[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 full_tree;

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 &&
	    !full_tree) {
		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++;
	}

	if (full_tree)
		printf("deleteall\n");
	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(extra_refs, full_name)->util = tag;
				tag = (struct tag *)tag->tagged;
			}
			if (!tag)
				die ("Tag %s points nowhere?", e->name);
			switch(tag->object.type) {
			case OBJ_COMMIT:
				commit = (struct commit *)tag;
				break;
			case OBJ_BLOB:
				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(extra_refs, full_name)->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 = OBJECT_ARRAY_INIT;
	struct string_list extra_refs = STRING_LIST_INIT_NODUP;
	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_BOOLEAN(0, "full-tree", &full_tree,
			     "Output full tree for each commit"),
		{ 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);

	if (import_filename && revs.prune_data)
		full_tree = 1;

	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;
7f40ab09	30	static int full_tree;
f2dc849e JS	31
	32	static int parse_opt_signed_tag_mode(const struct option *opt,
	33	const char *arg, int unset)
	34	{
	35	if (unset \|\| !strcmp(arg, "abort"))
	36	signed_tag_mode = ABORT;
ee4bc371 JS	37	else if (!strcmp(arg, "verbatim") \|\| !strcmp(arg, "ignore"))
ee4bc371 JS	38	signed_tag_mode = VERBATIM;
f2dc849e JS	39	else if (!strcmp(arg, "warn"))
	40	signed_tag_mode = WARN;
	41	else if (!strcmp(arg, "strip"))
	42	signed_tag_mode = STRIP;
	43	else
	44	return error("Unknown signed-tag mode: %s", arg);
	45	return 0;
	46	}
	47
2d8ad469 EN	48	static int parse_opt_tag_of_filtered_mode(const struct option *opt,
	49	const char *arg, int unset)
	50	{
	51	if (unset \|\| !strcmp(arg, "abort"))
	52	tag_of_filtered_mode = ABORT;
	53	else if (!strcmp(arg, "drop"))
	54	tag_of_filtered_mode = DROP;
	55	else if (!strcmp(arg, "rewrite"))
	56	tag_of_filtered_mode = REWRITE;
	57	else
	58	return error("Unknown tag-of-filtered mode: %s", arg);
	59	return 0;
	60	}
	61
f2dc849e JS	62	static struct decoration idnums;
	63	static uint32_t last_idnum;
	64
	65	static int has_unshown_parent(struct commit *commit)
	66	{
	67	struct commit_list *parent;
	68
	69	for (parent = commit->parents; parent; parent = parent->next)
	70	if (!(parent->item->object.flags & SHOWN) &&
	71	!(parent->item->object.flags & UNINTERESTING))
	72	return 1;
	73	return 0;
	74	}
	75
	76	/* Since intptr_t is C99, we do not use it here */
df6a7ff7	77	static inline uint32_t *mark_to_ptr(uint32_t mark)
f2dc849e	78	{
df6a7ff7 PB	79	return ((uint32_t *)NULL) + mark;
	80	}
	81
	82	static inline uint32_t ptr_to_mark(void * mark)
	83	{
	84	return (uint32_t )mark - (uint32_t )NULL;
	85	}
	86
	87	static inline void mark_object(struct object *object, uint32_t mark)
	88	{
	89	add_decoration(&idnums, object, mark_to_ptr(mark));
	90	}
	91
	92	static inline void mark_next_object(struct object *object)
	93	{
	94	mark_object(object, ++last_idnum);
f2dc849e JS	95	}
	96
	97	static int get_object_mark(struct object *object)
	98	{
	99	void *decoration = lookup_decoration(&idnums, object);
	100	if (!decoration)
	101	return 0;
df6a7ff7	102	return ptr_to_mark(decoration);
f2dc849e JS	103	}
	104
	105	static void show_progress(void)
