[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"

static const char git_mailsplit_usage[] =
"git mailsplit [-d<prec>] [-f<n>] [-b] -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;
}

/* Could be as small as 64, enough to hold a Unix "From " line. */
static char buf[4096];

/* We cannot use fgets() because our lines can contain NULs */
int read_line_with_nul(char *buf, int size, FILE *in)
{
	int len = 0, c;

	for (;;) {
		c = getc(in);
		if (c == EOF)
			break;
		buf[len++] = c;
		if (c == '\n' || len + 1 >= size)
			break;
	}
	buf[len] = '\0';

	return len;
}

/* 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 len = strlen(buf);
	int fd;
	int status = 0;
	int is_bare = !is_from_line(buf, len);

	if (is_bare && !allow_bare)
		goto corrupt;

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

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

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

		len = read_line_with_nul(buf, sizeof(buf), mbox);
		if (len == 0) {
			if (feof(mbox)) {
				status = 1;
				break;
			}
			die("cannot read mbox");
		}
		if (!is_partial && !is_bare && is_from_line(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(name, list);
		}

		closedir(dir);
	}

	return 0;
}

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 = {NULL, 0, 0, 1};

	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 (fgets(buf, sizeof(buf), f) == NULL) {
			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 (fgets(buf, sizeof(buf), f) == NULL) {
		/* 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] == 'b' && !arg[2] ) {
			allow_bare = 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"
2744b234	10
8b73edf4	11	static const char git_mailsplit_usage[] =
588c038a	12	"git mailsplit [-d<prec>] [-f<n>] [-b] -o<directory> [<mbox>\|<Maildir>...]";
2744b234 LT	13
	14	static int is_from_line(const char *line, int len)
	15	{
	16	const char *colon;
	17
	18	if (len < 20 \|\| memcmp("From ", line, 5))
	19	return 0;
	20
	21	colon = line + len - 2;
	22	line += 5;
	23	for (;;) {
	24	if (colon < line)
	25	return 0;
	26	if (*--colon == ':')
	27	break;
	28	}
	29
	30	if (!isdigit(colon[-4]) \|\|
	31	!isdigit(colon[-2]) \|\|
	32	!isdigit(colon[-1]) \|\|
	33	!isdigit(colon[ 1]) \|\|
	34	!isdigit(colon[ 2]))
	35	return 0;
	36
	37	/* year */
	38	if (strtol(colon+3, NULL, 10) <= 90)
	39	return 0;
	40
	41	/* Ok, close enough */
	42	return 1;
	43	}
	44
8b73edf4 JH	45	/* Could be as small as 64, enough to hold a Unix "From " line. */
	46	static char buf[4096];
	47
cce8d6fd JS	48	/* We cannot use fgets() because our lines can contain NULs */
	49	int read_line_with_nul(char buf, int size, FILE in)
	50	{
	51	int len = 0, c;
	52
	53	for (;;) {
	54	c = getc(in);
edc55941 JH	55	if (c == EOF)
edc55941 JH	56	break;
cce8d6fd	57	buf[len++] = c;
edc55941	58	if (c == '\n' \|\| len + 1 >= size)
cce8d6fd JS	59	break;
cce8d6fd JS	60	}
cce8d6fd JS	61	buf[len] = '\0';
	62
	63	return len;
	64	}
	65
8b73edf4 JH	66	/* Called with the first line (potentially partial)
	67	* already in buf[] -- normally that should begin with
	68	* the Unix "From " line. Write it into the specified
	69	* file.
	70	*/
b3f041fb	71	static int split_one(FILE mbox, const char name, int allow_bare)
2744b234	72	{
8b73edf4 JH	73	FILE *output = NULL;
	74	int len = strlen(buf);
	75	int fd;
	76	int status = 0;
b3f041fb	77	int is_bare = !is_from_line(buf, len);
