On Mon, Apr 06, 2020 at 04:59:52PM +0000, Garima Singh via GitGitGadget wrote:

+static void prepare_to_use_bloom_filter(struct rev_info *revs)
+{
+	struct pathspec_item *pi;
+	char *path_alloc = NULL;
+	const char *path;
+	int last_index;
+	int len;
+
+	if (!revs->commits)
+	    return;
+
+	repo_parse_commit(revs->repo, revs->commits->item);
+
+	if (!revs->repo->objects->commit_graph)
+		return;
+
+	revs->bloom_filter_settings = revs->repo->objects->commit_graph->bloom_filter_settings;
+	if (!revs->bloom_filter_settings)
+		return;
+
+	pi = &revs->pruning.pathspec.items[0];
+	last_index = pi->len - 1;
+
+	/* remove single trailing slash from path, if needed */
+	if (pi->match[last_index] == '/') {
+	    path_alloc = xstrdup(pi->match);
+	    path_alloc[last_index] = '\0';
+	    path = path_alloc;

fill_bloom_key() takes a length parameter, so there is no need to
duplicate the path to be able to shorten it by one character to remove
that trailing '/'.

+	} else
+	    path = pi->match;
+
+	len = strlen(path);

'struct pathspec_item's 'len' field already contains the length of the
path, so there is no need for this strlen().

+
+	revs->bloom_key = xmalloc(sizeof(struct bloom_key));
+	fill_bloom_key(path, len, revs->bloom_key, revs->bloom_filter_settings);
+
+	free(path_alloc);
+}

                return 0;
        if (revs->limited) {
                if (limit_list(revs) < 0)
                        return -1;

I extended the hunk context a bit to show that
prepare_to_use_bloom_filter() is called before limit_list().  This is
important, because specifying exclude revs and pathspecs, i.e.  'git
log ^v1.2.3 -- dir/file' does perform a lot of diffs in limit_list(),
and this way we can take advantage of Bloom filters even in this case.