summaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/importers/pubmed.py
blob: d32fcefa77bf1acee2e13499041ea78009ed7769 (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
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
import datetime
import json
import sys
import warnings
from typing import Any, Dict, List, Optional, Sequence

import fatcat_openapi_client
from bs4 import BeautifulSoup
from fatcat_openapi_client import ApiClient, ReleaseEntity

from fatcat_tools.normal import clean_doi, clean_issn, clean_pmcid, clean_pmid

from .common import LANG_MAP_MARC, EntityImporter, clean

# from: https://www.ncbi.nlm.nih.gov/books/NBK3827/table/pubmedhelp.T.publication_types/?report=objectonly
PUBMED_RELEASE_TYPE_MAP = {
    # Adaptive Clinical Trial
    "Address": "speech",
    "Autobiography": "book",
    # Bibliography
    "Biography": "book",
    # Case Reports
    "Classical Article": "article-journal",
    # Clinical Conference
    # Clinical Study
    # Clinical Trial
    # Clinical Trial, Phase I
    # Clinical Trial, Phase II
    # Clinical Trial, Phase III
    # Clinical Trial, Phase IV
    # Clinical Trial Protocol
    # Clinical Trial, Veterinary
    # Collected Works
    # Comparative Study
    # Congress
    # Consensus Development Conference
    # Consensus Development Conference, NIH
    # Controlled Clinical Trial
    "Dataset": "dataset",
    # Dictionary
    # Directory
    # Duplicate Publication
    "Editorial": "editorial",
    # English Abstract   # doesn't indicate that this is abstract-only
    # Equivalence Trial
    # Evaluation Studies
    # Expression of Concern
    # Festschrift
    # Government Document
    # Guideline
    "Historical Article": "article-journal",
    # Interactive Tutorial
    "Interview": "interview",
    "Introductory Journal Article": "article-journal",
    "Journal Article": "article-journal",
    "Lecture": "speech",
    "Legal Case": "legal_case",
    "Legislation": "legislation",
    "Letter": "letter",
    # Meta-Analysis
    # Multicenter Study
    # News
    "Newspaper Article": "article-newspaper",
    # Observational Study
    # Observational Study, Veterinary
    # Overall
    # Patient Education Handout
    # Periodical Index
    # Personal Narrative
    # Portrait
    # Practice Guideline
    # Pragmatic Clinical Trial
    # Publication Components
    # Publication Formats
    # Publication Type Category
    # Randomized Controlled Trial
    # Research Support, American Recovery and Reinvestment Act
    # Research Support, N.I.H., Extramural
    # Research Support, N.I.H., Intramural
    # Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.
    # Research Support, U.S. Gov't, P.H.S.
    # Review     # in the "literature review" sense, not "product review"
    # Scientific Integrity Review
    # Study Characteristics
    # Support of Research
    # Systematic Review
    "Technical Report": "report",
    # Twin Study
    # Validation Studies
    # Video-Audio Media
    # Webcasts
}

MONTH_ABBR_MAP = {
    "Jan": 1,
    "01": 1,
    "Feb": 2,
    "02": 2,
    "Mar": 3,
    "03": 3,
    "Apr": 4,
    "04": 4,
    "May": 5,
    "05": 5,
    "Jun": 6,
    "06": 6,
    "Jul": 7,
    "07": 7,
    "Aug": 8,
    "08": 8,
    "Sep": 9,
    "09": 9,
    "Oct": 10,
    "10": 10,
    "Nov": 11,
    "11": 11,
    "Dec": 12,
    "12": 12,
}