	106	{
	107	static int counter = 0;
	108	if (!progress)
	109	return;
	110	if ((++counter % progress) == 0)
	111	printf("progress %d objects\n", counter);
	112	}
	113
	114	static void handle_object(const unsigned char *sha1)
	115	{
	116	unsigned long size;
	117	enum object_type type;
	118	char *buf;
	119	struct object *object;
	120
79559f27 GI	121	if (no_data)
	122	return;
	123
f2dc849e JS	124	if (is_null_sha1(sha1))
	125	return;
	126
	127	object = parse_object(sha1);
	128	if (!object)
	129	die ("Could not read blob %s", sha1_to_hex(sha1));
	130
	131	if (object->flags & SHOWN)
	132	return;
	133
	134	buf = read_sha1_file(sha1, &type, &size);
	135	if (!buf)
	136	die ("Could not read blob %s", sha1_to_hex(sha1));
	137
df6a7ff7	138	mark_next_object(object);
f2dc849e	139
6e1c2344	140	printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
b0fe0d72	141	if (size && fwrite(buf, size, 1, stdout) != 1)
0721c314	142	die_errno ("Could not write blob '%s'", sha1_to_hex(sha1));
f2dc849e JS	143	printf("\n");
	144
	145	show_progress();
	146
	147	object->flags \|= SHOWN;
	148	free(buf);
	149	}
	150
060df624 EN	151	static int depth_first(const void a_, const void b_)
	152	{
	153	const struct diff_filepair a = ((const struct diff_filepair **)a_);
	154	const struct diff_filepair b = ((const struct diff_filepair **)b_);
	155	const char name_a, name_b;
	156	int len_a, len_b, len;
	157	int cmp;
	158
	159	name_a = a->one ? a->one->path : a->two->path;
	160	name_b = b->one ? b->one->path : b->two->path;
	161
	162	len_a = strlen(name_a);
	163	len_b = strlen(name_b);
	164	len = (len_a < len_b) ? len_a : len_b;
	165
	166	/* strcmp will sort 'd' before 'd/e', we want 'd/e' before 'd' */
	167	cmp = memcmp(name_a, name_b, len);
	168	if (cmp)
	169	return cmp;
4ce6fb80 JS	170	cmp = len_b - len_a;
	171	if (cmp)
	172	return cmp;
	173	/*
	174	* Move 'R'ename entries last so that all references of the file
	175	* appear in the output before it is renamed (e.g., when a file
	176	* was copied and renamed in the same commit).
	177	*/
	178	return (a->status == 'R') - (b->status == 'R');
060df624 EN	179	}
060df624 EN	180
f2dc849e JS	181	static void show_filemodify(struct diff_queue_struct *q,
	182	struct diff_options options, void data)
	183	{
	184	int i;
060df624 EN	185
	186	/*
	187	* Handle files below a directory first, in case they are all deleted
	188	* and the directory changes to a file or symlink.
	189	*/
	190	qsort(q->queue, q->nr, sizeof(q->queue[0]), depth_first);
	191
f2dc849e	192	for (i = 0; i < q->nr; i++) {
ae7c5dce	193	struct diff_filespec *ospec = q->queue[i]->one;
f2dc849e	194	struct diff_filespec *spec = q->queue[i]->two;
ae7c5dce AG	195
	196	switch (q->queue[i]->status) {
	197	case DIFF_STATUS_DELETED:
f2dc849e	198	printf("D %s\n", spec->path);
ae7c5dce AG	199	break;
	200
	201	case DIFF_STATUS_COPIED:
	202	case DIFF_STATUS_RENAMED:
	203	printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
	204	ospec->path, spec->path);
	205
	206	if (!hashcmp(ospec->sha1, spec->sha1) &&
	207	ospec->mode == spec->mode)
	208	break;
	209	/* fallthrough */
	210
	211	case DIFF_STATUS_TYPE_CHANGED:
	212	case DIFF_STATUS_MODIFIED:
	213	case DIFF_STATUS_ADDED:
03db4525 AG	214	/*
	215	* Links refer to objects in another repositories;
	216	* output the SHA-1 verbatim.
