#include "diff.h"
#include "diffcore.h"
#include "delta.h"
+#include "count-delta.h"
-struct diff_rename_pool {
- struct diff_filespec **s;
- int nr, alloc;
-};
+/* Table of rename/copy destinations */
+
+static struct diff_rename_dst {
+ struct diff_filespec *two;
+ struct diff_filepair *pair;
+} *rename_dst;
+static int rename_dst_nr, rename_dst_alloc;
-static void diff_rename_pool_clear(struct diff_rename_pool *pool)
+static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
+ int insert_ok)
{
- pool->s = NULL; pool->nr = pool->alloc = 0;
+ int first, last;
+
+ first = 0;
+ last = rename_dst_nr;
+ while (last > first) {
+ int next = (last + first) >> 1;
+ struct diff_rename_dst *dst = &(rename_dst[next]);
+ int cmp = strcmp(two->path, dst->two->path);
+ if (!cmp)
+ return dst;
+ if (cmp < 0) {
+ last = next;
+ continue;
+ }
+ first = next+1;
+ }
+ /* not found */
+ if (!insert_ok)
+ return NULL;
+ /* insert to make it at "first" */
+ if (rename_dst_alloc <= rename_dst_nr) {
+ rename_dst_alloc = alloc_nr(rename_dst_alloc);
+ rename_dst = xrealloc(rename_dst,
+ rename_dst_alloc * sizeof(*rename_dst));
+ }
+ rename_dst_nr++;
+ if (first < rename_dst_nr)
+ memmove(rename_dst + first + 1, rename_dst + first,
+ (rename_dst_nr - first - 1) * sizeof(*rename_dst));
+ rename_dst[first].two = two;
+ rename_dst[first].pair = NULL;
+ return &(rename_dst[first]);
}
-static void diff_rename_pool_add(struct diff_rename_pool *pool,
- struct diff_filespec *s)
+/* Table of rename/copy src files */
+static struct diff_rename_src {
+ struct diff_filespec *one;
+ unsigned src_stays : 1;
+} *rename_src;
+static int rename_src_nr, rename_src_alloc;
+
+static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
+ int src_stays)
{
- if (S_ISDIR(s->mode))
- return; /* rename/copy patch for tree does not make sense. */
+ int first, last;
+
+ first = 0;
+ last = rename_src_nr;
+ while (last > first) {
+ int next = (last + first) >> 1;
+ struct diff_rename_src *src = &(rename_src[next]);
+ int cmp = strcmp(one->path, src->one->path);
+ if (!cmp)
+ return src;
+ if (cmp < 0) {
+ last = next;
+ continue;
+ }
+ first = next+1;
+ }
- if (pool->alloc <= pool->nr) {
- pool->alloc = alloc_nr(pool->alloc);
- pool->s = xrealloc(pool->s,
- sizeof(*(pool->s)) * pool->alloc);
+ /* insert to make it at "first" */
+ if (rename_src_alloc <= rename_src_nr) {
+ rename_src_alloc = alloc_nr(rename_src_alloc);
+ rename_src = xrealloc(rename_src,
+ rename_src_alloc * sizeof(*rename_src));
}
- pool->s[pool->nr] = s;
- pool->nr++;
+ rename_src_nr++;
+ if (first < rename_src_nr)
+ memmove(rename_src + first + 1, rename_src + first,
+ (rename_src_nr - first - 1) * sizeof(*rename_src));
+ rename_src[first].one = one;
+ rename_src[first].src_stays = src_stays;
+ return &(rename_src[first]);
}
static int is_exact_match(struct diff_filespec *src, struct diff_filespec *dst)
if (src->sha1_valid && dst->sha1_valid &&
!memcmp(src->sha1, dst->sha1, 20))
return 1;
- if (diff_populate_filespec(src) || diff_populate_filespec(dst))
- /* this is an error but will be caught downstream */
+ if (diff_populate_filespec(src, 1) || diff_populate_filespec(dst, 1))
+ return 0;
+ if (src->size != dst->size)
+ return 0;
+ 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))
}
struct diff_score {
- struct diff_filespec *src;
- struct diff_filespec *dst;
+ int src; /* index in rename_src */
+ int dst; /* index in rename_dst */
int score;
- int rank;
};
static int estimate_similarity(struct diff_filespec *src,
* dst, and then some edit has been applied to dst.
*
* Compare them and return how similar they are, representing
- * the score as an integer between 0 and 10000, except
- * where they match exactly it is considered better than anything
- * else.
+ * the score as an integer between 0 and MAX_SCORE.
