summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/crossref.py
blob: 4a0322e7f4488e0a444c6ff87854fd03b99fa0fa (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388

import sys
import json
import sqlite3
import datetime
import itertools
import subprocess
import fatcat_client
from .common import EntityImporter, clean


# The docs/guide should be the cannonical home for these mappings; update there
# first
CROSSREF_TYPE_MAP = {
    'book': 'book',
    'book-chapter': 'chapter',
    'book-part': 'chapter',
    'book-section': 'chapter',
    'component': None,
    'dataset': 'dataset',
    'dissertation': 'thesis',
    'edited-book': 'book',
    'journal-article': 'article-journal',
    'monograph': 'book',
    'other': None,
    'peer-review': 'peer_review',
    'posted-content': 'post',
    'proceedings-article': 'paper-conference',
    'reference-book': 'book',
    'reference-entry': 'entry',
    'report': 'report',
    'standard': 'standard',
}

CONTAINER_TYPE_MAP = {
    'article-journal': 'journal',
    'paper-conference': 'conference',
    'book': 'book-series',
}

# TODO:
LICENSE_SLUG_MAP = {
    "http://creativecommons.org/licenses/by/3.0/": "CC-BY",
    "http://creativecommons.org/licenses/by/4.0/": "CC-BY",
    "http://creativecommons.org/licenses/by-sa/3.0/": "CC-BY-SA",
    "http://creativecommons.org/licenses/by-sa/4.0/": "CC-BY-SA",
    "http://creativecommons.org/licenses/by-nd/3.0/": "CC-BY-ND",
    "http://creativecommons.org/licenses/by-nd/4.0/": "CC-BY-ND",
    "http://creativecommons.org/licenses/by-nc/3.0/": "CC-BY-NC",
    "http://creativecommons.org/licenses/by-nc/4.0/": "CC-BY-NC",
    "http://creativecommons.org/licenses/by-nc-sa/3.0/": "CC-BY-NC-SA",
    "http://creativecommons.org/licenses/by-nc-sa/4.0/": "CC-BY-NC-SA",
    "http://creativecommons.org/licenses/by-nc-nd/3.0/": "CC-BY-NC-ND",
    "http://creativecommons.org/licenses/by-nc-nd/4.0/": "CC-BY-NC-ND",
    "http://www.elsevier.com/open-access/userlicense/1.0/": "ELSEVIER-USER-1.0",
    # http://onlinelibrary.wiley.com/termsAndConditions doesn't seem like a license
    # http://www.springer.com/tdm doesn't seem like a license
}

class CrossrefImporter(EntityImporter):
    """
    Importer for Crossref metadata.

    Can use a local sqlite3 file for faster "external identifier" lookups

    See https://github.com/CrossRef/rest-api-doc for JSON schema notes
    """

    def __init__(self, api, issn_map_file, **kwargs):

        eg_desc = kwargs.get('editgroup_description',
            "Automated import of Crossref DOI metadata, harvested from REST API")
        eg_extra = kwargs.get('editgroup_extra', dict())
        eg_extra['agent'] = eg_extra.get('agent', 'fatcat_tools.CrossrefImporter')
        super().__init__(api,
            issn_map_file=issn_map_file,
            editgroup_description=eg_desc,
            editgroup_extra=eg_extra)

        self.create_containers = kwargs.get('create_containers')
        extid_map_file = kwargs.get('extid_map_file')
        self.extid_map_db = None
        if extid_map_file:
            db_uri = "file:{}?mode=ro".format(extid_map_file)
            print("Using external ID map: {}".format(db_uri))
            self.extid_map_db = sqlite3.connect(db_uri, uri=True)
        else:
            print("Not using external ID map")

        self.read_issn_map_file(issn_map_file)

    def lookup_ext_ids(self, doi):
        if self.extid_map_db is None:
            return dict(core_id=None, pmid=None, pmcid=None, wikidata_qid=None, arxiv_id=None, jstor_id=None)
        row = self.extid_map_db.execute("SELECT core, pmid, pmcid, wikidata FROM ids WHERE doi=? LIMIT 1",
            [doi.lower()]).fetchone()
        if row is None:
            return dict(core_id=None, pmid=None, pmcid=None, wikidata_qid=None, arxiv_id=None, jstor_id=None)
        row = [str(cell or '') or None for cell in row]
        return dict(
            core_id=row[0],
            pmid=row[1],
            pmcid=row[2],
            wikidata_qid=row[3],
            # TODO:
            arxiv_id=None,
            jstor_id=None,
        )

    def map_release_type(self, crossref_type):
        return CROSSREF_TYPE_MAP.get(crossref_type)

    def map_container_type(self, crossref_type):
        return CONTAINER_TYPE_MAP.get(crossref_type)

    def want(self, obj):
        if not obj.get('title'):
            return False

        # do most of these checks in-line below
        return True

    def parse_record(self, obj):
        """
        obj is a python dict (parsed from json).
        returns a ReleaseEntity
        """

