gh-75707: tarfile: Add optional open() argument "mtime" (GH-138117)

This makes it possible to set the gzip header mtime field without
overriding time.time(), making it useful when creating reproducible
archives.

* 📜🤖 Added by blurb_it.

---------

Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
Co-authored-by: Ethan Furman <ethan@stoneleaf.us>

diff --git a/Doc/library/tarfile.rst b/Doc/library/tarfile.rst
index a86469bb9ad70419ffa97f06113833dcc0cf57b7..6f1e01cf5aa6ee95aa28241c6b49dc1251b32d72 100644 (file)
--- a/Doc/library/tarfile.rst
+++ b/Doc/library/tarfile.rst
@@ -142,6 +142,10 @@ Some facts and figures:
    a Zstandard dictionary used to improve compression of smaller amounts of
    data.
 
+   For modes ``'w:gz'`` and ``'w|gz'``, :func:`tarfile.open` accepts the
+   keyword argument *mtime* to create a gzip archive header with that mtime. By
+   default, the mtime is set to the time of creation of the archive.
+
    For special purposes, there is a second format for *mode*:
    ``'filemode|[compression]'``.  :func:`tarfile.open` will return a :class:`TarFile`
    object that processes its data as a stream of blocks.  No random seeking will

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 7f0b0b3c63257324f0285d5f98e1189ae58295a0..4f47aaab9028d0fc4e7f896ce695bfecf12e4c08 100644 (file)
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -337,7 +337,7 @@ class _Stream:
     """
 
     def __init__(self, name, mode, comptype, fileobj, bufsize,
-                 compresslevel, preset):
+                 compresslevel, preset, mtime):
         """Construct a _Stream object.
         """
         self._extfileobj = True
@@ -372,7 +372,7 @@ class _Stream:
                     self.exception = zlib.error
                     self._init_read_gz()
                 else:
-                    self._init_write_gz(compresslevel)
+                    self._init_write_gz(compresslevel, mtime)
 
             elif comptype == "bz2":
                 try:
@@ -421,7 +421,7 @@ class _Stream:
         if hasattr(self, "closed") and not self.closed:
             self.close()
 
-    def _init_write_gz(self, compresslevel):
+    def _init_write_gz(self, compresslevel, mtime):
         """Initialize for writing with gzip compression.
         """
         self.cmp = self.zlib.compressobj(compresslevel,
@@ -429,7 +429,9 @@ class _Stream:
                                          -self.zlib.MAX_WBITS,
                                          self.zlib.DEF_MEM_LEVEL,
                                          0)
-        timestamp = struct.pack("<L", int(time.time()))
+        if mtime is None:
+            mtime = int(time.time())
+        timestamp = struct.pack("<L", mtime)
         self.__write(b"\037\213\010\010" + timestamp + b"\002\377")
         if self.name.endswith(".gz"):
             self.name = self.name[:-3]
@@ -1745,7 +1747,7 @@ class TarFile(object):
     def __init__(self, name=None, mode="r", fileobj=None, format=None,
             tarinfo=None, dereference=None, ignore_zeros=None, encoding=None,
             errors="surrogateescape", pax_headers=None, debug=None,
-            errorlevel=None, copybufsize=None, stream=False):
+            errorlevel=None, copybufsize=None, stream=False, mtime=None):
         """Open an (uncompressed) tar archive 'name'. 'mode' is either 'r' to
            read from an existing archive, 'a' to append data to an existing
            file or 'w' to create a new file overwriting an existing one. 'mode'
@@ -1951,8 +1953,9 @@ class TarFile(object):
 
             compresslevel = kwargs.pop("compresslevel", 6)
             preset = kwargs.pop("preset", None)
+            mtime = kwargs.pop("mtime", None)
             stream = _Stream(name, filemode, comptype, fileobj, bufsize,
-                             compresslevel, preset)
+                             compresslevel, preset, mtime)
             try:
                 t = cls(name, filemode, stream, **kwargs)
             except:
@@ -1988,7 +1991,8 @@ class TarFile(object):
             raise CompressionError("gzip module is not available") from None
 
         try:
-            fileobj = GzipFile(name, mode + "b", compresslevel, fileobj)
+            mtime = kwargs.pop("mtime", None)
+            fileobj = GzipFile(name, mode + "b", compresslevel, fileobj, mtime=mtime)
         except OSError as e:
             if fileobj is not None and mode == 'r':
                 raise ReadError("not a gzip file") from e

diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index f2babaacc27d966da394cf7442419a2b0ff1be5a..e270cbb22e2d1a93c20a0606ce408eab2c637e81 100644 (file)
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -10,6 +10,7 @@ import shutil
 import re
 import warnings
 import stat
+import time
 
 import unittest
 import unittest.mock
@@ -1828,6 +1829,19 @@ class GzipStreamWriteTest(GzipTest, StreamWriteTest):
         payload = pathlib.Path(tmpname).read_text(encoding='latin-1')
         assert os.path.dirname(tmpname) not in payload
 
+    def test_create_with_mtime(self):
+        tarfile.open(tmpname, self.mode, mtime=0).close()
+        with self.open(tmpname, 'r') as fobj:
+            fobj.read()
+            self.assertEqual(fobj.mtime, 0)
+
+    def test_create_without_mtime(self):
+        before = int(time.time())
+        tarfile.open(tmpname, self.mode).close()
+        after = int(time.time())
+        with self.open(tmpname, 'r') as fobj:
+            fobj.read()
+            self.assertTrue(before <= fobj.mtime <= after)
 
 class Bz2StreamWriteTest(Bz2Test, StreamWriteTest):
     decompressor = bz2.BZ2Decompressor if bz2 else None
@@ -2134,6 +2148,19 @@ class GzipCreateTest(GzipTest, CreateTest):
         with tarfile.open(tmpname, 'r:gz', compresslevel=1) as tobj:
             pass
 
+    def test_create_with_mtime(self):
+        tarfile.open(tmpname, self.mode, mtime=0).close()
+        with self.open(tmpname, 'rb') as fobj:
+            fobj.read()
+            self.assertEqual(fobj.mtime, 0)
+
+    def test_create_without_mtime(self):
+        before = int(time.time())
+        tarfile.open(tmpname, self.mode).close()
+        after = int(time.time())
+        with self.open(tmpname, 'r') as fobj:
+            fobj.read()
+            self.assertTrue(before <= fobj.mtime <= after)
 
 class Bz2CreateTest(Bz2Test, CreateTest):
 

diff --git a/Misc/NEWS.d/next/Library/2025-08-24-15-09-30.gh-issue-75707.GOWZrC.rst b/Misc/NEWS.d/next/Library/2025-08-24-15-09-30.gh-issue-75707.GOWZrC.rst
new file mode 100644 (file)
index 0000000..b2ff8a0
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2025-08-24-15-09-30.gh-issue-75707.GOWZrC.rst
@@ -0,0 +1 @@
+Add optional ``mtime`` argument to :func:`tarfile.open`, for setting the ``mtime`` header field in ``.tar.gz`` archives.