From 376cde7b8cf308eee8a67fc9035a006a4d405c30 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Mon, 29 Jul 2019 14:52:21 +0000 Subject: [PATCH] Fix broken block digest calculation on malformed HTTP responses --- warc-tiny | 1 + 1 file changed, 1 insertion(+) diff --git a/warc-tiny b/warc-tiny index 01928f8..68d6f20 100755 --- a/warc-tiny +++ b/warc-tiny @@ -179,6 +179,7 @@ def iter_warc(f): yield HTTPResponseBodyChunk(httpDecompressor.decompress(httpBody)) else: print('Warning: malformed HTTP response in record {}, skipping'.format(recordID), file = sys.stderr) + yield WARCBlockChunk(warcContent) else: yield WARCBlockChunk(warcContent) yield EndOfRecord()