mailinfo: make ">From" in-body header check more robust

Since commit 81c5cf7 (mailinfo: skip bogus UNIX From line inside
body, 2006-05-21), we have treated lines like ">From" in the body as
headers. This makes "git am" work for people who erroneously paste
the whole output from format-patch:

  From 12345abcd...fedcba543210 Mon Sep 17 00:00:00 2001
  From: them
  Subject: [PATCH] whatever

into their email body (assuming that an mbox writer then quotes
"From" as ">From", as otherwise we would actually mailsplit on the
in-body line).

However, this has false positives if somebody actually has a commit
body that starts with "From "; in this case we erroneously remove
the line entirely from the commit message. We can make this check
more robust by making sure the line actually looks like a real mbox
"From" line.

Inspect the line that begins with ">From " a more carefully to only
skip lines that match the expected pattern (note that the datestamp
part of the format-patch output is designed to be kept constant to
help those who write magic(5) entries).

Signed-off-by: Jeff King <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: peff

builtin/mailinfo.c

@@ -288,6 +288,21 @@ static inline int cmp_header(const struct strbuf *line, const char *hdr)
 			line->buf[len] == ':' && isspace(line->buf[len + 1]);
 }
 
+#define SAMPLE "From e6807f3efca28b30decfecb1732a56c7db1137ee Mon Sep 17 00:00:00 2001\n"
+static int is_format_patch_separator(const char *line, int len)
+{
+	const char *cp;
+
+	if (len != strlen(SAMPLE))
+		return 0;
+	if (!skip_prefix(line, "From ", &cp))
+		return 0;
+	if (strspn(cp, "0123456789abcdef") != 40)
+		return 0;
+	cp += 40;
+	return !memcmp(SAMPLE + (cp - line), cp, strlen(SAMPLE) - (cp - line));
+}
+
 static int check_header(const struct strbuf *line,
 				struct strbuf *hdr_data[], int overwrite)
 {
@@ -329,7 +344,7 @@ static int check_header(const struct strbuf *line,
 
 	/* for inbody stuff */
 	if (starts_with(line->buf, ">From") && isspace(line->buf[5])) {
-		ret = 1; /* Should this return 0? */
+		ret = is_format_patch_separator(line->buf + 1, line->len - 1);
 		goto check_header_out;
 	}
 	if (starts_with(line->buf, "[PATCH]") && isspace(line->buf[7])) {

t/t5100-mailinfo.sh

@@ -89,4 +89,22 @@ test_expect_success 'mailinfo on from header without name works' '
 
 '
 
+test_expect_success 'mailinfo finds headers after embedded From line' '
+	mkdir embed-from &&
+	git mailsplit -oembed-from "$TEST_DIRECTORY"/t5100/embed-from.in &&
+	test_cmp "$TEST_DIRECTORY"/t5100/embed-from.in embed-from/0001 &&
+	git mailinfo embed-from/msg embed-from/patch \
+	  <embed-from/0001 >embed-from/out &&
+	test_cmp "$TEST_DIRECTORY"/t5100/embed-from.expect embed-from/out
+'
+
+test_expect_success 'mailinfo on message with quoted >From' '
+	mkdir quoted-from &&
+	git mailsplit -oquoted-from "$TEST_DIRECTORY"/t5100/quoted-from.in &&
+	test_cmp "$TEST_DIRECTORY"/t5100/quoted-from.in quoted-from/0001 &&
+	git mailinfo quoted-from/msg quoted-from/patch \
+	  <quoted-from/0001 >quoted-from/out &&
+	test_cmp "$TEST_DIRECTORY"/t5100/quoted-from.expect quoted-from/msg
+'
+
 test_done

t/t5100/embed-from.expect

@@ -0,0 +1,5 @@
+Author: Commit Author
+Email: [email protected]
+Subject: patch subject
+Date: Sat, 13 Sep 2014 21:13:23 -0400 
+

t/t5100/embed-from.in

@@ -0,0 +1,13 @@
+From 1234567890123456789012345678901234567890 Mon Sep 17 00:00:00 2001
+From: Email Author <[email protected]>
+Date: Sun, 25 May 2008 00:38:18 -0700
+Subject: [PATCH] email subject
+
+>From 1234567890123456789012345678901234567890 Mon Sep 17 00:00:00 2001
+From: Commit Author <[email protected]>
+Date: Sat, 13 Sep 2014 21:13:23 -0400
+Subject: patch subject
+
+patch body
+---
+patch

t/t5100/quoted-from.expect

@@ -0,0 +1,3 @@
+>From the depths of history, we are stuck with the
+flaky mbox format.
+

t/t5100/quoted-from.in

@@ -0,0 +1,10 @@
+From 1234567890123456789012345678901234567890 Mon Sep 17 00:00:00 2001
+From: Author Name <[email protected]>
+Date: Sun, 25 May 2008 00:38:18 -0700
+Subject: [PATCH] testing quoted >From
+
+>From the depths of history, we are stuck with the
+flaky mbox format.
+
+---
+patch