+ *
+ * When there is an exact match, it is considered a better
+ * match than anything else; the destination does not even
+ * call into this function in that case.
*/
void *delta;
- unsigned long delta_size, base_size;
+ unsigned long delta_size, base_size, src_copied, literal_added;
+ unsigned long delta_limit;
int score;
+ /* We deal only with regular files. Symlink renames are handled
+ * only when they are exact matches --- in other words, no edits
+ * after renaming.
+ */
+ if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
+ return 0;
+
delta_size = ((src->size < dst->size) ?
(dst->size - src->size) : (src->size - dst->size));
base_size = ((src->size < dst->size) ? src->size : dst->size);
/* We would not consider edits that change the file size so
* drastically. delta_size must be smaller than
- * minimum_score/MAX_SCORE * min(src->size, dst->size).
+ * (MAX_SCORE-minimum_score)/MAX_SCORE * min(src->size, dst->size).
+ *
* Note that base_size == 0 case is handled here already
* and the final score computation below would not have a
* divide-by-zero issue.
*/
- if (base_size * minimum_score < delta_size * MAX_SCORE)
+ if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
+ if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0))
+ return 0; /* error but caught downstream */
+
+ delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE;
delta = diff_delta(src->data, src->size,
dst->data, dst->size,
- &delta_size);
- /*
- * We currently punt here, but we may later end up parsing the
- * delta to really assess the extent of damage. A big consecutive
- * remove would produce small delta_size that affects quite a
- * big portion of the file.
+ &delta_size, delta_limit);
+ if (!delta)
+ /* If delta_limit is exceeded, we have too much differences */
+ return 0;
+
+ /* A delta that has a lot of literal additions would have
+ * big delta_size no matter what else it does.
*/
+ if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
+ return 0;
+
+ /* Estimate the edit size by interpreting delta. */
+ if (count_delta(delta, delta_size, &src_copied, &literal_added)) {
+ free(delta);
+ return 0;
+ }
free(delta);
+ /* Extent of damage */
+ if (src->size + literal_added < src_copied)
+ delta_size = 0;
+ else
+ delta_size = (src->size - src_copied) + literal_added;
+
/*
* Now we will give some score to it. 100% edit gets 0 points
* and 0% edit gets MAX_SCORE points.
return score;
}
-static void record_rename_pair(struct diff_queue_struct *outq,
- struct diff_filespec *src,
- struct diff_filespec *dst,
- int rank,
- int score)
+static void record_rename_pair(struct diff_queue_struct *renq,
+ int dst_index, int src_index, int score)
{
- /* The rank is used to sort the final output, because there
- * are certain dependencies.
- *
- * - rank #0 depends on deleted ones.
- * - rank #1 depends on kept files before they are modified.
- * - rank #2 depends on kept files after they are modified;
- * currently not used.
- *
- * Therefore, the final output order should be:
- *
- * 1. rank #0 rename/copy diffs.
- * 2. deletions in the original.
- * 3. rank #1 rename/copy diffs.
- * 4. additions and modifications in the original.
- * 5. rank #2 rename/copy diffs; currently not used.
- *
- * To achieve this sort order, we give xform_work the number
- * above.
- */
- struct diff_filepair *dp = diff_queue(outq, src, dst);
- dp->xfrm_work = (rank * 2 + 1) | (score<<RENAME_SCORE_SHIFT);
- dst->xfrm_flags |= RENAME_DST_MATCHED;
-}
+ struct diff_filespec *one, *two, *src, *dst;
+ struct diff_filepair *dp;
-#if 0
-static void debug_filespec(struct diff_filespec *s, int x, const char *one)
-{
- fprintf(stderr, "queue[%d] %s (%s) %s %06o %s\n",
- x, one,
- s->path,
- DIFF_FILE_VALID(s) ? "valid" : "invalid",
- s->mode,
- s->sha1_valid ? sha1_to_hex(s->sha1) : "");
- fprintf(stderr, "queue[%d] %s size %lu flags %d\n",
- x, one,
- s->size, s->xfrm_flags);
-}
+ if (rename_dst[dst_index].pair)
+ die("internal error: dst already matched.");
-static void debug_filepair(const struct diff_filepair *p, int i)
-{
- debug_filespec(p->one, i, "one");
- debug_filespec(p->two, i, "two");
- fprintf(stderr, "pair flags %d, orig order %d, score %d\n",
- (p->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1)),
- p->orig_order,
- (p->xfrm_work >> RENAME_SCORE_SHIFT));
-}
+ src = rename_src[src_index].one;
+ one = alloc_filespec(src->path);
+ fill_filespec(one, src->sha1, src->mode);
-static void debug_queue(const char *msg, struct diff_queue_struct *q)
-{
- int i;
- if (msg)
- fprintf(stderr, "%s\n", msg);
- fprintf(stderr, "q->nr = %d\n", q->nr);
- for (i = 0; i < q->nr; i++) {
- struct diff_filepair *p = q->queue[i];
- debug_filepair(p, i);
- }
-}
-#else
-#define debug_queue(a,b) do { ; /*nothing*/ } while(0)
-#endif
+ dst = rename_dst[dst_index].two;
+ two = alloc_filespec(dst->path);
+ fill_filespec(two, dst->sha1, dst->mode);
-/*
- * We sort the outstanding diff entries according to the rank (see
- * comment at the beginning of record_rename_pair) and tiebreak with
- * the order in the original input.
