git-am support for naked email messages (take 2)

This allows git-am to accept single-message files as well as mboxes.
Unlike the previous version, this one doesn't need to be explicitly told
which one it is; rather, it looks to see if the first line is a From
line and uses it to select mbox mode or not.

I moved the logic to do all this into git-mailsplit, which got a new
user interface as result, although the old interface is still available
for backwards compatibility.

[jc: applied with two obvious fixes.]

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/Documentation/git-mailsplit.txt b/Documentation/git-mailsplit.txt
index 03a9477664310c2dc5ee9bddc0b34a99b8ab6687..e0703e9dfab49070d5a9bbee5e630db81c620727 100644 (file)
--- a/Documentation/git-mailsplit.txt
+++ b/Documentation/git-mailsplit.txt
@@ -7,7 +7,7 @@ git-mailsplit - Totally braindamaged mbox splitter program.
 
 SYNOPSIS
 --------
-'git-mailsplit' [-d<prec>] [<mbox>] <directory>
+'git-mailsplit' [-b] [-f<nn>] [-d<prec>] -o<directory> [--] [<mbox>...]
 
 DESCRIPTION
 -----------
@@ -23,11 +23,18 @@ OPTIONS
 <directory>::
        Directory in which to place the individual messages.
 
+-b::
+       If any file doesn't begin with a From line, assume it is a
+       single mail message instead of signalling error.
+
 -d<prec>::
        Instead of the default 4 digits with leading zeros,
        different precision can be specified for the generated
        filenames.
 
+-f<nn>::
+       Skip the first <nn> numbers, for example if -f3 is specified,
+       start the numbering with 0004.
 
 Author
 ------

diff --git a/git-am.sh b/git-am.sh
index 6ed527c7a9c2d0bb9bbf84b2176b86ffc0670c93..f143b7e782ce3b7cc7043c2d00e6cdcc10741bfe 100755 (executable)
--- a/git-am.sh
+++ b/git-am.sh
@@ -164,10 +164,7 @@ else
        # Start afresh.
        mkdir -p "$dotest" || exit
 
-       # cat does the right thing for us, including '-' to mean
-       # standard input.
-       cat "$@" |
-       git-mailsplit -d$prec "$dotest/" >"$dotest/last" || {
+       git-mailsplit -d"$prec" -o"$dotest" -b -- "$@" > "$dotest/last" ||  {
                rm -fr "$dotest"
                exit 1
        }

diff --git a/mailsplit.c b/mailsplit.c
index 189f4ed724cba345eeb80cd41a9b7ae67068a037..eb58b1ebe430a1a1acf189097c5277545e3b67e9 100644 (file)
--- a/mailsplit.c
+++ b/mailsplit.c
@@ -15,7 +15,7 @@
 #include "cache.h"
 
 static const char git_mailsplit_usage[] =
-"git-mailsplit [-d<prec>] [<mbox>] <directory>";
+"git-mailsplit [-d<prec>] [-f<n>] [-b] -o<directory> <mbox>...";
 
 static int is_from_line(const char *line, int len)
 {
@@ -56,14 +56,15 @@ static char buf[4096];
  * the Unix "From " line.  Write it into the specified
  * file.
  */
-static int split_one(FILE *mbox, const char *name)
+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_from_line(buf, len))
+       if (is_bare && !allow_bare)
                goto corrupt;
 
        fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0666);
@@ -88,7 +89,7 @@ static int split_one(FILE *mbox, const char *name)
                        die("cannot read mbox");
                }
                len = strlen(buf);
-               if (!is_partial && is_from_line(buf, len))
+               if (!is_partial && !is_bare && is_from_line(buf, len))
                        break; /* done with one message */
        }
        fclose(output);
@@ -104,54 +105,82 @@ static int split_one(FILE *mbox, const char *name)
 
 int main(int argc, const char **argv)
 {
-       int i, nr, nr_prec = 4;
-       FILE *mbox = NULL;
+       int nr = 0, nr_prec = 4;
+       int allow_bare = 0;
+       const char *dir = NULL;
+       const char **argp;
+       static const char *stdin_only[] = { "-", NULL };
+       char *name;
 
-       for (i = 1; i < argc; i++) {
-               const char *arg = argv[i];
+       for (argp = argv+1; *argp; argp++) {
+               const char *arg = *argp;
 
                if (arg[0] != '-')
                        break;
                /* do flags here */
-               if (!strncmp(arg, "-d", 2)) {
-                       nr_prec = strtol(arg + 2, NULL, 10);
+               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);
                }
        }
 
-       /* Either one remaining arg (dir), or two (mbox and dir) */
-       switch (argc - i) {
-       case 1:
-               mbox = stdin;
-               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 ( !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;
        }
-       if (chdir(argv[argc - 1]) < 0)
-               usage(git_mailsplit_usage);
 
-       nr = 0;
-       if (fgets(buf, sizeof(buf), mbox) == NULL)
-               die("cannot read mbox");
+       name = xmalloc(strlen(dir) + 2 + 3 * sizeof(nr));
 
-       for (;;) {
-               char name[10];
+       while (*argp) {
+               const char *file = *argp++;
+               FILE *f = !strcmp(file, "-") ? stdin : fopen(file, "rt");
+               int file_done = 0;
 
-               sprintf(name, "%0*d", nr_prec, ++nr);
-               switch (split_one(mbox, name)) {
-               case 0:
-                       break;
-               case 1:
-                       printf("%d\n", nr);
-                       return 0;
-               default:
-                       exit(1);
+               if ( !f )
+                       die ("cannot open mbox %s", file);
+
+               if (fgets(buf, sizeof(buf), f) == NULL)
+                       die("cannot read mbox %s", file);
+
+               while (!file_done) {
+                       sprintf(name, "%s/%0*d", dir, nr_prec, ++nr);
+                       file_done = split_one(f, name, allow_bare);
                }
+
+               if (f != stdin)
+                       fclose(f);
        }
+
+       printf("%d\n", nr);
+       return 0;
 }