[PATCH 2/2] diff: don't retrieve binary blobs for diffstat

From

Jeff King <peff@peff.net>

Date

Feb 19, 2011, 08:16 UTC

Message-ID

<20110219081631.GB18056@sigill.intra.peff.net>

In-Reply-To

<20110219080307.GA18039@sigill.intra.peff.net>

Signed-off-by: Jeff King <peff@peff.net>
---
This of course is only really helpful if you have marked the files as
binary via gitattributes, since otherwise we have to pull in the blob to
find out that it's binary. :)

  $ time git show --stat >old
  real    0m0.428s
  user    0m0.392s
  sys     0m0.032s

  $ time git.jk.diffstat-binary show --stat >new
  real    0m0.005s
  user    0m0.004s
  sys     0m0.000s

  $ cmp old new && echo ok
  ok

8500% speedup isn't too bad. :)

 diff.c |   15 +++++++++++----
 1 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/diff.c b/diff.c
index 2ac0fe9..6640857 100644
--- a/diff.c
+++ b/diff.c
@@ -245,6 +245,15 @@ static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
 	return 0;
 }
 
+/* like fill_mmfile, but only for size, so we can avoid retrieving blob */
+static unsigned long diff_filespec_size(struct diff_filespec *one)
+{
+	if (!DIFF_FILE_VALID(one))
+		return 0;
+	diff_populate_filespec(one, 1);
+	return one->size;
+}
+
 static int count_trailing_blank(mmfile_t *mf, unsigned ws_rule)
 {
 	char *ptr = mf->ptr;
@@ -2081,11 +2090,9 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 	}
 
 	if (diff_filespec_is_binary(one) || diff_filespec_is_binary(two)) {
-		if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0)
-			die("unable to read files to diff");
 		data->is_binary = 1;
-		data->added = mf2.size;
-		data->deleted = mf1.size;
+		data->added = diff_filespec_size(two);
+		data->deleted = diff_filespec_size(one);
 	}
 
 	else if (complete_rewrite) {

-- 
1.7.4.1.26.g3372c