1 files changed, 243 insertions, 78 deletions

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 5790f0d554..85868162ee 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -31,13 +31,18 @@ static const char *fast_export_usage[] = {
 };
 
 static int progress;
-static enum { ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = ABORT;
-static enum { ERROR, DROP, REWRITE } tag_of_filtered_mode = ERROR;
+static enum { SIGNED_TAG_ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT;
+static enum { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT;
+static enum { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT;
 static int fake_missing_tagger;
 static int use_done_feature;
 static int no_data;
 static int full_tree;
+static int reference_excluded_commits;
+static int show_original_ids;
+static int mark_tags;
 static struct string_list extra_refs = STRING_LIST_INIT_NODUP;
+static struct string_list tag_refs = STRING_LIST_INIT_NODUP;
 static struct refspec refspecs = REFSPEC_INIT_FETCH;
 static int anonymize;
 static struct revision_sources revision_sources;
@@ -46,7 +51,7 @@ static int parse_opt_signed_tag_mode(const struct option *opt,
 				     const char *arg, int unset)
 {
 	if (unset || !strcmp(arg, "abort"))
-		signed_tag_mode = ABORT;
+		signed_tag_mode = SIGNED_TAG_ABORT;
 	else if (!strcmp(arg, "verbatim") || !strcmp(arg, "ignore"))
 		signed_tag_mode = VERBATIM;
 	else if (!strcmp(arg, "warn"))
@@ -64,7 +69,7 @@ static int parse_opt_tag_of_filtered_mode(const struct option *opt,
 					  const char *arg, int unset)
 {
 	if (unset || !strcmp(arg, "abort"))
-		tag_of_filtered_mode = ERROR;
+		tag_of_filtered_mode = TAG_FILTERING_ABORT;
 	else if (!strcmp(arg, "drop"))
 		tag_of_filtered_mode = DROP;
 	else if (!strcmp(arg, "rewrite"))
@@ -74,6 +79,31 @@ static int parse_opt_tag_of_filtered_mode(const struct option *opt,
 	return 0;
 }
 
+static int parse_opt_reencode_mode(const struct option *opt,
+				   const char *arg, int unset)
+{
+	if (unset) {
+		reencode_mode = REENCODE_ABORT;
+		return 0;
+	}
+
+	switch (git_parse_maybe_bool(arg)) {
+	case 0:
+		reencode_mode = REENCODE_NO;
+		break;
+	case 1:
+		reencode_mode = REENCODE_YES;
+		break;
+	default:
+		if (!strcasecmp(arg, "abort"))
+			reencode_mode = REENCODE_ABORT;
+		else
+			return error("Unknown reencoding mode: %s", arg);
+	}
+
+	return 0;
+}
+
 static struct decoration idnums;
 static uint32_t last_idnum;
 
@@ -97,10 +127,15 @@ struct anonymized_entry {
 };
 
 static int anonymized_entry_cmp(const void *unused_cmp_data,
-				const void *va, const void *vb,
+				const struct hashmap_entry *eptr,
+				const struct hashmap_entry *entry_or_key,
 				const void *unused_keydata)
 {
-	const struct anonymized_entry *a = va, *b = vb;
+	const struct anonymized_entry *a, *b;
+
+	a = container_of(eptr, const struct anonymized_entry, hash);
+	b = container_of(entry_or_key, const struct anonymized_entry, hash);
+
 	return a->orig_len != b->orig_len ||
 		memcmp(a->orig, b->orig, a->orig_len);
 }
@@ -119,10 +154,10 @@ static const void *anonymize_mem(struct hashmap *map,
 	if (!map->cmpfn)
 		hashmap_init(map, anonymized_entry_cmp, NULL, 0);
 
-	hashmap_entry_init(&key, memhash(orig, *len));
+	hashmap_entry_init(&key.hash, memhash(orig, *len));
 	key.orig = orig;
 	key.orig_len = *len;
-	ret = hashmap_get(map, &key, NULL);
+	ret = hashmap_get_entry(map, &key, hash, NULL);
 
 	if (!ret) {
 		ret = xmalloc(sizeof(*ret));
@@ -131,7 +166,7 @@ static const void *anonymize_mem(struct hashmap *map,
 		ret->orig_len = *len;
 		ret->anon = generate(orig, len);
 		ret->anon_len = *len;
-		hashmap_put(map, ret);
+		hashmap_put(map, &ret->hash);
 	}
 
 	*len = ret->anon_len;
@@ -187,6 +222,22 @@ static int get_object_mark(struct object *object)
 	return ptr_to_mark(decoration);
 }
 
