@@ -460,6 +460,14 @@ static void tgz_write_block(const void *data)
static const char internal_gzip_command[] = "git archive gzip";
+static void tgz_set_os(git_zstream *strm, int os)
+{
+#if ZLIB_VERNUM >= 0x1221
+ struct gz_header_s gzhead = { .os = os };
+ deflateSetHeader(&strm->z, &gzhead);
+#endif
+}
+
static int write_tar_filter_archive(const struct archiver *ar,
struct archiver_args *args)
{
@@ -473,6 +481,7 @@ static int write_tar_filter_archive(const struct archiver *ar,
if (!strcmp(ar->filter_command, internal_gzip_command)) {
write_block = tgz_write_block;
git_deflate_init_gzip(&gzstream, args->compression_level);
+ tgz_set_os(&gzstream, 3); /* Unix, for reproducibility */
gzstream.next_out = outbuf;
gzstream.avail_out = sizeof(outbuf);
gzip(1) encodes the OS it runs on in the 10th byte of its output. It uses the following OS_CODE values according to its tailor.h [1]: 0 - MS-DOS 3 - UNIX 5 - Atari ST 6 - OS/2 10 - TOPS-20 11 - Windows NT The gzip.exe that comes with Git for Windows uses OS_CODE 3 for some reason, so this value is used on practically all supported platforms when generating tgz archives using gzip(1). Zlib uses a bigger set of values according to its zutil.h [2], aligned with section 4.4.2 of the ZIP specification, APPNOTE.txt [3]: 0 - MS-DOS 1 - Amiga 3 - UNIX 4 - VM/CMS 5 - Atari ST 6 - OS/2 7 - Macintosh 8 - Z-System 10 - Windows NT 11 - MVS (OS/390 - Z/OS) 13 - Acorn Risc 16 - BeOS 18 - OS/400 19 - OS X (Darwin) Thus the internal gzip implementation in archive-tar.c sets different OS_CODE header values on major platforms Windows and macOS. Git for Windows uses its own zlib-based variant since v2.20.1 by default and thus embeds OS_CODE 10 in tgz archives. The tar archive for a commit is generated consistently on all systems (by the same Git version). The OS_CODE in the gzip header does not influence extraction. Avoid leaking OS information and make tgz archives constistent and reproducable (with the same Git and libz versions) by using OS_CODE 3 everywhere. NB: The function deflateSetHeader() was introduced by zlib 1.2.2.1, released 2004-10-31. At least on macOS 12.4 this produces the same output as gzip(1) for the examples I tried: # before $ git -c tar.tgz.command='git archive gzip' archive --format=tgz v2.36.0 | shasum 3abbffb40b7c63cf9b7d91afc682f11682f80759 - # with this patch $ git -c tar.tgz.command='git archive gzip' archive --format=tgz v2.36.0 | shasum dc6dc6ba9636d522799085d0d77ab6a110bcc141 - $ git archive --format=tar v2.36.0 | gzip -cn | shasum dc6dc6ba9636d522799085d0d77ab6a110bcc141 - [1] https://git.savannah.gnu.org/cgit/gzip.git/tree/tailor.h [2] https://github.com/madler/zlib/blob/master/zutil.h [3] https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT Signed-off-by: René Scharfe <l.s.r@web.de> --- Perhaps makes sense for remote-curl as well (out of scope of this series)? archive-tar.c | 9 +++++++++ 1 file changed, 9 insertions(+) -- 2.36.1