1 files changed, 396 insertions, 61 deletions

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index d1d68e9fc6..b8182c241d 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -17,6 +17,8 @@
 #include "utf8.h"
 #include "parse-options.h"
 #include "quote.h"
+#include "remote.h"
+#include "blob.h"
 
 static const char *fast_export_usage[] = {
 	N_("git fast-export [rev-list-opts]"),
@@ -30,6 +32,10 @@ static int fake_missing_tagger;
 static int use_done_feature;
 static int no_data;
 static int full_tree;
+static struct string_list extra_refs = STRING_LIST_INIT_NODUP;
+static struct refspec *refspecs;
+static int refspecs_nr;
+static int anonymize;
 
 static int parse_opt_signed_tag_mode(const struct option *opt,
 				     const char *arg, int unset)
@@ -77,6 +83,76 @@ static int has_unshown_parent(struct commit *commit)
 	return 0;
 }
 
+struct anonymized_entry {
+	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 *va, const void *vb,
+				const void *data)
+{
+	const struct anonymized_entry *a = va, *b = vb;
+	return a->orig_len != b->orig_len ||
+		memcmp(a->orig, b->orig, a->orig_len);
+}
+
+/*
+ * Basically keep a cache of X->Y so that we can repeatedly replace
+ * 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)
+{
+	struct anonymized_entry key, *ret;
+
+	if (!map->cmpfn)
+		hashmap_init(map, anonymized_entry_cmp, 0);
+
+	hashmap_entry_init(&key, memhash(orig, *len));
+	key.orig = orig;
+	key.orig_len = *len;
+	ret = hashmap_get(map, &key, NULL);
+
+	if (!ret) {
+		ret = xmalloc(sizeof(*ret));
+		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);
+	}
+
+	*len = ret->anon_len;
+	return ret->anon;
+}
+
+/*
+ * We anonymize each component of a path individually,
+ * so that paths a/b and a/c will share a common root.
+ * The paths are cached via anonymize_mem so that repeated
+ * lookups for "a" will yield the same value.
+ */
+static void anonymize_path(struct strbuf *out, const char *path,
+			   struct hashmap *map,
+			   void *(*generate)(const void *, size_t *))
+{
+	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);
+		path = end_of_component;
+		if (*path)
+			strbuf_addch(out, *path++);
+	}
+}
+
 /* Since intptr_t is C99, we do not use it here */
 static inline uint32_t *mark_to_ptr(uint32_t mark)
 {
@@ -115,6 +191,26 @@ static void show_progress(void)
 		printf("progress %d objects\n", counter);
 }
 
+/*
+ * Ideally we would want some transformation of the blob data here
+ * that is unreversible, but would still be the same size and have
+ * the same data relationship to other blobs (so that we get the same
+ * delta and packing behavior as the original). But the first and last
+ * requirements there are probably mutually exclusive, so let's take
+ * the easy way out for now, and just generate arbitrary content.
+ *
+ * There's no need to cache this result with anonymize_mem, since
+ * we already handle blob content caching with marks.
+ */
+static char *anonymize_blob(unsigned long *size)
+{
+	static int counter;
+	struct strbuf out = STRBUF_INIT;
+	strbuf_addf(&out, "anonymous blob %d", counter++);
+	*size = out.len;
+	return strbuf_detach(&out, NULL);
+}
+
 static void export_blob(const unsigned char *sha1)
 {
 	unsigned long size;
@@ -133,12 +229,19 @@ static void export_blob(const unsigned char *sha1)
 	if (object && object->flags & SHOWN)
 		return;
 
-	buf = read_sha1_file(sha1, &type, &size);
-	if (!buf)
-		die ("Could not read blob %s", sha1_to_hex(sha1));
-	if (check_sha1_signature(sha1, buf, size, typename(type)) < 0)
-		die("sha1 mismatch in blob %s", sha1_to_hex(sha1));
-	object = parse_object_buffer(sha1, type, size, buf, &eaten);
+	if (anonymize) {
+		buf = anonymize_blob(&size);
+		object = (struct object *)lookup_blob(sha1);
+		eaten = 0;
+	} else {
+		buf = read_sha1_file(sha1, &type, &size);
+		if (!buf)
+			die ("Could not read blob %s", sha1_to_hex(sha1));
+		if (check_sha1_signature(sha1, buf, size, typename(type)) < 0)
+			die("sha1 mismatch in blob %s", sha1_to_hex(sha1));
+		object = parse_object_buffer(sha1, type, size, buf, &eaten);
+	}
+
 	if (!object)
 		die("Could not read blob %s", sha1_to_hex(sha1));
 
