[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 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 (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 ("Could not write blob %s", sha1_to_hex(sha1));
	printf("\n");

	show_progress();

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

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

	f = fopen(file, "w");
	if (!f)
		error("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);
			fprintf(f, ":%"PRIu32" %s\n", mark,
				sha1_to_hex(deco->base->sha1));
		}
		deco++;
	}

	if (ferror(f) || fclose(f))
		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("cannot read %s: %s", input_file, strerror(errno));

	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"),
		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;
f2dc849e JS	29
	30	static int parse_opt_signed_tag_mode(const struct option *opt,
	31	const char *arg, int unset)
	32	{
	33	if (unset \|\| !strcmp(arg, "abort"))
	34	signed_tag_mode = ABORT;
ee4bc371 JS	35	else if (!strcmp(arg, "verbatim") \|\| !strcmp(arg, "ignore"))
ee4bc371 JS	36	signed_tag_mode = VERBATIM;
f2dc849e JS	37	else if (!strcmp(arg, "warn"))
	38	signed_tag_mode = WARN;
	39	else if (!strcmp(arg, "strip"))
	40	signed_tag_mode = STRIP;
	41	else
	42	return error("Unknown signed-tag mode: %s", arg);
	43	return 0;
	44	}
	45
2d8ad469 EN	46	static int parse_opt_tag_of_filtered_mode(const struct option *opt,
	47	const char *arg, int unset)
	48	{
	49	if (unset \|\| !strcmp(arg, "abort"))
	50	tag_of_filtered_mode = ABORT;
	51	else if (!strcmp(arg, "drop"))
	52	tag_of_filtered_mode = DROP;
	53	else if (!strcmp(arg, "rewrite"))
	54	tag_of_filtered_mode = REWRITE;
	55	else
	56	return error("Unknown tag-of-filtered mode: %s", arg);
	57	return 0;
	58	}
	59
f2dc849e JS	60	static struct decoration idnums;
	61	static uint32_t last_idnum;
	62
	63	static int has_unshown_parent(struct commit *commit)
	64	{
	65	struct commit_list *parent;
	66
	67	for (parent = commit->parents; parent; parent = parent->next)
	68	if (!(parent->item->object.flags & SHOWN) &&
	69	!(parent->item->object.flags & UNINTERESTING))
	70	return 1;
	71	return 0;
	72	}
	73
	74	/* Since intptr_t is C99, we do not use it here */
df6a7ff7	75	static inline uint32_t *mark_to_ptr(uint32_t mark)
f2dc849e	76	{
df6a7ff7 PB	77	return ((uint32_t *)NULL) + mark;
	78	}
	79
	80	static inline uint32_t ptr_to_mark(void * mark)
	81	{
	82	return (uint32_t )mark - (uint32_t )NULL;
	83	}
	84
	85	static inline void mark_object(struct object *object, uint32_t mark)
	86	{
	87	add_decoration(&idnums, object, mark_to_ptr(mark));
	88	}
	89
	90	static inline void mark_next_object(struct object *object)
	91	{
	92	mark_object(object, ++last_idnum);
f2dc849e JS	93	}
	94
	95	static int get_object_mark(struct object *object)
	96	{
	97	void *decoration = lookup_decoration(&idnums, object);
	98	if (!decoration)
	99	return 0;
df6a7ff7	100	return ptr_to_mark(decoration);
f2dc849e JS	101	}
	102
	103	static void show_progress(void)
	104	{
	105	static int counter = 0;
	106	if (!progress)
	107	return;
	108	if ((++counter % progress) == 0)
	109	printf("progress %d objects\n", counter);
	110	}
	111
