[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 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 (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)
		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);
			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
	150	static void show_filemodify(struct diff_queue_struct *q,
	151	struct diff_options options, void data)
	152	{
	153	int i;
	154	for (i = 0; i < q->nr; i++) {
ae7c5dce	155	struct diff_filespec *ospec = q->queue[i]->one;
f2dc849e	156	struct diff_filespec *spec = q->queue[i]->two;
ae7c5dce AG	157
	158	switch (q->queue[i]->status) {
	159	case DIFF_STATUS_DELETED:
f2dc849e	160	printf("D %s\n", spec->path);
ae7c5dce AG	161	break;
	162
	163	case DIFF_STATUS_COPIED:
	164	case DIFF_STATUS_RENAMED:
	165	printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
	166	ospec->path, spec->path);
	167
	168	if (!hashcmp(ospec->sha1, spec->sha1) &&
	169	ospec->mode == spec->mode)
	170	break;
	171	/* fallthrough */
	172
	173	case DIFF_STATUS_TYPE_CHANGED:
	174	case DIFF_STATUS_MODIFIED:
	175	case DIFF_STATUS_ADDED:
03db4525 AG	176	/*
	177	* Links refer to objects in another repositories;
	178	* output the SHA-1 verbatim.
	179	*/
79559f27	180	if (no_data \|\| S_ISGITLINK(spec->mode))
03db4525 AG	181	printf("M %06o %s %s\n", spec->mode,
	182	sha1_to_hex(spec->sha1), spec->path);
	183	else {
	184	struct object *object = lookup_object(spec->sha1);
	185	printf("M %06o :%d %s\n", spec->mode,
	186	get_object_mark(object), spec->path);
	187	}
ae7c5dce AG	188	break;
	189
	190	default:
	191	die("Unexpected comparison status '%c' for %s, %s",
	192	q->queue[i]->status,
	193	ospec->path ? ospec->path : "none",
	194	spec->path ? spec->path : "none");
f2dc849e JS	195	}
	196	}
	197	}
	198
	199	static const char find_encoding(const char begin, const char *end)
	200	{
	201	const char *needle = "\nencoding ";
	202	char bol, eol;
	203
	204	bol = memmem(begin, end ? end - begin : strlen(begin),
	205	needle, strlen(needle));
	206	if (!bol)
	207	return git_commit_encoding;
	208	bol += strlen(needle);
	209	eol = strchrnul(bol, '\n');
	210	*eol = '\0';
	211	return bol;
	212	}
	213
	214	static void handle_commit(struct commit commit, struct rev_info rev)
	215	{
	216	int saved_output_format = rev->diffopt.output_format;
	217	const char author, author_end, committer, committer_end;
	218	const char encoding, message;
	219	char *reencoded = NULL;
	220	struct commit_list *p;
	221	int i;
	222
	223	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
	224
	225	parse_commit(commit);
	226	author = strstr(commit->buffer, "\nauthor ");
	227	if (!author)
	228	die ("Could not find author in commit %s",
	229	sha1_to_hex(commit->object.sha1));
	230	author++;
	231	author_end = strchrnul(author, '\n');
	232	committer = strstr(author_end, "\ncommitter ");
	233	if (!committer)
	234	die ("Could not find committer in commit %s",
