2005-04-12 10:46:50 +04:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2005-10-07 02:55:43 +04:00
|
|
|
#include "cache.h"
|
2006-06-14 00:21:46 +04:00
|
|
|
#include "builtin.h"
|
2008-07-21 22:03:49 +04:00
|
|
|
#include "string-list.h"
|
2009-08-05 07:31:57 +04:00
|
|
|
#include "strbuf.h"
|
2005-04-12 10:46:50 +04:00
|
|
|
|
2005-10-07 02:55:43 +04:00
|
|
|
static const char git_mailsplit_usage[] =
|
2010-10-08 21:31:17 +04:00
|
|
|
"git mailsplit [-d<prec>] [-f<n>] [-b] [--keep-cr] -o<directory> [(<mbox>|<Maildir>)...]";
|
2005-04-12 10:46:50 +04:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2009-08-05 07:31:57 +04:00
|
|
|
static struct strbuf buf = STRBUF_INIT;
|
2009-08-05 07:31:59 +04:00
|
|
|
static int keep_cr;
|
2016-06-05 07:46:40 +03:00
|
|
|
static int mboxrd;
|
|
|
|
|
|
|
|
static int is_gtfrom(const struct strbuf *buf)
|
|
|
|
{
|
|
|
|
size_t min = strlen(">From ");
|
|
|
|
size_t ngt;
|
|
|
|
|
|
|
|
if (buf->len < min)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ngt = strspn(buf->buf, ">");
|
|
|
|
return ngt && starts_with(buf->buf + ngt, "From ");
|
|
|
|
}
|
2005-10-07 02:55:43 +04:00
|
|
|
|
|
|
|
/* 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.
|
|
|
|
*/
|
2005-12-14 09:39:23 +03:00
|
|
|
static int split_one(FILE *mbox, const char *name, int allow_bare)
|
2005-04-12 10:46:50 +04:00
|
|
|
{
|
2014-08-13 01:21:27 +04:00
|
|
|
FILE *output;
|
2005-10-07 02:55:43 +04:00
|
|
|
int fd;
|
|
|
|
int status = 0;
|
2009-08-05 07:31:57 +04:00
|
|
|
int is_bare = !is_from_line(buf.buf, buf.len);
|
2005-04-12 10:46:50 +04:00
|
|
|
|
2014-08-13 01:21:27 +04:00
|
|
|
if (is_bare && !allow_bare) {
|
|
|
|
fprintf(stderr, "corrupt mailbox\n");
|
|
|
|
exit(1);
|
|
|
|
}
|
2005-10-07 02:55:43 +04:00
|
|
|
fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0666);
|
|
|
|
if (fd < 0)
|
2009-06-27 19:58:47 +04:00
|
|
|
die_errno("cannot open output file '%s'", name);
|
2009-09-12 12:43:27 +04:00
|
|
|
output = xfdopen(fd, "w");
|
2005-04-12 10:46:50 +04:00
|
|
|
|
2005-10-07 02:55:43 +04:00
|
|
|
/* Copy it out, while searching for a line that begins with
|
|
|
|
* "From " and having something that looks like a date format.
|
2005-04-12 10:46:50 +04:00
|
|
|
*/
|
2005-10-07 02:55:43 +04:00
|
|
|
for (;;) {
|
2009-08-05 07:31:59 +04:00
|
|
|
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');
|
|
|
|
}
|
|
|
|
|
2016-06-05 07:46:40 +03:00
|
|
|
if (mboxrd && is_gtfrom(&buf))
|
|
|
|
strbuf_remove(&buf, 0, 1);
|
|
|
|
|
2009-08-05 07:31:57 +04:00
|
|
|
if (fwrite(buf.buf, 1, buf.len, output) != buf.len)
|
2009-06-27 19:58:47 +04:00
|
|
|
die_errno("cannot write output");
|
2005-10-07 02:55:43 +04:00
|
|
|
|
2009-08-05 07:31:57 +04:00
|
|
|
if (strbuf_getwholeline(&buf, mbox, '\n')) {
|
2005-10-07 02:55:43 +04:00
|
|
|
if (feof(mbox)) {
|
|
|
|
status = 1;
|
|
|
|
break;
|
|
|
|
}
|
2009-06-27 19:58:47 +04:00
|
|
|
die_errno("cannot read mbox");
|
2005-10-07 02:55:43 +04:00
|
|
|
}
|
2009-08-05 07:31:57 +04:00
|
|
|
if (!is_bare && is_from_line(buf.buf, buf.len))
|
2005-10-07 02:55:43 +04:00
|
|
|
break; /* done with one message */
|
|
|
|
}
|
|
|
|
fclose(output);
|
|
|
|
return status;
|
2005-04-12 10:46:50 +04:00
|
|
|
}
|
|
|
|
|
2008-07-21 22:03:49 +04:00
|
|
|
static int populate_maildir_list(struct string_list *list, const char *path)
|
2005-04-12 10:46:50 +04:00
|
|
|
{
|
2007-05-25 02:15:36 +04:00
|
|
|
DIR *dir;
|
|
|
|
struct dirent *dent;
|
2015-09-25 00:05:51 +03:00
|
|
|
char *name = NULL;
|
2007-11-06 11:54:18 +03:00
|
|
|
char *subs[] = { "cur", "new", NULL };
|
|
|
|
char **sub;
|