# From: https://www.ncbi.nlm.nih.gov/books/NBK7249/
COUNTRY_NAME_MAP = {
    "Afghanistan": "af",
    "Albania": "al",
    "Algeria": "dz",
    "Andorra": "ad",
    "Angola": "ao",
    "Antigua and Barbuda": "ag",
    "Argentina": "ar",
    "Armenia": "am",
    "Australia": "au",
    "Austria": "at",
    "Azerbaijan": "az",
    "Bahamas": "bs",
    "Bahrain": "bh",
    "Bangladesh": "bd",
    "Barbados": "bb",
    "Belarus": "by",
    "Belgium": "be",
    "Belize": "bz",
    "Benin": "bj",
    "Bhutan": "bt",
    "Bolivia": "bo",
    "Bosnia and Herzegowina": "ba",
    "Botswana": "bw",
    "Brazil": "br",
    "Brunei Darussalam": "bn",
    "Bulgaria": "bg",
    "Burkina Faso": "bf",
    "Burundi": "bi",
    "Cambodia": "kh",
    "Cameroon": "cm",
    "Canada": "ca",
    "Cape Verde": "cv",
    "Central African Republic": "cf",
    "Chad": "td",
    "Chile": "cl",
    "China": "cn",
    "Colombia": "co",
    "Comoros": "km",
    "Congo, Democratic Republic": "cd",
    "Congo, People’s Republic": "cg",
    "Costa Rica": "cr",
    "Cote d'Ivoire": "ci",
    "Croatia (Local Name: Hrvatska)": "hr",
    "Cuba": "cu",
    "Cyprus": "cy",
    "Czech Republic": "cz",
    "Denmark": "dk",
    "Djibouti": "dj",
    "Dominica": "dm",
    "Dominican Republic": "do",
    "East Timor": "tl",
    "Ecuador": "ec",
    "El Salvador": "sv",
    "Equatorial Guinea": "gq",
    "Eritrea": "er",
    "Estonia": "ee",
    "Ethiopia": "et",
    "Fiji": "fj",
    "Finland": "fi",
    "France": "fr",
    "Gabon": "ga",
    "Gambia": "gm",
    "Georgia": "ge",
    "Germany": "de",
    "Ghana": "gh",
    "Greece": "gr",
    "Greenland": "gl",
    "Grenada": "gd",
    "Guatemala": "gt",
    "Guinea": "gn",
    "Guinea-Bissau": "gw",
    "Guyana": "gy",
    "Haiti": "ht",
    "Honduras": "hn",
    "Hong Kong": "hk",
    "Hungary": "hu",
    "Iceland": "is",
    "India": "in",
    "Indonesia": "id",
    "Iran": "ir",
    "Iraq": "iq",
    "Ireland": "ie",
    "Israel": "il",
    "Italy": "it",
    "Jamaica": "jm",
    "Japan": "jp",
    "Jordan": "jo",
    "Kazakhstan": "kz",
    "Kenya": "ke",
    "Kiribati": "ki",
    "Korea, Democratic People's Republic": "kp",
    "Korea, Republic": "kr",
    "Kuwait": "kw",
    "Kyrgyzstan": "kg",
    "Laos": "la",
    "Latvia": "lv",
    "Lebanon": "lb",
    "Lesotho": "ls",
    "Liberia": "lr",
    "Libya": "ly",
    "Liechtenstein": "li",
    "Lithuania": "lt",
    "Luxembourg": "lu",
    "Macedonia": "mk",
    "Madagascar": "mg",
    "Malawi": "mw",
    "Malaysia": "my",
    "Maldives": "mv",
    "Mali": "ml",
    "Malta": "mt",
    "Marshall Islands": "mh",
    "Mauritania": "mr",
    "Mauritius": "mu",
    "Mexico": "mx",
    "Micronesia": "fm",
    "Moldova": "md",
    "Monaco": "mc",
    "Mongolia": "mn",
    "Morocco": "ma",
    "Mozambique": "mz",
    "Myanmar": "mm",
    "Namibia": "na",
    "Nauru": "nr",
    "Nepal": "np",
    "Netherlands": "nl",
    "New Zealand": "nz",
    "Nicaragua": "ni",
    "Niger": "ne",
    "Nigeria": "ng",
    "Norway": "no",
    "Oman": "om",
    "Pakistan": "pk",
    "Palau": "pw",
    "Panama": "pa",
    "Papua New Guinea": "pg",
    "Paraguay": "py",
    "Peru": "pe",
    "Philippines": "ph",
    "Poland": "pl",
    "Portugal": "pt",
    "Puerto Rico": "pr",
    "Qatar": "qa",
    "Romania": "ro",
    "Russian Federation": "ru",
    "Rwanda": "rw",
    "Saint Kitts and Nevis": "kn",
    "Saint Lucia": "lc",
    "Saint Vincent and the Grenadines": "vc",
    "Samoa": "ws",
    "San Marino": "sm",
    "Sao Tome and Príncipe": "st",
    "Saudi Arabia": "sa",
    "Senegal": "sn",
    "Serbia and Montenegro": "cs",
    "Seychelles": "sc",
    "Sierra Leone": "sl",
    "Singapore": "sg",
    "Slovakia (Slovak Republic)": "sk",
    "Slovenia": "si",
    "Solomon Islands": "sb",
    "Somalia": "so",
    "South Africa": "za",
    "Spain": "es",
    "Sri Lanka": "lk",
    "Sudan": "sd",
    "Suriname": "sr",
    "Swaziland": "sz",
    "Sweden": "se",
    "Switzerland": "ch",
    "Syrian Arab Republic": "sy",
    "Taiwan": "tw",
    "Tajikistan": "tj",
    "Tanzania": "tz",
    "Tanzania": "tz",
    "Thailand": "th",
    "Togo": "tg",
    "Tonga": "to",
    "Trinidad and Tobago": "tt",
    "Tunisia": "tn",
    "Turkey": "tr",
    "Turkmenistan": "tm",
    "Tuvalu": "tv",
    "Uganda": "ug",
    "Ukraine": "ua",
    "United Arab Emirates": "ae",
    "United Kingdom": "gb",
    "United States": "us",
    "Uruguay": "uy",
    # Additions from running over large files
    "Bosnia and Herzegovina": "ba",
    # "International"
    "China (Republic : 1949- )": "tw",  # pretty sure this is tw not cn
    "Russia (Federation)": "ru",
    "Scotland": "gb",
    "England": "gb",
    "Korea (South)": "kr",
    "Georgia (Republic)": "ge",
    "Egypt": "eg",
}


