aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_import.py
blob: 3225688c1fe9024b86d66ca28717722f7490b126 (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
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
#!/usr/bin/env python3

import argparse
import os
import sys

import raven

from fatcat_tools import authenticated_api
from fatcat_tools.importers import (
    ARABESQUE_MATCH_WHERE_CLAUSE,
    ArabesqueMatchImporter,
    ArxivRawImporter,
    Bs4XmlFileListPusher,
    Bs4XmlFilePusher,
    Bs4XmlLargeFilePusher,
    Bs4XmlLinesPusher,
    ChoculaImporter,
    CrossrefImporter,
    DataciteImporter,
    DblpContainerImporter,
    DblpReleaseImporter,
    DoajArticleImporter,
    FileMetaImporter,
    FilesetImporter,
    GrobidMetadataImporter,
    IngestFileResultImporter,
    IngestFilesetResultImporter,
    IngestWebResultImporter,
    JalcImporter,
    JournalMetadataImporter,
    JsonLinePusher,
    JstorImporter,
    KafkaBs4XmlPusher,
    KafkaJsonPusher,
    LinePusher,
    MatchedImporter,
    OrcidImporter,
    PubmedImporter,
    SavePaperNowFileImporter,
    SavePaperNowFilesetImporter,
    SavePaperNowWebImporter,
    ShadowLibraryImporter,
    SqlitePusher,
    auto_cdl_dash_dat,
    auto_wayback_static,
)

# Yep, a global. Gets DSN from `SENTRY_DSN` environment variable
sentry_client = raven.Client()


def run_crossref(args):
    fci = CrossrefImporter(args.api,
        args.issn_map_file,
        extid_map_file=args.extid_map_file,
        edit_batch_size=args.batch_size,
        bezerk_mode=args.bezerk_mode)
    if args.kafka_mode:
        KafkaJsonPusher(
            fci,
            args.kafka_hosts,
            args.kafka_env,
            "api-crossref",
            "fatcat-{}-import-crossref".format(args.kafka_env),
            consume_batch_size=args.batch_size,
        ).run()
    else:
        JsonLinePusher(fci, args.json_file).run()

def run_jalc(args):
    ji = JalcImporter(args.api,
        args.issn_map_file,
        extid_map_file=args.extid_map_file)
    Bs4XmlLinesPusher(ji, args.xml_file, "<rdf:Description").run()

def run_arxiv(args):
    ari = ArxivRawImporter(args.api,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaBs4XmlPusher(
            ari,
            args.kafka_hosts,
            args.kafka_env,
            "oaipmh-arxiv",
            "fatcat-{}-import-arxiv".format(args.kafka_env),
        ).run()
    else:
        if args.xml_file == sys.stdin:
            print('note: reading from stdin', file=sys.stderr)
        Bs4XmlFilePusher(ari, args.xml_file, "record").run()

def run_pubmed(args):
    pi = PubmedImporter(args.api,
        args.issn_map_file,
        edit_batch_size=args.batch_size,
        do_updates=args.do_updates,
        lookup_refs=(not args.no_lookup_refs))
    if args.kafka_mode:
        KafkaBs4XmlPusher(
            pi,
            args.kafka_hosts,
            args.kafka_env,
            "ftp-pubmed",
            "fatcat-{}-import-pubmed".format(args.kafka_env),
        ).run()
    else:
        Bs4XmlLargeFilePusher(
            pi,
            args.xml_file,
            ["PubmedArticle"],
        ).run()

def run_jstor(args):
    ji = JstorImporter(args.api,
        args.issn_map_file,
        edit_batch_size=args.batch_size)
    Bs4XmlFileListPusher(ji, args.list_file, "article").run()

def run_orcid(args):
    foi = OrcidImporter(args.api,
        edit_batch_size=args.batch_size)
    JsonLinePusher(foi, args.json_file).run()

def run_journal_metadata(args):
    fii = JournalMetadataImporter(args.api,
        edit_batch_size=args.batch_size)
    JsonLinePusher(fii, args.json_file).run()

def run_chocula(args):
    fii = ChoculaImporter(args.api,
        edit_batch_size=args.batch_size,
        do_updates=args.do_updates)
    JsonLinePusher(fii, args.json_file).run()