2015-09-25 00:05:51 +03:00
|
|
|
int ret = -1;
|
2007-11-06 11:54:18 +03:00
|
|
|
|
|
|
|
for (sub = subs; *sub; ++sub) {
|
2015-09-25 00:05:51 +03:00
|
|
|
free(name);
|
|
|
|
name = xstrfmt("%s/%s", path, *sub);
|
2007-11-06 11:54:18 +03:00
|
|
|
if ((dir = opendir(name)) == NULL) {
|
|
|
|
if (errno == ENOENT)
|
|
|
|
continue;
|
2016-05-08 12:47:28 +03:00
|
|
|
error_errno("cannot opendir %s", name);
|
2015-09-25 00:05:51 +03:00
|
|
|
goto out;
|
2007-11-06 11:54:18 +03:00
|
|
|
}
|
2007-05-25 02:15:36 +04:00
|
|
|
|
2007-11-06 11:54:18 +03:00
|
|
|
while ((dent = readdir(dir)) != NULL) {
|
|
|
|
if (dent->d_name[0] == '.')
|
|
|
|
continue;
|
2015-09-25 00:05:51 +03:00
|
|
|
free(name);
|
|
|
|
name = xstrfmt("%s/%s", *sub, dent->d_name);
|
2010-06-26 03:41:35 +04:00
|
|
|
string_list_insert(list, name);
|
2007-11-06 11:54:18 +03:00
|
|
|
}
|
2007-05-25 02:15:36 +04:00
|
|
|
|
2007-11-06 11:54:18 +03:00
|
|
|
closedir(dir);
|
2007-05-25 02:15:36 +04:00
|
|
|
}
|
|
|
|
|
2015-09-25 00:05:51 +03:00
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
free(name);
|
|
|
|
return ret;
|
2007-05-25 02:15:36 +04:00
|
|
|
}
|
|
|
|
|
mailsplit: sort maildir filenames more cleverly
A maildir does not technically record the order in which
items were placed into it. That means that when applying a
patch series from a maildir, we may get the patches in the
wrong order. We try to work around this by sorting the
filenames. Unfortunately, this may or may not work depending
on the naming scheme used by the writer of the maildir.
For instance, mutt will write:
${epoch_seconds}.${pid}_${seq}.${host}
where we have:
- epoch_seconds: timestamp at which entry was written
- pid: PID of writing process
- seq: a sequence number to ensure uniqueness of filenames
- host: hostname
None of the numbers are zero-padded. Therefore, when we sort
the names as byte strings, entries that cross a digit
boundary (e.g., 10) will sort out of order. In the case of
timestamps, it almost never matters (because we do not cross
a digit boundary in the epoch time very often these days).
But for the sequence number, a 10-patch series would be
ordered as 1, 10, 2, 3, etc.
To fix this, we can use a custom sort comparison function
which traverses each string, comparing chunks of digits
numerically, and otherwise doing a byte-for-byte comparison.
That would sort:
123.456_1.bar
123.456_2.bar
...
123.456_10.bar
according to the sequence number. Since maildir does not
define a filename format, this is really just a heuristic.
But it happens to work for mutt, and there is a reasonable
chance that it will work for other writers, too (at least as
well as a straight sort).
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-02 03:35:48 +04:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
static int split_maildir(const char *maildir, const char *dir,
|
|
|
|
int nr_prec, int skip)
|
|
|
|
{
|
2015-09-25 00:05:51 +03:00
|
|
|
char *file = NULL;
|
2015-09-25 00:03:05 +03:00
|
|
|
FILE *f = NULL;
|
2006-06-14 00:21:46 +04:00
|
|
|
int ret = -1;
|
2007-05-25 02:15:36 +04:00
|
|
|
int i;
|
2010-07-04 23:46:19 +04:00
|
|
|
struct string_list list = STRING_LIST_INIT_DUP;
|
2006-06-14 00:21:46 +04:00
|
|
|
|
mailsplit: sort maildir filenames more cleverly
A maildir does not technically record the order in which
items were placed into it. That means that when applying a
patch series from a maildir, we may get the patches in the
wrong order. We try to work around this by sorting the
filenames. Unfortunately, this may or may not work depending
on the naming scheme used by the writer of the maildir.
