aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/crossref.py
blob: c9f251fcdce965c2eebe6736c79f94acd0ff034a (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
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
import datetime
from typing import Any, Dict, List, Optional, Sequence

import fatcat_openapi_client
from fatcat_openapi_client import ApiClient, ReleaseContrib, ReleaseEntity

from fatcat_tools.normal import clean_doi

from .common import EntityImporter, clean

# The docs/guide should be the canonical home for these mappings; update there
# first
# Can get a list of Crossref types (with counts) via API:
# https://api.crossref.org/works?rows=0&facet=type-name:*
CROSSREF_TYPE_MAP: Dict[str, Optional[str]] = {
    "book": "book",
    "book-chapter": "chapter",
    "book-part": "chapter",
    "book-section": "chapter",
    "component": "component",
    "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: Dict[str, str] = {
    "article-journal": "journal",
    "paper-conference": "conference",
    "book": "book-series",
}

# These are based, informally, on sorting the most popular licenses found in
# Crossref metadata. There were over 500 unique strings and only a few most
# popular are here; many were variants of the CC URLs. Would be useful to
# normalize CC licenses better.
# The current norm is to only add license slugs that are at least partially OA.
LICENSE_SLUG_MAP: Dict[str, str] = {
    "//creativecommons.org/publicdomain/mark/1.0": "CC-0",
    "//creativecommons.org/publicdomain/mark/1.0/": "CC-0",
    "//creativecommons.org/publicdomain/mark/1.0/deed.de": "CC-0",
    "//creativecommons.org/publicdomain/mark/1.0/deed.de": "CC-0",
    "//creativecommons.org/publicdomain/zero/1.0/": "CC-0",
    "//creativecommons.org/publicdomain/zero/1.0/legalcode": "CC-0",
    "//creativecommons.org/share-your-work/public-domain/cc0/": "CC-0",
    "//creativecommons.org/licenses/by/2.0/": "CC-BY",
    "//creativecommons.org/licenses/by/3.0/": "CC-BY",
    "//creativecommons.org/licenses/by/4.0/": "CC-BY",
    "//creativecommons.org/licenses/by-sa/3.0/": "CC-BY-SA",
    "//creativecommons.org/licenses/by-sa/4.0/": "CC-BY-SA",
    "//creativecommons.org/licenses/by-nd/3.0/": "CC-BY-ND",
    "//creativecommons.org/licenses/by-nd/4.0/": "CC-BY-ND",
    "//creativecommons.org/licenses/by-nc/3.0/": "CC-BY-NC",
    "//creativecommons.org/licenses/by-nc/4.0/": "CC-BY-NC",
    "//creativecommons.org/licenses/by-nc-sa/3.0/": "CC-BY-NC-SA",
    "//creativecommons.org/licenses/by-nc-sa/4.0/": "CC-BY-NC-SA",
    "//creativecommons.org/licenses/by-nc-nd/3.0/": "CC-BY-NC-ND",
    "//creativecommons.org/licenses/by-nc-nd/4.0/": "CC-BY-NC-ND",
    "//spdx.org/licenses/CC0-1.0.json": "CC-0",
    "//spdx.org/licenses/CC-BY-1.0.json": "CC-BY",
    "//spdx.org/licenses/CC-BY-4.0.json": "CC-BY",
    "//spdx.org/licenses/CC-BY-NC-4.0.json": "CC-BY-NC",
    "//spdx.org/licenses/CC-BY-SA-3.0.json": "CC-BY-SA",
    "//spdx.org/licenses/CC-BY-SA-4.0.json": "CC-BY-SA",
    "//spdx.org/licenses/MIT.json": "MIT",
    "//spdx.org/licenses/OGL-Canada-2.0.json": "OGL-Canada",
    "//www.elsevier.com/open-access/userlicense/1.0/": "ELSEVIER-USER-1.0",
    "//www.karger.com/Services/SiteLicenses": "KARGER",
    "//pubs.acs.org/page/policy/authorchoice_termsofuse.html": "ACS-CHOICE",
    "//pubs.acs.org/page/policy/authorchoice_ccby_termsofuse.html": "CC-BY",
    "//www.biologists.com/user-licence-1-1/": "BIOLOGISTS-USER",
    "//www.biologists.com/user-licence-1-1": "BIOLOGISTS-USER",
    "//www.apa.org/pubs/journals/resources/open-access.aspx": "APA",
    "//www.ametsoc.org/PUBSReuseLicenses": "AMETSOC",
    # //onlinelibrary.wiley.com/termsAndConditions doesn't seem like a license
    # //www.springer.com/tdm doesn't seem like a license
    # //iopscience.iop.org/page/copyright is closed
    # //www.acm.org/publications/policies/copyright_policy#Background is closed
    # //rsc.li/journals-terms-of-use is closed for vor (am open)
    # //www.ieee.org/publications_standards/publications/rights/ieeecopyrightform.pdf is 404 (!)
    "//arxiv.org/licenses/nonexclusive-distrib/1.0/": "ARXIV-1.0",
}


