[Summary view] [Print] [Text view]

   1  <?php
   2  /**
   3  * An open source library
   4  * http://sourceforge.net/projects/phputf8
   5  * PHP UTF-8 is a UTF-8 aware library of functions mirroring PHP's own string functions.
   6  * Does not require PHP mbstring extension though will use it, if found, for a (small) performance gain.  
   7  *
   8  */
   9  
  10  // wordpress stuff
  11  function seems_utf8($Str) { # by bmorel at ssi dot fr
  12      for ($i=0; $i<strlen($Str); $i++) {
  13          if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
  14          elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
  15          elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
  16          elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
  17          elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
  18          elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
  19          else return false; # Does not match any model
  20          for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
  21              if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
  22              return false;
  23          }
  24      }
  25      return true;
  26  }
  27  
  28  function remove_accents($string) {
  29      if ( !preg_match('/[\x80-\xff]/', $string) )
  30          return $string;
  31  
  32      if (seems_utf8($string)) {
  33          $chars = array(
  34          // Decompositions for Latin-1 Supplement
  35          chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
  36          chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
  37          chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
  38          chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
  39          chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
  40          chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
  41          chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
  42          chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
  43          chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
  44          chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
  45          chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
  46          chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
  47          chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
  48          chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
  49          chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
  50          chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
  51          chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
  52          chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
  53          chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
  54          chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
  55          chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
  56          chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
  57          chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
  58          chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
  59          chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
  60          chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
  61          chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
  62          chr(195).chr(191) => 'y',
  63          // Decompositions for Latin Extended-A
  64          chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
  65          chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
  66          chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
  67          chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
  68          chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
  69          chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
  70          chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
  71          chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
  72          chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
  73          chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
  74          chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
  75          chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
  76          chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
  77          chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
  78          chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
  79          chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
  80          chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
  81          chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
  82          chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
  83          chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
  84          chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
  85          chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
  86          chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
  87          chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
  88          chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
  89          chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
  90          chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
  91          chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
  92          chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
  93          chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
  94          chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
  95          chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
  96          chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
  97          chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
  98          chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
  99          chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
 100          chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
 101          chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
 102          chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
 103          chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
 104          chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
 105          chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
 106          chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
 107          chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
 108          chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
 109          chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
 110          chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
 111          chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
 112          chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
 113          chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
 114          chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
 115          chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
 116          chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
 117          chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
 118          chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
 119          chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
 120          chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
 121          chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
 122          chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
 123          chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
 124          chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
 125          chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
 126          chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
 127          chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
 128          // Euro Sign
 129          chr(226).chr(130).chr(172) => 'E',
 130          // GBP (Pound) Sign
 131          chr(194).chr(163) => '');
 132  
 133          $string = strtr($string, $chars);
 134      } else {
 135          // Assume ISO-8859-1 if not UTF-8
 136          $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
 137              .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
 138              .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
 139              .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
 140              .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
 141              .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
 142              .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
 143              .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
 144              .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
 145              .chr(252).chr(253).chr(255);
 146  
 147          $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
 148  
 149          $string = strtr($string, $chars['in'], $chars['out']);
 150          $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
 151          $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
 152          $string = str_replace($double_chars['in'], $double_chars['out'], $string);
 153      }
 154  
 155      return $string;
 156  }
 157  
 158  function pre_remove_accents($string) {
 159  
 160      $string = strtr($string,    array('Þ' => 'TH', 'þ' => 'th', 'Ð' => 'DH', 'ð' => 'dh', 'ß' => 'ss',
 161                                        'Œ' => 'OE', 'œ' => 'oe', 'Æ' => 'AE', 'æ' => 'ae', 'µ' => 'u',
 162                                        'Ä' => 'AE', 'Ü' => 'UE', 'Ö' => 'OE', 'ä' => 'ae', 'ü' => 'ue',
 163                                        'ö' => 'oe' )    );
 164      $string = strtr($string,    'ŠŽšžŸÀÁÂÃÅÇÈÉÊËÌÍÎÏÑÒÓÔÕØÙÚÛÝàáâãåçèéêëìíîïñòóôõøùúûýÿ',
 165                                  'SZszYAAAAACEEEEIIIINOOOOOUUUYaaaaaceeeeiiiinooooouuuyy');
 166      return $string;
 167  }
 168  
 169  
 170  ?>