Merge branch 'ds/bloom-cleanup'

Code cleanup and typofixes

* ds/bloom-cleanup:
  completion: offer '--(no-)patch' among 'git log' options
  bloom: use num_changes not nr for limit detection
  bloom: de-duplicate directory entries
  Documentation: changed-path Bloom filters use byte words
  bloom: parse commit before computing filters
  test-bloom: fix usage typo
  bloom: fix whitespace around tab length

1 files changed, 38 insertions, 18 deletions

diff --git a/bloom.c b/bloom.c
index ee025e0c61..9b86aa3f59 100644
--- a/bloom.c
+++ b/bloom.c
@@ -29,8 +29,8 @@ static inline unsigned char get_bitmask(uint32_t pos)
 }
 
 static int load_bloom_filter_from_graph(struct commit_graph *g,
-				   struct bloom_filter *filter,
-				   struct commit *c)
+					struct bloom_filter *filter,
+					struct commit *c)
 {
 	uint32_t lex_pos, start_index, end_index;
 
@@ -123,9 +123,9 @@ uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len)
 }
 
 void fill_bloom_key(const char *data,
-					size_t len,
-					struct bloom_key *key,
-					const struct bloom_filter_settings *settings)
+		    size_t len,
+		    struct bloom_key *key,
+		    const struct bloom_filter_settings *settings)
 {
 	int i;
 	const uint32_t seed0 = 0x293ae76f;
@@ -139,8 +139,8 @@ void fill_bloom_key(const char *data,
 }
 
 void add_key_to_filter(const struct bloom_key *key,
-					   struct bloom_filter *filter,
-					   const struct bloom_filter_settings *settings)
+		       struct bloom_filter *filter,
+		       const struct bloom_filter_settings *settings)
 {
 	int i;
 	uint64_t mod = filter->len * BITS_PER_WORD;
@@ -158,9 +158,22 @@ void init_bloom_filters(void)
 	init_bloom_filter_slab(&bloom_filters);
 }
 
+static int pathmap_cmp(const void *hashmap_cmp_fn_data,
+		       const struct hashmap_entry *eptr,
+		       const struct hashmap_entry *entry_or_key,
+		       const void *keydata)
+{
+	const struct pathmap_hash_entry *e1, *e2;
+
+	e1 = container_of(eptr, const struct pathmap_hash_entry, entry);
+	e2 = container_of(entry_or_key, const struct pathmap_hash_entry, entry);
+
+	return strcmp(e1->path, e2->path);
+}
+
 struct bloom_filter *get_bloom_filter(struct repository *r,
 				      struct commit *c,
-					  int compute_if_not_present)
+				      int compute_if_not_present)
 {
 	struct bloom_filter *filter;
 	struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
@@ -193,35 +206,42 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
 	diffopt.max_changes = max_changes;
 	diff_setup_done(&diffopt);
 
+	/* ensure commit is parsed so we have parent information */
+	repo_parse_commit(r, c);
+
 	if (c->parents)
 		diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &diffopt);
 	else
 		diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
 	diffcore_std(&diffopt);
 
-	if (diff_queued_diff.nr <= max_changes) {
+	if (diffopt.num_changes <= max_changes) {
 		struct hashmap pathmap;
 		struct pathmap_hash_entry *e;
 		struct hashmap_iter iter;
-		hashmap_init(&pathmap, NULL, NULL, 0);
+		hashmap_init(&pathmap, pathmap_cmp, NULL, 0);
 
 		for (i = 0; i < diff_queued_diff.nr; i++) {
 			const char *path = diff_queued_diff.queue[i]->two->path;
 
 			/*
-			* Add each leading directory of the changed file, i.e. for
-			* 'dir/subdir/file' add 'dir' and 'dir/subdir' as well, so
-			* the Bloom filter could be used to speed up commands like
-			* 'git log dir/subdir', too.
-			*
-			* Note that directories are added without the trailing '/'.
-			*/
+			 * Add each leading directory of the changed file, i.e. for
+			 * 'dir/subdir/file' add 'dir' and 'dir/subdir' as well, so
+			 * the Bloom filter could be used to speed up commands like
+			 * 'git log dir/subdir', too.
+			 *
+			 * Note that directories are added without the trailing '/'.
+			 */
 			do {
 				char *last_slash = strrchr(path, '/');
 
 				FLEX_ALLOC_STR(e, path, path);
 				hashmap_entry_init(&e->entry, strhash(path));
-				hashmap_add(&pathmap, &e->entry);
+
+				if (!hashmap_get(&pathmap, &e->entry, NULL))
+					hashmap_add(&pathmap, &e->entry);
+				else
+					free(e);
 
 				if (!last_slash)
 					last_slash = (char*)path;