class PubmedImporter(EntityImporter):
    """
    Importer for PubMed/MEDLINE XML metadata.

    If lookup_refs is true, will do identifer-based lookups for all references.

    TODO: MEDLINE doesn't include PMC/OA license; could include in importer?
    """

    def __init__(
        self, api: ApiClient, issn_map_file: Sequence, lookup_refs: bool = True, **kwargs
    ):

        eg_desc = kwargs.get(
            "editgroup_description", "Automated import of PubMed/MEDLINE XML metadata"
        )
        eg_extra = kwargs.get("editgroup_extra", dict())
        eg_extra["agent"] = eg_extra.get("agent", "fatcat_tools.PubmedImporter")
        super().__init__(
            api,
            issn_map_file=issn_map_file,
            editgroup_description=eg_desc,
            editgroup_extra=eg_extra,
            **kwargs
        )

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

    def want(self, raw_record: BeautifulSoup) -> bool:
        return True

    # TODO: mypy annotations partially skipped on this function ('Any' instead of
    # 'BeautifulSoup') for now because XML parsing annotations are large and
    # complex
    def parse_record(self, a: Any) -> ReleaseEntity:

        medline = a.MedlineCitation
        # PubmedData isn't required by DTD, but seems to always be present
        pubmed = a.PubmedData
        extra = dict()
        extra_pubmed = dict()

        identifiers = pubmed.ArticleIdList
        pmid = medline.PMID.string.strip()
        doi = identifiers.find("ArticleId", IdType="doi")
        if doi and doi.string:
            doi = clean_doi(doi.string)
        else:
            doi = None