def run_matched(args):
    fmi = MatchedImporter(args.api,
        edit_batch_size=args.batch_size,
        editgroup_description=args.editgroup_description_override,
        default_link_rel=args.default_link_rel,
        default_mimetype=args.default_mimetype)
    JsonLinePusher(fmi, args.json_file).run()

def run_arabesque_match(args):
    if (args.sqlite_file and args.json_file) or not (args.sqlite_file or
            args.json_file):
        print("Supply one of --sqlite-file or --json-file")
    ami = ArabesqueMatchImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        do_updates=args.do_updates,
        require_grobid=(not args.no_require_grobid),
        extid_type=args.extid_type,
        crawl_id=args.crawl_id,
        default_link_rel=args.default_link_rel,
        edit_batch_size=args.batch_size)
    if args.sqlite_file:
        SqlitePusher(ami, args.sqlite_file, "crawl_result",
            ARABESQUE_MATCH_WHERE_CLAUSE).run()
    elif args.json_file:
        JsonLinePusher(ami, args.json_file).run()

def run_ingest_file(args):
    ifri = IngestFileResultImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        skip_source_allowlist=args.skip_source_allowlist,
        do_updates=args.do_updates,
        default_link_rel=args.default_link_rel,
        require_grobid=(not args.no_require_grobid),
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            ifri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-file-results",
            "fatcat-{}-ingest-file-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
        ).run()
    else:
        JsonLinePusher(ifri, args.json_file).run()

def run_ingest_web(args):
    iwri = IngestWebResultImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        skip_source_allowlist=args.skip_source_allowlist,
        do_updates=args.do_updates,
        default_link_rel=args.default_link_rel,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            iwri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-file-results",
            "fatcat-{}-ingest-web-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
            force_flush=True,
        ).run()
    else:
        JsonLinePusher(iwri, args.json_file).run()

def run_ingest_fileset(args):
    ifri = IngestFilesetResultImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        skip_source_allowlist=args.skip_source_allowlist,
        do_updates=args.do_updates,
        default_link_rel=args.default_link_rel,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            ifri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-fileset-results",
            "fatcat-{}-ingest-fileset-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
            force_flush=True,
        ).run()
    else:
        JsonLinePusher(ifri, args.json_file).run()

def run_savepapernow_file(args):
    ifri = SavePaperNowFileImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            ifri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-file-results",
            "fatcat-{}-savepapernow-file-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
            force_flush=True,
        ).run()
    else:
        JsonLinePusher(ifri, args.json_file).run()

def run_savepapernow_web(args):
    ifri = SavePaperNowWebImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            ifri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-file-results",
            "fatcat-{}-savepapernow-web-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
            force_flush=True,
        ).run()
    else:
        JsonLinePusher(ifri, args.json_file).run()

def run_savepapernow_fileset(args):
    ifri = SavePaperNowFilesetImporter(args.api,
        editgroup_description=args.editgroup_description_override,
        edit_batch_size=args.batch_size)
    if args.kafka_mode:
        KafkaJsonPusher(
            ifri,
            args.kafka_hosts,
            args.kafka_env,
            "ingest-file-results",
            "fatcat-{}-savepapernow-fileset-result".format(args.kafka_env),
            kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size,
            force_flush=True,
        ).run()
    else:
        JsonLinePusher(ifri, args.json_file).run()

def run_grobid_metadata(args):
    fmi = GrobidMetadataImporter(args.api,
        edit_batch_size=args.batch_size,
        longtail_oa=args.longtail_oa,
        bezerk_mode=args.bezerk_mode)
    LinePusher(fmi, args.tsv_file).run()

def run_shadow_lib(args):
    fmi = ShadowLibraryImporter(args.api,
        edit_batch_size=100)
    JsonLinePusher(fmi, args.json_file).run()

def run_wayback_static(args):
    api = args.api

    # find the release
    if args.release_id:
        release_id = args.release_id
    elif args.extid:
        idtype = args.extid.split(':')[0]
        extid = ':'.join(args.extid.split(':')[1:])
        if idtype == "doi":
            release_id = api.lookup_release(doi=extid).ident
        elif idtype == "pmid":
            release_id = api.lookup_release(pmid=extid).ident
        elif idtype == "wikidata":
            release_id = api.lookup_release(wikidata_qid=extid).ident
        else:
            raise NotImplementedError("extid type: {}".format(idtype))
    else:
        raise Exception("need either release_id or extid argument")