2744b234	78
b3f041fb	79	if (is_bare && !allow_bare)
2744b234 LT	80	goto corrupt;
2744b234 LT	81
8b73edf4 JH	82	fd = open(name, O_WRONLY \| O_CREAT \| O_EXCL, 0666);
	83	if (fd < 0)
	84	die("cannot open output file %s", name);
	85	output = fdopen(fd, "w");
2744b234	86
8b73edf4 JH	87	/* Copy it out, while searching for a line that begins with
8b73edf4 JH	88	* "From " and having something that looks like a date format.
2744b234	89	*/
8b73edf4	90	for (;;) {
cce8d6fd	91	int is_partial = len && buf[len-1] != '\n';
8b73edf4	92
cce8d6fd	93	if (fwrite(buf, 1, len, output) != len)
8b73edf4 JH	94	die("cannot write output");
8b73edf4 JH	95
cce8d6fd JS	96	len = read_line_with_nul(buf, sizeof(buf), mbox);
cce8d6fd JS	97	if (len == 0) {
8b73edf4 JH	98	if (feof(mbox)) {
	99	status = 1;
	100	break;
	101	}
	102	die("cannot read mbox");
	103	}
b3f041fb	104	if (!is_partial && !is_bare && is_from_line(buf, len))
8b73edf4 JH	105	break; /* done with one message */
	106	}
	107	fclose(output);
	108	return status;
	109
	110	corrupt:
	111	if (output)
	112	fclose(output);
	113	unlink(name);
2744b234 LT	114	fprintf(stderr, "corrupt mailbox\n");
	115	exit(1);
	116	}
	117
c455c87c	118	static int populate_maildir_list(struct string_list list, const char path)
2744b234	119	{
d63bd9a2 FP	120	DIR *dir;
d63bd9a2 FP	121	struct dirent *dent;
d50a4bc4 GP	122	char name[PATH_MAX];
	123	char *subs[] = { "cur", "new", NULL };
	124	char **sub;
	125
	126	for (sub = subs; *sub; ++sub) {
	127	snprintf(name, sizeof(name), "%s/%s", path, *sub);
	128	if ((dir = opendir(name)) == NULL) {
	129	if (errno == ENOENT)
	130	continue;
	131	error("cannot opendir %s (%s)", name, strerror(errno));
	132	return -1;
	133	}
d63bd9a2	134
d50a4bc4 GP	135	while ((dent = readdir(dir)) != NULL) {
	136	if (dent->d_name[0] == '.')
	137	continue;
	138	snprintf(name, sizeof(name), "%s/%s", *sub, dent->d_name);
c455c87c	139	string_list_insert(name, list);
d50a4bc4	140	}
d63bd9a2	141
d50a4bc4	142	closedir(dir);
d63bd9a2 FP	143	}
d63bd9a2 FP	144
d63bd9a2 FP	145	return 0;
	146	}
	147
	148	static int split_maildir(const char maildir, const char dir,
	149	int nr_prec, int skip)
	150	{
	151	char file[PATH_MAX];
d63bd9a2	152	char name[PATH_MAX];
e690e843	153	int ret = -1;
d63bd9a2	154	int i;
c455c87c	155	struct string_list list = {NULL, 0, 0, 1};
e690e843	156
d50a4bc4	157	if (populate_maildir_list(&list, maildir) < 0)
d63bd9a2	158	goto out;
e690e843	159
d63bd9a2 FP	160	for (i = 0; i < list.nr; i++) {
d63bd9a2 FP	161	FILE *f;
c455c87c	162	snprintf(file, sizeof(file), "%s/%s", maildir, list.items[i].string);
d63bd9a2 FP	163	f = fopen(file, "r");
	164	if (!f) {
	165	error("cannot open mail %s (%s)", file, strerror(errno));
e690e843 LS	166	goto out;
	167	}
	168
	169	if (fgets(buf, sizeof(buf), f) == NULL) {
d63bd9a2	170	error("cannot read mail %s (%s)", file, strerror(errno));
e690e843 LS	171	goto out;
	172	}
	173
d63bd9a2 FP	174	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	175	split_one(f, name, 1);
	176
	177	fclose(f);
	178	}
	179
d63bd9a2 FP	180	ret = skip;
d63bd9a2 FP	181	out:
c455c87c	182	string_list_clear(&list, 1);
d63bd9a2 FP	183	return ret;
	184	}
	185
fcd056a6 JH	186	static int split_mbox(const char file, const char dir, int allow_bare,
fcd056a6 JH	187	int nr_prec, int skip)
d63bd9a2 FP	188	{
	189	char name[PATH_MAX];
	190	int ret = -1;
f88a545a	191	int peek;
