aboutsummaryrefslogtreecommitdiffstats
path: root/python/persist_tool.py
blob: e08d66ce21b76eb37a5cd3bd2f0b2f818a9f1da6 (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
#!/usr/bin/env python3
"""
Commands for backfilling content from bulk files into postgresql and s3 (seaweedfs).

Normally this is done by workers (in sandcrawler_worker.py) consuming from
Kafka feeds, but sometimes we have bulk processing output we want to backfill.
"""

import argparse
import os
import sys

from sandcrawler import *
from sandcrawler.persist import *


def run_cdx(args):
    worker = PersistCdxWorker(
        db_url=args.db_url,
    )
    filter_mimetypes = ["application/pdf"]
    if args.no_mimetype_filter:
        filter_mimetypes = None
    pusher = CdxLinePusher(
        worker,
        args.cdx_file,
        filter_http_statuses=[200, 226],
        filter_mimetypes=filter_mimetypes,
        # allow_octet_stream
        batch_size=200,
    )
    pusher.run()


def run_grobid(args):
    worker = PersistGrobidWorker(
        db_url=args.db_url,
        s3_url=args.s3_url,
        s3_bucket=args.s3_bucket,
        s3_access_key=args.s3_access_key,
        s3_secret_key=args.s3_secret_key,
        s3_only=args.s3_only,
        db_only=args.db_only,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=50,
    )
    pusher.run()


def run_grobid_disk(args):
    """
    Writes XML to individual files on disk, and also prints non-XML metadata to
    stdout as JSON, which can be redirected to a separate file.
    """
    worker = PersistGrobidDiskWorker(
        output_dir=args.output_dir,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
    )
    pusher.run()


def run_pdftrio(args):
    worker = PersistPdfTrioWorker(
        db_url=args.db_url,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=100,
    )
    pusher.run()


def run_pdftext(args):
    worker = PersistPdfTextWorker(
        db_url=args.db_url,
        s3_url=args.s3_url,
        s3_bucket=args.s3_bucket,
        s3_access_key=args.s3_access_key,
        s3_secret_key=args.s3_secret_key,
        s3_only=args.s3_only,
        db_only=args.db_only,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=50,
    )
    pusher.run()


def run_ingest_file_result(args):
    worker = PersistIngestFileResultWorker(
        db_url=args.db_url,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=200,
    )
    pusher.run()


def run_ingest_request(args):
    worker = PersistIngestRequestWorker(
        db_url=args.db_url,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=200,
    )
    pusher.run()


def run_crossref(args):
    batch_size = 200
    if args.parse_refs:
        batch_size = 10
    grobid_client = GrobidClient(
        host_url=args.grobid_host,
    )
    worker = PersistCrossrefWorker(
        db_url=args.db_url,
        grobid_client=grobid_client,
        parse_refs=args.parse_refs,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=batch_size,
    )
    pusher.run()


def run_grobid_refs(args):
    worker = PersistGrobidRefsWorker(
        db_url=args.db_url,
    )
    pusher = JsonLinePusher(
        worker,
        args.json_file,
        batch_size=100,
    )
    pusher.run()


def main():
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument(
        "--db-url",
        help="postgresql database connection string",
        default="postgres:///sandcrawler",
    )
    parser.add_argument("--s3-url", help="S3 (seaweedfs) backend URL", default="localhost:9000")
    parser.add_argument(
        "--s3-access-key",
        help="S3 (seaweedfs) credential",
        default=os.environ.get("SANDCRAWLER_BLOB_ACCESS_KEY")
        or os.environ.get("MINIO_ACCESS_KEY"),
    )
    parser.add_argument(
        "--s3-secret-key",
        help="S3 (seaweedfs) credential",
        default=os.environ.get("SANDCRAWLER_BLOB_ACCESS_KEY")
        or os.environ.get("MINIO_SECRET_KEY"),
    )
    parser.add_argument(
        "--s3-bucket", help="S3 (seaweedfs) bucket to persist into", default="sandcrawler-dev"
    )
    subparsers = parser.add_subparsers()