+static struct commit *rewrite_commit(struct commit *p)
+{
+	for (;;) {
+		if (p->parents && p->parents->next)
+			break;
+		if (p->object.flags & UNINTERESTING)
+			break;
+		if (!(p->object.flags & TREESAME))
+			break;
+		if (!p->parents)
+			return NULL;
+		p = p->parents->item;
+	}
+	return p;
+}
+
 static void show_progress(void)
 {
 	static int counter = 0;
@@ -230,7 +281,7 @@ static void export_blob(const struct object_id *oid)
 	if (is_null_oid(oid))
 		return;
 
-	object = lookup_object(the_repository, oid->hash);
+	object = lookup_object(the_repository, oid);
 	if (object && object->flags & SHOWN)
 		return;
 
@@ -242,8 +293,9 @@ static void export_blob(const struct object_id *oid)
 		buf = read_object_file(oid, &type, &size);
 		if (!buf)
 			die("could not read blob %s", oid_to_hex(oid));
-		if (check_object_signature(oid, buf, size, type_name(type)) < 0)
-			die("sha1 mismatch in blob %s", oid_to_hex(oid));
+		if (check_object_signature(the_repository, oid, buf, size,
+					   type_name(type)) < 0)
+			die("oid mismatch in blob %s", oid_to_hex(oid));
 		object = parse_object_buffer(the_repository, oid, type,
 					     size, buf, &eaten);
 	}
@@ -253,7 +305,10 @@ static void export_blob(const struct object_id *oid)
 
 	mark_next_object(object);
 
-	printf("blob\nmark :%"PRIu32"\ndata %"PRIuMAX"\n", last_idnum, (uintmax_t)size);
+	printf("blob\nmark :%"PRIu32"\n", last_idnum);
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(oid));
+	printf("data %"PRIuMAX"\n", (uintmax_t)size);
 	if (size && fwrite(buf, size, 1, stdout) != 1)
 		die_errno("could not write blob '%s'", oid_to_hex(oid));
 	printf("\n");
@@ -330,17 +385,18 @@ static void print_path(const char *path)
 
 static void *generate_fake_oid(const void *old, size_t *len)
 {
-	static uint32_t counter = 1; /* avoid null sha1 */
-	unsigned char *out = xcalloc(GIT_SHA1_RAWSZ, 1);
-	put_be32(out + GIT_SHA1_RAWSZ - 4, counter++);
+	static uint32_t counter = 1; /* avoid null oid */
+	const unsigned hashsz = the_hash_algo->rawsz;
+	unsigned char *out = xcalloc(hashsz, 1);
+	put_be32(out + hashsz - 4, counter++);
 	return out;
 }
 
-static const unsigned char *anonymize_sha1(const struct object_id *oid)
+static const struct object_id *anonymize_oid(const struct object_id *oid)
 {
-	static struct hashmap sha1s;
-	size_t len = GIT_SHA1_RAWSZ;
-	return anonymize_mem(&sha1s, generate_fake_oid, oid, &len);
+	static struct hashmap objs;
+	size_t len = the_hash_algo->rawsz;
+	return anonymize_mem(&objs, generate_fake_oid, oid, &len);
 }
 
 static void show_filemodify(struct diff_queue_struct *q,
@@ -399,12 +455,12 @@ static void show_filemodify(struct diff_queue_struct *q,
 			 */
 			if (no_data || S_ISGITLINK(spec->mode))
 				printf("M %06o %s ", spec->mode,
-				       sha1_to_hex(anonymize ?
-						   anonymize_sha1(&spec->oid) :
-						   spec->oid.hash));
+				       oid_to_hex(anonymize ?
+						  anonymize_oid(&spec->oid) :
+						  &spec->oid));
 			else {
 				struct object *object = lookup_object(the_repository,
-								      spec->oid.hash);
+								      &spec->oid);
 				printf("M %06o :%d ", spec->mode,
 				       get_object_mark(object));
 			}
@@ -430,7 +486,7 @@ static const char *find_encoding(const char *begin, const char *end)
 	bol = memmem(begin, end ? end - begin : strlen(begin),
 		     needle, strlen(needle));
 	if (!bol)
-		return git_commit_encoding;
+		return NULL;
 	bol += strlen(needle);
 	eol = strchrnul(bol, '\n');
 	*eol = '\0';
@@ -579,7 +635,8 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 		message += 2;
 
 	if (commit->parents &&
-	    get_object_mark(&commit->parents->item->object) != 0 &&
+	    (get_object_mark(&commit->parents->item->object) != 0 ||
+	     reference_excluded_commits) &&
 	    !full_tree) {
 		parse_commit_or_die(commit->parents->item);
 		diff_tree_oid(get_commit_tree_oid(commit->parents->item),
@@ -595,6 +652,13 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 			export_blob(&diff_queued_diff.queue[i]->two->oid);
 
