Удалить акценты без использования iconv

Question

Каков наилучший способ удаления акцентов, например.

ÈâuÑ»становится "Eaun"

Без с использованием iconv

Answer 1

полный рабочий код. Я знаю, что это долго, но это верный выстрел способ, используемый Wordpress.

<?php 

function seems_utf8($str) 
{ 
    $length = strlen($str); 
    for ($i=0; $i < $length; $i++) { 
     $c = ord($str[$i]); 
     if ($c < 0x80) $n = 0; # 0bbbbbbb 
     elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb 
     elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb 
     elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb 
     elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb 
     elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b 
     else return false; # Does not match any model 
     for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? 
      if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) 
       return false; 
     } 
    } 
    return true; 
} 

/** 
* Converts all accent characters to ASCII characters. 
* 
* If there are no accent characters, then the string given is just returned. 
* 
* @param string $string Text that might have accent characters 
* @return string Filtered string with replaced "nice" characters. 
*/ 
function remove_accents($string) { 
    if (!preg_match('/[\x80-\xff]/', $string)) 
     return $string; 

    if (seems_utf8($string)) { 
     $chars = array(
     // Decompositions for Latin-1 Supplement 
     chr(195).chr(128) => 'A', chr(195).chr(129) => 'A', 
     chr(195).chr(130) => 'A', chr(195).chr(131) => 'A', 
     chr(195).chr(132) => 'A', chr(195).chr(133) => 'A', 
     chr(195).chr(135) => 'C', chr(195).chr(136) => 'E', 
     chr(195).chr(137) => 'E', chr(195).chr(138) => 'E', 
     chr(195).chr(139) => 'E', chr(195).chr(140) => 'I', 
     chr(195).chr(141) => 'I', chr(195).chr(142) => 'I', 
     chr(195).chr(143) => 'I', chr(195).chr(145) => 'N', 
     chr(195).chr(146) => 'O', chr(195).chr(147) => 'O', 
     chr(195).chr(148) => 'O', chr(195).chr(149) => 'O', 
     chr(195).chr(150) => 'O', chr(195).chr(153) => 'U', 
     chr(195).chr(154) => 'U', chr(195).chr(155) => 'U', 
     chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y', 
     chr(195).chr(159) => 's', chr(195).chr(160) => 'a', 
     chr(195).chr(161) => 'a', chr(195).chr(162) => 'a', 
     chr(195).chr(163) => 'a', chr(195).chr(164) => 'a', 
     chr(195).chr(165) => 'a', chr(195).chr(167) => 'c', 
     chr(195).chr(168) => 'e', chr(195).chr(169) => 'e', 
     chr(195).chr(170) => 'e', chr(195).chr(171) => 'e', 
     chr(195).chr(172) => 'i', chr(195).chr(173) => 'i', 
     chr(195).chr(174) => 'i', chr(195).chr(175) => 'i', 
     chr(195).chr(177) => 'n', chr(195).chr(178) => 'o', 
     chr(195).chr(179) => 'o', chr(195).chr(180) => 'o', 
     chr(195).chr(181) => 'o', chr(195).chr(182) => 'o', 
     chr(195).chr(182) => 'o', chr(195).chr(185) => 'u', 
     chr(195).chr(186) => 'u', chr(195).chr(187) => 'u', 
     chr(195).chr(188) => 'u', chr(195).chr(189) => 'y', 
     chr(195).chr(191) => 'y', 
     // Decompositions for Latin Extended-A 
     chr(196).chr(128) => 'A', chr(196).chr(129) => 'a', 
     chr(196).chr(130) => 'A', chr(196).chr(131) => 'a', 
     chr(196).chr(132) => 'A', chr(196).chr(133) => 'a', 
     chr(196).chr(134) => 'C', chr(196).chr(135) => 'c', 
     chr(196).chr(136) => 'C', chr(196).chr(137) => 'c', 
     chr(196).chr(138) => 'C', chr(196).chr(139) => 'c', 
     chr(196).chr(140) => 'C', chr(196).chr(141) => 'c', 
     chr(196).chr(142) => 'D', chr(196).chr(143) => 'd', 
     chr(196).chr(144) => 'D', chr(196).chr(145) => 'd', 
     chr(196).chr(146) => 'E', chr(196).chr(147) => 'e', 
     chr(196).chr(148) => 'E', chr(196).chr(149) => 'e', 
     chr(196).chr(150) => 'E', chr(196).chr(151) => 'e', 
     chr(196).chr(152) => 'E', chr(196).chr(153) => 'e', 
     chr(196).chr(154) => 'E', chr(196).chr(155) => 'e', 
     chr(196).chr(156) => 'G', chr(196).chr(157) => 'g', 
     chr(196).chr(158) => 'G', chr(196).chr(159) => 'g', 
     chr(196).chr(160) => 'G', chr(196).chr(161) => 'g', 
     chr(196).chr(162) => 'G', chr(196).chr(163) => 'g', 
