aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_import.py
blob: de5b420201da38dbba09f0e6ff07cacd6a8777b3 (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
#!/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").run()
    else:
        JsonLinePusher(fci, args.json_file).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_matched(args):
    fmi = MatchedImporter(args.api,
        edit_batch_size=args.batch_size)
    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_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="qa",
        help="Kafka topic namespace to use (eg, prod, qa)")
    parser.add_argument('--batch-size',
        help="size of batch to send",
        default=50, type=int)
    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('--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_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_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('--bezerk-mode',
        action='store_true',
        help="don't lookup existing files, just insert (clobbers; only for fast bootstrap)")

    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_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)

    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()