	235	sha1_to_hex(commit->object.sha1));
	236	committer++;
	237	committer_end = strchrnul(committer, '\n');
	238	message = strstr(committer_end, "\n\n");
	239	encoding = find_encoding(committer_end, message);
	240	if (message)
	241	message += 2;
	242
ebeec7db EN	243	if (commit->parents &&
ebeec7db EN	244	get_object_mark(&commit->parents->item->object) != 0) {
f2dc849e JS	245	parse_commit(commit->parents->item);
	246	diff_tree_sha1(commit->parents->item->tree->object.sha1,
	247	commit->tree->object.sha1, "", &rev->diffopt);
	248	}
	249	else
	250	diff_root_tree_sha1(commit->tree->object.sha1,
	251	"", &rev->diffopt);
	252
03db4525	253	/* Export the referenced blobs, and remember the marks. */
f2dc849e	254	for (i = 0; i < diff_queued_diff.nr; i++)
03db4525 AG	255	if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
03db4525 AG	256	handle_object(diff_queued_diff.queue[i]->two->sha1);
f2dc849e	257
df6a7ff7	258	mark_next_object(&commit->object);
f2dc849e JS	259	if (!is_encoding_utf8(encoding))
f2dc849e JS	260	reencoded = reencode_string(message, "UTF-8", encoding);
d8933f01 SP	261	if (!commit->parents)
d8933f01 SP	262	printf("reset %s\n", (const char*)commit->util);
6e1c2344	263	printf("commit %s\nmark :%"PRIu32"\n%.s\n%.s\ndata %u\n%s",
f2dc849e JS	264	(const char *)commit->util, last_idnum,
	265	(int)(author_end - author), author,
	266	(int)(committer_end - committer), committer,
	267	(unsigned)(reencoded
	268	? strlen(reencoded) : message
	269	? strlen(message) : 0),
	270	reencoded ? reencoded : message ? message : "");
8e0f7003	271	free(reencoded);
f2dc849e JS	272
	273	for (i = 0, p = commit->parents; p; p = p->next) {
	274	int mark = get_object_mark(&p->item->object);
	275	if (!mark)
	276	continue;
	277	if (i == 0)
	278	printf("from :%d\n", mark);
f2dc849e	279	else
5070b49e	280	printf("merge :%d\n", mark);
f2dc849e JS	281	i++;
f2dc849e JS	282	}
f2dc849e JS	283
	284	log_tree_diff_flush(rev);
	285	rev->diffopt.output_format = saved_output_format;
	286
	287	printf("\n");
	288
	289	show_progress();
	290	}
	291
	292	static void handle_tail(struct object_array commits, struct rev_info revs)
	293	{
	294	struct commit *commit;
	295	while (commits->nr) {
	296	commit = (struct commit *)commits->objects[commits->nr - 1].item;
	297	if (has_unshown_parent(commit))
	298	return;
	299	handle_commit(commit, revs);
	300	commits->nr--;
	301	}
	302	}
	303
	304	static void handle_tag(const char name, struct tag tag)
	305	{
	306	unsigned long size;
	307	enum object_type type;
	308	char *buf;
	309	const char tagger, tagger_end, *message;
	310	size_t message_size = 0;
02c48cd6	311	struct object *tagged;
2d8ad469 EN	312	int tagged_mark;
2d8ad469 EN	313	struct commit *p;
02c48cd6 EN	314
	315	/* Trees have no identifer in fast-export output, thus we have no way
	316	* to output tags of trees, tags of tags of trees, etc. Simply omit
	317	* such tags.