     chr(196).chr(164) => 'H', chr(196).chr(165) => 'h', 
     chr(196).chr(166) => 'H', chr(196).chr(167) => 'h', 
     chr(196).chr(168) => 'I', chr(196).chr(169) => 'i', 
     chr(196).chr(170) => 'I', chr(196).chr(171) => 'i', 
     chr(196).chr(172) => 'I', chr(196).chr(173) => 'i', 
     chr(196).chr(174) => 'I', chr(196).chr(175) => 'i', 
     chr(196).chr(176) => 'I', chr(196).chr(177) => 'i', 
     chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij', 
     chr(196).chr(180) => 'J', chr(196).chr(181) => 'j', 
     chr(196).chr(182) => 'K', chr(196).chr(183) => 'k', 
     chr(196).chr(184) => 'k', chr(196).chr(185) => 'L', 
     chr(196).chr(186) => 'l', chr(196).chr(187) => 'L', 
     chr(196).chr(188) => 'l', chr(196).chr(189) => 'L', 
     chr(196).chr(190) => 'l', chr(196).chr(191) => 'L', 
     chr(197).chr(128) => 'l', chr(197).chr(129) => 'L', 
     chr(197).chr(130) => 'l', chr(197).chr(131) => 'N', 
     chr(197).chr(132) => 'n', chr(197).chr(133) => 'N', 
     chr(197).chr(134) => 'n', chr(197).chr(135) => 'N', 
     chr(197).chr(136) => 'n', chr(197).chr(137) => 'N', 
     chr(197).chr(138) => 'n', chr(197).chr(139) => 'N', 
     chr(197).chr(140) => 'O', chr(197).chr(141) => 'o', 
     chr(197).chr(142) => 'O', chr(197).chr(143) => 'o', 
     chr(197).chr(144) => 'O', chr(197).chr(145) => 'o', 
     chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe', 
     chr(197).chr(148) => 'R',chr(197).chr(149) => 'r', 
     chr(197).chr(150) => 'R',chr(197).chr(151) => 'r', 
     chr(197).chr(152) => 'R',chr(197).chr(153) => 'r', 
     chr(197).chr(154) => 'S',chr(197).chr(155) => 's', 
     chr(197).chr(156) => 'S',chr(197).chr(157) => 's', 
     chr(197).chr(158) => 'S',chr(197).chr(159) => 's', 
     chr(197).chr(160) => 'S', chr(197).chr(161) => 's', 
     chr(197).chr(162) => 'T', chr(197).chr(163) => 't', 
     chr(197).chr(164) => 'T', chr(197).chr(165) => 't', 
     chr(197).chr(166) => 'T', chr(197).chr(167) => 't', 
     chr(197).chr(168) => 'U', chr(197).chr(169) => 'u', 
     chr(197).chr(170) => 'U', chr(197).chr(171) => 'u', 
     chr(197).chr(172) => 'U', chr(197).chr(173) => 'u', 
     chr(197).chr(174) => 'U', chr(197).chr(175) => 'u', 
     chr(197).chr(176) => 'U', chr(197).chr(177) => 'u', 
     chr(197).chr(178) => 'U', chr(197).chr(179) => 'u', 
     chr(197).chr(180) => 'W', chr(197).chr(181) => 'w', 
     chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y', 
     chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z', 
     chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z', 
     chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z', 
     chr(197).chr(190) => 'z', chr(197).chr(191) => 's', 
     // Euro Sign 
     chr(226).chr(130).chr(172) => 'E', 
     // GBP (Pound) Sign 
     chr(194).chr(163) => ''); 

     $string = strtr($string, $chars); 
    } else { 
     // Assume ISO-8859-1 if not UTF-8 
     $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158) 
      .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194) 
      .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202) 
      .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210) 
      .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218) 
      .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227) 
      .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235) 
      .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243) 
      .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251) 
      .chr(252).chr(253).chr(255); 

     $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy"; 

     $string = strtr($string, $chars['in'], $chars['out']); 
     $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254)); 
     $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); 
     $string = str_replace($double_chars['in'], $double_chars['out'], $string); 
    } 

    return $string; 
} 


$str = "ÈâuÑ"; 
echo remove_accents($str); // Output: EauN 
?> 

Answer 2

Проще говоря:

$text = "ÈâuÑ foo bar 88."; 
var_dump(preg_replace('/\p{M}/u', '', 
    Normalizer::normalize($text, Normalizer::FORM_D))); 

дает:

string(16) "EauN foo bar 88." 

