mailinfo: handle in-body header continuations

Mailinfo currently handles multi-line headers, but it does not handle
multi-line in-body headers. Teach it to handle such headers, for
example, for this input:

  From: author <author@example.com>
  Date: Fri, 9 Jun 2006 00:44:16 -0700
  Subject: a very long
   broken line

  Subject: another very long
   broken line

interpret the in-body subject to be "another very long broken line"
instead of "another very long".

An existing test (t/t5100/msg0015) has an indented line immediately
after an in-body header - it has been modified to reflect the new
functionality.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: jonathantanmy

mailinfo.c

@@ -500,6 +500,21 @@ static int check_header(struct mailinfo *mi,
 	return ret;
 }
 
+/*
+ * Returns 1 if the given line or any line beginning with the given line is an
+ * in-body header (that is, check_header will succeed when passed
+ * mi->s_hdr_data).
+ */
+static int is_inbody_header(const struct mailinfo *mi,
+			    const struct strbuf *line)
+{
+	int i;
+	for (i = 0; header[i]; i++)
+		if (!mi->s_hdr_data[i] && cmp_header(line, header[i]))
+			return 1;
+	return 0;
+}
+
 static void decode_transfer_encoding(struct mailinfo *mi, struct strbuf *line)
 {
 	struct strbuf *ret;
@@ -609,8 +624,33 @@ static int is_scissors_line(const char *line)
 		gap * 2 < perforation);
 }
 
+static void flush_inbody_header_accum(struct mailinfo *mi)
+{
+	if (!mi->inbody_header_accum.len)
+		return;
+	assert(check_header(mi, &mi->inbody_header_accum, mi->s_hdr_data, 0));
+	strbuf_reset(&mi->inbody_header_accum);
+}
+
 static int check_inbody_header(struct mailinfo *mi, const struct strbuf *line)
 {
+	if (mi->inbody_header_accum.len &&
+	    (line->buf[0] == ' ' || line->buf[0] == '\t')) {
+		if (mi->use_scissors && is_scissors_line(line->buf)) {
+			/*
+			 * This is a scissors line; do not consider this line
+			 * as a header continuation line.
+			 */
+			flush_inbody_header_accum(mi);
+			return 0;
+		}
+		strbuf_strip_suffix(&mi->inbody_header_accum, "\n");
+		strbuf_addbuf(&mi->inbody_header_accum, line);
+		return 1;
+	}
+
+	flush_inbody_header_accum(mi);
+
 	if (starts_with(line->buf, ">From") && isspace(line->buf[5]))
 		return is_format_patch_separator(line->buf + 1, line->len - 1);
 	if (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) {
@@ -622,7 +662,11 @@ static int check_inbody_header(struct mailinfo *mi, const struct strbuf *line)
 			}
 		return 0;
 	}
-	return check_header(mi, line, mi->s_hdr_data, 0);
+	if (is_inbody_header(mi, line)) {
+		strbuf_addbuf(&mi->inbody_header_accum, line);
+		return 1;
+	}
+	return 0;
 }
 
 static int handle_commit_msg(struct mailinfo *mi, struct strbuf *line)
@@ -888,6 +932,8 @@ static void handle_body(struct mailinfo *mi, struct strbuf *line)
 			break;
 	} while (!strbuf_getwholeline(line, mi->input, '\n'));
 
+	flush_inbody_header_accum(mi);
+
 handle_body_out:
 	strbuf_release(&prev);
 }
@@ -1003,6 +1049,7 @@ void setup_mailinfo(struct mailinfo *mi)
 	strbuf_init(&mi->email, 0);
 	strbuf_init(&mi->charset, 0);
 	strbuf_init(&mi->log_message, 0);
+	strbuf_init(&mi->inbody_header_accum, 0);
 	mi->header_stage = 1;
 	mi->use_inbody_headers = 1;
 	mi->content_top = mi->content;
@@ -1016,6 +1063,7 @@ void clear_mailinfo(struct mailinfo *mi)
 	strbuf_release(&mi->name);
 	strbuf_release(&mi->email);
 	strbuf_release(&mi->charset);
+	strbuf_release(&mi->inbody_header_accum);
 	free(mi->message_id);
 
 	for (i = 0; mi->p_hdr_data[i]; i++)

mailinfo.h

@@ -27,6 +27,7 @@ struct mailinfo {
 	int patch_lines;
 	int filter_stage; /* still reading log or are we copying patch? */
 	int header_stage; /* still checking in-body headers? */
+	struct strbuf inbody_header_accum;
 	struct strbuf **p_hdr_data;
 	struct strbuf **s_hdr_data;
 

t/t4150-am.sh

@@ -977,4 +977,27 @@ test_expect_success 'am --patch-format=mboxrd handles mboxrd' '
 	test_cmp msg out
 '
 
+test_expect_success 'am works with multi-line in-body headers' '
+	FORTY="String that has a length of more than forty characters" &&
+	LONG="$FORTY $FORTY" &&
+	rm -fr .git/rebase-apply &&
+	git checkout -f first &&
+	echo one >> file &&
+	git commit -am "$LONG" --author="$LONG <long@example.com>" &&
+	git format-patch --stdout -1 >patch &&
+	# bump from, date, and subject down to in-body header
+	perl -lpe "
+		if (/^From:/) {
+			print \"From: x <x\@example.com>\";
+			print \"Date: Sat, 1 Jan 2000 00:00:00 +0000\";
+			print \"Subject: x\n\";
+		}
+	" patch >msg &&
+	git checkout HEAD^ &&
+	git am msg &&
+	# Ensure that the author and full message are present
+	git cat-file commit HEAD | grep "^author.*long@example.com" &&
+	git cat-file commit HEAD | grep "^$LONG"
+'
+
 test_done

t/t5100-mailinfo.sh

@@ -11,7 +11,7 @@ test_expect_success 'split sample box' \
 	'git mailsplit -o. "$TEST_DIRECTORY"/t5100/sample.mbox >last &&
 	last=$(cat last) &&
 	echo total is $last &&
-	test $(cat last) = 17'
+	test $(cat last) = 18'
 
 check_mailinfo () {
 	mail=$1 opt=$2

t/t5100/info0018

@@ -0,0 +1,5 @@
+Author: Another Thor
+Email: a.thor@example.com
+Subject: This one contains a tab and a space
+Date: Fri, 9 Jun 2006 00:44:16 -0700
+

t/t5100/info0018--no-inbody-headers

@@ -0,0 +1,5 @@
+Author: A U Thor
+Email: a.u.thor@example.com
+Subject: check multiline inbody headers
+Date: Fri, 9 Jun 2006 00:44:16 -0700
+

t/t5100/msg0015

@@ -1,2 +0,0 @@
-  - a list
-  - of stuff

t/t5100/msg0018

@@ -0,0 +1,2 @@
+a commit message
+

t/t5100/msg0018--no-inbody-headers

@@ -0,0 +1,8 @@
+From: Another Thor
+ <a.thor@example.com>
+Subject: This one contains
+	a tab
+ and a space
+
+a commit message
+

t/t5100/patch0018

@@ -0,0 +1,6 @@
+diff --git a/foo b/foo
+index e69de29..d95f3ad 100644
+--- a/foo
++++ b/foo
+@@ -0,0 +1 @@
++content