Add a unichar_charlen() function to calculate length-in-characters from length-in-bytes

py/misc.h

@@ -100,6 +100,7 @@ bool unichar_isupper(unichar c);
 bool unichar_islower(unichar c);
 unichar unichar_tolower(unichar c);
 unichar unichar_toupper(unichar c);
+uint unichar_charlen(const char *str, uint len);
 #define UTF8_IS_NONASCII(ch) ((ch) & 0x80)
 #define UTF8_IS_CONT(ch) (((ch) & 0xC0) == 0x80)
 

py/unicode.c

@@ -86,6 +86,17 @@ char *utf8_next_char(const char *s) {
     return (char *)s;
 }
 
+uint unichar_charlen(const char *str, uint len)
+{
+    uint charlen = 0;
+    for (const char *top = str + len; str < top; ++str) {
+        if (!UTF8_IS_CONT(*str)) {
+            ++charlen;
+        }
+    }
+    return charlen;
+}
+
 // Be aware: These unichar_is* functions are actually ASCII-only!
 bool unichar_isspace(unichar c) {
     return c < 128 && (attr[c] & FL_SPACE) != 0;