summaryrefslogtreecommitdiff
path: root/diffcore-delta.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2007-06-28 23:14:13 -0700
committerJunio C Hamano <gitster@pobox.com>2007-06-30 20:51:31 -0700
commitb9905fed7a028cc9749cf8ad479cbb07940c8638 (patch)
tree62122a630a8871f2f3e63a54a744b25285a7ccb6 /diffcore-delta.c
parentaf3abef94af9c821a0c192c693c3e5342ab8729f (diff)
downloadgit-b9905fed7a028cc9749cf8ad479cbb07940c8638.tar.gz
diffcore-delta.c: Ignore CR in CRLF for text files
This ignores CR byte in CRLF sequence in text file when computing similarity of two blobs. Usually this should not matter as nobody sane would be checking in a file with CRLF line endings to the repository (they would use autocrlf so that the repository copy would have LF line endings). Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'diffcore-delta.c')
-rw-r--r--diffcore-delta.c14
1 files changed, 11 insertions, 3 deletions
diff --git a/diffcore-delta.c b/diffcore-delta.c
index 7116df0b83..a038b166c5 100644
--- a/diffcore-delta.c
+++ b/diffcore-delta.c
@@ -122,11 +122,14 @@ static struct spanhash_top *add_spanhash(struct spanhash_top *top,
}
}
-static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
+static struct spanhash_top *hash_chars(struct diff_filespec *one)
{
int i, n;
unsigned int accum1, accum2, hashval;
struct spanhash_top *hash;
+ unsigned char *buf = one->data;
+ unsigned int sz = one->size;
+ int is_text = !one->is_binary;
i = INITIAL_HASH_SIZE;
hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i));
@@ -140,6 +143,11 @@ static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
unsigned int c = *buf++;
unsigned int old_1 = accum1;
sz--;
+
+ /* Ignore CR in CRLF sequence if text */
+ if (is_text && c == '\r' && sz && *buf == '\n')
+ continue;
+
accum1 = (accum1 << 7) ^ (accum2 >> 25);
accum2 = (accum2 << 7) ^ (old_1 >> 25);
accum1 += c;
@@ -169,14 +177,14 @@ int diffcore_count_changes(struct diff_filespec *src,
if (src_count_p)
src_count = *src_count_p;
if (!src_count) {
- src_count = hash_chars(src->data, src->size);
+ src_count = hash_chars(src);
if (src_count_p)
*src_count_p = src_count;
}
if (dst_count_p)
dst_count = *dst_count_p;
if (!dst_count) {
- dst_count = hash_chars(dst->data, dst->size);
+ dst_count = hash_chars(dst);
if (dst_count_p)
*dst_count_p = dst_count;
}