[thirdparty/git.git] / builtin / mailsplit.c

/*
 * Totally braindamaged mbox splitter program.
 *
 * It just splits a mbox into a list of files: "0001" "0002" ..
 * so you can process them further from there.
 */
#include "cache.h"
#include "builtin.h"
#include "string-list.h"
#include "strbuf.h"

static const char git_mailsplit_usage[] =
"git mailsplit [-d<prec>] [-f<n>] [-b] [--keep-cr] -o<directory> [(<mbox>|<Maildir>)...]";

static int is_from_line(const char *line, int len)
{
	const char *colon;

	if (len < 20 || memcmp("From ", line, 5))
		return 0;

	colon = line + len - 2;
	line += 5;
	for (;;) {
		if (colon < line)
			return 0;
		if (*--colon == ':')
			break;
	}

	if (!isdigit(colon[-4]) ||
	    !isdigit(colon[-2]) ||
	    !isdigit(colon[-1]) ||
	    !isdigit(colon[ 1]) ||
	    !isdigit(colon[ 2]))
		return 0;

	/* year */
	if (strtol(colon+3, NULL, 10) <= 90)
		return 0;

	/* Ok, close enough */
	return 1;
}

static struct strbuf buf = STRBUF_INIT;
static int keep_cr;

/* Called with the first line (potentially partial)
 * already in buf[] -- normally that should begin with
 * the Unix "From " line.  Write it into the specified
 * file.
 */
static int split_one(FILE *mbox, const char *name, int allow_bare)
{
	FILE *output = NULL;
	int fd;
	int status = 0;
	int is_bare = !is_from_line(buf.buf, buf.len);

	if (is_bare && !allow_bare)
		goto corrupt;

	fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0666);
	if (fd < 0)
		die_errno("cannot open output file '%s'", name);
	output = xfdopen(fd, "w");

	/* Copy it out, while searching for a line that begins with
	 * "From " and having something that looks like a date format.
	 */
	for (;;) {
		if (!keep_cr && buf.len > 1 && buf.buf[buf.len-1] == '\n' &&
			buf.buf[buf.len-2] == '\r') {
			strbuf_setlen(&buf, buf.len-2);
			strbuf_addch(&buf, '\n');
		}

		if (fwrite(buf.buf, 1, buf.len, output) != buf.len)
			die_errno("cannot write output");

		if (strbuf_getwholeline(&buf, mbox, '\n')) {
			if (feof(mbox)) {
				status = 1;
				break;
			}
			die_errno("cannot read mbox");
		}
		if (!is_bare && is_from_line(buf.buf, buf.len))
			break; /* done with one message */
	}
	fclose(output);
	return status;

 corrupt:
	if (output)
		fclose(output);
	unlink(name);
	fprintf(stderr, "corrupt mailbox\n");
	exit(1);
}

static int populate_maildir_list(struct string_list *list, const char *path)
{
	DIR *dir;
	struct dirent *dent;
	char name[PATH_MAX];
	char *subs[] = { "cur", "new", NULL };
	char **sub;

	for (sub = subs; *sub; ++sub) {
		snprintf(name, sizeof(name), "%s/%s", path, *sub);
		if ((dir = opendir(name)) == NULL) {
			if (errno == ENOENT)
				continue;
			error("cannot opendir %s (%s)", name, strerror(errno));
			return -1;
		}

		while ((dent = readdir(dir)) != NULL) {
			if (dent->d_name[0] == '.')
				continue;
			snprintf(name, sizeof(name), "%s/%s", *sub, dent->d_name);
			string_list_insert(list, name);
		}

		closedir(dir);
	}

	return 0;
}

static int maildir_filename_cmp(const char *a, const char *b)
{
	while (*a && *b) {
		if (isdigit(*a) && isdigit(*b)) {
			long int na, nb;
			na = strtol(a, (char **)&a, 10);
			nb = strtol(b, (char **)&b, 10);
			if (na != nb)
				return na - nb;
			/* strtol advanced our pointers */
		}
		else {
			if (*a != *b)
				return (unsigned char)*a - (unsigned char)*b;
			a++;
			b++;
		}
	}
	return (unsigned char)*a - (unsigned char)*b;
}

static int split_maildir(const char *maildir, const char *dir,
	int nr_prec, int skip)
{
	char file[PATH_MAX];
	char name[PATH_MAX];
	int ret = -1;
	int i;
	struct string_list list = STRING_LIST_INIT_DUP;