        # Ways to be out of scope (provisionally)
        # journal-issue and journal-volume map to None, but allowed for now
        if obj.get('type') in (None, 'journal', 'proceedings',
                'standard-series', 'report-series', 'book-series', 'book-set',
                'book-track', 'proceedings-series'):
            return None

        # Do require the 'title' keys to exsit, as release entities do
        if (not 'title' in obj) or (not obj['title']):
            return None

        release_type = self.map_release_type(obj['type'])

        # contribs
        def do_contribs(obj_list, ctype):
            contribs = []
            for i, am in enumerate(obj_list):
                creator_id = None
                if 'ORCID' in am.keys():
                    creator_id = self.lookup_orcid(am['ORCID'].split('/')[-1])
                # Sorry humans :(
                if am.get('given') and am.get('family'):
                    raw_name = "{} {}".format(am['given'], am['family'])
                elif am.get('family'):
                    raw_name = am['family']
                else:
                    # TODO: defaults back to a pseudo-null value
                    raw_name = am.get('given', '<blank>')
                extra = dict()
                if ctype == "author":
                    index = i
                else:
                    index = None
                raw_affiliation = None
                if am.get('affiliation'):
                    if len(am.get('affiliation')) > 0:
                        raw_affiliation = am.get('affiliation')[0]['name']
                    if len(am.get('affiliation')) > 1:
                        # note: affiliation => more_affiliations
                        extra['more_affiliations'] = [clean(a['name']) for a in am.get('affiliation')[1:]]
                if am.get('sequence') and am.get('sequence') != "additional":
                    extra['seq'] = clean(am.get('sequence'))
                if not extra:
                    extra = None
                assert ctype in ("author", "editor", "translator")
                contribs.append(fatcat_client.ReleaseContrib(
                    creator_id=creator_id,
                    index=index,
                    raw_name=clean(raw_name),
                    raw_affiliation=clean(raw_affiliation),
                    role=ctype,
                    extra=extra))
            return contribs
        contribs = do_contribs(obj.get('author', []), "author")
        contribs.extend(do_contribs(obj.get('editor', []), "editor"))
        contribs.extend(do_contribs(obj.get('translator', []), "translator"))

        # container
        issn = obj.get('ISSN', [None])[0]
        issnl = self.issn2issnl(issn)
        container_id = None
        if issnl:
            container_id = self.lookup_issnl(issnl)
        publisher = obj.get('publisher')

        if (container_id is None and self.create_containers and (issnl is not None)
            and obj.get('container-title') and len(obj['container-title']) > 0):
            ce = fatcat_client.ContainerEntity(
                issnl=issnl,
                publisher=clean(publisher),
                container_type=self.map_container_type(release_type),
                name=clean(obj['container-title'][0], force_xml=True))
            ce_edit = self.create_container(ce)
            container_id = ce_edit.ident

        # license slug
        license_slug = None
        license_extra = []
        for l in obj.get('license', []):
            if l['content-version'] not in ('vor', 'unspecified'):
                continue
            slug = LICENSE_SLUG_MAP.get(l['URL'])
            if slug:
                license_slug = slug
            if 'start' in l:
                l['start'] = l['start']['date-time']
            license_extra.append(l)

        # references
        refs = []
        for i, rm in enumerate(obj.get('reference', [])):
            try:
                year = int(rm.get('year'))
                # TODO: will need to update/config in the future!
                # NOTE: are there crossref works with year < 100?
                if year > 2025 or year < 100:
                    year = None
            except:
                year = None
            key = rm.get('key')
            if key and key.startswith(obj['DOI'].upper()):
                key = key.replace(obj['DOI'].upper() + "-", '')
                key = key.replace(obj['DOI'].upper(), '')
            container_name = rm.get('volume-title')
            if not container_name:
                container_name = rm.get('journal-title')
            elif rm.get('journal-title'):
                extra['journal-title'] = rm['journal-title']
            extra = dict()
            if rm.get('DOI'):
                extra['doi'] = rm.get('DOI').lower()
            # TODO: what fields here? CSL citation stuff
            for k in ('author', 'editor', 'edition', 'authority', 'version',
                    'genre', 'url', 'event', 'issue', 'volume', 'date',
                    'accessed_date', 'issued', 'page', 'medium',
                    'collection_title', 'chapter_number'):
                if clean(rm.get(k)):
                    extra[k] = clean(rm[k])
            if extra:
                extra = dict(crossref=extra)
            else:
                extra = None
            refs.append(fatcat_client.ReleaseRef(
                index=i,
                # doing lookups would be a second import pass
                target_release_id=None,
                key=key,
                year=year,
                container_name=clean(container_name),
                title=clean(rm.get('title')),
                locator=clean(rm.get('first-page')),
                # TODO: just dump JSON somewhere here?
                extra=extra))

