#include "cache.h"
#include "diff.h"
#include "diffcore.h"
+#include "object-store.h"
#include "hashmap.h"
#include "progress.h"
} *rename_dst;
static int rename_dst_nr, rename_dst_alloc;
-static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
- int insert_ok)
+static int find_rename_dst(struct diff_filespec *two)
{
int first, last;
struct diff_rename_dst *dst = &(rename_dst[next]);
int cmp = strcmp(two->path, dst->two->path);
if (!cmp)
- return dst;
+ return next;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
- /* not found */
- if (!insert_ok)
- return NULL;
+ return -first - 1;
+}
+
+static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two)
+{
+ int ofs = find_rename_dst(two);
+ return ofs < 0 ? NULL : &rename_dst[ofs];
+}
+
+/*
+ * Returns 0 on success, -1 if we found a duplicate.
+ */
+static int add_rename_dst(struct diff_filespec *two)
+{
+ int first = find_rename_dst(two);
+
+ if (first >= 0)
+ return -1;
+ first = -first - 1;
+
/* insert to make it at "first" */
ALLOC_GROW(rename_dst, rename_dst_nr + 1, rename_dst_alloc);
rename_dst_nr++;
if (first < rename_dst_nr)
- memmove(rename_dst + first + 1, rename_dst + first,
- (rename_dst_nr - first - 1) * sizeof(*rename_dst));
+ MOVE_ARRAY(rename_dst + first + 1, rename_dst + first,
+ rename_dst_nr - first - 1);
rename_dst[first].two = alloc_filespec(two->path);
- fill_filespec(rename_dst[first].two, two->sha1, two->sha1_valid, two->mode);
+ fill_filespec(rename_dst[first].two, &two->oid, two->oid_valid,
+ two->mode);
rename_dst[first].pair = NULL;
- return &(rename_dst[first]);
+ return 0;
}
/* Table of rename/copy src files */
ALLOC_GROW(rename_src, rename_src_nr + 1, rename_src_alloc);
rename_src_nr++;
if (first < rename_src_nr)
- memmove(rename_src + first + 1, rename_src + first,
- (rename_src_nr - first - 1) * sizeof(*rename_src));
+ MOVE_ARRAY(rename_src + first + 1, rename_src + first,
+ rename_src_nr - first - 1);
rename_src[first].p = p;
rename_src[first].score = score;
return &(rename_src[first]);
short name_score;
};
-static int estimate_similarity(struct diff_filespec *src,
+static int estimate_similarity(struct repository *r,
+ struct diff_filespec *src,
struct diff_filespec *dst,
int minimum_score)
{
* call into this function in that case.
*/
unsigned long max_size, delta_size, base_size, src_copied, literal_added;
- unsigned long delta_limit;
int score;
/* We deal only with regular files. Symlink renames are handled
* say whether the size is valid or not!)
*/
if (!src->cnt_data &&
- diff_populate_filespec(src, CHECK_SIZE_ONLY))
+ diff_populate_filespec(r, src, CHECK_SIZE_ONLY))
return 0;
if (!dst->cnt_data &&
- diff_populate_filespec(dst, CHECK_SIZE_ONLY))
+ diff_populate_filespec(r, dst, CHECK_SIZE_ONLY))
return 0;
max_size = ((src->size > dst->size) ? src->size : dst->size);
if (max_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
- if (!src->cnt_data && diff_populate_filespec(src, 0))
+ if (!src->cnt_data && diff_populate_filespec(r, src, 0))
return 0;
- if (!dst->cnt_data && diff_populate_filespec(dst, 0))
+ if (!dst->cnt_data && diff_populate_filespec(r, dst, 0))
return 0;
- delta_limit = (unsigned long)
- (base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
- if (diffcore_count_changes(src, dst,
+ if (diffcore_count_changes(r, src, dst,
&src->cnt_data, &dst->cnt_data,
- delta_limit,
&src_copied, &literal_added))
return 0;
struct diff_filespec *filespec;
};
-static unsigned int hash_filespec(struct diff_filespec *filespec)
+static unsigned int hash_filespec(struct repository *r,
+ struct diff_filespec *filespec)
{
- if (!filespec->sha1_valid) {
- if (diff_populate_filespec(filespec, 0))
+ if (!filespec->oid_valid) {
+ if (diff_populate_filespec(r, filespec, 0))
return 0;
- hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
+ hash_object_file(filespec->data, filespec->size, "blob",
+ &filespec->oid);
}
- return sha1hash(filespec->sha1);
+ return sha1hash(filespec->oid.hash);
}
static int find_identical_files(struct hashmap *srcs,
/*
* Find the best source match for specified destination.
*/
- p = hashmap_get_from_hash(srcs, hash_filespec(target), NULL);
+ p = hashmap_get_from_hash(srcs,
+ hash_filespec(options->repo, target),
+ NULL);
for (; p; p = hashmap_get_next(srcs, p)) {
int score;
struct diff_filespec *source = p->filespec;
/* False hash collision? */
- if (hashcmp(source->sha1, target->sha1))
+ if (!oideq(&source->oid, &target->oid))
continue;
/* Non-regular files? If so, the modes must match! */
if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
return renames;
}
-static void insert_file_table(struct hashmap *table, int index, struct diff_filespec *filespec)
+static void insert_file_table(struct repository *r,
+ struct hashmap *table, int index,
+ struct diff_filespec *filespec)
{
struct file_similarity *entry = xmalloc(sizeof(*entry));
entry->index = index;
entry->filespec = filespec;
- hashmap_entry_init(entry, hash_filespec(filespec));
+ hashmap_entry_init(entry, hash_filespec(r, filespec));
hashmap_add(table, entry);
}
int i, renames = 0;
struct hashmap file_table;
- /* Add all sources to the hash table */
- hashmap_init(&file_table, NULL, rename_src_nr);
- for (i = 0; i < rename_src_nr; i++)
- insert_file_table(&file_table, i, rename_src[i].p->one);
+ /* Add all sources to the hash table in reverse order, because
+ * later on they will be retrieved in LIFO order.