For instance, mutt will write:
${epoch_seconds}.${pid}_${seq}.${host}
where we have:
- epoch_seconds: timestamp at which entry was written
- pid: PID of writing process
- seq: a sequence number to ensure uniqueness of filenames
- host: hostname
None of the numbers are zero-padded. Therefore, when we sort
the names as byte strings, entries that cross a digit
boundary (e.g., 10) will sort out of order. In the case of
timestamps, it almost never matters (because we do not cross
a digit boundary in the epoch time very often these days).
But for the sequence number, a 10-patch series would be
ordered as 1, 10, 2, 3, etc.
To fix this, we can use a custom sort comparison function
which traverses each string, comparing chunks of digits
numerically, and otherwise doing a byte-for-byte comparison.
That would sort:
123.456_1.bar
123.456_2.bar
...
123.456_10.bar
according to the sequence number. Since maildir does not
define a filename format, this is really just a heuristic.
But it happens to work for mutt, and there is a reasonable
chance that it will work for other writers, too (at least as
well as a straight sort).
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-02 03:35:48 +04:00
|
|
|
list.cmp = maildir_filename_cmp;
|
|
|
|
|
2007-11-06 11:54:18 +03:00
|
|
|
if (populate_maildir_list(&list, maildir) < 0)
|
2007-05-25 02:15:36 +04:00
|
|
|
goto out;
|
2006-06-14 00:21:46 +04:00
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
for (i = 0; i < list.nr; i++) {
|
2015-09-25 00:05:51 +03:00
|
|
|
char *name;
|
|
|
|
|
|
|
|
free(file);
|
|
|
|
file = xstrfmt("%s/%s", maildir, list.items[i].string);
|
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
f = fopen(file, "r");
|
|
|
|
if (!f) {
|
2016-05-08 12:47:28 +03:00
|
|
|
error_errno("cannot open mail %s", file);
|
2006-06-14 00:21:46 +04:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2009-08-05 07:31:57 +04:00
|
|
|
if (strbuf_getwholeline(&buf, f, '\n')) {
|
2016-05-08 12:47:28 +03:00
|
|
|
error_errno("cannot read mail %s", file);
|
2006-06-14 00:21:46 +04:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2015-09-25 00:05:51 +03:00
|
|
|
name = xstrfmt("%s/%0*d", dir, nr_prec, ++skip);
|
2007-05-25 02:15:36 +04:00
|
|
|
split_one(f, name, 1);
|
2015-09-25 00:05:51 +03:00
|
|
|
free(name);
|
2007-05-25 02:15:36 +04:00
|
|
|
|
|
|
|
fclose(f);
|
2015-09-25 00:03:05 +03:00
|
|
|
f = NULL;
|
2007-05-25 02:15:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
ret = skip;
|
|
|
|
out:
|
2015-09-25 00:03:05 +03:00
|
|
|
if (f)
|
|
|
|
fclose(f);
|
2015-09-25 00:05:51 +03:00
|
|
|
free(file);
|
2008-07-21 22:03:49 +04:00
|
|
|
string_list_clear(&list, 1);
|
2007-05-25 02:15:36 +04:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-06-08 13:22:56 +04:00
|
|
|
static int split_mbox(const char *file, const char *dir, int allow_bare,
|
|
|
|
int nr_prec, int skip)
|
2007-05-25 02:15:36 +04:00
|
|
|
{
|
|
|
|
int ret = -1;
|
2007-11-02 01:57:45 +03:00
|
|
|
int peek;
|
2007-05-25 02:15:36 +04:00
|
|
|
|
|
|
|
FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "r");
|
|
|
|
int file_done = 0;
|
|
|
|
|
|
|
|
if (!f) {
|
2016-05-08 12:47:28 +03:00
|
|
|
error_errno("cannot open mbox %s", file);
|
2007-05-25 02:15:36 +04:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2007-11-02 01:57:45 +03:00
|
|
|
do {
|
|
|
|
peek = fgetc(f);
|
|
|
|
} while (isspace(peek));
|
|
|
|
ungetc(peek, f);
|
|
|
|
|
2009-08-05 07:31:57 +04:00
|
|
|
if (strbuf_getwholeline(&buf, f, '\n')) {