        pmcid = identifiers.find("ArticleId", IdType="pmc")
        if pmcid:
            pmcid = clean_pmcid(pmcid.string.strip().upper())

        release_type = None
        pub_types = []
        for pub_type in medline.Article.PublicationTypeList.find_all("PublicationType"):
            pub_types.append(pub_type.string)
            if pub_type.string in PUBMED_RELEASE_TYPE_MAP:
                release_type = PUBMED_RELEASE_TYPE_MAP[pub_type.string]
                break
        if pub_types:
            extra_pubmed["pub_types"] = pub_types
        if medline.Article.PublicationTypeList.find(string="Retraction of Publication"):
            release_type = "retraction"
            retraction_of = medline.find("CommentsCorrections", RefType="RetractionOf")
            if retraction_of:
                if retraction_of.RefSource:
                    extra_pubmed["retraction_of_raw"] = retraction_of.RefSource.string
                if retraction_of.PMID:
                    extra_pubmed["retraction_of_pmid"] = retraction_of.PMID.string

        # everything in medline is published
        release_stage = "published"
        if medline.Article.PublicationTypeList.find(string="Corrected and Republished Article"):
            release_stage = "updated"
        if medline.Article.PublicationTypeList.find(string="Retraction of Publication"):
            release_stage = "retraction"

        withdrawn_status = None
        if medline.Article.PublicationTypeList.find(string="Retracted Publication"):
            withdrawn_status = "retracted"
        elif medline.find("CommentsCorrections", RefType="ExpressionOfConcernIn"):
            withdrawn_status = "concern"

        pages = medline.find("MedlinePgn")
        if pages:
            pages = pages.string

        title = medline.Article.ArticleTitle.get_text()  # always present
        if title:
            title = title.replace("\n", " ")
            if title.endswith("."):
                title = title[:-1]
            # this hides some "special" titles, but the vast majority are
            # translations; translations don't always include the original_title
            if title.startswith("[") and title.endswith("]"):
                title = title[1:-1]
        else:
            # will filter out later
            title = None

        original_title = medline.Article.find("VernacularTitle", recurse=False)
        if original_title:
            original_title = original_title.get_text() or None
            original_title = original_title.replace("\n", " ")
            if original_title and original_title.endswith("."):
                original_title = original_title[:-1]

        if original_title and not title:
            # if we only have an "original" title, but not translated/english
            # title, sub in the original title so the entity can be created
            title = original_title
            original_title = None

        # TODO: happening in alpha order, not handling multi-language well.
        language = medline.Article.Language
        if language:
            language = language.get_text()
            if language in ("und", "un"):
                # "undetermined"
                language = None
            else:
                language = LANG_MAP_MARC.get(language)
                if not language and not (medline.Article.Language.get_text() in LANG_MAP_MARC):
                    warnings.warn(
                        "MISSING MARC LANG: {}".format(medline.Article.Language.string)
                    )

        ### Journal/Issue Metadata
        # MedlineJournalInfo is always present
        issnl = None
        container_id = None
        container_name = None
        container_extra = dict()
        mji = medline.MedlineJournalInfo
        if mji.find("Country"):
            country_name = mji.Country.string.strip()
            country_code = COUNTRY_NAME_MAP.get(country_name)
            if country_code:
                container_extra["country"] = country_code
            elif country_name:
                container_extra["country_name"] = country_name
        if mji.find("ISSNLinking"):
            issnl = mji.ISSNLinking.string

        journal = medline.Article.Journal
        issnp = journal.find("ISSN", IssnType="Print")
        if issnp:
            issnp = clean_issn(issnp.string)
        else:
            issnp = None

        if not issnl and issnp:
            issnl = self.issn2issnl(issnp)
        else:
            issnl = None

        if issnl:
            container_id = self.lookup_issnl(issnl)

