Merge branch 'bnewbold-ingest-tweaks' into 'master'

ingest importer behavior tweaks

See merge request webgroup/fatcat!120

1 files changed, 33 insertions, 0 deletions

diff --git a/python/fatcat_import.py b/python/fatcat_import.py
index 1dcfec21..b82e81c7 100755
--- a/python/fatcat_import.py
+++ b/python/fatcat_import.py
@@ -159,6 +159,7 @@ def run_ingest_web(args):
             "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()
@@ -176,6 +177,25 @@ def run_savepapernow_file(args):
             "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()
@@ -554,6 +574,19 @@ def main():
         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_grobid_metadata = subparsers.add_parser('grobid-metadata',
         help="create release and file entities based on GROBID PDF metadata extraction")
     sub_grobid_metadata.set_defaults(