1 files changed, 232 insertions, 209 deletions

diff --git a/diffcore-rename.c b/diffcore-rename.c
index 63ac998bfa..7f03eb5a04 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -4,7 +4,8 @@
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
-#include "hash.h"
+#include "hashmap.h"
+#include "progress.h"
 
 /* Table of rename/copy destinations */
 
@@ -14,8 +15,7 @@ static struct diff_rename_dst {
 } *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;
 
@@ -26,50 +26,64 @@ static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
 		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" */
-	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));
-	}
+	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));
 	rename_dst[first].two = alloc_filespec(two->path);
-	fill_filespec(rename_dst[first].two, two->sha1, two->mode);
+	fill_filespec(rename_dst[first].two, two->sha1, two->sha1_valid, two->mode);
 	rename_dst[first].pair = NULL;
-	return &(rename_dst[first]);
+	return 0;
 }
 
 /* Table of rename/copy src files */
 static struct diff_rename_src {
-	struct diff_filespec *one;
+	struct diff_filepair *p;
 	unsigned short score; /* to remember the break score */
 } *rename_src;
 static int rename_src_nr, rename_src_alloc;
 
-static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
-						   unsigned short score)
+static struct diff_rename_src *register_rename_src(struct diff_filepair *p)
 {
 	int first, last;
+	struct diff_filespec *one = p->one;
+	unsigned short score = p->score;
 
 	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);
+		int cmp = strcmp(one->path, src->p->one->path);
 		if (!cmp)
 			return src;
 		if (cmp < 0) {
@@ -80,16 +94,12 @@ static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
 	}
 
 	/* 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));
-	}
+	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));
-	rename_src[first].one = one;
+	rename_src[first].p = p;
 	rename_src[first].score = score;
 	return &(rename_src[first]);
 }
@@ -153,9 +163,11 @@ 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, 1))
+	if (!src->cnt_data &&
+	    diff_populate_filespec(src, CHECK_SIZE_ONLY))
 		return 0;
-	if (!dst->cnt_data && diff_populate_filespec(dst, 1))
+	if (!dst->cnt_data &&
+	    diff_populate_filespec(dst, CHECK_SIZE_ONLY))
 		return 0;
 
 	max_size = ((src->size > dst->size) ? src->size : dst->size);
@@ -170,7 +182,7 @@ static int estimate_similarity(struct diff_filespec *src,
 	 * 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))
@@ -204,7 +216,7 @@ static void record_rename_pair(int dst_index, int src_index, int score)
 	if (rename_dst[dst_index].pair)
 		die("internal error: dst already matched.");
 
-	src = rename_src[src_index].one;
+	src = rename_src[src_index].p->one;
 	src->rename_used++;
 	src->count++;
 
@@ -241,133 +253,79 @@ static int score_compare(const void *a_, const void *b_)
 }
 
 struct file_similarity {
-	int src_dst, index;
+	struct hashmap_entry entry;
+	int 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 collision? */
-			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)
+static unsigned int hash_filespec(struct diff_filespec *filespec)
 {
-	while (p) {
-		struct file_similarity *entry = p;
-		p = p->next;
-		free(entry);
+	if (!filespec->sha1_valid) {
+		if (diff_populate_filespec(filespec, 0))
+			return 0;
+		hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
 	}
+	return sha1hash(filespec->sha1);
 }
 
-static int find_same_files(void *ptr)
+static int find_identical_files(struct hashmap *srcs,
+				int dst_index,
+				struct diff_options *options)
 {
-	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);
+	int renames = 0;
+
+	struct diff_filespec *target = rename_dst[dst_index].two;
+	struct file_similarity *p, *best = NULL;
+	int i = 100, best_score = -1;
 
 	/*
-	 * If we have both sources *and* destinations, see if
-	 * we can match them up
+	 * Find the best source match for specified destination.
 	 */
-	ret = (src && dst) ? find_identical_files(src, dst) : 0;
+	p = hashmap_get_from_hash(srcs, hash_filespec(target), NULL);
+	for (; p; p = hashmap_get_next(srcs, p)) {
+		int score;
+		struct diff_filespec *source = p->filespec;
 
-	/* Free the hashes and return the number of renames found */
-	free_similarity_list(src);
-	free_similarity_list(dst);
-	return ret;
-}
+		/* False hash collision? */
+		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;
+		if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
+			continue;
+		score += basename_same(source, target);
+		if (score > best_score) {
+			best = p;
+			best_score = score;
+			if (score == 2)
+				break;
+		}
 
-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);
+		/* Too many identical alternatives? Pick one */
+		if (!--i)
+			break;
+	}
+	if (best) {
+		record_rename_pair(dst_index, best->index, MAX_SCORE);
+		renames++;
 	}
-	memcpy(&hash, filespec->sha1, sizeof(hash));
-	return hash;
+	return renames;
 }
 
-static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec)
+static void insert_file_table(struct hashmap *table, 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;
-	}
+	hashmap_entry_init(entry, hash_filespec(filespec));
+	hashmap_add(table, entry);
 }
 
 /*
@@ -377,25 +335,26 @@ static void insert_file_table(struct hash_table *table, int src_dst, int index,
  * 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;
+	int i, renames = 0;
+	struct hashmap file_table;
 
-	init_hash(&file_table);
-	for (i = 0; i < rename_src_nr; i++)
-		insert_file_table(&file_table, -1, i, rename_src[i].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, rename_src_nr);
+	for (i = rename_src_nr-1; i >= 0; i--)
+		insert_file_table(&file_table, i, rename_src[i].p->one);
 