@@ -186,7 +289,7 @@ static int depth_first(const void *a_, const void *b_)
 	return (a->status == 'R') - (b->status == 'R');
 }
 
-static void print_path(const char *path)
+static void print_path_1(const char *path)
 {
 	int need_quote = quote_c_style(path, NULL, NULL, 0);
 	if (need_quote)
@@ -197,6 +300,43 @@ static void print_path(const char *path)
 		printf("%s", path);
 }
 
+static void *anonymize_path_component(const void *path, size_t *len)
+{
+	static int counter;
+	struct strbuf out = STRBUF_INIT;
+	strbuf_addf(&out, "path%d", counter++);
+	return strbuf_detach(&out, len);
+}
+
+static void print_path(const char *path)
+{
+	if (!anonymize)
+		print_path_1(path);
+	else {
+		static struct hashmap paths;
+		static struct strbuf anon = STRBUF_INIT;
+
+		anonymize_path(&anon, path, &paths, anonymize_path_component);
+		print_path_1(anon.buf);
+		strbuf_reset(&anon);
+	}
+}
+
+static void *generate_fake_sha1(const void *old, size_t *len)
+{
+	static uint32_t counter = 1; /* avoid null sha1 */
+	unsigned char *out = xcalloc(20, 1);
+	put_be32(out + 16, counter++);
+	return out;
+}
+
+static const unsigned char *anonymize_sha1(const unsigned char *sha1)
+{
+	static struct hashmap sha1s;
+	size_t len = 20;
+	return anonymize_mem(&sha1s, generate_fake_sha1, sha1, &len);
+}
+
 static void show_filemodify(struct diff_queue_struct *q,
 			    struct diff_options *options, void *data)
 {
@@ -241,7 +381,9 @@ 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(spec->sha1));
+				       sha1_to_hex(anonymize ?
+						   anonymize_sha1(spec->sha1) :
+						   spec->sha1));
 			else {
 				struct object *object = lookup_object(spec->sha1);
 				printf("M %06o :%d ", spec->mode,
@@ -275,19 +417,130 @@ static const char *find_encoding(const char *begin, const char *end)
 	return bol;
 }
 
+static void *anonymize_ref_component(const void *old, size_t *len)
+{
+	static int counter;
+	struct strbuf out = STRBUF_INIT;
+	strbuf_addf(&out, "ref%d", counter++);
+	return strbuf_detach(&out, len);
+}
+
+static const char *anonymize_refname(const char *refname)
+{
+	/*
+	 * If any of these prefixes is found, we will leave it intact
+	 * so that tags remain tags and so forth.
+	 */
+	static const char *prefixes[] = {
+		"refs/heads/",
+		"refs/tags/",
+		"refs/remotes/",
+		"refs/"
+	};
+	static struct hashmap refs;
+	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)) {
+			strbuf_addstr(&anon, prefixes[i]);
+			break;
+		}
+	}
+
+	anonymize_path(&anon, refname, &refs, anonymize_ref_component);
+	return anon.buf;
+}
+
+/*
+ * We do not even bother to cache commit messages, as they are unlikely
+ * to be repeated verbatim, and it is not that interesting when they are.
+ */
+static char *anonymize_commit_message(const char *old)
+{
+	static int counter;
+	return xstrfmt("subject %d\n\nbody\n", counter++);
+}
+
+static struct hashmap idents;
+static void *anonymize_ident(const void *old, size_t *len)
+{
+	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);
+}
+
+/*
+ * Our strategy here is to anonymize the names and email addresses,
+ * but keep timestamps intact, as they influence things like traversal
+ * order (and by themselves should not be too revealing).
+ */
+static void anonymize_ident_line(const char **beg, const char **end)
+{
+	static struct strbuf buffers[] = { STRBUF_INIT, STRBUF_INIT };
+	static unsigned which_buffer;
+
+	struct strbuf *out;
+	struct ident_split split;
+	const char *end_of_header;
+
+	out = &buffers[which_buffer++];
+	which_buffer %= ARRAY_SIZE(buffers);
+	strbuf_reset(out);
+
+	/* skip "committer", "author", "tagger", etc */
+	end_of_header = strchr(*beg, ' ');
+	if (!end_of_header)
+		die("BUG: malformed line fed to anonymize_ident_line: %.*s",
+		    (int)(*end - *beg), *beg);
+	end_of_header++;
+	strbuf_add(out, *beg, end_of_header - *beg);
+
+	if (!split_ident_line(&split, end_of_header, *end - end_of_header) &&
+	    split.date_begin) {
+		const char *ident;
+		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);
+		strbuf_addch(out, ' ');
+		strbuf_add(out, split.date_begin, split.tz_end - split.date_begin);
+	} else {
+		strbuf_addstr(out, "Malformed Ident <malformed@example.com> 0 -0000");
+	}
+
+	*beg = out->buf;
+	*end = out->buf + out->len;
+}
+
 static void handle_commit(struct commit *commit, struct rev_info *rev)
 {
 	int saved_output_format = rev->diffopt.output_format;
+	const char *commit_buffer;
 	const char *author, *author_end, *committer, *committer_end;
 	const char *encoding, *message;
 	char *reencoded = NULL;
 	struct commit_list *p;
+	const char *refname;
 	int i;
 