Идея заключается в том, чтобы разложить символы в виде где они на самом деле два Unicode кода единицы, с отдельным один для акцентов. Затем вы удаляете эти акценты.

\p{M}means «персонаж, предназначенный для сочетания с другим персонажем (например, акценты, умлауты, закрывающие коробки и т. Д.)».

Обратите внимание, что это не окончательное решение. Это может быть достаточно для ввода текста, который у вас есть, но многие символы, такие как ø, не разлагаются, поэтому этот метод не удастся.

Answer 3

Или попробуйте эту функцию (с str_replace и исчерпывающее таблицы акцентов): http://idilix.net/php-strip-accents.php

Answer 4

Я написал это в PHP. Надеюсь, это поможет кому-то. Это позволяет мне использовать iconv.

// 
// This function takes a string with international accented characters and anglicizes it. 
// For example, "Hafþór Júlíus Björnsson" becomes "Hafthor Julius Bjornsson" 
// 

function anglicize($string) { 
$accented = array("À","Á","Â","Ã","Ä","Å","Æ", "Ç","È","É","Ê","Ë","Ì","Í","Î","Ï","Ð","Ñ","Ò","Ó","Ô","Õ","Ö","Ø","Ù","Ú","Û","Ü","Þ", "ß", "à","á","â","ã","ä","å","æ", "ç","è","é","ê","ë","ì","í","î","ï","ð","ñ","ò","ó","ô","õ","ö","ø","ù","ú","û","ü","þ", "Ā","ā","Ă","ă","Ą","ą","Ć","ć","Ĉ","ĉ","Ċ","ċ","Č","č","Ď","ď","Đ","đ","Ē","ē","Ĕ","ĕ","Ė","ė","Ę","ę","Ě","ě","Ĝ","ĝ","Ğ","ğ","Ġ","ġ","Ģ","ģ","Ĥ","ĥ","Ħ","ħ","Ĩ","ĩ","Ī","ī","Ĭ","ĭ","Į","į","İ","ı","IJ", "ij", "Ĵ","ĵ","Ķ","ķ","Ĺ","ĺ","Ļ","ļ","Ľ","ľ","Ŀ","ŀ","Ł","ł","Ń","ń","Ņ","ņ","Ň","ň","ʼn","Ō","ō","Ŏ","ŏ","Ő","ő","Œ", "œ", "Ŕ","ŕ","Ŗ","ŗ","Ř","ř","Ś","ś","Ŝ","ŝ","Ş","ş","Š","š","Ţ","ţ","Ť","ť","Ŧ","ŧ","Ũ","ũ","Ū","ū","Ŭ","ŭ","Ů","ů","Ű","ű","Ų","ų","ſ","ƒ","DŽ", "Dž", "dž", "LJ", "Lj", "lj", "NJ", "Nj", "nj", "DZ", "Dz", "dz", "Ș","ș","Ț","ț","Ḁ","ḁ","Ḃ","ḃ","Ḅ","ḅ","Ḇ","ḇ","Ḉ","ḉ","Ḋ","ḋ","Ḍ","ḍ","Ḏ","ḏ","Ḑ","ḑ","Ḓ","ḓ","Ḕ","ḕ","Ḗ","ḗ","Ḙ","ḙ","Ḛ","ḛ","Ḝ","ḝ","Ḟ","ḟ","Ḡ","ḡ","Ḣ","ḣ","Ḥ","ḥ","Ḧ","ḧ","Ḩ","ḩ","Ḫ","ḫ","Ḭ","ḭ","Ḯ","ḯ","Ḱ","ḱ","Ḳ","ḳ","Ḵ","ḵ","Ḷ","ḷ","Ḹ","ḹ","Ḻ","ḻ","Ḽ","ḽ","Ḿ","ḿ","Ṁ","ṁ","Ṃ","ṃ","Ṅ","ṅ","Ṇ","ṇ","Ṉ","ṉ","Ṋ","ṋ","Ṍ","ṍ","Ṏ","ṏ","Ṑ","ṑ","Ṓ","ṓ","Ṕ","ṕ","Ṗ","ṗ","Ṙ","ṙ","Ṛ","ṛ","Ṝ","ṝ","Ṟ","ṟ","Ṡ","ṡ","Ṣ","ṣ","Ṥ","ṥ","Ṧ","ṧ","Ṩ","ṩ","Ṫ","ṫ","Ṭ","ṭ","Ṯ","ṯ","Ṱ","ṱ","Ṳ","ṳ","Ṵ","ṵ","Ṷ","ṷ","Ṹ","ṹ","Ṻ","ṻ","Ṽ","ṽ","Ṿ","ṿ","Ẁ","ẁ","Ẃ","ẃ","Ẅ","ẅ","Ẇ","