[thirdparty/git.git] / builtin / fast-export.c

/*
 * "git fast-export" builtin command
 *
 * Copyright (C) 2007 Johannes E. Schindelin
 */
#include "builtin.h"
#include "cache.h"
#include "commit.h"
#include "object.h"
#include "tag.h"
#include "diff.h"
#include "diffcore.h"
#include "log-tree.h"
#include "revision.h"
#include "decorate.h"
#include "string-list.h"
#include "utf8.h"
#include "parse-options.h"

static const char *fast_export_usage[] = {
	"git fast-export [rev-list-opts]",
	NULL
};

static int progress;
static enum { ABORT, VERBATIM, WARN, STRIP } signed_tag_mode = ABORT;
static enum { ERROR, DROP, REWRITE } tag_of_filtered_mode = ABORT;
static int fake_missing_tagger;
static int no_data;

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;
	else if (!strcmp(arg, "verbatim") || !strcmp(arg, "ignore"))
		signed_tag_mode = VERBATIM;
	else if (!strcmp(arg, "warn"))
		signed_tag_mode = WARN;
	else if (!strcmp(arg, "strip"))
		signed_tag_mode = STRIP;
	else
		return error("Unknown signed-tag mode: %s", arg);
	return 0;
}

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 = ABORT;
	else if (!strcmp(arg, "drop"))
		tag_of_filtered_mode = DROP;
	else if (!strcmp(arg, "rewrite"))
		tag_of_filtered_mode = REWRITE;
	else
		return error("Unknown tag-of-filtered mode: %s", arg);
	return 0;
}

static struct decoration idnums;
static uint32_t last_idnum;

static int has_unshown_parent(struct commit *commit)
{
	struct commit_list *parent;

	for (parent = commit->parents; parent; parent = parent->next)
		if (!(parent->item->object.flags & SHOWN) &&
		    !(parent->item->object.flags & UNINTERESTING))
			return 1;
	return 0;
}

/* Since intptr_t is C99, we do not use it here */
static inline uint32_t *mark_to_ptr(uint32_t mark)
{
	return ((uint32_t *)NULL) + mark;
}

static inline uint32_t ptr_to_mark(void * mark)
{
	return (uint32_t *)mark - (uint32_t *)NULL;
}

static inline void mark_object(struct object *object, uint32_t mark)
{
	add_decoration(&idnums, object, mark_to_ptr(mark));
}

static inline void mark_next_object(struct object *object)
{
	mark_object(object, ++last_idnum);
}

static int get_object_mark(struct object *object)
{
	void *decoration = lookup_decoration(&idnums, object);
	if (!decoration)
		return 0;
	return ptr_to_mark(decoration);
}

static void show_progress(void)
{
	static int counter = 0;
	if (!progress)
		return;
	if ((++counter % progress) == 0)
		printf("progress %d objects\n", counter);
}

static void handle_object(const unsigned char *sha1)
{
	unsigned long size;
	enum object_type type;
	char *buf;
	struct object *object;

	if (no_data)
		return;

	if (is_null_sha1(sha1))
		return;

	object = parse_object(sha1);
	if (!object)
		die ("Could not read blob %s", sha1_to_hex(sha1));

	if (object->flags & SHOWN)
		return;

	buf = read_sha1_file(sha1, &type, &size);
	if (!buf)
		die ("Could not read blob %s", sha1_to_hex(sha1));

	mark_next_object(object);

	printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
	if (size && fwrite(buf, size, 1, stdout) != 1)
		die_errno ("Could not write blob '%s'", sha1_to_hex(sha1));
	printf("\n");

	show_progress();

	object->flags |= SHOWN;
	free(buf);
}

static int depth_first(const void *a_, const void *b_)
{
	const struct diff_filepair *a = *((const struct diff_filepair **)a_);
	const struct diff_filepair *b = *((const struct diff_filepair **)b_);
	const char *name_a, *name_b;
	int len_a, len_b, len;
	int cmp;

	name_a = a->one ? a->one->path : a->two->path;
	name_b = b->one ? b->one->path : b->two->path;

	len_a = strlen(name_a);
	len_b = strlen(name_b);
	len = (len_a < len_b) ? len_a : len_b;

	/* strcmp will sort 'd' before 'd/e', we want 'd/e' before 'd' */
	cmp = memcmp(name_a, name_b, len);
	if (cmp)
		return cmp;
	cmp = len_b - len_a;
	if (cmp)
		return cmp;
	/*
	 * Move 'R'ename entries last so that all references of the file
	 * appear in the output before it is renamed (e.g., when a file
	 * was copied and renamed in the same commit).
	 */
	return (a->status == 'R') - (b->status == 'R');
}

static void show_filemodify(struct diff_queue_struct *q,
			    struct diff_options *options, void *data)
{
	int i;