	list.cmp = maildir_filename_cmp;

	if (populate_maildir_list(&list, maildir) < 0)
		goto out;

	for (i = 0; i < list.nr; i++) {
		FILE *f;
		snprintf(file, sizeof(file), "%s/%s", maildir, list.items[i].string);
		f = fopen(file, "r");
		if (!f) {
			error("cannot open mail %s (%s)", file, strerror(errno));
			goto out;
		}

		if (strbuf_getwholeline(&buf, f, '\n')) {
			error("cannot read mail %s (%s)", file, strerror(errno));
			goto out;
		}

		sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
		split_one(f, name, 1);

		fclose(f);
	}

	ret = skip;
out:
	string_list_clear(&list, 1);
	return ret;
}

static int split_mbox(const char *file, const char *dir, int allow_bare,
		      int nr_prec, int skip)
{
	char name[PATH_MAX];
	int ret = -1;
	int peek;

	FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "r");
	int file_done = 0;

	if (!f) {
		error("cannot open mbox %s", file);
		goto out;
	}

	do {
		peek = fgetc(f);
	} while (isspace(peek));
	ungetc(peek, f);

	if (strbuf_getwholeline(&buf, f, '\n')) {
		/* empty stdin is OK */
		if (f != stdin) {
			error("cannot read mbox %s", file);
			goto out;
		}
		file_done = 1;
	}

	while (!file_done) {
		sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
		file_done = split_one(f, name, allow_bare);
	}

	if (f != stdin)
		fclose(f);

	ret = skip;
out:
	return ret;
}

int cmd_mailsplit(int argc, const char **argv, const char *prefix)
{
	int nr = 0, nr_prec = 4, num = 0;
	int allow_bare = 0;
	const char *dir = NULL;
	const char **argp;
	static const char *stdin_only[] = { "-", NULL };

	for (argp = argv+1; *argp; argp++) {
		const char *arg = *argp;

		if (arg[0] != '-')
			break;
		/* do flags here */
		if ( arg[1] == 'd' ) {
			nr_prec = strtol(arg+2, NULL, 10);
			if (nr_prec < 3 || 10 <= nr_prec)
				usage(git_mailsplit_usage);
			continue;
		} else if ( arg[1] == 'f' ) {
			nr = strtol(arg+2, NULL, 10);
		} else if ( arg[1] == 'h' ) {
			usage(git_mailsplit_usage);
		} else if ( arg[1] == 'b' && !arg[2] ) {
			allow_bare = 1;
		} else if (!strcmp(arg, "--keep-cr")) {
			keep_cr = 1;
		} else if ( arg[1] == 'o' && arg[2] ) {
			dir = arg+2;
		} else if ( arg[1] == '-' && !arg[2] ) {
			argp++;	/* -- marks end of options */
			break;
		} else {
			die("unknown option: %s", arg);
		}
	}

	if ( !dir ) {
		/* Backwards compatibility: if no -o specified, accept
		   <mbox> <dir> or just <dir> */
		switch (argc - (argp-argv)) {
		case 1:
			dir = argp[0];
			argp = stdin_only;
			break;
		case 2:
			stdin_only[0] = argp[0];
			dir = argp[1];
			argp = stdin_only;
			break;
		default:
			usage(git_mailsplit_usage);
		}
	} else {
		/* New usage: if no more argument, parse stdin */
		if ( !*argp )
			argp = stdin_only;
	}

	while (*argp) {
		const char *arg = *argp++;
		struct stat argstat;
		int ret = 0;

		if (arg[0] == '-' && arg[1] == 0) {
			ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
			if (ret < 0) {
				error("cannot split patches from stdin");
				return 1;
			}
			num += (ret - nr);
			nr = ret;
			continue;
		}

		if (stat(arg, &argstat) == -1) {
			error("cannot stat %s (%s)", arg, strerror(errno));
			return 1;
		}

		if (S_ISDIR(argstat.st_mode))
			ret = split_maildir(arg, dir, nr_prec, nr);
		else
			ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);

		if (ret < 0) {
			error("cannot split patches from %s", arg);
			return 1;
		}
		num += (ret - nr);
		nr = ret;
	}

	printf("%d\n", num);

