encoding.utf8: fix len and ulen and optimize raw_index (#9682)

vlib/encoding/utf8/utf8_util.v

@@ -15,6 +15,10 @@ Utility functions
 
 // len return the length as number of unicode chars from a string
 pub fn len(s string) int {
+	if s.len == 0 {
+		return 0
+	}
+
 	mut count := 0
 	mut index := 0
 
@@ -82,10 +86,16 @@ pub fn get_uchar(s string, index int) int {
 // raw_index - get the raw chracter from the string by the given index value.
 // example: '我是V Lang'.raw_index(1) => '是'
 
+// raw_index - get the raw chracter from the string by the given index value.
+// example: utf8.raw_index('我是V Lang', 1) => '是'
 pub fn raw_index(s string, index int) string {
 	mut r := []rune{}
 
 	for i := 0; i < s.len; i++ {
+		if r.len - 1 == index {
+			break
+		}
+
 		b := s[i]
 		ch_len := ((0xe5000000 >> ((b >> 3) & 0x1e)) & 3)
 

vlib/encoding/utf8/utf8_util_test.v

@@ -21,10 +21,12 @@ fn test_utf8_util() {
 	assert lower1 == (src_lower.ustring())
 
 	// test len function
+	assert utf8.len('') == 0
 	assert utf8.len('pippo') == 5
 	assert utf8.len(src) == 15 // 29
 	assert src.len == 24 // 49
 	// test u_len function
+	assert utf8.u_len(''.ustring()) == 0
 	assert utf8.u_len(src1) == 15 // 29
 	assert utf8.u_len('pippo'.ustring()) == 5