	/*
	 * Handle files below a directory first, in case they are all deleted
	 * and the directory changes to a file or symlink.
	 */
	qsort(q->queue, q->nr, sizeof(q->queue[0]), depth_first);

	for (i = 0; i < q->nr; i++) {
		struct diff_filespec *ospec = q->queue[i]->one;
		struct diff_filespec *spec = q->queue[i]->two;

		switch (q->queue[i]->status) {
		case DIFF_STATUS_DELETED:
			printf("D %s\n", spec->path);
			break;

		case DIFF_STATUS_COPIED:
		case DIFF_STATUS_RENAMED:
			printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
			       ospec->path, spec->path);

			if (!hashcmp(ospec->sha1, spec->sha1) &&
			    ospec->mode == spec->mode)
				break;
			/* fallthrough */

		case DIFF_STATUS_TYPE_CHANGED:
		case DIFF_STATUS_MODIFIED:
		case DIFF_STATUS_ADDED:
			/*
			 * Links refer to objects in another repositories;
			 * output the SHA-1 verbatim.
			 */
			if (no_data || S_ISGITLINK(spec->mode))
				printf("M %06o %s %s\n", spec->mode,
				       sha1_to_hex(spec->sha1), spec->path);
			else {
				struct object *object = lookup_object(spec->sha1);
				printf("M %06o :%d %s\n", spec->mode,
				       get_object_mark(object), spec->path);
			}
			break;

		default:
			die("Unexpected comparison status '%c' for %s, %s",
				q->queue[i]->status,
				ospec->path ? ospec->path : "none",
				spec->path ? spec->path : "none");
		}
	}
}

static const char *find_encoding(const char *begin, const char *end)
{
	const char *needle = "\nencoding ";
	char *bol, *eol;

	bol = memmem(begin, end ? end - begin : strlen(begin),
		     needle, strlen(needle));
	if (!bol)
		return git_commit_encoding;
	bol += strlen(needle);
	eol = strchrnul(bol, '\n');
	*eol = '\0';
	return bol;
}

static void handle_commit(struct commit *commit, struct rev_info *rev)
{
	int saved_output_format = rev->diffopt.output_format;
	const char *author, *author_end, *committer, *committer_end;
	const char *encoding, *message;
	char *reencoded = NULL;
	struct commit_list *p;
	int i;

	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;

	parse_commit(commit);
	author = strstr(commit->buffer, "\nauthor ");
	if (!author)
		die ("Could not find author in commit %s",
		     sha1_to_hex(commit->object.sha1));
	author++;
	author_end = strchrnul(author, '\n');
	committer = strstr(author_end, "\ncommitter ");
	if (!committer)
		die ("Could not find committer in commit %s",
		     sha1_to_hex(commit->object.sha1));
	committer++;
	committer_end = strchrnul(committer, '\n');
	message = strstr(committer_end, "\n\n");
	encoding = find_encoding(committer_end, message);
	if (message)
		message += 2;

	if (commit->parents &&
	    get_object_mark(&commit->parents->item->object) != 0) {
		parse_commit(commit->parents->item);
		diff_tree_sha1(commit->parents->item->tree->object.sha1,
			       commit->tree->object.sha1, "", &rev->diffopt);
	}
	else
		diff_root_tree_sha1(commit->tree->object.sha1,
				    "", &rev->diffopt);

	/* Export the referenced blobs, and remember the marks. */
	for (i = 0; i < diff_queued_diff.nr; i++)
		if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
			handle_object(diff_queued_diff.queue[i]->two->sha1);

	mark_next_object(&commit->object);
	if (!is_encoding_utf8(encoding))
		reencoded = reencode_string(message, "UTF-8", encoding);
	if (!commit->parents)
		printf("reset %s\n", (const char*)commit->util);
	printf("commit %s\nmark :%"PRIu32"\n%.*s\n%.*s\ndata %u\n%s",
	       (const char *)commit->util, last_idnum,
	       (int)(author_end - author), author,
	       (int)(committer_end - committer), committer,
	       (unsigned)(reencoded
			  ? strlen(reencoded) : message
			  ? strlen(message) : 0),
	       reencoded ? reencoded : message ? message : "");
	free(reencoded);

	for (i = 0, p = commit->parents; p; p = p->next) {
		int mark = get_object_mark(&p->item->object);
		if (!mark)
			continue;
		if (i == 0)
			printf("from :%d\n", mark);
		else
			printf("merge :%d\n", mark);
		i++;
	}

	log_tree_diff_flush(rev);
	rev->diffopt.output_format = saved_output_format;

	printf("\n");

	show_progress();
}

static void handle_tail(struct object_array *commits, struct rev_info *revs)
{
	struct commit *commit;
	while (commits->nr) {
		commit = (struct commit *)commits->objects[commits->nr - 1].item;
		if (has_unshown_parent(commit))
			return;
		handle_commit(commit, revs);
		commits->nr--;
	}
}

static void handle_tag(const char *name, struct tag *tag)
{
	unsigned long size;
	enum object_type type;
	char *buf;
	const char *tagger, *tagger_end, *message;
	size_t message_size = 0;
	struct object *tagged;
	int tagged_mark;
	struct commit *p;

	/* Trees have no identifer in fast-export output, thus we have no way
	 * to output tags of trees, tags of tags of trees, etc.  Simply omit
	 * such tags.
	 */
	tagged = tag->tagged;
	while (tagged->type == OBJ_TAG) {
		tagged = ((struct tag *)tagged)->tagged;
	}
	if (tagged->type == OBJ_TREE) {
		warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
			sha1_to_hex(tag->object.sha1));
		return;
	}

	buf = read_sha1_file(tag->object.sha1, &type, &size);
	if (!buf)
		die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	message = memmem(buf, size, "\n\n", 2);
	if (message) {
		message += 2;
		message_size = strlen(message);
	}
	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
	if (!tagger) {
		if (fake_missing_tagger)
			tagger = "tagger Unspecified Tagger "
				"<unspecified-tagger> 0 +0000";
		else
			tagger = "";
		tagger_end = tagger + strlen(tagger);
	} else {
		tagger++;
		tagger_end = strchrnul(tagger, '\n');
	}

