From 05bd7cbcc62588e431c5efd533189e246b2a997e Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 26 Oct 2021 12:54:37 -0700
Subject: make fmt

---
 python/grobid_tool.py | 64 +++++++++++++++++++++++++++------------------------
 1 file changed, 34 insertions(+), 30 deletions(-)

(limited to 'python/grobid_tool.py')

diff --git a/python/grobid_tool.py b/python/grobid_tool.py
index 0084330..4ba9540 100755
--- a/python/grobid_tool.py
+++ b/python/grobid_tool.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-
 """
 These are generally for running one-off tasks from the command line. Output
 might go to stdout, or might go to Kafka topic.
@@ -30,6 +29,7 @@ def run_extract_json(args):
         pusher = JsonLinePusher(worker, args.json_file)
     pusher.run()
 
+
 def run_extract_cdx(args):
     grobid_client = GrobidClient(host_url=args.grobid_host)
     wayback_client = WaybackClient()
@@ -53,6 +53,7 @@ def run_extract_cdx(args):
         )
     pusher.run()
 
+
 def run_extract_zipfile(args):
     grobid_client = GrobidClient(host_url=args.grobid_host)
     if args.jobs > 1:
@@ -65,6 +66,7 @@ def run_extract_zipfile(args):
         pusher = ZipfilePusher(worker, args.zip_file)
     pusher.run()
 
+
 def run_transform(args):
     grobid_client = GrobidClient()
     for line in args.json_file:
@@ -82,52 +84,54 @@ def run_transform(args):
 
 
 def main():
-    parser = argparse.ArgumentParser(
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument('--kafka-mode',
-        action='store_true',
-        help="send output to Kafka (not stdout)")
+                        action='store_true',
+                        help="send output to Kafka (not stdout)")
     parser.add_argument('--kafka-hosts',
-        default="localhost:9092",
-        help="list of Kafka brokers (host/port) to use")
+                        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, dev)")
-    parser.add_argument('-j', '--jobs',
-        default=8, type=int,
-        help="parallelism for batch CPU jobs")
+                        default="dev",
+                        help="Kafka topic namespace to use (eg, prod, qa, dev)")
+    parser.add_argument('-j',
+                        '--jobs',
+                        default=8,
+                        type=int,
+                        help="parallelism for batch CPU jobs")
     parser.add_argument('--grobid-host',
-        default="http://grobid.qa.fatcat.wiki",
-        help="GROBID API host/port")
+                        default="http://grobid.qa.fatcat.wiki",
+                        help="GROBID API host/port")
     subparsers = parser.add_subparsers()
 
-    sub_extract_json = subparsers.add_parser('extract-json',
+    sub_extract_json = subparsers.add_parser(
+        'extract-json',
         help="for each JSON line with CDX info, fetches PDF and does GROBID extraction")
     sub_extract_json.set_defaults(func=run_extract_json)
     sub_extract_json.add_argument('json_file',
-        help="JSON file to import from (or '-' for stdin)",
-        type=argparse.FileType('r'))
+                                  help="JSON file to import from (or '-' for stdin)",
+                                  type=argparse.FileType('r'))
 
-    sub_extract_cdx = subparsers.add_parser('extract-cdx',
-        help="for each CDX line, fetches PDF and does GROBID extraction")
+    sub_extract_cdx = subparsers.add_parser(
+        'extract-cdx', help="for each CDX line, fetches PDF and does GROBID extraction")
     sub_extract_cdx.set_defaults(func=run_extract_cdx)
     sub_extract_cdx.add_argument('cdx_file',
-        help="CDX file to import from (or '-' for stdin)",
-        type=argparse.FileType('r'))
+                                 help="CDX file to import from (or '-' for stdin)",
+                                 type=argparse.FileType('r'))
 
-    sub_extract_zipfile = subparsers.add_parser('extract-zipfile',
+    sub_extract_zipfile = subparsers.add_parser(
+        'extract-zipfile',
         help="opens zipfile, iterates over PDF files inside and does GROBID extract for each")
     sub_extract_zipfile.set_defaults(func=run_extract_zipfile)
-    sub_extract_zipfile.add_argument('zip_file',
-        help="zipfile with PDFs to extract",
-        type=str)
+    sub_extract_zipfile.add_argument('zip_file', help="zipfile with PDFs to extract", type=str)
 
     sub_transform = subparsers.add_parser('transform')
     sub_transform.set_defaults(func=run_transform)
     sub_transform.add_argument('--metadata-only',
-        action='store_true',
-        help="Only pass through bibliographic metadata, not fulltext")
-    sub_transform.add_argument('json_file',
+                               action='store_true',
+                               help="Only pass through bibliographic metadata, not fulltext")
+    sub_transform.add_argument(
+        'json_file',
         help="convert TEI-XML to JSON. Input is JSON lines with tei_xml field",
         type=argparse.FileType('r'))
 
@@ -140,10 +144,10 @@ def main():
     if args.kafka_mode:
         produce_topic = "sandcrawler-{}.grobid-output-pg".format(args.kafka_env)
         print("Running in kafka output mode, publishing to {}\n".format(produce_topic))
-        args.sink = KafkaCompressSink(kafka_hosts=args.kafka_hosts,
-            produce_topic=produce_topic)
+        args.sink = KafkaCompressSink(kafka_hosts=args.kafka_hosts, produce_topic=produce_topic)
 
     args.func(args)
 
+
 if __name__ == '__main__':
     main()
-- 
cgit v1.2.3