.getDataInfo() != null && right.getDataInfo() != null) {
res = left.getDataInfo().getTrust().compareTo(right.getDataInfo().getTrust());
}
// result type
if (res == 0) {
if (left instanceof Result && right instanceof Result) {
Result r1 = (Result) left;
Result r2 = (Result) right;
if (r1.getResulttype() == null || r1.getResulttype().getClassid() == null) {
if (r2.getResulttype() != null && r2.getResulttype().getClassid() != null) {
return -1;
}
} else if (r2.getResulttype() == null || r2.getResulttype().getClassid() == null) {
return 1;
}
int rt1 = RESULT_TYPES.indexOf(r1.getResulttype().getClassid());
int rt2 = RESULT_TYPES.indexOf(r2.getResulttype().getClassid());
if (rt1 >= 0 && rt1 > rt2) {
return 1;
} else if (rt2 >= 0 && rt2 > rt1) {
return -1;
}
}
}
// id
if (res == 0) {
if (left instanceof OafEntity && right instanceof OafEntity) {
res = ((OafEntity) left).getId().compareTo(((OafEntity) right).getId());
}
}
return res;
}
}

View File

@ -30,6 +30,7 @@ import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
public class MergeUtils {
public static <T extends Oaf> T mergeById(String s, Iterator<T> oafEntityIterator) {
return mergeGroup(s, oafEntityIterator, true);
}
@ -40,27 +41,12 @@ public class MergeUtils {
public static <T extends Oaf> T mergeGroup(String s, Iterator<T> oafEntityIterator,
boolean checkDelegateAuthority) {
TreeSet<T> sortedEntities = new TreeSet<>((o1, o2) -> {
int res = 0;
if (o1.getDataInfo() != null && o2.getDataInfo() != null) {
res = o1.getDataInfo().getTrust().compareTo(o2.getDataInfo().getTrust());
}
ArrayList<T> sortedEntities = new ArrayList<>();
oafEntityIterator.forEachRemaining(sortedEntities::add);
sortedEntities.sort(MergeEntitiesComparator.INSTANCE.reversed());
if (res == 0) {
if (o1 instanceof Result && o2 instanceof Result) {
return ResultTypeComparator.INSTANCE.compare((Result) o1, (Result) o2);
}
}
return res;
});
while (oafEntityIterator.hasNext()) {
sortedEntities.add(oafEntityIterator.next());
}
Iterator<T> it = sortedEntities.descendingIterator();
Iterator<T> it = sortedEntities.iterator();
T merged = it.next();
while (it.hasNext()) {
@ -103,7 +89,7 @@ public class MergeUtils {
private static Oaf mergeEntities(Oaf left, Oaf right, boolean checkDelegatedAuthority) {
if (sameClass(left, right, Result.class)) {
if (!left.getClass().equals(right.getClass()) || checkDelegatedAuthority) {
if (checkDelegatedAuthority) {
return mergeResultsOfDifferentTypes((Result) left, (Result) right);
}
@ -143,7 +129,7 @@ public class MergeUtils {
* https://graph.openaire.eu/docs/data-model/pids-and-identifiers#delegated-authorities and in that case it prefers
* such version.
* <p>
* Otherwise, it considers a resulttype priority order implemented in {@link ResultTypeComparator}
* Otherwise, it considers a resulttype priority order implemented in {@link MergeEntitiesComparator}
* and proceeds with the canonical property merging.
*
* @param left
@ -161,8 +147,9 @@ public class MergeUtils {
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
return right;
}
// TODO: raise trust to have preferred fields from one or the other??
if (new ResultTypeComparator().compare(left, right) < 0) {
if (MergeEntitiesComparator.INSTANCE.compare(left, right) > 0) {
return mergeResultFields(left, right);
} else {
return mergeResultFields(right, left);
@ -225,9 +212,9 @@ public class MergeUtils {
private static <T, K> List<T> mergeLists(final List<T> left, final List<T> right, int trust,
Function<T, K> keyExtractor, BinaryOperator<T> merger) {
if (left == null) {
return right;
} else if (right == null) {
if (left == null || left.isEmpty()) {
return right != null ? right : new ArrayList<>();
} else if (right == null || right.isEmpty()) {
return left;
}
@ -342,7 +329,7 @@ public class MergeUtils {
final T merged = mergeOafFields(original, enrich, trust);
merged.setOriginalId(unionDistinctListOfString(merged.getOriginalId(), enrich.getOriginalId()));
merged.setPid(unionDistinctLists(merged.getPid(), enrich.getPid(), trust));
merged.setPid(mergeLists(merged.getPid(), enrich.getPid(), trust, MergeUtils::spKeyExtractor, (p1, p2) -> p1));
merged.setDateofcollection(LocalDateTime.now().toString());
merged
.setDateoftransformation(
@ -405,7 +392,7 @@ public class MergeUtils {
}
// should be an instance attribute, get the first non-null value
merge.setLanguage(coalesce(merge.getLanguage(), enrich.getLanguage()));
merge.setLanguage(coalesceQualifier(merge.getLanguage(), enrich.getLanguage()));
// distinct countries, do not manage datainfo
merge.setCountry(mergeQualifiers(merge.getCountry(), enrich.getCountry(), trust));
@ -446,7 +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;
}));
@ -575,6 +565,13 @@ public class MergeUtils {
return m != null ? m : e;
}
private static Qualifier coalesceQualifier(Qualifier m, Qualifier e) {
if (m == null || m.getClassid() == null || StringUtils.isBlank(m.getClassid())) {
return e;
}
return m;
}
private static List<Author> mergeAuthors(List<Author> author, List<Author> author1, int trust) {
List<List<Author>> authors = new ArrayList<>();
if (author != null) {
@ -587,6 +584,10 @@ public class MergeUtils {
}
private static String instanceKeyExtractor(Instance i) {
// three levels of concatenating:
// 1. ::
// 2. @@
// 3. ||
return String
.join(
"::",
@ -594,10 +595,10 @@ public class MergeUtils {
kvKeyExtractor(i.getCollectedfrom()),
qualifierKeyExtractor(i.getAccessright()),
qualifierKeyExtractor(i.getInstancetype()),
Optional.ofNullable(i.getUrl()).map(u -> String.join("::", u)).orElse(null),
Optional.ofNullable(i.getUrl()).map(u -> String.join("@@", u)).orElse(null),
Optional
.ofNullable(i.getPid())
.map(pp -> pp.stream().map(MergeUtils::spKeyExtractor).collect(Collectors.joining("::")))
.map(pp -> pp.stream().map(MergeUtils::spKeyExtractor).collect(Collectors.joining("@@")))
.orElse(null));
}
@ -658,6 +659,13 @@ public class MergeUtils {
return d1;
}
if (StringUtils.contains(d1.getValue(), "null")) {
return d2;
}
if (StringUtils.contains(d2.getValue(), "null")) {
return d1;
}
return Stream
.of(d1, d2)
.min(
@ -706,7 +714,7 @@ public class MergeUtils {
private static String spKeyExtractor(StructuredProperty sp) {
return Optional
.ofNullable(sp)
.map(s -> Joiner.on("::").join(s, qualifierKeyExtractor(s.getQualifier())))
.map(s -> Joiner.on("||").join(qualifierKeyExtractor(s.getQualifier()), s.getValue()))
.orElse(null);
}

View File

@ -1,87 +0,0 @@
package eu.dnetlib.dhp.schema.oaf.utils;
import static eu.dnetlib.dhp.schema.common.ModelConstants.CROSSREF_ID;
import java.util.Comparator;
import java.util.HashSet;
import java.util.Optional;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Result;
public class ResultTypeComparator implements Comparator<Result> {
public static final ResultTypeComparator INSTANCE = new ResultTypeComparator();
@Override
public int compare(Result left, Result right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
HashSet<String> lCf = getCollectedFromIds(left);
HashSet<String> rCf = getCollectedFromIds(right);
if (lCf.contains(CROSSREF_ID) && !rCf.contains(CROSSREF_ID)) {
return -1;
}
if (!lCf.contains(CROSSREF_ID) && rCf.contains(CROSSREF_ID)) {
return 1;
}
if (left.getResulttype() == null || left.getResulttype().getClassid() == null) {
if (right.getResulttype() == null || right.getResulttype().getClassid() == null) {
return 0;
}
return 1;
} else if (right.getResulttype() == null || right.getResulttype().getClassid() == null) {
return -1;
}
String lClass = left.getResulttype().getClassid();
String rClass = right.getResulttype().getClassid();
if (!lClass.equals(rClass)) {
if (lClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return 1;
}
// Else (but unlikely), lexicographical ordering will do.
return lClass.compareTo(rClass);
}
protected HashSet<String> getCollectedFromIds(Result left) {
return Optional
.ofNullable(left.getCollectedfrom())
.map(
cf -> cf
.stream()
.map(KeyValue::getKey)
.collect(Collectors.toCollection(HashSet::new)))
.orElse(new HashSet<>());
}
}

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

@ -1,12 +1,6 @@
package eu.dnetlib.pace.common;
import com.google.common.base.Joiner;
import com.google.common.collect.Sets;
import com.ibm.icu.text.Transliterator;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import java.io.IOException;
import java.io.StringWriter;
import java.nio.charset.StandardCharsets;
@ -15,6 +9,13 @@ import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import com.google.common.base.Joiner;
import com.google.common.collect.Sets;
import com.ibm.icu.text.Transliterator;
/**
* Set of common functions for the framework
*

View File

@ -0,0 +1,48 @@
package eu.dnetlib.pace.tree;
import java.util.Map;
import com.wcohen.ss.AbstractStringDistance;
import eu.dnetlib.pace.config.Config;
import eu.dnetlib.pace.tree.support.AbstractStringComparator;
import eu.dnetlib.pace.tree.support.ComparatorClass;
@ComparatorClass("countryMatch")
public class CountryMatch extends AbstractStringComparator {
public CountryMatch(Map<String, String> params) {
super(params, new com.wcohen.ss.JaroWinkler());
}
public CountryMatch(final double weight) {
super(weight, new com.wcohen.ss.JaroWinkler());
}
protected CountryMatch(final double weight, final AbstractStringDistance ssalgo) {
super(weight, ssalgo);
}
@Override
public double distance(final String a, final String b, final Config conf) {
if (a.isEmpty() || b.isEmpty()) {
return -1.0; // return -1 if a field is missing
}
if (a.equalsIgnoreCase("unknown") || b.equalsIgnoreCase("unknown")) {
return -1.0; // return -1 if a country is UNKNOWN
}
return a.equals(b) ? 1.0 : 0;
}
@Override
public double getWeight() {
return super.weight;
}
@Override
protected double normalize(final double d) {
return d;
}
}

View File

@ -336,4 +336,23 @@ public class ComparatorTest extends AbstractPaceTest {
System.out.println("compare = " + compare);
}
@Test
public void countryMatch() {
CountryMatch countryMatch = new CountryMatch(params);
double result = countryMatch.distance("UNKNOWN", "UNKNOWN", conf);
assertEquals(-1.0, result);
result = countryMatch.distance("CHILE", "UNKNOWN", conf);
assertEquals(-1.0, result);
result = countryMatch.distance("CHILE", "ITALY", conf);
assertEquals(0.0, result);
result = countryMatch.distance("CHILE", "CHILE", conf);
assertEquals(1.0, result);
}
}