        pub_date = medline.Article.find("ArticleDate")
        if not pub_date:
            pub_date = journal.PubDate
        if not pub_date:
            pub_date = journal.JournalIssue.PubDate
        release_date: Optional[str] = None
        release_year: Optional[int] = None
        if pub_date.Year:
            release_year = int(pub_date.Year.string)
            if pub_date.find("Day") and pub_date.find("Month"):
                try:
                    release_date_date = datetime.date(
                        release_year,
                        MONTH_ABBR_MAP[pub_date.Month.string],
                        int(pub_date.Day.string),
                    )
                    release_date = release_date_date.isoformat()
                except ValueError as ve:
                    print("bad date, skipping: {}".format(ve), file=sys.stderr)
                    release_date = None
        elif pub_date.MedlineDate:
            medline_date = pub_date.MedlineDate.string.strip()
            if len(medline_date) >= 4 and medline_date[:4].isdigit():
                release_year = int(medline_date[:4])
                if release_year < 1300 or release_year > 2040:
                    print(
                        "bad medline year, skipping: {}".format(release_year), file=sys.stderr
                    )
                    release_year = None
            else:
                print(
                    "unparsable medline date, skipping: {}".format(medline_date),
                    file=sys.stderr,
                )

        if journal.find("Title"):
            container_name = journal.Title.get_text()

        if (
            container_id is None
            and self.create_containers
            and (issnl is not None)
            and container_name
        ):
            # name, type, publisher, issnl
            # extra: original_name, languages, country
            ce = fatcat_openapi_client.ContainerEntity(
                name=container_name,
                container_type="journal",
                # NOTE: publisher not included
                issnl=issnl,
                issnp=issnp,
                extra=(container_extra or None),
            )
            ce_edit = self.create_container(ce)
            container_id = ce_edit.ident
            self._issnl_id_map[issnl] = container_id

        ji = journal.JournalIssue
        volume = None
        if ji.find("Volume"):
            volume = ji.Volume.string
        issue = None
        if ji.find("Issue"):
            issue = ji.Issue.string

        ### Abstracts
        # "All abstracts are in English"
        abstracts = []
        primary_abstract = medline.find("Abstract")
        if primary_abstract and primary_abstract.AbstractText.get("NlmCategory"):
            joined = "\n".join(
                [m.get_text() for m in primary_abstract.find_all("AbstractText")]
            )
            abst = fatcat_openapi_client.ReleaseAbstract(
                content=joined,
                mimetype="text/plain",
                lang="en",
            )
            if abst.content:
                abstracts.append(abst)
        elif primary_abstract:
            for abstract in primary_abstract.find_all("AbstractText"):
                abst = fatcat_openapi_client.ReleaseAbstract(
                    content=abstract.get_text().strip(),
                    mimetype="text/plain",
                    lang="en",
                )
                if abst.content:
                    abstracts.append(abst)
                if abstract.find("math"):
                    abst = fatcat_openapi_client.ReleaseAbstract(
                        # strip the <AbstractText> tags
                        content=str(abstract)[14:-15],
                        mimetype="application/mathml+xml",
                        lang="en",
                    )
                    if abst.content:
                        abstracts.append(abst)
        other_abstracts = medline.find_all("OtherAbstract")
        for other in other_abstracts:
            lang: Optional[str] = "en"
            if other.get("Language"):
                lang = LANG_MAP_MARC.get(other["Language"])
            abst = fatcat_openapi_client.ReleaseAbstract(
                content=other.AbstractText.get_text().strip(),
                mimetype="text/plain",
                lang=lang,
            )
            if abst.content:
                abstracts.append(abst)

