From 7d55f030cadbdc213e0773a52ad52ccfbfa07cad Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 25 Jan 2019 16:42:28 -0800 Subject: update journal meta import/transform --- python/fatcat_import.py | 6 +- python/fatcat_tools/importers/journal_metadata.py | 143 +++++----------- python/fatcat_tools/transforms.py | 183 +++++++++++++++++---- python/tests/files/journal_extra_metadata.snip.csv | 10 -- python/tests/files/journal_metadata.sample.json | 20 +++ python/tests/import_journal_metadata.py | 18 +- 6 files changed, 226 insertions(+), 154 deletions(-) delete mode 100644 python/tests/files/journal_extra_metadata.snip.csv create mode 100644 python/tests/files/journal_metadata.sample.json (limited to 'python') diff --git a/python/fatcat_import.py b/python/fatcat_import.py index a47aa175..8d952067 100755 --- a/python/fatcat_import.py +++ b/python/fatcat_import.py @@ -24,7 +24,7 @@ def run_orcid(args): def run_journal_metadata(args): fii = JournalMetadataImporter(args.api, edit_batch_size=args.batch_size) - CsvLinePusher(fii, args.csv_file).run() + JsonLinePusher(fii, args.json_file).run() def run_matched(args): fmi = MatchedImporter(args.api, @@ -93,8 +93,8 @@ def main(): func=run_journal_metadata, auth_var="FATCAT_AUTH_WORKER_JOURNAL_METADATA", ) - sub_journal_metadata.add_argument('csv_file', - help="Journal ISSN CSV metadata file to import from (or stdin)", + sub_journal_metadata.add_argument('json_file', + help="Journal JSON metadata file to import from (or stdin)", default=sys.stdin, type=argparse.FileType('r')) sub_journal_metadata.add_argument('--batch-size', help="size of batch to send", diff --git a/python/fatcat_tools/importers/journal_metadata.py b/python/fatcat_tools/importers/journal_metadata.py index cf3971b5..7f6b1ee8 100644 --- a/python/fatcat_tools/importers/journal_metadata.py +++ b/python/fatcat_tools/importers/journal_metadata.py @@ -28,90 +28,9 @@ def truthy(s): class JournalMetadataImporter(EntityImporter): """ Imports journal metadata ("containers") by ISSN, currently from a custom - (data munged) .csv file format - - CSV format (generated from git.archive.org/webgroup/oa-journal-analysis): - - ISSN-L,in_doaj,in_road,in_norwegian,in_crossref,title,publisher,url,lang,ISSN-print,ISSN-electronic,doi_count,has_doi,is_oa,is_kept,publisher_size,url_live,url_live_status,url_live_final_status,url_live_final_url,url_live_status_simple,url_live_final_status_simple,url_domain,gwb_pdf_count - - - 'extra' fields: - - doaj - as_of: datetime of most recent check; if not set, not actually in DOAJ - seal: bool - work_level: bool (are work-level publications deposited with DOAJ?) - archiving: array, can include 'library' or 'other' - road - as_of: datetime of most recent check; if not set, not actually in ROAD - pubmed (TODO: delete?) - as_of: datetime of most recent check; if not set, not actually indexed in pubmed - norwegian (TODO: drop this?) - as_of: datetime of most recent check; if not set, not actually indexed in pubmed - id (integer) - level (integer; 0-2) - kbart - lockss - year_rle - volume_rle - portico - ... - clockss - ... - sherpa_romeo - color - jstor - year_rle - volume_rle - scopus - id - TODO: print/electronic distinction? - wos - id - doi - crossref_doi: DOI of the title in crossref (if exists) - prefixes: array of strings (DOI prefixes, up to the '/'; any registrar, not just Crossref) - ia - sim - nap_id - year_rle - volume_rle - longtail: boolean - homepage - as_of: datetime of last attempt - url - status: HTTP/heritrix status of homepage crawl - - issnp: string - issne: string - coden: string - abbrev: string - oclc_id: string (TODO: lookup?) - lccn_id: string (TODO: lookup?) - dblb_id: string - default_license: slug - original_name: native name (if name is translated) - platform: hosting