	/* handle signed tags */
	if (message) {
		const char *signature = strstr(message,
					       "\n-----BEGIN PGP SIGNATURE-----\n");
		if (signature)
			switch(signed_tag_mode) {
			case ABORT:
				die ("Encountered signed tag %s; use "
				     "--signed-tag=<mode> to handle it.",
				     sha1_to_hex(tag->object.sha1));
			case WARN:
				warning ("Exporting signed tag %s",
					 sha1_to_hex(tag->object.sha1));
				/* fallthru */
			case VERBATIM:
				break;
			case STRIP:
				message_size = signature + 1 - message;
				break;
			}
	}

	/* handle tag->tagged having been filtered out due to paths specified */
	tagged = tag->tagged;
	tagged_mark = get_object_mark(tagged);
	if (!tagged_mark) {
		switch(tag_of_filtered_mode) {
		case ABORT:
			die ("Tag %s tags unexported object; use "
			     "--tag-of-filtered-object=<mode> to handle it.",
			     sha1_to_hex(tag->object.sha1));
		case DROP:
			/* Ignore this tag altogether */
			return;
		case REWRITE:
			if (tagged->type != OBJ_COMMIT) {
				die ("Tag %s tags unexported %s!",
				     sha1_to_hex(tag->object.sha1),
				     typename(tagged->type));
			}
			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\n",
					     sha1_to_hex(tag->object.sha1));
				p = p->parents->item;
			}
			tagged_mark = get_object_mark(&p->object);
		}
	}

	if (!prefixcmp(name, "refs/tags/"))
		name += 10;
	printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
	       name, tagged_mark,
	       (int)(tagger_end - tagger), tagger,
	       tagger == tagger_end ? "" : "\n",
	       (int)message_size, (int)message_size, message ? message : "");
}

static void get_tags_and_duplicates(struct object_array *pending,
				    struct string_list *extra_refs)
{
	struct tag *tag;
	int i;

	for (i = 0; i < pending->nr; i++) {
		struct object_array_entry *e = pending->objects + i;
		unsigned char sha1[20];
		struct commit *commit = commit;
		char *full_name;

		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(full_name, extra_refs)->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:
				handle_object(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;
			}
			break;
		default:
			warning("%s: Unexpected object of type %s, skipping.",
				e->name,
				typename(e->item->type));
			continue;
		}
		if (commit->util)
			/* more than one name for the same object */
			string_list_append(full_name, extra_refs)->util = commit;
		else
			commit->util = full_name;
	}
}

static void handle_tags_and_duplicates(struct string_list *extra_refs)
{
	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;
		switch (object->type) {
		case OBJ_TAG:
			handle_tag(name, (struct tag *)object);
			break;
		case OBJ_COMMIT:
			/* create refs pointing to already seen commits */
			commit = (struct commit *)object;
			printf("reset %s\nfrom :%d\n\n", name,
			       get_object_mark(&commit->object));
			show_progress();
			break;
		}
	}
}

static void export_marks(char *file)
{
	unsigned int i;
	uint32_t mark;
	struct object_decoration *deco = idnums.hash;
	FILE *f;
	int e = 0;

	f = fopen(file, "w");
	if (!f)
		die_errno("Unable to open marks file %s for writing.", file);

	for (i = 0; i < idnums.size; i++) {
		if (deco->base && deco->base->type == 1) {
			mark = ptr_to_mark(deco->decoration);
			if (fprintf(f, ":%"PRIu32" %s\n", mark,
				sha1_to_hex(deco->base->sha1)) < 0) {
			    e = 1;
			    break;
			}
		}
		deco++;
	}

	e |= ferror(f);
	e |= fclose(f);
	if (e)
		error("Unable to write marks file %s.", file);
}

static void import_marks(char *input_file)
{
	char line[512];
	FILE *f = fopen(input_file, "r");
	if (!f)
		die_errno("cannot read '%s'", input_file);

	while (fgets(line, sizeof(line), f)) {
		uint32_t mark;
		char *line_end, *mark_end;
		unsigned char sha1[20];
		struct object *object;

		line_end = strchr(line, '\n');
		if (line[0] != ':' || !line_end)
			die("corrupt mark line: %s", line);
		*line_end = '\0';

		mark = strtoumax(line + 1, &mark_end, 10);
		if (!mark || mark_end == line + 1
			|| *mark_end != ' ' || get_sha1(mark_end + 1, sha1))
			die("corrupt mark line: %s", line);

		object = parse_object(sha1);
		if (!object)
			die ("Could not read blob %s", sha1_to_hex(sha1));

		if (object->flags & SHOWN)
			error("Object %s already has a mark", sha1);

		mark_object(object, mark);
		if (last_idnum < mark)
			last_idnum = mark;

		object->flags |= SHOWN;
	}
	fclose(f);
}

int cmd_fast_export(int argc, const char **argv, const char *prefix)
{
	struct rev_info revs;
	struct object_array commits = { 0, 0, NULL };
	struct string_list extra_refs = { NULL, 0, 0, 0 };
	struct commit *commit;
	char *export_filename = NULL, *import_filename = NULL;
	struct option options[] = {
		OPT_INTEGER(0, "progress", &progress,
			    "show progress after <n> objects"),
		OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
			     "select handling of signed tags",
			     parse_opt_signed_tag_mode),
		OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
			     "select handling of tags that tag filtered objects",
			     parse_opt_tag_of_filtered_mode),
		OPT_STRING(0, "export-marks", &export_filename, "FILE",
			     "Dump marks to this file"),
		OPT_STRING(0, "import-marks", &import_filename, "FILE",
			     "Import marks from this file"),
		OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
			     "Fake a tagger when tags lack one"),
		{ OPTION_NEGBIT, 0, "data", &no_data, NULL,
			"Skip output of blob data",
			PARSE_OPT_NOARG | PARSE_OPT_NEGHELP, NULL, 1 },
		OPT_END()
	};

	if (argc == 1)
		usage_with_options (fast_export_usage, options);