        ### Contribs
        contribs = []
        if medline.AuthorList:
            for author in medline.AuthorList.find_all("Author"):
                creator_id = None
                given_name = None
                surname = None
                raw_name = None
                if author.ForeName:
                    given_name = author.ForeName.get_text().replace("\n", " ")
                if author.LastName:
                    surname = author.LastName.get_text().replace("\n", " ")
                if given_name and surname:
                    raw_name = "{} {}".format(given_name, surname)
                elif surname:
                    raw_name = surname
                if not raw_name and author.CollectiveName and author.CollectiveName.get_text():
                    raw_name = author.CollectiveName.get_text().replace("\n", " ")
                contrib_extra = dict()
                orcid = author.find("Identifier", Source="ORCID")
                if orcid:
                    # needs re-formatting from, eg, "0000000179841889"
                    orcid = orcid.string
                    if orcid.startswith("http://orcid.org/"):
                        orcid = orcid.replace("http://orcid.org/", "")
                    elif orcid.startswith("https://orcid.org/"):
                        orcid = orcid.replace("https://orcid.org/", "")
                    elif "-" not in orcid:
                        orcid = "{}-{}-{}-{}".format(
                            orcid[0:4],
                            orcid[4:8],
                            orcid[8:12],
                            orcid[12:16],
                        )
                    creator_id = self.lookup_orcid(orcid)
                    contrib_extra["orcid"] = orcid
                affiliations = author.find_all("Affiliation")
                raw_affiliation = None
                if affiliations:
                    raw_affiliation = affiliations[0].get_text().replace("\n", " ")
                    if len(affiliations) > 1:
                        contrib_extra["more_affiliations"] = [
                            ra.get_text().replace("\n", " ") for ra in affiliations[1:]
                        ]
                if author.find("EqualContrib"):
                    # TODO: schema for this?
                    contrib_extra["equal"] = True
                contribs.append(
                    fatcat_openapi_client.ReleaseContrib(
                        raw_name=raw_name,
                        given_name=given_name,
                        surname=surname,
                        role="author",
                        raw_affiliation=raw_affiliation,
                        creator_id=creator_id,
                        extra=contrib_extra,
                    )
                )

            if medline.AuthorList["CompleteYN"] == "N":
                contribs.append(fatcat_openapi_client.ReleaseContrib(raw_name="et al."))

        for i, contrib in enumerate(contribs):
            if contrib.raw_name != "et al.":
                contrib.index = i

        ### References
        refs = []
        if pubmed.ReferenceList:
            # note that Reference always exists within a ReferenceList, but
            # that there may be multiple ReferenceList (eg, sometimes one per
            # Reference)
            for ref in pubmed.find_all("Reference"):
                ref_extra: Dict[str, Any] = dict()
                ref_doi = ref.find("ArticleId", IdType="doi")
                if ref_doi:
                    ref_doi = clean_doi(ref_doi.string)
                ref_pmid = ref.find("ArticleId", IdType="pubmed")
                if ref_pmid:
                    ref_pmid = clean_pmid(ref_pmid.string)
                ref_release_id = None
                if ref_doi:
                    ref_extra["doi"] = ref_doi
                    if self.lookup_refs:
                        ref_release_id = self.lookup_doi(ref_doi)
                if ref_pmid:
                    ref_extra["pmid"] = ref_pmid
                    if self.lookup_refs:
                        ref_release_id = self.lookup_pmid(ref_pmid)
                ref_raw = ref.Citation
                if ref_raw:
                    ref_extra["unstructured"] = ref_raw.get_text()
                refs.append(
                    fatcat_openapi_client.ReleaseRef(
                        target_release_id=ref_release_id,
                        extra=ref_extra or None,
                    )
                )

        # extra:
        #   translation_of
        #   aliases
        #   container_name
        #   group-title
        #   pubmed: retraction refs
        if extra_pubmed:
            extra["pubmed"] = extra_pubmed

        title = clean(title)
        if not title:
            return None

        re = fatcat_openapi_client.ReleaseEntity(
            work_id=None,
            title=title,
            original_title=clean(original_title),
            release_type=release_type,
            release_stage=release_stage,
            release_date=release_date,
            release_year=release_year,
            withdrawn_status=withdrawn_status,
            ext_ids=fatcat_openapi_client.ReleaseExtIds(
                doi=doi,
                pmid=pmid,
                pmcid=pmcid,
                # isbn13     # never in Article
            ),
            volume=volume,
            issue=issue,
            pages=pages,
            # publisher  # not included?
            language=language,
            # license_slug   # not in MEDLINE
            abstracts=abstracts or None,
            contribs=contribs or None,
            refs=refs or None,
            container_id=container_id,
            extra=extra or None,
        )
        return re