ẇ","Ẉ","ẉ","Ẋ","ẋ","Ẍ","ẍ","Ẏ","ẏ","Ẑ","ẑ","Ẓ","ẓ","Ẕ","ẕ","ẖ","ẗ","ẘ","ẙ","ẚ","ẞ","Ạ","ạ","Ả","ả","Ấ","ấ","Ầ","ầ","Ẩ","ẩ","Ẫ","ẫ","Ậ","ậ","Ắ","ắ","Ằ","ằ","Ẳ","ẳ","Ẵ","ẵ","Ặ","ặ","Ẹ","ẹ","Ẻ","ẻ","Ẽ","ẽ","Ế","ế","Ề","ề","Ể","ể","Ễ","ễ","Ệ","ệ","Ỉ","ỉ","Ị","ị","Ọ","ọ","Ỏ","ỏ","Ố","ố","Ồ","ồ","Ổ","ổ","Ỗ","ỗ","Ộ","ộ","Ớ","ớ","Ờ","ờ","Ở","ở","Ỡ","ỡ","Ợ","ợ","Ụ","ụ","Ủ","ủ","Ứ","ứ","Ừ","ừ","Ử","ử","Ữ","ữ","Ự","ự","Ỳ","ỳ","Ỵ","ỵ","Ỷ","ỷ","Ỹ","ỹ"); 
$nonaccented = array("A","A","A","A","A","A","AE","C","E","E","E","E","I","I","I","I","D","N","O","O","O","O","O","O","U","U","U","U","Th","ss","a","a","a","a","a","a","ae","c","e","e","e","e","i","i","i","i","d","n","o","o","o","o","o","o","u","u","u","u","th","A","a","A","a","A","a","C","c","C","c","C","c","C","c","D","d","D","d","E","e","E","e","E","e","E","e","E","e","G","g","G","g","G","g","G","g","H","h","H","h","I","i","I","i","I","i","I","i","I","i","IJ","ij","J","j","K","k","L","l","L","l","L","l","L","l","L","l","N","n","N","n","N","n","n","O","o","O","o","O","o","OE","oe","R","r","R","r","R","r","S","s","S","s","S","s","S","s","T","t","T","t","T","t","U","u","U","u","U","u","U","u","U","u","U","u","s","f","DZ","Dz","dz","LJ","Lj","lj","NJ","Nj","nj","DZ","Dz","dz","S","s","T","t","A","a","B","b","B","b","B","b","C","c","D","d","D","d","D","d","D","d","D","d","E","e","E","e","E","e","E","e","E","e","F","f","G","g","H","h","H","h","H","h","H","h","H","h","I","i","I","i","K","k","K","k","K","k","L","l","L","l","L","l","L","l","M","m","M","m","M","m","N","n","N","n","N","n","N","n","O","o","O","o","O","o","O","o","P","p","P","p","R","r","R","r","R","r","R","r","S","s","S","s","S","s","S","s","S","s","T","t","T","t","T","t","T","t","U","u","U","u","U","u","U","u","U","u","V","v","V","v","W","w","W","w","W","w","W","w","W","w","X","x","X","x","Y","y","Z","z","Z","z","Z","z","h","t","w","y","a","B","A","a","A","a","A","a","A","a","A","a","A","a","A","a","A","a","A","a","A","a","A","a","A","a","E","e","E","e","E","e","E","e","E","e","E","e","E","e","E","e","I","i","I","i","O","o","O","o","O","o","O","o","O","o","O","o","O","o","O","o","O","o","O","o","O","o","O","o","U","u","U","u","U","u","U","u","U","u","U","u","U","u","Y","y","Y","y","Y","y","Y","y"); 
return str_replace($accented,$nonaccented,$string); 
}