	/* we handle encodings */
	git_config(git_default_config, NULL);

	init_revisions(&revs, prefix);
	revs.topo_order = 1;
	revs.show_source = 1;
	revs.rewrite_parents = 1;
	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 (import_filename)
		import_marks(import_filename);

	get_tags_and_duplicates(&revs.pending, &extra_refs);

	if (prepare_revision_walk(&revs))
		die("revision walk setup failed");
	revs.diffopt.format_callback = show_filemodify;
	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
	while ((commit = get_revision(&revs))) {
		if (has_unshown_parent(commit)) {
			add_object_array(&commit->object, NULL, &commits);
		}
		else {
			handle_commit(commit, &revs);
			handle_tail(&commits, &revs);
		}
	}

	handle_tags_and_duplicates(&extra_refs);

	if (export_filename)
		export_marks(export_filename);

	return 0;
}
Commit	Line	Data
f2dc849e JS	1	/*
	2	* "git fast-export" builtin command
	3	*
	4	* Copyright (C) 2007 Johannes E. Schindelin
	5	*/
	6	#include "builtin.h"
	7	#include "cache.h"
	8	#include "commit.h"
	9	#include "object.h"
	10	#include "tag.h"
	11	#include "diff.h"
	12	#include "diffcore.h"
	13	#include "log-tree.h"
	14	#include "revision.h"
	15	#include "decorate.h"
c455c87c	16	#include "string-list.h"
f2dc849e JS	17	#include "utf8.h"
	18	#include "parse-options.h"
	19
	20	static const char *fast_export_usage[] = {
1b1dd23f	21	"git fast-export [rev-list-opts]",
f2dc849e JS	22	NULL
	23	};
	24
	25	static int progress;
2d8ad469 EN	26	static enum { ABORT, VERBATIM, WARN, STRIP } signed_tag_mode = ABORT;
2d8ad469 EN	27	static enum { ERROR, DROP, REWRITE } tag_of_filtered_mode = ABORT;
4e46a8d6	28	static int fake_missing_tagger;
79559f27	29	static int no_data;
f2dc849e JS	30
	31	static int parse_opt_signed_tag_mode(const struct option *opt,
	32	const char *arg, int unset)
	33	{
	34	if (unset \|\| !strcmp(arg, "abort"))
	35	signed_tag_mode = ABORT;
ee4bc371 JS	36	else if (!strcmp(arg, "verbatim") \|\| !strcmp(arg, "ignore"))
ee4bc371 JS	37	signed_tag_mode = VERBATIM;
f2dc849e JS	38	else if (!strcmp(arg, "warn"))
	39	signed_tag_mode = WARN;
	40	else if (!strcmp(arg, "strip"))
	41	signed_tag_mode = STRIP;
	42	else
	43	return error("Unknown signed-tag mode: %s", arg);
	44	return 0;
	45	}
	46
2d8ad469 EN	47	static int parse_opt_tag_of_filtered_mode(const struct option *opt,
	48	const char *arg, int unset)
	49	{
	50	if (unset \|\| !strcmp(arg, "abort"))
	51	tag_of_filtered_mode = ABORT;
	52	else if (!strcmp(arg, "drop"))
	53	tag_of_filtered_mode = DROP;
	54	else if (!strcmp(arg, "rewrite"))
	55	tag_of_filtered_mode = REWRITE;
	56	else
	57	return error("Unknown tag-of-filtered mode: %s", arg);
	58	return 0;
	59	}
	60
f2dc849e JS	61	static struct decoration idnums;
	62	static uint32_t last_idnum;
	63
	64	static int has_unshown_parent(struct commit *commit)
	65	{
	66	struct commit_list *parent;
	67
	68	for (parent = commit->parents; parent; parent = parent->next)
	69	if (!(parent->item->object.flags & SHOWN) &&
	70	!(parent->item->object.flags & UNINTERESTING))
	71	return 1;
	72	return 0;
	73	}
	74
	75	/* Since intptr_t is C99, we do not use it here */
df6a7ff7	76	static inline uint32_t *mark_to_ptr(uint32_t mark)
f2dc849e	77	{
df6a7ff7 PB	78	return ((uint32_t *)NULL) + mark;
	79	}
	80
	81	static inline uint32_t ptr_to_mark(void * mark)
	82	{
	83	return (uint32_t )mark - (uint32_t )NULL;
	84	}
	85
	86	static inline void mark_object(struct object *object, uint32_t mark)
	87	{
	88	add_decoration(&idnums, object, mark_to_ptr(mark));
	89	}
	90
	91	static inline void mark_next_object(struct object *object)
	92	{
	93	mark_object(object, ++last_idnum);
f2dc849e JS	94	}
	95
	96	static int get_object_mark(struct object *object)
	97	{
	98	void *decoration = lookup_decoration(&idnums, object);
	99	if (!decoration)
	100	return 0;
df6a7ff7	101	return ptr_to_mark(decoration);
f2dc849e JS	102	}
	103
	104	static void show_progress(void)
	105	{
	106	static int counter = 0;
	107	if (!progress)
	108	return;
	109	if ((++counter % progress) == 0)
	110	printf("progress %d objects\n", counter);
	111	}
	112
	113	static void handle_object(const unsigned char *sha1)
	114	{
	115	unsigned long size;
	116	enum object_type type;
	117	char *buf;
	118	struct object *object;
	119
79559f27 GI	120	if (no_data)
	121	return;
	122
f2dc849e JS	123	if (is_null_sha1(sha1))
	124	return;
	125