	return 0;
}
Commit	Line	Data
2744b234 LT	1	/*
	2	* Totally braindamaged mbox splitter program.
	3	*
	4	* It just splits a mbox into a list of files: "0001" "0002" ..
	5	* so you can process them further from there.
	6	*/
8b73edf4	7	#include "cache.h"
e690e843	8	#include "builtin.h"
c455c87c	9	#include "string-list.h"
c8f373a5	10	#include "strbuf.h"
2744b234	11
8b73edf4	12	static const char git_mailsplit_usage[] =
0adda936	13	"git mailsplit [-d<prec>] [-f<n>] [-b] [--keep-cr] -o<directory> [(<mbox>\|<Maildir>)...]";
2744b234 LT	14
	15	static int is_from_line(const char *line, int len)
	16	{
	17	const char *colon;
	18
	19	if (len < 20 \|\| memcmp("From ", line, 5))
	20	return 0;
	21
	22	colon = line + len - 2;
	23	line += 5;
	24	for (;;) {
	25	if (colon < line)
	26	return 0;
	27	if (*--colon == ':')
	28	break;
	29	}
	30
	31	if (!isdigit(colon[-4]) \|\|
	32	!isdigit(colon[-2]) \|\|
	33	!isdigit(colon[-1]) \|\|
	34	!isdigit(colon[ 1]) \|\|
	35	!isdigit(colon[ 2]))
	36	return 0;
	37
	38	/* year */
	39	if (strtol(colon+3, NULL, 10) <= 90)
	40	return 0;
	41
	42	/* Ok, close enough */
	43	return 1;
	44	}
	45
c8f373a5	46	static struct strbuf buf = STRBUF_INIT;
c2ca1d79	47	static int keep_cr;
8b73edf4 JH	48
	49	/* Called with the first line (potentially partial)
	50	* already in buf[] -- normally that should begin with
	51	* the Unix "From " line. Write it into the specified
	52	* file.
	53	*/
b3f041fb	54	static int split_one(FILE mbox, const char name, int allow_bare)
2744b234	55	{
8b73edf4	56	FILE *output = NULL;
8b73edf4 JH	57	int fd;
8b73edf4 JH	58	int status = 0;
c8f373a5	59	int is_bare = !is_from_line(buf.buf, buf.len);
2744b234	60
b3f041fb	61	if (is_bare && !allow_bare)
2744b234 LT	62	goto corrupt;
2744b234 LT	63
8b73edf4 JH	64	fd = open(name, O_WRONLY \| O_CREAT \| O_EXCL, 0666);
8b73edf4 JH	65	if (fd < 0)
0721c314	66	die_errno("cannot open output file '%s'", name);
41698375	67	output = xfdopen(fd, "w");
2744b234	68
8b73edf4 JH	69	/* Copy it out, while searching for a line that begins with
8b73edf4 JH	70	* "From " and having something that looks like a date format.
2744b234	71	*/
8b73edf4	72	for (;;) {
c2ca1d79 JH	73	if (!keep_cr && buf.len > 1 && buf.buf[buf.len-1] == '\n' &&
	74	buf.buf[buf.len-2] == '\r') {
	75	strbuf_setlen(&buf, buf.len-2);
	76	strbuf_addch(&buf, '\n');
	77	}
	78
c8f373a5	79	if (fwrite(buf.buf, 1, buf.len, output) != buf.len)
0721c314	80	die_errno("cannot write output");
8b73edf4	81
c8f373a5	82	if (strbuf_getwholeline(&buf, mbox, '\n')) {
8b73edf4 JH	83	if (feof(mbox)) {
	84	status = 1;
	85	break;
	86	}
0721c314	87	die_errno("cannot read mbox");
8b73edf4	88	}
c8f373a5	89	if (!is_bare && is_from_line(buf.buf, buf.len))
8b73edf4 JH	90	break; /* done with one message */
	91	}
	92	fclose(output);
	93	return status;
	94
	95	corrupt:
	96	if (output)
	97	fclose(output);
	98	unlink(name);
2744b234 LT	99	fprintf(stderr, "corrupt mailbox\n");
	100	exit(1);
	101	}
	102
c455c87c	103	static int populate_maildir_list(struct string_list list, const char path)
2744b234	104	{
d63bd9a2 FP	105	DIR *dir;
d63bd9a2 FP	106	struct dirent *dent;
