diff options
Diffstat (limited to 'python/fatcat_import.py')
| -rwxr-xr-x | python/fatcat_import.py | 74 |
1 files changed, 74 insertions, 0 deletions
diff --git a/python/fatcat_import.py b/python/fatcat_import.py index 6f331aaa..41a51ad4 100755 --- a/python/fatcat_import.py +++ b/python/fatcat_import.py @@ -164,6 +164,27 @@ def run_ingest_web(args): 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, @@ -200,6 +221,24 @@ def run_savepapernow_web(args): 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, @@ -569,6 +608,28 @@ def main(): 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( @@ -595,6 +656,19 @@ def main(): 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( |