- */
-static int rank_compare(const void *a_, const void *b_)
-{
- const struct diff_filepair *a = *(const struct diff_filepair **)a_;
- const struct diff_filepair *b = *(const struct diff_filepair **)b_;
- int a_rank = a->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1);
- int b_rank = b->xfrm_work & ((1<<RENAME_SCORE_SHIFT) - 1);
-
- if (a_rank != b_rank)
- return a_rank - b_rank;
- return a->orig_order - b->orig_order;
+ dp = diff_queue(renq, one, two);
+ dp->score = score;
+ dp->source_stays = rename_src[src_index].src_stays;
+ rename_dst[dst_index].pair = dp;
}
/*
* We sort the rename similarity matrix with the score, in descending
- * order (more similar first).
+ * order (the most similar first).
*/
static int score_compare(const void *a_, const void *b_)
{
return b->score - a->score;
}
-static int needs_to_stay(struct diff_queue_struct *q, int i,
- struct diff_filespec *it)
-{
- /* If it will be used in later entry (either stay or used
- * as the source of rename/copy), we need to copy, not rename.
- */
- while (i < q->nr) {
- struct diff_filepair *p = q->queue[i++];
- if (!DIFF_FILE_VALID(p->two))
- continue; /* removed is fine */
- if (strcmp(p->one->path, it->path))
- continue; /* not relevant */
-
- /* p has its src set to *it and it is not a delete;
- * it will be used for in-place change or rename/copy,
- * so we cannot rename it out.
- */
- return 1;
- }
- return 0;
-}
-
-void diff_detect_rename(int detect_rename,
- int minimum_score)
+void diffcore_rename(int detect_rename, int minimum_score)
{
struct diff_queue_struct *q = &diff_queued_diff;
- struct diff_queue_struct outq;
- struct diff_rename_pool created, deleted, stay;
- struct diff_rename_pool *(srcs[2]);
+ struct diff_queue_struct renq, outq;
struct diff_score *mx;
- int h, i, j;
- int num_create, num_src, dst_cnt, src_cnt;
-
- outq.queue = NULL;
- outq.nr = outq.alloc = 0;
-
- diff_rename_pool_clear(&created);
- diff_rename_pool_clear(&deleted);
- diff_rename_pool_clear(&stay);
+ int i, j;
+ int num_create, num_src, dst_cnt;
- srcs[0] = &deleted;
- srcs[1] = &stay;
+ if (!minimum_score)
+ minimum_score = DEFAULT_RENAME_SCORE;
+ renq.queue = NULL;
+ renq.nr = renq.alloc = 0;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (!DIFF_FILE_VALID(p->one))
if (!DIFF_FILE_VALID(p->two))
- continue; /* ignore nonsense */
+ continue; /* unmerged */
else
- diff_rename_pool_add(&created, p->two);
- else if (!DIFF_FILE_VALID(p->two))
- diff_rename_pool_add(&deleted, p->one);
- else if (1 < detect_rename) /* find copy, too */
- diff_rename_pool_add(&stay, p->one);
+ locate_rename_dst(p->two, 1);
+ else if (!DIFF_FILE_VALID(p->two)) {
+ /* If the source is a broken "delete", and
+ * they did not really want to get broken,
+ * that means the source actually stays.
+ */
+ int stays = (p->broken_pair && !p->score);
+ register_rename_src(p->one, stays);
+ }
+ else if (detect_rename == DIFF_DETECT_COPY)
+ register_rename_src(p->one, 1);
}
- if (created.nr == 0)
+ if (rename_dst_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.
- *
- * With the current callers, we should not have already
- * matched entries at this point, but it is nonetheless
- * checked for sanity.
