From 34597c1f5a77c710dae33092cb8a7cb01c6b21c1 Mon Sep 17 00:00:00 2001 From: Clemens Buchacher Date: Sun, 15 Aug 2010 09:20:43 +0200 Subject: hash binary sha1 into patch id Since commit 2f82f760 (Take binary diffs into account for "git rebase"), binary files are included in patch ID computation. Binary files are diffed using the text diff algorithm, however, which has a huge impact on performance. The following tests performance for a 50000 line file marked as binary in .gitattributes. $ git format-patch --stdout --ignore-if-in-upstream master real 0m0.367s user 0m0.354s sys 0m0.010s Instead of diffing the binary files, hash the pre- and post-image sha1, which is just as unique. As a result, performance is much improved. $ git format-patch --stdout --ignore-if-in-upstream master real 0m0.016s user 0m0.015s sys 0m0.001s Signed-off-by: Clemens Buchacher Signed-off-by: Junio C Hamano --- diff.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/diff.c b/diff.c index 17873f3d9e..f4a23ab1db 100644 --- a/diff.c +++ b/diff.c @@ -3758,6 +3758,13 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1) len2, p->two->path); git_SHA1_Update(&ctx, buffer, len1); + if (diff_filespec_is_binary(p->one) || + diff_filespec_is_binary(p->two)) { + git_SHA1_Update(&ctx, sha1_to_hex(p->one->sha1), 40); + git_SHA1_Update(&ctx, sha1_to_hex(p->two->sha1), 40); + continue; + } + xpp.flags = 0; xecfg.ctxlen = 3; xecfg.flags = XDL_EMIT_FUNCNAMES; -- cgit v1.2.3