1 files changed, 221 insertions, 88 deletions

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 9e283482ef..d2e33f5005 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -33,16 +33,19 @@ static const char *fast_export_usage[] = {
 static int progress;
 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 hashmap anonymized_seeds;
 static struct revision_sources revision_sources;
 
 static int parse_opt_signed_tag_mode(const struct option *opt,
@@ -77,6 +80,31 @@ 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;
 
@@ -93,19 +121,33 @@ static int has_unshown_parent(struct commit *commit)
 
 struct anonymized_entry {
 	struct hashmap_entry hash;
+	const char *anon;
+	const char orig[FLEX_ARRAY];
+};
+
+struct anonymized_entry_key {
+	struct hashmap_entry hash;
 	const char *orig;
 	size_t orig_len;
-	const char *anon;
-	size_t anon_len;
 };
 
 static int anonymized_entry_cmp(const void *unused_cmp_data,
-				const void *va, const void *vb,
-				const void *unused_keydata)
+				const struct hashmap_entry *eptr,
+				const struct hashmap_entry *entry_or_key,
+				const void *keydata)
 {
-	const struct anonymized_entry *a = va, *b = vb;
-	return a->orig_len != b->orig_len ||
-		memcmp(a->orig, b->orig, a->orig_len);
+	const struct anonymized_entry *a, *b;
+
+	a = container_of(eptr, const struct anonymized_entry, hash);
+	if (keydata) {
+		const struct anonymized_entry_key *key = keydata;
+		int equal = !strncmp(a->orig, key->orig, key->orig_len) &&
+			    !a->orig[key->orig_len];
+		return !equal;
+	}
+
+	b = container_of(entry_or_key, const struct anonymized_entry, hash);
+	return strcmp(a->orig, b->orig);
 }
 
 /*
@@ -113,31 +155,39 @@ static int anonymized_entry_cmp(const void *unused_cmp_data,
  * the same anonymized string with another. The actual generation
  * is farmed out to the generate function.
  */
-static const void *anonymize_mem(struct hashmap *map,
-				 void *(*generate)(const void *, size_t *),
-				 const void *orig, size_t *len)
+static const char *anonymize_str(struct hashmap *map,
+				 char *(*generate)(void *),
+				 const char *orig, size_t len,
+				 void *data)
 {
-	struct anonymized_entry key, *ret;
+	struct anonymized_entry_key key;
+	struct anonymized_entry *ret;
 
 	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);
+	key.orig_len = len;
+
+	/* First check if it's a token the user configured manually... */
+	if (anonymized_seeds.cmpfn)
+		ret = hashmap_get_entry(&anonymized_seeds, &key, hash, &key);
+	else
+		ret = NULL;
+
+	/* ...otherwise check if we've already seen it in this context... */
+	if (!ret)
+		ret = hashmap_get_entry(map, &key, hash, &key);
 
+	/* ...and finally generate a new mapping if necessary */
 	if (!ret) {
-		ret = xmalloc(sizeof(*ret));
+		FLEX_ALLOC_MEM(ret, orig, orig, len);
 		hashmap_entry_init(&ret->hash, key.hash.hash);
-		ret->orig = xstrdup(orig);
-		ret->orig_len = *len;
-		ret->anon = generate(orig, len);
-		ret->anon_len = *len;
-		hashmap_put(map, ret);
+		ret->anon = generate(data);
+		hashmap_put(map, &ret->hash);
 	}
 
-	*len = ret->anon_len;
 	return ret->anon;
 }
 
@@ -149,13 +199,13 @@ static const void *anonymize_mem(struct hashmap *map,
  */
 static void anonymize_path(struct strbuf *out, const char *path,
 			   struct hashmap *map,
-			   void *(*generate)(const void *, size_t *))
+			   char *(*generate)(void *))
 {
 	while (*path) {
 		const char *end_of_component = strchrnul(path, '/');
 		size_t len = end_of_component - path;
-		const char *c = anonymize_mem(map, generate, path, &len);
-		strbuf_add(out, c, len);
+		const char *c = anonymize_str(map, generate, path, len, NULL);
+		strbuf_addstr(out, c);
 		path = end_of_component;
 		if (*path)
 			strbuf_addch(out, *path++);
@@ -249,7 +299,7 @@ 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;
 
@@ -261,7 +311,8 @@ 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)
+		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);
@@ -328,12 +379,12 @@ static void print_path_1(const char *path)
 		printf("%s", path);
 }
 