View File

@ -0,0 +1,113 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<parent>
<artifactId>dhp</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.2.5-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-shade-package</artifactId>
<description>This module create a jar of all module dependencies</description>
<build>
<plugins>
<plugin>
<artifactId>maven-shade-plugin</artifactId>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<transformers>
<transformer>
<mainClass>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</mainClass>
</transformer>
<transformer />
<transformer>
<resource>META-INF/cxf/bus-extensions.txt</resource>
</transformer>
</transformers>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/maven/**</exclude>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<relocations>
<relocation>
<pattern>com</pattern>
<shadedPattern>repackaged.com.google.common</shadedPattern>
<includes>
<include>com.google.common.**</include>
</includes>
</relocation>
</relocations>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
<dependencies>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<version>1.18.28</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter</artifactId>
<version>5.6.1</version>
<scope>test</scope>
<exclusions>
<exclusion>
<artifactId>junit-jupiter-api</artifactId>
<groupId>org.junit.jupiter</groupId>
</exclusion>
<exclusion>
<artifactId>junit-jupiter-params</artifactId>
<groupId>org.junit.jupiter</groupId>
</exclusion>
<exclusion>
<artifactId>junit-jupiter-engine</artifactId>
<groupId>org.junit.jupiter</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-core</artifactId>
<version>3.3.3</version>
<scope>test</scope>
<exclusions>
<exclusion>
<artifactId>byte-buddy</artifactId>
<groupId>net.bytebuddy</groupId>
</exclusion>
<exclusion>
<artifactId>byte-buddy-agent</artifactId>
<groupId>net.bytebuddy</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-junit-jupiter</artifactId>
<version>3.3.3</version>
<scope>test</scope>
</dependency>
</dependencies>
<distributionManagement>
<site>
<id>DHPSite</id>
<url>${dhp.site.stage.path}/dhp-common</url>
</site>
</distributionManagement>
</project>

View File

@ -103,6 +103,7 @@
--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=${spark2YarnHistoryServerAddress}
@ -156,6 +157,7 @@
--executor-memory=${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

@ -95,6 +95,7 @@
--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

@ -125,6 +125,7 @@
--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

@ -95,6 +95,7 @@
--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

@ -103,6 +103,7 @@
--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=${spark2YarnHistoryServerAddress}
@ -155,11 +156,12 @@
--executor-memory=${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.shuffle.partitions=2560
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--inputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>

View File

@ -95,6 +95,7 @@
--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

@ -103,11 +103,12 @@
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7000
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/publication</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
@ -156,11 +157,12 @@
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7000
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--inputGraphTablePath</arg><arg>${workingDir}/publication</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>

View File

@ -95,11 +95,12 @@
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=10000
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/relation</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>

View File

@ -103,6 +103,7 @@
--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=${spark2YarnHistoryServerAddress}
@ -155,11 +156,12 @@
--executor-memory=${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.shuffle.partitions=2560
--conf spark.sql.shuffle.partitions=4000
</spark-opts>
<arg>--inputGraphTablePath</arg><arg>${workingDir}/software</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>

View File

@ -0,0 +1,210 @@
/*
* Copyright (c) 2024.
* SPDX-FileCopyrightText: © 2023 Consiglio Nazionale delle Ricerche
* SPDX-License-Identifier: AGPL-3.0-or-later
*/
package eu.dnetlib.dhp.actionmanager.promote;
import static eu.dnetlib.dhp.common.FunctionalInterfaceSupport.*;
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
import static org.apache.spark.sql.functions.*;
import static org.junit.jupiter.api.Assertions.*;
import java.io.IOException;
import java.nio.file.DirectoryStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.HashSet;
import java.util.List;
import java.util.function.BiFunction;
import java.util.function.Function;
import java.util.stream.Collectors;
import org.apache.commons.io.FileUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.sql.*;
import org.apache.spark.sql.Dataset;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.Lists;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
public class PromoteResultWithMeasuresTest {
private static final Logger log = LoggerFactory.getLogger(PromoteResultWithMeasuresTest.class);
private static SparkSession spark;
private static Path tempDir;
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@BeforeAll
public static void beforeAll() throws IOException {
tempDir = Files.createTempDirectory(PromoteResultWithMeasuresTest.class.getSimpleName());
log.info("using work dir {}", tempDir);
SparkConf conf = new SparkConf();
conf.setMaster("local[*]");
conf.setAppName(PromoteResultWithMeasuresTest.class.getSimpleName());
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", tempDir.toString());
conf.set("hive.metastore.warehouse.dir", tempDir.resolve("warehouse").toString());
spark = SparkSession.builder().config(conf).getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
spark.stop();
FileUtils.deleteDirectory(tempDir.toFile());
}
@Test
void testPromoteResultWithMeasures_job() throws Exception {
final String inputGraphTablePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/promote/measures/graph")
.getPath();
final String inputActionPayloadPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/promote/measures/actionPayloads")
.getPath();
final String actionPayloadsPath = tempDir.resolve("actionPayloads").toString();
spark
.read()
.text(inputActionPayloadPath)
.withColumn("payload", col("value"))
.select("payload")
.write()
.parquet(actionPayloadsPath);
final Path outputGraphTablePath = tempDir.resolve("outputGraphTablePath");
PromoteActionPayloadForGraphTableJob
.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--graphTableClassName", Publication.class.getCanonicalName(),
"--inputGraphTablePath", inputGraphTablePath,
"--inputActionPayloadPath", actionPayloadsPath,
"--actionPayloadClassName", Result.class.getCanonicalName(),
"--outputGraphTablePath", outputGraphTablePath.toString(),
"--mergeAndGetStrategy", MergeAndGet.Strategy.MERGE_FROM_AND_GET.toString(),
"--promoteActionStrategy", PromoteAction.Strategy.ENRICH.toString(),
"--shouldGroupById", "true"
});
assertFalse(isDirEmpty(outputGraphTablePath));
final Encoder<Publication> pubEncoder = Encoders.bean(Publication.class);
List<Publication> results = spark
.read()
.schema(pubEncoder.schema())
.json(outputGraphTablePath.toString())
.as(pubEncoder)
.collectAsList();
verify(results);
}
@Test
void testPromoteResultWithMeasures_internal() throws JsonProcessingException {
Dataset<Publication> rowDS = spark
.read()
.schema(Encoders.bean(Publication.class).schema())
.json("src/test/resources/eu/dnetlib/dhp/actionmanager/promote/measures/graph")
.as(Encoders.bean(Publication.class));
Dataset<Result> actionPayloadDS = spark
.read()
.schema(Encoders.bean(Result.class).schema())
.json("src/test/resources/eu/dnetlib/dhp/actionmanager/promote/measures/actionPayloads")
.as(Encoders.bean(Result.class));
final MergeAndGet.Strategy mergeFromAndGet = MergeAndGet.Strategy.MERGE_FROM_AND_GET;
final SerializableSupplier<Function<Publication, String>> rowIdFn = ModelSupport::idFn;
final SerializableSupplier<BiFunction<Publication, Result, Publication>> mergeAndGetFn = MergeAndGet
.functionFor(mergeFromAndGet);
final SerializableSupplier<Publication> zeroFn = () -> Publication.class
.cast(new eu.dnetlib.dhp.schema.oaf.Publication());
final SerializableSupplier<Function<Publication, Boolean>> isNotZeroFn = PromoteResultWithMeasuresTest::isNotZeroFnUsingIdOrSourceAndTarget;
Dataset<Publication> joinedResults = PromoteActionPayloadFunctions
.joinGraphTableWithActionPayloadAndMerge(
rowDS,
actionPayloadDS,
rowIdFn,
ModelSupport::idFn,
mergeAndGetFn,
PromoteAction.Strategy.ENRICH,
Publication.class,
Result.class);
SerializableSupplier<BiFunction<Publication, Publication, Publication>> mergeRowsAndGetFn = MergeAndGet
.functionFor(mergeFromAndGet);
Dataset<Publication> mergedResults = PromoteActionPayloadFunctions
.groupGraphTableByIdAndMerge(
joinedResults, rowIdFn, mergeRowsAndGetFn, zeroFn, isNotZeroFn, Publication.class);
verify(mergedResults.collectAsList());
}
private static void verify(List<Publication> results) throws JsonProcessingException {
assertNotNull(results);
assertEquals(1, results.size());
Result r = results.get(0);
log.info(OBJECT_MAPPER.writeValueAsString(r));
assertNotNull(r.getMeasures());
assertFalse(r.getMeasures().isEmpty());
assertTrue(
r
.getMeasures()
.stream()
.map(Measure::getId)
.collect(Collectors.toCollection(HashSet::new))
.containsAll(
Lists
.newArrayList(
"downloads", "views", "influence", "popularity", "influence_alt", "popularity_alt",
"impulse")));
}
private static <T extends Oaf> Function<T, Boolean> isNotZeroFnUsingIdOrSourceAndTarget() {
return t -> {
if (isSubClass(t, Relation.class)) {
final Relation rel = (Relation) t;
return StringUtils.isNotBlank(rel.getSource()) && StringUtils.isNotBlank(rel.getTarget());
}
return StringUtils.isNotBlank(((OafEntity) t).getId());
};
}
private static boolean isDirEmpty(final Path directory) throws IOException {
try (DirectoryStream<Path> dirStream = Files.newDirectoryStream(directory)) {
return !dirStream.iterator().hasNext();
}
}
}

View File

@ -0,0 +1,3 @@
{"collectedfrom":null,"dataInfo":null,"lastupdatetimestamp":null,"id":"50|doi_dedup___::02317b7093277ec8aa0311d5c6a25b9b","originalId":null,"pid":null,"dateofcollection":null,"dateoftransformation":null,"extraInfo":null,"oaiprovenance":null,"measures":[{"id":"downloads","unit":[{"key":"opendoar____::358aee4cc897452c00244351e4d91f69||ZENODO","value":"125","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:usage_counts","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"id":"views","unit":[{"key":"opendoar____::358aee4cc897452c00244351e4d91f69||ZENODO","value":"35","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:usage_counts","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]}],"context":null,"processingchargeamount":null,"processingchargecurrency":null,"author":null,"resulttype":null,"metaResourceType":null,"language":null,"country":null,"subject":null,"title":null,"relevantdate":null,"description":null,"dateofacceptance":null,"publisher":null,"embargoenddate":null,"source":null,"fulltext":null,"format":null,"contributor":null,"resourcetype":null,"coverage":null,"bestaccessright":null,"externalReference":null,"instance":null,"eoscifguidelines":null,"openAccessColor":null,"publiclyFunded":null,"transformativeAgreement":null,"isGreen":null,"isInDiamondJournal":null}
{"collectedfrom":null,"dataInfo":null,"lastupdatetimestamp":null,"id":"50|doi_dedup___::02317b7093277ec8aa0311d5c6a25b9b","originalId":null,"pid":null,"dateofcollection":null,"dateoftransformation":null,"extraInfo":null,"oaiprovenance":null,"measures":[{"id":"influence","unit":[{"key":"score","value":"3.1167566E-9","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}},{"key":"class","value":"C5","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"id":"popularity","unit":[{"key":"score","value":"7.335433E-9","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}},{"key":"class","value":"C4","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"id":"influence_alt","unit":[{"key":"score","value":"4","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}},{"key":"class","value":"C5","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"id":"popularity_alt","unit":[{"key":"score","value":"2.96","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}},{"key":"class","value":"C4","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"id":"impulse","unit":[{"key":"score","value":"4","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}},{"key":"class","value":"C5","dataInfo":{"invisible":false,"inferred":true,"deletedbyinference":false,"trust":"","inferenceprovenance":"update","provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]}],"context":null,"processingchargeamount":null,"processingchargecurrency":null,"author":null,"resulttype":null,"metaResourceType":null,"language":null,"country":null,"subject":null,"title":null,"relevantdate":null,"description":null,"dateofacceptance":null,"publisher":null,"embargoenddate":null,"source":null,"fulltext":null,"format":null,"contributor":null,"resourcetype":null,"coverage":null,"bestaccessright":null,"externalReference":null,"instance":null,"eoscifguidelines":null,"openAccessColor":null,"publiclyFunded":null,"transformativeAgreement":null,"isGreen":null,"isInDiamondJournal":null}
{"collectedfrom":null,"dataInfo":null,"lastupdatetimestamp":null,"id":"50|doi_dedup___::02317b7093277ec8aa0311d5c6a25b9b","originalId":null,"pid":null,"dateofcollection":null,"dateoftransformation":null,"extraInfo":null,"oaiprovenance":null,"measures":null,"context":null,"processingchargeamount":null,"processingchargecurrency":null,"author":null,"resulttype":null,"metaResourceType":null,"language":null,"country":null,"subject":null,"title":null,"relevantdate":null,"description":null,"dateofacceptance":null,"publisher":null,"embargoenddate":null,"source":null,"fulltext":null,"format":null,"contributor":null,"resourcetype":null,"coverage":null,"bestaccessright":null,"externalReference":null,"instance":null,"eoscifguidelines":null,"openAccessColor":"hybrid","publiclyFunded":false,"transformativeAgreement":null,"isGreen":true,"isInDiamondJournal":false}