 	refname = *revision_sources_at(&revision_sources, commit);
+	/*
+	 * FIXME: string_list_remove() below for each ref is overall
+	 * O(N^2).  Compared to a history walk and diffing trees, this is
+	 * just lost in the noise in practice.  However, theoretically a
+	 * repo may have enough refs for this to become slow.
+	 */
+	string_list_remove(&extra_refs, refname, 0);
 	if (anonymize) {
 		refname = anonymize_refname(refname);
 		anonymize_ident_line(&committer, &committer_end);
@@ -602,16 +666,32 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	}
 
 	mark_next_object(&commit->object);
-	if (anonymize)
+	if (anonymize) {
 		reencoded = anonymize_commit_message(message);
-	else if (!is_encoding_utf8(encoding))
-		reencoded = reencode_string(message, "UTF-8", encoding);
+	} else if (encoding) {
+		switch(reencode_mode) {
+		case REENCODE_YES:
+			reencoded = reencode_string(message, "UTF-8", encoding);
+			break;
+		case REENCODE_NO:
+			break;
+		case REENCODE_ABORT:
+			die("Encountered commit-specific encoding %s in commit "
+			    "%s; use --reencode=[yes|no] to handle it",
+			    encoding, oid_to_hex(&commit->object.oid));
+		}
+	}
 	if (!commit->parents)
 		printf("reset %s\n", refname);
-	printf("commit %s\nmark :%"PRIu32"\n%.*s\n%.*s\ndata %u\n%s",
-	       refname, last_idnum,
+	printf("commit %s\nmark :%"PRIu32"\n", refname, last_idnum);
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
+	printf("%.*s\n%.*s\n",
 	       (int)(author_end - author), author,
-	       (int)(committer_end - committer), committer,
+	       (int)(committer_end - committer), committer);
+	if (!reencoded && encoding)
+		printf("encoding %s\n", encoding);
+	printf("data %u\n%s",
 	       (unsigned)(reencoded
 			  ? strlen(reencoded) : message
 			  ? strlen(message) : 0),
@@ -620,13 +700,21 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	unuse_commit_buffer(commit, commit_buffer);
 
 	for (i = 0, p = commit->parents; p; p = p->next) {
-		int mark = get_object_mark(&p->item->object);
-		if (!mark)
+		struct object *obj = &p->item->object;
+		int mark = get_object_mark(obj);
+
+		if (!mark && !reference_excluded_commits)
 			continue;
 		if (i == 0)
-			printf("from :%d\n", mark);
+			printf("from ");
+		else
+			printf("merge ");
+		if (mark)
+			printf(":%d\n", mark);
 		else
-			printf("merge :%d\n", mark);
+			printf("%s\n", oid_to_hex(anonymize ?
+						  anonymize_oid(&obj->oid) :
+						  &obj->oid));
 		i++;
 	}
 
@@ -727,7 +815,7 @@ static void handle_tag(const char *name, struct tag *tag)
 					       "\n-----BEGIN PGP SIGNATURE-----\n");
 		if (signature)
 			switch(signed_tag_mode) {
-			case ABORT:
+			case SIGNED_TAG_ABORT:
 				die("encountered signed tag %s; use "
 				    "--signed-tags=<mode> to handle it",
 				    oid_to_hex(&tag->object.oid));
@@ -752,7 +840,7 @@ static void handle_tag(const char *name, struct tag *tag)
 	tagged_mark = get_object_mark(tagged);
 	if (!tagged_mark) {
 		switch(tag_of_filtered_mode) {
-		case ABORT:
+		case TAG_FILTERING_ABORT:
 			die("tag %s tags unexported object; use "
 			    "--tag-of-filtered-object=<mode> to handle it",
 			    oid_to_hex(&tag->object.oid));
@@ -761,32 +849,42 @@ static void handle_tag(const char *name, struct tag *tag)
 			free(buf);
 			return;
 		case REWRITE:
-			if (tagged->type != OBJ_COMMIT) {
-				die("tag %s tags unexported %s!",
-				    oid_to_hex(&tag->object.oid),
-				    type_name(tagged->type));
+			if (tagged->type == OBJ_TAG && !mark_tags) {
+				die(_("Error: Cannot export nested tags unless --mark-tags is specified."));
+			} else if (tagged->type == OBJ_COMMIT) {
+				p = rewrite_commit((struct commit *)tagged);
+				if (!p) {
+					printf("reset %s\nfrom %s\n\n",
+					       name, oid_to_hex(&null_oid));
+					free(buf);
+					return;
+				}
+				tagged_mark = get_object_mark(&p->object);
+			} else {
+				/* tagged->type is either OBJ_BLOB or OBJ_TAG */
+				tagged_mark = get_object_mark(tagged);
 			}
-			p = (struct commit *)tagged;
-			for (;;) {
-				if (p->parents && p->parents->next)
-					break;
-				if (p->object.flags & UNINTERESTING)
-					break;
-				if (!(p->object.flags & TREESAME))
-					break;
-				if (!p->parents)
-					die("can't find replacement commit for tag %s",
-					     oid_to_hex(&tag->object.oid));
-				p = p->parents->item;
-			}
-			tagged_mark = get_object_mark(&p->object);
 		}
 	}
 
