aboutsummaryrefslogtreecommitdiffstats
path: root/revision.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2025-07-23 15:45:15 -0700
committerJunio C Hamano <gitster@pobox.com>2025-07-23 15:45:15 -0700
commitf22d4ac4fd50b55c88142dfd15a361680cf3fb40 (patch)
tree92a3be8ed47f75e15d2bda0932b6e4ca45d6d064 /revision.c
parent0e8243a355a69035dac269528b49dc8c9bc81f8a (diff)
parent2a6ce090f27016d68ee6952809d98fe88ce53522 (diff)
downloadgit-f22d4ac4fd50b55c88142dfd15a361680cf3fb40.tar.gz
Merge branch 'ly/changed-paths-traversal'
Lift the limitation to use changed-path filter in "git log" so that it can be used for a pathspec with multiple literal paths. * ly/changed-paths-traversal: bloom: optimize multiple pathspec items in revision revision: make helper for pathspec to bloom keyvec bloom: replace struct bloom_key * with struct bloom_keyvec bloom: rename function operates on bloom_key bloom: add test helper to return murmur3 hash
Diffstat (limited to 'revision.c')
-rw-r--r--revision.c122
1 files changed, 60 insertions, 62 deletions
diff --git a/revision.c b/revision.c
index 0ca6a297a6..212ca0de27 100644
--- a/revision.c
+++ b/revision.c
@@ -675,24 +675,48 @@ static int forbid_bloom_filters(struct pathspec *spec)
{
if (spec->has_wildcard)
return 1;
- if (spec->nr > 1)
- return 1;
if (spec->magic & ~PATHSPEC_LITERAL)
return 1;
- if (spec->nr && (spec->items[0].magic & ~PATHSPEC_LITERAL))
- return 1;
+ for (size_t nr = 0; nr < spec->nr; nr++)
+ if (spec->items[nr].magic & ~PATHSPEC_LITERAL)
+ return 1;
return 0;
}
-static void prepare_to_use_bloom_filter(struct rev_info *revs)
+static void release_revisions_bloom_keyvecs(struct rev_info *revs);
+
+static int convert_pathspec_to_bloom_keyvec(struct bloom_keyvec **out,
+ const struct pathspec_item *pi,
+ const struct bloom_filter_settings *settings)
{
- struct pathspec_item *pi;
char *path_alloc = NULL;
- const char *path, *p;
+ const char *path;
size_t len;
- int path_component_nr = 1;
+ int res = 0;
+
+ /* remove single trailing slash from path, if needed */
+ if (pi->len > 0 && pi->match[pi->len - 1] == '/') {
+ path_alloc = xmemdupz(pi->match, pi->len - 1);
+ path = path_alloc;
+ } else
+ path = pi->match;
+ len = strlen(path);
+ if (!len) {
+ res = -1;
+ goto cleanup;
+ }
+
+ *out = bloom_keyvec_new(path, len, settings);
+
+cleanup:
+ free(path_alloc);
+ return res;
+}
+
+static void prepare_to_use_bloom_filter(struct rev_info *revs)
+{
if (!revs->commits)
return;
@@ -708,48 +732,14 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
if (!revs->pruning.pathspec.nr)
return;
- pi = &revs->pruning.pathspec.items[0];
-
- /* remove single trailing slash from path, if needed */
- if (pi->len > 0 && pi->match[pi->len - 1] == '/') {
- path_alloc = xmemdupz(pi->match, pi->len - 1);
- path = path_alloc;
- } else
- path = pi->match;
-
- len = strlen(path);
- if (!len) {
- revs->bloom_filter_settings = NULL;
- free(path_alloc);
- 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_keyvecs_nr = revs->pruning.pathspec.nr;
+ CALLOC_ARRAY(revs->bloom_keyvecs, revs->bloom_keyvecs_nr);
- revs->bloom_keys_nr = path_component_nr;
- ALLOC_ARRAY(revs->bloom_keys, revs->bloom_keys_nr);
-
- 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--;
+ for (int i = 0; i < revs->pruning.pathspec.nr; i++) {
+ if (convert_pathspec_to_bloom_keyvec(&revs->bloom_keyvecs[i],
+ &revs->pruning.pathspec.items[i],
+ revs->bloom_filter_settings))
+ goto fail;
}
if (trace2_is_enabled() && !bloom_filter_atexit_registered) {
@@ -757,14 +747,18 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
bloom_filter_atexit_registered = 1;
}
- free(path_alloc);
+ return;
+
+fail:
+ revs->bloom_filter_settings = NULL;
+ release_revisions_bloom_keyvecs(revs);
}
static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
struct commit *commit)
{
struct bloom_filter *filter;
- int result = 1, j;
+ int result = 0;
if (!revs->repo->objects->commit_graph)
return -1;
@@ -779,10 +773,10 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
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);
+ for (size_t nr = 0; !result && nr < revs->bloom_keyvecs_nr; nr++) {
+ result = bloom_filter_contains_vec(filter,
+ revs->bloom_keyvecs[nr],
+ revs->bloom_filter_settings);
}
if (result)
@@ -823,7 +817,7 @@ static int rev_compare_tree(struct rev_info *revs,
return REV_TREE_SAME;
}
- if (revs->bloom_keys_nr && !nth_parent) {
+ if (revs->bloom_keyvecs_nr && !nth_parent) {
bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
if (bloom_ret == 0)
@@ -850,7 +844,7 @@ static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit,
if (!t1)
return 0;
- if (!nth_parent && revs->bloom_keys_nr) {
+ if (!nth_parent && revs->bloom_keyvecs_nr) {
bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
if (!bloom_ret)
return 1;
@@ -3202,6 +3196,14 @@ static void release_revisions_mailmap(struct string_list *mailmap)
static void release_revisions_topo_walk_info(struct topo_walk_info *info);
+static void release_revisions_bloom_keyvecs(struct rev_info *revs)
+{
+ for (size_t nr = 0; nr < revs->bloom_keyvecs_nr; nr++)
+ bloom_keyvec_free(revs->bloom_keyvecs[nr]);
+ FREE_AND_NULL(revs->bloom_keyvecs);
+ revs->bloom_keyvecs_nr = 0;
+}
+
static void free_void_commit_list(void *list)
{
free_commit_list(list);
@@ -3230,11 +3232,7 @@ void release_revisions(struct rev_info *revs)
clear_decoration(&revs->treesame, free);
line_log_free(revs);
oidset_clear(&revs->missing_commits);
-
- for (int i = 0; i < revs->bloom_keys_nr; i++)
- clear_bloom_key(&revs->bloom_keys[i]);
- FREE_AND_NULL(revs->bloom_keys);
- revs->bloom_keys_nr = 0;
+ release_revisions_bloom_keyvecs(revs);
}
static void add_child(struct rev_info *revs, struct commit *parent, struct commit *child)