    # create it
    (editgroup_id, wc) = auto_wayback_static(api, release_id, args.wayback_url,
        editgroup_id=args.editgroup_id)
    if not wc:
        return
    print("release_id: {}".format(release_id))
    print("editgroup_id: {}".format(editgroup_id))
    print("webcapture id: {}".format(wc.ident))
    print("link: https://fatcat.wiki/webcapture/{}".format(wc.ident))

def run_cdl_dash_dat(args):
    api = args.api

    # create it
    (editgroup_id, release, fs) = auto_cdl_dash_dat(api, args.dat_path,
        release_id=args.release_id, editgroup_id=args.editgroup_id)
    if not fs:
        return
    print("release_id: {}".format(release.ident))
    print("editgroup_id: {}".format(editgroup_id))
    print("fileset id: {}".format(fs.ident))
    print("link: https://fatcat.wiki/fileset/{}".format(fs.ident))

def run_datacite(args):
    dci = DataciteImporter(args.api,
        args.issn_map_file,
        edit_batch_size=args.batch_size,
        bezerk_mode=args.bezerk_mode,
        debug=args.debug,
        extid_map_file=args.extid_map_file,
        insert_log_file=args.insert_log_file)
    if args.kafka_mode:
        KafkaJsonPusher(
            dci,
            args.kafka_hosts,
            args.kafka_env,
            "api-datacite",
            "fatcat-{}-import-datacite".format(args.kafka_env),
            consume_batch_size=args.batch_size,
        ).run()
    else:
        JsonLinePusher(dci, args.json_file).run()

def run_doaj_article(args):
    dai = DoajArticleImporter(args.api,
        args.issn_map_file,
        edit_batch_size=args.batch_size,
        do_updates=args.do_updates,
    )
    if args.kafka_mode:
        KafkaJsonPusher(
            dai,
            args.kafka_hosts,
            args.kafka_env,
            "api-doaj",
            "fatcat-{}-import-doaj".format(args.kafka_env),
            consume_batch_size=args.batch_size,
        ).run()
    else:
        JsonLinePusher(dai, args.json_file).run()

def run_dblp_release(args):
    dri = DblpReleaseImporter(args.api,
        dblp_container_map_file=args.dblp_container_map_file,
        edit_batch_size=args.batch_size,
        do_updates=args.do_updates,
        dump_json_mode=args.dump_json_mode,
    )
    Bs4XmlLargeFilePusher(
        dri,
        args.xml_file,
        DblpReleaseImporter.ELEMENT_TYPES,
        use_lxml=True,
    ).run()

def run_dblp_container(args):
    dci = DblpContainerImporter(args.api,
        args.issn_map_file,
        dblp_container_map_file=args.dblp_container_map_file,
        dblp_container_map_output=args.dblp_container_map_output,
        edit_batch_size=args.batch_size,
        do_updates=args.do_updates,
    )
    JsonLinePusher(dci, args.json_file).run()

def run_file_meta(args):
    # do_updates defaults to true for this importer
    fmi = FileMetaImporter(args.api,
        edit_batch_size=100,
        editgroup_description=args.editgroup_description_override,
    )
    JsonLinePusher(fmi, args.json_file).run()

def run_fileset(args):
    fmi = FilesetImporter(
        args.api,
        edit_batch_size=100,
        skip_release_fileset_check=args.skip_release_fileset_check,
    )
    JsonLinePusher(fmi, args.json_file).run()

def main():
    parser = argparse.ArgumentParser(
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--host-url',
        default="http://localhost:9411/v0",
        help="connect to this host/port")
    parser.add_argument('--kafka-hosts',
        default="localhost:9092",
        help="list of Kafka brokers (host/port) to use")
    parser.add_argument('--kafka-env',
        default="dev",
        help="Kafka topic namespace to use (eg, prod, qa)")
    parser.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)
    parser.add_argument('--editgroup-description-override',
        help="editgroup description override",
        default=None, type=str)
    subparsers = parser.add_subparsers()

