From 826c7538e091fac14d987a3cd654975da964e240 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Wed, 27 Oct 2021 18:50:17 -0700
Subject: make fmt (black 21.9b0)

---
 python/ingest_tool.py | 85 +++++++++++++++++++++++++++++----------------------
 1 file changed, 49 insertions(+), 36 deletions(-)

(limited to 'python/ingest_tool.py')

diff --git a/python/ingest_tool.py b/python/ingest_tool.py
index eb1047d..7405d28 100755
--- a/python/ingest_tool.py
+++ b/python/ingest_tool.py
@@ -17,9 +17,9 @@ def run_single_ingest(args):
         fatcat=dict(release_ident=args.release_id),
     )
     if args.force_recrawl:
-        request['force_recrawl'] = True
-    if request['ingest_type'] in [
-            'dataset',
+        request["force_recrawl"] = True
+    if request["ingest_type"] in [
+        "dataset",
     ]:
         ingester = IngestFilesetWorker(
             try_spn2=not args.no_spn2,
@@ -41,11 +41,13 @@ def run_requests(args):
         try_spn2=not args.no_spn2,
         html_quick_mode=args.html_quick_mode,
     )
-    fileset_worker = IngestFilesetWorker(try_spn2=not args.no_spn2, )
+    fileset_worker = IngestFilesetWorker(
+        try_spn2=not args.no_spn2,
+    )
     for line in args.json_file:
         request = json.loads(line.strip())
-        if request['ingest_type'] in [
-                'dataset',
+        if request["ingest_type"] in [
+            "dataset",
         ]:
             result = fileset_worker.process(request)
         else:
@@ -56,7 +58,7 @@ def run_requests(args):
 def run_api(args):
     port = 8083
     print("Listening on localhost:{}".format(port))
-    server = HTTPServer(('', port), IngestFileRequestHandler)
+    server = HTTPServer(("", port), IngestFileRequestHandler)
     server.serve_forever()
 
 
@@ -64,41 +66,52 @@ def main():
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     subparsers = parser.add_subparsers()
 
-    sub_single = subparsers.add_parser('single', help="ingests a single base URL")
+    sub_single = subparsers.add_parser("single", help="ingests a single base URL")
     sub_single.set_defaults(func=run_single_ingest)
-    sub_single.add_argument('ingest_type',
-                            default="pdf",
-                            help="type of ingest (pdf, html, etc)")
-    sub_single.add_argument('--release-id',
-                            help="(optional) existing release ident to match to")
-    sub_single.add_argument('--doi', help="(optional) existing release DOI to match to")
-    sub_single.add_argument('--force-recrawl',
-                            action='store_true',
-                            help="ignore GWB history and use SPNv2 to re-crawl")
-    sub_single.add_argument('--no-spn2', action='store_true', help="don't use live web (SPNv2)")
-    sub_single.add_argument('--html-quick-mode',
-                            action='store_true',
-                            help="don't fetch individual sub-resources, just use CDX")
-    sub_single.add_argument('url', help="URL of paper to fetch")
+    sub_single.add_argument(
+        "ingest_type", default="pdf", help="type of ingest (pdf, html, etc)"
+    )
+    sub_single.add_argument(
+        "--release-id", help="(optional) existing release ident to match to"
+    )
+    sub_single.add_argument("--doi", help="(optional) existing release DOI to match to")
+    sub_single.add_argument(
+        "--force-recrawl",
+        action="store_true",
+        help="ignore GWB history and use SPNv2 to re-crawl",
+    )
+    sub_single.add_argument("--no-spn2", action="store_true", help="don't use live web (SPNv2)")
+    sub_single.add_argument(
+        "--html-quick-mode",
+        action="store_true",
+        help="don't fetch individual sub-resources, just use CDX",
+    )
+    sub_single.add_argument("url", help="URL of paper to fetch")
 
     sub_requests = subparsers.add_parser(
-        'requests', help="takes a series of ingest requests (JSON, per line) and runs each")
-    sub_requests.add_argument('--no-spn2',
-                              action='store_true',
-                              help="don't use live web (SPNv2)")
-    sub_requests.add_argument('--html-quick-mode',
-                              action='store_true',
-                              help="don't fetch individual sub-resources, just use CDX")
+        "requests", help="takes a series of ingest requests (JSON, per line) and runs each"
+    )
+    sub_requests.add_argument(
+        "--no-spn2", action="store_true", help="don't use live web (SPNv2)"
+    )
+    sub_requests.add_argument(
+        "--html-quick-mode",
+        action="store_true",
+        help="don't fetch individual sub-resources, just use CDX",
+    )
     sub_requests.set_defaults(func=run_requests)
-    sub_requests.add_argument('json_file',
-                              help="JSON file (request per line) to import from (or stdin)",
-                              default=sys.stdin,
-                              type=argparse.FileType('r'))
+    sub_requests.add_argument(
+        "json_file",
+        help="JSON file (request per line) to import from (or stdin)",
+        default=sys.stdin,
+        type=argparse.FileType("r"),
+    )
 
     sub_api = subparsers.add_parser(
-        'api', help="starts a simple HTTP server that processes ingest requests")
+        "api", help="starts a simple HTTP server that processes ingest requests"
+    )
     sub_api.set_defaults(func=run_api)
-    sub_api.add_argument('--port', help="HTTP port to listen on", default=8033, type=int)
+    sub_api.add_argument("--port", help="HTTP port to listen on", default=8033, type=int)
 
     args = parser.parse_args()
     if not args.__dict__.get("func"):
@@ -108,5 +121,5 @@ def main():
     args.func(args)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()
-- 
cgit v1.2.3