*/
- for (i = 0; i < created.nr; i++) {
- if (created.s[i]->xfrm_flags & RENAME_DST_MATCHED)
- continue; /* we have matched exactly already */
- for (h = 0; h < sizeof(srcs)/sizeof(srcs[0]); h++) {
- struct diff_rename_pool *p = srcs[h];
- for (j = 0; j < p->nr; j++) {
- if (!is_exact_match(p->s[j], created.s[i]))
- continue;
- record_rename_pair(&outq,
- p->s[j], created.s[i], h,
- MAX_SCORE);
- break; /* we are done with this entry */
- }
+ for (i = 0; i < rename_dst_nr; i++) {
+ struct diff_filespec *two = rename_dst[i].two;
+ for (j = 0; j < rename_src_nr; j++) {
+ struct diff_filespec *one = rename_src[j].one;
+ if (!is_exact_match(one, two))
+ continue;
+ record_rename_pair(&renq, i, j, MAX_SCORE);
+ break; /* we are done with this entry */
}
}
- debug_queue("done detecting exact", &outq);
+ diff_debug_queue("done detecting exact", &renq);
/* Have we run out the created file pool? If so we can avoid
* doing the delta matrix altogether.
*/
- if (outq.nr == created.nr)
- goto flush_rest;
+ if (renq.nr == rename_dst_nr)
+ goto cleanup;
- num_create = (created.nr - outq.nr);
- num_src = deleted.nr + stay.nr;
+ num_create = (rename_dst_nr - renq.nr);
+ num_src = rename_src_nr;
mx = xmalloc(sizeof(*mx) * num_create * num_src);
- for (dst_cnt = i = 0; i < created.nr; i++) {
+ for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
int base = dst_cnt * num_src;
- if (created.s[i]->xfrm_flags & RENAME_DST_MATCHED)
+ struct diff_filespec *two = rename_dst[i].two;
+ if (rename_dst[i].pair)
continue; /* dealt with exact match already. */
- for (src_cnt = h = 0; h < sizeof(srcs)/sizeof(srcs[0]); h++) {
- struct diff_rename_pool *p = srcs[h];
- for (j = 0; j < p->nr; j++, src_cnt++) {
- struct diff_score *m = &mx[base + src_cnt];
- m->src = p->s[j];
- m->dst = created.s[i];
- m->score = estimate_similarity(m->src, m->dst,
- minimum_score);
- m->rank = h;
- }
+ 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);
}
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++) {
- if (mx[i].dst->xfrm_flags & RENAME_DST_MATCHED)
- continue; /* alreayd done, either exact or fuzzy. */
+ 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 not any more diffs applicable. */
- record_rename_pair(&outq,
- mx[i].src, mx[i].dst, mx[i].rank,
- mx[i].score);
+ break; /* there is no more usable pair. */
+ record_rename_pair(&renq, mx[i].dst, mx[i].src, mx[i].score);
}
free(mx);
- debug_queue("done detecting fuzzy", &outq);
+ diff_debug_queue("done detecting fuzzy", &renq);
- flush_rest:
+ cleanup:
/* At this point, we have found some renames and copies and they
- * are kept in outq. The original list is still in *q.
- *
- * Scan the original list and move them into the outq; we will sort
- * outq and swap it into the queue supplied to pass that to
- * downstream, so we assign the sort keys in this loop.
- *
- * See comments at the top of record_rename_pair for numbers used
- * to assign xfrm_work.
- *
- * Note that we have not annotated the diff_filepair with any comment
- * so there is nothing other than p to free.
+ * are kept in renq. The original list is still in *q.
*/
+ outq.queue = NULL;
+ outq.nr = outq.alloc = 0;
for (i = 0; i < q->nr; i++) {
- struct diff_filepair *dp, *p = q->queue[i];
- if (!DIFF_FILE_VALID(p->one)) {
- if (DIFF_FILE_VALID(p->two)) {
- /* creation */
- dp = diff_queue(&outq, p->one, p->two);
- dp->xfrm_work = 4;
+ struct diff_filepair *p = q->queue[i];
+ struct diff_filepair *pair_to_free = NULL;
+
+ if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
+ /*
+ * Creation
+ *
+ * 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);
+ if (dst && dst->pair) {
+ diff_q(&outq, dst->pair);
+ pair_to_free = p;
}
- /* otherwise it is a nonsense; just ignore it */
- }
- else if (!DIFF_FILE_VALID(p->two)) {
- /* deletion */
- dp = diff_queue(&outq, p->one, p->two);
- dp->xfrm_work = 2;
- }
- else {
- /* modification, or stay as is */
- dp = diff_queue(&outq, p->one, p->two);
- dp->xfrm_work = 4;
- }
- free(p);
- }
- debug_queue("done copying original", &outq);
-
- /* Sort outq */
- qsort(outq.queue, outq.nr, sizeof(outq.queue[0]), rank_compare);
-
- debug_queue("done sorting", &outq);
-
- free(q->queue);
- q->nr = q->alloc = 0;
- q->queue = NULL;
-
- /* Copy it out to q, removing duplicates. */
- for (i = 0; i < outq.nr; i++) {
- struct diff_filepair *p = outq.queue[i];
- if (!DIFF_FILE_VALID(p->one)) {
- /* created */
- if (p->two->xfrm_flags & RENAME_DST_MATCHED)
- ; /* rename/copy created it already */
else
- diff_queue(q, p->one, p->two);
+ /* no matching rename/copy source, so
+ * record this as a creation.