    sub_crossref = subparsers.add_parser('crossref',
        help="import Crossref API metadata format (JSON)")
    sub_crossref.set_defaults(
        func=run_crossref,
        auth_var="FATCAT_AUTH_WORKER_CROSSREF",
    )
    sub_crossref.add_argument('json_file',
        help="crossref JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_crossref.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_crossref.add_argument('--extid-map-file',
        help="DOI-to-other-identifiers sqlite3 database",
        default=None, type=str)
    sub_crossref.add_argument('--no-lookup-refs',
        action='store_true',
        help="skip lookup of references (PMID or DOI)")
    sub_crossref.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_crossref.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing DOIs, just insert (clobbers; only for fast bootstrap)")

    sub_jalc = subparsers.add_parser('jalc',
        help="import JALC DOI metadata from XML dump")
    sub_jalc.set_defaults(
        func=run_jalc,
        auth_var="FATCAT_AUTH_WORKER_JALC",
    )
    sub_jalc.add_argument('xml_file',
        help="Jalc RDF XML file (record-per-line) to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_jalc.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_jalc.add_argument('--extid-map-file',
        help="DOI-to-other-identifiers sqlite3 database",
        default=None, type=str)

    sub_arxiv = subparsers.add_parser('arxiv',
        help="import arxiv.org metadata from XML files")
    sub_arxiv.set_defaults(
        func=run_arxiv,
        auth_var="FATCAT_AUTH_WORKER_ARXIV",
    )
    sub_arxiv.add_argument('xml_file',
        nargs='?',
        help="arXivRaw XML file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_arxiv.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_pubmed = subparsers.add_parser('pubmed',
        help="import MEDLINE/PubMed work-level metadata (XML)")
    sub_pubmed.set_defaults(
        func=run_pubmed,
        auth_var="FATCAT_AUTH_WORKER_PUBMED",
    )
    sub_pubmed.add_argument('xml_file',
        nargs='?',
        help="Pubmed XML file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_pubmed.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_pubmed.add_argument('--no-lookup-refs',
        action='store_true',
        help="skip lookup of references (PMID or DOI)")
    sub_pubmed.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing release entities")
    sub_pubmed.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_jstor = subparsers.add_parser('jstor',
        help="import JSTOR work-level metadata from XML dump")
    sub_jstor.set_defaults(
        func=run_jstor,
        auth_var="FATCAT_AUTH_WORKER_JSTOR",
    )
    sub_jstor.add_argument('list_file',
        help="List of JSTOR XML file paths to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_jstor.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))

    sub_orcid = subparsers.add_parser('orcid',
        help="import creator entities from ORCID XML dump")
    sub_orcid.set_defaults(
        func=run_orcid,
        auth_var="FATCAT_AUTH_WORKER_ORCID"
    )
    sub_orcid.add_argument('json_file',
        help="orcid JSON file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))

    sub_journal_metadata = subparsers.add_parser('journal-metadata',
        help="import/update container metadata from old manual munging format")
    sub_journal_metadata.set_defaults(
        func=run_journal_metadata,
        auth_var="FATCAT_AUTH_WORKER_JOURNAL_METADATA",
    )
    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_chocula = subparsers.add_parser('chocula',
        help="import/update container metadata from chocula JSON export")
    sub_chocula.set_defaults(
        func=run_chocula,
        auth_var="FATCAT_AUTH_WORKER_JOURNAL_METADATA",
    )
    sub_chocula.add_argument('json_file',
        help="chocula JSON entities file (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_chocula.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing container entities")

    sub_matched = subparsers.add_parser('matched',
        help="add file entities matched against existing releases; custom JSON format")
    sub_matched.set_defaults(
        func=run_matched,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_matched.add_argument('json_file',
        help="JSON file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_matched.add_argument('--default-mimetype',
        default=None,
        help="default mimetype for imported files (if not specified per-file)")
    sub_matched.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing files, just insert (clobbers; only for fast bootstrap)")
    sub_matched.add_argument('--default-link-rel',
        default="web",
        help="default URL rel for matches (eg, 'publisher', 'web')")