    sub_cdx = subparsers.add_parser("cdx", help="backfill a CDX file into postgresql cdx table")
    sub_cdx.set_defaults(func=run_cdx)
    sub_cdx.add_argument(
        "cdx_file",
        help="CDX file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )
    sub_cdx.add_argument(
        "--no-mimetype-filter",
        action="store_true",
        help="ignore mimetype filtering; insert all content types (eg, assuming pre-filtered)",
    )

    sub_grobid = subparsers.add_parser(
        "grobid", help="backfill a grobid JSON ('pg') dump into postgresql and s3 (seaweedfs)"
    )
    sub_grobid.set_defaults(func=run_grobid)
    sub_grobid.add_argument(
        "json_file",
        help="grobid file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )
    sub_grobid.add_argument(
        "--s3-only",
        action="store_true",
        help="only upload TEI-XML to S3 (don't write to database)",
    )
    sub_grobid.add_argument(
        "--db-only",
        action="store_true",
        help="only write status to sandcrawler-db (don't save TEI-XML to S3)",
    )

    sub_pdftext = subparsers.add_parser(
        "pdftext", help="backfill a pdftext JSON ('pg') dump into postgresql and s3 (seaweedfs)"
    )
    sub_pdftext.set_defaults(func=run_pdftext)
    sub_pdftext.add_argument(
        "json_file",
        help="pdftext file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )
    sub_pdftext.add_argument(
        "--s3-only",
        action="store_true",
        help="only upload TEI-XML to S3 (don't write to database)",
    )
    sub_pdftext.add_argument(
        "--db-only",
        action="store_true",
        help="only write status to sandcrawler-db (don't save TEI-XML to S3)",
    )

    sub_grobid_disk = subparsers.add_parser(
        "grobid-disk", help="dump GRBOID output to (local) files on disk"
    )
    sub_grobid_disk.set_defaults(func=run_grobid_disk)
    sub_grobid_disk.add_argument(
        "json_file",
        help="grobid file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )
    sub_grobid_disk.add_argument("output_dir", help="base directory to output into", type=str)

    sub_pdftrio = subparsers.add_parser(
        "pdftrio", help="backfill a pdftrio JSON ('pg') dump into postgresql and s3 (seaweedfs)"
    )
    sub_pdftrio.set_defaults(func=run_pdftrio)
    sub_pdftrio.add_argument(
        "json_file",
        help="pdftrio file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )

    sub_ingest_file_result = subparsers.add_parser(
        "ingest-file-result", help="backfill a ingest_file_result JSON dump into postgresql"
    )
    sub_ingest_file_result.set_defaults(func=run_ingest_file_result)
    sub_ingest_file_result.add_argument(
        "json_file",
        help="ingest_file_result file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )

    sub_ingest_request = subparsers.add_parser(
        "ingest-request", help="backfill a ingest_request JSON dump into postgresql"
    )
    sub_ingest_request.set_defaults(func=run_ingest_request)
    sub_ingest_request.add_argument(
        "json_file",
        help="ingest_request to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )

    sub_crossref = subparsers.add_parser(
        "crossref",
        help="backfill a crossref JSON dump into postgresql, and extract references at the same time",
    )
    sub_crossref.set_defaults(func=run_crossref)
    sub_crossref.add_argument(
        "json_file",
        help="crossref file to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )
    sub_crossref.add_argument(
        "--grobid-host", default="https://grobid.qa.fatcat.wiki", help="GROBID API host/port"
    )
    sub_crossref.add_argument(
        "--parse-refs",
        action="store_true",
        help="use GROBID to parse any unstructured references (default is to not)",
    )

    sub_grobid_refs = subparsers.add_parser(
        "grobid-refs", help="backfill a grobid_refs JSON dump into postgresql"
    )
    sub_grobid_refs.set_defaults(func=run_grobid_refs)
    sub_grobid_refs.add_argument(
        "json_file",
        help="grobid_refs to import from (or '-' for stdin)",
        type=argparse.FileType("r"),
    )

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

    args.func(args)


if __name__ == "__main__":
    main()