pretty: support "mboxrd" output format

This output format prevents format-patch output from breaking
readers if somebody copy+pasted an mbox into a commit message.

Unlike the traditional "mboxo" format, "mboxrd" is designed to
be fully-reversible.  "mboxrd" also gracefully degrades to
showing extra ">" in existing "mboxo" readers.

This degradation is preferable to breaking message splitting
completely, a problem I've seen in "mboxcl" due to having
multiple, non-existent, or inaccurate Content-Length headers.

"mboxcl2" is a non-starter since it's inherits the problems
of "mboxcl" while being completely incompatible with existing
tooling based around mailsplit.

ref: http://homepage.ntlworld.com/jonathan.deboynepollard/FGA/mail-mbox-formats.html

Signed-off-by: Eric Wong <e@80x24.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 25 insertions, 8 deletions

diff --git a/pretty.c b/pretty.c
index 87c44971a..6abd8a121 100644
--- a/pretty.c
+++ b/pretty.c
@@ -92,6 +92,7 @@ static void setup_commit_formats(void)
 		{ "medium",	CMIT_FMT_MEDIUM,	0,	8 },
 		{ "short",	CMIT_FMT_SHORT,		0,	0 },
 		{ "email",	CMIT_FMT_EMAIL,		0,	0 },
+		{ "mboxrd",	CMIT_FMT_MBOXRD,	0,	0 },
 		{ "fuller",	CMIT_FMT_FULLER,	0,	8 },
 		{ "full",	CMIT_FMT_FULL,		0,	8 },
 		{ "oneline",	CMIT_FMT_ONELINE,	1,	0 }
@@ -444,7 +445,7 @@ void pp_user_info(struct pretty_print_context *pp,
 	if (pp->mailmap)
 		map_user(pp->mailmap, &mailbuf, &maillen, &namebuf, &namelen);
 
-	if (pp->fmt == CMIT_FMT_EMAIL) {
+	if (cmit_fmt_is_mail(pp->fmt)) {
 		if (pp->from_ident && ident_cmp(pp->from_ident, &ident)) {
 			struct strbuf buf = STRBUF_INIT;
 
@@ -494,6 +495,7 @@ void pp_user_info(struct pretty_print_context *pp,
 			    show_ident_date(&ident, &pp->date_mode));
 		break;
 	case CMIT_FMT_EMAIL:
+	case CMIT_FMT_MBOXRD:
 		strbuf_addf(sb, "Date: %s\n",
 			    show_ident_date(&ident, DATE_MODE(RFC2822)));
 		break;
@@ -535,7 +537,7 @@ static void add_merge_info(const struct pretty_print_context *pp,
 {
 	struct commit_list *parent = commit->parents;
 
-	if ((pp->fmt == CMIT_FMT_ONELINE) || (pp->fmt == CMIT_FMT_EMAIL) ||
+	if ((pp->fmt == CMIT_FMT_ONELINE) || (cmit_fmt_is_mail(pp->fmt)) ||
 	    !parent || !parent->next)
 		return;
 
@@ -1614,7 +1616,7 @@ void pp_title_line(struct pretty_print_context *pp,
 	if (pp->after_subject) {
 		strbuf_addstr(sb, pp->after_subject);
 	}
-	if (pp->fmt == CMIT_FMT_EMAIL) {
+	if (cmit_fmt_is_mail(pp->fmt)) {
 		strbuf_addch(sb, '\n');
 	}
 
@@ -1697,6 +1699,16 @@ static void pp_handle_indent(struct pretty_print_context *pp,
 		strbuf_add(sb, line, linelen);
 }
 
+static int is_mboxrd_from(const char *line, int len)
+{
+	/*
+	 * a line matching /^From $/ here would only have len == 4
+	 * at this point because is_empty_line would've trimmed all
+	 * trailing space
+	 */
+	return len > 4 && starts_with(line + strspn(line, ">"), "From ");
+}
+
 void pp_remainder(struct pretty_print_context *pp,
 		  const char **msg_p,
 		  struct strbuf *sb,
@@ -1725,8 +1737,13 @@ void pp_remainder(struct pretty_print_context *pp,
 		else if (pp->expand_tabs_in_log)
 			strbuf_add_tabexpand(sb, pp->expand_tabs_in_log,
 					     line, linelen);
-		else
+		else {
+			if (pp->fmt == CMIT_FMT_MBOXRD &&
+					is_mboxrd_from(line, linelen))
+				strbuf_addch(sb, '>');
+
 			strbuf_add(sb, line, linelen);
+		}
 		strbuf_addch(sb, '\n');
 	}
 }
@@ -1750,14 +1767,14 @@ void pretty_print_commit(struct pretty_print_context *pp,
 	encoding = get_log_output_encoding();
 	msg = reencoded = logmsg_reencode(commit, NULL, encoding);
 
-	if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
+	if (pp->fmt == CMIT_FMT_ONELINE || cmit_fmt_is_mail(pp->fmt))
 		indent = 0;
 
 	/*
 	 * We need to check and emit Content-type: to mark it
 	 * as 8-bit if we haven't done so.
 	 */
-	if (pp->fmt == CMIT_FMT_EMAIL && need_8bit_cte == 0) {
+	if (cmit_fmt_is_mail(pp->fmt) && need_8bit_cte == 0) {
 		int i, ch, in_body;
 
 		for (in_body = i = 0; (ch = msg[i]); i++) {
@@ -1785,7 +1802,7 @@ void pretty_print_commit(struct pretty_print_context *pp,
 	msg = skip_empty_lines(msg);
 
 	/* These formats treat the title line specially. */
-	if (pp->fmt == CMIT_FMT_ONELINE || pp->fmt == CMIT_FMT_EMAIL)
+	if (pp->fmt == CMIT_FMT_ONELINE || cmit_fmt_is_mail(pp->fmt))
 		pp_title_line(pp, &msg, sb, encoding, need_8bit_cte);
 
 	beginning_of_body = sb->len;
@@ -1802,7 +1819,7 @@ void pretty_print_commit(struct pretty_print_context *pp,
 	 * format.  Make sure we did not strip the blank line
 	 * between the header and the body.
 	 */
-	if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
+	if (cmit_fmt_is_mail(pp->fmt) && sb->len <= beginning_of_body)
 		strbuf_addch(sb, '\n');
 
 	unuse_commit_buffer(commit, reencoded);