	112	static void handle_object(const unsigned char *sha1)
	113	{
	114	unsigned long size;
	115	enum object_type type;
	116	char *buf;
	117	struct object *object;
	118
	119	if (is_null_sha1(sha1))
	120	return;
	121
	122	object = parse_object(sha1);
	123	if (!object)
	124	die ("Could not read blob %s", sha1_to_hex(sha1));
	125
	126	if (object->flags & SHOWN)
	127	return;
	128
	129	buf = read_sha1_file(sha1, &type, &size);
	130	if (!buf)
	131	die ("Could not read blob %s", sha1_to_hex(sha1));
	132
df6a7ff7	133	mark_next_object(object);
f2dc849e	134
6e1c2344	135	printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
b0fe0d72	136	if (size && fwrite(buf, size, 1, stdout) != 1)
f2dc849e JS	137	die ("Could not write blob %s", sha1_to_hex(sha1));
	138	printf("\n");
	139
	140	show_progress();
	141
	142	object->flags \|= SHOWN;
	143	free(buf);
	144	}
	145
	146	static void show_filemodify(struct diff_queue_struct *q,
	147	struct diff_options options, void data)
	148	{
	149	int i;
	150	for (i = 0; i < q->nr; i++) {
ae7c5dce	151	struct diff_filespec *ospec = q->queue[i]->one;
f2dc849e	152	struct diff_filespec *spec = q->queue[i]->two;
ae7c5dce AG	153
	154	switch (q->queue[i]->status) {
	155	case DIFF_STATUS_DELETED:
f2dc849e	156	printf("D %s\n", spec->path);
ae7c5dce AG	157	break;
	158
	159	case DIFF_STATUS_COPIED:
	160	case DIFF_STATUS_RENAMED:
	161	printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
	162	ospec->path, spec->path);
	163
	164	if (!hashcmp(ospec->sha1, spec->sha1) &&
	165	ospec->mode == spec->mode)
	166	break;
	167	/* fallthrough */
	168
	169	case DIFF_STATUS_TYPE_CHANGED:
	170	case DIFF_STATUS_MODIFIED:
	171	case DIFF_STATUS_ADDED:
03db4525 AG	172	/*
	173	* Links refer to objects in another repositories;
	174	* output the SHA-1 verbatim.
	175	*/
	176	if (S_ISGITLINK(spec->mode))
	177	printf("M %06o %s %s\n", spec->mode,
	178	sha1_to_hex(spec->sha1), spec->path);
	179	else {
	180	struct object *object = lookup_object(spec->sha1);
	181	printf("M %06o :%d %s\n", spec->mode,
	182	get_object_mark(object), spec->path);
	183	}
ae7c5dce AG	184	break;
	185
	186	default:
	187	die("Unexpected comparison status '%c' for %s, %s",
	188	q->queue[i]->status,
	189	ospec->path ? ospec->path : "none",
	190	spec->path ? spec->path : "none");
f2dc849e JS	191	}
	192	}
	193	}
	194
	195	static const char find_encoding(const char begin, const char *end)
	196	{
	197	const char *needle = "\nencoding ";
	198	char bol, eol;
	199
	200	bol = memmem(begin, end ? end - begin : strlen(begin),
	201	needle, strlen(needle));
	202	if (!bol)
	203	return git_commit_encoding;
	204	bol += strlen(needle);
	205	eol = strchrnul(bol, '\n');
	206	*eol = '\0';
	207	return bol;
	208	}
	209
	210	static void handle_commit(struct commit commit, struct rev_info rev)
	211	{
	212	int saved_output_format = rev->diffopt.output_format;
	213	const char author, author_end, committer, committer_end;
	214	const char encoding, message;
	215	char *reencoded = NULL;
	216	struct commit_list *p;
	217	int i;
	218
	219	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
	220
	221	parse_commit(commit);
	222	author = strstr(commit->buffer, "\nauthor ");