+	/* Walk the destinations and find best source match */
 	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);
+		renames += find_identical_files(&file_table, i, options);
 
-	/* .. and free the hash data structure */
-	free_hash(&file_table);
+	/* Free the hash data structure and entries */
+	hashmap_free(&file_table, 1);
 
-	return i;
+	return renames;
 }
 
 #define NUM_CANDIDATE_PER_DST 4
@@ -414,16 +373,86 @@ static void record_if_better(struct diff_score m[], struct diff_score *o)
 		m[worst] = *o;
 }
 
+/*
+ * Returns:
+ * 0 if we are under the limit;
+ * 1 if we need to disable inexact rename detection;
+ * 2 if we would be under the limit if we were given -C instead of -C -C.
+ */
+static int too_many_rename_candidates(int num_create,
+				      struct diff_options *options)
+{
+	int rename_limit = options->rename_limit;
+	int num_src = rename_src_nr;
+	int i;
+
+	options->needed_rename_limit = 0;
+
+	/*
+	 * This basically does a test for the rename matrix not
+	 * 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)
+		rename_limit = 32767;
+	if ((num_create <= rename_limit || num_src <= rename_limit) &&
+	    (num_create * num_src <= rename_limit * 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))
+		return 1;
+
+	/* Would we bust the limit if we were running under -C? */
+	for (num_src = i = 0; i < rename_src_nr; i++) {
+		if (diff_unmodified_pair(rename_src[i].p))
+			continue;
+		num_src++;
+	}
+	if ((num_create <= rename_limit || num_src <= rename_limit) &&
+	    (num_create * num_src <= rename_limit * rename_limit))
+		return 2;
+	return 1;
+}
+
+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].p->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;
 	int minimum_score = options->rename_score;
-	int rename_limit = options->rename_limit;
 	struct diff_queue_struct *q = &diff_queued_diff;
 	struct diff_queue_struct outq;
 	struct diff_score *mx;
-	int i, j, rename_count;
-	int num_create, num_src, dst_cnt;
+	int i, j, rename_count, skip_unmodified = 0;
+	int num_create, dst_cnt;
+	struct progress *progress = NULL;
 
 	if (!minimum_score)
 		minimum_score = DEFAULT_RENAME_SCORE;
@@ -436,10 +465,20 @@ void diffcore_rename(struct diff_options *options)
 			else if (options->single_follow &&
 				 strcmp(options->single_follow, p->two->path))
 				continue; /* not interested */
-			else
-				locate_rename_dst(p->two, 1);
+			else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
+				 is_empty_blob_sha1(p->two->sha1))
+				continue;
+			else if (add_rename_dst(p->two) < 0) {
+				warning("skipping rename detection, detected"
+					" duplicate destination '%s'",
+					p->two->path);
+				goto cleanup;
+			}
 		}
-		else if (!DIFF_FILE_VALID(p->two)) {
+		else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
+			 is_empty_blob_sha1(p->one->sha1))
+			continue;
+		else if (!DIFF_PAIR_UNMERGED(p) && !DIFF_FILE_VALID(p->two)) {
 			/*
 			 * If the source is a broken "delete", and
 			 * they did not really want to get broken,
@@ -449,7 +488,7 @@ void diffcore_rename(struct diff_options *options)
 			 */
 			if (p->broken_pair && !p->score)
 				p->one->rename_used++;
-			register_rename_src(p->one, p->score);
+			register_rename_src(p);
 		}
 		else if (detect_rename == DIFF_DETECT_COPY) {
 			/*
@@ -457,7 +496,7 @@ void diffcore_rename(struct diff_options *options)
 			 * one, to indicate ourselves as a user.
 			 */
 			p->one->rename_used++;
-			register_rename_src(p->one, p->score);
+			register_rename_src(p);
 		}
 	}
 	if (rename_dst_nr == 0 || rename_src_nr == 0)
@@ -467,7 +506,7 @@ void diffcore_rename(struct diff_options *options)
 	 * 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)
@@ -478,31 +517,29 @@ void diffcore_rename(struct diff_options *options)
 	 * 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:
-	 *
-	 *    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 ((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 (created: %d deleted: %d), skipping inexact rename detection", num_create, num_src);
+	switch (too_many_rename_candidates(num_create, options)) {
+	case 1:
 		goto cleanup;
+	case 2:
+		options->degraded_cc_to_c = 1;
+		skip_unmodified = 1;
+		break;
+	default:
+		break;
+	}
+
+	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));
+	mx = xcalloc(st_mult(num_create, NUM_CANDIDATE_PER_DST), sizeof(*mx));
 	for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
 		struct diff_filespec *two = rename_dst[i].two;
 		struct diff_score *m;
@@ -515,72 +552,59 @@ void diffcore_rename(struct diff_options *options)
 			m[j].dst = -1;
 
 		for (j = 0; j < rename_src_nr; j++) {
-			struct diff_filespec *one = rename_src[j].one;
+			struct diff_filespec *one = rename_src[j].p->one;
 			struct diff_score this_src;
+
+			if (skip_unmodified &&
+			    diff_unmodified_pair(rename_src[j].p))
+				continue;
+
 			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, 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 (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++;
-	}
+	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;
 
-		if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
+		if (DIFF_PAIR_UNMERGED(p)) {
+			diff_q(&outq, p);
+		}
+		else 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);
+			struct diff_rename_dst *dst = locate_rename_dst(p->two);
 			if (dst && dst->pair) {
 				diff_q(&outq, dst->pair);
 				pair_to_free = p;
@@ -610,8 +634,7 @@ void diffcore_rename(struct diff_options *options)
 			 */
 			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;