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

6 files changed, 49 insertions, 28 deletions

diff --git a/Documentation/technical/commit-graph-format.txt b/Documentation/technical/commit-graph-format.txt
index de56f9f1ef..1beef17182 100644
--- a/Documentation/technical/commit-graph-format.txt
+++ b/Documentation/technical/commit-graph-format.txt
@@ -97,10 +97,10 @@ CHUNK DATA:
       bit on. The other bits correspond to the position of the last parent.
 
   Bloom Filter Index (ID: {'B', 'I', 'D', 'X'}) (N * 4 bytes) [Optional]
-    * The ith entry, BIDX[i], stores the number of 8-byte word blocks in all
-      Bloom filters from commit 0 to commit i (inclusive) in lexicographic
-      order. The Bloom filter for the i-th commit spans from BIDX[i-1] to
-      BIDX[i] (plus header length), where BIDX[-1] is 0.
+    * The ith entry, BIDX[i], stores the number of bytes in all Bloom filters
+      from commit 0 to commit i (inclusive) in lexicographic order. The Bloom
+      filter for the i-th commit spans from BIDX[i-1] to BIDX[i] (plus header
+      length), where BIDX[-1] is 0.
     * The BIDX chunk is ignored if the BDAT chunk is not present.
 
   Bloom Filter Data (ID: {'B', 'D', 'A', 'T'}) [Optional]
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;
diff --git a/bloom.h b/bloom.h
index e0e59e0754..b2a8379a71 100644
--- a/bloom.h
+++ b/bloom.h
@@ -74,8 +74,8 @@ void fill_bloom_key(const char *data,
 		    const struct bloom_filter_settings *settings);
 
 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);
 
 void init_bloom_filters(void);
 
diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash
index b1d6e5ebed..70ad04e1b2 100644
--- a/contrib/completion/git-completion.bash
+++ b/contrib/completion/git-completion.bash
@@ -1860,6 +1860,7 @@ _git_log ()
 			$merge
 			$__git_diff_common_options
 			--pickaxe-all --pickaxe-regex
+			--patch --no-patch
 			"
 		return
 		;;
diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 456f5ea7f9..f0aa80b98e 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -44,7 +44,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 }
 
 static const char *bloom_usage = "\n"
-"  test-tool bloom get_murmer3 <string>\n"
+"  test-tool bloom get_murmur3 <string>\n"
 "  test-tool bloom generate_filter <string> [<string>...]\n"
 "  test-tool get_filter_for_commit <commit-hex>\n";
 
diff --git a/t/t0095-bloom.sh b/t/t0095-bloom.sh
index 809ec7b0b8..232ba2c485 100755
--- a/t/t0095-bloom.sh
+++ b/t/t0095-bloom.sh
@@ -89,8 +89,8 @@ test_expect_success 'get bloom filter for commit with 10 changes' '
 	git add smallDir &&
 	git commit -m "commit with 10 changes" &&
 	cat >expect <<-\EOF &&
-	Filter_Length:25
-	Filter_Data:82|a0|65|47|0c|92|90|c0|a1|40|02|a0|e2|40|e0|04|0a|9a|66|cf|80|19|85|42|23|
+	Filter_Length:14
+	Filter_Data:02|b3|c4|a0|34|e7|fe|eb|cb|47|fe|a0|e8|72|
 	EOF
 	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
 	test_cmp expect actual
@@ -100,7 +100,7 @@ test_expect_success EXPENSIVE 'get bloom filter for commit with 513 changes' '
 	rm actual &&
 	rm expect &&
 	mkdir bigDir &&
-	for i in $(test_seq 0 512)
+	for i in $(test_seq 0 511)
 	do
 		echo $i >bigDir/$i
 	done &&