platform: OJS, wordpress, scielo, etc - mimetypes: array of strings (eg, 'application/pdf', 'text/html') - first_year: year (integer) - last_year: if publishing has stopped - primary_language: single ISO code, or 'mixed' - languages: array of ISO codes - region: TODO: continent/world-region - nation: shortcode of nation - discipline: TODO: highest-level subject; "life science", "humanities", etc - field: TODO: narrower description of field - subjects: TODO? - url: homepage - is_oa: boolean. If true, can assume all releases under this container are "Open Access" - TODO: domains, if exclusive? - TODO: fulltext_regex, if a known pattern? - - For KBART, etc: - We "over-count" on the assumption that "in-progress" status works will soon actually be preserved. - year and volume spans are run-length-encoded arrays, using integers: - - if an integer, means that year is preserved - - if an array of length 2, means everything between the two numbers (inclusive) is preserved + munged JSON format (see ../extra/journal_metadata/). + + See guide for details on the many 'extra' fields used here. """ def __init__(self, api, **kwargs): @@ -125,34 +44,50 @@ class JournalMetadataImporter(EntityImporter): editgroup_extra=eg_extra) def want(self, raw_record): - if raw_record.get('ISSN-L'): + if raw_record.get('issnl'): return True return False def parse_record(self, row): """ - row is a python dict (parsed from CSV). + row is a python dict (parsed from JSON). + returns a ContainerEntity (or None if invalid or couldn't parse) """ - title = or_none(row['title']) - issnl = or_none(row['ISSN-L']) - if title is None or issnl is None: - return None - extra = dict( - in_doaj=truthy(row['in_doaj']), - in_road=truthy(row['in_road']), - in_norwegian=truthy(row['in_norwegian']), - language=or_none(row['lang']), - url=or_none(row['url']), - ISSNp=or_none(row['ISSN-print']), - ISSNe=or_none(row['ISSN-electronic']), - is_oa=truthy(row['is_oa']), - is_kept=truthy(row['is_kept']), - ) + + extra = dict() + for key in ('issne', 'issnp', 'languages', 'country', 'urls', 'abbrev', + 'coden', 'aliases', 'original_name', 'first_year', 'last_year', + 'platform', 'default_license', 'road', 'mimetypes', + 'sherpa_romeo', 'kbart'): + if row.get(key): + extra[key] = row[key] + # TODO: not including for now: norwegian, dois/crossref, ia + + extra_doaj = dict() + if row.get('doaj'): + if row['doaj'].get('as_of'): + extra_doaj['as_of'] = row['doaj']['as_of'] + if row['doaj'].get('works'): + extra_doaj['works'] = row['doaj']['works'] + if extra_doaj: + extra['doaj'] = extra_doaj + + extra_ia = dict() + # TODO: would like an ia.longtail_ia flag + if row.get('sim'): + extra_ia['sim'] = { + 'year_spans': row['sim']['year_spans'], + } + if extra_ia: + extra['ia'] = extra_ia + ce = fatcat_client.ContainerEntity( - issnl=issnl, - name=clean(title), - publisher=or_none(clean(row['publisher'])), + issnl=row['issnl'], + container_type=None, # TODO + name=clean(row.get('name')), + publisher=clean(row.get('publisher')), + wikidata_qid=None, # TODO extra=extra) return ce diff --git a/python/fatcat_tools/transforms.py b/python/fatcat_tools/transforms.py index 2493b1ab..a85c877c 100644 --- a/python/fatcat_tools/transforms.py +++ b/python/fatcat_tools/transforms.py @@ -19,7 +19,22 @@ def entity_from_json(json_str, entity_type): thing.data = json_str return ac.deserialize(thing, entity_type) -def release_to_elasticsearch(release): +def check_kbart(year, archive): + if not archive or not archive.get('year_spans'): + return None + for span in archive['year_spans']: + if year >= span[0] and year <= span[1]: + return True + return False + +def test_check_kbart(): + + assert check_kbart(1990, dict(year_spans=[[2000, 2000]])) == False + assert check_kbart(2000, dict(year_spans=[[2000, 