d63bd9a2 FP	192
	193	FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "r");
	194	int file_done = 0;
	195
	196	if (!f) {
	197	error("cannot open mbox %s", file);
	198	goto out;
	199	}
	200
f88a545a SS	201	do {
	202	peek = fgetc(f);
	203	} while (isspace(peek));
	204	ungetc(peek, f);
	205
d63bd9a2 FP	206	if (fgets(buf, sizeof(buf), f) == NULL) {
	207	/* empty stdin is OK */
	208	if (f != stdin) {
	209	error("cannot read mbox %s", file);
	210	goto out;
e690e843	211	}
d63bd9a2 FP	212	file_done = 1;
d63bd9a2 FP	213	}
e690e843	214
d63bd9a2 FP	215	while (!file_done) {
	216	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	217	file_done = split_one(f, name, allow_bare);
e690e843	218	}
d63bd9a2 FP	219
	220	if (f != stdin)
	221	fclose(f);
	222
e690e843 LS	223	ret = skip;
e690e843 LS	224	out:
e690e843 LS	225	return ret;
e690e843 LS	226	}
d63bd9a2	227
a633fca0	228	int cmd_mailsplit(int argc, const char *argv, const char prefix)
e690e843	229	{
d63bd9a2	230	int nr = 0, nr_prec = 4, num = 0;
b3f041fb PA	231	int allow_bare = 0;
	232	const char *dir = NULL;
	233	const char **argp;
	234	static const char *stdin_only[] = { "-", NULL };
8b73edf4	235
b3f041fb PA	236	for (argp = argv+1; *argp; argp++) {
b3f041fb PA	237	const char arg = argp;
8b73edf4 JH	238
	239	if (arg[0] != '-')
	240	break;
	241	/* do flags here */
b3f041fb PA	242	if ( arg[1] == 'd' ) {
b3f041fb PA	243	nr_prec = strtol(arg+2, NULL, 10);
8b73edf4 JH	244	if (nr_prec < 3 \|\| 10 <= nr_prec)
	245	usage(git_mailsplit_usage);
	246	continue;
b3f041fb PA	247	} else if ( arg[1] == 'f' ) {
	248	nr = strtol(arg+2, NULL, 10);
	249	} else if ( arg[1] == 'b' && !arg[2] ) {
	250	allow_bare = 1;
	251	} else if ( arg[1] == 'o' && arg[2] ) {
	252	dir = arg+2;
	253	} else if ( arg[1] == '-' && !arg[2] ) {
	254	argp++; /* -- marks end of options */
	255	break;
	256	} else {
	257	die("unknown option: %s", arg);
8b73edf4	258	}
2744b234	259	}
8b73edf4	260
b3f041fb PA	261	if ( !dir ) {
	262	/* Backwards compatibility: if no -o specified, accept
	263	<mbox> <dir> or just <dir> */
	264	switch (argc - (argp-argv)) {
	265	case 1:
	266	dir = argp[0];
	267	argp = stdin_only;
	268	break;
	269	case 2:
	270	stdin_only[0] = argp[0];
	271	dir = argp[1];
	272	argp = stdin_only;
	273	break;
	274	default:
	275	usage(git_mailsplit_usage);
	276	}
	277	} else {
	278	/* New usage: if no more argument, parse stdin */
	279	if ( !*argp )
	280	argp = stdin_only;
2744b234	281	}
8b73edf4	282
d63bd9a2 FP	283	while (*argp) {
	284	const char arg = argp++;
	285	struct stat argstat;
	286	int ret = 0;
	287
	288	if (arg[0] == '-' && arg[1] == 0) {
	289	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	290	if (ret < 0) {
	291	error("cannot split patches from stdin");
	292	return 1;
	293	}
b3327180 JH	294	num += (ret - nr);
b3327180 JH	295	nr = ret;
d63bd9a2 FP	296	continue;
	297	}
	298
	299	if (stat(arg, &argstat) == -1) {
	300	error("cannot stat %s (%s)", arg, strerror(errno));
	301	return 1;
	302	}
	303
	304	if (S_ISDIR(argstat.st_mode))
	305	ret = split_maildir(arg, dir, nr_prec, nr);
	306	else
	307	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	308
	309	if (ret < 0) {
	310	error("cannot split patches from %s", arg);
	311	return 1;
	312	}
b3327180 JH	313	num += (ret - nr);
b3327180 JH	314	nr = ret;
d63bd9a2 FP	315	}
	316
	317	printf("%d\n", num);
b3f041fb	318
d63bd9a2	319	return 0;
2744b234	320	}