#include "cache.h"
#include "diff.h"
#include "diffcore.h"
+#include "hash.h"
/* Table of rename/copy destinations */
return &(rename_src[first]);
}
-static int is_exact_match(struct diff_filespec *src,
- struct diff_filespec *dst,
- int contents_too)
-{
- if (src->sha1_valid && dst->sha1_valid &&
- !hashcmp(src->sha1, dst->sha1))
- return 1;
- if (!contents_too)
- return 0;
- if (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
- return 0;
- if (src->size != dst->size)
- return 0;
- if (src->sha1_valid && dst->sha1_valid)
- return !hashcmp(src->sha1, dst->sha1);
- if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
- return 0;
- if (src->size == dst->size &&
- !memcmp(src->data, dst->data, src->size))
- return 1;
- return 0;
-}
-
static int basename_same(struct diff_filespec *src, struct diff_filespec *dst)
{
int src_len = strlen(src->path), dst_len = strlen(dst->path);
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,
if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
return 0;
+ /*
+ * Need to check that source and destination sizes are
+ * filled in before comparing them.
+ *
+ * If we already have "cnt_data" filled in, we know it's
+ * all good (avoid checking the size for zero, as that
+ * 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))
+ return 0;
+ if (!dst->cnt_data && diff_populate_filespec(dst, 0))
+ return 0;
+
max_size = ((src->size > dst->size) ? src->size : dst->size);
base_size = ((src->size < dst->size) ? src->size : dst->size);
delta_size = max_size - base_size;
if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
- if ((!src->cnt_data && diff_populate_filespec(src, 0))
- || (!dst->cnt_data && diff_populate_filespec(dst, 0)))
- return 0; /* error but caught downstream */
-
-
delta_limit = (unsigned long)
(base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
if (diffcore_count_changes(src, dst,
{
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;
return b->score - a->score;
}
+struct file_similarity {
+ int src_dst, index;
+ struct diff_filespec *filespec;
+ struct file_similarity *next;
+};
+
+static int find_identical_files(struct file_similarity *src,
+ struct file_similarity *dst)
+{
+ int renames = 0;
+
+ /*
+ * Walk over all the destinations ...
+ */
+ do {
+ struct diff_filespec *target = dst->filespec;
+ struct file_similarity *p, *best;
+ int i = 100, best_score = -1;
+
+ /*
+ * .. to find the best source match
+ */
+ best = NULL;
+ for (p = src; p; p = p->next) {
+ int score;
+ struct diff_filespec *source = p->filespec;
+
+ /* False hash collission? */
+ if (hashcmp(source->sha1, target->sha1))
+ continue;
+ /* Non-regular files? If so, the modes must match! */
+ if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
+ if (source->mode != target->mode)
+ continue;
+ }
+ /* Give higher scores to sources that haven't been used already */
+ score = !source->rename_used;
+ score += basename_same(source, target);
+ if (score > best_score) {
+ best = p;
+ best_score = score;
+ if (score == 2)
+ break;
+ }
+
+ /* Too many identical alternatives? Pick one */
+ if (!--i)
+ break;
+ }
+ if (best) {
+ record_rename_pair(dst->index, best->index, MAX_SCORE);
+ renames++;
+ }
+ } while ((dst = dst->next) != NULL);
+ return renames;
+}
+
+static void free_similarity_list(struct file_similarity *p)
+{
+ while (p) {
+ struct file_similarity *entry = p;
+ p = p->next;
+ free(entry);
+ }
+}
+
+static int find_same_files(void *ptr)
+{
+ int ret;
+ struct file_similarity *p = ptr;
+ struct file_similarity *src = NULL, *dst = NULL;
+
+ /* Split the hash list up into sources and destinations */
+ do {
+ struct file_similarity *entry = p;
+ p = p->next;
+ if (entry->src_dst < 0) {
+ entry->next = src;
+ src = entry;
+ } else {
+ entry->next = dst;
+ dst = entry;
+ }
+ } while (p);
+
+ /*
+ * If we have both sources *and* destinations, see if
+ * we can match them up
+ */
+ ret = (src && dst) ? find_identical_files(src, dst) : 0;
+
+ /* Free the hashes and return the number of renames found */
+ free_similarity_list(src);
+ free_similarity_list(dst);
+ return ret;
+}
+
+static unsigned int hash_filespec(struct diff_filespec *filespec)
+{
+ unsigned int hash;
+ if (!filespec->sha1_valid) {
+ if (diff_populate_filespec(filespec, 0))
+ return 0;
+ hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
+ }
+ memcpy(&hash, filespec->sha1, sizeof(hash));
+ return hash;
+}
+
+static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec)
+{
+ void **pos;
+ unsigned int hash;
+ struct file_similarity *entry = xmalloc(sizeof(*entry));
+
+ entry->src_dst = src_dst;
+ entry->index = index;
+ entry->filespec = filespec;
+ entry->next = NULL;
+
+ hash = hash_filespec(filespec);
+ pos = insert_hash(hash, entry, table);
+
+ /* We already had an entry there? */
+ if (pos) {
+ entry->next = *pos;
+ *pos = entry;
+ }
+}
+
/*
* Find exact renames first.