d50a4bc4 GP	107	char name[PATH_MAX];
	108	char *subs[] = { "cur", "new", NULL };
	109	char **sub;
	110
	111	for (sub = subs; *sub; ++sub) {
	112	snprintf(name, sizeof(name), "%s/%s", path, *sub);
	113	if ((dir = opendir(name)) == NULL) {
	114	if (errno == ENOENT)
	115	continue;
	116	error("cannot opendir %s (%s)", name, strerror(errno));
	117	return -1;
	118	}
d63bd9a2	119
d50a4bc4 GP	120	while ((dent = readdir(dir)) != NULL) {
	121	if (dent->d_name[0] == '.')
	122	continue;
	123	snprintf(name, sizeof(name), "%s/%s", *sub, dent->d_name);
78a395d3	124	string_list_insert(list, name);
d50a4bc4	125	}
d63bd9a2	126
d50a4bc4	127	closedir(dir);
d63bd9a2 FP	128	}
d63bd9a2 FP	129
d63bd9a2 FP	130	return 0;
	131	}
	132
18505c34 JK	133	static int maildir_filename_cmp(const char a, const char b)
	134	{
	135	while (a && b) {
	136	if (isdigit(a) && isdigit(b)) {
	137	long int na, nb;
	138	na = strtol(a, (char **)&a, 10);
	139	nb = strtol(b, (char **)&b, 10);
	140	if (na != nb)
	141	return na - nb;
	142	/* strtol advanced our pointers */
	143	}
	144	else {
	145	if (a != b)
	146	return (unsigned char)a - (unsigned char)b;
	147	a++;
	148	b++;
	149	}
	150	}
	151	return (unsigned char)a - (unsigned char)b;
	152	}
	153
d63bd9a2 FP	154	static int split_maildir(const char maildir, const char dir,
	155	int nr_prec, int skip)
	156	{
	157	char file[PATH_MAX];
d63bd9a2	158	char name[PATH_MAX];
e690e843	159	int ret = -1;
d63bd9a2	160	int i;
183113a5	161	struct string_list list = STRING_LIST_INIT_DUP;
e690e843	162
18505c34 JK	163	list.cmp = maildir_filename_cmp;
18505c34 JK	164
d50a4bc4	165	if (populate_maildir_list(&list, maildir) < 0)
d63bd9a2	166	goto out;
e690e843	167
d63bd9a2 FP	168	for (i = 0; i < list.nr; i++) {
d63bd9a2 FP	169	FILE *f;
c455c87c	170	snprintf(file, sizeof(file), "%s/%s", maildir, list.items[i].string);
d63bd9a2 FP	171	f = fopen(file, "r");
	172	if (!f) {
	173	error("cannot open mail %s (%s)", file, strerror(errno));
e690e843 LS	174	goto out;
	175	}
	176
c8f373a5	177	if (strbuf_getwholeline(&buf, f, '\n')) {
d63bd9a2	178	error("cannot read mail %s (%s)", file, strerror(errno));
e690e843 LS	179	goto out;
	180	}
	181
d63bd9a2 FP	182	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	183	split_one(f, name, 1);
	184
	185	fclose(f);
	186	}
	187
d63bd9a2 FP	188	ret = skip;
d63bd9a2 FP	189	out:
c455c87c	190	string_list_clear(&list, 1);
d63bd9a2 FP	191	return ret;
	192	}
	193
fcd056a6 JH	194	static int split_mbox(const char file, const char dir, int allow_bare,
fcd056a6 JH	195	int nr_prec, int skip)
d63bd9a2 FP	196	{
	197	char name[PATH_MAX];
	198	int ret = -1;
f88a545a	199	int peek;
d63bd9a2 FP	200
	201	FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "r");
	202	int file_done = 0;
	203
	204	if (!f) {
	205	error("cannot open mbox %s", file);
	206	goto out;
	207	}
	208
f88a545a SS	209	do {
	210	peek = fgetc(f);
	211	} while (isspace(peek));
	212	ungetc(peek, f);
	213
c8f373a5	214	if (strbuf_getwholeline(&buf, f, '\n')) {
d63bd9a2 FP	215	/* empty stdin is OK */
	216	if (f != stdin) {
	217	error("cannot read mbox %s", file);
	218	goto out;
e690e843	219	}
