Merge branch 'ds/commit-graph-bloom-updates' into master

Updates to the changed-paths bloom filter.

* ds/commit-graph-bloom-updates:
  commit-graph: check all leading directories in changed path Bloom filters
  revision: empty pathspecs should not use Bloom filters
  revision.c: fix whitespace
  commit-graph: check chunk sizes after writing
  commit-graph: simplify chunk writes into loop
  commit-graph: unify the signatures of all write_graph_chunk_*() functions
  commit-graph: persist existence of changed-paths
  bloom: fix logic in get_bloom_filter()
  commit-graph: change test to die on parse, not load
  commit-graph: place bloom_settings in context

1 files changed, 44 insertions, 19 deletions

diff --git a/revision.c b/revision.c
index 049008c..6de29cd 100644
--- a/revision.c
+++ b/revision.c
@@ -633,7 +633,6 @@ static unsigned int count_bloom_filter_maybe;
 static unsigned int count_bloom_filter_definitely_not;
 static unsigned int count_bloom_filter_false_positive;
 static unsigned int count_bloom_filter_not_present;
-static unsigned int count_bloom_filter_length_zero;
 
 static void trace2_bloom_filter_statistics_atexit(void)
 {
@@ -641,7 +640,6 @@ static void trace2_bloom_filter_statistics_atexit(void)
 
 	jw_object_begin(&jw, 0);
 	jw_object_intmax(&jw, "filter_not_present", count_bloom_filter_not_present);
-	jw_object_intmax(&jw, "zero_length_filter", count_bloom_filter_length_zero);
 	jw_object_intmax(&jw, "maybe", count_bloom_filter_maybe);
 	jw_object_intmax(&jw, "definitely_not", count_bloom_filter_definitely_not);
 	jw_object_intmax(&jw, "false_positive", count_bloom_filter_false_positive);
@@ -670,9 +668,10 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 {
 	struct pathspec_item *pi;
 	char *path_alloc = NULL;
-	const char *path;
+	const char *path, *p;
 	int last_index;
-	int len;
+	size_t len;
+	int path_component_nr = 1;
 
 	if (!revs->commits)
 		return;
@@ -697,16 +696,45 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 
 	/* remove single trailing slash from path, if needed */
 	if (pi->match[last_index] == '/') {
-	    path_alloc = xstrdup(pi->match);
-	    path_alloc[last_index] = '\0';
-	    path = path_alloc;
+		path_alloc = xstrdup(pi->match);
+		path_alloc[last_index] = '\0';
+		path = path_alloc;
 	} else
-	    path = pi->match;
+		path = pi->match;
 
 	len = strlen(path);
+	if (!len) {
+		revs->bloom_filter_settings = NULL;
+		return;
+	}
+
+	p = path;
+	while (*p) {
+		/*
+		 * At this point, the path is normalized to use Unix-style
+		 * path separators. This is required due to how the
+		 * changed-path Bloom filters store the paths.
+		 */
+		if (*p == '/')
+			path_component_nr++;
+		p++;
+	}
+
+	revs->bloom_keys_nr = path_component_nr;
+	ALLOC_ARRAY(revs->bloom_keys, revs->bloom_keys_nr);
 
-	revs->bloom_key = xmalloc(sizeof(struct bloom_key));
-	fill_bloom_key(path, len, revs->bloom_key, revs->bloom_filter_settings);
+	fill_bloom_key(path, len, &revs->bloom_keys[0],
+		       revs->bloom_filter_settings);
+	path_component_nr = 1;
+
+	p = path + len - 1;
+	while (p > path) {
+		if (*p == '/')
+			fill_bloom_key(path, p - path,
+				       &revs->bloom_keys[path_component_nr++],
+				       revs->bloom_filter_settings);
+		p--;
+	}
 
 	if (trace2_is_enabled() && !bloom_filter_atexit_registered) {
 		atexit(trace2_bloom_filter_statistics_atexit);
@@ -720,7 +748,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 						 struct commit *commit)
 {
 	struct bloom_filter *filter;
-	int result;
+	int result = 1, j;
 
 	if (!revs->repo->objects->commit_graph)
 		return -1;
@@ -735,15 +763,12 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 		return -1;
 	}
 
-	if (!filter->len) {
-		count_bloom_filter_length_zero++;
-		return -1;
+	for (j = 0; result && j < revs->bloom_keys_nr; j++) {
+		result = bloom_filter_contains(filter,
+					       &revs->bloom_keys[j],
+					       revs->bloom_filter_settings);
 	}
 
-	result = bloom_filter_contains(filter,
-				       revs->bloom_key,
-				       revs->bloom_filter_settings);
-
 	if (result)
 		count_bloom_filter_maybe++;
 	else
@@ -782,7 +807,7 @@ static int rev_compare_tree(struct rev_info *revs,
 			return REV_TREE_SAME;
 	}
 
-	if (revs->bloom_key && !nth_parent) {
+	if (revs->bloom_keys_nr && !nth_parent) {
 		bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
 
 		if (bloom_ret == 0)