Sync 'ds/multi-pack-index' to v2.19.0-rc0

* ds/multi-pack-index: (23 commits)
  midx: clear midx on repack
  packfile: skip loading index if in multi-pack-index
  midx: prevent duplicate packfile loads
  midx: use midx in approximate_object_count
  midx: use existing midx when writing new one
  midx: use midx in abbreviation calculations
  midx: read objects from multi-pack-index
  config: create core.multiPackIndex setting
  midx: write object offsets
  midx: write object id fanout chunk
  midx: write object ids in a chunk
  midx: sort and deduplicate objects from packfiles
  midx: read pack names into array
  multi-pack-index: write pack names in chunk
  multi-pack-index: read packfile list
  packfile: generalize pack directory list
  t5319: expand test data
  multi-pack-index: load into memory
  midx: write header information to lockfile
  multi-pack-index: add 'write' verb
  ...

1 files changed, 70 insertions, 0 deletions

diff --git a/sha1-name.c b/sha1-name.c
index c9cc1318b7..6cccfbbfbf 100644
--- a/sha1-name.c
+++ b/sha1-name.c
@@ -12,6 +12,7 @@
 #include "packfile.h"
 #include "object-store.h"
 #include "repository.h"
+#include "midx.h"
 
 static int get_oid_oneline(const char *, struct object_id *, struct commit_list *);
 
@@ -149,6 +150,32 @@ static int match_sha(unsigned len, const unsigned char *a, const unsigned char *
 	return 1;
 }
 
+static void unique_in_midx(struct multi_pack_index *m,
+			   struct disambiguate_state *ds)
+{
+	uint32_t num, i, first = 0;
+	const struct object_id *current = NULL;
+	num = m->num_objects;
+
+	if (!num)
+		return;
+
+	bsearch_midx(&ds->bin_pfx, m, &first);
+
+	/*
+	 * At this point, "first" is the location of the lowest object
+	 * with an object name that could match "bin_pfx".  See if we have
+	 * 0, 1 or more objects that actually match(es).
+	 */
+	for (i = first; i < num && !ds->ambiguous; i++) {
+		struct object_id oid;
+		current = nth_midxed_object_oid(&oid, m, i);
+		if (!match_sha(ds->len, ds->bin_pfx.hash, current->hash))
+			break;
+		update_candidates(ds, current);
+	}
+}
+
 static void unique_in_pack(struct packed_git *p,
 			   struct disambiguate_state *ds)
 {
@@ -177,8 +204,12 @@ static void unique_in_pack(struct packed_git *p,
 
 static void find_short_packed_object(struct disambiguate_state *ds)
 {
+	struct multi_pack_index *m;
 	struct packed_git *p;
 
+	for (m = get_multi_pack_index(the_repository); m && !ds->ambiguous;
+	     m = m->next)
+		unique_in_midx(m, ds);
 	for (p = get_packed_git(the_repository); p && !ds->ambiguous;
 	     p = p->next)
 		unique_in_pack(p, ds);
@@ -529,6 +560,42 @@ static int extend_abbrev_len(const struct object_id *oid, void *cb_data)
 	return 0;
 }
 
+static void find_abbrev_len_for_midx(struct multi_pack_index *m,
+				     struct min_abbrev_data *mad)
+{
+	int match = 0;
+	uint32_t num, first = 0;
+	struct object_id oid;
+	const struct object_id *mad_oid;
+
+	if (!m->num_objects)
+		return;
+
+	num = m->num_objects;
+	mad_oid = mad->oid;
+	match = bsearch_midx(mad_oid, m, &first);
+
+	/*
+	 * first is now the position in the packfile where we would insert
+	 * mad->hash if it does not exist (or the position of mad->hash if
+	 * it does exist). Hence, we consider a maximum of two objects
+	 * nearby for the abbreviation length.
+	 */
+	mad->init_len = 0;
+	if (!match) {
+		if (nth_midxed_object_oid(&oid, m, first))
+			extend_abbrev_len(&oid, mad);
+	} else if (first < num - 1) {
+		if (nth_midxed_object_oid(&oid, m, first + 1))
+			extend_abbrev_len(&oid, mad);
+	}
+	if (first > 0) {
+		if (nth_midxed_object_oid(&oid, m, first - 1))
+			extend_abbrev_len(&oid, mad);
+	}
+	mad->init_len = mad->cur_len;
+}
+
 static void find_abbrev_len_for_pack(struct packed_git *p,
 				     struct min_abbrev_data *mad)
 {
@@ -567,8 +634,11 @@ static void find_abbrev_len_for_pack(struct packed_git *p,
 
 static void find_abbrev_len_packed(struct min_abbrev_data *mad)
 {
+	struct multi_pack_index *m;
 	struct packed_git *p;
 
+	for (m = get_multi_pack_index(the_repository); m; m = m->next)
+		find_abbrev_len_for_midx(m, mad);
 	for (p = get_packed_git(the_repository); p; p = p->next)
 		find_abbrev_len_for_pack(p, mad);
 }