From e0baeade7924019c5bbd27d9a7c116a1e26854fc Mon Sep 17 00:00:00 2001 From: Martin Czygan Date: Wed, 22 Apr 2020 22:25:36 +0200 Subject: datacite: fix type error Up to now, we expected the description to be a string or list. Add handling for int as well. First appeared: Apr 22 19:58:39. --- python/fatcat_tools/importers/datacite.py | 4 +- python/tests/files/datacite/datacite_doc_32.json | 53 ++++++++++++++++++++++ .../tests/files/datacite/datacite_result_32.json | 23 ++++++++++ python/tests/import_datacite.py | 2 +- 4 files changed, 80 insertions(+), 2 deletions(-) create mode 100644 python/tests/files/datacite/datacite_doc_32.json create mode 100644 python/tests/files/datacite/datacite_result_32.json diff --git a/python/fatcat_tools/importers/datacite.py b/python/fatcat_tools/importers/datacite.py index 244984f5..d998f266 100644 --- a/python/fatcat_tools/importers/datacite.py +++ b/python/fatcat_tools/importers/datacite.py @@ -496,10 +496,12 @@ class DataciteImporter(EntityImporter): if not desc.get('descriptionType') == 'Abstract': continue - # Description maybe a string or list. + # Description maybe a string, int or list. text = desc.get('description', '') if not text: continue + if isinstance(text, int): + text = '{}'.format(text) if isinstance(text, list): try: text = "\n".join(text) diff --git a/python/tests/files/datacite/datacite_doc_32.json b/python/tests/files/datacite/datacite_doc_32.json new file mode 100644 index 00000000..7ea7e873 --- /dev/null +++ b/python/tests/files/datacite/datacite_doc_32.json @@ -0,0 +1,53 @@ +{ + "id": "10.17912/micropub.biology.000143", + "type": "dois", + "attributes": { + "doi": "10.17912/micropub.biology.000143", + "identifiers": null, + "creators": [ + { + "raw_name": " ", + "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" + }, + "relationships": { + "client": { + "data": { + "id": "caltech.micropub", + "type": "clients" + } + } + } +} diff --git a/python/tests/files/datacite/datacite_result_32.json b/python/tests/files/datacite/datacite_result_32.json new file mode 100644 index 00000000..1a84a043 --- /dev/null +++ b/python/tests/files/datacite/datacite_result_32.json @@ -0,0 +1,23 @@ +{ + "abstracts": [ + { + "content": "1234567890", + "mimetype": "text/plain" + } + ], + "contribs": [], + "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 7fdd8230..c9210ea4 100644 --- a/python/tests/import_datacite.py +++ b/python/tests/import_datacite.py @@ -287,7 +287,7 @@ def test_datacite_conversions(datacite_importer): for now. """ datacite_importer.debug = True - for i in range(32): + for i in range(33): 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: -- cgit v1.2.3