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>

diff --git a/diffcore-delta.c b/diffcore-delta.c
index 7116df0b83f68b9d31dc8e4c3a89ad365a138a37..a038b166c5aa095ffdf31c2fb0e3263ed13cf8b1 100644 (file)
--- 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;
 {
        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));
 
        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--;
                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;
                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) {
        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) {
                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;
        }
                if (dst_count_p)
                        *dst_count_p = dst_count;
        }

diff --git a/t/t0022-crlf-rename.sh b/t/t0022-crlf-rename.sh
new file mode 100755 (executable)
index 0000000..430a1d1
--- /dev/null
+++ b/t/t0022-crlf-rename.sh
@@ -0,0 +1,33 @@
+#!/bin/sh
+
+test_description='ignore CR in CRLF sequence while computing similiarity'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+
+       cat ../t0022-crlf-rename.sh >sample &&
+       git add sample &&
+
+       test_tick &&
+       git commit -m Initial &&
+
+       sed -e "s/\$/\r/" ../t0022-crlf-rename.sh >elpmas &&
+       git add elpmas &&
+       rm -f sample &&
+
+       test_tick &&
+       git commit -a -m Second
+
+'
+
+test_expect_success 'diff -M' '
+
+       git diff-tree -M -r --name-status HEAD^ HEAD |
+       sed -e "s/R[0-9]*/RNUM/" >actual &&
+       echo "RNUM      sample  elpmas" >expect &&
+       diff -u expect actual
+
+'
+
+test_done