Escape Latin Characters

[userMikeD]

I need to escape latin characters in an xml doc. Example: "é" is escaped to "é". I thought I could use the ASCII function, but SELECT ASCII('é') FROM DUAL in Oracle gives me 50089.

I coded this as a quick fix, but I'm sure there's a better way.

      FUNCTION escape_latin(p_str IN VARCHAR2) RETURN VARCHAR2 IS
         v_str VARCHAR2(3000) := p_str;
      BEGIN
         v_str := REPLACE(v_str, 'À', 'À');
         v_str := REPLACE(v_str, 'Á', 'Á');
         v_str := REPLACE(v_str, 'Â', 'Â');
         v_str := REPLACE(v_str, 'Ã', 'Ã');
         v_str := REPLACE(v_str, 'Ä', 'Ä');
         v_str := REPLACE(v_str, 'Å', 'Å');
         v_str := REPLACE(v_str, 'Æ', 'Æ');
         v_str := REPLACE(v_str, 'Ç', 'Ç');
         v_str := REPLACE(v_str, 'È', 'È');
         v_str := REPLACE(v_str, 'É', 'É');
         v_str := REPLACE(v_str, 'Ê', 'Ê');
         v_str := REPLACE(v_str, 'Ë', 'Ë');
         v_str := REPLACE(v_str, 'Ì', 'Ì');
         v_str := REPLACE(v_str, 'Í', 'Í');
         v_str := REPLACE(v_str, 'Î', 'Î');
         v_str := REPLACE(v_str, 'Ï', 'Ï');
         v_str := REPLACE(v_str, 'Ð', 'Ð');
         v_str := REPLACE(v_str, 'Ñ', 'Ñ');
         v_str := REPLACE(v_str, 'Ò', 'Ò');
         v_str := REPLACE(v_str, 'Ó', 'Ó');
         v_str := REPLACE(v_str, 'Ô', 'Ô');
         v_str := REPLACE(v_str, 'Õ', 'Õ');
         v_str := REPLACE(v_str, 'Ö', 'Ö');
         v_str := REPLACE(v_str, '×', '×');
         v_str := REPLACE(v_str, 'Ø', 'Ø');
         v_str := REPLACE(v_str, 'Ù', 'Ù');
         v_str := REPLACE(v_str, 'Ú', 'Ú');
         v_str := REPLACE(v_str, 'Û', 'Û');
         v_str := REPLACE(v_str, 'Ü', 'Ü');
         v_str := REPLACE(v_str, 'Ý', 'Ý');
         v_str := REPLACE(v_str, 'Þ', 'Þ');
         v_str := REPLACE(v_str, 'ß', 'ß');
         v_str := REPLACE(v_str, 'à', 'à');
         v_str := REPLACE(v_str, 'á', 'á');
         v_str := REPLACE(v_str, 'â', 'â');
         v_str := REPLACE(v_str, 'ã', 'ã');
         v_str := REPLACE(v_str, 'ä', 'ä');
         v_str := REPLACE(v_str, 'å', 'å');
         v_str := REPLACE(v_str, 'æ', 'æ');
         v_str := REPLACE(v_str, 'ç', 'ç');
         v_str := REPLACE(v_str, 'è', 'è');
         v_str := REPLACE(v_str, 'é', 'é');
         v_str := REPLACE(v_str, 'ê', 'ê');
         v_str := REPLACE(v_str, 'ë', 'ë');
         v_str := REPLACE(v_str, 'ì', 'ì');
         v_str := REPLACE(v_str, 'í', 'í');
         v_str := REPLACE(v_str, 'î', 'î');
         v_str := REPLACE(v_str, 'ï', 'ï');
         v_str := REPLACE(v_str, 'ð', 'ð');
         v_str := REPLACE(v_str, 'ñ', 'ñ');
         v_str := REPLACE(v_str, 'ò', 'ò');
         v_str := REPLACE(v_str, 'ó', 'ó');
         v_str := REPLACE(v_str, 'ô', 'ô');
         v_str := REPLACE(v_str, 'õ', 'õ');
         v_str := REPLACE(v_str, 'ö', 'ö');
         v_str := REPLACE(v_str, '÷', '÷');
         v_str := REPLACE(v_str, 'ø', 'ø');
         v_str := REPLACE(v_str, 'ù', 'ù');
         v_str := REPLACE(v_str, 'ú', 'ú');
         v_str := REPLACE(v_str, 'û', 'û');
         v_str := REPLACE(v_str, 'ü', 'ü');
         v_str := REPLACE(v_str, 'ý', 'ý');
         v_str := REPLACE(v_str, 'þ', 'þ');
         v_str := REPLACE(v_str, 'ÿ', 'ÿ');

         RETURN v_str;
      
      END escape_latin;

Is there a built in function I can use to make this cleaner and shorter?

Thanks,
Mike

 

[userMikeD]

Found a cleaner way with this:

FUNCTION escape_latin(p_str IN VARCHAR2) RETURN VARCHAR2 IS
     v_str  VARCHAR2(10000);
 BEGIN
     SELECT REGEXP_REPLACE(ASCIISTR(p_str), '\\(.{4})', '&#x\1;')
       INTO v_str
       FROM dual;
     RETURN v_str;
END escape_latin;