fixes #36 fix bug in BM-prefix check when handling runes more than 16 bits.

Author: dlclark

regexp_test.go

@@ -1093,27 +1093,23 @@ func TestEmptyCaptureLargeRepeat(t *testing.T) {
 	}
 }
 
-func TestFuzzBytes(t *testing.T) {
+func TestFuzzBytes_NoCompile(t *testing.T) {
 	//some crash cases found from fuzzing
 
 	var testCases = []struct {
-		r, s []byte
+		r []byte
 	}{
 		{
 			r: []byte{0x28, 0x28, 0x29, 0x5c, 0x37, 0x28, 0x3f, 0x28, 0x29, 0x29},
-			s: []byte{0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30},
 		},
 		{
 			r: []byte{0x28, 0x5c, 0x32, 0x28, 0x3f, 0x28, 0x30, 0x29, 0x29},
-			s: []byte{0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30},
 		},
 		{
 			r: []byte{0x28, 0x3f, 0x28, 0x29, 0x29, 0x5c, 0x31, 0x30, 0x28, 0x3f, 0x28, 0x30, 0x29},
-			s: []byte{0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30},
 		},
 		{
 			r: []byte{0x28, 0x29, 0x28, 0x28, 0x29, 0x5c, 0x37, 0x28, 0x3f, 0x28, 0x29, 0x29},
-			s: []byte{0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30},
 		},
 	}
 
@@ -1129,3 +1125,32 @@ func TestFuzzBytes(t *testing.T) {
 	}
 
 }
+
+func TestFuzzBytes_Match(t *testing.T) {
+
+	var testCases = []struct {
+		r, s []byte
+	}{
+		{
+			r: []byte{0x30, 0xbf, 0x30, 0x2a, 0x30, 0x30},
+			s: []byte{0xf0, 0xb0, 0x80, 0x91, 0xf7},
+		},
+		{
+			r: []byte{0x30, 0xaf, 0xf3, 0x30, 0x2a},
+			s: []byte{0xf3, 0x80, 0x80, 0x87, 0x80, 0x89},
+		},
+	}
+
+	for _, c := range testCases {
+		r := string(c.r)
+		t.Run(r, func(t *testing.T) {
+			re, err := Compile(r, 0)
+
+			if err != nil {
+				t.Fatal("should compile, but didn't")
+			}
+
+			re.MatchString(string(c.s))
+		})
+	}
+}

syntax/prefix.go

@@ -712,7 +712,7 @@ func (b *BmPrefix) Scan(text []rune, index, beglimit, endlimit int) int {
 
 				if chTest != b.pattern[match] {
 					advance = b.positive[match]
-					if (chTest & 0xFF80) == 0 {
+					if chTest < 128 {
 						test2 = (match - startmatch) + b.negativeASCII[chTest]
 					} else if chTest < 0xffff && len(b.negativeUnicode) > 0 {
 						unicodeLookup = b.negativeUnicode[chTest>>8]