	217	*/
79559f27	218	if (no_data \|\| S_ISGITLINK(spec->mode))
03db4525 AG	219	printf("M %06o %s %s\n", spec->mode,
	220	sha1_to_hex(spec->sha1), spec->path);
	221	else {
	222	struct object *object = lookup_object(spec->sha1);
	223	printf("M %06o :%d %s\n", spec->mode,
	224	get_object_mark(object), spec->path);
	225	}
ae7c5dce AG	226	break;
	227
	228	default:
	229	die("Unexpected comparison status '%c' for %s, %s",
	230	q->queue[i]->status,
	231	ospec->path ? ospec->path : "none",
	232	spec->path ? spec->path : "none");
f2dc849e JS	233	}
	234	}
	235	}
	236
	237	static const char find_encoding(const char begin, const char *end)
	238	{
	239	const char *needle = "\nencoding ";
	240	char bol, eol;
	241
	242	bol = memmem(begin, end ? end - begin : strlen(begin),
	243	needle, strlen(needle));
	244	if (!bol)
	245	return git_commit_encoding;
	246	bol += strlen(needle);
	247	eol = strchrnul(bol, '\n');
	248	*eol = '\0';
	249	return bol;
	250	}
	251
	252	static void handle_commit(struct commit commit, struct rev_info rev)
	253	{
	254	int saved_output_format = rev->diffopt.output_format;
	255	const char author, author_end, committer, committer_end;
	256	const char encoding, message;
	257	char *reencoded = NULL;
	258	struct commit_list *p;
	259	int i;
	260
	261	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
	262
	263	parse_commit(commit);
	264	author = strstr(commit->buffer, "\nauthor ");
	265	if (!author)
	266	die ("Could not find author in commit %s",
	267	sha1_to_hex(commit->object.sha1));
	268	author++;
	269	author_end = strchrnul(author, '\n');
	270	committer = strstr(author_end, "\ncommitter ");
	271	if (!committer)
	272	die ("Could not find committer in commit %s",
	273	sha1_to_hex(commit->object.sha1));
	274	committer++;
	275	committer_end = strchrnul(committer, '\n');
	276	message = strstr(committer_end, "\n\n");
	277	encoding = find_encoding(committer_end, message);
	278	if (message)
	279	message += 2;
	280
ebeec7db	281	if (commit->parents &&
4087a02e EN	282	get_object_mark(&commit->parents->item->object) != 0 &&
4087a02e EN	283	!full_tree) {
f2dc849e JS	284	parse_commit(commit->parents->item);
	285	diff_tree_sha1(commit->parents->item->tree->object.sha1,
	286	commit->tree->object.sha1, "", &rev->diffopt);
	287	}
	288	else
	289	diff_root_tree_sha1(commit->tree->object.sha1,
	290	"", &rev->diffopt);
	291
03db4525	292	/* Export the referenced blobs, and remember the marks. */
f2dc849e	293	for (i = 0; i < diff_queued_diff.nr; i++)
03db4525 AG	294	if (!S_ISGITLINK(diff_queued_diff.queue[i]->two->mode))
03db4525 AG	295	handle_object(diff_queued_diff.queue[i]->two->sha1);
f2dc849e	296
df6a7ff7	297	mark_next_object(&commit->object);
f2dc849e JS	298	if (!is_encoding_utf8(encoding))
f2dc849e JS	299	reencoded = reencode_string(message, "UTF-8", encoding);
d8933f01 SP	300	if (!commit->parents)
d8933f01 SP	301	printf("reset %s\n", (const char*)commit->util);
6e1c2344	302	printf("commit %s\nmark :%"PRIu32"\n%.s\n%.s\ndata %u\n%s",
f2dc849e JS	303	(const char *)commit->util, last_idnum,
	304	(int)(author_end - author), author,
	305	(int)(committer_end - committer), committer,
	306	(unsigned)(reencoded
	307	? strlen(reencoded) : message
	308	? strlen(message) : 0),
	309	reencoded ? reencoded : message ? message : "");
8e0f7003	310	free(reencoded);
f2dc849e JS	311
	312	for (i = 0, p = commit->parents; p; p = p->next) {
	313	int mark = get_object_mark(&p->item->object);
	314	if (!mark)
	315	continue;
	316	if (i == 0)
	317	printf("from :%d\n", mark);
f2dc849e	318	else
5070b49e	319	printf("merge :%d\n", mark);
f2dc849e JS	320	i++;
f2dc849e JS	321	}
f2dc849e	322
4087a02e EN	323	if (full_tree)
4087a02e EN	324	printf("deleteall\n");
f2dc849e JS	325	log_tree_diff_flush(rev);
	326	rev->diffopt.output_format = saved_output_format;
	327
	328	printf("\n");
	329
	330	show_progress();
	331	}
	332
	333	static void handle_tail(struct object_array commits, struct rev_info revs)
	334	{
	335	struct commit *commit;
	336	while (commits->nr) {
	337	commit = (struct commit *)commits->objects[commits->nr - 1].item;
	338	if (has_unshown_parent(commit))
	339	return;
	340	handle_commit(commit, revs);
	341	commits->nr--;
	342	}
	343	}
	344
	345	static void handle_tag(const char name, struct tag tag)
	346	{
	347	unsigned long size;
	348	enum object_type type;
	349	char *buf;
	350	const char tagger, tagger_end, *message;
	351	size_t message_size = 0;
02c48cd6	352	struct object *tagged;
2d8ad469 EN	353	int tagged_mark;
2d8ad469 EN	354	struct commit *p;
02c48cd6 EN	355
	356	/* Trees have no identifer in fast-export output, thus we have no way
	357	* to output tags of trees, tags of tags of trees, etc. Simply omit
	358	* such tags.