-	if (starts_with(name, "refs/tags/"))
-		name += 10;
-	printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
-	       name, tagged_mark,
+	if (tagged->type == OBJ_TAG) {
+		printf("reset %s\nfrom %s\n\n",
+		       name, oid_to_hex(&null_oid));
+	}
+	skip_prefix(name, "refs/tags/", &name);
+	printf("tag %s\n", name);
+	if (mark_tags) {
+		mark_next_object(&tag->object);
+		printf("mark :%"PRIu32"\n", last_idnum);
+	}
+	if (tagged_mark)
+		printf("from :%d\n", tagged_mark);
+	else
+		printf("from %s\n", oid_to_hex(&tagged->oid));
+
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(&tag->object.oid));
+	printf("%.*s%sdata %d\n%.*s\n",
 	       (int)(tagger_end - tagger), tagger,
 	       tagger == tagger_end ? "" : "\n",
 	       (int)message_size, (int)message_size, message ? message : "");
@@ -804,7 +902,7 @@ static struct commit *get_commit(struct rev_cmdline_entry *e, char *full_name)
 		/* handle nested tags */
 		while (tag && tag->object.type == OBJ_TAG) {
 			parse_object(the_repository, &tag->object.oid);
-			string_list_append(&extra_refs, full_name)->util = tag;
+			string_list_append(&tag_refs, full_name)->util = tag;
 			tag = (struct tag *)tag->tagged;
 		}
 		if (!tag)
@@ -863,25 +961,30 @@ static void get_tags_and_duplicates(struct rev_cmdline_info *info)
 		}
 
 		/*
-		 * This ref will not be updated through a commit, lets make
-		 * sure it gets properly updated eventually.
+		 * Make sure this ref gets properly updated eventually, whether
+		 * through a commit or manually at the end.
 		 */
-		if (*revision_sources_at(&revision_sources, commit) ||
-		    commit->object.flags & SHOWN)
+		if (e->item->type != OBJ_TAG)
 			string_list_append(&extra_refs, full_name)->util = commit;
+
 		if (!*revision_sources_at(&revision_sources, commit))
 			*revision_sources_at(&revision_sources, commit) = full_name;
 	}
+
+	string_list_sort(&extra_refs);
+	string_list_remove_duplicates(&extra_refs, 0);
 }
 
-static void handle_tags_and_duplicates(void)
+static void handle_tags_and_duplicates(struct string_list *extras)
 {
 	struct commit *commit;
 	int i;
 
-	for (i = extra_refs.nr - 1; i >= 0; i--) {
-		const char *name = extra_refs.items[i].string;
-		struct object *object = extra_refs.items[i].util;
+	for (i = extras->nr - 1; i >= 0; i--) {
+		const char *name = extras->items[i].string;
+		struct object *object = extras->items[i].util;
+		int mark;
+
 		switch (object->type) {
 		case OBJ_TAG:
 			handle_tag(name, (struct tag *)object);
@@ -890,9 +993,45 @@ static void handle_tags_and_duplicates(void)
 			if (anonymize)
 				name = anonymize_refname(name);
 			/* create refs pointing to already seen commits */
-			commit = (struct commit *)object;
-			printf("reset %s\nfrom :%d\n\n", name,
-			       get_object_mark(&commit->object));
+			commit = rewrite_commit((struct commit *)object);
+			if (!commit) {
+				/*
+				 * Neither this object nor any of its
+				 * ancestors touch any relevant paths, so
+				 * it has been filtered to nothing.  Delete
+				 * it.
+				 */
+				printf("reset %s\nfrom %s\n\n",
+				       name, oid_to_hex(&null_oid));
+				continue;
+			}
+
+			mark = get_object_mark(&commit->object);
+			if (!mark) {
+				/*
+				 * Getting here means we have a commit which
+				 * was excluded by a negative refspec (e.g.
+				 * fast-export ^master master).  If we are
+				 * referencing excluded commits, set the ref
+				 * to the exact commit.  Otherwise, the user
+				 * wants the branch exported but every commit
+				 * in its history to be deleted, which basically
+				 * just means deletion of the ref.
+				 */
+				if (!reference_excluded_commits) {
+					/* delete the ref */
+					printf("reset %s\nfrom %s\n\n",
+					       name, oid_to_hex(&null_oid));
+					continue;
+				}
+				/* set ref to commit using oid, not mark */
+				printf("reset %s\nfrom %s\n\n", name,
+				       oid_to_hex(&commit->object.oid));
+				continue;
+			}
+
+			printf("reset %s\nfrom :%d\n\n", name, mark
+			       );
 			show_progress();
 			break;
 		}
@@ -929,11 +1068,16 @@ static void export_marks(char *file)
 		error("Unable to write marks file %s.", file);
 }
 