    sub_arabesque_match = subparsers.add_parser('arabesque',
        help="add file entities matched to releases from crawl log analysis")
    sub_arabesque_match.set_defaults(
        func=run_arabesque_match,
        auth_var="FATCAT_AUTH_WORKER_CRAWL",
    )
    sub_arabesque_match.add_argument('--sqlite-file',
        help="sqlite database file to import from")
    sub_arabesque_match.add_argument('--json-file',
        help="JSON file to import from (or stdin)",
        type=argparse.FileType('r'))
    sub_arabesque_match.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing file entities if new match (instead of skipping)")
    sub_arabesque_match.add_argument('--no-require-grobid',
        action='store_true',
        help="whether postproc_status column must be '200'")
    sub_arabesque_match.add_argument('--extid-type',
        default="doi",
        help="identifier type in the database (eg, 'doi', 'pmcid'")
    sub_arabesque_match.add_argument('--crawl-id',
        help="crawl ID (optionally included in editgroup metadata)")
    sub_arabesque_match.add_argument('--default-link-rel',
        default="web",
        help="default URL rel for matches (eg, 'publisher', 'web')")

    sub_ingest_file = subparsers.add_parser('ingest-file-results',
        help="add/update file entities linked to releases based on sandcrawler ingest results")
    sub_ingest_file.set_defaults(
        func=run_ingest_file,
        auth_var="FATCAT_AUTH_WORKER_CRAWL",
    )
    sub_ingest_file.add_argument('json_file',
        help="ingest_file JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_ingest_file.add_argument('--skip-source-allowlist',
        action='store_true',
        help="don't filter import based on request source allowlist")
    sub_ingest_file.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_ingest_file.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing file entities if new match (instead of skipping)")
    sub_ingest_file.add_argument('--no-require-grobid',
        action='store_true',
        help="whether postproc_status column must be '200'")
    sub_ingest_file.add_argument('--default-link-rel',
        default="web",
        help="default URL rel for matches (eg, 'publisher', 'web')")

    sub_ingest_web = subparsers.add_parser('ingest-web-results',
        help="add/update web entities linked to releases based on sandcrawler ingest results")
    sub_ingest_web.set_defaults(
        func=run_ingest_web,
        auth_var="FATCAT_AUTH_WORKER_CRAWL",
    )
    sub_ingest_web.add_argument('json_file',
        help="ingest_web JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_ingest_web.add_argument('--skip-source-allowlist',
        action='store_true',
        help="don't filter import based on request source allowlist")
    sub_ingest_web.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_ingest_web.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing web entities if new match (instead of skipping)")
    sub_ingest_web.add_argument('--default-link-rel',
        default="web",
        help="default URL rel for matches (eg, 'publisher', 'web')")

    sub_ingest_fileset = subparsers.add_parser('ingest-fileset-results',
        help="add/update fileset entities linked to releases based on sandcrawler ingest results")
    sub_ingest_fileset.set_defaults(
        func=run_ingest_fileset,
        auth_var="FATCAT_AUTH_WORKER_CRAWL",
    )
    sub_ingest_fileset.add_argument('json_file',
        help="ingest_fileset JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_ingest_fileset.add_argument('--skip-source-allowlist',
        action='store_true',
        help="don't filter import based on request source allowlist")
    sub_ingest_fileset.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_ingest_fileset.add_argument('--do-updates',
        action='store_true',
        help="update pre-existing fileset entities if new match (instead of skipping)")
    sub_ingest_fileset.add_argument('--default-link-rel',
        default="fileset",
        help="default URL rel for matches (eg, 'publisher', 'web')")