	126	object = parse_object(sha1);
	127	if (!object)
	128	die ("Could not read blob %s", sha1_to_hex(sha1));
	129
	130	if (object->flags & SHOWN)
	131	return;
	132
	133	buf = read_sha1_file(sha1, &type, &size);
	134	if (!buf)
	135	die ("Could not read blob %s", sha1_to_hex(sha1));
	136
df6a7ff7	137	mark_next_object(object);
f2dc849e	138
6e1c2344	139	printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
b0fe0d72	140	if (size && fwrite(buf, size, 1, stdout) != 1)
0721c314	141	die_errno ("Could not write blob '%s'", sha1_to_hex(sha1));
f2dc849e JS	142	printf("\n");
	143
	144	show_progress();
	145
	146	object->flags \|= SHOWN;
	147	free(buf);
	148	}
	149
060df624 EN	150	static int depth_first(const void a_, const void b_)
	151	{
	152	const struct diff_filepair a = ((const struct diff_filepair **)a_);
	153	const struct diff_filepair b = ((const struct diff_filepair **)b_);
	154	const char name_a, name_b;
	155	int len_a, len_b, len;
	156	int cmp;
	157
	158	name_a = a->one ? a->one->path : a->two->path;
	159	name_b = b->one ? b->one->path : b->two->path;
	160
	161	len_a = strlen(name_a);
	162	len_b = strlen(name_b);
	163	len = (len_a < len_b) ? len_a : len_b;
	164
	165	/* strcmp will sort 'd' before 'd/e', we want 'd/e' before 'd' */
	166	cmp = memcmp(name_a, name_b, len);
	167	if (cmp)
	168	return cmp;
4ce6fb80 JS	169	cmp = len_b - len_a;
	170	if (cmp)
	171	return cmp;
	172	/*
	173	* Move 'R'ename entries last so that all references of the file
	174	* appear in the output before it is renamed (e.g., when a file
	175	* was copied and renamed in the same commit).
	176	*/
	177	return (a->status == 'R') - (b->status == 'R');
060df624 EN	178	}
060df624 EN	179
f2dc849e JS	180	static void show_filemodify(struct diff_queue_struct *q,
	181	struct diff_options options, void data)
	182	{
	183	int i;
060df624 EN	184
	185	/*
	186	* Handle files below a directory first, in case they are all deleted
	187	* and the directory changes to a file or symlink.
	188	*/
	189	qsort(q->queue, q->nr, sizeof(q->queue[0]), depth_first);
	190
f2dc849e	191	for (i = 0; i < q->nr; i++) {
ae7c5dce	192	struct diff_filespec *ospec = q->queue[i]->one;
f2dc849e	193	struct diff_filespec *spec = q->queue[i]->two;
ae7c5dce AG	194
	195	switch (q->queue[i]->status) {
	196	case DIFF_STATUS_DELETED:
f2dc849e	197	printf("D %s\n", spec->path);
ae7c5dce AG	198	break;
	199
	200	case DIFF_STATUS_COPIED:
	201	case DIFF_STATUS_RENAMED:
	202	printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
	203	ospec->path, spec->path);
	204
	205	if (!hashcmp(ospec->sha1, spec->sha1) &&
	206	ospec->mode == spec->mode)
	207	break;
	208	/* fallthrough */
	209
	210	case DIFF_STATUS_TYPE_CHANGED:
	211	case DIFF_STATUS_MODIFIED:
	212	case DIFF_STATUS_ADDED:
03db4525 AG	213	/*
	214	* Links refer to objects in another repositories;
	215	* output the SHA-1 verbatim.
	216	*/
79559f27	217	if (no_data \|\| S_ISGITLINK(spec->mode))
03db4525 AG	218	printf("M %06o %s %s\n", spec->mode,
	219	sha1_to_hex(spec->sha1), spec->path);
	220	else {
	221	struct object *object = lookup_object(spec->sha1);
	222	printf("M %06o :%d %s\n", spec->mode,
	223	get_object_mark(object), spec->path);
	224	}
ae7c5dce AG	225	break;
	226
	227	default:
	228	die("Unexpected comparison status '%c' for %s, %s",
	229	q->queue[i]->status,
	230	ospec->path ? ospec->path : "none",
	231	spec->path ? spec->path : "none");
f2dc849e JS	232	}
	233	}
	234	}
	235
	236	static const char find_encoding(const char begin, const char *end)
	237	{
	238	const char *needle = "\nencoding ";
	239	char bol, eol;
	240
	241	bol = memmem(begin, end ? end - begin : strlen(begin),
	242	needle, strlen(needle));
	243	if (!bol)
	244	return git_commit_encoding;
	245	bol += strlen(needle);
	246	eol = strchrnul(bol, '\n');
	247	*eol = '\0';
	248	return bol;
	249	}
	250
	251	static void handle_commit(struct commit commit, struct rev_info rev)
	252	{
	253	int saved_output_format = rev->diffopt.output_format;
	254	const char author, author_end, committer, committer_end;
	255	const char encoding, message;
	256	char *reencoded = NULL;
	257	struct commit_list *p;
	258	int i;
	259
	260	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
	261
	262	parse_commit(commit);
	263	author = strstr(commit->buffer, "\nauthor ");
	264	if (!author)
	265	die ("Could not find author in commit %s",