2000]])) == True + assert check_kbart(1950, dict(year_spans=[[1900, 1920], [1990, 2000]])) == False + assert check_kbart(1950, dict(year_spans=[[1900, 1920], [1930, 2000]])) == True + +def release_to_elasticsearch(entity): """ Converts from an entity model/schema to elasticsearch oriented schema. @@ -27,15 +42,16 @@ def release_to_elasticsearch(release): Raises exception on error (never returns None) """ - if release.state in ('redirect', 'deleted'): + if entity.state in ('redirect', 'deleted'): return dict( - ident = release.ident, - state = release.state, + ident = entity.ident, + state = entity.state, ) - elif release.state != 'active': - raise ValueError("Unhandled release state: {}".format(release.state)) + elif entity.state != 'active': + raise ValueError("Unhandled entity state: {}".format(entity.state)) # First, the easy ones (direct copy) + release = entity t = dict( ident = release.ident, state = release.state, @@ -57,11 +73,14 @@ def release_to_elasticsearch(release): ) is_oa = None + is_preserved = None is_longtail_oa = None in_kbart = None + in_jstor = False in_web = False in_dweb = False in_ia = False + in_ia_sim = False in_shadow = False if release.release_date: @@ -88,19 +107,35 @@ def release_to_elasticsearch(release): t['container_issnl'] = container.issnl t['container_type'] = container.container_type if container.extra: - if container.extra.get('is_oa') or container.extra.get('in_doaj'): + c_extra = container.extra + if c_extra.get('kbart') and release.year: + in_jstor = check_kbart(release.year, c_extra['kbart'].get('jstor')) + in_kbart = in_jstor + for archive in ('portico', 'lockss', 'clockss'): + in_kbart = in_kbart or check_kbart(release.year, c_extra['kbart'].get(archive)) + + if c_extra.get('ia'): + if c_extra['ia'].get('sim') and release.year: + in_ia_sim = check_kbart(release, c_extra['ia']['sim'].get('year_spans')) + if c_extra['ia'].get('longtail_oa'): + is_longtail_oa = True + if c_extra.get('sherpa_romeo'): + if c_extra['sherpa_romeo'].get('color') == 'white': + is_oa = False + if c_extra.get('default_license') and c_extra.get('default_license').startswith('CC-'): is_oa = True - if container.extra.get('in_kbart'): - # TODO: better KBART check goes here - in_kbart = True - if container.extra.get('ia'): - # TODO: container longtail check goes here - # TODO: sim/microfilm check goes here - pass - # TODO: SHERPA/Romeo goes here + if c_extra.get('doaj'): + if c_extra['doaj'].get('as_of'): + is_oa = True + if c_extra.get('road'): + if c_extra['road'].get('as_of'): + is_oa = True else: t['publisher'] = release.publisher + if release.jstor_id or (release.doi and release.doi.startswith('10.2307/')): + in_jstor = True + files = release.files or [] t['file_count'] = len(files) t['fileset_count'] = len(release.filesets or []) @@ -118,13 +153,15 @@ def release_to_elasticsearch(release): if url.url.lower().startswith('http'): in_web = True if url.rel in ('dweb', 'p2p', 'ipfs', 'dat', 'torrent'): - # TODO: not sure what rel will be + # not sure what rel will be for this stuff in_dweb = True if is_pdf: any_pdf_url = url.url if is_pdf and url.rel in ('webarchive', 'repository') and is_pdf: is_preserved = True good_pdf_url = url.url + if '//www.jstor.org/' in url.url: + in_jstor = True if '//web.archive.org/' in url.url or '//archive.org/' in url.url: in_ia = True if is_pdf: @@ -141,18 +178,15 @@ def release_to_elasticsearch(release): extra = release.extra or dict() if extra: - # TODO: longtail OA check from GROBID here - if extra.get('in_kbart'): - # NOTE: not actually setting this anywhere - in_kbart = True if extra.get('is_oa'): - # NOTE: not actually setting this anywhere + # NOTE: not actually setting this anywhere... but could is_oa = True - if extra.get('grobid'): - if not