Merge branch 'tb/path-filter-fix'

The Bloom filter used for path limited history traversal was broken
on systems whose "char" is unsigned; update the implementation and
bump the format version to 2.

* tb/path-filter-fix:
  bloom: introduce `deinit_bloom_filters()`
  commit-graph: reuse existing Bloom filters where possible
  object.h: fix mis-aligned flag bits table
  commit-graph: new Bloom filter version that fixes murmur3
  commit-graph: unconditionally load Bloom filters
  bloom: prepare to discard incompatible Bloom filters
  bloom: annotate filters with hash version
  repo-settings: introduce commitgraph.changedPathsVersion
  t4216: test changed path filters with high bit paths
  t/helper/test-read-graph: implement `bloom-filters` mode
  bloom.h: make `load_bloom_filter_from_graph()` public
  t/helper/test-read-graph.c: extract `dump_graph_info()`
  gitformat-commit-graph: describe version 2 of BDAT
  commit-graph: ensure Bloom filters are read with consistent settings
  revision.c: consult Bloom filters for root commits
  t/t4216-log-bloom.sh: harden `test_bloom_filters_not_used()`

t/helper/test-bloom.c

@@ -51,6 +51,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
 
 static const char *bloom_usage = "\n"
 "  test-tool bloom get_murmur3 <string>\n"
+"  test-tool bloom get_murmur3_seven_highbit\n"
 "  test-tool bloom generate_filter <string> [<string>...]\n"
 "  test-tool bloom get_filter_for_commit <commit-hex>\n";
 
@@ -65,7 +66,13 @@ int cmd__bloom(int argc, const char **argv)
 		uint32_t hashed;
 		if (argc < 3)
 			usage(bloom_usage);
-		hashed = murmur3_seeded(0, argv[2], strlen(argv[2]));
+		hashed = murmur3_seeded_v2(0, argv[2], strlen(argv[2]));
+		printf("Murmur3 Hash with seed=0:0x%08x\n", hashed);
+	}
+
+	if (!strcmp(argv[1], "get_murmur3_seven_highbit")) {
+		uint32_t hashed;
+		hashed = murmur3_seeded_v2(0, "\x99\xaa\xbb\xcc\xdd\xee\xff", 7);
 		printf("Murmur3 Hash with seed=0:0x%08x\n", hashed);
 	}
 

t/helper/test-read-graph.c

@@ -7,20 +7,8 @@
 #include "bloom.h"
 #include "setup.h"
 
-int cmd__read_graph(int argc UNUSED, const char **argv UNUSED)
+static void dump_graph_info(struct commit_graph *graph)
 {
-	struct commit_graph *graph = NULL;
-	struct object_directory *odb;
-
-	setup_git_directory();
-	odb = the_repository->objects->odb;
-
-	prepare_repo_settings(the_repository);
-
-	graph = read_commit_graph_one(the_repository, odb);
-	if (!graph)
-		return 1;
-
 	printf("header: %08x %d %d %d %d\n",
 		ntohl(*(uint32_t*)graph->data),
 		*(unsigned char*)(graph->data + 4),
@@ -59,8 +47,57 @@ int cmd__read_graph(int argc UNUSED, const char **argv UNUSED)
 	if (graph->topo_levels)
 		printf(" topo_levels");
 	printf("\n");
+}
 
+static void dump_graph_bloom_filters(struct commit_graph *graph)
+{
+	uint32_t i;
+
+	for (i = 0; i < graph->num_commits + graph->num_commits_in_base; i++) {
+		struct bloom_filter filter = { 0 };
+		size_t j;
+
+		if (load_bloom_filter_from_graph(graph, &filter, i) < 0) {
+			fprintf(stderr, "missing Bloom filter for graph "
+				"position %"PRIu32"\n", i);
+			continue;
+		}
+
+		for (j = 0; j < filter.len; j++)
+			printf("%02x", filter.data[j]);
+		if (filter.len)
+			printf("\n");
+	}
+}
+
+int cmd__read_graph(int argc, const char **argv)
+{
+	struct commit_graph *graph = NULL;
+	struct object_directory *odb;
+	int ret = 0;
+
+	setup_git_directory();
+	odb = the_repository->objects->odb;
+
+	prepare_repo_settings(the_repository);
+
+	graph = read_commit_graph_one(the_repository, odb);
+	if (!graph) {
+		ret = 1;
+		goto done;
+	}
+
+	if (argc <= 1)
+		dump_graph_info(graph);
+	else if (!strcmp(argv[1], "bloom-filters"))
+		dump_graph_bloom_filters(graph);
+	else {
+		fprintf(stderr, "unknown sub-command: '%s'\n", argv[1]);
+		ret = 1;
+	}
+
+done:
 	UNLEAK(graph);
 
-	return 0;
+	return ret;
 }