    sub_savepapernow_file = subparsers.add_parser('savepapernow-file-results',
        help="add file entities crawled due to async Save Paper Now request")
    sub_savepapernow_file.set_defaults(
        func=run_savepapernow_file,
        auth_var="FATCAT_AUTH_WORKER_SAVEPAPERNOW",
    )
    sub_savepapernow_file.add_argument('json_file',
        help="ingest-file JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_savepapernow_file.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_savepapernow_web = subparsers.add_parser('savepapernow-web-results',
        help="add webcapture entities crawled due to async Save Paper Now request")
    sub_savepapernow_web.set_defaults(
        func=run_savepapernow_web,
        auth_var="FATCAT_AUTH_WORKER_SAVEPAPERNOW",
    )
    sub_savepapernow_web.add_argument('json_file',
        help="ingest-file JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_savepapernow_web.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_savepapernow_fileset = subparsers.add_parser('savepapernow-fileset-results',
        help="add fileset entities crawled due to async Save Paper Now request")
    sub_savepapernow_fileset.set_defaults(
        func=run_savepapernow_fileset,
        auth_var="FATCAT_AUTH_WORKER_SAVEPAPERNOW",
    )
    sub_savepapernow_fileset.add_argument('json_file',
        help="ingest-file JSON file to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_savepapernow_fileset.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_grobid_metadata = subparsers.add_parser('grobid-metadata',
        help="create release and file entities based on GROBID PDF metadata extraction")
    sub_grobid_metadata.set_defaults(
        func=run_grobid_metadata,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_grobid_metadata.add_argument('tsv_file',
        help="TSV file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_grobid_metadata.add_argument('--group-size',
        help="editgroup group size to use",
        default=75, type=int)
    sub_grobid_metadata.add_argument('--longtail-oa',
        action='store_true',
        help="if this is an import of longtail OA content (sets an 'extra' flag)")
    sub_grobid_metadata.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing files, just insert (clobbers; only for fast bootstrap)")

    sub_shadow_lib = subparsers.add_parser('shadow-lib',
        help="create release and file entities based on GROBID PDF metadata extraction")
    sub_shadow_lib.set_defaults(
        func=run_shadow_lib,
        auth_var="FATCAT_AUTH_WORKER_SHADOW",
    )
    sub_shadow_lib.add_argument('json_file',
        help="JSON file to import from (or stdin)",
        default=sys.stdin, type=argparse.FileType('r'))

    sub_wayback_static = subparsers.add_parser('wayback-static',
        help="crude crawl+ingest tool for single-page HTML docs from wayback")
    sub_wayback_static.set_defaults(
        func=run_wayback_static,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_wayback_static.add_argument('wayback_url',
        type=str,
        help="URL of wayback capture to extract from")
    sub_wayback_static.add_argument('--extid',
        type=str,
        help="external identifier for release lookup")
    sub_wayback_static.add_argument('--release-id',
        type=str,
        help="release entity identifier")
    sub_wayback_static.add_argument('--editgroup-id',
        type=str,
        help="use existing editgroup (instead of creating a new one)")

    sub_cdl_dash_dat = subparsers.add_parser('cdl-dash-dat',
        help="crude helper to import datasets from Dat/CDL mirror pilot project")
    sub_cdl_dash_dat.set_defaults(
        func=run_cdl_dash_dat,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_cdl_dash_dat.add_argument('dat_path',
        type=str,
        help="local path dat to import (must be the dat discovery key)")
    sub_cdl_dash_dat.add_argument('--release-id',
        type=str,
        help="release entity identifier")
    sub_cdl_dash_dat.add_argument('--editgroup-id',
        type=str,
        help="use existing editgroup (instead of creating a new one)")

    sub_datacite = subparsers.add_parser('datacite',
        help="import datacite.org metadata")
    sub_datacite.add_argument('json_file',
        help="File with jsonlines from datacite.org v2 API to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_datacite.add_argument('issn_map_file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_datacite.add_argument('--extid-map-file',
        help="DOI-to-other-identifiers sqlite3 database",
        default=None, type=str)
    sub_datacite.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_datacite.add_argument('--bezerk-mode',
        action='store_true',
        help="don't lookup existing DOIs, just insert (clobbers; only for fast bootstrap)")
    sub_datacite.add_argument('--debug',
        action='store_true',
        help="write converted JSON to stdout")
    sub_datacite.add_argument('--insert-log-file',
        default='',
        type=str,
        help="write inserted documents into file (for debugging)")
    sub_datacite.set_defaults(
        func=run_datacite,
        auth_var="FATCAT_AUTH_WORKER_DATACITE",
    )

