aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_import.py
blob: 400b1915531926342bb8d8981ef09a34fa2fe2de (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
#!/usr/bin/env python3

import os, sys, argparse
from fatcat_tools import authenticated_api
from fatcat_tools.importers import *


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", 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:
        raise NotImplementedError
        #KafkaBs4XmlPusher(ari, args.kafka_hosts, args.kafka_env, "api-arxiv", "fatcat-import").run()
    else:
        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,
        lookup_refs=(not args.no_lookup_refs))
    if args.kafka_mode:
        raise NotImplementedError
        #KafkaBs4XmlPusher(pi, args.kafka_hosts, args.kafka_env, "api-pubmed", "fatcat-import").run()
    else:
        Bs4XmlLargeFilePusher(pi, args.xml_file, "PubmedArticle", record_list_tag="PubmedArticleSet").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)
    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,
        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,
        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", kafka_namespace="sandcrawler",
            consume_batch_size=args.batch_size).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_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 main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--debug',
        action='store_true',
        help="enable debugging interface")
    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')
    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')
    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')
    sub_arxiv.set_defaults(
        func=run_arxiv,
        auth_var="FATCAT_AUTH_WORKER_ARXIV",
    )
    sub_arxiv.add_argument('xml_file',
        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')
    sub_pubmed.set_defaults(
        func=run_pubmed,
        auth_var="FATCAT_AUTH_WORKER_PUBMED",
    )
    sub_pubmed.add_argument('xml_file',
        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('--kafka-mode',
        action='store_true',
        help="consume from kafka topic (not stdin)")

    sub_jstor = subparsers.add_parser('jstor')
    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')
    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')
    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')
    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_matched = subparsers.add_parser('matched')
    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')
    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="identifer 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-result')
    sub_ingest_file.set_defaults(
        func=run_ingest_file,
        auth_var="FATCAT_AUTH_WORKER_SANDCRAWLER",
    )
    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('--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_grobid_metadata = subparsers.add_parser('grobid-metadata')
    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_wayback_static = subparsers.add_parser('wayback-static')
    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')
    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)")

    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()