-static void *anonymize_path_component(const void *path, size_t *len)
+static char *anonymize_path_component(void *data)
 {
 	static int counter;
 	struct strbuf out = STRBUF_INIT;
 	strbuf_addf(&out, "path%d", counter++);
-	return strbuf_detach(&out, len);
+	return strbuf_detach(&out, NULL);
 }
 
 static void print_path(const char *path)
@@ -350,20 +401,23 @@ static void print_path(const char *path)
 	}
 }
 
-static void *generate_fake_oid(const void *old, size_t *len)
+static char *generate_fake_oid(void *data)
 {
 	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;
+	struct object_id oid;
+	char *hex = xmallocz(GIT_MAX_HEXSZ);
+
+	oidclr(&oid);
+	put_be32(oid.hash + hashsz - 4, counter++);
+	return oid_to_hex_r(hex, &oid);
 }
 
-static const struct object_id *anonymize_oid(const struct object_id *oid)
+static const char *anonymize_oid(const char *oid_hex)
 {
 	static struct hashmap objs;
-	size_t len = the_hash_algo->rawsz;
-	return anonymize_mem(&objs, generate_fake_oid, oid, &len);
+	size_t len = strlen(oid_hex);
+	return anonymize_str(&objs, generate_fake_oid, oid_hex, len, NULL);
 }
 
 static void show_filemodify(struct diff_queue_struct *q,
@@ -422,12 +476,12 @@ static void show_filemodify(struct diff_queue_struct *q,
 			 */
 			if (no_data || S_ISGITLINK(spec->mode))
 				printf("M %06o %s ", spec->mode,
-				       oid_to_hex(anonymize ?
-						  anonymize_oid(&spec->oid) :
-						  &spec->oid));
+				       anonymize ?
+				       anonymize_oid(oid_to_hex(&spec->oid)) :
+				       oid_to_hex(&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));
 			}
@@ -453,19 +507,19 @@ 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';
 	return bol;
 }
 
-static void *anonymize_ref_component(const void *old, size_t *len)
+static char *anonymize_ref_component(void *data)
 {
 	static int counter;
 	struct strbuf out = STRBUF_INIT;
 	strbuf_addf(&out, "ref%d", counter++);
-	return strbuf_detach(&out, len);
+	return strbuf_detach(&out, NULL);
 }
 
 static const char *anonymize_refname(const char *refname)
@@ -484,13 +538,6 @@ static const char *anonymize_refname(const char *refname)
 	static struct strbuf anon = STRBUF_INIT;
 	int i;
 
-	/*
-	 * We also leave "master" as a special case, since it does not reveal
-	 * anything interesting.
-	 */
-	if (!strcmp(refname, "refs/heads/master"))
-		return refname;
-
 	strbuf_reset(&anon);
 	for (i = 0; i < ARRAY_SIZE(prefixes); i++) {
 		if (skip_prefix(refname, prefixes[i], &refname)) {
@@ -513,14 +560,13 @@ static char *anonymize_commit_message(const char *old)
 	return xstrfmt("subject %d\n\nbody\n", counter++);
 }
 
-static struct hashmap idents;
-static void *anonymize_ident(const void *old, size_t *len)
+static char *anonymize_ident(void *data)
 {
 	static int counter;
 	struct strbuf out = STRBUF_INIT;
 	strbuf_addf(&out, "User %d <user%d@example.com>", counter, counter);
 	counter++;
-	return strbuf_detach(&out, len);
+	return strbuf_detach(&out, NULL);
 }
 
 /*
@@ -530,6 +576,7 @@ static void *anonymize_ident(const void *old, size_t *len)
  */
 static void anonymize_ident_line(const char **beg, const char **end)
 {
+	static struct hashmap idents;
 	static struct strbuf buffers[] = { STRBUF_INIT, STRBUF_INIT };
 	static unsigned which_buffer;
 
@@ -555,9 +602,9 @@ static void anonymize_ident_line(const char **beg, const char **end)
 		size_t len;
 
 		len = split.mail_end - split.name_begin;
-		ident = anonymize_mem(&idents, anonymize_ident,
-				      split.name_begin, &len);
-		strbuf_add(out, ident, len);
+		ident = anonymize_str(&idents, anonymize_ident,
+				      split.name_begin, len, NULL);
+		strbuf_addstr(out, ident);
 		strbuf_addch(out, ' ');
 		strbuf_add(out, split.date_begin, split.tz_end - split.date_begin);
 	} else {
@@ -633,18 +680,32 @@ 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", refname, last_idnum);
 	if (show_original_ids)
 		printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
-	printf("%.*s\n%.*s\ndata %u\n%s",
+	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),
@@ -665,9 +726,10 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 		if (mark)
 			printf(":%d\n", mark);
 		else
-			printf("%s\n", oid_to_hex(anonymize ?
-						  anonymize_oid(&obj->oid) :
-						  &obj->oid));
+			printf("%s\n",
+			       anonymize ?
+			       anonymize_oid(oid_to_hex(&obj->oid)) :
+			       oid_to_hex(&obj->oid));
 		i++;
 	}
 