	266	sha1_to_hex(commit->object.sha1));
	267	author++;
	268	author_end = strchrnul(author, '\n');
	269	committer = strstr(author_end, "\ncommitter ");
	270	if (!committer)
	271	die ("Could not find committer in commit %s",
	272	sha1_to_hex(commit->object.sha1));
	273	committer++;
	274	committer_end = strchrnul(committer, '\n');
	275	message = strstr(committer_end, "\n\n");
	276	encoding = find_encoding(committer_end, message);
	277	if (message)
	278	message += 2;
	279
ebeec7db EN	280	if (commit->parents &&
ebeec7db EN	281	get_object_mark(&commit->parents->item->object) != 0) {
f2dc849e JS	282	parse_commit(commit->parents->item);
	283	diff_tree_sha1(commit->parents->item->tree->object.sha1,
	284	commit->tree->object.sha1, "", &rev->diffopt);
	285	}
	286	else
	287	diff_root_tree_sha1(commit->tree->object.sha1,
	288	"", &rev->diffopt);
	289
03db4525	290	/* Export the referenced blobs, and remember the marks. */
f2dc849e	291	for (i = 0; i < diff_queued_diff.nr; i++)
03db4525 AG	292	if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
03db4525 AG	293	handle_object(diff_queued_diff.queue[i]->two->sha1);
f2dc849e	294
df6a7ff7	295	mark_next_object(&commit->object);
f2dc849e JS	296	if (!is_encoding_utf8(encoding))
f2dc849e JS	297	reencoded = reencode_string(message, "UTF-8", encoding);
d8933f01 SP	298	if (!commit->parents)
d8933f01 SP	299	printf("reset %s\n", (const char*)commit->util);
6e1c2344	300	printf("commit %s\nmark :%"PRIu32"\n%.s\n%.s\ndata %u\n%s",
f2dc849e JS	301	(const char *)commit->util, last_idnum,
	302	(int)(author_end - author), author,
	303	(int)(committer_end - committer), committer,
	304	(unsigned)(reencoded
	305	? strlen(reencoded) : message
	306	? strlen(message) : 0),
	307	reencoded ? reencoded : message ? message : "");
8e0f7003	308	free(reencoded);
f2dc849e JS	309
	310	for (i = 0, p = commit->parents; p; p = p->next) {
	311	int mark = get_object_mark(&p->item->object);
	312	if (!mark)
	313	continue;
	314	if (i == 0)
	315	printf("from :%d\n", mark);
f2dc849e	316	else
5070b49e	317	printf("merge :%d\n", mark);
f2dc849e JS	318	i++;
f2dc849e JS	319	}
f2dc849e JS	320
	321	log_tree_diff_flush(rev);
	322	rev->diffopt.output_format = saved_output_format;
	323
	324	printf("\n");
	325
	326	show_progress();
	327	}
	328
	329	static void handle_tail(struct object_array commits, struct rev_info revs)
	330	{
	331	struct commit *commit;
	332	while (commits->nr) {
	333	commit = (struct commit *)commits->objects[commits->nr - 1].item;
	334	if (has_unshown_parent(commit))
	335	return;
	336	handle_commit(commit, revs);
	337	commits->nr--;
	338	}
	339	}
	340
	341	static void handle_tag(const char name, struct tag tag)
	342	{
	343	unsigned long size;
	344	enum object_type type;
	345	char *buf;
	346	const char tagger, tagger_end, *message;
	347	size_t message_size = 0;
02c48cd6	348	struct object *tagged;
2d8ad469 EN	349	int tagged_mark;
2d8ad469 EN	350	struct commit *p;
02c48cd6 EN	351
	352	/* Trees have no identifer in fast-export output, thus we have no way
	353	* to output tags of trees, tags of tags of trees, etc. Simply omit
	354	* such tags.
	355	*/
	356	tagged = tag->tagged;
	357	while (tagged->type == OBJ_TAG) {
	358	tagged = ((struct tag *)tagged)->tagged;
	359	}
	360	if (tagged->type == OBJ_TREE) {
	361	warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
	362	sha1_to_hex(tag->object.sha1));
	363	return;
	364	}
f2dc849e JS	365
	366	buf = read_sha1_file(tag->object.sha1, &type, &size);
	367	if (!buf)
	368	die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	369	message = memmem(buf, size, "\n\n", 2);
	370	if (message) {
	371	message += 2;
	372	message_size = strlen(message);
	373	}
	374	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
4e46a8d6 JS	375	if (!tagger) {
	376	if (fake_missing_tagger)
	377	tagger = "tagger Unspecified Tagger "
	378	"<unspecified-tagger> 0 +0000";
	379	else
	380	tagger = "";
	381	tagger_end = tagger + strlen(tagger);
	382	} else {
	383	tagger++;
	384	tagger_end = strchrnul(tagger, '\n');
	385	}
f2dc849e JS	386
	387	/* handle signed tags */
	388	if (message) {
	389	const char *signature = strstr(message,
	390	"\n-----BEGIN PGP SIGNATURE-----\n");
	391	if (signature)
	392	switch(signed_tag_mode) {
	393	case ABORT:
	394	die ("Encountered signed tag %s; use "
	395	"--signed-tag=<mode> to handle it.",
	396	sha1_to_hex(tag->object.sha1));