def lookup_license_slug(raw: Optional[str]) -> Optional[str]:
    if not raw:
        return None
    raw = raw.strip().replace("http://", "//").replace("https://", "//")
    if "creativecommons.org" in raw.lower():
        raw = raw.lower()
        raw = raw.replace("/legalcode", "/").replace("/uk", "")
        if not raw.endswith("/"):
            raw = raw + "/"
    return LICENSE_SLUG_MAP.get(raw)


def test_lookup_license_slug() -> None:

    assert lookup_license_slug("https://creativecommons.org/licenses/by-nc/3.0/") == "CC-BY-NC"
    assert (
        lookup_license_slug("http://creativecommons.org/licenses/by/2.0/uk/legalcode")
        == "CC-BY"
    )
    assert (
        lookup_license_slug("https://creativecommons.org/publicdomain/zero/1.0/legalcode")
        == "CC-0"
    )
    assert lookup_license_slug("http://creativecommons.org/licenses/by/4.0") == "CC-BY"
    assert (
        lookup_license_slug("https://creativecommons.org/licenses/by-nc-sa/4.0/")
        == "CC-BY-NC-SA"
    )
    assert lookup_license_slug("https://www.ametsoc.org/PUBSReuseLicenses") == "AMETSOC"
    assert lookup_license_slug("https://www.amec.org/PUBSReuseLicenses") is None
    assert lookup_license_slug("") is None
    assert lookup_license_slug(None) is None


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

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

    def __init__(self, api: ApiClient, issn_map_file: Sequence, **kwargs) -> None:

        eg_desc: Optional[str] = kwargs.get(
            "editgroup_description",
            "Automated import of Crossref DOI metadata, harvested from REST API",
        )
        eg_extra: Dict[str, Any] = 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,
            **kwargs
        )

        self.create_containers: bool = kwargs.get("create_containers", True)
        self.read_issn_map_file(issn_map_file)

    def map_release_type(self, crossref_type: str) -> Optional[str]:
        return CROSSREF_TYPE_MAP.get(crossref_type)

    def map_container_type(self, crossref_type: Optional[str]) -> Optional[str]:
        if not crossref_type:
            return None
        return CONTAINER_TYPE_MAP.get(crossref_type)

    def want(self, obj: Dict[str, Any]) -> bool:
        if not obj.get("title"):
            self.counts["skip-blank-title"] += 1
            return False

        # these are pre-registered DOIs before the actual record is ready
        # title is a list of titles
        titles = obj.get("title")
        if titles is not None and titles[0].strip().lower() in [
            "OUP accepted manuscript".lower(),
        ]:
            self.counts["skip-stub-title"] += 1
            return False

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

    def parse_record(self, obj: Dict[str, Any]) -> Optional[ReleaseEntity]:
        """
        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",
        ):
            self.counts["skip-release-type"] += 1
            return None

        # Do require the 'title' keys to exist, as release entities do
        if ("title" not in obj) or (not obj["title"]):
            self.counts["skip-blank-title"] += 1
            return None

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

        # contribs
        def do_contribs(obj_list: List[Dict[str, Any]], ctype: str) -> List[ReleaseContrib]:
            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: Optional[str] = "{} {}".format(am["given"], am["family"])
                elif am.get("family"):
                    raw_name = am["family"]
                else:
                    # TODO: can end up empty
                    raw_name = am.get("name") or am.get("given")
                extra: Dict[str, Any] = dict()
                if ctype == "author":
                    index: Optional[int] = i
                else:
                    index = None
                raw_affiliation = None
                affiliation_list = am.get("affiliation") or []
                if affiliation_list and len(affiliation_list) > 0:
                    raw_affiliation = affiliation_list[0]["name"]
                    if len(affiliation_list) > 1:
                        # note: affiliation => more_affiliations
                        extra["more_affiliations"] = [
                            clean(a["name"]) for a in affiliation_list[1:]
                        ]
                if am.get("sequence") and am.get("sequence") != "additional":
                    extra["seq"] = clean(am.get("sequence"))
                assert ctype in ("author", "editor", "translator")
                raw_name = clean(raw_name)
                # TODO: what if 'raw_name' is None?
                contribs.append(
                    ReleaseContrib(
                        creator_id=creator_id,
                        index=index,
                        raw_name=raw_name,
                        given_name=clean(am.get("given")),
                        surname=clean(am.get("family")),
                        raw_affiliation=clean(raw_affiliation),
                        role=ctype,
                        extra=extra or None,
                    )
                )
            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 = clean(obj.get("publisher"))