View File

@ -42,6 +42,9 @@ public class Constants {
public static final String NULL = "NULL";
public static final String NA = "N/A";
public static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
public static final String WEB_CRAWL_NAME = "Web Crawl";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private Constants() {

View File

@ -9,6 +9,7 @@ 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;
@ -40,9 +41,11 @@ public class PrepareAffiliationRelations implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareAffiliationRelations.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String ID_PREFIX = "50|doi_________::";
public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference";
public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!";
public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref";
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 <I extends Result> void main(String[] args) throws Exception {
@ -70,6 +73,12 @@ public class PrepareAffiliationRelations implements Serializable {
final String dataciteInputPath = parser.get("dataciteInputPath");
log.info("dataciteInputPath: {}", dataciteInputPath);
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);
@ -80,7 +89,15 @@ public class PrepareAffiliationRelations implements Serializable {
isSparkSessionManaged,
spark -> {
Constants.removeOutputDir(spark, outputPath);
createActionSet(
spark, crossrefInputPath, pubmedInputPath, openapcInputPath, dataciteInputPath, webcrawlInputPath,
publisherInputPath, outputPath);
});
}
private static void createActionSet(SparkSession spark, String crossrefInputPath, String pubmedInputPath,
String openapcInputPath, String dataciteInputPath, String webcrawlInputPath, String publisherlInputPath,
String outputPath) {
List<KeyValue> collectedFromCrossref = OafMapperUtils
.listKeyValues(ModelConstants.CROSSREF_ID, "Crossref");
JavaPairRDD<Text, Text> crossrefRelations = prepareAffiliationRelations(
@ -101,14 +118,37 @@ public class PrepareAffiliationRelations implements Serializable {
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
spark, dataciteInputPath, collectedFromDatacite);
List<KeyValue> collectedFromWebCrawl = OafMapperUtils
.listKeyValues(OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME);
JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelations(
spark, webcrawlInputPath, collectedFromWebCrawl);
List<KeyValue> collectedfromPublisher = OafMapperUtils
.listKeyValues(OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME);
JavaPairRDD<Text, Text> publisherRelations = prepareAffiliationRelationFromPublisher(
spark, publisherlInputPath, collectedfromPublisher);
crossrefRelations
.union(pubmedRelations)
.union(openAPCRelations)
.union(dataciteRelations)
.union(webCrawlRelations)
.union(publisherRelations)
.saveAsHadoopFile(
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
}
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,
@ -119,8 +159,13 @@ public class PrepareAffiliationRelations implements Serializable {
Dataset<Row> df = spark
.read()
.schema("`DOI` STRING, `Matchings` ARRAY<STRUCT<`RORid`:STRING,`Confidence`:DOUBLE>>")
.json(inputPath);
.json(inputPath)
.where("DOI is not null");
return getTextTextJavaPairRDD(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")))

View File

@ -115,19 +115,7 @@ public class PrepareFOSSparkJob implements Serializable {
.forEach(
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
r.setSubject(sbjs);
r
.setDataInfo(
OafMapperUtils
.dataInfo(
false, null, true,
false,
OafMapperUtils
.qualifier(
ModelConstants.PROVENANCE_ENRICH,
null,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
null));
return r;
}

View File

@ -81,19 +81,7 @@ public class PrepareSDGSparkJob implements Serializable {
s -> sbjs
.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
r.setSubject(sbjs);
r
.setDataInfo(
OafMapperUtils
.dataInfo(
false, null, true,
false,
OafMapperUtils
.qualifier(
ModelConstants.PROVENANCE_ENRICH,
null,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
null));
return r;
}, Encoders.bean(Result.class))
.write()

View File

@ -12,6 +12,7 @@ import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.types.StructType;
@ -20,6 +21,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.Constants;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
@ -43,8 +45,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
private static final String PMID_PREFIX = "50|pmid________::";
private static final String PMCID_PREFIX = "50|pmc_________::";
private static final String WEB_CRAWL_ID = "10|openaire____::fb98a192f6a055ba495ef414c330834b";
private static final String WEB_CRAWL_NAME = "Web Crawl";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception {
@ -70,6 +71,9 @@ public class CreateActionSetFromWebEntries implements Serializable {
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final String blackListInputPath = parser.get("blackListPath");
log.info("blackListInputPath: {}", blackListInputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
@ -77,25 +81,29 @@ public class CreateActionSetFromWebEntries implements Serializable {
isSparkSessionManaged,
spark -> {
createActionSet(spark, inputPath, outputPath);
createActionSet(spark, inputPath, outputPath, blackListInputPath);
});
}
public static void createActionSet(SparkSession spark, String inputPath,
String outputPath) {
String outputPath, String blackListInputPath) {
final Dataset<Row> dataset = readWebCrawl(spark, inputPath)
.filter("publication_year <= 2020 or country_code=='IE'")
.filter("country_code=='IE'")
.drop("publication_year");
dataset.flatMap((FlatMapFunction<Row, Relation>) row -> {
final Dataset<Row> blackList = readBlackList(spark, blackListInputPath);
dataset
.join(blackList, dataset.col("id").equalTo(blackList.col("OpenAlexId")), "left")
.filter((FilterFunction<Row>) r -> r.getAs("OpenAlexId") == null)
.drop("OpenAlexId")
.flatMap((FlatMapFunction<Row, Relation>) row -> {
List<Relation> ret = new ArrayList<>();
final String ror = ROR_PREFIX
+ IdentifierFactory.md5(PidCleaner.normalizePidValue("ROR", row.getAs("ror")));
ret.addAll(createAffiliationRelationPairDOI(row.getAs("doi"), ror));
ret.addAll(createAffiliationRelationPairPMID(row.getAs("pmid"), ror));
ret.addAll(createAffiliationRelationPairPMCID(row.getAs("pmcid"), ror));
return ret
.iterator();
@ -129,47 +137,27 @@ public class CreateActionSetFromWebEntries implements Serializable {
"institution", functions
.explode(
functions.col("institutions")))
.selectExpr(
"id", "doi", "ids.pmcid as pmcid", "ids.pmid as pmid", "institution.ror as ror",
"id", "doi", "institution.ror as ror",
"institution.country_code as country_code", "publication_year")
.distinct();
}
private static List<Relation> createAffiliationRelationPairPMCID(String pmcid, String ror) {
if (pmcid == null)
return new ArrayList<>();
private static Dataset<Row> readBlackList(SparkSession spark, String inputPath) {
return createAffiliatioRelationPair(
PMCID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), removeResolver("PMC", pmcid))),
ror);
}
private static List<Relation> createAffiliationRelationPairPMID(String pmid, String ror) {
if (pmid == null)
return new ArrayList<>();
return createAffiliatioRelationPair(
PMID_PREFIX
+ IdentifierFactory
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), removeResolver("PMID", pmid))),
ror);
return spark
.read()
.json(inputPath)
.select("OpenAlexId");
}
private static String removeResolver(String pidType, String pid) {
switch (pidType) {
case "PMID":
return pid.substring(33);
case "PMC":
return "PMC" + pid.substring(43);
case "DOI":
if (pidType.equals("DOI")) {
return pid.substring(16);
}
throw new RuntimeException();
throw new IllegalArgumentException("DOI is the only supported PID type");
}
private static List<Relation> createAffiliationRelationPairDOI(String doi, String ror) {
@ -195,7 +183,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
ModelConstants.IS_AUTHOR_INSTITUTION_OF,
Arrays
.asList(
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)),
OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
OafMapperUtils
.dataInfo(
false, null, false, false,
@ -214,7 +202,7 @@ public class CreateActionSetFromWebEntries implements Serializable {
ModelConstants.HAS_AUTHOR_INSTITUTION,
Arrays
.asList(
OafMapperUtils.keyValue(WEB_CRAWL_ID, WEB_CRAWL_NAME)),
OafMapperUtils.keyValue(Constants.WEB_CRAWL_ID, Constants.WEB_CRAWL_NAME)),
OafMapperUtils
.dataInfo(
false, null, false, false,

View File

@ -1,6 +1,7 @@
package eu.dnetlib.dhp.collection.plugin.rest;
import java.util.Map;
import java.util.Optional;
import java.util.Spliterator;
import java.util.Spliterators;
@ -9,6 +10,8 @@ import java.util.stream.StreamSupport;
import org.apache.commons.lang3.StringUtils;
import com.google.gson.Gson;
import eu.dnetlib.dhp.collection.ApiDescriptor;
import eu.dnetlib.dhp.collection.plugin.CollectorPlugin;
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
@ -47,6 +50,9 @@ public class RestCollectorPlugin implements CollectorPlugin {
final String entityXpath = api.getParams().get("entityXpath");
final String authMethod = api.getParams().get("authMethod");
final String authToken = api.getParams().get("authToken");
final String requestHeaderMap = api.getParams().get("requestHeaderMap");
Gson gson = new Gson();
Map requestHeaders = gson.fromJson(requestHeaderMap, Map.class);
final String resultSizeValue = Optional
.ofNullable(api.getParams().get("resultSizeValue"))
.filter(StringUtils::isNotBlank)
@ -64,9 +70,6 @@ public class RestCollectorPlugin implements CollectorPlugin {
if (StringUtils.isBlank(resultFormatValue)) {
throw new CollectorException("Param 'resultFormatValue' is null or empty");
}
if (StringUtils.isBlank(queryParams)) {
throw new CollectorException("Param 'queryParams' is null or empty");
}
if (StringUtils.isBlank(entityXpath)) {
throw new CollectorException("Param 'entityXpath' is null or empty");
}
@ -92,7 +95,8 @@ public class RestCollectorPlugin implements CollectorPlugin {
entityXpath,
authMethod,
authToken,
resultOutputFormat);
resultOutputFormat,
requestHeaders);
return StreamSupport
.stream(