 	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
 
-	parse_commit(commit);
-	author = strstr(commit->buffer, "\nauthor ");
+	parse_commit_or_die(commit);
+	commit_buffer = get_commit_buffer(commit, NULL);
+	author = strstr(commit_buffer, "\nauthor ");
 	if (!author)
 		die ("Could not find author in commit %s",
 		     sha1_to_hex(commit->object.sha1));
@@ -307,7 +560,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	if (commit->parents &&
 	    get_object_mark(&commit->parents->item->object) != 0 &&
 	    !full_tree) {
-		parse_commit(commit->parents->item);
+		parse_commit_or_die(commit->parents->item);
 		diff_tree_sha1(commit->parents->item->tree->object.sha1,
 			       commit->tree->object.sha1, "", &rev->diffopt);
 	}
@@ -320,13 +573,22 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 		if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
 			export_blob(diff_queued_diff.queue[i]->two->sha1);
 
+	refname = commit->util;
+	if (anonymize) {
+		refname = anonymize_refname(refname);
+		anonymize_ident_line(&committer, &committer_end);
+		anonymize_ident_line(&author, &author_end);
+	}
+
 	mark_next_object(&commit->object);
-	if (!is_encoding_utf8(encoding))
+	if (anonymize)
+		reencoded = anonymize_commit_message(message);
+	else if (!is_encoding_utf8(encoding))
 		reencoded = reencode_string(message, "UTF-8", encoding);
 	if (!commit->parents)
-		printf("reset %s\n", (const char*)commit->util);
+		printf("reset %s\n", refname);
 	printf("commit %s\nmark :%"PRIu32"\n%.*s\n%.*s\ndata %u\n%s",
-	       (const char *)commit->util, last_idnum,
+	       refname, last_idnum,
 	       (int)(author_end - author), author,
 	       (int)(committer_end - committer), committer,
 	       (unsigned)(reencoded
@@ -334,6 +596,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 			  ? strlen(message) : 0),
 	       reencoded ? reencoded : message ? message : "");
 	free(reencoded);
+	unuse_commit_buffer(commit, commit_buffer);
 
 	for (i = 0, p = commit->parents; p; p = p->next) {
 		int mark = get_object_mark(&p->item->object);
@@ -356,6 +619,14 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	show_progress();
 }
 
+static void *anonymize_tag(const void *old, size_t *len)
+{
+	static int counter;
+	struct strbuf out = STRBUF_INIT;
+	strbuf_addf(&out, "tag message %d", counter++);
+	return strbuf_detach(&out, len);
+}
+
 static void handle_tail(struct object_array *commits, struct rev_info *revs)
 {
 	struct commit *commit;
@@ -379,7 +650,7 @@ static void handle_tag(const char *name, struct tag *tag)
 	int tagged_mark;
 	struct commit *p;
 