t.get('container_name'): - t['container_name'] = extra['grobid'].get('container_name') - if extra['grobid'].get('longtail_oa'): - is_longtail_oa = True + if extra.get('longtail_oa'): + # sometimes set by GROBID/matcher + is_oa = True + is_longtail_oa = True + if not t.get('container_name'): + t['container_name'] = extra.get('container_name') if extra.get('crossref'): if extra['crossref'].get('archive'): # all crossref archives are KBART, I believe @@ -163,8 +197,101 @@ def release_to_elasticsearch(release): t['is_oa'] = is_oa t['is_longtail_oa'] = is_longtail_oa t['in_kbart'] = in_kbart + t['in_jstor'] = in_jstor t['in_web'] = in_web t['in_dweb'] = in_dweb - t['in_ia'] = in_ia - t['is_preserved'] = in_ia or in_kbart + t['in_ia'] = bool(in_ia) + t['is_preserved'] = bool(is_preserved or in_ia or in_kbart or in_jstor) + return t + +def container_to_elasticsearch(entity): + """ + Converts from an entity model/schema to elasticsearch oriented schema. + + Returns: dict + Raises exception on error (never returns None) + """ + + if entity.state in ('redirect', 'deleted'): + return dict( + ident = entity.ident, + state = entity.state, + ) + elif entity.state != 'active': + raise ValueError("Unhandled entity state: {}".format(entity.state)) + + # First, the easy ones (direct copy) + t = dict( + ident = entity.ident, + state = entity.state, + revision = entity.revision, + + name = entity.name, + publisher = entity.publisher, + container_type = entity.container_type, + issnl = entity.issnl, + wikidata_qid = entity.wikidata_qid, + + entity_status = entity.entity_status, + language = entity.language, + license = entity.license_slug, + doi = entity.doi, + pmid = entity.pmid, + isbn13 = entity.isbn13, + core_id = entity.core_id, + arxiv_id = entity.core_id, + jstor_id = entity.jstor_id, + ) + + # TODO: region, discipline + # TODO: single primary language? + for key in ('country', 'languages', 'mimetypes', 'first_year', 'last_year'): + if entity.extra.get(key): + t[key] = entity.extra[key] + + in_doaj = None + in_road = None + # TODO: not currently implemented + in_doi = None + # TODO: would be nice to have 'in_doaj_works', or maybe just "any_pid" + #in_doaj_works = None + in_sherpa_romeo = None + is_oa = None + # TODO: not actually set/stored anywhere? + is_longtail_oa = None + any_kbart = None + any_jstor = None + any_ia_sim = None + + extra = entity.extra + if extra.get('doaj'): + if extra['doaj'].get('as_of'): + in_doaj = True + if extra.get('road'): + if extra['road'].get('as_of'): + in_road = True + if extra.get('default_license'): + if extra['default_license'].startswith('CC-'): + is_oa = True + if extra.get('sherpa_romeo'): + in_sherpa_romeo = True + if extra['sherpa_romeo'].get('color') == 'white': + is_oa = False + if extra.get('kbart'): + any_kbart = True + if extra['kbart'].get('jstor'): + any_jstor = True + if extra.get('ia'): + if extra['ia'].get('sim'): + any_ia_sim = True + + t['in_doaj'] = is_doaj + t['in_road'] = is_road + t['in_doi'] = in_doi + t['in_sherpa_romeo'] = in_sherpa_romeo + t['is_oa'] = in_doaj or in_road or is_longtail_oa or ia_oa + t['is_longtail_oa'] = is_longtail_oa + t['any_kbart'] = any_ia_sim + t['any_jstor'] = any_ia_sim + t['any_ia_sim'] = bool(any_ia_sim) return t diff --git a/python/tests/files/journal_extra_metadata.snip.csv b/python/tests/files/journal_extra_metadata.snip.csv deleted file mode 100644 index 8cc50ee9..00000000 --- a/python/tests/files/journal_extra_metadata.snip.csv +++ /dev/null @@ -1,10 +0,0 @@ -ISSN-L,in_doaj,in_road,in_norwegian,in_crossref,title,publisher,url,lang,ISSN-print,ISSN-electronic,doi_count,has_doi,is_oa,is_kept,publisher_size,url_live,url_live_status,url_live_final_status,url_live_final_url,url_live_status_simple,url_live_final_status_simple,url_domain,gwb_pdf_count -0000-0019,False,False,True,False,Publishers weekly,,http://www.publishersweekly.com/,,0000-0019,2150-4008,0.0,False,False,False,,http://www.publishersweekly.com/,301.0,200.0,https://www.publishersweekly.com/,3xx,200,publishersweekly.com,1055.0 -0001-0782,False,False,True,True,Communications of the ACM,Association for Computing Machinery,http://www.acm.org/pubs/cacm/,,0001-0782,1557-7317,11894.0,True,False,True,55.0,http://www.acm.org/pubs/cacm/,301.0,200.0,https://cacm.acm.org/,3xx,200,acm.org,9.0 -0001-1452,False,False,True,True,AIAA Journal,American Institute of Aeronautics and Astronautics,http://www.aiaa.org/content.cfm?pageid=322&lupubid=2,,0001-1452,1533-385X,24193.0,True,False,True,6.0,http://www.aiaa.org/content.cfm?pageid=322&lupubid=2,404.0,404.0,http://www.aiaa.org/content.cfm?pageid=322&lupubid=2,404,404,aiaa.org,16.0 -0001-1541,False,False,True,True,AIChE Journal,Wiley Blackwell (John Wiley & Sons),http://www.aiche.org/Publications/AIChEJournal/index.aspx,,0001-1541,1547-5905,15860.0,True,False,True,607.0,http://www.aiche.org/Publications/AIChEJournal/index.aspx,301.0,200.0,https://www.aiche.org/publications/journals/aiche-journal,3xx,200,aiche.org,25.0 -0001-2092,False,False,True,True,AORN Journal,Wiley Blackwell (John Wiley & Sons),http://www.aorn.org/AORNJournal/,,0001-2092,1878-0369,12413.0,True,False,True,607.0,http://www.aorn.org/AORNJournal/,301.0,200.0,https://www.aorn.org/aorn-journal,3xx,200,aorn.org,0.0 -0001-2343,False,False,True,True,Archiv fuer Rechts- und Sozialphilosphie,Franz Steiner Verlag GmbH,http://www.steiner-verlag.de/programm/zeitschriften/archiv-fuer-rechts-und-sozialphilosophie/,,0001-2343,2363-5614,14.0,True,False,False,2.0,http://www.steiner-verlag.de/programm/zeitschriften/archiv-fuer-rechts-und-sozialphilosophie/,200.0,200.0,http://www.steiner-verlag.de/programm/zeitschriften/archiv-fuer-rechts-und-sozialphilosophie/,200,200,steiner-verlag.de,226.0 -0001-2351,False,False,True,True,Transactions of the ASAE,American Society of Agricultural and Biological Engineers,,,0001-2351,2151-0059,11515.0,True,False,True,3.0,,,,,,,,0.0 -0001-2491,False,False,True,False,ASHRAE Journal,,http://www.ashrae.org/,,0001-2491,1943-6637,0.0,False,False,False,,http://www.ashrae.org/,301.0,200.0,https://www.ashrae.org/,3xx,200,ashrae.org,684.0 -0001-2505,False,False,True,False,ASHRAE Transactions,,http://www.ashrae.org/template/AssetDetail/assetid/25903,,0001-2505,,0.0,False,False,False,,http://www.ashrae.org/template/AssetDetail/assetid/25903,301.0,404.0,https://www.ashrae.org/template/AssetDetail/assetid/25903,3xx,404,ashrae.org,684.0 diff --git a/python/tests/files/journal_metadata.sample.json b/python/tests/files/journal_metadata.sample.json new file mode 100644 index 00000000..56df2ea1 --- /dev/null +++ b/python/tests/files/journal_metadata.sample.json @@ -0,0 +1,20 @@ +{"publisher": "Peter Lang International Academic Publishers", "sherpa_romeo": {"color": "yellow"}, "name": "Monographs in Linguistics and the Philosophy of Language", "issnp": "1056-5019", "issnl": "1056-5019"} +{"ia": {"homepage_url": "http://arjournals.annualreviews.org/loi/pharmtox", "homepage_status": -1}, "issnp": "0362-1642", "issne": "1545-4304", "urls": ["http://arjournals.annualreviews.org/loi/pharmtox"], "publisher": "Annual Reviews", "kbart": {"portico": {"year_spans": [[2011, 2017]]}}, "country": "us", "abbrev": "Annu. Rev. Pharmacol. Toxicol.", "crossref": {"any": true, "doi": "10.1146/pharmtox.711"}, "languages": ["en"], "issnl": "0362-1642", "name": "Annual Review of Pharmacology and Toxicology", "sherpa_romeo": {"color": "yellow"}, "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 437839}, "sim": {"last_year": 2009, "id": "5091", "year_spans": [[1961, 2009]], "first_year": 1961}} +{"name": "The international journal