View File

@ -9,8 +9,11 @@ import java.net.URL;
import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import java.util.Iterator;
import java.util.Map;
import java.util.Queue;
import java.util.concurrent.PriorityBlockingQueue;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
@ -22,14 +25,14 @@ import javax.xml.xpath.*;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.http.HttpHeaders;
import org.apache.http.entity.ContentType;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import com.google.common.collect.Maps;
import eu.dnetlib.dhp.collection.plugin.utils.JsonUtils;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
@ -44,23 +47,28 @@ import eu.dnetlib.dhp.common.collection.HttpClientParams;
*
*/
public class RestIterator implements Iterator<String> {
private static final Logger log = LoggerFactory.getLogger(RestIterator.class);
public static final String UTF_8 = "UTF-8";
private static final int MAX_ATTEMPTS = 5;
private final HttpClientParams clientParams;
private final String BASIC = "basic";
private final String AUTHBASIC = "basic";
private static final String XML_HEADER = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
private static final String EMPTY_XML = XML_HEADER + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG
+ ">";
private final String baseUrl;
private final String resumptionType;
private final String resumptionParam;
private final String resultFormatValue;
private String queryParams;
private String queryParams = "";
private final int resultSizeValue;
private int resumptionInt = 0; // integer resumption token (first record to harvest)
private int resultTotal = -1;
private String resumptionStr = Integer.toString(resumptionInt); // string resumption token (first record to harvest
private String resumptionStr = Integer.toString(this.resumptionInt); // string resumption token (first record to
// harvest
// or token scanned from results)
private InputStream resultStream;
private Transformer transformer;
@ -73,7 +81,7 @@ public class RestIterator implements Iterator<String> {
private final String querySize;
private final String authMethod;
private final String authToken;
private final Queue<String> recordQueue = new PriorityBlockingQueue<String>();
private final Queue<String> recordQueue = new PriorityBlockingQueue<>();
private int discoverResultSize = 0;
private int pagination = 1;
/*
@ -83,8 +91,13 @@ public class RestIterator implements Iterator<String> {
*/
private final String resultOutputFormat;
/** RestIterator class
* compatible to version 1.3.33
/*
* Can be used to set additional request headers, like for content negotiation
*/
private Map<String, String> requestHeaders;
/**
* RestIterator class compatible to version 1.3.33
*/
public RestIterator(
final HttpClientParams clientParams,
@ -101,47 +114,56 @@ public class RestIterator implements Iterator<String> {
final String entityXpath,
final String authMethod,
final String authToken,
final String resultOutputFormat) {
final String resultOutputFormat,
final Map<String, String> requestHeaders) {
this.clientParams = clientParams;
this.baseUrl = baseUrl;
this.resumptionType = resumptionType;
this.resumptionParam = resumptionParam;
this.resultFormatValue = resultFormatValue;
this.resultSizeValue = Integer.valueOf(resultSizeValueStr);
this.resultSizeValue = Integer.parseInt(resultSizeValueStr);
this.queryParams = queryParams;
this.authMethod = authMethod;
this.authToken = authToken;
this.resultOutputFormat = resultOutputFormat;
this.requestHeaders = requestHeaders != null ? requestHeaders : Maps.newHashMap();
queryFormat = StringUtils.isNotBlank(resultFormatParam) ? "&" + resultFormatParam + "=" + resultFormatValue
this.queryFormat = StringUtils.isNotBlank(resultFormatParam) ? "&" + resultFormatParam + "=" + resultFormatValue
: "";
this.querySize = StringUtils.isNotBlank(resultSizeParam) ? "&" + resultSizeParam + "=" + resultSizeValueStr
: "";
querySize = StringUtils.isNotBlank(resultSizeParam) ? "&" + resultSizeParam + "=" + resultSizeValueStr : "";
try {
initXmlTransformation(resultTotalXpath, resumptionXpath, entityXpath);
} catch (Exception e) {
} catch (final Exception e) {
throw new IllegalStateException("xml transformation init failed: " + e.getMessage());
}
initQueue();
}
private void initXmlTransformation(String resultTotalXpath, String resumptionXpath, String entityXpath)
private void initXmlTransformation(final String resultTotalXpath, final String resumptionXpath,
final String entityXpath)
throws TransformerConfigurationException, XPathExpressionException {
final TransformerFactory factory = TransformerFactory.newInstance();
transformer = factory.newTransformer();
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
xpath = XPathFactory.newInstance().newXPath();
xprResultTotalPath = xpath.compile(resultTotalXpath);
xprResumptionPath = xpath.compile(StringUtils.isBlank(resumptionXpath) ? "/" : resumptionXpath);
xprEntity = xpath.compile(entityXpath);
this.transformer = factory.newTransformer();
this.transformer.setOutputProperty(OutputKeys.INDENT, "yes");
this.transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "3");
this.xpath = XPathFactory.newInstance().newXPath();
this.xprResultTotalPath = this.xpath.compile(resultTotalXpath);
this.xprResumptionPath = this.xpath.compile(StringUtils.isBlank(resumptionXpath) ? "/" : resumptionXpath);
this.xprEntity = this.xpath.compile(entityXpath);
}
private void initQueue() {
if (queryParams.equals("") && querySize.equals("") && queryFormat.equals("")) {
query = baseUrl;
} else {
query = baseUrl + "?" + queryParams + querySize + queryFormat;
log.info("REST calls starting with {}", query);
}
log.info("REST calls starting with {}", this.query);
}
private void disconnect() {
@ -154,11 +176,22 @@ public class RestIterator implements Iterator<String> {
*/
@Override
public boolean hasNext() {
if (recordQueue.isEmpty() && query.isEmpty()) {
synchronized (this.recordQueue) {
while (this.recordQueue.isEmpty() && !this.query.isEmpty()) {
try {
this.query = downloadPage(this.query, 0);
} catch (final CollectorException e) {
log.debug("CollectorPlugin.next()-Exception: {}", e);
throw new RuntimeException(e);
}
}
if (!this.recordQueue.isEmpty()) {
return true;
}
disconnect();
return false;
} else {
return true;
}
}
@ -168,27 +201,34 @@ public class RestIterator implements Iterator<String> {
*/
@Override
public String next() {
synchronized (recordQueue) {
while (recordQueue.isEmpty() && !query.isEmpty()) {
try {
query = downloadPage(query);
} catch (CollectorException e) {
log.debug("CollectorPlugin.next()-Exception: {}", e);
throw new RuntimeException(e);
}
}
return recordQueue.poll();
synchronized (this.recordQueue) {
return this.recordQueue.poll();
}
}
/*
* download page and return nextQuery
* download page and return nextQuery (with number of attempt)
*/
private String downloadPage(String query) throws CollectorException {
private String downloadPage(String query, final int attempt) throws CollectorException {
if (attempt > MAX_ATTEMPTS) {
throw new CollectorException("Max Number of attempts reached, query:" + query);
}
if (attempt > 0) {
final int delay = (attempt * 5000);
log.debug("Attempt {} with delay {}", attempt, delay);
try {
Thread.sleep(delay);
} catch (final InterruptedException e) {
new CollectorException(e);
}
}
try {
String resultJson;
String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
String resultXml = XML_HEADER;
String nextQuery = "";
String emptyXml = resultXml + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG + ">";
Node resultNode = null;
NodeList nodeList = null;
String qUrlArgument = "";
@ -196,81 +236,96 @@ public class RestIterator implements Iterator<String> {
InputStream theHttpInputStream;
// check if cursor=* is initial set otherwise add it to the queryParam URL
if (resumptionType.equalsIgnoreCase("deep-cursor")) {
if ("deep-cursor".equalsIgnoreCase(this.resumptionType)) {
log.debug("check resumptionType deep-cursor and check cursor=*?{}", query);
if (!query.contains("&cursor=")) {
query += "&cursor=*";
}
}
// find pagination page start number in queryParam and remove before start the first query
if ((resumptionType.toLowerCase().equals("pagination") || resumptionType.toLowerCase().equals("page"))
&& (query.contains("paginationStart="))) {
final Matcher m = Pattern.compile("paginationStart=([0-9]+)").matcher(query);
m.find(); // guaranteed to be true for this regex
String[] pageVal = m.group(0).split("=");
pagination = Integer.parseInt(pageVal[1]);
// remove page start number from query and queryParams
queryParams = queryParams.replaceFirst("&?paginationStart=[0-9]+", "");
query = query.replaceFirst("&?paginationStart=[0-9]+", "");
}
try {
log.info("requestig URL [{}]", query);
log.info("requesting URL [{}]", query);
URL qUrl = new URL(query);
log.debug("authMethod: {}", authMethod);
if ("bearer".equalsIgnoreCase(this.authMethod)) {
log.trace("authMethod before inputStream: {}", resultXml);
HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + authToken);
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.getMimeType());
conn.setRequestMethod("GET");
theHttpInputStream = conn.getInputStream();
} else if (BASIC.equalsIgnoreCase(this.authMethod)) {
log.trace("authMethod before inputStream: {}", resultXml);
HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Basic " + authToken);
conn.setRequestProperty(HttpHeaders.ACCEPT, ContentType.APPLICATION_XML.getMimeType());
conn.setRequestMethod("GET");
theHttpInputStream = conn.getInputStream();
} else {
theHttpInputStream = qUrl.openStream();
final URL qUrl = new URL(query);
log.debug("authMethod: {}", this.authMethod);
if (this.authMethod == "bearer") {
log.trace("RestIterator.downloadPage():: authMethod before inputStream: " + resultXml);
requestHeaders.put("Authorization", "Bearer " + authToken);
// requestHeaders.put("Content-Type", "application/json");
} else if (AUTHBASIC.equalsIgnoreCase(this.authMethod)) {
log.trace("RestIterator.downloadPage():: authMethod before inputStream: " + resultXml);
requestHeaders.put("Authorization", "Basic " + authToken);
// requestHeaders.put("accept", "application/xml");
}