-	/* Trees have no identifer in fast-export output, thus we have no way
+	/* Trees have no identifier in fast-export output, thus we have no way
 	 * to output tags of trees, tags of tags of trees, etc.  Simply omit
 	 * such tags.
 	 */
@@ -412,6 +683,17 @@ static void handle_tag(const char *name, struct tag *tag)
 	} else {
 		tagger++;
 		tagger_end = strchrnul(tagger, '\n');
+		if (anonymize)
+			anonymize_ident_line(&tagger, &tagger_end);
+	}
+
+	if (anonymize) {
+		name = anonymize_refname(name);
+		if (message) {
+			static struct hashmap tags;
+			message = anonymize_mem(&tags, anonymize_tag,
+						message, &message_size);
+		}
 	}
 
 	/* handle signed tags */
@@ -475,7 +757,7 @@ static void handle_tag(const char *name, struct tag *tag)
 		}
 	}
 
-	if (!prefixcmp(name, "refs/tags/"))
+	if (starts_with(name, "refs/tags/"))
 		name += 10;
 	printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
 	       name, tagged_mark,
@@ -484,10 +766,32 @@ static void handle_tag(const char *name, struct tag *tag)
 	       (int)message_size, (int)message_size, message ? message : "");
 }
 
-static void get_tags_and_duplicates(struct rev_cmdline_info *info,
-				    struct string_list *extra_refs)
+static struct commit *get_commit(struct rev_cmdline_entry *e, char *full_name)
+{
+	switch (e->item->type) {
+	case OBJ_COMMIT:
+		return (struct commit *)e->item;
+	case OBJ_TAG: {
+		struct tag *tag = (struct tag *)e->item;
+
+		/* handle nested tags */
+		while (tag && tag->object.type == OBJ_TAG) {
+			parse_object(tag->object.sha1);
+			string_list_append(&extra_refs, full_name)->util = tag;
+			tag = (struct tag *)tag->tagged;
+		}
+		if (!tag)
+			die("Tag %s points nowhere?", e->name);
+		return (struct commit *)tag;
+		break;
+	}
+	default:
+		return NULL;
+	}
+}
+
+static void get_tags_and_duplicates(struct rev_cmdline_info *info)
 {
-	struct tag *tag;
 	int i;
 
 	for (i = 0; i < info->nr; i++) {
@@ -502,65 +806,61 @@ static void get_tags_and_duplicates(struct rev_cmdline_info *info,
 		if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
 			continue;
 
-		switch (e->item->type) {
-		case OBJ_COMMIT:
-			commit = (struct commit *)e->item;
-			break;
-		case OBJ_TAG:
-			tag = (struct tag *)e->item;
-
-			/* handle nested tags */
-			while (tag && tag->object.type == OBJ_TAG) {
-				parse_object(tag->object.sha1);
-				string_list_append(extra_refs, full_name)->util = tag;
-				tag = (struct tag *)tag->tagged;
-			}
-			if (!tag)
-				die ("Tag %s points nowhere?", e->name);
-			switch(tag->object.type) {
-			case OBJ_COMMIT:
-				commit = (struct commit *)tag;
-				break;
-			case OBJ_BLOB:
-				export_blob(tag->object.sha1);
-				continue;
-			default: /* OBJ_TAG (nested tags) is already handled */
-				warning("Tag points to object of unexpected type %s, skipping.",
-					typename(tag->object.type));
-				continue;
+		if (refspecs) {
+			char *private;
+			private = apply_refspecs(refspecs, refspecs_nr, full_name);
+			if (private) {
+				free(full_name);
+				full_name = private;
 			}
-			break;
-		default:
+		}
+
+		commit = get_commit(e, full_name);
+		if (!commit) {
 			warning("%s: Unexpected object of type %s, skipping.",
 				e->name,
 				typename(e->item->type));
 			continue;
 		}
 
+		switch(commit->object.type) {
+		case OBJ_COMMIT:
+			break;
+		case OBJ_BLOB:
+			export_blob(commit->object.sha1);
+			continue;
+		default: /* OBJ_TAG (nested tags) is already handled */
+			warning("Tag points to object of unexpected type %s, skipping.",
+				typename(commit->object.type));
+			continue;
+		}
+
 		/*
 		 * This ref will not be updated through a commit, lets make
 		 * sure it gets properly updated eventually.
 		 */
 		if (commit->util || commit->object.flags & SHOWN)
-			string_list_append(extra_refs, full_name)->util = commit;
+			string_list_append(&extra_refs, full_name)->util = commit;
 		if (!commit->util)
 			commit->util = full_name;
 	}
 }
 