	223	if (!author)
	224	die ("Could not find author in commit %s",
	225	sha1_to_hex(commit->object.sha1));
	226	author++;
	227	author_end = strchrnul(author, '\n');
	228	committer = strstr(author_end, "\ncommitter ");
	229	if (!committer)
	230	die ("Could not find committer in commit %s",
	231	sha1_to_hex(commit->object.sha1));
	232	committer++;
	233	committer_end = strchrnul(committer, '\n');
	234	message = strstr(committer_end, "\n\n");
	235	encoding = find_encoding(committer_end, message);
	236	if (message)
	237	message += 2;
	238
ebeec7db EN	239	if (commit->parents &&
ebeec7db EN	240	get_object_mark(&commit->parents->item->object) != 0) {
f2dc849e JS	241	parse_commit(commit->parents->item);
	242	diff_tree_sha1(commit->parents->item->tree->object.sha1,
	243	commit->tree->object.sha1, "", &rev->diffopt);
	244	}
	245	else
	246	diff_root_tree_sha1(commit->tree->object.sha1,
	247	"", &rev->diffopt);
	248
03db4525	249	/* Export the referenced blobs, and remember the marks. */
f2dc849e	250	for (i = 0; i < diff_queued_diff.nr; i++)
03db4525 AG	251	if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
03db4525 AG	252	handle_object(diff_queued_diff.queue[i]->two->sha1);
f2dc849e	253
df6a7ff7	254	mark_next_object(&commit->object);
f2dc849e JS	255	if (!is_encoding_utf8(encoding))
f2dc849e JS	256	reencoded = reencode_string(message, "UTF-8", encoding);
d8933f01 SP	257	if (!commit->parents)
d8933f01 SP	258	printf("reset %s\n", (const char*)commit->util);
6e1c2344	259	printf("commit %s\nmark :%"PRIu32"\n%.s\n%.s\ndata %u\n%s",
f2dc849e JS	260	(const char *)commit->util, last_idnum,
	261	(int)(author_end - author), author,
	262	(int)(committer_end - committer), committer,
	263	(unsigned)(reencoded
	264	? strlen(reencoded) : message
	265	? strlen(message) : 0),
	266	reencoded ? reencoded : message ? message : "");
8e0f7003	267	free(reencoded);
f2dc849e JS	268
	269	for (i = 0, p = commit->parents; p; p = p->next) {
	270	int mark = get_object_mark(&p->item->object);
	271	if (!mark)
	272	continue;
	273	if (i == 0)
	274	printf("from :%d\n", mark);
f2dc849e	275	else
5070b49e	276	printf("merge :%d\n", mark);
f2dc849e JS	277	i++;
f2dc849e JS	278	}
f2dc849e JS	279
	280	log_tree_diff_flush(rev);
	281	rev->diffopt.output_format = saved_output_format;
	282
	283	printf("\n");
	284
	285	show_progress();
	286	}
	287
	288	static void handle_tail(struct object_array commits, struct rev_info revs)
	289	{
	290	struct commit *commit;
	291	while (commits->nr) {
	292	commit = (struct commit *)commits->objects[commits->nr - 1].item;
	293	if (has_unshown_parent(commit))
	294	return;
	295	handle_commit(commit, revs);
	296	commits->nr--;
	297	}
	298	}
	299
	300	static void handle_tag(const char name, struct tag tag)
	301	{
	302	unsigned long size;
	303	enum object_type type;
	304	char *buf;
	305	const char tagger, tagger_end, *message;
	306	size_t message_size = 0;
02c48cd6	307	struct object *tagged;
2d8ad469 EN	308	int tagged_mark;
2d8ad469 EN	309	struct commit *p;
02c48cd6 EN	310
	311	/* Trees have no identifer in fast-export output, thus we have no way
	312	* to output tags of trees, tags of tags of trees, etc. Simply omit
	313	* such tags.