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

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

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

        # abstracts
        abstracts = []
        abstract = clean(obj.get("abstract"))
        if abstract and len(abstract) > 10:
            abstracts.append(
                fatcat_openapi_client.ReleaseAbstract(
                    mimetype="application/xml+jats", content=abstract
                )
            )

        # extra fields
        extra: Dict[str, Any] = dict()
        extra_crossref: Dict[str, Any] = dict()
        # top-level extra keys
        if not container_id:
            if obj.get("container-title"):
                extra["container_name"] = container_name
        for key in "group-title":
            val = obj.get(key)
            if val:
                if type(val) == list:
                    val = val[0]
                if type(val) == str:
                    val = clean(val)
                    if val:
                        extra[key] = clean(val)
                else:
                    extra[key] = val
        # crossref-nested extra keys
        for key in ("subject", "type", "alternative-id", "archive", "funder"):
            val = obj.get(key)
            if val:
                if type(val) == str:
                    extra_crossref[key] = clean(val)
                else:
                    extra_crossref[key] = val
        if license_extra:
            extra_crossref["license"] = license_extra

        if len(obj["title"]) > 1:
            aliases = [clean(t) for t in obj["title"][1:]]
            aliases = [t for t in aliases if t]
            if aliases:
                extra["aliases"] = aliases

        # 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_stage: Optional[str] = "published"
        else:
            # unknown
            release_stage = None

        # filter out unreasonably huge releases
        if len(abstracts) > 100:
            self.counts["skip-huge-abstracts"] += 1
            return None
        if len(contribs) > 2000:
            self.counts["skip-huge-contribs"] += 1
            return None
        if len(refs) > 5000:
            self.counts["skip-huge-refs"] += 1
            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: Optional[str] = None
        if obj.get("original-title"):
            ot = obj.get("original-title")
            if ot is not None:
                original_title = clean(ot[0], force_xml=True)

        title: Optional[str] = None
        if obj.get("title"):
            title = clean(obj["title"][0], force_xml=True)
            if not title or len(title) <= 1:
                # title can't be just a single character
                self.counts["skip-blank-title"] += 1
                return None

        doi = clean_doi(obj["DOI"].lower())
        if not doi:
            self.counts["skip-bad-doi"] += 1
            return None

        subtitle = None
        if obj.get("subtitle"):
            subtitle = clean(obj["subtitle"][0], force_xml=True)
            if not subtitle or len(subtitle) <= 1:
                # subtitle can't be just a single character
                subtitle = None

        if extra_crossref:
            extra["crossref"] = extra_crossref

        re = ReleaseEntity(
            work_id=None,
            container_id=container_id,
            title=title,
            subtitle=subtitle,
            original_title=original_title,
            release_type=release_type,
            release_stage=release_stage,
            release_date=release_date,
            release_year=release_year,
            publisher=publisher,
            ext_ids=fatcat_openapi_client.ReleaseExtIds(
                doi=doi,
                isbn13=isbn13,
            ),
            volume=clean(obj.get("volume")),
            issue=clean(obj.get("issue")),
            pages=clean(obj.get("page")),
            language=clean(obj.get("language")),
            license_slug=license_slug,
            extra=extra or None,
            abstracts=abstracts or None,
            contribs=contribs or None,
            refs=refs or None,
        )
        return re

    def try_update(self, re: ReleaseEntity) -> bool:

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

        # 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: List[ReleaseEntity]) -> None:
        self.api.create_release_auto_batch(
            fatcat_openapi_client.ReleaseAutoBatch(
                editgroup=fatcat_openapi_client.Editgroup(
                    description=self.editgroup_description, extra=self.editgroup_extra
                ),
                entity_list=batch,
            )
        )