-static void handle_tags_and_duplicates(struct string_list *extra_refs)
+static void handle_tags_and_duplicates(void)
 {
 	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 = extra_refs.nr - 1; i >= 0; i--) {
+		const char *name = extra_refs.items[i].string;
+		struct object *object = extra_refs.items[i].util;
 		switch (object->type) {
 		case OBJ_TAG:
 			handle_tag(name, (struct tag *)object);
 			break;
 		case OBJ_COMMIT:
+			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,
@@ -653,14 +953,27 @@ static void import_marks(char *input_file)
 	fclose(f);
 }
 
+static void handle_deletes(void)
+{
+	int i;
+	for (i = 0; i < refspecs_nr; i++) {
+		struct refspec *refspec = &refspecs[i];
+		if (*refspec->src)
+			continue;
+
+		printf("reset %s\nfrom %s\n\n",
+				refspec->dst, sha1_to_hex(null_sha1));
+	}
+}
+
 int cmd_fast_export(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
 	struct object_array commits = OBJECT_ARRAY_INIT;
-	struct string_list extra_refs = STRING_LIST_INIT_NODUP;
 	struct commit *commit;
 	char *export_filename = NULL, *import_filename = NULL;
 	uint32_t lastimportid;
+	struct string_list refspecs_list = STRING_LIST_INIT_NODUP;
 	struct option options[] = {
 		OPT_INTEGER(0, "progress", &progress,
 			    N_("show progress after <n> objects")),
@@ -674,13 +987,16 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 			     N_("Dump marks to this file")),
 		OPT_STRING(0, "import-marks", &import_filename, N_("file"),
 			     N_("Import marks from this file")),
-		OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
-			     N_("Fake a tagger when tags lack one")),
-		OPT_BOOLEAN(0, "full-tree", &full_tree,
-			     N_("Output full tree for each commit")),
-		OPT_BOOLEAN(0, "use-done-feature", &use_done_feature,
+		OPT_BOOL(0, "fake-missing-tagger", &fake_missing_tagger,
+			 N_("Fake a tagger when tags lack one")),
+		OPT_BOOL(0, "full-tree", &full_tree,
+			 N_("Output full tree for each commit")),
+		OPT_BOOL(0, "use-done-feature", &use_done_feature,
 			     N_("Use the done feature to terminate the stream")),
 		OPT_BOOL(0, "no-data", &no_data, N_("Skip output of blob data")),
+		OPT_STRING_LIST(0, "refspec", &refspecs_list, N_("refspec"),
+			     N_("Apply refspec to exported refs")),
+		OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")),
 		OPT_END()
 	};
 
@@ -694,11 +1010,27 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	revs.topo_order = 1;
 	revs.show_source = 1;
 	revs.rewrite_parents = 1;
+	argc = parse_options(argc, argv, prefix, options, fast_export_usage,
+			PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN);
 	argc = setup_revisions(argc, argv, &revs, NULL);
-	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
 	if (argc > 1)
 		usage_with_options (fast_export_usage, options);
 
+	if (refspecs_list.nr) {
+		const char **refspecs_str;
+		int i;
+
+		refspecs_str = xmalloc(sizeof(*refspecs_str) * refspecs_list.nr);
+		for (i = 0; i < refspecs_list.nr; i++)
+			refspecs_str[i] = refspecs_list.items[i].string;
+
+		refspecs_nr = refspecs_list.nr;
+		refspecs = parse_fetch_refspec(refspecs_nr, refspecs_str);
+
+		string_list_clear(&refspecs_list, 1);
+		free(refspecs_str);
+	}
+
 	if (use_done_feature)
 		printf("feature done\n");
 
@@ -709,7 +1041,7 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	if (import_filename && revs.prune_data.nr)
 		full_tree = 1;
 
-	get_tags_and_duplicates(&revs.cmdline, &extra_refs);
+	get_tags_and_duplicates(&revs.cmdline);
 
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
@@ -725,7 +1057,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	handle_tags_and_duplicates(&extra_refs);
+	handle_tags_and_duplicates();
+	handle_deletes();
 
 	if (export_filename && lastimportid != last_idnum)
 		export_marks(export_filename);
@@ -733,5 +1066,7 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	if (use_done_feature)
 		printf("done\n");
 
+	free_refspec(refspecs_nr, refspecs);
+
 	return 0;
 }