d63bd9a2 FP	220	file_done = 1;
d63bd9a2 FP	221	}
e690e843	222
d63bd9a2 FP	223	while (!file_done) {
	224	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	225	file_done = split_one(f, name, allow_bare);
e690e843	226	}
d63bd9a2 FP	227
	228	if (f != stdin)
	229	fclose(f);
	230
e690e843 LS	231	ret = skip;
e690e843 LS	232	out:
e690e843 LS	233	return ret;
e690e843 LS	234	}
d63bd9a2	235
a633fca0	236	int cmd_mailsplit(int argc, const char *argv, const char prefix)
e690e843	237	{
d63bd9a2	238	int nr = 0, nr_prec = 4, num = 0;
b3f041fb PA	239	int allow_bare = 0;
	240	const char *dir = NULL;
	241	const char **argp;
	242	static const char *stdin_only[] = { "-", NULL };
8b73edf4	243
b3f041fb PA	244	for (argp = argv+1; *argp; argp++) {
b3f041fb PA	245	const char arg = argp;
8b73edf4 JH	246
	247	if (arg[0] != '-')
	248	break;
	249	/* do flags here */
b3f041fb PA	250	if ( arg[1] == 'd' ) {
b3f041fb PA	251	nr_prec = strtol(arg+2, NULL, 10);
8b73edf4 JH	252	if (nr_prec < 3 \|\| 10 <= nr_prec)
	253	usage(git_mailsplit_usage);
	254	continue;
b3f041fb PA	255	} else if ( arg[1] == 'f' ) {
b3f041fb PA	256	nr = strtol(arg+2, NULL, 10);
aa481d38 JN	257	} else if ( arg[1] == 'h' ) {
aa481d38 JN	258	usage(git_mailsplit_usage);
b3f041fb PA	259	} else if ( arg[1] == 'b' && !arg[2] ) {
b3f041fb PA	260	allow_bare = 1;
c2ca1d79 JH	261	} else if (!strcmp(arg, "--keep-cr")) {
c2ca1d79 JH	262	keep_cr = 1;
b3f041fb PA	263	} else if ( arg[1] == 'o' && arg[2] ) {
	264	dir = arg+2;
	265	} else if ( arg[1] == '-' && !arg[2] ) {
	266	argp++; /* -- marks end of options */
	267	break;
	268	} else {
	269	die("unknown option: %s", arg);
8b73edf4	270	}
2744b234	271	}
8b73edf4	272
b3f041fb PA	273	if ( !dir ) {
	274	/* Backwards compatibility: if no -o specified, accept
	275	<mbox> <dir> or just <dir> */
	276	switch (argc - (argp-argv)) {
	277	case 1:
	278	dir = argp[0];
	279	argp = stdin_only;
	280	break;
	281	case 2:
	282	stdin_only[0] = argp[0];
	283	dir = argp[1];
	284	argp = stdin_only;
	285	break;
	286	default:
	287	usage(git_mailsplit_usage);
	288	}
	289	} else {
	290	/* New usage: if no more argument, parse stdin */
	291	if ( !*argp )
	292	argp = stdin_only;
2744b234	293	}
8b73edf4	294
d63bd9a2 FP	295	while (*argp) {
	296	const char arg = argp++;
	297	struct stat argstat;
	298	int ret = 0;
	299
	300	if (arg[0] == '-' && arg[1] == 0) {
	301	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	302	if (ret < 0) {
	303	error("cannot split patches from stdin");
	304	return 1;
	305	}
b3327180 JH	306	num += (ret - nr);
b3327180 JH	307	nr = ret;
d63bd9a2 FP	308	continue;
	309	}
	310
	311	if (stat(arg, &argstat) == -1) {
	312	error("cannot stat %s (%s)", arg, strerror(errno));
	313	return 1;
	314	}
	315
	316	if (S_ISDIR(argstat.st_mode))
	317	ret = split_maildir(arg, dir, nr_prec, nr);
	318	else
	319	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	320
	321	if (ret < 0) {
	322	error("cannot split patches from %s", arg);
	323	return 1;
	324	}
b3327180 JH	325	num += (ret - nr);
b3327180 JH	326	nr = ret;
d63bd9a2 FP	327	}
	328
	329	printf("%d\n", num);
b3f041fb	330
d63bd9a2	331	return 0;
2744b234	332	}