-static void import_marks(char *input_file)
+static void import_marks(char *input_file, int check_exists)
 {
 	char line[512];
-	FILE *f = xfopen(input_file, "r");
+	FILE *f;
+	struct stat sb;
 
+	if (check_exists && stat(input_file, &sb))
+		return;
+
+	f = xfopen(input_file, "r");
 	while (fgets(line, sizeof(line), f)) {
 		uint32_t mark;
 		char *line_end, *mark_end;
@@ -988,7 +1132,7 @@ static void handle_deletes(void)
 			continue;
 
 		printf("reset %s\nfrom %s\n\n",
-				refspec->dst, sha1_to_hex(null_sha1));
+				refspec->dst, oid_to_hex(&null_oid));
 	}
 }
 
@@ -997,7 +1141,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	struct rev_info revs;
 	struct object_array commits = OBJECT_ARRAY_INIT;
 	struct commit *commit;
-	char *export_filename = NULL, *import_filename = NULL;
+	char *export_filename = NULL,
+	     *import_filename = NULL,
+	     *import_filename_if_exists = NULL;
 	uint32_t lastimportid;
 	struct string_list refspecs_list = STRING_LIST_INIT_NODUP;
 	struct string_list paths_of_changed_objects = STRING_LIST_INIT_DUP;
@@ -1010,10 +1156,17 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, N_("mode"),
 			     N_("select handling of tags that tag filtered objects"),
 			     parse_opt_tag_of_filtered_mode),
+		OPT_CALLBACK(0, "reencode", &reencode_mode, N_("mode"),
+			     N_("select handling of commit messages in an alternate encoding"),
+			     parse_opt_reencode_mode),
 		OPT_STRING(0, "export-marks", &export_filename, N_("file"),
 			     N_("Dump marks to this file")),
 		OPT_STRING(0, "import-marks", &import_filename, N_("file"),
 			     N_("Import marks from this file")),
+		OPT_STRING(0, "import-marks-if-exists",
+			     &import_filename_if_exists,
+			     N_("file"),
+			     N_("Import marks from this file if it exists")),
 		OPT_BOOL(0, "fake-missing-tagger", &fake_missing_tagger,
 			 N_("Fake a tagger when tags lack one")),
 		OPT_BOOL(0, "full-tree", &full_tree,
@@ -1024,6 +1177,13 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		OPT_STRING_LIST(0, "refspec", &refspecs_list, N_("refspec"),
 			     N_("Apply refspec to exported refs")),
 		OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")),
+		OPT_BOOL(0, "reference-excluded-parents",
+			 &reference_excluded_commits, N_("Reference parents which are not in fast-export stream by object id")),
+		OPT_BOOL(0, "show-original-ids", &show_original_ids,
+			    N_("Show original object ids of blobs/commits")),
+		OPT_BOOL(0, "mark-tags", &mark_tags,
+			    N_("Label tags with mark ids")),
+
 		OPT_END()
 	};
 
@@ -1056,8 +1216,12 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	if (use_done_feature)
 		printf("feature done\n");
 
+	if (import_filename && import_filename_if_exists)
+		die(_("Cannot pass both --import-marks and --import-marks-if-exists"));
 	if (import_filename)
-		import_marks(import_filename);
+		import_marks(import_filename, 0);
+	else if (import_filename_if_exists)
+		import_marks(import_filename_if_exists, 1);
 	lastimportid = last_idnum;
 
 	if (import_filename && revs.prune_data.nr)
@@ -1080,7 +1244,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	handle_tags_and_duplicates();
+	handle_tags_and_duplicates(&extra_refs);
+	handle_tags_and_duplicates(&tag_refs);
 	handle_deletes();
 
 	if (export_filename && lastimportid != last_idnum)