Slightly modified UTF-8 handling. Based on http://man7.org/linux/man-pages/man7/utf-8.7.html.

src/system/text.c

@@ -397,26 +397,47 @@ static char *nextCharacter(const char *str, int *i)
 	static char character[MAX_NAME_LENGTH];
 
 	unsigned char bit;
-	int n;
+	int n, numBits;
 
 	memset(character, '\0', MAX_NAME_LENGTH);
 
-	n = 0;
-	
-	while (1)
-	{
 	bit = (unsigned char)str[*i];
 
-		if ((bit >= ' ' && bit <= '~') || bit >= 0xC0 || bit == '\0')
+	numBits = 0;
+
+	if (bit == '\0')
 	{
-			if (n > 0)
-			{
-				return character[0] != '\0' ? character : NULL;
+		return NULL;
 	}
+	else if (bit <= 0x0000007F)
+	{
+		numBits = 1;
+	}
+	else if (bit <= 0x000007FF)
+	{
+		numBits = 2;
+	}
+	else if (bit <= 0x0000FFFF)
+	{
+		numBits = 3;
+	}
+	else if (bit <= 0x001FFFFF)
+	{
+		numBits = 4;
+	}
+	else if (bit <= 0x03FFFFFF)
+	{
+		numBits = 5;
+	}
+	else if (bit <= 0x7FFFFFFF)
+	{
+		numBits = 6;
 	}
 
-		character[n++] = str[*i];
-		
-		*i = *i + 1;
+	for (n = 0 ; n < numBits ; n++)
+	{
+		character[n] = str[(*i)++];
 	}
+
+	return character;
 }