        # abstracts
        abstracts = []
        if obj.get('abstract') != None:
            abstracts.append(fatcat_client.ReleaseEntityAbstracts(
                mimetype="application/xml+jats",
                content=clean(obj.get('abstract'))))

        # extra fields
        extra = dict()
        for key in ('subject', 'type', 'alternative-id', 'container-title',
                'subtitle', 'archive', 'funder', 'group-title'):
            # TODO: unpack "container-title" array?
            val = obj.get(key)
            if val:
                if type(val) == str:
                    extra[key] = clean(val)
                else:
                    extra[key] = val
        if license_extra:
            extra['license'] = license_extra

        if len(obj['title']) > 1:
            extra['other-titles'] = [clean(t) for t in obj['title'][1:]]

        # ISBN
        isbn13 = None
        for raw in obj.get('ISBN', []):
            # TODO: convert if not ISBN-13 format
            if len(raw) == 17:
                isbn13 = raw
                break

        # release status
        if obj['type'] in ('journal-article', 'conference-proceeding', 'book',
                'dissertation', 'book-chapter'):
            release_status = "published"
        else:
            # unknown
            release_status = None

        # external identifiers
        extids = self.lookup_ext_ids(doi=obj['DOI'].lower())

        # filter out unreasonably huge releases
        if len(abstracts) > 100:
            return None
        if len(refs) > 2000:
            return None
        if len(refs) > 5000:
            return None

        # release date parsing is amazingly complex
        raw_date = obj['issued']['date-parts'][0]
        if not raw_date or not raw_date[0]:
            # got some NoneType, even though at least year is supposed to be set
            release_year = None
            release_date = None
        elif len(raw_date) == 3:
            release_year = raw_date[0]
            release_date = datetime.date(year=raw_date[0], month=raw_date[1], day=raw_date[2])
        else:
            # sometimes only the year is included, not the full date
            release_year = raw_date[0]
            release_date = None

        original_title = None
        if obj.get('original-title'):
            original_title = clean(obj.get('original-title')[0], force_xml=True)
        if obj.get('title'):
            title = clean(obj.get('title')[0], force_xml=True)
        re = fatcat_client.ReleaseEntity(
            work_id=None,
            container_id=container_id,
            title=title,
            original_title=original_title,
            release_type=release_type,
            release_status=release_status,
            release_date=release_date,
            release_year=release_year,
            publisher=clean(publisher),
            doi=obj['DOI'].lower(),
            pmid=extids['pmid'],
            pmcid=extids['pmcid'],
            wikidata_qid=extids['wikidata_qid'],
            isbn13=isbn13,
            core_id=extids['core_id'],
            arxiv_id=extids['arxiv_id'],
            jstor_id=extids['jstor_id'],
            volume=clean(obj.get('volume')),
            issue=clean(obj.get('issue')),
            pages=clean(obj.get('page')),
            language=None,  # crossref doesn't supply language info
            license_slug=license_slug,
            extra=dict(crossref=extra),
            abstracts=abstracts,
            contribs=contribs,
            refs=refs,
        )
        return re

    def try_update(self, re):

        # lookup existing DOI (don't need to try other ext idents for crossref)
        existing = None
        try:
            existing = self.api.lookup_release(doi=re.doi)
        except fatcat_client.rest.ApiException as err:
            if err.status != 404:
                raise err
            # doesn't exist, need to update
            return True

        # eventually we'll want to support "updates", but for now just skip if
        # entity already exists
        if existing:
            self.counts['exists'] += 1
            return False
        
        return True

    def insert_batch(self, batch):
        self.api.create_release_batch(batch,
            autoaccept=True,
            description=self.editgroup_description,
            extra=json.dumps(self.editgroup_extra))