[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 "path-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];

/* 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 = (buf[len-1] != '\n');

		if (fputs(buf, output) == EOF)
			die("cannot write output");

		if (fgets(buf, sizeof(buf), mbox) == NULL) {
			if (feof(mbox)) {
				status = 1;
				break;
			}
			die("cannot read mbox");
		}
		len = strlen(buf);
		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 path_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);
			path_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 path_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].path);
		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:
	path_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"
d63bd9a2	9	#include "path-list.h"
2744b234	10
8b73edf4	11	static const char git_mailsplit_usage[] =
d63bd9a2	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
	48	/* Called with the first line (potentially partial)
	49	* already in buf[] -- normally that should begin with
	50	* the Unix "From " line. Write it into the specified
	51	* file.
	52	*/
b3f041fb	53	static int split_one(FILE mbox, const char name, int allow_bare)
2744b234	54	{
8b73edf4 JH	55	FILE *output = NULL;
	56	int len = strlen(buf);
	57	int fd;
	58	int status = 0;
b3f041fb	59	int is_bare = !is_from_line(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);
	65	if (fd < 0)
	66	die("cannot open output file %s", name);
	67	output = fdopen(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 JH	72	for (;;) {
	73	int is_partial = (buf[len-1] != '\n');
	74
	75	if (fputs(buf, output) == EOF)
	76	die("cannot write output");
	77
	78	if (fgets(buf, sizeof(buf), mbox) == NULL) {
	79	if (feof(mbox)) {
	80	status = 1;
	81	break;
	82	}
	83	die("cannot read mbox");
	84	}
	85	len = strlen(buf);
b3f041fb	86	if (!is_partial && !is_bare && is_from_line(buf, len))
8b73edf4 JH	87	break; /* done with one message */
	88	}
	89	fclose(output);
	90	return status;
	91
	92	corrupt:
	93	if (output)
	94	fclose(output);
	95	unlink(name);
2744b234 LT	96	fprintf(stderr, "corrupt mailbox\n");
	97	exit(1);
	98	}
	99
d63bd9a2	100	static int populate_maildir_list(struct path_list list, const char path)
2744b234	101	{
d63bd9a2 FP	102	DIR *dir;
d63bd9a2 FP	103	struct dirent *dent;
d50a4bc4 GP	104	char name[PATH_MAX];
	105	char *subs[] = { "cur", "new", NULL };
	106	char **sub;
	107
	108	for (sub = subs; *sub; ++sub) {
	109	snprintf(name, sizeof(name), "%s/%s", path, *sub);
	110	if ((dir = opendir(name)) == NULL) {
	111	if (errno == ENOENT)
	112	continue;
	113	error("cannot opendir %s (%s)", name, strerror(errno));
	114	return -1;
	115	}
d63bd9a2	116
d50a4bc4 GP	117	while ((dent = readdir(dir)) != NULL) {
	118	if (dent->d_name[0] == '.')
	119	continue;
	120	snprintf(name, sizeof(name), "%s/%s", *sub, dent->d_name);
	121	path_list_insert(name, list);
	122	}
d63bd9a2	123
d50a4bc4	124	closedir(dir);
d63bd9a2 FP	125	}
d63bd9a2 FP	126
d63bd9a2 FP	127	return 0;
	128	}
	129
	130	static int split_maildir(const char maildir, const char dir,
	131	int nr_prec, int skip)
	132	{
	133	char file[PATH_MAX];
d63bd9a2	134	char name[PATH_MAX];
e690e843	135	int ret = -1;
d63bd9a2 FP	136	int i;
d63bd9a2 FP	137	struct path_list list = {NULL, 0, 0, 1};
e690e843	138
d50a4bc4	139	if (populate_maildir_list(&list, maildir) < 0)
d63bd9a2	140	goto out;
e690e843	141
d63bd9a2 FP	142	for (i = 0; i < list.nr; i++) {
d63bd9a2 FP	143	FILE *f;
d50a4bc4	144	snprintf(file, sizeof(file), "%s/%s", maildir, list.items[i].path);
d63bd9a2 FP	145	f = fopen(file, "r");
	146	if (!f) {
	147	error("cannot open mail %s (%s)", file, strerror(errno));
e690e843 LS	148	goto out;
	149	}
	150
	151	if (fgets(buf, sizeof(buf), f) == NULL) {
d63bd9a2	152	error("cannot read mail %s (%s)", file, strerror(errno));
e690e843 LS	153	goto out;