	314	*/
	315	tagged = tag->tagged;
	316	while (tagged->type == OBJ_TAG) {
	317	tagged = ((struct tag *)tagged)->tagged;
	318	}
	319	if (tagged->type == OBJ_TREE) {
	320	warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
	321	sha1_to_hex(tag->object.sha1));
	322	return;
	323	}
f2dc849e JS	324
	325	buf = read_sha1_file(tag->object.sha1, &type, &size);
	326	if (!buf)
	327	die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	328	message = memmem(buf, size, "\n\n", 2);
	329	if (message) {
	330	message += 2;
	331	message_size = strlen(message);
	332	}
	333	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
4e46a8d6 JS	334	if (!tagger) {
	335	if (fake_missing_tagger)
	336	tagger = "tagger Unspecified Tagger "
	337	"<unspecified-tagger> 0 +0000";
	338	else
	339	tagger = "";
	340	tagger_end = tagger + strlen(tagger);
	341	} else {
	342	tagger++;
	343	tagger_end = strchrnul(tagger, '\n');
	344	}
f2dc849e JS	345
	346	/* handle signed tags */
	347	if (message) {
	348	const char *signature = strstr(message,
	349	"\n-----BEGIN PGP SIGNATURE-----\n");
	350	if (signature)
	351	switch(signed_tag_mode) {
	352	case ABORT:
	353	die ("Encountered signed tag %s; use "
	354	"--signed-tag=<mode> to handle it.",
	355	sha1_to_hex(tag->object.sha1));
	356	case WARN:
	357	warning ("Exporting signed tag %s",
	358	sha1_to_hex(tag->object.sha1));
	359	/* fallthru */
ee4bc371	360	case VERBATIM:
f2dc849e JS	361	break;
	362	case STRIP:
	363	message_size = signature + 1 - message;
	364	break;
	365	}
	366	}
	367
2d8ad469 EN	368	/* handle tag->tagged having been filtered out due to paths specified */
	369	tagged = tag->tagged;
	370	tagged_mark = get_object_mark(tagged);
	371	if (!tagged_mark) {
	372	switch(tag_of_filtered_mode) {
	373	case ABORT:
	374	die ("Tag %s tags unexported object; use "
	375	"--tag-of-filtered-object=<mode> to handle it.",
	376	sha1_to_hex(tag->object.sha1));
	377	case DROP:
	378	/* Ignore this tag altogether */
	379	return;
	380	case REWRITE:
	381	if (tagged->type != OBJ_COMMIT) {
	382	die ("Tag %s tags unexported %s!",
	383	sha1_to_hex(tag->object.sha1),
	384	typename(tagged->type));
	385	}
	386	p = (struct commit *)tagged;
	387	for (;;) {
	388	if (p->parents && p->parents->next)
	389	break;
	390	if (p->object.flags & UNINTERESTING)
	391	break;
	392	if (!(p->object.flags & TREESAME))
	393	break;
	394	if (!p->parents)
	395	die ("Can't find replacement commit for tag %s\n",
	396	sha1_to_hex(tag->object.sha1));
	397	p = p->parents->item;
	398	}
	399	tagged_mark = get_object_mark(&p->object);
	400	}
	401	}
	402
f2dc849e JS	403	if (!prefixcmp(name, "refs/tags/"))
f2dc849e JS	404	name += 10;
4e46a8d6	405	printf("tag %s\nfrom :%d\n%.s%sdata %d\n%.s\n",
2d8ad469	406	name, tagged_mark,
f2dc849e	407	(int)(tagger_end - tagger), tagger,
4e46a8d6	408	tagger == tagger_end ? "" : "\n",
f2dc849e JS	409	(int)message_size, (int)message_size, message ? message : "");
	410	}
	411
	412	static void get_tags_and_duplicates(struct object_array *pending,
c455c87c	413	struct string_list *extra_refs)
f2dc849e JS	414	{
	415	struct tag *tag;
	416	int i;
	417
	418	for (i = 0; i < pending->nr; i++) {
	419	struct object_array_entry *e = pending->objects + i;
	420	unsigned char sha1[20];