	359	*/
	360	tagged = tag->tagged;
	361	while (tagged->type == OBJ_TAG) {
	362	tagged = ((struct tag *)tagged)->tagged;
	363	}
	364	if (tagged->type == OBJ_TREE) {
	365	warning("Omitting tag %s,\nsince tags of trees (or tags of tags of trees, etc.) are not supported.",
	366	sha1_to_hex(tag->object.sha1));
	367	return;
	368	}
f2dc849e JS	369
	370	buf = read_sha1_file(tag->object.sha1, &type, &size);
	371	if (!buf)
	372	die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
	373	message = memmem(buf, size, "\n\n", 2);
	374	if (message) {
	375	message += 2;
	376	message_size = strlen(message);
	377	}
	378	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
4e46a8d6 JS	379	if (!tagger) {
	380	if (fake_missing_tagger)
	381	tagger = "tagger Unspecified Tagger "
	382	"<unspecified-tagger> 0 +0000";
	383	else
	384	tagger = "";
	385	tagger_end = tagger + strlen(tagger);
	386	} else {
	387	tagger++;
	388	tagger_end = strchrnul(tagger, '\n');
	389	}
f2dc849e JS	390
	391	/* handle signed tags */
	392	if (message) {
	393	const char *signature = strstr(message,
	394	"\n-----BEGIN PGP SIGNATURE-----\n");
	395	if (signature)
	396	switch(signed_tag_mode) {
	397	case ABORT:
	398	die ("Encountered signed tag %s; use "
	399	"--signed-tag=<mode> to handle it.",
	400	sha1_to_hex(tag->object.sha1));
	401	case WARN:
	402	warning ("Exporting signed tag %s",
	403	sha1_to_hex(tag->object.sha1));
	404	/* fallthru */
ee4bc371	405	case VERBATIM:
f2dc849e JS	406	break;
	407	case STRIP:
	408	message_size = signature + 1 - message;
	409	break;
	410	}
	411	}
	412
2d8ad469 EN	413	/* handle tag->tagged having been filtered out due to paths specified */
	414	tagged = tag->tagged;
	415	tagged_mark = get_object_mark(tagged);
	416	if (!tagged_mark) {
	417	switch(tag_of_filtered_mode) {
	418	case ABORT:
	419	die ("Tag %s tags unexported object; use "
	420	"--tag-of-filtered-object=<mode> to handle it.",
	421	sha1_to_hex(tag->object.sha1));
	422	case DROP:
	423	/* Ignore this tag altogether */
	424	return;
	425	case REWRITE:
	426	if (tagged->type != OBJ_COMMIT) {
	427	die ("Tag %s tags unexported %s!",
	428	sha1_to_hex(tag->object.sha1),
	429	typename(tagged->type));
	430	}
	431	p = (struct commit *)tagged;
	432	for (;;) {
	433	if (p->parents && p->parents->next)
	434	break;
	435	if (p->object.flags & UNINTERESTING)
	436	break;
	437	if (!(p->object.flags & TREESAME))
	438	break;
	439	if (!p->parents)
	440	die ("Can't find replacement commit for tag %s\n",
	441	sha1_to_hex(tag->object.sha1));
	442	p = p->parents->item;
	443	}
	444	tagged_mark = get_object_mark(&p->object);
	445	}
	446	}
	447
f2dc849e JS	448	if (!prefixcmp(name, "refs/tags/"))
f2dc849e JS	449	name += 10;
4e46a8d6	450	printf("tag %s\nfrom :%d\n%.s%sdata %d\n%.s\n",
2d8ad469	451	name, tagged_mark,
f2dc849e	452	(int)(tagger_end - tagger), tagger,
4e46a8d6	453	tagger == tagger_end ? "" : "\n",
f2dc849e JS	454	(int)message_size, (int)message_size, message ? message : "");
	455	}
	456
	457	static void get_tags_and_duplicates(struct object_array *pending,
c455c87c	458	struct string_list *extra_refs)
f2dc849e JS	459	{
	460	struct tag *tag;
	461	int i;
	462
	463	for (i = 0; i < pending->nr; i++) {
	464	struct object_array_entry *e = pending->objects + i;
	465	unsigned char sha1[20];
	466	struct commit *commit = commit;
	467	char *full_name;
	468
	469	if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
	470	continue;
	471
