internal/encoding/text: escape \x7f (DEL) in strings

We already escape ASCII control characters in the range [0x00,0x20). Escape the one control character outside this range as well. Change-Id: If954da0d4a178b36128d1a53d25397d1b3fd2e17 Reviewed-on: https://go-review.googlesource.com/c/protobuf/+/262681 Trust: Damien Neil <dneil@google.com> Run-TryBot: Damien Neil <dneil@google.com> Reviewed-by: Joe Tsai <thebrokentoaster@gmail.com>
protocolbuffers · Oct 15, 2020 · b1cd8e3 · b1cd8e3
1 parent 9712361
commit b1cd8e3
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 4 deletions.
diff --git a/internal/encoding/text/encode.go b/internal/encoding/text/encode.go
@@ -124,7 +124,7 @@ func appendString(out []byte, in string, outputASCII bool) []byte {
 			// are used to represent both the proto string and bytes type.
 			r = rune(in[0])
 			fallthrough
-		case r < ' ' || r == '"' || r == '\\':
+		case r < ' ' || r == '"' || r == '\\' || r == 0x7f:
 			out = append(out, '\\')
 			switch r {
 			case '"', '\\':
@@ -166,7 +166,7 @@ func appendString(out []byte, in string, outputASCII bool) []byte {
 // escaping. If no characters need escaping, this returns the input length.
 func indexNeedEscapeInString(s string) int {
 	for i := 0; i < len(s); i++ {
-		if c := s[i]; c < ' ' || c == '"' || c == '\'' || c == '\\' || c >= utf8.RuneSelf {
+		if c := s[i]; c < ' ' || c == '"' || c == '\'' || c == '\\' || c >= 0x7f {
 			return i
 		}
 	}

diff --git a/internal/encoding/text/encode_test.go b/internal/encoding/text/encode_test.go
@@ -403,8 +403,8 @@ func TestEncodeStrings(t *testing.T) {
 				}
 				return string(b)
 			}(),
-			wantOut:      `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\x7f\"",
-			wantOutASCII: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\x7f\"",
+			wantOut:      `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\"",
+			wantOutASCII: `"\x01\x02\x03\x04\x05\x06\x07\x08\t\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[]^_` + "`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\"",
 		},
 		{
 			// Valid UTF-8 wire encoding of the RuneError rune.
@@ -482,6 +482,11 @@ func TestEncodeStrings(t *testing.T) {
 			wantOut:      `"\x0f"`,
 			wantOutASCII: `"\x0f"`,
 		},
+		{
+			in:           "\x7f",
+			wantOut:      `"\x7f"`,
+			wantOutASCII: `"\x7f"`,
+		},
 		{
 			in:           "\xff",
 			wantOut:      `"\xff"`,