feat: allow disable of extended timestamps

docs/advanced-usage.md

@@ -22,3 +22,15 @@ for zipped_chunk in stream_zip(unzipped_files(), chunk_size=65536):
 This one size is used both for input - splitting or gathering any uncompressed data into `chunk_size` bytes before attempting to compress it, and in output - splitting or gathering any compressed data into `chunk_size` bytes before returning it to client code.
 
 There may be performance differences with a different `chunk_size` values. The default chunk_size may not be optimal for your use case.
+
+
+## Without extended timestamps
+
+By default so-called extended timestamps are included in the ZIP, which store the modification time of member files more accurately than the original ZIP format allows. To omit the extended timestamps, you can pass `extended_timestamps=False` to `stream_zip`.
+
+```python
+for zipped_chunk in stream_zip(unzipped_files(), extended_timestamps=False):
+    print(zipped_chunk)
+```
+
+This is useful to keep the total number of bytes down as much as possible. This is also useful when creating Open Document files using `stream_zip`. Open Document files cannot have extended timestamps in their member files if they are to pass validation.

stream_zip.py

@@ -41,7 +41,7 @@ def method_compressobj(offset, default_get_compressobj):
     return method_compressobj
 
 
-def stream_zip(files, chunk_size=65536, get_compressobj=lambda: zlib.compressobj(wbits=-zlib.MAX_WBITS, level=9)):
+def stream_zip(files, chunk_size=65536, get_compressobj=lambda: zlib.compressobj(wbits=-zlib.MAX_WBITS, level=9), extended_timestamps=True):
 
     def evenly_sized(chunks):
         chunk = b''
@@ -398,7 +398,7 @@ def _chunks():
                 5,        # Size of extra
                 b'\x01',  # Only modification time (as opposed to also other times)
                 int(modified_at.timestamp()),
-            )
+            ) if extended_timestamps else b''
             external_attr = \
                 (mode << 16) | \
                 (0x10 if name_encoded[-1:] == b'/' else 0x0)  # MS-DOS directory

test_stream_zip.py

@@ -984,3 +984,37 @@ def test_unzip_modification_time(method, timezone, modified_at):
         subprocess.run(['unzip', f'{d}/test.zip', '-d', d], env={'TZ': timezone})
 
         assert os.path.getmtime('my_file') == int(modified_at.timestamp())
+
+
+@pytest.mark.parametrize(
+    "method",
+    [
+        ZIP_32,
+        ZIP_64,
+        NO_COMPRESSION_64,
+        NO_COMPRESSION_32,
+    ],
+)
+@pytest.mark.parametrize(
+    "timezone,modified_at,expected_modified_at",
+    [
+        ('UTC+1', datetime(2011, 1, 1, 1, 2, 3, 123), datetime(2011, 1, 1, 2, 2, 2, 0)),
+    ],
+)
+def test_unzip_modification_time_extended_timestamps_disabled(method, timezone, modified_at, expected_modified_at):
+    member_files = (
+        ('my_file', modified_at, stat.S_IFREG | 0o600, method, ()),
+    )
+    zipped_chunks = stream_zip(member_files, extended_timestamps=False)
+
+    with \
+            TemporaryDirectory() as d, \
+            cwd(d): \
+
+        with open('test.zip', 'wb') as fp:
+            for zipped_chunk in zipped_chunks:
+                fp.write(zipped_chunk)
+
+        subprocess.run(['unzip', f'{d}/test.zip', '-d', d], env={'TZ': timezone})
+
+        assert os.path.getmtime('my_file') == expected_modified_at.timestamp()