[PATCH v2 2/2] mailinfo: unescape quoted-pair in header fields

From: Kevin Daudt <me@ikke.info>
Date: Sep 19, 2016, 18:54 UTC
Message-ID: <20160919185440.18234-3-me@ikke.info>
In-Reply-To: <20160919185440.18234-1-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.

Remove exterior quotes and remove escape characters so that they don't show up in the author field.

Signed-off-by: Kevin Daudt <me@ikke.info>
---
 mailinfo.c                   | 46 ++++++++++++++++++++++++++++++++++++++++++++
 t/t5100-mailinfo.sh          | 14 ++++++++++++++
 t/t5100/comment.expect       |  5 +++++
 t/t5100/comment.in           |  9 +++++++++
 t/t5100/quoted-string.expect |  5 +++++
 t/t5100/quoted-string.in     |  9 +++++++++
 6 files changed, 88 insertions(+)
 create mode 100644 t/t5100/comment.expect
 create mode 100644 t/t5100/comment.in
 create mode 100644 t/t5100/quoted-string.expect
 create mode 100644 t/t5100/quoted-string.in

diff --git a/mailinfo.c b/mailinfo.c
index e19abe3..6a7c2f2 100644
--- a/mailinfo.c
+++ b/mailinfo.c
@@ -54,6 +54,50 @@ static void parse_bogus_from(struct mailinfo *mi, const struct strbuf *line)
 	get_sane_name(&mi->name, &mi->name, &mi->email);
 }
 
+static void unquote_quoted_string(struct strbuf *line)
+{
+	const char *in = strbuf_detach(line, NULL);
+	int c, take_next_literally = 0;
+	int found_error = 0;
+
+	/*
+	 * Stores the character that started the escape mode so that we know what
+	 * character will stop it
+	 */
+	char escape_context = 0;
+
+	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 = '(';
+				break;
+			case ')':
+				if (escape_context == '(')
+					escape_context = 0;
+				break;
+			}
+		}
+
+		strbuf_addch(line, c);
+	}
+}
+
 static void handle_from(struct mailinfo *mi, const struct strbuf *from)
 {
 	char *at;
@@ -63,6 +107,8 @@ static void handle_from(struct mailinfo *mi, const struct strbuf *from)
 	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 27bf3b8..8c21434 100755
--- a/t/t5100-mailinfo.sh
+++ b/t/t5100-mailinfo.sh
@@ -144,4 +144,18 @@ test_expect_success 'mailinfo unescapes with --mboxrd' '
 	test_cmp expect mboxrd/msg
 '
 
+test_expect_success 'mailinfo handles rfc2822 quoted-string' '
+	mkdir quoted-string &&
+	git mailinfo /dev/null /dev/null <"$DATA"/quoted-string.in \
+		>quoted-string/info &&
+	test_cmp "$DATA"/quoted-string.expect quoted-string/info
+'
+
+test_expect_success 'mailinfo handles rfc2822 comment' '
+	mkdir comment &&
+	git mailinfo /dev/null /dev/null <"$DATA"/comment.in \
+		>comment/info &&
+	test_cmp "$DATA"/comment.expect comment/info
+'
+
 test_done
diff --git a/t/t5100/comment.expect b/t/t5100/comment.expect
new file mode 100644
index 0000000..1197e76
--- /dev/null
+++ b/t/t5100/comment.expect
@@ -0,0 +1,5 @@
+Author: A U Thor (this is a comment (really))
+Email: somebody@example.com
+Subject: testing comments
+Date: Sun, 25 May 2008 00:38:18 -0700
+
diff --git a/t/t5100/comment.in b/t/t5100/comment.in
new file mode 100644
index 0000000..430ba97
--- /dev/null
+++ b/t/t5100/comment.in
@@ -0,0 +1,9 @@
+From 1234567890123456789012345678901234567890 Mon Sep 17 00:00:00 2001
+From: "A U Thor" <somebody@example.com> (this is a comment \(really\))
+Date: Sun, 25 May 2008 00:38:18 -0700
+Subject: [PATCH] testing comments
+
+
+
+---
+patch
diff --git a/t/t5100/quoted-string.expect b/t/t5100/quoted-string.expect
new file mode 100644
index 0000000..cab1bce
--- /dev/null
+++ b/t/t5100/quoted-string.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-string.in b/t/t5100/quoted-string.in
new file mode 100644
index 0000000..e2e627a
--- /dev/null
+++ b/t/t5100/quoted-string.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