HttpURLConnection conn = (HttpURLConnection) qUrl.openConnection();
conn.setRequestMethod("GET");
this.setRequestHeader(conn);
resultStream = conn.getInputStream();
resultStream = theHttpInputStream;
if ("json".equals(resultOutputFormat)) {
resultJson = IOUtils.toString(resultStream, StandardCharsets.UTF_8);
if ("json".equals(this.resultOutputFormat)) {
resultJson = IOUtils.toString(this.resultStream, StandardCharsets.UTF_8);
resultXml = JsonUtils.convertToXML(resultJson);
resultStream = IOUtils.toInputStream(resultXml, UTF_8);
this.resultStream = IOUtils.toInputStream(resultXml, UTF_8);
}
if (!(emptyXml).equalsIgnoreCase(resultXml)) {
resultNode = (Node) xpath.evaluate("/", new InputSource(resultStream), XPathConstants.NODE);
nodeList = (NodeList) xprEntity.evaluate(resultNode, XPathConstants.NODESET);
if (!isEmptyXml(resultXml)) {
resultNode = (Node) this.xpath
.evaluate("/", new InputSource(this.resultStream), XPathConstants.NODE);
nodeList = (NodeList) this.xprEntity.evaluate(resultNode, XPathConstants.NODESET);
log.debug("nodeList.length: {}", nodeList.getLength());
for (int i = 0; i < nodeList.getLength(); i++) {
StringWriter sw = new StringWriter();
transformer.transform(new DOMSource(nodeList.item(i)), new StreamResult(sw));
String toEnqueue = sw.toString();
if (toEnqueue == null || StringUtils.isBlank(toEnqueue) || emptyXml.equalsIgnoreCase(toEnqueue)) {
log.warn("The following record resulted in empty item for the feeding queue: {}", resultXml);
final StringWriter sw = new StringWriter();
this.transformer.transform(new DOMSource(nodeList.item(i)), new StreamResult(sw));
final String toEnqueue = sw.toString();
if ((toEnqueue == null) || StringUtils.isBlank(toEnqueue) || isEmptyXml(toEnqueue)) {
log
.warn(
"The following record resulted in empty item for the feeding queue: {}", resultXml);
} else {
recordQueue.add(sw.toString());
this.recordQueue.add(sw.toString());
}
}
} else {
log.warn("resultXml is equal with emptyXml");
}
resumptionInt += resultSizeValue;
this.resumptionInt += this.resultSizeValue;
switch (resumptionType.toLowerCase()) {
switch (this.resumptionType.toLowerCase()) {
case "scan": // read of resumptionToken , evaluate next results, e.g. OAI, iterate over items
resumptionStr = xprResumptionPath.evaluate(resultNode);
this.resumptionStr = this.xprResumptionPath.evaluate(resultNode);
break;
case "count": // begin at one step for all records, iterate over items
resumptionStr = Integer.toString(resumptionInt);
this.resumptionStr = Integer.toString(this.resumptionInt);
break;
case "discover": // size of result items unknown, iterate over items (for openDOAR - 201808)
if (resultSizeValue < 2) {
if (this.resultSizeValue < 2) {
throw new CollectorException("Mode: discover, Param 'resultSizeValue' is less than 2");
}
qUrlArgument = qUrl.getQuery();
String[] arrayQUrlArgument = qUrlArgument.split("&");
for (String arrayUrlArgStr : arrayQUrlArgument) {
if (arrayUrlArgStr.startsWith(resumptionParam)) {
String[] resumptionKeyValue = arrayUrlArgStr.split("=");
final String[] arrayQUrlArgument = qUrlArgument.split("&");
for (final String arrayUrlArgStr : arrayQUrlArgument) {
if (arrayUrlArgStr.startsWith(this.resumptionParam)) {
final String[] resumptionKeyValue = arrayUrlArgStr.split("=");
if (isInteger(resumptionKeyValue[1])) {
urlOldResumptionSize = Integer.parseInt(resumptionKeyValue[1]);
log.debug("discover OldResumptionSize from Url (int): {}", urlOldResumptionSize);
@ -280,61 +335,63 @@ public class RestIterator implements Iterator<String> {
}
}
if (((emptyXml).equalsIgnoreCase(resultXml))
|| ((nodeList != null) && (nodeList.getLength() < resultSizeValue))) {
if (isEmptyXml(resultXml)
|| ((nodeList != null) && (nodeList.getLength() < this.resultSizeValue))) {
// resumptionStr = "";
if (nodeList != null) {
discoverResultSize += nodeList.getLength();
this.discoverResultSize += nodeList.getLength();
}
resultTotal = discoverResultSize;
this.resultTotal = this.discoverResultSize;
} else {
resumptionStr = Integer.toString(resumptionInt);
resultTotal = resumptionInt + 1;
this.resumptionStr = Integer.toString(this.resumptionInt);
this.resultTotal = this.resumptionInt + 1;
if (nodeList != null) {
discoverResultSize += nodeList.getLength();
this.discoverResultSize += nodeList.getLength();
}
}
log.info("discoverResultSize: {}", discoverResultSize);
log.info("discoverResultSize: {}", this.discoverResultSize);
break;
case "pagination":
case "page": // pagination, iterate over page numbers
pagination += 1;
if (nodeList != null) {
discoverResultSize += nodeList.getLength();
if (nodeList != null && nodeList.getLength() > 0) {
this.discoverResultSize += nodeList.getLength();
} else {
resultTotal = discoverResultSize;
pagination = discoverResultSize;
this.resultTotal = this.discoverResultSize;
this.pagination = this.discoverResultSize;
}
resumptionInt = pagination;
resumptionStr = Integer.toString(resumptionInt);
this.pagination += 1;
this.resumptionInt = this.pagination;
this.resumptionStr = Integer.toString(this.resumptionInt);
break;
case "deep-cursor": // size of result items unknown, iterate over items (for supporting deep cursor in
case "deep-cursor": // size of result items unknown, iterate over items (for supporting deep cursor
// in
// solr)
// isn't relevant -- if (resultSizeValue < 2) {throw new CollectorServiceException("Mode:
// deep-cursor, Param 'resultSizeValue' is less than 2");}
resumptionStr = encodeValue(xprResumptionPath.evaluate(resultNode));
queryParams = queryParams.replace("&cursor=*", "");
this.resumptionStr = encodeValue(this.xprResumptionPath.evaluate(resultNode));
this.queryParams = this.queryParams.replace("&cursor=*", "");
// terminating if length of nodeList is 0
if ((nodeList != null) && (nodeList.getLength() < discoverResultSize)) {
resumptionInt += (nodeList.getLength() + 1 - resultSizeValue);
if ((nodeList != null) && (nodeList.getLength() < this.discoverResultSize)) {
this.resumptionInt += ((nodeList.getLength() + 1) - this.resultSizeValue);
} else {
resumptionInt += (nodeList.getLength() - resultSizeValue); // subtract the resultSizeValue
this.resumptionInt += (nodeList.getLength() - this.resultSizeValue); // subtract the
// resultSizeValue
// because the iteration is over
// real length and the
// resultSizeValue is added before
// the switch()
}
discoverResultSize = nodeList.getLength();
this.discoverResultSize = nodeList.getLength();
log
.debug(
"downloadPage().deep-cursor: resumptionStr=" + resumptionStr + " ; queryParams="
+ queryParams + " resumptionLengthIncreased: " + resumptionInt);
"downloadPage().deep-cursor: resumptionStr=" + this.resumptionStr + " ; queryParams="
+ this.queryParams + " resumptionLengthIncreased: " + this.resumptionInt);
break;
@ -343,28 +400,30 @@ public class RestIterator implements Iterator<String> {
break;
}
} catch (Exception e) {
} catch (final Exception e) {
log.error(e.getMessage(), e);
throw new IllegalStateException("collection failed: " + e.getMessage());
}
try {
if (resultTotal == -1) {
resultTotal = Integer.parseInt(xprResultTotalPath.evaluate(resultNode));
if (resumptionType.equalsIgnoreCase("page") && !BASIC.equalsIgnoreCase(authMethod)) {
resultTotal += 1;
if (this.resultTotal == -1) {
this.resultTotal = Integer.parseInt(this.xprResultTotalPath.evaluate(resultNode));
if ("page".equalsIgnoreCase(this.resumptionType)
&& !this.AUTHBASIC.equalsIgnoreCase(this.authMethod)) {
this.resultTotal += 1;
} // to correct the upper bound
log.info("resultTotal was -1 is now: " + resultTotal);
log.info("resultTotal was -1 is now: " + this.resultTotal);
}
} catch (Exception e) {
} catch (final Exception e) {
log.error(e.getMessage(), e);
throw new IllegalStateException("downloadPage resultTotal couldn't parse: " + e.getMessage());
}
log.debug("resultTotal: " + resultTotal);
log.debug("resInt: " + resumptionInt);
if (resumptionInt <= resultTotal) {
nextQuery = baseUrl + "?" + queryParams + querySize + "&" + resumptionParam + "=" + resumptionStr
+ queryFormat;
log.debug("resultTotal: " + this.resultTotal);
log.debug("resInt: " + this.resumptionInt);
if (this.resumptionInt <= this.resultTotal) {
nextQuery = this.baseUrl + "?" + this.queryParams + this.querySize + "&" + this.resumptionParam + "="
+ this.resumptionStr
+ this.queryFormat;
} else {
nextQuery = "";
// if (resumptionType.toLowerCase().equals("deep-cursor")) { resumptionInt -= 1; } // correct the
@ -372,10 +431,18 @@ public class RestIterator implements Iterator<String> {
}
log.debug("nextQueryUrl: " + nextQuery);
return nextQuery;
} catch (final Throwable e) {
log.warn(e.getMessage(), e);
return downloadPage(query, attempt + 1);
}
}
private boolean isInteger(String s) {
private boolean isEmptyXml(String s) {
return EMPTY_XML.equalsIgnoreCase(s);
}
private boolean isInteger(final String s) {
boolean isValidInteger = false;
try {
Integer.parseInt(s);
@ -383,7 +450,7 @@ public class RestIterator implements Iterator<String> {
// s is a valid integer
isValidInteger = true;
} catch (NumberFormatException ex) {
} catch (final NumberFormatException ex) {
// s is not an integer
}
@ -391,20 +458,36 @@ public class RestIterator implements Iterator<String> {
}
// Method to encode a string value using `UTF-8` encoding scheme
private String encodeValue(String value) {
private String encodeValue(final String value) {
try {
return URLEncoder.encode(value, StandardCharsets.UTF_8.toString());
} catch (UnsupportedEncodingException ex) {
} catch (final UnsupportedEncodingException ex) {
throw new RuntimeException(ex.getCause());
}
}
/**
* setRequestHeader
*
* setRequestProperty: Sets the general request property. If a property with the key already exists, overwrite its value with the new value.
* @param conn
*/
private void setRequestHeader(HttpURLConnection conn) {
if (requestHeaders != null) {
for (String key : requestHeaders.keySet()) {
conn.setRequestProperty(key, requestHeaders.get(key));
}
log.debug("Set Request Header with: " + requestHeaders);
}
}
public String getResultFormatValue() {
return resultFormatValue;
return this.resultFormatValue;
}
public String getResultOutputFormat() {
return resultOutputFormat;
return this.resultOutputFormat;
}
}