	472	switch (e->item->type) {
	473	case OBJ_COMMIT:
	474	commit = (struct commit *)e->item;
	475	break;
	476	case OBJ_TAG:
	477	tag = (struct tag *)e->item;
1982467d EFL	478
1982467d EFL	479	/* handle nested tags */
f2dc849e	480	while (tag && tag->object.type == OBJ_TAG) {
1982467d	481	parse_object(tag->object.sha1);
1d2f80fa	482	string_list_append(extra_refs, full_name)->util = tag;
f2dc849e JS	483	tag = (struct tag *)tag->tagged;
	484	}
	485	if (!tag)
	486	die ("Tag %s points nowhere?", e->name);
	487	switch(tag->object.type) {
	488	case OBJ_COMMIT:
	489	commit = (struct commit *)tag;
	490	break;
	491	case OBJ_BLOB:
	492	handle_object(tag->object.sha1);
	493	continue;
1982467d	494	default: /* OBJ_TAG (nested tags) is already handled */
c0582c53 EFL	495	warning("Tag points to object of unexpected type %s, skipping.",
	496	typename(tag->object.type));
	497	continue;
f2dc849e JS	498	}
	499	break;
	500	default:
2d07f6d4 EFL	501	warning("%s: Unexpected object of type %s, skipping.",
	502	e->name,
	503	typename(e->item->type));
	504	continue;
f2dc849e JS	505	}
	506	if (commit->util)
	507	/* more than one name for the same object */
1d2f80fa	508	string_list_append(extra_refs, full_name)->util = commit;
f2dc849e JS	509	else
	510	commit->util = full_name;
	511	}
	512	}
	513
c455c87c	514	static void handle_tags_and_duplicates(struct string_list *extra_refs)
f2dc849e JS	515	{
	516	struct commit *commit;
	517	int i;
	518
	519	for (i = extra_refs->nr - 1; i >= 0; i--) {
c455c87c	520	const char *name = extra_refs->items[i].string;
f2dc849e JS	521	struct object *object = extra_refs->items[i].util;
	522	switch (object->type) {
	523	case OBJ_TAG:
	524	handle_tag(name, (struct tag *)object);
	525	break;
	526	case OBJ_COMMIT:
	527	/* create refs pointing to already seen commits */
	528	commit = (struct commit *)object;
	529	printf("reset %s\nfrom :%d\n\n", name,
	530	get_object_mark(&commit->object));
	531	show_progress();
	532	break;
	533	}
	534	}
	535	}
	536
df6a7ff7 PB	537	static void export_marks(char *file)
	538	{
	539	unsigned int i;
	540	uint32_t mark;
	541	struct object_decoration *deco = idnums.hash;
	542	FILE *f;
96d69b55	543	int e = 0;
df6a7ff7 PB	544
	545	f = fopen(file, "w");
	546	if (!f)
bb6ad28c	547	die_errno("Unable to open marks file %s for writing.", file);
df6a7ff7	548
69913575 JH	549	for (i = 0; i < idnums.size; i++) {
69913575 JH	550	if (deco->base && deco->base->type == 1) {
df6a7ff7	551	mark = ptr_to_mark(deco->decoration);
96d69b55 MA	552	if (fprintf(f, ":%"PRIu32" %s\n", mark,
	553	sha1_to_hex(deco->base->sha1)) < 0) {
	554	e = 1;
	555	break;
	556	}
df6a7ff7	557	}
69913575	558	deco++;
df6a7ff7 PB	559	}
df6a7ff7 PB	560
96d69b55 MA	561	e \|= ferror(f);
	562	e \|= fclose(f);
	563	if (e)
df6a7ff7 PB	564	error("Unable to write marks file %s.", file);
	565	}
	566
69913575	567	static void import_marks(char *input_file)
df6a7ff7 PB	568	{
	569	char line[512];
	570	FILE *f = fopen(input_file, "r");
	571	if (!f)
d824cbba	572	die_errno("cannot read '%s'", input_file);
df6a7ff7 PB	573
	574	while (fgets(line, sizeof(line), f)) {
	575	uint32_t mark;
	576	char line_end, mark_end;
	577	unsigned char sha1[20];
	578	struct object *object;
	579
	580	line_end = strchr(line, '\n');
	581	if (line[0] != ':' \|\| !line_end)
	582	die("corrupt mark line: %s", line);
69913575	583	*line_end = '\0';
df6a7ff7 PB	584
	585	mark = strtoumax(line + 1, &mark_end, 10);