	318	*/
	319	tagged = tag->tagged;
	320	while (tagged->type == OBJ_TAG) {
	321	tagged = ((struct tag *)tagged)->tagged;
	322	}
	323	if (tagged->type == OBJ_TREE) {
	324	warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
	325	sha1_to_hex(tag->object.sha1));
	326	return;
	327	}
f2dc849e JS	328
	329	buf = read_sha1_file(tag->object.sha1, &type, &size);
	330	if (!buf)
	331	die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	332	message = memmem(buf, size, "\n\n", 2);
	333	if (message) {
	334	message += 2;
	335	message_size = strlen(message);
	336	}
	337	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
4e46a8d6 JS	338	if (!tagger) {
	339	if (fake_missing_tagger)
	340	tagger = "tagger Unspecified Tagger "
	341	"<unspecified-tagger> 0 +0000";
	342	else
	343	tagger = "";
	344	tagger_end = tagger + strlen(tagger);
	345	} else {
	346	tagger++;
	347	tagger_end = strchrnul(tagger, '\n');
	348	}
f2dc849e JS	349
	350	/* handle signed tags */
	351	if (message) {
	352	const char *signature = strstr(message,
	353	"\n-----BEGIN PGP SIGNATURE-----\n");
	354	if (signature)
	355	switch(signed_tag_mode) {
	356	case ABORT:
	357	die ("Encountered signed tag %s; use "
	358	"--signed-tag=<mode> to handle it.",
	359	sha1_to_hex(tag->object.sha1));
	360	case WARN:
	361	warning ("Exporting signed tag %s",
	362	sha1_to_hex(tag->object.sha1));
	363	/* fallthru */
ee4bc371	364	case VERBATIM:
f2dc849e JS	365	break;
	366	case STRIP:
	367	message_size = signature + 1 - message;
	368	break;
	369	}
	370	}
	371
2d8ad469 EN	372	/* handle tag->tagged having been filtered out due to paths specified */
	373	tagged = tag->tagged;
	374	tagged_mark = get_object_mark(tagged);
	375	if (!tagged_mark) {
	376	switch(tag_of_filtered_mode) {
	377	case ABORT:
	378	die ("Tag %s tags unexported object; use "
	379	"--tag-of-filtered-object=<mode> to handle it.",
	380	sha1_to_hex(tag->object.sha1));
	381	case DROP:
	382	/* Ignore this tag altogether */
	383	return;
	384	case REWRITE:
	385	if (tagged->type != OBJ_COMMIT) {
	386	die ("Tag %s tags unexported %s!",
	387	sha1_to_hex(tag->object.sha1),
	388	typename(tagged->type));
	389	}
	390	p = (struct commit *)tagged;
	391	for (;;) {
	392	if (p->parents && p->parents->next)
	393	break;
	394	if (p->object.flags & UNINTERESTING)
	395	break;
	396	if (!(p->object.flags & TREESAME))
	397	break;
	398	if (!p->parents)
	399	die ("Can't find replacement commit for tag %s\n",
	400	sha1_to_hex(tag->object.sha1));
	401	p = p->parents->item;
	402	}
	403	tagged_mark = get_object_mark(&p->object);
	404	}
	405	}
	406
f2dc849e JS	407	if (!prefixcmp(name, "refs/tags/"))
f2dc849e JS	408	name += 10;
4e46a8d6	409	printf("tag %s\nfrom :%d\n%.s%sdata %d\n%.s\n",
2d8ad469	410	name, tagged_mark,
f2dc849e	411	(int)(tagger_end - tagger), tagger,
4e46a8d6	412	tagger == tagger_end ? "" : "\n",
f2dc849e JS	413	(int)message_size, (int)message_size, message ? message : "");
	414	}
	415
	416	static void get_tags_and_duplicates(struct object_array *pending,
c455c87c	417	struct string_list *extra_refs)
f2dc849e JS	418	{
	419	struct tag *tag;
	420	int i;
	421
	422	for (i = 0; i < pending->nr; i++) {
	423	struct object_array_entry *e = pending->objects + i;
	424	unsigned char sha1[20];
	425	struct commit *commit = commit;
	426	char *full_name;
	427
	428	if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