+ */
+ diff_q(&outq, p);
}
- else if (!DIFF_FILE_VALID(p->two)) {
- /* deleted */
- if (p->one->xfrm_flags & RENAME_SRC_GONE)
- ; /* rename/copy deleted it already */
- else
- diff_queue(q, p->one, p->two);
- }
- else if (strcmp(p->one->path, p->two->path)) {
- /* rename or copy */
- struct diff_filepair *dp =
- diff_queue(q, p->one, p->two);
- int msglen = (strlen(p->one->path) +
- strlen(p->two->path) + 100);
- int score = (p->xfrm_work >> RENAME_SCORE_SHIFT);
- dp->xfrm_msg = xmalloc(msglen);
-
- /* if we have a later entry that is a rename/copy
- * that depends on p->one, then we copy here.
- * otherwise we rename it.
+ else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) {
+ /*
+ * Deletion
+ *
+ * We would output this delete record if:
+ *
+ * (1) this is a broken delete and the counterpart
+ * broken create remains in the output; or
+ * (2) this is not a broken delete, and renq does
+ * not have a rename/copy to move p->one->path
+ * out.
+ *
+ * Otherwise, the counterpart broken create
+ * has been turned into a rename-edit; or
+ * delete did not have a matching create to
+ * begin with.
*/
- if (needs_to_stay(&outq, i+1, p->one)) {
- /* copy it */
- sprintf(dp->xfrm_msg,
- "similarity index %d%%\n"
- "copy from %s\n"
- "copy to %s\n",
- (int)(0.5 + score * 100 / MAX_SCORE),
- p->one->path, p->two->path);
+ if (DIFF_PAIR_BROKEN(p)) {
+ /* broken delete */
+ struct diff_rename_dst *dst =
+ locate_rename_dst(p->one, 0);
+ if (dst && dst->pair)
+ /* counterpart is now rename/copy */
+ pair_to_free = p;
}
else {
- /* rename it, and mark it as gone. */
- p->one->xfrm_flags |= RENAME_SRC_GONE;
- sprintf(dp->xfrm_msg,
- "similarity index %d%%\n"
- "rename old %s\n"
- "rename new %s\n",
- (int)(0.5 + score * 100 / MAX_SCORE),
- p->one->path, p->two->path);
+ for (j = 0; j < renq.nr; j++)
+ if (!strcmp(renq.queue[j]->one->path,
+ p->one->path))
+ break;
+ if (j < renq.nr)
+ /* this path remains */
+ pair_to_free = p;
}
+
+ if (pair_to_free)
+ ;
+ else
+ diff_q(&outq, p);
}
+ else if (!diff_unmodified_pair(p))
+ /* all the usual ones need to be kept */
+ diff_q(&outq, p);
else
- /* otherwise it is a modified (or stayed) entry */
- diff_queue(q, p->one, p->two);
- free(p);
- }
+ /* no need to keep unmodified pairs */
+ pair_to_free = p;
- free(outq.queue);
- debug_queue("done collapsing", q);
+ if (pair_to_free)
+ diff_free_filepair(pair_to_free);
+ }
+ diff_debug_queue("done copying original", &outq);
- cleanup:
- free(created.s);
- free(deleted.s);
- free(stay.s);
+ free(renq.queue);
+ free(q->queue);
+ *q = outq;
+ diff_debug_queue("done collapsing", q);
+
+ free(rename_dst);
+ rename_dst = NULL;
+ rename_dst_nr = rename_dst_alloc = 0;
+ free(rename_src);
+ rename_src = NULL;
+ rename_src_nr = rename_src_alloc = 0;
return;
}