of applied radiation and isotopes", "issnp": "0020-708X", "issne": "1878-1284", "publisher": "Elsevier", "kbart": {"clockss": {"year_spans": [[1957, 1985]]}, "portico": {"year_spans": [[1956, 1985]]}}, "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 447572}, "abbrev": "Int J Appl Radiat Isot", "crossref": {"any": true}, "issnl": "0020-708X"} +{"issnp": "2449-8920", "issne": "2449-8939", "road": {"as_of": "2018-01-24"}, "languages": ["en"], "publisher": "Uniwersytet Jagiellonski \u2013 Wydawnictwo Uniwersytetu Jagiellonskiego", "country": "pl", "urls": ["http://www.ejournals.eu/ijcm/", "http://www.ejournals.eu/ijcm"], "crossref": {"any": true}, "issnl": "2449-8920", "name": "International Journal of Contemporary Management", "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 488900}, "ia": {"homepage_url": "http://www.ejournals.eu/ijcm", "homepage_status": 200}} +{"issnp": "1976-1317", "default_license": "CC-BY-NC-ND", "road": {"as_of": "2018-01-24"}, "doaj": {"as_of": "2019-01-24", "seal": false, "archive": ["national-library"]}, "languages": ["en"], "publisher": "Elsevier", "kbart": {"clockss": {"year_spans": [[2007, 2018]]}, "portico": {"year_spans": [[2007, 2018]]}}, "country": "kr", "urls": ["http://www.journals.elsevier.com/asian-nursing-research", "http://www.asian-nursingresearch.com"], "crossref": {"any": true}, "issnl": "1976-1317", "abbrev": "Asian Nurs Res (Korean Soc Nurs Sci)", "name": "Asian Nursing Research", "sherpa_romeo": {"color": "green"}, "ia": {"homepage_url": "https://www.journals.elsevier.com/asian-nursing-research", "homepage_status": 200}, "issne": "2093-7482"} +{"name": "Research on Managing Groups and Teams", "issnp": "1534-0856", "languages": ["en"], "ia": {"homepage_url": "http://www.emeraldinsight.com/series/rmgt", "homepage_status": -1}, "country": "us", "urls": ["http://www.emeraldinsight.com/series/rmgt"], "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 484721}, "issnl": "1534-0856"} +{"name": "Asian Journal of Medical Sciences", "issne": "2091-0576", "road": {"as_of": "2018-01-24"}, "languages": ["en"], "publisher": "Manipal Colleges of Medical Sciences", "ia": {"homepage_url": "https://www.nepjol.info/index.php/AJMS", "homepage_status": 200}, "country": "np", "urls": ["http://www.nepjol.info/index.php/AJMS/about", "http://www.nepjol.info/index.php/AJMS"], "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 478318}, "issnl": "2091-0576"} +{"name": "ATZproduktion", "issnp": "1865-4908", "issne": "2192-8886", "publisher": "Springer Fachmedien Wiesbaden GmbH", "crossref": {"any": true}, "issnl": "1865-4908"} +{"publisher": "Boom Uitgevers Den Haag", "name": "StAB", "issnp": "1573-806X", "crossref": {"any": true}, "issnl": "1573-806X"} +{"publisher": "University of Victoria", "sherpa_romeo": {"color": "blue"}, "name": "Musicological Explorations", "issnp": "1711-9235", "issnl": "1711-9235"} +{"publisher": "Transstellar Journal Publications and Research Consultancy Private Limited", "name": "International Journal of Robotics Research and Development", "issnp": "2250-1592", "crossref": {"any": true}, "issnl": "2250-1592"} +{"name": "BioProcess international", "issnp": "1542-6319", "abbrev": "Bioprocess Int", "issne": "1945-7065", "issnl": "1542-6319"} +{"name": "Journal of the American Podiatry Association", "issnp": "0003-0538", "abbrev": "J Am Podiatry Assoc", "issnl": "0003-0538"} +{"publisher": "Masson Editeur", "name": "Bulletin de la Societe francaise de dermatologie et de syphiligraphie", "languages": ["en"], "sim": {"last_year": 1972, "id": "3407", "year_spans": [[1890, 1941], [1968, 1972]], "gaps": [1942, 1943, 1944, 1945, 1946, 1947, 1948, 1949, 1950, 1951, 1952, 1953, 1954, 1955, 1956, 1957, 1958, 1959, 1960, 1961, 1962, 1963, 1964, 1965, 1966, 