#include "diff.h"
#include "diffcore.h"
#include "hash.h"
+#include "progress.h"
/* Table of rename/copy destinations */
struct diff_score {
int src; /* index in rename_src */
int dst; /* index in rename_dst */
- int score;
- int name_score;
+ unsigned short score;
+ short name_score;
};
static int estimate_similarity(struct diff_filespec *src,
* is a possible size - we really should have a flag to
* say whether the size is valid or not!)
*/
- if (!src->cnt_data && diff_populate_filespec(src, 0))
+ if (!src->cnt_data && diff_populate_filespec(src, 1))
return 0;
- if (!dst->cnt_data && diff_populate_filespec(dst, 0))
+ if (!dst->cnt_data && diff_populate_filespec(dst, 1))
return 0;
max_size = ((src->size > dst->size) ? src->size : dst->size);
* and the final score computation below would not have a
* divide-by-zero issue.
*/
- if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
+ if (max_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
+ return 0;
+
+ if (!src->cnt_data && diff_populate_filespec(src, 0))
+ return 0;
+ if (!dst->cnt_data && diff_populate_filespec(dst, 0))
return 0;
delta_limit = (unsigned long)
{
const struct diff_score *a = a_, *b = b_;
+ /* sink the unused ones to the bottom */
+ if (a->dst < 0)
+ return (0 <= b->dst);
+ else if (b->dst < 0)
+ return -1;
+
if (a->score == b->score)
return b->name_score - a->name_score;
};
static int find_identical_files(struct file_similarity *src,
- struct file_similarity *dst)
+ struct file_similarity *dst,
+ struct diff_options *options)
{
int renames = 0;
int score;
struct diff_filespec *source = p->filespec;
- /* False hash collission? */
+ /* False hash collision? */
if (hashcmp(source->sha1, target->sha1))
continue;
/* Non-regular files? If so, the modes must match! */
}
/* Give higher scores to sources that haven't been used already */
score = !source->rename_used;
+ if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
+ continue;
score += basename_same(source, target);
if (score > best_score) {
best = p;
}
}
-static int find_same_files(void *ptr)
+static int find_same_files(void *ptr, void *data)
{
int ret;
struct file_similarity *p = ptr;
struct file_similarity *src = NULL, *dst = NULL;
+ struct diff_options *options = data;
/* Split the hash list up into sources and destinations */
do {
* If we have both sources *and* destinations, see if
* we can match them up
*/
- ret = (src && dst) ? find_identical_files(src, dst) : 0;
+ ret = (src && dst) ? find_identical_files(src, dst, options) : 0;
/* Free the hashes and return the number of renames found */
free_similarity_list(src);
* and then during the second round we try to match
* cache-dirty entries as well.
*/
-static int find_exact_renames(void)
+static int find_exact_renames(struct diff_options *options)
{
int i;
struct hash_table file_table;
insert_file_table(&file_table, 1, i, rename_dst[i].two);
/* Find the renames */
- i = for_each_hash(&file_table, find_same_files);
+ i = for_each_hash(&file_table, find_same_files, options);
/* .. and free the hash data structure */
free_hash(&file_table);
return i;
}
+#define NUM_CANDIDATE_PER_DST 4
+static void record_if_better(struct diff_score m[], struct diff_score *o)
+{
+ int i, worst;
+
+ /* find the worst one */
+ worst = 0;
+ for (i = 1; i < NUM_CANDIDATE_PER_DST; i++)
+ if (score_compare(&m[i], &m[worst]) > 0)
+ worst = i;
+
+ /* is it better than the worst one? */
+ if (score_compare(&m[worst], o) > 0)
+ m[worst] = *o;
+}
+
+static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, int copies)
+{
+ int count = 0, i;
+
+ for (i = 0; i < dst_cnt * NUM_CANDIDATE_PER_DST; i++) {
+ struct diff_rename_dst *dst;
+
+ if ((mx[i].dst < 0) ||
+ (mx[i].score < minimum_score))
+ break; /* there is no more usable pair. */
+ dst = &rename_dst[mx[i].dst];
+ if (dst->pair)
+ continue; /* already done, either exact or fuzzy. */
+ if (!copies && rename_src[mx[i].src].one->rename_used)
+ continue;
+ record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
+ count++;
+ }
+ return count;
+}
+
void diffcore_rename(struct diff_options *options)
{
int detect_rename = options->detect_rename;
struct diff_score *mx;
int i, j, rename_count;
int num_create, num_src, dst_cnt;
+ struct progress *progress = NULL;
if (!minimum_score)
minimum_score = DEFAULT_RENAME_SCORE;
* We really want to cull the candidates list early
* with cheap tests in order to avoid doing deltas.
