#10694: zipfile now ignores garbage at the end of a zipfile.
Original fix by 'rep', final patch (with tests) by Xuanji Li.
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
index c4a64a3..6cba26c 100644
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -335,6 +335,24 @@
with zipfile.ZipFile(f, "r") as zipfp:
self.assertEqual(zipfp.namelist(), [TESTFN])
+ def test_ignores_newline_at_end(self):
+ with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp:
+ zipfp.write(TESTFN, TESTFN)
+ with open(TESTFN2, 'a') as f:
+ f.write("\r\n\00\00\00")
+ with zipfile.ZipFile(TESTFN2, "r") as zipfp:
+ self.assertIsInstance(zipfp, zipfile.ZipFile)
+
+ def test_ignores_stuff_appended_past_comments(self):
+ with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp:
+ zipfp.comment = b"this is a comment"
+ zipfp.write(TESTFN, TESTFN)
+ with open(TESTFN2, 'a') as f:
+ f.write("abcdef\r\n")
+ with zipfile.ZipFile(TESTFN2, "r") as zipfp:
+ self.assertIsInstance(zipfp, zipfile.ZipFile)
+ self.assertEqual(zipfp.comment, b"this is a comment")
+
def test_write_default_name(self):
"""Check that calling ZipFile.write without arcname specified
produces the expected result."""
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
index 7e3caf0..f876f42 100644
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -236,16 +236,14 @@
# found the magic number; attempt to unpack and interpret
recData = data[start:start+sizeEndCentDir]
endrec = list(struct.unpack(structEndArchive, recData))
- comment = data[start+sizeEndCentDir:]
- # check that comment length is correct
- if endrec[_ECD_COMMENT_SIZE] == len(comment):
- # Append the archive comment and start offset
- endrec.append(comment)
- endrec.append(maxCommentStart + start)
+ commentSize = endrec[_ECD_COMMENT_SIZE] #as claimed by the zip file
+ comment = data[start+sizeEndCentDir:start+sizeEndCentDir+commentSize]
+ endrec.append(comment)
+ endrec.append(maxCommentStart + start)
- # Try to read the "Zip64 end of central directory" structure
- return _EndRecData64(fpin, maxCommentStart + start - filesize,
- endrec)
+ # Try to read the "Zip64 end of central directory" structure
+ return _EndRecData64(fpin, maxCommentStart + start - filesize,
+ endrec)
# Unable to find a valid end of central directory structure
return