View File

@ -29,6 +29,18 @@
"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": "pip",
"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

@ -17,6 +17,14 @@
<name>dataciteInputPath</name>
<description>the path where to find the inferred affiliation relations from Datacite</description>
</property>
<property>
<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>
@ -112,7 +120,8 @@
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
<arg>--openapcInputPath</arg><arg>${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

@ -16,5 +16,10 @@
"paramLongName": "isSparkSessionManaged",
"paramDescription": "the hdfs name node",
"paramRequired": false
},{
"paramName": "bl",
"paramLongName": "blackListPath",
"paramDescription": "the working path",
"paramRequired": true
}
]

View File

@ -1,2 +1,3 @@
sourcePath=/user/miriam.baglioni/openalex-snapshot/data/works/
outputPath=/tmp/miriam/webcrawlComplete/
blackListPath=/user/miriam.baglioni/openalex-blackList

View File

@ -45,6 +45,7 @@
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
<arg>--blackListPath</arg><arg>${blackListPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

View File

@ -1,10 +1,5 @@
[
{
"id": "100007630",
"uri": "http://dx.doi.org/10.13039/100007630",
"name": "College of Engineering and Informatics, National University of Ireland, Galway",
"synonym": []
},
{
"id": "100007731",
"uri": "http://dx.doi.org/10.13039/100007731",
@ -58,7 +53,7 @@
"uri": "http://dx.doi.org/10.13039/100010414",
"name": "Health Research Board",
"synonym": [
"501100001590"
"501100001590", "501100023273"
]
},
{
@ -85,24 +80,6 @@
"name": "Irish College of General Practitioners",
"synonym": []
},
{
"id": "100012734",
"uri": "http://dx.doi.org/10.13039/100012734",
"name": "Department for Culture, Heritage and the Gaeltacht, Ireland",
"synonym": []
},
{
"id": "100012754",
"uri": "http://dx.doi.org/10.13039/100012754",
"name": "Horizon Pharma",
"synonym": []
},
{
"id": "100012891",
"uri": "http://dx.doi.org/10.13039/100012891",
"name": "Medical Research Charities Group",
"synonym": []
},
{
"id": "100012919",
"uri": "http://dx.doi.org/10.13039/100012919",
@ -233,7 +210,7 @@
"id": "100018064",
"uri": "http://dx.doi.org/10.13039/100018064",
"name": "Department of Tourism, Culture, Arts, Gaeltacht, Sport and Media",
"synonym": []
"synonym": ["100012734"]
},
{
"id": "100018172",
@ -281,13 +258,13 @@
"id": "100019637",
"uri": "http://dx.doi.org/10.13039/100019637",
"name": "Horizon Therapeutics",
"synonym": []
"synonym": ["100012754"]
},
{
"id": "100020174",
"uri": "http://dx.doi.org/10.13039/100020174",
"name": "Health Research Charities Ireland",
"synonym": []
"synonym": ["100012891"]
},
{
"id": "100020202",
@ -319,12 +296,7 @@
"name": "Centre for Ageing Research and Development in Ireland",
"synonym": []
},
{
"id": "501100001583",
"uri": "http://dx.doi.org/10.13039/501100001583",
"name": "Cystinosis Foundation Ireland",
"synonym": []
},
{
"id": "501100001584",
"uri": "http://dx.doi.org/10.13039/501100001584",
@ -455,13 +427,13 @@
"id": "501100001634",
"uri": "http://dx.doi.org/10.13039/501100001634",
"name": "University of Galway",
"synonym": []
"synonym": ["501100019905", "100007630", "501100020570", "501100023852"]
},
{
"id": "501100001635",
"uri": "http://dx.doi.org/10.13039/501100001635",
"name": "University of Limerick",
"synonym": []
"synonym": ["501100014531"]
},
{
"id": "501100001636",
@ -491,7 +463,7 @@
"id": "501100002736",
"uri": "http://dx.doi.org/10.13039/501100002736",
"name": "Covidien",
"synonym": []
"synonym": ["501100003956"]
},
{
"id": "501100002755",
@ -521,7 +493,7 @@
"id": "501100003037",
"uri": "http://dx.doi.org/10.13039/501100003037",
"name": "Elan",
"synonym": []
"synonym": ["501100021694"]
},
{
"id": "501100003496",
@ -541,12 +513,6 @@
"name": "Irish Institute of Clinical Neuroscience",
"synonym": []
},
{
"id": "501100003956",
"uri": "http://dx.doi.org/10.13039/501100003956",
"name": "Aspect Medical Systems",
"synonym": []
},
{
"id": "501100004162",
"uri": "http://dx.doi.org/10.13039/501100004162",
@ -595,17 +561,11 @@
"name": "Technological University Dublin",
"synonym": []
},
{
"id": "501100009269",
"uri": "http://dx.doi.org/10.13039/501100009269",
"name": "Programme of Competitive Forestry Research for Development",
"synonym": []
},
{
"id": "501100009315",
"uri": "http://dx.doi.org/10.13039/501100009315",
"name": "Cystinosis Ireland",
"synonym": []
"synonym": ["501100001583"]
},
{
"id": "501100010808",
@ -625,12 +585,6 @@
"name": "Alimentary Health",
"synonym": []
},
{
"id": "501100011103",
"uri": "http://dx.doi.org/10.13039/501100011103",
"name": "Rann\u00eds",
"synonym": []
},
{
"id": "501100012354",
"uri": "http://dx.doi.org/10.13039/501100012354",
@ -679,12 +633,7 @@
"name": "Irish Centre for High-End Computing",
"synonym": []
},
{
"id": "501100019905",
"uri": "http://dx.doi.org/10.13039/501100019905",
"name": "Galway University Foundation",
"synonym": []
},
{
"id": "501100020036",
"uri": "http://dx.doi.org/10.13039/501100020036",
@ -733,12 +682,6 @@
"name": "Insight SFI Research Centre for Data Analytics",
"synonym": []
},
{
"id": "501100021694",
"uri": "http://dx.doi.org/10.13039/501100021694",
"name": "Elan Pharma International",
"synonym": []
},
{
"id": "501100021838",
"uri": "http://dx.doi.org/10.13039/501100021838",
@ -769,12 +712,6 @@
"name": "Institute of Technology, Tralee",
"synonym": []
},
{
"id": "501100023273",
"uri": "http://dx.doi.org/10.13039/501100023273",
"name": "HRB Clinical Research Facility Galway",
"synonym": []
},
{
"id": "501100023378",
"uri": "http://dx.doi.org/10.13039/501100023378",
@ -871,12 +808,7 @@
"name": "Energy Policy Research Centre, Economic and Social Research Institute",
"synonym": []
},
{
"id": "501100014531",
"uri": "http://dx.doi.org/10.13039/501100014531",
"name": "Physical Education and Sport Sciences Department, University of Limerick",
"synonym": []
},
{
"id": "501100014745",
"uri": "http://dx.doi.org/10.13039/501100014745",
@ -889,22 +821,11 @@
"name": "ADAPT - Centre for Digital Content Technology",
"synonym": []
},
{
"id": "501100020570",
"uri": "http://dx.doi.org/10.13039/501100020570",
"name": "College of Medicine, Nursing and Health Sciences, National University of Ireland, Galway",
"synonym": []
},
{
"id": "501100020871",
"uri": "http://dx.doi.org/10.13039/501100020871",
"name": "Bernal Institute, University of Limerick",
"synonym": []
},
{
"id": "501100023852",
"uri": "http://dx.doi.org/10.13039/501100023852",
"name": "Moore Institute for Research in the Humanities and Social Studies, University of Galway",
"synonym": []
}
]

View File

@ -48,12 +48,37 @@
<description>Used to configure the heap size for the map JVM process. Should be 80% of mapreduce.map.memory.mb.</description>
</property>
<property>
<name>JAVA_HOME</name>
<value>/srv/java/openjdk-17</value>
<description>Used to configure the Java home location for oozie.launcher.mapreduce.map.env</description>
</property>
<property>
<name>JAVA_OPTS</name>
<value>-Dcom.sun.security.enableAIAcaIssuers=true</value>
<description>Used to configure the JAVA_OPTS parameter</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.launcher.mapreduce.map.env</name>
<value>JAVA_HOME=${JAVA_HOME}</value>
</property>
</configuration>
</global>
<start to="collection_mode"/>
@ -99,7 +124,7 @@
<action name="CollectionWorker">
<java>
<main-class>eu.dnetlib.dhp.collection.CollectorWorkerApplication</main-class>
<java-opts>${collection_java_xmx}</java-opts>
<java-opts>${JAVA_OPTS} ${collection_java_xmx}</java-opts>
<arg>--apidescriptor</arg><arg>${apiDescription}</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--workflowId</arg><arg>${workflowId}</arg>

View File

@ -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

@ -93,7 +93,7 @@ case object Crossref2Oaf {
val cf = new KeyValue
cf.setValue("UnpayWall")
cf.setKey(s"10|openaire____:${DHPUtils.md5("UnpayWall".toLowerCase)}")
cf.setKey(s"10|openaire____::${DHPUtils.md5("UnpayWall".toLowerCase)}")
cf
}

View File

@ -79,23 +79,6 @@ object MagUtility extends Serializable {
private val MAGCollectedFrom = keyValue(ModelConstants.MAG_ID, ModelConstants.MAG_NAME)
private val MAGDataInfo: DataInfo = {
val di = new DataInfo
di.setDeletedbyinference(false)
di.setInferred(false)
di.setInvisible(false)
di.setTrust("0.9")
di.setProvenanceaction(
OafMapperUtils.qualifier(
ModelConstants.SYSIMPORT_ACTIONSET,
ModelConstants.SYSIMPORT_ACTIONSET,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS
)
)
di
}
private val MAGDataInfoInvisible: DataInfo = {
val di = new DataInfo
di.setDeletedbyinference(false)
di.setInferred(false)
@ -453,7 +436,6 @@ object MagUtility extends Serializable {
case "repository" =>
result = new Publication()
result.setDataInfo(MAGDataInfoInvisible)
qualifier(
"0038",
"Other literature type",
@ -488,7 +470,6 @@ object MagUtility extends Serializable {
}
if (result != null) {
if (result.getDataInfo == null)
result.setDataInfo(MAGDataInfo)
val i = new Instance
i.setInstancetype(tp)
@ -512,7 +493,7 @@ object MagUtility extends Serializable {
return null
result.setCollectedfrom(List(MAGCollectedFrom).asJava)
val pidList = List(
var pidList = List(
structuredProperty(
paper.paperId.get.toString,
qualifier(
@ -525,8 +506,6 @@ object MagUtility extends Serializable {
)
)
result.setPid(pidList.asJava)
result.setOriginalId(pidList.map(s => s.getValue).asJava)
result.setId(s"50|mag_________::${DHPUtils.md5(paper.paperId.get.toString)}")
@ -618,10 +597,9 @@ object MagUtility extends Serializable {
}
val instance = result.getInstance().get(0)
instance.setPid(pidList.asJava)
if (paper.doi.orNull != null)
instance.setAlternateIdentifier(
List(
if (paper.doi.orNull != null) {
pidList = pidList ::: List(
structuredProperty(
paper.doi.get,
qualifier(
@ -632,8 +610,10 @@ object MagUtility extends Serializable {
),
null
)
).asJava
)
}
instance.setPid(pidList.asJava)
result.setPid(pidList.asJava)
instance.setUrl(paper.urls.get.asJava)
instance.setHostedby(ModelConstants.UNKNOWN_REPOSITORY)
instance.setCollectedfrom(MAGCollectedFrom)

View File

@ -38,6 +38,7 @@ class SparkMAGtoOAF(propertyPath: String, args: Array[String], log: Logger)
spark.read
.load(s"$magBasePath/mag_denormalized")
.as[MAGPaper]
.filter(col("doi").isNotNull)
.map(s => MagUtility.convertMAGtoOAF(s))
.filter(s => s != null)
.write

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

@ -78,6 +78,10 @@ public class PrepareAffiliationRelationsTest {
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
.getPath();
String publisherAffiliationRelationPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/publishers")
.getPath();
String outputPath = workingDir.toString() + "/actionSet";
PrepareAffiliationRelations
@ -88,6 +92,8 @@ public class PrepareAffiliationRelationsTest {
"-pubmedInputPath", crossrefAffiliationRelationPath,
"-openapcInputPath", crossrefAffiliationRelationPath,
"-dataciteInputPath", crossrefAffiliationRelationPath,
"-webCrawlInputPath", crossrefAffiliationRelationPath,
"-publisherInputPath", publisherAffiliationRelationPath,
"-outputPath", outputPath
});
@ -104,7 +110,7 @@ public class PrepareAffiliationRelationsTest {
// );
// }
// count the number of relations
assertEquals(80, tmp.count());
assertEquals(138, tmp.count());
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
dataset.createOrReplaceTempView("result");
@ -115,7 +121,7 @@ public class PrepareAffiliationRelationsTest {
// verify that we have equal number of bi-directional relations
Assertions
.assertEquals(
40, execVerification
69, execVerification
.filter(
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
.collectAsList()
@ -123,7 +129,7 @@ public class PrepareAffiliationRelationsTest {
Assertions
.assertEquals(
40, execVerification
69, execVerification
.filter(
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
.collectAsList()
@ -144,5 +150,12 @@ public class PrepareAffiliationRelationsTest {
.get(0)
.getString(4));
final String publisherid = ID_PREFIX
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s00217-010-1268-9"));
final String rorId = "20|ror_________::" + IdentifierFactory.md5("https://ror.org/03265fv13");
Assertions
.assertEquals(
1, execVerification.filter("source = '" + publisherid + "' and target = '" + rorId + "'").count());
}
}

