diff options
-rw-r--r-- | python/fatcat_tools/importers/datacite.py | 16 | ||||
-rw-r--r-- | python/tests/files/datacite/datacite_doc_33.json | 62 | ||||
-rw-r--r-- | python/tests/files/datacite/datacite_result_05.json | 3 | ||||
-rw-r--r-- | python/tests/files/datacite/datacite_result_08.json | 7 | ||||
-rw-r--r-- | python/tests/files/datacite/datacite_result_33.json | 31 | ||||
-rw-r--r-- | python/tests/import_datacite.py | 2 |
6 files changed, 110 insertions, 11 deletions
diff --git a/python/fatcat_tools/importers/datacite.py b/python/fatcat_tools/importers/datacite.py index 434a2941..66ec2023 100644 --- a/python/fatcat_tools/importers/datacite.py +++ b/python/fatcat_tools/importers/datacite.py @@ -298,6 +298,9 @@ class DataciteImporter(EntityImporter): contribs = self.parse_datacite_creators(creators, doi=doi) + self.parse_datacite_creators(contributors, role=None, set_index=False, doi=doi) + # Address duplicated author names; use raw_name string comparison; refs #59. + contribs = unique_contributors(contribs) + # Title, may come with "attributes.titles[].titleType", like # "AlternativeTitle", "Other", "Subtitle", "TranslatedTitle" titles = attributes.get('titles', []) or [] @@ -823,6 +826,19 @@ class DataciteImporter(EntityImporter): return contribs +def unique_contributors(contribs): + """ + Given a list of ReleaseContrib items, return a list of unique + ReleaseContribs, refs GH #59. + """ + unique_names, unique_contribs = set(), [] + for rc in contribs: + if rc.raw_name and rc.raw_name in unique_names: + continue + unique_names.add(rc.raw_name) + unique_contribs.append(rc) + return unique_contribs + def lookup_license_slug(raw): """ Resolve a variety of strings into a some pseudo-canonical form, e.g. diff --git a/python/tests/files/datacite/datacite_doc_33.json b/python/tests/files/datacite/datacite_doc_33.json new file mode 100644 index 00000000..571d1220 --- /dev/null +++ b/python/tests/files/datacite/datacite_doc_33.json @@ -0,0 +1,62 @@ +{ + "id": "10.17912/micropub.biology.000143", + "type": "dois", + "attributes": { + "doi": "10.17912/micropub.biology.000143", + "identifiers": null, + "creators": [ + { + "name": "ABC News", + "givenName": "", + "familyName": "", + "affiliation": [], + "role": "author" + } + ], + "titles": [ + { + "title": "Sample" + } + ], + "publisher": "microPublication Biology", + "publicationYear": 2019, + "types": { + "resourceTypeGeneral": "DataPaper" + }, + "relatedIdentifiers": [], + "sizes": [], + "formats": [], + "version": null, + "rightsList": [], + "descriptions": [ + { + "description": 1234567890, + "descriptionType": "Abstract" + } + ], + "geoLocations": [], + "fundingReferences": [], + "url": "https://www.micropublication.org/journals/biology/micropub.biology.000143", + "created": "2019-08-19T14:43:08.000Z", + "registered": "2019-08-19T14:43:09.000Z", + "published": "2019", + "updated": "2019-11-09T12:32:02.000Z", + "contributors": [ + { + "name": "ABC News", + "givenName": "", + "familyName": "", + "affiliation": [], + "role": "" + } + ] + }, + "relationships": { + "client": { + "data": { + "id": "caltech.micropub", + "type": "clients" + } + } + } +} diff --git a/python/tests/files/datacite/datacite_result_05.json b/python/tests/files/datacite/datacite_result_05.json index 79c2a8fb..d634490d 100644 --- a/python/tests/files/datacite/datacite_result_05.json +++ b/python/tests/files/datacite/datacite_result_05.json @@ -505,9 +505,6 @@ "surname": "Wurzbacher" }, { - "raw_name": "Kessy Abarenkov" - }, - { "raw_name": "NHM UT-University Of Tartu; Natural History Museum And Botanic Garden" } ], diff --git a/python/tests/files/datacite/datacite_result_08.json b/python/tests/files/datacite/datacite_result_08.json index 70237280..5a46ef50 100644 --- a/python/tests/files/datacite/datacite_result_08.json +++ b/python/tests/files/datacite/datacite_result_08.json @@ -13,13 +13,6 @@ "raw_name": "Kei Kajisa", "role": "author", "surname": "Kajisa" - }, - { - "given_name": "Kei", - "index": 1, - "raw_name": "Kei Kajisa", - "role": "author", - "surname": "Kajisa" } ], "ext_ids": { diff --git a/python/tests/files/datacite/datacite_result_33.json b/python/tests/files/datacite/datacite_result_33.json new file mode 100644 index 00000000..bcb72469 --- /dev/null +++ b/python/tests/files/datacite/datacite_result_33.json @@ -0,0 +1,31 @@ +{ + "abstracts": [ + { + "content": "1234567890", + "mimetype": "text/plain" + } + ], + "contribs": [ + { + "given_name": "", + "surname": "", + "index": 0, + "raw_name": "ABC News", + "role": "author" + } + ], + "ext_ids": { + "doi": "10.17912/micropub.biology.000143" + }, + "extra": { + "datacite": { + "resourceTypeGeneral": "DataPaper" + }, + "container_name": "microPublication Biology" + }, + "refs": [], + "release_stage": "published", + "release_year": 2019, + "publisher": "microPublication Biology", + "title": "Sample" +} diff --git a/python/tests/import_datacite.py b/python/tests/import_datacite.py index 20c1eaf8..1472b8ea 100644 --- a/python/tests/import_datacite.py +++ b/python/tests/import_datacite.py @@ -288,7 +288,7 @@ def test_datacite_conversions(datacite_importer): for now. """ datacite_importer.debug = True - for i in range(33): + for i in range(34): src = 'tests/files/datacite/datacite_doc_{0:02d}.json'.format(i) dst = 'tests/files/datacite/datacite_result_{0:02d}.json'.format(i) with open(src, 'r') as f: |