@@ -682,12 +744,12 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	show_progress();
 }
 
-static void *anonymize_tag(const void *old, size_t *len)
+static char *anonymize_tag(void *data)
 {
 	static int counter;
 	struct strbuf out = STRBUF_INIT;
 	strbuf_addf(&out, "tag message %d", counter++);
-	return strbuf_detach(&out, len);
+	return strbuf_detach(&out, NULL);
 }
 
 static void handle_tail(struct object_array *commits, struct rev_info *revs,
@@ -757,8 +819,8 @@ static void handle_tag(const char *name, struct tag *tag)
 		name = anonymize_refname(name);
 		if (message) {
 			static struct hashmap tags;
-			message = anonymize_mem(&tags, anonymize_tag,
-						message, &message_size);
+			message = anonymize_str(&tags, anonymize_tag,
+						message, message_size, NULL);
 		}
 	}
 
@@ -802,25 +864,39 @@ 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));
-			}
-			p = rewrite_commit((struct commit *)tagged);
-			if (!p) {
-				printf("reset %s\nfrom %s\n\n",
-				       name, oid_to_hex(&null_oid));
-				free(buf);
-				return;
+			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);
 			}
-			tagged_mark = get_object_mark(&p->object);
 		}
 	}
 
-	if (starts_with(name, "refs/tags/"))
-		name += 10;
-	printf("tag %s\nfrom :%d\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",
@@ -867,7 +943,7 @@ static void get_tags_and_duplicates(struct rev_cmdline_info *info)
 		if (e->flags & UNINTERESTING)
 			continue;
 
-		if (dwim_ref(e->name, strlen(e->name), &oid, &full_name) != 1)
+		if (dwim_ref(e->name, strlen(e->name), &oid, &full_name, 0) != 1)
 			continue;
 
 		if (refspecs.nr) {
@@ -950,7 +1026,7 @@ static void handle_tags_and_duplicates(struct string_list *extras)
 				/*
 				 * Getting here means we have a commit which
 				 * was excluded by a negative refspec (e.g.
-				 * fast-export ^master master).  If we are
+				 * fast-export ^HEAD HEAD).  If we are
 				 * referencing excluded commits, set the ref
 				 * to the exact commit.  Otherwise, the user
 				 * wants the branch exported but every commit
@@ -1007,11 +1083,16 @@ 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;
@@ -1070,12 +1151,45 @@ static void handle_deletes(void)
 	}
 }
 
+static char *anonymize_seed(void *data)
+{
+	return xstrdup(data);
+}
+
+static int parse_opt_anonymize_map(const struct option *opt,
+				   const char *arg, int unset)
+{
+	struct hashmap *map = opt->value;
+	const char *delim, *value;
+	size_t keylen;
+
+	BUG_ON_OPT_NEG(unset);
+
+	delim = strchr(arg, ':');
+	if (delim) {
+		keylen = delim - arg;
+		value = delim + 1;
+	} else {
+		keylen = strlen(arg);
+		value = arg;
+	}
+
+	if (!keylen || !*value)
+		return error(_("--anonymize-map token cannot be empty"));
+
+	anonymize_str(map, anonymize_seed, arg, keylen, (void *)value);
+
+	return 0;
+}
+
 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;
@@ -1088,10 +1202,17 @@ 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,
@@ -1102,10 +1223,15 @@ 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_CALLBACK_F(0, "anonymize-map", &anonymized_seeds, N_("from:to"),
+			       N_("convert <from> to <to> in anonymized output"),
+			       PARSE_OPT_NONEG, parse_opt_anonymize_map),
 		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()
 	};
@@ -1127,6 +1253,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	if (argc > 1)
 		usage_with_options (fast_export_usage, options);
 
+	if (anonymized_seeds.cmpfn && !anonymize)
+		die(_("--anonymize-map without --anonymize does not make sense"));
+
 	if (refspecs_list.nr) {
 		int i;
 
@@ -1139,8 +1268,12 @@ 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)