1967], "first_year": 1890}, "issnl": "0049-1071"} +{"name": "International journal of innovative and applied research", "urls": ["http://www.journalijiar.com"], "ia": {"homepage_url": "http://www.journalijiar.com/", "homepage_status": 200}, "road": {"as_of": "2018-01-24"}, "issnl": "2348-0319"} +{"issnp": "1025-6415", "issne": "1025-6415", "road": {"as_of": "2018-01-24"}, "languages": ["ru"], "publisher": "Natsional'na Akademiya Nauk Ukrainy", "abbrev": "Dopov Natsionalnoi Akad Nauk Ukr Matemat Pryrodoznavstvo Tekhnichni Nauky", "country": "ua", "urls": ["http://www.nbuv.gov.ua/portal/all/reports/index.html", "http://dopovidi-nanu.org.ua/"], "crossref": {"any": true, "doi": "10.15407/dopovidi"}, "issnl": "1025-6415", "name": "Natsional'na Akademiya Nauk Ukrainy. Dopovidi: naukovyi zhurnal", "norwegian": {"level": 1, "as_of": "2018-03-02", "id": 477246}, "ia": {"homepage_url": "http://dopovidi-nanu.org.ua/", "homepage_status": 200}} +{"publisher": "International Bee Research Association", "name": "Journal of ApiProduct and ApiMedical Science", "crossref": {"any": true, "doi": "10.3896/IBRA.4"}, "issne": "1759-7986", "issnl": "1759-7986"} +{"publisher": "E3 Journals Ltd", "name": "E3 Journal of Agricultural Research and Development", "crossref": {"any": true, "doi": "10.18685/EJARD"}, "issne": "2276-9897", "issnl": "2276-9897"} +{"name": "Tung wu hsueh tsa chih : Dongwuxue zazhi", "issnp": "0250-3263", "abbrev": "Dongwuxue Zazhi", "issnl": "0250-3263"} +{"name": "Buca e\u011fitim fak\u00fcltesi dergisi (Online)", "urls": ["http://www.befjournal.com/index.php/dergi/index"], "ia": {"homepage_url": "http://www.befjournal.com/cgi-sys/suspendedpage.cgi", "homepage_status": 200}, "road": {"as_of": "2018-01-24"}, "issnl": "1302-5147"} diff --git a/python/tests/import_journal_metadata.py b/python/tests/import_journal_metadata.py index a2b10a65..cfeee517 100644 --- a/python/tests/import_journal_metadata.py +++ b/python/tests/import_journal_metadata.py @@ -1,6 +1,6 @@ import pytest -from fatcat_tools.importers import JournalMetadataImporter, CsvPusher +from fatcat_tools.importers import JournalMetadataImporter, JsonLinePusher from fixtures import api @@ -10,15 +10,15 @@ def journal_metadata_importer(api): # TODO: use API to check that entities actually created... def test_journal_metadata_importer_batch(journal_metadata_importer): - with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f: - CsvPusher(journal_metadata_importer, f).run() + with open('tests/files/journal_metadata.sample.json', 'r') as f: + JsonLinePusher(journal_metadata_importer, f).run() def test_journal_metadata_importer(journal_metadata_importer): last_index = journal_metadata_importer.api.get_changelog(limit=1)[0].index - with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f: + with open('tests/files/journal_metadata.sample.json', 'r') as f: journal_metadata_importer.bezerk_mode = True - counts = CsvPusher(journal_metadata_importer, f).run() - assert counts['insert'] == 9 + counts = JsonLinePusher(journal_metadata_importer, f).run() + assert counts['insert'] == 20 assert counts['exists'] == 0 assert counts['skip'] == 0 @@ -30,10 +30,10 @@ def test_journal_metadata_importer(journal_metadata_importer): assert eg.extra['git_rev'] assert "fatcat_tools.JournalMetadataImporter" in eg.extra['agent'] - with open('tests/files/journal_extra_metadata.snip.csv', 'r') as f: + with open('tests/files/journal_metadata.sample.json', 'r') as f: journal_metadata_importer.reset() journal_metadata_importer.bezerk_mode = False - counts = CsvPusher(journal_metadata_importer, f).run() + counts = JsonLinePusher(journal_metadata_importer, f).run() assert counts['insert'] == 0 - assert counts['exists'] == 9 + assert counts['exists'] == 20 assert counts['skip'] == 0 -- cgit v1.2.3