    sub_doaj_article = subparsers.add_parser('doaj-article',
        help="import doaj.org article metadata")
    sub_doaj_article.add_argument('json_file',
        help="File with JSON lines from DOAJ API (or bulk dump) to import from",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_doaj_article.add_argument('--issn-map-file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_doaj_article.add_argument('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")
    sub_doaj_article.add_argument('--do-updates',
        action='store_true',
        help="update any pre-existing release entities")
    sub_doaj_article.set_defaults(
        func=run_doaj_article,
        auth_var="FATCAT_AUTH_WORKER_DOAJ",
    )

    sub_dblp_release = subparsers.add_parser('dblp-release',
        help="import dblp release metadata")
    sub_dblp_release.add_argument('xml_file',
        help="File with DBLP XML to import from",
        default=sys.stdin, type=argparse.FileType('rb'))
    sub_dblp_release.add_argument('--dblp-container-map-file',
        help="file path to dblp prefix to container_id TSV file",
        default=None, type=argparse.FileType('r'))
    sub_dblp_release.add_argument('--do-updates',
        action='store_true',
        help="update any pre-existing release entities")
    sub_dblp_release.add_argument('--dump-json-mode',
        action='store_true',
        help="print release entities to stdout instead of importing")
    sub_dblp_release.set_defaults(
        func=run_dblp_release,
        auth_var="FATCAT_AUTH_WORKER_DBLP",
    )

    sub_dblp_container = subparsers.add_parser('dblp-container',
        help="import dblp container metadata")
    sub_dblp_container.add_argument('json_file',
        help="File with DBLP container JSON to import from (see extra/dblp/)",
        default=sys.stdin, type=argparse.FileType('rb'))
    sub_dblp_container.add_argument('--dblp-container-map-file',
        help="file path to dblp pre-existing prefix to container_id TSV file",
        default=None, type=argparse.FileType('r'))
    sub_dblp_container.add_argument('--dblp-container-map-output',
        help="file path to output new dblp container map TSV to",
        default=None, type=argparse.FileType('w'))
    sub_dblp_container.add_argument('--issn-map-file',
        help="ISSN to ISSN-L mapping file",
        default=None, type=argparse.FileType('r'))
    sub_dblp_container.add_argument('--do-updates',
        action='store_true',
        help="update any pre-existing container entities")
    sub_dblp_container.set_defaults(
        func=run_dblp_container,
        auth_var="FATCAT_AUTH_WORKER_DBLP",
    )

    sub_file_meta = subparsers.add_parser('file-meta',
        help="simple update-only importer for file metadata")
    sub_file_meta.set_defaults(
        func=run_file_meta,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_file_meta.add_argument('json_file',
        help="File with jsonlines from file_meta schema to import from",
        default=sys.stdin, type=argparse.FileType('r'))

    sub_fileset = subparsers.add_parser('fileset',
        help="generic fileset importer")
    sub_fileset.set_defaults(
        func=run_fileset,
        auth_var="FATCAT_API_AUTH_TOKEN",
    )
    sub_fileset.add_argument('json_file',
        help="File with jsonlines of fileset entities to import",
        default=sys.stdin, type=argparse.FileType('r'))
    sub_fileset.add_argument('--skip-release-fileset-check',
        action='store_true',
        help="create without checking if releases already have related filesets")

    args = parser.parse_args()
    if not args.__dict__.get("func"):
        print("tell me what to do!")
        sys.exit(-1)

    # allow editgroup description override via env variable (but CLI arg takes
    # precedence)
    if not args.editgroup_description_override \
            and os.environ.get('FATCAT_EDITGROUP_DESCRIPTION'):
        args.editgroup_description_override = os.environ.get('FATCAT_EDITGROUP_DESCRIPTION')

    args.api = authenticated_api(
        args.host_url,
        # token is an optional kwarg (can be empty string, None, etc)
        token=os.environ.get(args.auth_var))
    args.func(args)

if __name__ == '__main__':
    main()