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

        # first, lookup existing by PMID (which must be defined)
        existing = None
        try:
            existing = self.api.lookup_release(pmid=re.ext_ids.pmid)
        except fatcat_openapi_client.rest.ApiException as err:
            if err.status != 404:
                raise err

        # then try DOI lookup if there is one
        if not existing and re.ext_ids.doi:
            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
            if existing and existing.ext_ids.pmid and existing.ext_ids.pmid != re.ext_ids.pmid:
                warn_str = "PMID/DOI mismatch: release {}, pmid {} != {}".format(
                    existing.ident, existing.ext_ids.pmid, re.ext_ids.pmid
                )
                warnings.warn(warn_str)
                self.counts["warn-pmid-doi-mismatch"] += 1
                # don't clobber DOI, but do group together
                re.ext_ids.doi = None
                re.work_id = existing.work_id

        if existing and not self.do_updates:
            self.counts["exists"] += 1
            return False

        if existing and existing.ext_ids.pmid and (existing.refs or not re.refs):
            # TODO: any other reasons to do an update?
            # don't update if it already has PMID
            self.counts["exists"] += 1
            return False
        elif existing:
            # but do update if only DOI was set
            existing.ext_ids.doi = existing.ext_ids.doi or re.ext_ids.doi
            existing.ext_ids.pmid = existing.ext_ids.pmid or re.ext_ids.pmid
            existing.ext_ids.pmcid = existing.ext_ids.pmcid or re.ext_ids.pmcid

            existing.container_id = existing.container_id or re.container_id
            existing.refs = existing.refs or re.refs
            existing.abstracts = existing.abstracts or re.abstracts
            existing.extra["pubmed"] = re.extra["pubmed"]

            # fix stub titles
            if existing.title in [
                "OUP accepted manuscript",
            ]:
                existing.title = re.title

            existing.original_title = existing.original_title or re.original_title
            existing.release_type = existing.release_type or re.release_type
            existing.release_stage = existing.release_stage or re.release_stage
            existing.release_date = existing.release_date or re.release_date
            existing.release_year = existing.release_year or re.release_year
            existing.withdrawn_status = existing.withdrawn_status or re.withdrawn_status
            existing.volume = existing.volume or re.volume
            existing.issue = existing.issue or re.issue
            existing.pages = existing.pages or re.pages
            existing.language = existing.language or re.language

            # update subtitle in-place first
            if not existing.subtitle and existing.extra.get("subtitle"):
                subtitle = existing.extra.pop("subtitle")
                if type(subtitle) == list:
                    subtitle = subtitle[0]
                if subtitle:
                    existing.subtitle = subtitle
            if not existing.subtitle:
                existing.subtitle = re.subtitle

            try:
                self.api.update_release(self.get_editgroup_id(), existing.ident, existing)
                self.counts["update"] += 1
            except fatcat_openapi_client.rest.ApiException as err:
                # there is a code path where we try to update the same release
                # twice in a row; if that happens, just skip
                # NOTE: API behavior might change in the future?
                if "release_edit_editgroup_id_ident_id_key" in err.body:
                    self.counts["skip-update-conflict"] += 1
                    return False
                else:
                    raise err
            finally:
                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,
            )
        )

    def parse_file(self, handle: Any) -> None:

        # 1. open with beautiful soup
        soup = BeautifulSoup(handle, "xml")

        # 2. iterate over articles, call parse_article on each
        for article in soup.find_all("PubmedArticle"):
            resp = self.parse_record(article)
            print(json.dumps(resp))
            # sys.exit(-1)