Merge branch 'gs/commit-graph-path-filter'

Introduce an extension to the commit-graph to make it efficient to
check for the paths that were modified at each commit using Bloom
filters.

* gs/commit-graph-path-filter:
  bloom: ignore renames when computing changed paths
  commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag
  t4216: add end to end tests for git log with Bloom filters
  revision.c: add trace2 stats around Bloom filter usage
  revision.c: use Bloom filters to speed up path based revision walks
  commit-graph: add --changed-paths option to write subcommand
  commit-graph: reuse existing Bloom filters during write
  commit-graph: write Bloom filters to commit graph file
  commit-graph: examine commits by generation number
  commit-graph: examine changed-path objects in pack order
  commit-graph: compute Bloom filters for changed paths
  diff: halt tree-diff early after max_changes
  bloom.c: core Bloom filter implementation for changed paths.
  bloom.c: introduce core Bloom filter constructs
  bloom.c: add the murmur3 hash implementation
  commit-graph: define and use MAX_NUM_CHUNKS

4 files changed, 87 insertions, 0 deletions

diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
new file mode 100644
index 0000000..ce41266
--- /dev/null
+++ b/t/helper/test-bloom.c
@@ -0,0 +1,81 @@
+#include "git-compat-util.h"
+#include "bloom.h"
+#include "test-tool.h"
+#include "commit.h"
+
+struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
+
+static void add_string_to_filter(const char *data, struct bloom_filter *filter) {
+		struct bloom_key key;
+		int i;
+
+		fill_bloom_key(data, strlen(data), &key, &settings);
+		printf("Hashes:");
+		for (i = 0; i < settings.num_hashes; i++){
+			printf("0x%08x|", key.hashes[i]);
+		}
+		printf("\n");
+		add_key_to_filter(&key, filter, &settings);
+}
+
+static void print_bloom_filter(struct bloom_filter *filter) {
+	int i;
+
+	if (!filter) {
+		printf("No filter.\n");
+		return;
+	}
+	printf("Filter_Length:%d\n", (int)filter->len);
+	printf("Filter_Data:");
+	for (i = 0; i < filter->len; i++){
+		printf("%02x|", filter->data[i]);
+	}
+	printf("\n");
+}
+
+static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
+{
+	struct commit *c;
+	struct bloom_filter *filter;
+	setup_git_directory();
+	c = lookup_commit(the_repository, commit_oid);
+	filter = get_bloom_filter(the_repository, c, 1);
+	print_bloom_filter(filter);
+}
+
+int cmd__bloom(int argc, const char **argv)
+{
+	if (!strcmp(argv[1], "get_murmur3")) {
+		uint32_t hashed = murmur3_seeded(0, argv[2], strlen(argv[2]));
+		printf("Murmur3 Hash with seed=0:0x%08x\n", hashed);
+	}
+
+    if (!strcmp(argv[1], "generate_filter")) {
+		struct bloom_filter filter;
+		int i = 2;
+		filter.len =  (settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+		filter.data = xcalloc(filter.len, sizeof(unsigned char));
+
+		if (!argv[2]){
+			die("at least one input string expected");
+		}
+
+		while (argv[i]) {
+			add_string_to_filter(argv[i], &filter);
+			i++;
+		}
+
+		print_bloom_filter(&filter);
+	}
+
+    if (!strcmp(argv[1], "get_filter_for_commit")) {
+		struct object_id oid;
+		const char *end;
+		if (parse_oid_hex(argv[2], &oid, &end))
+			die("cannot parse oid '%s'", argv[2]);
+		init_bloom_filters();
+		get_bloom_filter_for_commit(&oid);
+	}
+
+	return 0;
+}
\ No newline at end of file
diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index 4846040..6d0c962 100644
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -34,6 +34,10 @@ int cmd__read_graph(int argc, const char **argv)
 		printf(" commit_metadata");
 	if (graph->chunk_extra_edges)
 		printf(" extra_edges");
+	if (graph->chunk_bloom_indexes)
+		printf(" bloom_indexes");
+	if (graph->chunk_bloom_data)
+		printf(" bloom_data");
 	printf("\n");
 
 	UNLEAK(graph);
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index 2ece4d1..590b2ef 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -15,6 +15,7 @@ struct test_cmd {
 
 static struct test_cmd cmds[] = {
 	{ "advise", cmd__advise_if_enabled },
+	{ "bloom", cmd__bloom },
 	{ "chmtime", cmd__chmtime },
 	{ "config", cmd__config },
 	{ "ctype", cmd__ctype },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index 1cbaec0..ddc8e99 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -5,6 +5,7 @@
 #include "git-compat-util.h"
 
 int cmd__advise_if_enabled(int argc, const char **argv);
+int cmd__bloom(int argc, const char **argv);
 int cmd__chmtime(int argc, const char **argv);
 int cmd__config(int argc, const char **argv);
 int cmd__ctype(int argc, const char **argv);