View File

@ -75,7 +75,11 @@ public class CreateASTest {
String inputPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/webcrawl/")
"/eu/dnetlib/dhp/actionmanager/webcrawl/input/")
.getPath();
String blackListPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/webcrawl/blackList/")
.getPath();
CreateActionSetFromWebEntries
@ -86,7 +90,8 @@ public class CreateASTest {
"-sourcePath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet1"
workingDir.toString() + "/actionSet1",
"-blackListPath", blackListPath
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
@ -96,7 +101,7 @@ public class CreateASTest {
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
Assertions.assertEquals(64, tmp.count());
Assertions.assertEquals(58, tmp.count());
}
@ -109,6 +114,10 @@ public class CreateASTest {
.getResource(
"/eu/dnetlib/dhp/actionmanager/webcrawl/")
.getPath();
String blackListPath = getClass()
.getResource(
"/eu/dnetlib/dhp/actionmanager/webcrawl/blackList/")
.getPath();
CreateActionSetFromWebEntries
.main(
@ -118,7 +127,8 @@ public class CreateASTest {
"-sourcePath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet1"
workingDir.toString() + "/actionSet1",
"-blackListPath", blackListPath
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
@ -184,7 +194,7 @@ public class CreateASTest {
Assertions
.assertEquals(
5, tmp
2, tmp
.filter(
r -> r
.getSource()
@ -197,7 +207,7 @@ public class CreateASTest {
Assertions
.assertEquals(
5, tmp
2, tmp
.filter(
r -> r
.getTarget()
@ -210,7 +220,7 @@ public class CreateASTest {
Assertions
.assertEquals(
2, tmp
1, tmp
.filter(
r -> r
.getTarget()
@ -224,7 +234,7 @@ public class CreateASTest {
Assertions
.assertEquals(
2, tmp
1, tmp
.filter(
r -> r
.getTarget()
@ -238,7 +248,7 @@ public class CreateASTest {
Assertions
.assertEquals(
1, tmp
0, tmp
.filter(
r -> r
.getTarget()

View File

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.collection.plugin.rest;
import java.util.HashMap;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.concurrent.atomic.AtomicLong;
import java.util.stream.Stream;
import org.junit.jupiter.api.Assertions;
@ -38,8 +39,8 @@ public class OsfPreprintCollectorTest {
private final String resumptionType = "page";
private final String resumptionXpath = "/*/*[local-name()='links']/*[local-name()='next']";
private final String resultSizeParam = "";
private final String resultSizeValue = "";
private final String resultSizeParam = "page[size]";
private final String resultSizeValue = "100";
private final String resultFormatParam = "format";
private final String resultFormatValue = "json";
@ -69,11 +70,11 @@ public class OsfPreprintCollectorTest {
@Test
@Disabled
void test() throws CollectorException {
void test_limited() throws CollectorException {
final AtomicInteger i = new AtomicInteger(0);
final Stream<String> stream = this.rcp.collect(this.api, new AggregatorReport());
stream.limit(200).forEach(s -> {
stream.limit(2000).forEach(s -> {
Assertions.assertTrue(s.length() > 0);
i.incrementAndGet();
log.info(s);
@ -82,4 +83,23 @@ public class OsfPreprintCollectorTest {
log.info("{}", i.intValue());
Assertions.assertTrue(i.intValue() > 0);
}
@Test
@Disabled
void test_all() throws CollectorException {
final AtomicLong i = new AtomicLong(0);
final Stream<String> stream = this.rcp.collect(this.api, new AggregatorReport());
stream.forEach(s -> {
Assertions.assertTrue(s.length() > 0);
if ((i.incrementAndGet() % 1000) == 0) {
log.info("COLLECTED: {}", i.get());
}
});
log.info("TOTAL: {}", i.get());
Assertions.assertTrue(i.get() > 0);
}
}

View File

@ -4,6 +4,11 @@
package eu.dnetlib.dhp.collection.plugin.rest;
import java.io.IOException;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.HashMap;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Stream;
@ -12,6 +17,8 @@ import org.junit.jupiter.api.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.gson.Gson;
import eu.dnetlib.dhp.collection.ApiDescriptor;
import eu.dnetlib.dhp.common.aggregation.AggregatorReport;
import eu.dnetlib.dhp.common.collection.CollectorException;
@ -25,18 +32,18 @@ class RestCollectorPluginTest {
private static final Logger log = LoggerFactory.getLogger(RestCollectorPluginTest.class);
private final String baseUrl = "https://share.osf.io/api/v2/search/creativeworks/_search";
private final String resumptionType = "count";
private final String resumptionParam = "from";
private final String entityXpath = "//hits/hits";
private final String resumptionXpath = "//hits";
private final String resultTotalXpath = "//hits/total";
private final String resultFormatParam = "format";
private final String baseUrl = "https://ddh-openapi.worldbank.org/search";
private final String resumptionType = "discover";
private final String resumptionParam = "skip";
private final String entityXpath = "//*[local-name()='data']";
private final String resumptionXpath = "";
private final String resultTotalXpath = "//*[local-name()='count']";
private final String resultFormatParam = "";
private final String resultFormatValue = "json";
private final String resultSizeParam = "size";
private final String resultSizeParam = "top";
private final String resultSizeValue = "10";
// private String query = "q=%28sources%3ASocArXiv+AND+type%3Apreprint%29";
private final String query = "q=%28sources%3AengrXiv+AND+type%3Apreprint%29";
private final String query = "";
// private String query = "=(sources:engrXiv AND type:preprint)";
private final String protocolDescriptor = "rest_json2xml";
@ -56,6 +63,7 @@ class RestCollectorPluginTest {
params.put("resultSizeValue", resultSizeValue);
params.put("queryParams", query);
params.put("entityXpath", entityXpath);
params.put("requestHeaderMap", "{\"User-Agent\": \"OpenAIRE DEV\"}");
api.setBaseUrl(baseUrl);
api.setParams(params);
@ -78,4 +86,19 @@ class RestCollectorPluginTest {
log.info("{}", i.intValue());
Assertions.assertTrue(i.intValue() > 0);
}
@Disabled
@Test
void testUrl() throws IOException {
String url_s = "https://ddh-openapi.worldbank.org/search?&top=10";
URL url = new URL(url_s);
final HttpURLConnection conn = (HttpURLConnection) url.openConnection();
conn.setRequestMethod("GET");
conn.setRequestProperty("User-Agent", "OpenAIRE");
Gson gson = new Gson();
System.out.println("Request header");
System.out.println(gson.toJson(conn.getHeaderFields()));
InputStream inputStream = conn.getInputStream();
}
}

View File

@ -44,7 +44,7 @@ public class RestIteratorTest {
final RestIterator iterator = new RestIterator(clientParams, baseUrl, resumptionType, resumptionParam,
resumptionXpath, resultTotalXpath, resultFormatParam, resultFormatValue, resultSizeParam, resultSizeValue,
query, entityXpath, authMethod, authToken, resultOffsetParam);
query, entityXpath, authMethod, authToken, resultOffsetParam, null);
int i = 20;
while (iterator.hasNext() && i > 0) {
String result = iterator.next();

View File

@ -5,3 +5,5 @@
{"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"}]}

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

@ -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

@ -3,6 +3,7 @@ package eu.dnetlib.dhp.collection.mag
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.oaf.{Dataset, Publication, Result}
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions.col
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
@ -18,10 +19,8 @@ class MAGMappingTest {
.master("local[*]")
.getOrCreate()
val s = new SparkMagOrganizationAS(null, null, null)
s.generateAS(spark, "/home/sandro/Downloads/mag_test", "/home/sandro/Downloads/mag_AS")
val s = new SparkMAGtoOAF(null, null, null)
s.convertMAG(spark, "/Users/sandro/Downloads/", "/Users/sandro/Downloads/mag_OAF")
}
@Test

View File

@ -26,15 +26,15 @@ import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.Software;
public class PrepareSimpleEntititiesJob {
public class PrepareSimpleEntitiesJob {
private static final Logger log = LoggerFactory.getLogger(PrepareSimpleEntititiesJob.class);
private static final Logger log = LoggerFactory.getLogger(PrepareSimpleEntitiesJob.class);
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
PrepareSimpleEntititiesJob.class
PrepareSimpleEntitiesJob.class
.getResourceAsStream("/eu/dnetlib/dhp/broker/oa/common_params.json")));
parser.parseArgument(args);

View File

@ -160,8 +160,7 @@ public class ConversionUtils {
.stream()
.filter(Objects::nonNull)
.filter(pid -> pid.getQualifier() != null)
.filter(pid -> pid.getQualifier().getClassid() != null)
.filter(pid -> pid.getQualifier().getClassid().equalsIgnoreCase(ModelConstants.ORCID))
.filter(pid -> StringUtils.startsWithIgnoreCase(pid.getQualifier().getClassid(), ModelConstants.ORCID))
.map(StructuredProperty::getValue)
.map(ConversionUtils::cleanOrcid)
.filter(StringUtils::isNotBlank)

View File

@ -7,7 +7,7 @@
</property>
<property>
<name>outputDir</name>
<description>the path where the the generated data will be stored</description>
<description>the path where the generated data will be stored</description>
</property>
<property>
<name>datasourceIdWhitelist</name>
@ -179,17 +179,18 @@
<master>yarn</master>
<mode>cluster</mode>
<name>PrepareSimpleEntititiesJob</name>
<class>eu.dnetlib.dhp.broker.oa.PrepareSimpleEntititiesJob</class>
<class>eu.dnetlib.dhp.broker.oa.PrepareSimpleEntitiesJob</class>
<jar>dhp-broker-events-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=5000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -209,11 +210,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -234,11 +236,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -258,11 +261,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=5000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -282,11 +286,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=10000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -306,11 +311,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=2000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -332,11 +338,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -356,11 +363,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -380,11 +388,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -404,11 +413,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -428,11 +438,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -452,11 +463,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--graphPath</arg><arg>${graphInputPath}</arg>
<arg>--workingDir</arg><arg>${workingDir}</arg>
@ -476,11 +488,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${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.shuffle.partitions=3840
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--workingDir</arg><arg>${workingDir}</arg>
<arg>--outputDir</arg><arg>${outputDir}</arg>
@ -503,6 +516,7 @@
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.dynamicAllocation.maxExecutors=${sparkMaxExecutorsForIndexing}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -535,6 +549,7 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -562,6 +577,7 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -585,6 +601,7 @@
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.dynamicAllocation.maxExecutors=${sparkMaxExecutorsForIndexing}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}