	429	continue;
	430
	431	switch (e->item->type) {
	432	case OBJ_COMMIT:
	433	commit = (struct commit *)e->item;
	434	break;
	435	case OBJ_TAG:
	436	tag = (struct tag *)e->item;
1982467d EFL	437
1982467d EFL	438	/* handle nested tags */
f2dc849e	439	while (tag && tag->object.type == OBJ_TAG) {
1982467d	440	parse_object(tag->object.sha1);
2075ffb5	441	string_list_append(full_name, extra_refs)->util = tag;
f2dc849e JS	442	tag = (struct tag *)tag->tagged;
	443	}
	444	if (!tag)
	445	die ("Tag %s points nowhere?", e->name);
	446	switch(tag->object.type) {
	447	case OBJ_COMMIT:
	448	commit = (struct commit *)tag;
	449	break;
	450	case OBJ_BLOB:
	451	handle_object(tag->object.sha1);
	452	continue;
1982467d	453	default: /* OBJ_TAG (nested tags) is already handled */
c0582c53 EFL	454	warning("Tag points to object of unexpected type %s, skipping.",
	455	typename(tag->object.type));
	456	continue;
f2dc849e JS	457	}
	458	break;
	459	default:
2d07f6d4 EFL	460	warning("%s: Unexpected object of type %s, skipping.",
	461	e->name,
	462	typename(e->item->type));
	463	continue;
f2dc849e JS	464	}
	465	if (commit->util)
	466	/* more than one name for the same object */
2075ffb5	467	string_list_append(full_name, extra_refs)->util = commit;
f2dc849e JS	468	else
	469	commit->util = full_name;
	470	}
	471	}
	472
c455c87c	473	static void handle_tags_and_duplicates(struct string_list *extra_refs)
f2dc849e JS	474	{
	475	struct commit *commit;
	476	int i;
	477
	478	for (i = extra_refs->nr - 1; i >= 0; i--) {
c455c87c	479	const char *name = extra_refs->items[i].string;
f2dc849e JS	480	struct object *object = extra_refs->items[i].util;
	481	switch (object->type) {
	482	case OBJ_TAG:
	483	handle_tag(name, (struct tag *)object);
	484	break;
	485	case OBJ_COMMIT:
	486	/* create refs pointing to already seen commits */
	487	commit = (struct commit *)object;
	488	printf("reset %s\nfrom :%d\n\n", name,
	489	get_object_mark(&commit->object));
	490	show_progress();
	491	break;
	492	}
	493	}
	494	}
	495
df6a7ff7 PB	496	static void export_marks(char *file)
	497	{
	498	unsigned int i;
	499	uint32_t mark;
	500	struct object_decoration *deco = idnums.hash;
	501	FILE *f;
96d69b55	502	int e = 0;
df6a7ff7 PB	503
	504	f = fopen(file, "w");
	505	if (!f)
96d69b55	506	error("Unable to open marks file %s for writing.", file);
df6a7ff7	507
69913575 JH	508	for (i = 0; i < idnums.size; i++) {
69913575 JH	509	if (deco->base && deco->base->type == 1) {
df6a7ff7	510	mark = ptr_to_mark(deco->decoration);
96d69b55 MA	511	if (fprintf(f, ":%"PRIu32" %s\n", mark,
	512	sha1_to_hex(deco->base->sha1)) < 0) {
	513	e = 1;
	514	break;
	515	}
df6a7ff7	516	}
69913575	517	deco++;
df6a7ff7 PB	518	}
df6a7ff7 PB	519
96d69b55 MA	520	e \|= ferror(f);
	521	e \|= fclose(f);
	522	if (e)
df6a7ff7 PB	523	error("Unable to write marks file %s.", file);
	524	}
	525
69913575	526	static void import_marks(char *input_file)
df6a7ff7 PB	527	{
	528	char line[512];
	529	FILE *f = fopen(input_file, "r");
	530	if (!f)
d824cbba	531	die_errno("cannot read '%s'", input_file);
df6a7ff7 PB	532
	533	while (fgets(line, sizeof(line), f)) {
	534	uint32_t mark;
	535	char line_end, mark_end;
	536	unsigned char sha1[20];
	537	struct object *object;
	538
	539	line_end = strchr(line, '\n');
	540	if (line[0] != ':' \|\| !line_end)