|
2007-05-25 02:15:36 +04:00
|
|
|
/* empty stdin is OK */
|
|
|
|
if (f != stdin) {
|
|
|
|
error("cannot read mbox %s", file);
|
|
|
|
goto out;
|
2006-06-14 00:21:46 +04:00
|
|
|
}
|
2007-05-25 02:15:36 +04:00
|
|
|
file_done = 1;
|
|
|
|
}
|
2006-06-14 00:21:46 +04:00
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
while (!file_done) {
|
2015-09-25 00:05:51 +03:00
|
|
|
char *name = xstrfmt("%s/%0*d", dir, nr_prec, ++skip);
|
2007-05-25 02:15:36 +04:00
|
|
|
file_done = split_one(f, name, allow_bare);
|
2015-09-25 00:05:51 +03:00
|
|
|
free(name);
|
2006-06-14 00:21:46 +04:00
|
|
|
}
|
2007-05-25 02:15:36 +04:00
|
|
|
|
|
|
|
if (f != stdin)
|
|
|
|
fclose(f);
|
|
|
|
|
2006-06-14 00:21:46 +04:00
|
|
|
ret = skip;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
2007-05-25 02:15:36 +04:00
|
|
|
|
2006-07-29 09:44:25 +04:00
|
|
|
int cmd_mailsplit(int argc, const char **argv, const char *prefix)
|
2006-06-14 00:21:46 +04:00
|
|
|
{
|
2007-05-25 02:15:36 +04:00
|
|
|
int nr = 0, nr_prec = 4, num = 0;
|
2005-12-14 09:39:23 +03:00
|
|
|
int allow_bare = 0;
|
|
|
|
const char *dir = NULL;
|
|
|
|
const char **argp;
|
|
|
|
static const char *stdin_only[] = { "-", NULL };
|
2005-10-07 02:55:43 +04:00
|
|
|
|
2005-12-14 09:39:23 +03:00
|
|
|
for (argp = argv+1; *argp; argp++) {
|
|
|
|
const char *arg = *argp;
|
2005-10-07 02:55:43 +04:00
|
|
|
|
|
|
|
if (arg[0] != '-')
|
|
|
|
break;
|
|
|
|
/* do flags here */
|
2005-12-14 09:39:23 +03:00
|
|
|
if ( arg[1] == 'd' ) {
|
|
|
|
nr_prec = strtol(arg+2, NULL, 10);
|
2005-10-07 02:55:43 +04:00
|
|
|
if (nr_prec < 3 || 10 <= nr_prec)
|
|
|
|
usage(git_mailsplit_usage);
|
|
|
|
continue;
|
2005-12-14 09:39:23 +03:00
|
|
|
} else if ( arg[1] == 'f' ) {
|
|
|
|
nr = strtol(arg+2, NULL, 10);
|
2009-11-09 18:04:52 +03:00
|
|
|
} else if ( arg[1] == 'h' ) {
|
|
|
|
usage(git_mailsplit_usage);
|
2005-12-14 09:39:23 +03:00
|
|
|
} else if ( arg[1] == 'b' && !arg[2] ) {
|
|
|
|
allow_bare = 1;
|
2009-08-05 07:31:59 +04:00
|
|
|
} else if (!strcmp(arg, "--keep-cr")) {
|
|
|
|
keep_cr = 1;
|
2005-12-14 09:39:23 +03:00
|
|
|
} else if ( arg[1] == 'o' && arg[2] ) {
|
|
|
|
dir = arg+2;
|
2016-06-05 07:46:40 +03:00
|
|
|
} else if (!strcmp(arg, "--mboxrd")) {
|
|
|
|
mboxrd = 1;
|
2005-12-14 09:39:23 +03:00
|
|
|
} else if ( arg[1] == '-' && !arg[2] ) {
|
|
|
|
argp++; /* -- marks end of options */
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
die("unknown option: %s", arg);
|
2005-10-07 02:55:43 +04:00
|
|
|
}
|
2005-04-12 10:46:50 +04:00
|
|
|
}
|
2005-10-07 02:55:43 +04:00
|
|
|
|
2005-12-14 09:39:23 +03:00
|
|
|
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;
|
2005-04-12 10:46:50 +04:00
|
|
|
}
|
2005-10-07 02:55:43 +04:00
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
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;
|
|
|
|
}
|
2007-05-29 02:48:07 +04:00
|
|
|
num += (ret - nr);
|
|
|
|
nr = ret;
|
2007-05-25 02:15:36 +04:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (stat(arg, &argstat) == -1) {
|
2016-05-08 12:47:28 +03:00
|
|
|
error_errno("cannot stat %s", arg);
|
2007-05-25 02:15:36 +04:00
|
|
|
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;
|
|
|
|
}
|
2007-05-29 02:48:07 +04:00
|
|
|
num += (ret - nr);
|
|
|
|
nr = ret;
|
2007-05-25 02:15:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
printf("%d\n", num);
|
2005-12-14 09:39:23 +03:00
|
|
|
|
2007-05-25 02:15:36 +04:00
|
|
|
return 0;
|
2005-04-12 10:46:50 +04:00
|
|
|
}
|