undef/git-commit-vandalism
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

mailsplit: allow feeding mbox from standard input.

Browse Source 
When mbox argument is missing, read the mailbox from the standard
input.

Signed-off-by: Junio C Hamano <junkio@cox.net>
This commit is contained in:
Junio C Hamano 2005-10-06 15:55:43 -07:00
parent 54ba6013b4
commit 8b73edf498
2 changed files with 95 additions and 85 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Documentation/git-mailsplit.txt
View File

@ -7,7 +7,7 @@ git-mailsplit - Totally braindamaged mbox splitter program.
SYNOPSIS SYNOPSIS
-------- --------
'git-mailsplit' [-d<prec>] <mbox> <directory> 'git-mailsplit' [-d<prec>] [<mbox>] <directory>
DESCRIPTION DESCRIPTION
----------- -----------
@ -17,7 +17,8 @@ directory so you can process them further from there.
OPTIONS OPTIONS
------- -------
<mbox>:: <mbox>::
Mbox file to split. Mbox file to split. If not given, the mbox is read from
the standard input.
<directory>:: <directory>::
Directory in which to place the individual messages. Directory in which to place the individual messages.
@ -31,6 +32,8 @@ OPTIONS
Author Author
------ ------
Written by Linus Torvalds <torvalds@osdl.org> Written by Linus Torvalds <torvalds@osdl.org>
and Junio C Hamano <junkio@cox.net>
Documentation Documentation
-------------- --------------

173
mailsplit.c
View File

@ -14,25 +14,10 @@
#include <stdio.h> #include <stdio.h>
#include <ctype.h> #include <ctype.h>
#include <assert.h> #include <assert.h>
#include "cache.h"
static int usage(void) static const char git_mailsplit_usage[] =
{ "git-mailsplit [-d<prec>] [<mbox>] <directory>";
fprintf(stderr, "git-mailsplit [-d<prec>] <mbox> <directory>\n");
exit(1);
}
static int linelen(const char *map, unsigned long size)
{
int len = 0, c;
do {
c = *map;
map++;
size--;
len++;
} while (size && c != '\n');
return len;
}
static int is_from_line(const char *line, int len) static int is_from_line(const char *line, int len)
{ {
@ -65,88 +50,110 @@ static int is_from_line(const char *line, int len)
return 1; return 1;
} }
static int parse_email(const void *map, unsigned long size) /* Could be as small as 64, enough to hold a Unix "From " line. */
{ static char buf[4096];
unsigned long offset;
if (size < 6 || memcmp("From ", map, 5)) /* 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)
{
FILE *output = NULL;
int len = strlen(buf);
int fd;
int status = 0;
if (!is_from_line(buf, len))
goto corrupt; goto corrupt;
/* Make sure we don't trigger on this first line */ fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0666);
map++; size--; offset=1; 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
* Search for a line beginning with "From ", and * "From " and having something that looks like a date format.
* having something that looks like a date format.
*/ */
do { for (;;) {
int len = linelen(map, size); int is_partial = (buf[len-1] != '\n');
if (is_from_line(map, len))
return offset;
map += len;
size -= len;
offset += len;
} while (size);
return offset;
corrupt: 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_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"); fprintf(stderr, "corrupt mailbox\n");
exit(1); exit(1);
} }
int main(int argc, char **argv) int main(int argc, const char **argv)
{ {
int fd, nr, nr_prec = 4; int i, nr, nr_prec = 4;
struct stat st; FILE *mbox = NULL;
unsigned long size;
void *map;
if (argc == 4 && !strncmp(argv[1], "-d", 2)) { for (i = 1; i < argc; i++) {
nr_prec = strtol(argv[1] + 2, NULL, 10); const char *arg = argv[i];
if (nr_prec < 3 || 10 <= nr_prec)
usage(); if (arg[0] != '-')
argc--; argv++; break;
/* do flags here */
if (!strncmp(arg, "-d", 2)) {
nr_prec = strtol(arg + 2, NULL, 10);
if (nr_prec < 3 || 10 <= nr_prec)
usage(git_mailsplit_usage);
continue;
}
} }
if (argc != 3)
usage(); /* Either one remaining arg (dir), or two (mbox and dir) */
fd = open(argv[1], O_RDONLY); switch (argc - i) {
if (fd < 0) { case 1:
perror(argv[1]); mbox = stdin;
exit(1); break;
case 2:
if ((mbox = fopen(argv[i], "r")) == NULL)
die("cannot open mbox %s for reading", argv[i]);
break;
default:
usage(git_mailsplit_usage);
} }
if (chdir(argv[2]) < 0) if (chdir(argv[argc - 1]) < 0)
usage(); usage(git_mailsplit_usage);
if (fstat(fd, &st) < 0) {
perror("stat");
exit(1);
}
size = st.st_size;
map = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
if (map == MAP_FAILED) {
perror("mmap");
close(fd);
exit(1);
}
close(fd);
nr = 0; nr = 0;
do { if (fgets(buf, sizeof(buf), mbox) == NULL)
die("cannot read mbox");
for (;;) {
char name[10]; char name[10];
unsigned long len = parse_email(map, size);
assert(len <= size);
sprintf(name, "%0*d", nr_prec, ++nr); sprintf(name, "%0*d", nr_prec, ++nr);
fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0666); switch (split_one(mbox, name)) {
if (fd < 0) { case 0:
perror(name); break;
case 1:
printf("%d\n", nr);
return 0;
default:
exit(1); exit(1);
} }
if (write(fd, map, len) != len) { }
perror("write");
exit(1);
}
close(fd);
map += len;
size -= len;
} while (size > 0);
printf("%d\n", nr);
return 0;
} }