	397	case WARN:
	398	warning ("Exporting signed tag %s",
	399	sha1_to_hex(tag->object.sha1));
	400	/* fallthru */
ee4bc371	401	case VERBATIM:
f2dc849e JS	402	break;
	403	case STRIP:
	404	message_size = signature + 1 - message;
	405	break;
	406	}
	407	}
	408
2d8ad469 EN	409	/* handle tag->tagged having been filtered out due to paths specified */
	410	tagged = tag->tagged;
	411	tagged_mark = get_object_mark(tagged);
	412	if (!tagged_mark) {
	413	switch(tag_of_filtered_mode) {
	414	case ABORT:
	415	die ("Tag %s tags unexported object; use "
	416	"--tag-of-filtered-object=<mode> to handle it.",
	417	sha1_to_hex(tag->object.sha1));
	418	case DROP:
	419	/* Ignore this tag altogether */
	420	return;
	421	case REWRITE:
	422	if (tagged->type != OBJ_COMMIT) {
	423	die ("Tag %s tags unexported %s!",
	424	sha1_to_hex(tag->object.sha1),
	425	typename(tagged->type));
	426	}
	427	p = (struct commit *)tagged;
	428	for (;;) {
	429	if (p->parents && p->parents->next)
	430	break;
	431	if (p->object.flags & UNINTERESTING)
	432	break;
	433	if (!(p->object.flags & TREESAME))
	434	break;
	435	if (!p->parents)
	436	die ("Can't find replacement commit for tag %s\n",
	437	sha1_to_hex(tag->object.sha1));
	438	p = p->parents->item;
	439	}
	440	tagged_mark = get_object_mark(&p->object);
	441	}
	442	}
	443
f2dc849e JS	444	if (!prefixcmp(name, "refs/tags/"))
f2dc849e JS	445	name += 10;
4e46a8d6	446	printf("tag %s\nfrom :%d\n%.s%sdata %d\n%.s\n",
2d8ad469	447	name, tagged_mark,
f2dc849e	448	(int)(tagger_end - tagger), tagger,
4e46a8d6	449	tagger == tagger_end ? "" : "\n",
f2dc849e JS	450	(int)message_size, (int)message_size, message ? message : "");
	451	}
	452
	453	static void get_tags_and_duplicates(struct object_array *pending,
c455c87c	454	struct string_list *extra_refs)
f2dc849e JS	455	{
	456	struct tag *tag;
	457	int i;
	458
	459	for (i = 0; i < pending->nr; i++) {
	460	struct object_array_entry *e = pending->objects + i;
	461	unsigned char sha1[20];
	462	struct commit *commit = commit;
	463	char *full_name;
	464
	465	if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
	466	continue;
	467
	468	switch (e->item->type) {
	469	case OBJ_COMMIT:
	470	commit = (struct commit *)e->item;
	471	break;
	472	case OBJ_TAG:
	473	tag = (struct tag *)e->item;
1982467d EFL	474
1982467d EFL	475	/* handle nested tags */
f2dc849e	476	while (tag && tag->object.type == OBJ_TAG) {
1982467d	477	parse_object(tag->object.sha1);
2075ffb5	478	string_list_append(full_name, extra_refs)->util = tag;
f2dc849e JS	479	tag = (struct tag *)tag->tagged;
	480	}
	481	if (!tag)
	482	die ("Tag %s points nowhere?", e->name);
	483	switch(tag->object.type) {
	484	case OBJ_COMMIT:
	485	commit = (struct commit *)tag;
	486	break;
	487	case OBJ_BLOB:
	488	handle_object(tag->object.sha1);
	489	continue;
1982467d	490	default: /* OBJ_TAG (nested tags) is already handled */
c0582c53 EFL	491	warning("Tag points to object of unexpected type %s, skipping.",
	492	typename(tag->object.type));
	493	continue;
f2dc849e JS	494	}
	495	break;
	496	default:
2d07f6d4 EFL	497	warning("%s: Unexpected object of type %s, skipping.",
	498	e->name,
	499	typename(e->item->type));
	500	continue;
f2dc849e JS	501	}
	502	if (commit->util)
	503	/* more than one name for the same object */
2075ffb5	504	string_list_append(full_name, extra_refs)->util = commit;
f2dc849e JS	505	else
	506	commit->util = full_name;
	507	}
	508	}
	509
c455c87c	510	static void handle_tags_and_duplicates(struct string_list *extra_refs)
f2dc849e JS	511	{
	512	struct commit *commit;
	513	int i;
	514
	515	for (i = extra_refs->nr - 1; i >= 0; i--) {
c455c87c	516	const char *name = extra_refs->items[i].string;
f2dc849e JS	517	struct object *object = extra_refs->items[i].util;
	518	switch (object->type) {
	519	case OBJ_TAG:
	520	handle_tag(name, (struct tag *)object);
	521	break;
	522	case OBJ_COMMIT:
	523	/* create refs pointing to already seen commits */
	524	commit = (struct commit *)object;
	525	printf("reset %s\nfrom :%d\n\n", name,
	526	get_object_mark(&commit->object));
	527	show_progress();
	528	break;
	529	}
	530	}
	531	}
	532
df6a7ff7 PB	533	static void export_marks(char *file)
	534	{
	535	unsigned int i;
	536	uint32_t mark;
	537	struct object_decoration *deco = idnums.hash;
	538	FILE *f;
96d69b55	539	int e = 0;
df6a7ff7 PB	540
	541	f = fopen(file, "w");
	542	if (!f)
