From: Taylor Blau <me@ttaylorr.com>
Date: Tue, 19 May 2026 15:57:42 +0000 (-0400)
Subject: midx: use `strset` for retained MIDX files
X-Git-Url: http://git.ipfire.org/gitweb/index.cgi?a=commitdiff_plain;h=ddaa7a6fb79038a30b59341ed3f0f2097014ccbf;p=thirdparty%2Fgit.git

midx: use `strset` for retained MIDX files

Both `clear_midx_files_ext()` and `clear_incremental_midx_files_ext()`
build a list of filenames to keep while pruning stale MIDX files. Today
they hand-roll an array instead of using a `strset`, thus requiring us
to pass an additional length parameter, and makes lookups linear.

Replace the bare array with a `strset` which can be passed around as a
single parameter. Though it improves lookup performance, the difference
is likely immeasurable given how small the keep_hashes array typically
is.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

diff --git a/midx.c b/midx.c
index 81d6ab11e6..f75e3c9fa6 100644
--- a/midx.c
+++ b/midx.c
@@ -758,8 +758,7 @@ int midx_checksum_valid(struct multi_pack_index *m)
 }
 
 struct clear_midx_data {
-	char **keep;
-	uint32_t keep_nr;
+	struct strset keep;
 	const char *ext;
 };
 
@@ -767,15 +766,12 @@ static void clear_midx_file_ext(const char *full_path, size_t full_path_len UNUS
 				const char *file_name, void *_data)
 {
 	struct clear_midx_data *data = _data;
-	uint32_t i;
 
 	if (!(starts_with(file_name, "multi-pack-index-") &&
 	      ends_with(file_name, data->ext)))
 		return;
-	for (i = 0; i < data->keep_nr; i++) {
-		if (!strcmp(data->keep[i], file_name))
-			return;
-	}
+	if (strset_contains(&data->keep, file_name))
+		return;
 	if (unlink(full_path))
 		die_errno(_("failed to remove %s"), full_path);
 }
@@ -783,48 +779,49 @@ static void clear_midx_file_ext(const char *full_path, size_t full_path_len UNUS
 void clear_midx_files_ext(struct odb_source *source, const char *ext,
 			  const char *keep_hash)
 {
-	struct clear_midx_data data;
-	memset(&data, 0, sizeof(struct clear_midx_data));
+	struct clear_midx_data data = {
+		.keep = STRSET_INIT,
+		.ext = ext,
+	};
 
 	if (keep_hash) {
-		ALLOC_ARRAY(data.keep, 1);
+		struct strbuf buf = STRBUF_INIT;
+		strbuf_addf(&buf, "multi-pack-index-%s.%s", keep_hash, ext);
+
+		strset_add(&data.keep, buf.buf);
 
-		data.keep[0] = xstrfmt("multi-pack-index-%s.%s", keep_hash, ext);
-		data.keep_nr = 1;
+		strbuf_release(&buf);
 	}
-	data.ext = ext;
 
-	for_each_file_in_pack_dir(source->path,
-				  clear_midx_file_ext,
-				  &data);
+	for_each_file_in_pack_dir(source->path, clear_midx_file_ext, &data);
 
-	if (keep_hash)
-		free(data.keep[0]);
-	free(data.keep);
+	strset_clear(&data.keep);
 }
 
 void clear_incremental_midx_files_ext(struct odb_source *source, const char *ext,
 				      char **keep_hashes,
 				      uint32_t hashes_nr)
 {
-	struct clear_midx_data data;
+	struct clear_midx_data data = {
+		.keep = STRSET_INIT,
+		.ext = ext,
+	};
+	struct strbuf buf = STRBUF_INIT;
 	uint32_t i;
 
-	memset(&data, 0, sizeof(struct clear_midx_data));
+	for (i = 0; i < hashes_nr; i++) {
+		strbuf_reset(&buf);
+		strbuf_addf(&buf, "multi-pack-index-%s.%s", keep_hashes[i],
+			    ext);
 
-	ALLOC_ARRAY(data.keep, hashes_nr);
-	for (i = 0; i < hashes_nr; i++)
-		data.keep[i] = xstrfmt("multi-pack-index-%s.%s", keep_hashes[i],
-				       ext);
-	data.keep_nr = hashes_nr;
-	data.ext = ext;
+		strset_add(&data.keep, buf.buf);
+	}
 
 	for_each_file_in_pack_subdir(source->path, "multi-pack-index.d",
 				     clear_midx_file_ext, &data);
 
-	for (i = 0; i < hashes_nr; i++)
-		free(data.keep[i]);
-	free(data.keep);
+	strbuf_release(&buf);
+	strset_clear(&data.keep);
 }
 
 void clear_midx_file(struct repository *r)