+ */
+ hashmap_init(&file_table, NULL, NULL, rename_src_nr);
+ for (i = rename_src_nr-1; i >= 0; i--)
+ insert_file_table(options->repo,
+ &file_table, i,
+ rename_src[i].p->one);
/* Walk the destinations and find best source match */
for (i = 0; i < rename_dst_nr; i++)
* growing larger than a "rename_limit" square matrix, ie:
*
* num_create * num_src > rename_limit * rename_limit
- *
- * but handles the potential overflow case specially (and we
- * assume at least 32-bit integers)
*/
- if (rename_limit <= 0 || rename_limit > 32767)
+ if (rename_limit <= 0)
rename_limit = 32767;
if ((num_create <= rename_limit || num_src <= rename_limit) &&
- (num_create * num_src <= rename_limit * rename_limit))
+ ((uint64_t)num_create * (uint64_t)num_src
+ <= (uint64_t)rename_limit * (uint64_t)rename_limit))
return 0;
options->needed_rename_limit =
num_src > num_create ? num_src : num_create;
/* Are we running under -C -C? */
- if (!DIFF_OPT_TST(options, FIND_COPIES_HARDER))
+ if (!options->flags.find_copies_harder)
return 1;
/* Would we bust the limit if we were running under -C? */
num_src++;
}
if ((num_create <= rename_limit || num_src <= rename_limit) &&
- (num_create * num_src <= rename_limit * rename_limit))
+ ((uint64_t)num_create * (uint64_t)num_src
+ <= (uint64_t)rename_limit * (uint64_t)rename_limit))
return 2;
return 1;
}
else if (options->single_follow &&
strcmp(options->single_follow, p->two->path))
continue; /* not interested */
- else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
- is_empty_blob_sha1(p->two->sha1))
+ else if (!options->flags.rename_empty &&
+ is_empty_blob_oid(&p->two->oid))
continue;
- else
- locate_rename_dst(p->two, 1);
+ else if (add_rename_dst(p->two) < 0) {
+ warning("skipping rename detection, detected"
+ " duplicate destination '%s'",
+ p->two->path);
+ goto cleanup;
+ }
}
- else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
- is_empty_blob_sha1(p->one->sha1))
+ else if (!options->flags.rename_empty &&
+ is_empty_blob_oid(&p->one->oid))
continue;
else if (!DIFF_PAIR_UNMERGED(p) && !DIFF_FILE_VALID(p->two)) {
/*
}
if (options->show_rename_progress) {
- progress = start_progress_delay(
+ progress = start_delayed_progress(
_("Performing inexact rename detection"),
- rename_dst_nr * rename_src_nr, 50, 1);
+ (uint64_t)rename_dst_nr * (uint64_t)rename_src_nr);
}
- mx = xcalloc(num_create * NUM_CANDIDATE_PER_DST, sizeof(*mx));
+ mx = xcalloc(st_mult(NUM_CANDIDATE_PER_DST, num_create), sizeof(*mx));
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
struct diff_filespec *two = rename_dst[i].two;
struct diff_score *m;
diff_unmodified_pair(rename_src[j].p))
continue;
- this_src.score = estimate_similarity(one, two,
+ this_src.score = estimate_similarity(options->repo,
+ one, two,
minimum_score);
this_src.name_score = basename_same(one, two);
this_src.dst = i;
diff_free_filespec_blob(two);
}
dst_cnt++;
- display_progress(progress, (i+1)*rename_src_nr);
+ display_progress(progress, (uint64_t)(i+1)*(uint64_t)rename_src_nr);
}
stop_progress(&progress);
/* cost matrix sorted by most to least similar pair */
- qsort(mx, dst_cnt * NUM_CANDIDATE_PER_DST, sizeof(*mx), score_compare);
+ QSORT(mx, dst_cnt * NUM_CANDIDATE_PER_DST, score_compare);
rename_count += find_renames(mx, dst_cnt, minimum_score, 0);
if (detect_rename == DIFF_DETECT_COPY)
* We would output this create record if it has
* not been turned into a rename/copy already.
*/
- struct diff_rename_dst *dst =
- locate_rename_dst(p->two, 0);
+ struct diff_rename_dst *dst = locate_rename_dst(p->two);
if (dst && dst->pair) {
diff_q(&outq, dst->pair);
pair_to_free = p;
*/
if (DIFF_PAIR_BROKEN(p)) {
/* broken delete */
- struct diff_rename_dst *dst =
- locate_rename_dst(p->one, 0);
+ struct diff_rename_dst *dst = locate_rename_dst(p->one);
if (dst && dst->pair)
/* counterpart is now rename/copy */
pair_to_free = p;
for (i = 0; i < rename_dst_nr; i++)
free_filespec(rename_dst[i].two);
- free(rename_dst);
- rename_dst = NULL;
+ FREE_AND_NULL(rename_dst);
rename_dst_nr = rename_dst_alloc = 0;
- free(rename_src);
- rename_src = NULL;
+ FREE_AND_NULL(rename_src);
rename_src_nr = rename_src_alloc = 0;
return;
}