Merge pull request #25 from tdakkota/fix/keep-graphic-unicode

fix: do not escape some unicode characters

encode_test.go

@@ -483,6 +483,8 @@ var marshalTests = []struct {
 	},
 
 	// Encode unicode as utf-8 rather than in escaped form.
+	//
+	// See https://github.com/go-yaml/yaml/issues/737.
 	{
 		map[string]string{"a": "你好"},
 		"a: 你好\n",
@@ -491,6 +493,19 @@ var marshalTests = []struct {
 		"你好",
 		"你好\n",
 	},
+	{
+		map[string]string{"a": "🛑"},
+		"a: 🛑\n",
+	},
+	// Notice that result is not escaped.
+	{
+		map[string]string{"a": "\U0001f3f3\ufe0f\u200d\U0001f308"},
+		"a: " + "\U0001f3f3\ufe0f\u200d\U0001f308" + "\n",
+	},
+	{"\U0001f3f3\ufe0f\u200d\U0001f308", "\U0001f3f3\ufe0f\u200d\U0001f308\n"},
+	{"\U0001f439", "\U0001f439\n"},
+	{"\U0001f1fa\U0001f1f8", "\U0001f1fa\U0001f1f8\n"},
+	{"\U0001f474\U0001f3ff", "\U0001f474\U0001f3ff\n"},
 
 	// Support encoding.TextMarshaler.
 	{

yamlprivateh.go

@@ -22,6 +22,11 @@
 
 package yaml
 
+import (
+	"unicode"
+	"unicode/utf8"
+)
+
 const (
 	// The size of the input raw buffer.
 	input_raw_buffer_size = 512
@@ -83,15 +88,17 @@ func is_ascii(b []byte, i int) bool {
 
 // Check if the character at the start of the buffer can be printed unescaped.
 func is_printable(b []byte, i int) bool {
+	r, _ := utf8.DecodeRune(b[i:])
+	if r == utf8.RuneError {
+		return false
+	}
+
 	return ((b[i] == 0x0A) || // . == #x0A
 		(b[i] >= 0x20 && b[i] <= 0x7E) || // #x20 <= . <= #x7E
 		(b[i] == 0xC2 && b[i+1] >= 0xA0) || // #0xA0 <= . <= #xD7FF
 		(b[i] > 0xC2 && b[i] < 0xED) ||
 		(b[i] == 0xED && b[i+1] < 0xA0) ||
-		(b[i] == 0xEE) ||
-		(b[i] == 0xEF && // #xE000 <= . <= #xFFFD
-			!(b[i+1] == 0xBB && b[i+2] == 0xBF) && // && . != #xFEFF
-			!(b[i+1] == 0xBF && (b[i+2] == 0xBE || b[i+2] == 0xBF))))
+		unicode.IsGraphic(r))
 }
 
 // Check if the character at the specified position is NUL.