Merge branch 'maint'

[git.git] / diffcore-delta.c

diff --git a/diffcore-delta.c b/diffcore-delta.c
index 7116df0b83f68b9d31dc8e4c3a89ad365a138a37..e670f8512558c38d9a9d6e754cfc609b042b1195 100644 (file)
--- a/diffcore-delta.c
+++ b/diffcore-delta.c
@@ -46,22 +46,6 @@ struct spanhash_top {
        struct spanhash data[FLEX_ARRAY];
 };
 
-static struct spanhash *spanhash_find(struct spanhash_top *top,
-                                     unsigned int hashval)
-{
-       int sz = 1 << top->alloc_log2;
-       int bucket = hashval & (sz - 1);
-       while (1) {
-               struct spanhash *h = &(top->data[bucket++]);
-               if (!h->cnt)
-                       return NULL;
-               if (h->hashval == hashval)
-                       return h;
-               if (sz <= bucket)
-                       bucket = 0;
-       }
-}
-
 static struct spanhash_top *spanhash_rehash(struct spanhash_top *orig)
 {
        struct spanhash_top *new;
@@ -122,11 +106,28 @@ static struct spanhash_top *add_spanhash(struct spanhash_top *top,
        }
 }
 
-static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
+static int spanhash_cmp(const void *a_, const void *b_)
+{
+       const struct spanhash *a = a_;
+       const struct spanhash *b = b_;
+
+       /* A count of zero compares at the end.. */
+       if (!a->cnt)
+               return !b->cnt ? 0 : 1;
+       if (!b->cnt)
+               return -1;
+       return a->hashval < b->hashval ? -1 :
+               a->hashval > b->hashval ? 1 : 0;
+}
+
+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 = !diff_filespec_is_binary(one);
 
        i = INITIAL_HASH_SIZE;
        hash = xmalloc(sizeof(*hash) + sizeof(struct spanhash) * (1<<i));
@@ -140,6 +141,11 @@ 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;
@@ -150,6 +156,10 @@ static struct spanhash_top *hash_chars(unsigned char *buf, unsigned int sz)
                n = 0;
                accum1 = accum2 = 0;
        }
+       qsort(hash->data,
+               1ul << hash->alloc_log2,
+               sizeof(hash->data[0]),
+               spanhash_cmp);
        return hash;
 }
 
@@ -161,7 +171,7 @@ int diffcore_count_changes(struct diff_filespec *src,
                           unsigned long *src_copied,
                           unsigned long *literal_added)
 {
-       int i, ssz;
+       struct spanhash *s, *d;
        struct spanhash_top *src_count, *dst_count;
        unsigned long sc, la;
 
@@ -169,35 +179,39 @@ 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;
        }
        sc = la = 0;
 
-       ssz = 1 << src_count->alloc_log2;
-       for (i = 0; i < ssz; i++) {
-               struct spanhash *s = &(src_count->data[i]);
-               struct spanhash *d;
+       s = src_count->data;
+       d = dst_count->data;
+       for (;;) {
                unsigned dst_cnt, src_cnt;
                if (!s->cnt)
-                       continue;
+                       break; /* we checked all in src */
+               while (d->cnt) {
+                       if (d->hashval >= s->hashval)
+                               break;
+                       d++;
+               }
                src_cnt = s->cnt;
-               d = spanhash_find(dst_count, s->hashval);
-               dst_cnt = d ? d->cnt : 0;
+               dst_cnt = d->hashval == s->hashval ? d->cnt : 0;
                if (src_cnt < dst_cnt) {
                        la += dst_cnt - src_cnt;
                        sc += src_cnt;
                }
                else
                        sc += dst_cnt;
+               s++;
        }
 
        if (!src_count_p)