bb6ad28c	543	die_errno("Unable to open marks file %s for writing.", file);
df6a7ff7	544
69913575 JH	545	for (i = 0; i < idnums.size; i++) {
69913575 JH	546	if (deco->base && deco->base->type == 1) {
df6a7ff7	547	mark = ptr_to_mark(deco->decoration);
96d69b55 MA	548	if (fprintf(f, ":%"PRIu32" %s\n", mark,
	549	sha1_to_hex(deco->base->sha1)) < 0) {
	550	e = 1;
	551	break;
	552	}
df6a7ff7	553	}
69913575	554	deco++;
df6a7ff7 PB	555	}
df6a7ff7 PB	556
96d69b55 MA	557	e \|= ferror(f);
	558	e \|= fclose(f);
	559	if (e)
df6a7ff7 PB	560	error("Unable to write marks file %s.", file);
	561	}
	562
69913575	563	static void import_marks(char *input_file)
df6a7ff7 PB	564	{
	565	char line[512];
	566	FILE *f = fopen(input_file, "r");
	567	if (!f)
d824cbba	568	die_errno("cannot read '%s'", input_file);
df6a7ff7 PB	569
	570	while (fgets(line, sizeof(line), f)) {
	571	uint32_t mark;
	572	char line_end, mark_end;
	573	unsigned char sha1[20];
	574	struct object *object;
	575
	576	line_end = strchr(line, '\n');
	577	if (line[0] != ':' \|\| !line_end)
	578	die("corrupt mark line: %s", line);
69913575	579	*line_end = '\0';
df6a7ff7 PB	580
	581	mark = strtoumax(line + 1, &mark_end, 10);
	582	if (!mark \|\| mark_end == line + 1
	583	\|\| *mark_end != ' ' \|\| get_sha1(mark_end + 1, sha1))
	584	die("corrupt mark line: %s", line);
	585
	586	object = parse_object(sha1);
	587	if (!object)
	588	die ("Could not read blob %s", sha1_to_hex(sha1));
	589
	590	if (object->flags & SHOWN)
	591	error("Object %s already has a mark", sha1);
	592
	593	mark_object(object, mark);
	594	if (last_idnum < mark)
	595	last_idnum = mark;
	596
	597	object->flags \|= SHOWN;
	598	}
	599	fclose(f);
	600	}
	601
f2dc849e JS	602	int cmd_fast_export(int argc, const char *argv, const char prefix)
	603	{
	604	struct rev_info revs;
	605	struct object_array commits = { 0, 0, NULL };
c455c87c	606	struct string_list extra_refs = { NULL, 0, 0, 0 };
f2dc849e	607	struct commit *commit;
df6a7ff7	608	char export_filename = NULL, import_filename = NULL;
f2dc849e JS	609	struct option options[] = {
	610	OPT_INTEGER(0, "progress", &progress,
	611	"show progress after <n> objects"),
	612	OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
	613	"select handling of signed tags",
	614	parse_opt_signed_tag_mode),
2d8ad469 EN	615	OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
	616	"select handling of tags that tag filtered objects",
	617	parse_opt_tag_of_filtered_mode),
df6a7ff7 PB	618	OPT_STRING(0, "export-marks", &export_filename, "FILE",
	619	"Dump marks to this file"),
	620	OPT_STRING(0, "import-marks", &import_filename, "FILE",
	621	"Import marks from this file"),
4e46a8d6 JS	622	OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
4e46a8d6 JS	623	"Fake a tagger when tags lack one"),
79559f27 GI	624	{ OPTION_NEGBIT, 0, "data", &no_data, NULL,
	625	"Skip output of blob data",
	626	PARSE_OPT_NOARG \| PARSE_OPT_NEGHELP, NULL, 1 },
f2dc849e JS	627	OPT_END()
	628	};
	629
dcfdbdf0 MV	630	if (argc == 1)
	631	usage_with_options (fast_export_usage, options);
	632
f2dc849e	633	/* we handle encodings */
ef90d6d4	634	git_config(git_default_config, NULL);
f2dc849e JS	635
f2dc849e JS	636	init_revisions(&revs, prefix);
668f3aa7	637	revs.topo_order = 1;
2374502c	638	revs.show_source = 1;
32164131	639	revs.rewrite_parents = 1;
f2dc849e	640	argc = setup_revisions(argc, argv, &revs, NULL);
37782920	641	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
f2dc849e JS	642	if (argc > 1)
	643	usage_with_options (fast_export_usage, options);
	644
df6a7ff7 PB	645	if (import_filename)
	646	import_marks(import_filename);
	647
f2dc849e JS	648	get_tags_and_duplicates(&revs.pending, &extra_refs);
f2dc849e JS	649
3d51e1b5 MK	650	if (prepare_revision_walk(&revs))
3d51e1b5 MK	651	die("revision walk setup failed");
f2dc849e JS	652	revs.diffopt.format_callback = show_filemodify;
	653	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
	654	while ((commit = get_revision(&revs))) {
	655	if (has_unshown_parent(commit)) {
f2dc849e	656	add_object_array(&commit->object, NULL, &commits);
f2dc849e JS	657	}
	658	else {
	659	handle_commit(commit, &revs);
	660	handle_tail(&commits, &revs);
	661	}
	662	}
	663
	664	handle_tags_and_duplicates(&extra_refs);
	665
df6a7ff7 PB	666	if (export_filename)
	667	export_marks(export_filename);
	668
f2dc849e JS	669	return 0;
f2dc849e JS	670	}