*
* The first round matches up the up-to-date entries,
* and then during the second round we try to match
* cache-dirty entries as well.
- *
- * Note: the rest of the rename logic depends on this
- * phase also populating all the filespecs for any
- * entry that isn't matched up with an exact rename,
- * see "is_exact_match()".
*/
static int find_exact_renames(void)
{
- int rename_count = 0;
- int contents_too;
-
- for (contents_too = 0; contents_too < 2; contents_too++) {
- int i;
-
- for (i = 0; i < rename_dst_nr; i++) {
- struct diff_filespec *two = rename_dst[i].two;
- int j;
-
- if (rename_dst[i].pair)
- continue; /* dealt with an earlier round */
- for (j = 0; j < rename_src_nr; j++) {
- int k;
- struct diff_filespec *one = rename_src[j].one;
- if (!is_exact_match(one, two, contents_too))
- continue;
+ int i;
+ struct hash_table file_table;
- /* see if there is a basename match, too */
- for (k = j; k < rename_src_nr; k++) {
- one = rename_src[k].one;
- if (basename_same(one, two) &&
- is_exact_match(one, two,
- contents_too)) {
- j = k;
- break;
- }
- }
-
- record_rename_pair(i, j, (int)MAX_SCORE);
- rename_count++;
- break; /* we are done with this entry */
- }
- }
- }
- return rename_count;
+ init_hash(&file_table);
+ for (i = 0; i < rename_src_nr; i++)
+ insert_file_table(&file_table, -1, i, rename_src[i].one);
+
+ for (i = 0; i < rename_dst_nr; i++)
+ insert_file_table(&file_table, 1, i, rename_dst[i].two);
+
+ /* Find the renames */
+ i = for_each_hash(&file_table, find_same_files);
+
+ /* .. 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;
}
void diffcore_rename(struct diff_options *options)
if (rename_dst_nr == 0 || rename_src_nr == 0)
goto cleanup; /* nothing to do */
+ /*
+ * We really want to cull the candidates list early
+ * with cheap tests in order to avoid doing deltas.
+ */
+ rename_count = find_exact_renames();
+
+ /* Did we only want exact renames? */
+ if (minimum_score == MAX_SCORE)
+ goto cleanup;
+
+ /*
+ * Calculate how many renames are left (but all the source
+ * files still remain as options for rename/copies!)
+ */
+ num_create = (rename_dst_nr - rename_count);
+ num_src = rename_src_nr;
+
+ /* All done? */
+ if (!num_create)
+ goto cleanup;
+
/*
* This basically does a test for the rename matrix not
* growing larger than a "rename_limit" square matrix, ie:
*
- * rename_dst_nr * rename_src_nr > rename_limit * rename_limit
+ * 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)
rename_limit = 32767;
- if (rename_dst_nr > rename_limit && rename_src_nr > rename_limit)
- goto cleanup;
- if (rename_dst_nr * rename_src_nr > rename_limit * rename_limit)
- goto cleanup;
-
- /*
- * We really want to cull the candidates list early
- * with cheap tests in order to avoid doing deltas.
- */
- rename_count = find_exact_renames();
-
- /* Have we run out the created file pool? If so we can avoid
- * doing the delta matrix altogether.
- */
- if (rename_count == rename_dst_nr)
- goto cleanup;
-
- if (minimum_score == MAX_SCORE)
+ if ((num_create > rename_limit && num_src > rename_limit) ||
+ (num_create * num_src > rename_limit * rename_limit)) {
+ if (options->warn_on_too_large_rename)
+ warning("too many files, skipping inexact rename detection");
goto cleanup;
+ }
- num_create = (rename_dst_nr - rename_count);
- num_src = rename_src_nr;
- mx = xmalloc(sizeof(*mx) * num_create * num_src);
+ 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);
diff_free_filespec_blob(one);
}
/* We do not need the text anymore */
diff_free_filespec_blob(two);
dst_cnt++;
}
+
/* 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];
+ qsort(mx, dst_cnt * NUM_CANDIDATE_PER_DST, sizeof(*mx), score_compare);
+
+ 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 (mx[i].score < minimum_score)
+ if (rename_src[mx[i].src].one->rename_used)
+ continue;
+ record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
+ rename_count++;
+ }
+
+ 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. */
record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
rename_count++;
}