From: Alex A Skinner <alex@lx.lc>
Date: Tue, 30 Jul 2013 04:11:47 +0000 (+1000)
Subject: encoding/xml: Do not pass through invalid utf8 bytes
X-Git-Tag: go1.2rc2~897
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=789e1c351e6fca96fe3cec467029732c03d55d64;p=gostls13.git

encoding/xml: Do not pass through invalid utf8 bytes

EscapeText now escapes 0xFFFD returned from DecodeRune as 0xFFFD, rather than passing through the original byte.
Fixes #5880.

R=golang-dev, r, bradfitz, adg
CC=golang-dev
https://golang.org/cl/11975043
---

diff --git a/src/pkg/encoding/xml/xml.go b/src/pkg/encoding/xml/xml.go
index 021f7e47d9..2f36604797 100644
--- a/src/pkg/encoding/xml/xml.go
+++ b/src/pkg/encoding/xml/xml.go
@@ -1758,7 +1758,7 @@ func EscapeText(w io.Writer, s []byte) error {
 		case '\r':
 			esc = esc_cr
 		default:
-			if !isInCharacterRange(r) {
+			if !isInCharacterRange(r) || (r == 0xFFFD && width == 1) {
 				esc = esc_fffd
 				break
 			}
diff --git a/src/pkg/encoding/xml/xml_test.go b/src/pkg/encoding/xml/xml_test.go
index eeedbe575f..52477d3429 100644
--- a/src/pkg/encoding/xml/xml_test.go
+++ b/src/pkg/encoding/xml/xml_test.go
@@ -11,6 +11,7 @@ import (
 	"reflect"
 	"strings"
 	"testing"
+	"unicode/utf8"
 )
 
 const testInput = `
@@ -714,3 +715,14 @@ func TestEscapeTextInvalidChar(t *testing.T) {
 		t.Errorf("have %v, want %v", text, expected)
 	}
 }
+
+func TestIssue5880(t *testing.T) {
+	type T []byte
+	data, err := Marshal(T{192, 168, 0, 1})
+	if err != nil {
+		t.Errorf("Marshal error: %v", err)
+	}
+	if !utf8.Valid(data) {
+		t.Errorf("Marshal generated invalid UTF-8: %x", data)
+	}
+}