Skip to content

[3.8] bpo-39389: gzip: fix compression level metadata (GH-18077) #18100

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 21, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions Lib/gzip.py
Original file line number Diff line number Diff line change
Expand Up @@ -201,7 +201,7 @@ def __init__(self, filename=None, mode=None,
self.fileobj = fileobj

if self.mode == WRITE:
self._write_gzip_header()
self._write_gzip_header(compresslevel)

@property
def filename(self):
Expand All @@ -228,7 +228,7 @@ def _init_write(self, filename):
self.bufsize = 0
self.offset = 0 # Current file offset for seek(), tell(), etc

def _write_gzip_header(self):
def _write_gzip_header(self, compresslevel):
self.fileobj.write(b'\037\213') # magic header
self.fileobj.write(b'\010') # compression method
try:
Expand All @@ -249,7 +249,13 @@ def _write_gzip_header(self):
if mtime is None:
mtime = time.time()
write32u(self.fileobj, int(mtime))
self.fileobj.write(b'\002')
if compresslevel == _COMPRESS_LEVEL_BEST:
xfl = b'\002'
elif compresslevel == _COMPRESS_LEVEL_FAST:
xfl = b'\004'
else:
xfl = b'\000'
self.fileobj.write(xfl)
self.fileobj.write(b'\377')
if fname:
self.fileobj.write(fname + b'\000')
Expand Down
20 changes: 20 additions & 0 deletions Lib/test/test_gzip.py
Original file line number Diff line number Diff line change
Expand Up @@ -358,6 +358,26 @@ def test_metadata(self):
isizeBytes = fRead.read(4)
self.assertEqual(isizeBytes, struct.pack('<i', len(data1)))

def test_compresslevel_metadata(self):
# see RFC 1952: http://www.faqs.org/rfcs/rfc1952.html
# specifically, discussion of XFL in section 2.3.1
cases = [
('fast', 1, b'\x04'),
('best', 9, b'\x02'),
('tradeoff', 6, b'\x00'),
]
xflOffset = 8

for (name, level, expectedXflByte) in cases:
with self.subTest(name):
fWrite = gzip.GzipFile(self.filename, 'w', compresslevel=level)
with fWrite:
fWrite.write(data1)
with open(self.filename, 'rb') as fRead:
fRead.seek(xflOffset)
xflByte = fRead.read(1)
self.assertEqual(xflByte, expectedXflByte)

def test_with_open(self):
# GzipFile supports the context management protocol
with gzip.GzipFile(self.filename, "wb") as f:
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Write accurate compression level metadata in :mod:`gzip` archives, rather
than always signaling maximum compression.