bloom.c: core Bloom filter implementation for changed paths.

Add the core implementation for computing Bloom filters for
the paths changed between a commit and it's first parent.

We fill the Bloom filters as (const char *data, int len) pairs
as `struct bloom_filters" within a commit slab.

Filters for commits with no changes and more than 512 changes,
is represented with a filter of length zero. There is no gain
in distinguishing between a computed filter of length zero for
a commit with no changes, and an uncomputed filter for new commits
or for commits with more than 512 changes. The effect on
`git log -- path` is the same in both cases. We will fall back to
the normal diffing algorithm when we can't benefit from the
existence of Bloom filters.

Helped-by: Jeff King <peff@peff.net>
Helped-by: Derrick Stolee <dstolee@microsoft.com>
Reviewed-by: Jakub Narębski <jnareb@gmail.com>
Signed-off-by: Garima Singh <garima.singh@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 67 insertions, 0 deletions

diff --git a/t/helper/test-bloom.c b/t/helper/test-bloom.c
index 20460cde77..f18d1b722e 100644
--- a/t/helper/test-bloom.c
+++ b/t/helper/test-bloom.c
@@ -1,6 +1,7 @@
 #include "git-compat-util.h"
 #include "bloom.h"
 #include "test-tool.h"
+#include "commit.h"
 
 struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
 
@@ -32,6 +33,16 @@ static void print_bloom_filter(struct bloom_filter *filter) {
 	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);
+	print_bloom_filter(filter);
+}
+
 int cmd__bloom(int argc, const char **argv)
 {
 	if (!strcmp(argv[1], "get_murmur3")) {
@@ -57,5 +68,14 @@ int cmd__bloom(int argc, const char **argv)
 		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/t0095-bloom.sh b/t/t0095-bloom.sh
index 36a086c7c6..8f9eef116d 100755
--- a/t/t0095-bloom.sh
+++ b/t/t0095-bloom.sh
@@ -67,4 +67,51 @@ test_expect_success 'compute bloom key for test string 2' '
 	test_cmp expect actual
 '
 
+test_expect_success 'get bloom filters for commit with no changes' '
+	git init &&
+	git commit --allow-empty -m "c0" &&
+	cat >expect <<-\EOF &&
+	Filter_Length:0
+	Filter_Data:
+	EOF
+	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'get bloom filter for commit with 10 changes' '
+	rm actual &&
+	rm expect &&
+	mkdir smallDir &&
+	for i in $(test_seq 0 9)
+	do
+		echo $i >smallDir/$i
+	done &&
+	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|
+	EOF
+	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
+	test_cmp expect actual
+'
+
+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)
+	do
+		echo $i >bigDir/$i
+	done &&
+	git add bigDir &&
+	git commit -m "commit with 513 changes" &&
+	cat >expect <<-\EOF &&
+	Filter_Length:0
+	Filter_Data:
+	EOF
+	test-tool bloom get_filter_for_commit "$(git rev-parse HEAD)" >actual &&
+	test_cmp expect actual
+'
+
 test_done
\ No newline at end of file