View File

@ -0,0 +1,66 @@
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.List;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import eu.dnetlib.broker.objects.OaBrokerAuthor;
import eu.dnetlib.broker.objects.OaBrokerMainEntity;
class EnrichMissingAuthorOrcidTest {
final EnrichMissingAuthorOrcid matcher = new EnrichMissingAuthorOrcid();
@BeforeEach
void setUp() throws Exception {
}
@Test
void testFindDifferences_1() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
@Test
void testFindDifferences_2() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", null));
final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
assertEquals(1, list.size());
}
@Test
void testFindDifferences_3() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", null));
target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
@Test
void testFindDifferences_4() {
final OaBrokerMainEntity source = new OaBrokerMainEntity();
final OaBrokerMainEntity target = new OaBrokerMainEntity();
source.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
target.getCreators().add(new OaBrokerAuthor("Claudio Atzori", "0000-0001-9613-6639"));
final List<OaBrokerAuthor> list = this.matcher.findDifferences(source, target);
assertTrue(list.isEmpty());
}
}

View File

@ -2,27 +2,32 @@
package eu.dnetlib.dhp.broker.oa.util;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertNull;
import java.util.ArrayList;
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;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.Instance;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
class ConversionUtilsTest {
public class ConversionUtilsTest {
@BeforeEach
void setUp() throws Exception {
public void setUp() throws Exception {
}
@Test
void testAllResultPids() {
public void testAllResultPids() {
final Qualifier qf = new Qualifier();
qf.setClassid("test");
qf.setClassname("test");
@ -91,4 +96,42 @@ class ConversionUtilsTest {
assertEquals(6, list.size());
}
public void testOafResultToBrokerResult() {
final Author a1 = createAuthor("Michele Artini", "0000-0002-4406-428X");
final Author a2 = createAuthor("Claudio Atzori", "http://orcid.org/0000-0001-9613-6639");
final Author a3 = createAuthor("Alessia Bardi", null);
final Result r = new Result();
r.setAuthor(Arrays.asList(a1, a2, a3));
final OaBrokerMainEntity br = ConversionUtils.oafResultToBrokerResult(r);
assertEquals(3, br.getCreators().size());
assertEquals("0000-0002-4406-428X", br.getCreators().get(0).getOrcid());
assertEquals("0000-0001-9613-6639", br.getCreators().get(1).getOrcid());
assertNull(br.getCreators().get(2).getOrcid());
}
private Author createAuthor(final String name, final String orcid) {
final Author a = new Author();
a.setFullname("Michele Artini");
if (orcid != null) {
final Qualifier q = new Qualifier();
q.setClassid(ModelConstants.ORCID);
q.setClassname(ModelConstants.ORCID);
q.setSchemeid("dnet:pids");
q.setSchemename("dnet:pids");
final StructuredProperty pid = new StructuredProperty();
pid.setQualifier(q);
pid.setValue(orcid);
a.setPid(Arrays.asList(pid));
}
return a;
}
}

View File

@ -203,8 +203,8 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
WindowSpec w = Window
.partitionBy("groupId")
.orderBy(
col("lastUsage").desc_nulls_last(),
col("pidType").asc_nulls_last(),
col("lastUsage").desc_nulls_last(),
col("collectedfrom").desc_nulls_last(),
col("date").asc_nulls_last(),
col("id").asc_nulls_last());

View File

@ -22,7 +22,9 @@ import eu.dnetlib.dhp.oa.dedup.model.OrgSimRel;
import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@ -164,12 +166,12 @@ public class SparkPrepareNewOrgs extends AbstractSparkAction {
.map(
(MapFunction<Tuple2<Tuple2<String, Organization>, Tuple2<String, String>>, OrgSimRel>) r -> new OrgSimRel(
"",
r._1()._2().getOriginalId().get(0),
r._1()._2().getLegalname() != null ? r._1()._2().getLegalname().getValue() : "",
r._1()._2().getLegalshortname() != null ? r._1()._2().getLegalshortname().getValue() : "",
r._1()._2().getCountry() != null ? r._1()._2().getCountry().getClassid() : "",
r._1()._2().getWebsiteurl() != null ? r._1()._2().getWebsiteurl().getValue() : "",
r._1()._2().getCollectedfrom().get(0).getValue(),
Optional.ofNullable(r._1()._2().getOriginalId()).map(oid -> oid.get(0)).orElse(null),
Optional.ofNullable(r._1()._2().getLegalname()).map(Field::getValue).orElse(""),
Optional.ofNullable(r._1()._2().getLegalshortname()).map(Field::getValue).orElse(""),
Optional.ofNullable(r._1()._2().getCountry()).map(Qualifier::getClassid).orElse(""),
Optional.ofNullable(r._1()._2().getWebsiteurl()).map(Field::getValue).orElse(""),
Optional.ofNullable(r._1()._2().getCollectedfrom()).map(cf -> cf.get(0).getValue()).orElse(null),
"",
structuredPropertyListToString(r._1()._2().getPid()),
parseECField(r._1()._2().getEclegalbody()),

View File

@ -217,7 +217,7 @@ public class SparkPrepareOrgRels extends AbstractSparkAction {
final Organization o = r._2()._2();
return new OrgSimRel(
r._1()._1(),
o.getOriginalId().get(0),
Optional.ofNullable(o.getOriginalId()).map(oid -> oid.get(0)).orElse(null),
Optional.ofNullable(o.getLegalname()).map(Field::getValue).orElse(""),
Optional.ofNullable(o.getLegalshortname()).map(Field::getValue).orElse(""),
Optional.ofNullable(o.getCountry()).map(Qualifier::getClassid).orElse(""),
@ -249,7 +249,9 @@ public class SparkPrepareOrgRels extends AbstractSparkAction {
.map(
(MapFunction<Tuple2<Tuple2<String, OrgSimRel>, Tuple2<String, Organization>>, OrgSimRel>) r -> {
OrgSimRel orgSimRel = r._1()._2();
orgSimRel.setLocal_id(r._2()._2().getOriginalId().get(0));
orgSimRel
.setLocal_id(
Optional.ofNullable(r._2()._2().getOriginalId()).map(oid -> oid.get(0)).orElse(null));
return orgSimRel;
},
Encoders.bean(OrgSimRel.class));

View File

@ -15,4 +15,12 @@
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hiveMetastoreUris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>pivotHistoryDatabase</name>
<value>&#x200B;</value>
</property>
</configuration>

View File

@ -198,6 +198,8 @@
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--actionSetId</arg><arg>${actionSetId}</arg>
<arg>--cutConnectedComponent</arg><arg>${cutConnectedComponent}</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
<arg>--pivotHistoryDatabase</arg><arg>${pivotHistoryDatabase}</arg>
</spark>
<ok to="PrepareOrgRels"/>
<error to="Kill"/>

View File

@ -0,0 +1,103 @@
package eu.dnetlib.dhp.oa.dedup;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.io.Serializable;
import java.lang.reflect.InvocationTargetException;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;
import org.codehaus.jackson.map.ObjectMapper;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
import eu.dnetlib.pace.util.MapDocumentUtil;
import scala.Tuple2;
class DatasetMergerTest implements Serializable {
private List<Tuple2<String, Dataset>> datasets;
private String testEntityBasePath;
private DataInfo dataInfo;
private final String dedupId = "50|doi_________::3d18564ef27ebe9ef3bd8b4dec67e148";
private Dataset dataset_top;
@BeforeEach
public void setUp() throws Exception {
testEntityBasePath = Paths
.get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/json").toURI())
.toFile()
.getAbsolutePath();
datasets = readSample(testEntityBasePath + "/dataset_merge.json", Dataset.class);
dataset_top = getTopPub(datasets);
dataInfo = setDI();
}
@Test
void datasetMergerTest() throws InstantiationException, IllegalAccessException, InvocationTargetException {
Dataset pub_merged = MergeUtils.mergeGroup(dedupId, datasets.stream().map(Tuple2::_2).iterator());
// verify id
assertEquals(dedupId, pub_merged.getId());
assertEquals(2, pub_merged.getInstance().size());
}
public DataInfo setDI() {
DataInfo dataInfo = new DataInfo();
dataInfo.setTrust("0.9");
dataInfo.setDeletedbyinference(false);
dataInfo.setInferenceprovenance("testing");
dataInfo.setInferred(true);
return dataInfo;
}
public Dataset getTopPub(List<Tuple2<String, Dataset>> publications) {
Double maxTrust = 0.0;
Dataset maxPub = new Dataset();
for (Tuple2<String, Dataset> publication : publications) {
Double pubTrust = Double.parseDouble(publication._2().getDataInfo().getTrust());
if (pubTrust > maxTrust) {
maxTrust = pubTrust;
maxPub = publication._2();
}
}
return maxPub;
}
public <T> List<Tuple2<String, T>> readSample(String path, Class<T> clazz) {
List<Tuple2<String, T>> res = new ArrayList<>();
BufferedReader reader;
try {
reader = new BufferedReader(new FileReader(path));
String line = reader.readLine();
while (line != null) {
res
.add(
new Tuple2<>(
MapDocumentUtil.getJPathString("$.id", line),
new ObjectMapper().readValue(line, clazz)));
// read next line
line = reader.readLine();
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
return res;
}
}

View File

@ -93,14 +93,14 @@ class EntityMergerTest implements Serializable {
assertEquals(pub_top.getJournal().getConferencedate(), pub_merged.getJournal().getConferencedate());
assertEquals(pub_top.getJournal().getConferenceplace(), pub_merged.getJournal().getConferenceplace());
assertEquals("OPEN", pub_merged.getBestaccessright().getClassid());
assertEquals(pub_top.getResulttype(), pub_merged.getResulttype());
assertEquals(pub_top.getLanguage(), pub_merged.getLanguage());
assertEquals(pub_top.getPublisher(), pub_merged.getPublisher());
assertEquals(pub_top.getEmbargoenddate(), pub_merged.getEmbargoenddate());
assertEquals(pub_top.getResulttype().getClassid(), pub_merged.getResulttype().getClassid());
assertEquals(pub_top.getLanguage().getClassid(), pub_merged.getLanguage().getClassid());
assertEquals("Elsevier BV", pub_merged.getPublisher().getValue());
assertEquals(pub_top.getEmbargoenddate().getValue(), pub_merged.getEmbargoenddate().getValue());
assertEquals(pub_top.getResourcetype().getClassid(), "");
assertEquals(pub_top.getDateoftransformation(), pub_merged.getDateoftransformation());
assertEquals(pub_top.getOaiprovenance(), pub_merged.getOaiprovenance());
assertEquals(pub_top.getDateofcollection(), pub_merged.getDateofcollection());
// assertEquals(pub_top.getDateofcollection(), pub_merged.getDateofcollection());
assertEquals(3, pub_merged.getInstance().size());
assertEquals(2, pub_merged.getCountry().size());
assertEquals(0, pub_merged.getSubject().size());

View File

@ -49,7 +49,7 @@
},
{
"field": "country",
"comparator": "exactMatch",
"comparator": "countryMatch",
"weight": 1,
"countIfUndefined": "true",
"params": {}

File diff suppressed because one or more lines are too long

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

@ -172,7 +172,7 @@ public class SparkBulkTagJob {
.option("compression", "gzip")
.json(outputPath + "project");
readPath(spark, outputPath + "project", Datasource.class)
readPath(spark, outputPath + "project", Project.class)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")

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

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