*/
- rename_count = find_exact_renames();
+ rename_count = find_exact_renames(options);
/* Did we only want exact renames? */
if (minimum_score == MAX_SCORE)
* but handles the potential overflow case specially (and we
* assume at least 32-bit integers)
*/
+ options->needed_rename_limit = 0;
if (rename_limit <= 0 || rename_limit > 32767)
rename_limit = 32767;
if ((num_create > rename_limit && num_src > rename_limit) ||
(num_create * num_src > rename_limit * rename_limit)) {
- warning("too many files, skipping inexact rename detection");
+ options->needed_rename_limit =
+ num_src > num_create ? num_src : num_create;
goto cleanup;
}
- mx = xmalloc(sizeof(*mx) * num_create * num_src);
+ if (options->show_rename_progress) {
+ progress = start_progress_delay(
+ "Performing inexact rename detection",
+ rename_dst_nr * rename_src_nr, 50, 1);
+ }
+
+ mx = xcalloc(num_create * NUM_CANDIDATE_PER_DST, sizeof(*mx));
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
- int base = dst_cnt * num_src;
struct diff_filespec *two = rename_dst[i].two;
+ struct diff_score *m;
+
if (rename_dst[i].pair)
continue; /* dealt with exact match already. */
+
+ m = &mx[dst_cnt * NUM_CANDIDATE_PER_DST];
+ for (j = 0; j < NUM_CANDIDATE_PER_DST; j++)
+ m[j].dst = -1;
+
for (j = 0; j < rename_src_nr; j++) {
struct diff_filespec *one = rename_src[j].one;
- struct diff_score *m = &mx[base+j];
- m->src = j;
- m->dst = i;
- m->score = estimate_similarity(one, two,
- minimum_score);
- m->name_score = basename_same(one, two);
+ struct diff_score this_src;
+ this_src.score = estimate_similarity(one, two,
+ minimum_score);
+ this_src.name_score = basename_same(one, two);
+ this_src.dst = i;
+ this_src.src = j;
+ record_if_better(m, &this_src);
+ /*
+ * Once we run estimate_similarity,
+ * We do not need the text anymore.
+ */
diff_free_filespec_blob(one);
+ diff_free_filespec_blob(two);
}
- /* We do not need the text anymore */
- diff_free_filespec_blob(two);
dst_cnt++;
+ display_progress(progress, (i+1)*rename_src_nr);
}
+ stop_progress(&progress);
+
/* cost matrix sorted by most to least similar pair */
- qsort(mx, num_create * num_src, sizeof(*mx), score_compare);
- for (i = 0; i < num_create * num_src; i++) {
- struct diff_rename_dst *dst = &rename_dst[mx[i].dst];
- struct diff_filespec *src;
- if (dst->pair)
- continue; /* already done, either exact or fuzzy. */
- if (mx[i].score < minimum_score)
- break; /* there is no more usable pair. */
- src = rename_src[mx[i].src].one;
- if (src->rename_used)
- continue;
- record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
- rename_count++;
- }
- for (i = 0; i < num_create * num_src; i++) {
- struct diff_rename_dst *dst = &rename_dst[mx[i].dst];
- if (dst->pair)
- continue; /* already done, either exact or fuzzy. */
- if (mx[i].score < minimum_score)
- break; /* there is no more usable pair. */
- record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
- rename_count++;
- }
+ qsort(mx, dst_cnt * NUM_CANDIDATE_PER_DST, sizeof(*mx), score_compare);
+
+ rename_count += find_renames(mx, dst_cnt, minimum_score, 0);
+ if (detect_rename == DIFF_DETECT_COPY)
+ rename_count += find_renames(mx, dst_cnt, minimum_score, 1);
free(mx);
cleanup:
/* At this point, we have found some renames and copies and they
* are recorded in rename_dst. The original list is still in *q.
*/
- outq.queue = NULL;
- outq.nr = outq.alloc = 0;
+ DIFF_QUEUE_CLEAR(&outq);
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
struct diff_filepair *pair_to_free = NULL;