	586	if (!mark \|\| mark_end == line + 1
	587	\|\| *mark_end != ' ' \|\| get_sha1(mark_end + 1, sha1))
	588	die("corrupt mark line: %s", line);
	589
	590	object = parse_object(sha1);
	591	if (!object)
	592	die ("Could not read blob %s", sha1_to_hex(sha1));
	593
	594	if (object->flags & SHOWN)
	595	error("Object %s already has a mark", sha1);
	596
	597	mark_object(object, mark);
	598	if (last_idnum < mark)
	599	last_idnum = mark;
	600
	601	object->flags \|= SHOWN;
	602	}
	603	fclose(f);
	604	}
	605
f2dc849e JS	606	int cmd_fast_export(int argc, const char *argv, const char prefix)
	607	{
	608	struct rev_info revs;
3cd47459	609	struct object_array commits = OBJECT_ARRAY_INIT;
183113a5	610	struct string_list extra_refs = STRING_LIST_INIT_NODUP;
f2dc849e	611	struct commit *commit;
df6a7ff7	612	char export_filename = NULL, import_filename = NULL;
f2dc849e JS	613	struct option options[] = {
	614	OPT_INTEGER(0, "progress", &progress,
	615	"show progress after <n> objects"),
	616	OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
	617	"select handling of signed tags",
	618	parse_opt_signed_tag_mode),
2d8ad469 EN	619	OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, "mode",
	620	"select handling of tags that tag filtered objects",
	621	parse_opt_tag_of_filtered_mode),
df6a7ff7 PB	622	OPT_STRING(0, "export-marks", &export_filename, "FILE",
	623	"Dump marks to this file"),
	624	OPT_STRING(0, "import-marks", &import_filename, "FILE",
	625	"Import marks from this file"),
4e46a8d6 JS	626	OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
4e46a8d6 JS	627	"Fake a tagger when tags lack one"),
7f40ab09 EN	628	OPT_BOOLEAN(0, "full-tree", &full_tree,
7f40ab09 EN	629	"Output full tree for each commit"),
79559f27 GI	630	{ OPTION_NEGBIT, 0, "data", &no_data, NULL,
	631	"Skip output of blob data",
	632	PARSE_OPT_NOARG \| PARSE_OPT_NEGHELP, NULL, 1 },
f2dc849e JS	633	OPT_END()
	634	};
	635
dcfdbdf0 MV	636	if (argc == 1)
	637	usage_with_options (fast_export_usage, options);
	638
f2dc849e	639	/* we handle encodings */
ef90d6d4	640	git_config(git_default_config, NULL);
f2dc849e JS	641
f2dc849e JS	642	init_revisions(&revs, prefix);
668f3aa7	643	revs.topo_order = 1;
2374502c	644	revs.show_source = 1;
32164131	645	revs.rewrite_parents = 1;
f2dc849e	646	argc = setup_revisions(argc, argv, &revs, NULL);
37782920	647	argc = parse_options(argc, argv, prefix, options, fast_export_usage, 0);
f2dc849e JS	648	if (argc > 1)
	649	usage_with_options (fast_export_usage, options);
	650
df6a7ff7 PB	651	if (import_filename)
	652	import_marks(import_filename);
	653
4087a02e EN	654	if (import_filename && revs.prune_data)
	655	full_tree = 1;
	656
f2dc849e JS	657	get_tags_and_duplicates(&revs.pending, &extra_refs);
f2dc849e JS	658
3d51e1b5 MK	659	if (prepare_revision_walk(&revs))
3d51e1b5 MK	660	die("revision walk setup failed");
f2dc849e JS	661	revs.diffopt.format_callback = show_filemodify;
	662	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
	663	while ((commit = get_revision(&revs))) {
	664	if (has_unshown_parent(commit)) {
f2dc849e	665	add_object_array(&commit->object, NULL, &commits);
f2dc849e JS	666	}
	667	else {
	668	handle_commit(commit, &revs);
	669	handle_tail(&commits, &revs);
	670	}
	671	}
	672
	673	handle_tags_and_duplicates(&extra_refs);
	674
df6a7ff7 PB	675	if (export_filename)
	676	export_marks(export_filename);
	677
f2dc849e JS	678	return 0;
f2dc849e JS	679	}