Add UTF-16 test case

Author: Gusted

modules/charset/escape.go

@@ -69,7 +69,6 @@ func EscapeControlReader(text io.Reader, output io.Writer) (escaped EscapeStatus
 	lineHasBIDI := false
 	lineHasRTLScript := false
 	lineHasLTRScript := false
-
 readingloop:
 	for err == nil {
 		n, err = text.Read(buf[readStart:])
@@ -79,6 +78,7 @@ readingloop:
 
 		for i < len(bs) {
 			r, size := utf8.DecodeRune(bs[i:])
+
 			// Now handle the codepoints
 			switch {
 			case r == utf8.RuneError:
@@ -145,7 +145,7 @@ readingloop:
 				}
 				writePos = i + size
 			// 65279 == BOM rune.
-			case unicode.Is(unicode.C, r) && r != rune(65279):
+			case r != rune(65279) && unicode.Is(unicode.C, r):
 				escaped.Escaped = true
 				escaped.HasControls = true
 				if writePos < i {

modules/charset/escape_test.go

@@ -135,6 +135,14 @@ then resh (ר), and finally heh (ה) (which should appear leftmost).`,
 		result: string([]byte{'\xef', '\xbb', '\xbf'}),
 		status: EscapeStatus{},
 	},
+	{
+		name:   "BOM encoding UTF-16",
+		text:   string([]byte{239, 187, 191, 228, 189, 160, 229, 165, 189, 239, 188, 140, 228, 184, 150, 231, 149, 140, 10, 104, 101, 108, 108, 111, 44, 32, 119, 111, 114, 108, 100, 10}),
+		result: string([]byte{239, 187, 191, 228, 189, 160, 229, 165, 189, 239, 188, 140, 228, 184, 150, 231, 149, 140, 10, 104, 101, 108, 108, 111, 44, 32, 119, 111, 114, 108, 100, 10}),
+		status: EscapeStatus{
+			HasLTRScript: true,
+		},
+	},
 }
 
 func TestEscapeControlString(t *testing.T) {