	421	struct commit *commit = commit;
	422	char *full_name;
	423
	424	if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
	425	continue;
	426
	427	switch (e->item->type) {
	428	case OBJ_COMMIT:
	429	commit = (struct commit *)e->item;
	430	break;
	431	case OBJ_TAG:
	432	tag = (struct tag *)e->item;
1982467d EFL	433
1982467d EFL	434	/* handle nested tags */
f2dc849e	435	while (tag && tag->object.type == OBJ_TAG) {
1982467d	436	parse_object(tag->object.sha1);
2075ffb5	437	string_list_append(full_name, extra_refs)->util = tag;
f2dc849e JS	438	tag = (struct tag *)tag->tagged;
	439	}
	440	if (!tag)
	441	die ("Tag %s points nowhere?", e->name);
	442	switch(tag->object.type) {
	443	case OBJ_COMMIT:
	444	commit = (struct commit *)tag;
	445	break;
	446	case OBJ_BLOB:
	447	handle_object(tag->object.sha1);
	448	continue;
1982467d	449	default: /* OBJ_TAG (nested tags) is already handled */
c0582c53 EFL	450	warning("Tag points to object of unexpected type %s, skipping.",
	451	typename(tag->object.type));
	452	continue;
f2dc849e JS	453	}
	454	break;
	455	default:
2d07f6d4 EFL	456	warning("%s: Unexpected object of type %s, skipping.",
	457	e->name,
	458	typename(e->item->type));
	459	continue;
f2dc849e JS	460	}
	461	if (commit->util)
	462	/* more than one name for the same object */
2075ffb5	463	string_list_append(full_name, extra_refs)->util = commit;
f2dc849e JS	464	else
	465	commit->util = full_name;
	466	}
	467	}
	468
c455c87c	469	static void handle_tags_and_duplicates(struct string_list *extra_refs)
f2dc849e JS	470	{
	471	struct commit *commit;
	472	int i;
	473
	474	for (i = extra_refs->nr - 1; i >= 0; i--) {
c455c87c	475	const char *name = extra_refs->items[i].string;
f2dc849e JS	476	struct object *object = extra_refs->items[i].util;
	477	switch (object->type) {
	478	case OBJ_TAG:
	479	handle_tag(name, (struct tag *)object);
	480	break;
	481	case OBJ_COMMIT:
	482	/* create refs pointing to already seen commits */
	483	commit = (struct commit *)object;
	484	printf("reset %s\nfrom :%d\n\n", name,
	485	get_object_mark(&commit->object));
	486	show_progress();
	487	break;
	488	}
	489	}
	490	}
	491
df6a7ff7 PB	492	static void export_marks(char *file)
	493	{
	494	unsigned int i;
	495	uint32_t mark;
	496	struct object_decoration *deco = idnums.hash;
	497	FILE *f;
	498
	499	f = fopen(file, "w");
	500	if (!f)
	501	error("Unable to open marks file %s for writing", file);
	502
69913575 JH	503	for (i = 0; i < idnums.size; i++) {
69913575 JH	504	if (deco->base && deco->base->type == 1) {
df6a7ff7	505	mark = ptr_to_mark(deco->decoration);
d47fb8b0 RJ	506	fprintf(f, ":%"PRIu32" %s\n", mark,
d47fb8b0 RJ	507	sha1_to_hex(deco->base->sha1));
df6a7ff7	508	}
69913575	509	deco++;
df6a7ff7 PB	510	}
	511
	512	if (ferror(f) \|\| fclose(f))
	513	error("Unable to write marks file %s.", file);
	514	}
	515
69913575	516	static void import_marks(char *input_file)
df6a7ff7 PB	517	{
	518	char line[512];
	519	FILE *f = fopen(input_file, "r");
	520	if (!f)
	521	die("cannot read %s: %s", input_file, strerror(errno));
	522
	523	while (fgets(line, sizeof(line), f)) {
	524	uint32_t mark;
	525	char line_end, mark_end;
	526	unsigned char sha1[20];
	527	struct object *object;
	528
	529	line_end = strchr(line, '\n');
