[3.13] gh-112346: Always set OS byte to 255, simpler gzip.compress function. (GH...

gh-112346: Always set OS byte to 255, simpler gzip.compress function. (GH-120486)

This matches the output behavior in 3.10 and earlier; the optimization in 3.11 allowed the zlib library's "os" value to be filled in instead in the circumstance when mtime was 0.  this keeps things consistent.
(cherry picked from commit 08d09cf5ba041c9c5c3860200b56bab66fd44a23)

Co-authored-by: Ruben Vorderman <r.h.p.vorderman@lumc.nl>

diff --git a/Doc/library/gzip.rst b/Doc/library/gzip.rst
index 965da5981f6dbcc23aa353bedd9984fe37e2f4de..152cba4f653cb4eac292abbda7d0b7248afa0316 100644 (file)
--- a/Doc/library/gzip.rst
+++ b/Doc/library/gzip.rst
@@ -188,9 +188,7 @@ The module defines the following items:
 
    Compress the *data*, returning a :class:`bytes` object containing
    the compressed data.  *compresslevel* and *mtime* have the same meaning as in
-   the :class:`GzipFile` constructor above. When *mtime* is set to ``0``, this
-   function is equivalent to :func:`zlib.compress` with *wbits* set to ``31``.
-   The zlib function is faster.
+   the :class:`GzipFile` constructor above.
 
    .. versionadded:: 3.2
    .. versionchanged:: 3.8
@@ -200,6 +198,10 @@ The module defines the following items:
       streamed fashion. Calls with *mtime* set to ``0`` are delegated to
       :func:`zlib.compress` for better speed.
 
+   .. versionchanged:: 3.13
+      The gzip header OS byte is guaranteed to be set to 255 when this function
+      is used as was the case in 3.10 and earlier.
+
 .. function:: decompress(data)
 
    Decompress the *data*, returning a :class:`bytes` object containing the

diff --git a/Lib/gzip.py b/Lib/gzip.py
index 0d19c84c59cfa703fc92f5138b095c5f29461426..ba753ce3050dd84982332faba369ac14ee4f45e9 100644 (file)
--- a/Lib/gzip.py
+++ b/Lib/gzip.py
@@ -580,27 +580,6 @@ class _GzipReader(_compression.DecompressReader):
         self._new_member = True
 
 
-def _create_simple_gzip_header(compresslevel: int,
-                               mtime = None) -> bytes:
-    """
-    Write a simple gzip header with no extra fields.
-    :param compresslevel: Compresslevel used to determine the xfl bytes.
-    :param mtime: The mtime (must support conversion to a 32-bit integer).
-    :return: A bytes object representing the gzip header.
-    """
-    if mtime is None:
-        mtime = time.time()
-    if compresslevel == _COMPRESS_LEVEL_BEST:
-        xfl = 2
-    elif compresslevel == _COMPRESS_LEVEL_FAST:
-        xfl = 4
-    else:
-        xfl = 0
-    # Pack ID1 and ID2 magic bytes, method (8=deflate), header flags (no extra
-    # fields added to header), mtime, xfl and os (255 for unknown OS).
-    return struct.pack("<BBBBLBB", 0x1f, 0x8b, 8, 0, int(mtime), xfl, 255)
-
-
 def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=None):
     """Compress data in one shot and return the compressed string.
 
@@ -608,15 +587,14 @@ def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=None):
     mtime can be used to set the modification time. The modification time is
     set to the current time by default.
     """
-    if mtime == 0:
-        # Use zlib as it creates the header with 0 mtime by default.
-        # This is faster and with less overhead.
-        return zlib.compress(data, level=compresslevel, wbits=31)
-    header = _create_simple_gzip_header(compresslevel, mtime)
-    trailer = struct.pack("<LL", zlib.crc32(data), (len(data) & 0xffffffff))
-    # Wbits=-15 creates a raw deflate block.
-    return (header + zlib.compress(data, level=compresslevel, wbits=-15) +
-            trailer)
+    # Wbits=31 automatically includes a gzip header and trailer.
+    gzip_data = zlib.compress(data, level=compresslevel, wbits=31)
+    if mtime is None:
+        mtime = time.time()
+    # Reuse gzip header created by zlib, replace mtime and OS byte for
+    # consistency.
+    header = struct.pack("<4sLBB", gzip_data, int(mtime), gzip_data[8], 255)
+    return header + gzip_data[10:]
 
 
 def decompress(data):

diff --git a/Lib/test/test_gzip.py b/Lib/test/test_gzip.py
index cf801278da9e9bdbe9f95ae7d4e421ae908ca3ba..ae384c3849d49eb789882bc602596e4e26570d15 100644 (file)
--- a/Lib/test/test_gzip.py
+++ b/Lib/test/test_gzip.py
@@ -714,7 +714,6 @@ class TestGzip(BaseTest):
                         self.assertEqual(f.mtime, mtime)
 
     def test_compress_correct_level(self):
-        # gzip.compress calls with mtime == 0 take a different code path.
         for mtime in (0, 42):
             with self.subTest(mtime=mtime):
                 nocompress = gzip.compress(data1, compresslevel=0, mtime=mtime)
@@ -722,6 +721,17 @@ class TestGzip(BaseTest):
                 self.assertIn(data1, nocompress)
                 self.assertNotIn(data1, yescompress)
 
+    def test_issue112346(self):
+        # The OS byte should be 255, this should not change between Python versions.
+        for mtime in (0, 42):
+            with self.subTest(mtime=mtime):
+                compress = gzip.compress(data1, compresslevel=1, mtime=mtime)
+                self.assertEqual(
+                    struct.unpack("<IxB", compress[4:10]),
+                    (mtime, 255),
+                    "Gzip header does not properly set either mtime or OS byte."
+                )
+
     def test_decompress(self):
         for data in (data1, data2):
             buf = io.BytesIO()

diff --git a/Misc/NEWS.d/next/Library/2024-06-12-10-00-31.gh-issue-90425.5CfkKG.rst b/Misc/NEWS.d/next/Library/2024-06-12-10-00-31.gh-issue-90425.5CfkKG.rst
new file mode 100644 (file)
index 0000000..d152af4
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-06-12-10-00-31.gh-issue-90425.5CfkKG.rst
@@ -0,0 +1,2 @@
+The OS byte in gzip headers is now always set to 255 when using
+:func:`gzip.compress`.