Initial project import

tools/v/vlib/encoding/utf8/validate/encoding_utf8_test.v

@@ -0,0 +1,88 @@
+import encoding.utf8.validate
+
+fn test_validate_str() {
+	assert validate.utf8_string('añçá') == true
+	assert validate.utf8_string('\x61\xC3\xB1\xC3\xA7\xC3\xA1') == true
+
+	assert validate.utf8_string('\x01') == true
+	assert validate.utf8_string('\x7e') == true
+	assert validate.utf8_string('\x7f') == true
+	assert validate.utf8_string('\xc2\x80') == true
+	assert validate.utf8_string('\xc2\x81') == true
+	assert validate.utf8_string('\xc2\xbf') == true
+	assert validate.utf8_string('\xc3\x80') == true
+	assert validate.utf8_string('\xc3\x81') == true
+	assert validate.utf8_string('\xc3\x88') == true
+	assert validate.utf8_string('\xc3\x90') == true
+	assert validate.utf8_string('\xc3\xa0') == true
+	assert validate.utf8_string('\xc3\xb0') == true
+	assert validate.utf8_string('\xc3\xb8') == true
+	assert validate.utf8_string('\xc3\xbf') == true
+	assert validate.utf8_string('\xc4\x80') == true
+	assert validate.utf8_string('\xdf\xbf') == true
+	assert validate.utf8_string('\xd0\x80') == true
+	assert validate.utf8_string('\xe0\xa0\x80') == true
+	assert validate.utf8_string('\xe0\xa0\x81') == true
+	assert validate.utf8_string('\xe1\x80\x80') == true
+	assert validate.utf8_string('\xed\x80\x80') == true
+	assert validate.utf8_string('\xed\x9f\xbf') == true
+	assert validate.utf8_string('\xee\x80\x80') == true
+	assert validate.utf8_string('\xef\xbf\xbe') == true
+	assert validate.utf8_string('\xef\xbf\xbf') == true
+	assert validate.utf8_string('\xf0\x90\x80\x80') == true
+	assert validate.utf8_string('\xf0\x90\x80\x81') == true
+	assert validate.utf8_string('\xf1\x80\x80\x80') == true
+	assert validate.utf8_string('\xf4\x8f\xbf\xbe') == true
+	assert validate.utf8_string('\xf4\x8f\xbf\xbf') == true
+	assert validate.utf8_string('\xef\xbf\xbd') == true
+}
+
+fn test_validate_invalid_str() {
+	assert validate.utf8_string('\xC0\xC1') == false
+	assert validate.utf8_string('\xF5\xFF') == false
+	assert validate.utf8_string('\xE0\xEF') == false
+
+	// xx
+	assert validate.utf8_string('\x91\x80\x80\x80') == false
+
+	// s1
+	assert validate.utf8_string('\xC2\x7F\x80\x80') == false
+	assert validate.utf8_string('\xC2\xC0\x80\x80') == false
+	assert validate.utf8_string('\xDF\x7F\x80\x80') == false
+	assert validate.utf8_string('\xDF\xC0\x80\x80') == false
+
+	// s2
+	assert validate.utf8_string('\xE0\x9F\xBF\x80') == false
+	assert validate.utf8_string('\xE0\xA0\x7F\x80') == false
+	assert validate.utf8_string('\xE0\xBF\xC0\x80') == false
+	assert validate.utf8_string('\xE0\xC0\x80\x80') == false
+
+	// s3
+	assert validate.utf8_string('\xE1\x7F\xBF\x80') == false
+	assert validate.utf8_string('\xE1\x80\x7F\x80') == false
+	assert validate.utf8_string('\xE1\xBF\xC0\x80') == false
+	assert validate.utf8_string('\xE1\xC0\x80\x80') == false
+
+	// s4
+	assert validate.utf8_string('\xED\x7F\xBF\x80') == false
+	assert validate.utf8_string('\xED\x80\x7F\x80') == false
+	assert validate.utf8_string('\xED\x9F\xC0\x80') == false
+	assert validate.utf8_string('\xED\xA0\x80\x80') == false
+
+	// s5
+	assert validate.utf8_string('\xF0\x8F\xBF\xBF') == false
+	assert validate.utf8_string('\xF0\x90\x7F\xBF') == false
+	assert validate.utf8_string('\xF0\x90\x80\x7F') == false
+	assert validate.utf8_string('\xF0\xBF\xBF\xC0') == false
+	assert validate.utf8_string('\xF0\xBF\xC0\x80') == false
+	assert validate.utf8_string('\xF0\xC0\x80\x80') == false
+
+	// s6
+	assert validate.utf8_string('\xF1\x7F\xBF\xBF') == false
+	assert validate.utf8_string('\xF1\x80\x7F\xBF') == false
+	assert validate.utf8_string('\xF1\x80\x80\x7F') == false
+	assert validate.utf8_string('\xF1\xBF\xBF\xC0') == false
+	assert validate.utf8_string('\xF1\xBF\xC0\x80') == false
+	assert validate.utf8_string('\xF1\xC0\x80\x80') == false
+	assert validate.utf8_string('\xED\xEF\xBF\x89') == false
+}

tools/v/vlib/encoding/utf8/validate/validate_utf8.v

@@ -0,0 +1,45 @@
+module validate
+
+// http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+
+// vfmt off
+const utf8d = [
+	u8(0), 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+	1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+	7, 7, 7, 7, 7, 7, 7, 7, 7, 8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+	2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 10, 3, 3, 3, 3,
+	3, 3, 3, 3, 3, 3, 3, 3, 4, 3, 3, 11, 6, 6, 6, 5, 8, 8, 8, 8, 8, 8, 8,
+	8, 8, 8, 8, 0, 12, 24, 36, 60, 96, 84, 12, 12, 12, 48, 72, 12, 12, 12,
+	12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 0, 12, 12, 12, 12, 12, 0, 12,
+	0, 12, 12, 12, 24, 12, 12, 12, 12, 12, 24, 12, 24, 12, 12, 12, 12, 12,
+	12, 12, 12, 12, 24, 12, 12, 12, 12, 12, 24, 12, 12, 12, 12, 12, 12, 12,
+	24, 12, 12, 12, 12, 12, 12, 12, 12, 12, 36, 12, 36, 12, 12, 12, 36, 12,
+	12, 12, 12, 12, 36, 12, 36, 12, 12, 12, 36, 12, 12, 12, 12, 12, 12, 12,
+	12, 12, 12 ]!
+// vfmt on
+
+// utf8_string returns true, if the given string `s` consists only of valid UTF-8 runes
+pub fn utf8_string(s string) bool {
+	return utf8_data(s.str, s.len)
+}
+
+// utf8_data returns true, if the given `data` block, with length `len` bytes, consists only of valid UTF-8 runes
+@[direct_array_access]
+pub fn utf8_data(data &u8, len int) bool {
+	mut state := 0
+
+	for i := 0; i < len; i++ {
+		b := unsafe { data[i] }
+		state = utf8d[256 + state + utf8d[b]]
+		if state == 12 {
+			return false
+		}
+	}
+	return state == 0
+}