	154	}
	155
d63bd9a2 FP	156	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	157	split_one(f, name, 1);
	158
	159	fclose(f);
	160	}
	161
d63bd9a2 FP	162	ret = skip;
d63bd9a2 FP	163	out:
d50a4bc4	164	path_list_clear(&list, 1);
d63bd9a2 FP	165	return ret;
	166	}
	167
fcd056a6 JH	168	static int split_mbox(const char file, const char dir, int allow_bare,
fcd056a6 JH	169	int nr_prec, int skip)
d63bd9a2 FP	170	{
	171	char name[PATH_MAX];
	172	int ret = -1;
f88a545a	173	int peek;
d63bd9a2 FP	174
	175	FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "r");
	176	int file_done = 0;
	177
	178	if (!f) {
	179	error("cannot open mbox %s", file);
	180	goto out;
	181	}
	182
f88a545a SS	183	do {
	184	peek = fgetc(f);
	185	} while (isspace(peek));
	186	ungetc(peek, f);
	187
d63bd9a2 FP	188	if (fgets(buf, sizeof(buf), f) == NULL) {
	189	/* empty stdin is OK */
	190	if (f != stdin) {
	191	error("cannot read mbox %s", file);
	192	goto out;
e690e843	193	}
d63bd9a2 FP	194	file_done = 1;
d63bd9a2 FP	195	}
e690e843	196
d63bd9a2 FP	197	while (!file_done) {
	198	sprintf(name, "%s/%0*d", dir, nr_prec, ++skip);
	199	file_done = split_one(f, name, allow_bare);
e690e843	200	}
d63bd9a2 FP	201
	202	if (f != stdin)
	203	fclose(f);
	204
e690e843 LS	205	ret = skip;
e690e843 LS	206	out:
e690e843 LS	207	return ret;
e690e843 LS	208	}
d63bd9a2	209
a633fca0	210	int cmd_mailsplit(int argc, const char *argv, const char prefix)
e690e843	211	{
d63bd9a2	212	int nr = 0, nr_prec = 4, num = 0;
b3f041fb PA	213	int allow_bare = 0;
	214	const char *dir = NULL;
	215	const char **argp;
	216	static const char *stdin_only[] = { "-", NULL };
8b73edf4	217
b3f041fb PA	218	for (argp = argv+1; *argp; argp++) {
b3f041fb PA	219	const char arg = argp;
8b73edf4 JH	220
	221	if (arg[0] != '-')
	222	break;
	223	/* do flags here */
b3f041fb PA	224	if ( arg[1] == 'd' ) {
b3f041fb PA	225	nr_prec = strtol(arg+2, NULL, 10);
8b73edf4 JH	226	if (nr_prec < 3 \|\| 10 <= nr_prec)
	227	usage(git_mailsplit_usage);
	228	continue;
b3f041fb PA	229	} else if ( arg[1] == 'f' ) {
	230	nr = strtol(arg+2, NULL, 10);
	231	} else if ( arg[1] == 'b' && !arg[2] ) {
	232	allow_bare = 1;
	233	} else if ( arg[1] == 'o' && arg[2] ) {
	234	dir = arg+2;
	235	} else if ( arg[1] == '-' && !arg[2] ) {
	236	argp++; /* -- marks end of options */
	237	break;
	238	} else {
	239	die("unknown option: %s", arg);
8b73edf4	240	}
2744b234	241	}
8b73edf4	242
b3f041fb PA	243	if ( !dir ) {
	244	/* Backwards compatibility: if no -o specified, accept
	245	<mbox> <dir> or just <dir> */
	246	switch (argc - (argp-argv)) {
	247	case 1:
	248	dir = argp[0];
	249	argp = stdin_only;
	250	break;
	251	case 2:
	252	stdin_only[0] = argp[0];
	253	dir = argp[1];
	254	argp = stdin_only;
	255	break;
	256	default:
	257	usage(git_mailsplit_usage);
	258	}
	259	} else {
	260	/* New usage: if no more argument, parse stdin */
	261	if ( !*argp )
	262	argp = stdin_only;
2744b234	263	}
8b73edf4	264
d63bd9a2 FP	265	while (*argp) {
	266	const char arg = argp++;
	267	struct stat argstat;
	268	int ret = 0;
	269
	270	if (arg[0] == '-' && arg[1] == 0) {
	271	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	272	if (ret < 0) {
	273	error("cannot split patches from stdin");
	274	return 1;
	275	}
b3327180 JH	276	num += (ret - nr);
b3327180 JH	277	nr = ret;
d63bd9a2 FP	278	continue;
	279	}
	280
	281	if (stat(arg, &argstat) == -1) {
	282	error("cannot stat %s (%s)", arg, strerror(errno));
	283	return 1;
	284	}
	285
	286	if (S_ISDIR(argstat.st_mode))
	287	ret = split_maildir(arg, dir, nr_prec, nr);
	288	else
	289	ret = split_mbox(arg, dir, allow_bare, nr_prec, nr);
	290
	291	if (ret < 0) {
	292	error("cannot split patches from %s", arg);
	293	return 1;
	294	}
b3327180 JH	295	num += (ret - nr);
b3327180 JH	296	nr = ret;
d63bd9a2 FP	297	}
	298
	299	printf("%d\n", num);
b3f041fb	300
d63bd9a2	301	return 0;
2744b234	302	}