	541	die("corrupt mark line: %s", line);
69913575	542	*line_end = '\0';
df6a7ff7 PB	543
	544	mark = strtoumax(line + 1, &mark_end, 10);
	545	if (!mark \|\| mark_end == line + 1
	546	\|\| *mark_end != ' ' \|\| get_sha1(mark_end + 1, sha1))
	547	die("corrupt mark line: %s", line);
	548
	549	object = parse_object(sha1);
	550	if (!object)
	551	die ("Could not read blob %s", sha1_to_hex(sha1));
	552
	553	if (object->flags & SHOWN)
	554	error("Object %s already has a mark", sha1);
	555
	556	mark_object(object, mark);
	557	if (last_idnum < mark)
	558	last_idnum = mark;
	559
	560	object->flags \|= SHOWN;
	561	}
	562	fclose(f);
	563	}
	564
f2dc849e JS	565	int cmd_fast_export(int argc, const char *argv, const char prefix)
	566	{
	567	struct rev_info revs;
	568	struct object_array commits = { 0, 0, NULL };
c455c87c	569	struct string_list extra_refs = { NULL, 0, 0, 0 };
f2dc849e	570	struct commit *commit;
df6a7ff7	571	char export_filename = NULL, import_filename = NULL;
f2dc849e JS	572	struct option options[] = {
	573	OPT_INTEGER(0, "progress", &progress,
	574	"show progress after <n> objects"),
	575	OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
	576	"select handling of signed tags",
	577	parse_opt_signed_tag_mode),
2d8ad469 EN	578	OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
	579	"select handling of tags that tag filtered objects",
	580	parse_opt_tag_of_filtered_mode),
df6a7ff7 PB	581	OPT_STRING(0, "export-marks", &export_filename, "FILE",
	582	"Dump marks to this file"),
	583	OPT_STRING(0, "import-marks", &import_filename, "FILE",
	584	"Import marks from this file"),
4e46a8d6 JS	585	OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
4e46a8d6 JS	586	"Fake a tagger when tags lack one"),
79559f27 GI	587	{ OPTION_NEGBIT, 0, "data", &no_data, NULL,
	588	"Skip output of blob data",
	589	PARSE_OPT_NOARG \| PARSE_OPT_NEGHELP, NULL, 1 },
f2dc849e JS	590	OPT_END()
	591	};
	592
dcfdbdf0 MV	593	if (argc == 1)
	594	usage_with_options (fast_export_usage, options);
	595
f2dc849e	596	/* we handle encodings */
ef90d6d4	597	git_config(git_default_config, NULL);
f2dc849e JS	598
f2dc849e JS	599	init_revisions(&revs, prefix);
668f3aa7	600	revs.topo_order = 1;
2374502c	601	revs.show_source = 1;
32164131	602	revs.rewrite_parents = 1;
f2dc849e	603	argc = setup_revisions(argc, argv, &revs, NULL);
37782920	604	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
f2dc849e JS	605	if (argc > 1)
	606	usage_with_options (fast_export_usage, options);
	607
df6a7ff7 PB	608	if (import_filename)
	609	import_marks(import_filename);
	610
f2dc849e JS	611	get_tags_and_duplicates(&revs.pending, &extra_refs);
f2dc849e JS	612
3d51e1b5 MK	613	if (prepare_revision_walk(&revs))
3d51e1b5 MK	614	die("revision walk setup failed");
f2dc849e JS	615	revs.diffopt.format_callback = show_filemodify;
	616	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
	617	while ((commit = get_revision(&revs))) {
	618	if (has_unshown_parent(commit)) {
f2dc849e	619	add_object_array(&commit->object, NULL, &commits);
f2dc849e JS	620	}
	621	else {
	622	handle_commit(commit, &revs);
	623	handle_tail(&commits, &revs);
	624	}
	625	}
	626
	627	handle_tags_and_duplicates(&extra_refs);
	628
df6a7ff7 PB	629	if (export_filename)
	630	export_marks(export_filename);
	631
f2dc849e JS	632	return 0;
f2dc849e JS	633	}