[PATCH] mailinfo: unescape quoted-pair in header fields

[Kevin Daudt <me@ikke.info>]

rfc2822 has provisions for quoted strings in structured header fields,
but also allows for escaping these with so-called quoted-pairs.

The only thing git currently does is removing exterior quotes, but
quotes within are left alone.

Tell mailinfo to remove exterior quotes and remove escape characters from the
author so that they don't show up in the commits author field.

Signed-off-by: Kevin Daudt <me@ikke.info>
---
The only thing I could not easily fix is the prevent git am from removing any quotes around the author. This is done in fmt_ident, which calls `strbuf_addstr_without_crud`. 

 mailinfo.c                 | 54 ++++++++++++++++++++++++++++++++++++++++++++++
 t/t5100-mailinfo.sh        |  6 ++++++
 t/t5100/quoted-pair.expect |  5 +++++
 t/t5100/quoted-pair.in     |  9 ++++++++
 4 files changed, 74 insertions(+)
 create mode 100644 t/t5100/quoted-pair.expect
 create mode 100644 t/t5100/quoted-pair.in

diff --git a/mailinfo.c b/mailinfo.c
index e19abe3..04036f3 100644
--- a/mailinfo.c
+++ b/mailinfo.c
@@ -54,15 +54,69 @@ static void parse_bogus_from(struct mailinfo *mi, const struct strbuf *line)
 	get_sane_name(&mi->name, &mi->name, &mi->email);
 }
 
+static int unquote_quoted_string(struct strbuf *line)
+{
+	struct strbuf outbuf;
+	const char *in = line->buf;
+	int c, take_next_literally = 0;
+	int found_error = 0;
+	char escape_context=0;
+
+	strbuf_init(&outbuf, line->len);
+
+	while ((c = *in++) != 0) {
+		if (take_next_literally) {
+			take_next_literally = 0;
+		} else {
+			switch (c) {
+			case '"':
+				if (!escape_context)
+					escape_context = '"';
+				else if (escape_context == '"')
+					escape_context = 0;
+				continue;
+			case '\\':
+				if (escape_context) {
+					take_next_literally = 1;
+					continue;
+				}
+				break;
+			case '(':
+				if (!escape_context)
+					escape_context = '(';
+				else if (escape_context == '(')
+					found_error = 1;
+				break;
+			case ')':
+				if (escape_context == '(')
+					escape_context = 0;
+				break;
+			}
+		}
+
+		strbuf_addch(&outbuf, c);
+	}
+
+	strbuf_reset(line);
+	strbuf_addbuf(line, &outbuf);
+	strbuf_release(&outbuf);
+
+	return found_error;
+
+}
+
 static void handle_from(struct mailinfo *mi, const struct strbuf *from)
 {
 	char *at;
 	size_t el;
 	struct strbuf f;
 
+
 	strbuf_init(&f, from->len);
 	strbuf_addbuf(&f, from);
 
+	unquote_quoted_string(&f);
+
 	at = strchr(f.buf, '@');
 	if (!at) {
 		parse_bogus_from(mi, from);
diff --git a/t/t5100-mailinfo.sh b/t/t5100-mailinfo.sh
index 1a5a546..d0c21fc 100755
--- a/t/t5100-mailinfo.sh
+++ b/t/t5100-mailinfo.sh
@@ -142,4 +142,10 @@ test_expect_success 'mailinfo unescapes with --mboxrd' '
 	test_cmp expect mboxrd/msg
 '
 
+test_expect_success 'mailinfo unescapes rfc2822 quoted-string' '
+    mkdir quoted-pair &&
+    git mailinfo /dev/null /dev/null <"$TEST_DIRECTORY"/t5100/quoted-pair.in >quoted-pair/info &&
+    test_cmp "$TEST_DIRECTORY"/t5100/quoted-pair.expect quoted-pair/info
+'
+
 test_done
diff --git a/t/t5100/quoted-pair.expect b/t/t5100/quoted-pair.expect
new file mode 100644
index 0000000..cab1bce
--- /dev/null
+++ b/t/t5100/quoted-pair.expect
@@ -0,0 +1,5 @@
+Author: Author "The Author" Name
+Email: somebody@example.com
+Subject: testing quoted-pair
+Date: Sun, 25 May 2008 00:38:18 -0700
+
diff --git a/t/t5100/quoted-pair.in b/t/t5100/quoted-pair.in
new file mode 100644
index 0000000..e2e627a
--- /dev/null
+++ b/t/t5100/quoted-pair.in
@@ -0,0 +1,9 @@
+From 1234567890123456789012345678901234567890 Mon Sep 17 00:00:00 2001
+From: "Author \"The Author\" Name" <somebody@example.com>
+Date: Sun, 25 May 2008 00:38:18 -0700
+Subject: [PATCH] testing quoted-pair
+
+
+
+---
+patch
-- 
2.10.0.86.g6ffa4f1.dirty