From e44488eb16d03ac94211d84a6796befa1139bd72 Mon Sep 17 00:00:00 2001 From: Toon Claes Date: Fri, 7 Aug 2026 20:26:48 +0200 Subject: [PATCH] revision: expose check for paths maybe changed in Bloom filter check_maybe_different_in_bloom_filter() looks up a commit's changed-path Bloom filter and consults it to see whether the commit might have modified any of the paths in the pathspec that `revs` was set up with. In a follow-up commit we want to reuse this logic from another builtin. That caller, however, has already looked up the commit's Bloom filter for its own purposes, so having the function look it up again would mean a redundant lookup. Extract the filter-consulting part into a new public function, revs_maybe_changed_in_bloom(). This function takes an already looked-up `struct bloom_filter` instead of a commit. The existing check_maybe_different_in_bloom_filter() becomes a thin wrapper that looks up the filter and delegates. Expose the new function via revision.h so other builtins can reuse the exact same filtering that `git log ` performs. The existing function check_maybe_different_in_bloom_filter() returns a tristate value. This returns either: * `-1` : No Bloom filter was used. * `0` : The commit definitely did not change any of the paths. * `1` : The commit maybe changed one of the paths. These return values are used to keep count of false-positives. But because the new function revs_maybe_changed_in_bloom() is not involved in counting statistics, it returns a boolean value telling whether the commit definitely did not change any of the paths, or maybe changed some of them. Signed-off-by: Toon Claes Signed-off-by: Junio C Hamano --- revision.c | 30 ++++++++++++++++++++---------- revision.h | 12 ++++++++++++ 2 files changed, 32 insertions(+), 10 deletions(-) diff --git a/revision.c b/revision.c index 087d64d572..3628ef963d 100644 --- a/revision.c +++ b/revision.c @@ -750,7 +750,6 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs, struct commit *commit) { struct bloom_filter *filter; - int result = 0; if (!revs->bloom_keyvecs_nr) return -1; @@ -765,18 +764,29 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs, return -1; } - 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 (revs_maybe_changed_in_bloom(revs, filter)) { + count_bloom_filter_maybe++; + return 1; } - if (result) - count_bloom_filter_maybe++; - else - count_bloom_filter_definitely_not++; + count_bloom_filter_definitely_not++; - return result; + return 0; +} + +bool revs_maybe_changed_in_bloom(struct rev_info *revs, + struct bloom_filter *filter) +{ + if (!revs->bloom_keyvecs_nr || !filter) + return true; + + for (size_t nr = 0; nr < revs->bloom_keyvecs_nr; nr++) + if (bloom_filter_contains_vec(filter, + revs->bloom_keyvecs[nr], + revs->bloom_filter_settings)) + return true; + + return false; } static int rev_compare_tree(struct rev_info *revs, diff --git a/revision.h b/revision.h index 569b3fa1cb..14be39e20c 100644 --- a/revision.h +++ b/revision.h @@ -68,6 +68,7 @@ struct string_list; struct saved_parents; struct follow_pathspec_slab; struct bloom_keyvec; +struct bloom_filter; struct bloom_filter_settings; struct option; struct parse_opt_ctx_t; @@ -493,6 +494,17 @@ void reset_revision_walk(void); */ int prepare_revision_walk(struct rev_info *revs); +/** + * Consult a changed-path Bloom filter to determine if the commit to which the + * filter belongs might have changed any of the paths in the `revs`. + * prepare_revision_walk() needs to be called in advance to ensure + * pathspec key vectors are set up. + * + * Returns false iff the commit definitely did not change any of the paths. + */ +bool revs_maybe_changed_in_bloom(struct rev_info *revs, + struct bloom_filter *filter); + /* Drain the commits linked list into the priority queue. */ void rev_info_commit_list_to_queue(struct rev_info *revs); /**