	530	if (line[0] != ':' \|\| !line_end)
	531	die("corrupt mark line: %s", line);
69913575	532	*line_end = '\0';
df6a7ff7 PB	533
	534	mark = strtoumax(line + 1, &mark_end, 10);
	535	if (!mark \|\| mark_end == line + 1
	536	\|\| *mark_end != ' ' \|\| get_sha1(mark_end + 1, sha1))
	537	die("corrupt mark line: %s", line);
	538
	539	object = parse_object(sha1);
	540	if (!object)
	541	die ("Could not read blob %s", sha1_to_hex(sha1));
	542
	543	if (object->flags & SHOWN)
	544	error("Object %s already has a mark", sha1);
	545
	546	mark_object(object, mark);
	547	if (last_idnum < mark)
	548	last_idnum = mark;
	549
	550	object->flags \|= SHOWN;
	551	}
	552	fclose(f);
	553	}
	554
f2dc849e JS	555	int cmd_fast_export(int argc, const char *argv, const char prefix)
	556	{
	557	struct rev_info revs;
	558	struct object_array commits = { 0, 0, NULL };
c455c87c	559	struct string_list extra_refs = { NULL, 0, 0, 0 };
f2dc849e	560	struct commit *commit;
df6a7ff7	561	char export_filename = NULL, import_filename = NULL;
f2dc849e JS	562	struct option options[] = {
	563	OPT_INTEGER(0, "progress", &progress,
	564	"show progress after <n> objects"),
	565	OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
	566	"select handling of signed tags",
	567	parse_opt_signed_tag_mode),
2d8ad469 EN	568	OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
	569	"select handling of tags that tag filtered objects",
	570	parse_opt_tag_of_filtered_mode),
df6a7ff7 PB	571	OPT_STRING(0, "export-marks", &export_filename, "FILE",
	572	"Dump marks to this file"),
	573	OPT_STRING(0, "import-marks", &import_filename, "FILE",
	574	"Import marks from this file"),
4e46a8d6 JS	575	OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
4e46a8d6 JS	576	"Fake a tagger when tags lack one"),
f2dc849e JS	577	OPT_END()
	578	};
	579
dcfdbdf0 MV	580	if (argc == 1)
	581	usage_with_options (fast_export_usage, options);
	582
f2dc849e	583	/* we handle encodings */
ef90d6d4	584	git_config(git_default_config, NULL);
f2dc849e JS	585
f2dc849e JS	586	init_revisions(&revs, prefix);
668f3aa7	587	revs.topo_order = 1;
2374502c	588	revs.show_source = 1;
32164131	589	revs.rewrite_parents = 1;
f2dc849e	590	argc = setup_revisions(argc, argv, &revs, NULL);
37782920	591	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
f2dc849e JS	592	if (argc > 1)
	593	usage_with_options (fast_export_usage, options);
	594
df6a7ff7 PB	595	if (import_filename)
	596	import_marks(import_filename);
	597
f2dc849e JS	598	get_tags_and_duplicates(&revs.pending, &extra_refs);
f2dc849e JS	599
3d51e1b5 MK	600	if (prepare_revision_walk(&revs))
3d51e1b5 MK	601	die("revision walk setup failed");
f2dc849e JS	602	revs.diffopt.format_callback = show_filemodify;
	603	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
	604	while ((commit = get_revision(&revs))) {
	605	if (has_unshown_parent(commit)) {
f2dc849e	606	add_object_array(&commit->object, NULL, &commits);
f2dc849e JS	607	}
	608	else {
	609	handle_commit(commit, &revs);
	610	handle_tail(&commits, &revs);
	611	}
	612	}
	613
	614	handle_tags_and_duplicates(&extra_refs);
	615
df6a7ff7 PB	616	if (export_filename)
	617	export_marks(export_filename);
	618
f2dc849e JS	619	return 0;
f2dc849e JS	620	}