Convert Vietnamese from UTF8 to ASCII

If you need to convert from UTF8/Unicode Vietnamese with intonation/ascent signs like acute, grave, circumflex, tilde, dot below, hook above, and more to just plain old ASCII without any extras, or to VIRQ format. Here is a PHP class that performs the conversion. Some examples:

an toàn => an toan
áo giáp => ao giap
xúc phạm => xuc pham

Source Code: <?php /** * @author Son Nguyen * @since 3/3/2006 * @package Framework * @subpackage String */ class CStringVI { private $mTxt; private $mMap; /** constructor */ function __construct($pTxt) { $this->mTxt = $pTxt; $this->initMapping(); } /** from file vumaps.js in package vietuni8 */ function initMapping() { $this->mMap['Unicode'] = array( 97,226,259,101,234,105,111,244,417,117,432,121, 65,194,258,69,202,73,79,212,416,85,431,89, 225,7845,7855,233,7871,237,243,7889,7899,250,7913,253, 193,7844,7854,201,7870,205,211,7888,7898,218,7912,221, 224,7847,7857,232,7873,236,242,7891,7901,249,7915,7923, 192,7846,7856,200,7872,204,210,7890,7900,217,7914,7922, 7841,7853,7863,7865,7879,7883,7885,7897,7907,7909,7921,7925, 7840,7852,7862,7864,7878,7882,7884,7896,7906,7908,7920,7924, 7843,7849,7859,7867,7875,7881,7887,7893,7903,7911,7917,7927, 7842,7848,7858,7866,7874,7880,7886,7892,7902,7910,7916,7926, 227,7851,7861,7869,7877,297,245,7895,7905,361,7919,7929, 195,7850,7860,7868,7876,296,213,7894,7904,360,7918,7928, 100,273,68,272 ); $this->mMap['ASCII'] = array( 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'a','a','a','e','e','i','o','o','o','u','u','y', 'A','A','A','E','E','I','O','O','O','U','U','Y', 'd','d','D','D' ); $this->mMap['VIRQ'] = array( "a","a^","a(","e","e^","i","o","o^","o+","u","u+","y", "A","A^","A(","E","E^","I","O","O^","O+","U","U+", "Y", "a'","a^'","a('","e'","e^'","i'","o'","o^'","o+'","u'","u+'","y'", "A'","A^'","A('","E'","E^'","I'","O'","O^'","O+'","U'","U+'","Y'", "a`","a^`","a(`","e`","e^`","i`","o`","o^`","o+`","u`","u+`","y`", "A`","A^`","A(`","E`","E^`","I`","O`","O^`","O+`","U`","U+`","Y`", "a.","a^.","a(.","e.","e^.","i.","o.","o^.","o+.","u.","u+.","y.", "A.","A^.","A(.","E.","E^.","I.","O.","O^.","O+.","U.","U+.","Y.", "a?","a^?","a(?","e?","e^?","i?","o?","o^?","o+?","u?","u+?","y?", "A?","A^?","A(?","E?","E^?","I?","O?","O^?","O+?","U?","U+?","Y?", "a~","a^~","a(~","e~","e^~","i~","o~","o^~","o+~","u~","u+~","y~", "A~","A^~","A(~","E~","E^~","I~","O~","O^~","O+~","U~","U+~","Y~", "d","dd","D","DD" ); } /** check if it's in order */ private function between($pStart,$pVar,$pEnd) { return ($pVar>=$pStart && $pVar<=$pEnd); } /** map from one charset to another */ function map($pFrom,$pTo) { $vStr = $this->mTxt; $vLen = strlen($this->mTxt); $vOutput = ''; for ($i=0;$i<$vLen;$i++) { $vOrd = 0; $vOrds = array(); for ($j=0;$j<6;$j++) { //if ($i+$j<$vLen) { if (isset($vStr[$i+$j])) { $vOrds[$j] = ord($vStr[$i+$j]); } // fi } // rof // http://www1.tip.nl/~t876506/utf8tbl.html if ($this->between(0,$vOrds[0],127)) { $vOrd = $vOrds[0]; } elseif ($this->between(192,$vOrds[0],223)) { $vOrd = ($vOrds[0]-192)*64+($vOrds[1]-128); $i = $i+1; } elseif ($this->between(224,$vOrds[0],239)) { $vOrd = ($vOrds[0]-224)*4096+($vOrds[1]-128)*64+($vOrds[2]-128); $i = $i+2; } elseif ($this->between(240,$vOrds[0],247)) { $vOrd = ($vOrds[0]-240)*262144+($vOrds[1]-128)*4096+($vOrds[2]-128)*64+($vOrds[3]-128); $i = $i+3; } elseif ($this->between(248,$vOrds[0],251)) { $vOrd = ($vOrds[0]-248)*16777216+($vOrds[1]-128)*262144+($vOrds[2]-128)*4096+($vOrds[3]-128)*64+($vOrds[4]-128); $i = $i+4; } elseif ($this->between(252,$vOrds[0],253)) { $vOrd = ($vOrds[0]-252)*1073741824+($vOrds[1]-128)*16777216+($vOrds[2]-128)*262144+($vOrds[3]-128)*4096+($vOrds[4]-128)*64+($vOrds[5]-128); $i = $i+5; } elseif ($this->between(254,$vOrds[0],255)) { // error $vOrd = 0; } // fi if ($vOrd > 127 ) { $vKey = array_search($vOrd,$this->mMap[$pFrom]); $vOutput .= $this->mMap[$pTo][$vKey]; } else { $vOutput .= chr($vOrd); } // fi } // rof return $vOutput; } /** convert from utf8 to plain text ascii */ function uni2ascii() { return $this->map('Unicode','ASCII'); } } ?> Sample Usage: $vStr = new CStringVI('an toàn'); echo ($vStr->uni2ascii()); // prints out "an toan"