Merge pull request dlclark#52 from mstoykov/ecmascriptUnicodeEscape

Support \u{HEX} syntax with ECMAScript with Unicode flag

Author: dlclark

README.md

@@ -92,6 +92,10 @@ if isMatch, _ := re.MatchString(`Something to match`); isMatch {
 
 This feature is a work in progress and I'm open to ideas for more things to put here (maybe more relaxed character escaping rules?).
 
+## ECMAScript compatibility mode
+In this mode the engine provides compatibility with the [regex engine](https://tc39.es/ecma262/multipage/text-processing.html#sec-regexp-regular-expression-objects) described in the ECMAScript specification.
+
+Additionally a Unicode mode is provided which allows parsing of `\u{CodePoint}` syntax that is only when both are provided.
 
 ## Library features that I'm still working on
 - Regex split

regexp.go

@@ -121,6 +121,7 @@ const (
 	Debug                                = 0x0080 // "d"
 	ECMAScript                           = 0x0100 // "e"
 	RE2                                  = 0x0200 // RE2 (regexp package) compatibility mode
+	Unicode                              = 0x0400 // "u"
 )
 
 func (re *Regexp) RightToLeft() bool {

regexp_test.go

@@ -858,6 +858,20 @@ func TestECMAScriptXCurlyBraceEscape(t *testing.T) {
 	}
 }
 
+func TestEcmaScriptUnicodeRange(t *testing.T) {
+	r, err := Compile(`([\u{001a}-\u{ffff}]+)`, ECMAScript|Unicode)
+	if err != nil {
+		panic(err)
+	}
+	m, err := r.FindStringMatch("qqqq")
+	if err != nil {
+		panic(err)
+	}
+	if m == nil {
+		t.Fatal("Expected non-nil, got nil")
+	}
+}
+
 func TestNegateRange(t *testing.T) {
 	re := MustCompile(`[\D]`, 0)
 	if m, err := re.MatchString("A"); err != nil {

syntax/parser.go

@@ -22,6 +22,7 @@ const (
 	Debug                                = 0x0080 // "d"
 	ECMAScript                           = 0x0100 // "e"
 	RE2                                  = 0x0200 // RE2 compat mode
+	Unicode                              = 0x0400 // "u"
 )
 
 func optionFromCode(ch rune) RegexOptions {
@@ -43,6 +44,8 @@ func optionFromCode(ch rune) RegexOptions {
 		return Debug
 	case 'e', 'E':
 		return ECMAScript
+	case 'u', 'U':
+		return Unicode
 	default:
 		return 0
 	}
@@ -1695,7 +1698,13 @@ func (p *parser) scanCharEscape() (r rune, err error) {
 			r, err = p.scanHex(2)
 		}
 	case 'u':
-		r, err = p.scanHex(4)
+		// ECMAscript suppot \u{HEX} only if `u` is also set
+		if p.useOptionE() && p.useOptionU() && p.charsRight() > 0 && p.rightChar(0) == '{' {
+			p.moveRight(1)
+			return p.scanHexUntilBrace()
+		} else {
+			r, err = p.scanHex(4)
+		}
 	case 'a':
 		return '\u0007', nil
 	case 'b':
@@ -1972,6 +1981,11 @@ func (p *parser) useRE2() bool {
 	return (p.options & RE2) != 0
 }
 
+// True if U option enabling ECMAScript's Unicode behavior on.
+func (p *parser) useOptionU() bool {
+	return (p.options & Unicode) != 0
+}
+
 // True if options stack is empty.
 func (p *parser) emptyOptionsStack() bool {
 	return len(p.optionsStack) == 0