Merge branch 'ds/partial-bundles'

Bundle file format gets extended to allow a partial bundle,
filtered by similar criteria you would give when making a
partial/lazy clone.

* ds/partial-bundles:
  clone: fail gracefully when cloning filtered bundle
  bundle: unbundle promisor packs
  bundle: create filtered bundles
  rev-list: move --filter parsing into revision.c
  bundle: parse filter capability
  list-objects: handle NULL function pointers
  MyFirstObjectWalk: update recommended usage
  list-objects: consolidate traverse_commit_list[_filtered]
  pack-bitmap: drop filter in prepare_bitmap_walk()
  pack-objects: use rev.filter when possible
  revision: put object filter into struct rev_info
  list-objects-filter-options: create copy helper
  index-pack: document and test the --promisor option

1 files changed, 62 insertions, 12 deletions

diff --git a/bundle.c b/bundle.c
index 7608701a51..e359370cfc 100644
--- a/bundle.c
+++ b/bundle.c
@@ -11,7 +11,7 @@
 #include "run-command.h"
 #include "refs.h"
 #include "strvec.h"
-
+#include "list-objects-filter-options.h"
 
 static const char v2_bundle_signature[] = "# v2 git bundle\n";
 static const char v3_bundle_signature[] = "# v3 git bundle\n";
@@ -33,6 +33,7 @@ void bundle_header_release(struct bundle_header *header)
 {
 	string_list_clear(&header->prerequisites, 1);
 	string_list_clear(&header->references, 1);
+	list_objects_filter_release(&header->filter);
 }
 
 static int parse_capability(struct bundle_header *header, const char *capability)
@@ -45,6 +46,10 @@ static int parse_capability(struct bundle_header *header, const char *capability
 		header->hash_algo = &hash_algos[algo];
 		return 0;
 	}
+	if (skip_prefix(capability, "filter=", &arg)) {
+		parse_list_objects_filter(&header->filter, arg);
+		return 0;
+	}
 	return error(_("unknown capability '%s'"), capability);
 }
 
@@ -220,6 +225,8 @@ int verify_bundle(struct repository *r,
 	req_nr = revs.pending.nr;
 	setup_revisions(2, argv, &revs, NULL);
 
+	list_objects_filter_copy(&revs.filter, &header->filter);
+
 	if (prepare_revision_walk(&revs))
 		die(_("revision walk setup failed"));
 
@@ -259,6 +266,12 @@ int verify_bundle(struct repository *r,
 			     r->nr),
 			  (uintmax_t)r->nr);
 		list_refs(r, 0, NULL);
+
+		if (header->filter.choice) {
+			printf_ln("The bundle uses this filter: %s",
+				  list_objects_filter_spec(&header->filter));
+		}
+
 		r = &header->prerequisites;
 		if (!r->nr) {
 			printf_ln(_("The bundle records a complete history."));
@@ -319,6 +332,9 @@ static int write_pack_data(int bundle_fd, struct rev_info *revs, struct strvec *
 		     "--stdout", "--thin", "--delta-base-offset",
 		     NULL);
 	strvec_pushv(&pack_objects.args, pack_options->v);
+	if (revs->filter.choice)
+		strvec_pushf(&pack_objects.args, "--filter=%s",
+			     list_objects_filter_spec(&revs->filter));
 	pack_objects.in = -1;
 	pack_objects.out = bundle_fd;
 	pack_objects.git_cmd = 1;
@@ -486,10 +502,37 @@ int create_bundle(struct repository *r, const char *path,
 	int bundle_to_stdout;
 	int ref_count = 0;
 	struct rev_info revs, revs_copy;
-	int min_version = the_hash_algo == &hash_algos[GIT_HASH_SHA1] ? 2 : 3;
+	int min_version = 2;
 	struct bundle_prerequisites_info bpi;
 	int i;
 
+	/* init revs to list objects for pack-objects later */
+	save_commit_buffer = 0;
+	repo_init_revisions(r, &revs, NULL);
+
+	/*
+	 * Pre-initialize the '--objects' flag so we can parse a
+	 * --filter option successfully.
+	 */
+	revs.tree_objects = revs.blob_objects = 1;
+
+	argc = setup_revisions(argc, argv, &revs, NULL);
+
+	/*
+	 * Reasons to require version 3:
+	 *
+	 * 1. @object-format is required because our hash algorithm is not
+	 *    SHA1.
+	 * 2. @filter is required because we parsed an object filter.
+	 */
+	if (the_hash_algo != &hash_algos[GIT_HASH_SHA1] || revs.filter.choice)
+		min_version = 3;
+
+	if (argc > 1) {
+		error(_("unrecognized argument: %s"), argv[1]);
+		goto err;
+	}
+
 	bundle_to_stdout = !strcmp(path, "-");
 	if (bundle_to_stdout)
 		bundle_fd = 1;
@@ -512,17 +555,14 @@ int create_bundle(struct repository *r, const char *path,
 		write_or_die(bundle_fd, capability, strlen(capability));
 		write_or_die(bundle_fd, the_hash_algo->name, strlen(the_hash_algo->name));
 		write_or_die(bundle_fd, "\n", 1);
-	}
 
-	/* init revs to list objects for pack-objects later */
-	save_commit_buffer = 0;
-	repo_init_revisions(r, &revs, NULL);
-
-	argc = setup_revisions(argc, argv, &revs, NULL);
-
-	if (argc > 1) {
-		error(_("unrecognized argument: %s"), argv[1]);
-		goto err;
+		if (revs.filter.choice) {
+			const char *value = expand_list_objects_filter_spec(&revs.filter);
+			capability = "@filter=";
+			write_or_die(bundle_fd, capability, strlen(capability));
+			write_or_die(bundle_fd, value, strlen(value));
+			write_or_die(bundle_fd, "\n", 1);
+		}
 	}
 
 	/* save revs.pending in revs_copy for later use */
@@ -544,6 +584,12 @@ int create_bundle(struct repository *r, const char *path,
 		die("revision walk setup failed");
 	bpi.fd = bundle_fd;
 	bpi.pending = &revs_copy.pending;
+
+	/*
+	 * Remove any object walking here. We only care about commits and
+	 * tags here. The revs_copy has the right instances of these values.
+	 */
+	revs.blob_objects = revs.tree_objects = 0;
 	traverse_commit_list(&revs, write_bundle_prerequisites, NULL, &bpi);
 	object_array_remove_duplicates(&revs_copy.pending);
 
@@ -574,6 +620,10 @@ int unbundle(struct repository *r, struct bundle_header *header,
 	struct child_process ip = CHILD_PROCESS_INIT;
 	strvec_pushl(&ip.args, "index-pack", "--fix-thin", "--stdin", NULL);
 
+	/* If there is a filter, then we need to create the promisor pack. */
+	if (header->filter.choice)
+		strvec_push(&ip.args, "--promisor=from-bundle");
+
 	if (extra_index_pack_args) {
 		strvec_pushv(&ip.args, extra_index_pack_args->v);
 		strvec_clear(extra_index_pack_args);