Unaccent a string


/ Published in: PHP
Save to your folder(s)

Unaccent a string.

An example string like ÀØėÿᾜὨζὅБю will be translated to AOeyIOzoBY.


Copy this code and paste it in your HTML
  1. /**
  2.  * Unaccent a string
  3.  *
  4.  * An example string like ÀØėÿᾜὨζὅБю will be translated to AOeyIOzoBY.
  5.  * More complete than :
  6.  *
  7.  * strtr(
  8.  * (string)$str,
  9.  * "ÀÁÂÃÄÅàáâãäåÒÓÔÕÖØòóôõöøÈÉÊËèéêëÇçÌÍÎÏìíîïÙÚÛÜùúûüÿÑñ",
  10.  * "aaaaaaaaaaaaooooooooooooeeeeeeeecciiiiiiiiuuuuuuuuynn"
  11.  * );
  12.  *
  13.  * @author http://www.evaisse.net/2008/php-translit-remove-accent-unaccent-21001
  14.  * @param $str input string
  15.  * @param $utf8 if null, function will detect input string encoding
  16.  * @return string input string without accent
  17.  */
  18. function removeAccents($str, $utf8 = true) {
  19. $str = (string) $str;
  20. if (is_null($utf8)) {
  21. if (!function_exists('mb_detect_encoding')) {
  22. $utf8 = (strtolower(mb_detect_encoding($str)) == 'utf-8');
  23. } else {
  24. $length = strlen($str);
  25. $utf8 = true;
  26.  
  27. for ($i = 0; $i < $length; $i++) {
  28. $c = ord($str[$i]);
  29.  
  30. if ($c < 0x80) $n = 0; // 0bbbbbbb
  31. elseif (($c & 0xE0) == 0xC0) $n = 1; // 110bbbbb
  32. elseif (($c & 0xF0) == 0xE0) $n = 2; // 1110bbbb
  33. elseif (($c & 0xF8) == 0xF0) $n = 3; // 11110bbb
  34. elseif (($c & 0xFC) == 0xF8) $n = 4; // 111110bb
  35. elseif (($c & 0xFE) == 0xFC) $n = 5; // 1111110b
  36. else return false; // Does not match any model
  37.  
  38. for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
  39. if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
  40. $utf8 = false;
  41. break;
  42. }
  43. }
  44. }
  45. }
  46. }
  47.  
  48. if (!$utf8) {
  49. $str = utf8_encode($str);
  50. }
  51.  
  52. $transliteration = array(
  53. 'IJ' => 'I', 'Ö' => 'O', 'Œ' => 'O', 'Ü' => 'U', 'ä' => 'a', 'æ' => 'a',
  54. 'ij' => 'i', 'ö' => 'o', 'œ' => 'o', 'ü' => 'u', 'ß' => 's', 'ſ' => 's',
  55. 'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A',
  56. 'Æ' => 'A', 'Ā' => 'A', 'Ą' => 'A', 'Ă' => 'A', 'Ç' => 'C', 'Ć' => 'C',
  57. 'Č' => 'C', 'Ĉ' => 'C', 'Ċ' => 'C', 'Ď' => 'D', 'Đ' => 'D', 'È' => 'E',
  58. 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ē' => 'E', 'Ę' => 'E', 'Ě' => 'E',
  59. 'Ĕ' => 'E', 'Ė' => 'E', 'Ĝ' => 'G', 'Ğ' => 'G', 'Ġ' => 'G', 'Ģ' => 'G',
  60. 'Ĥ' => 'H', 'Ħ' => 'H', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I',
  61. 'Ī' => 'I', 'Ĩ' => 'I', 'Ĭ' => 'I', 'Į' => 'I', 'İ' => 'I', 'Ĵ' => 'J',
  62. 'Ķ' => 'K', 'Ľ' => 'K', 'Ĺ' => 'K', 'Ļ' => 'K', 'Ŀ' => 'K', 'Ł' => 'L',
  63. 'Ñ' => 'N', 'Ń' => 'N', 'Ň' => 'N', 'Ņ' => 'N', 'Ŋ' => 'N', 'Ò' => 'O',
  64. 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ø' => 'O', 'Ō' => 'O', 'Ő' => 'O',
  65. 'Ŏ' => 'O', 'Ŕ' => 'R', 'Ř' => 'R', 'Ŗ' => 'R', 'Ś' => 'S', 'Ş' => 'S',
  66. 'Ŝ' => 'S', 'Ș' => 'S', 'Š' => 'S', 'Ť' => 'T', 'Ţ' => 'T', 'Ŧ' => 'T',
  67. 'Ț' => 'T', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ū' => 'U', 'Ů' => 'U',
  68. 'Ű' => 'U', 'Ŭ' => 'U', 'Ũ' => 'U', 'Ų' => 'U', 'Ŵ' => 'W', 'Ŷ' => 'Y',
  69. 'Ÿ' => 'Y', 'Ý' => 'Y', 'Ź' => 'Z', 'Ż' => 'Z', 'Ž' => 'Z', 'à' => 'a',
  70. 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ā' => 'a', 'ą' => 'a', 'ă' => 'a',
  71. 'å' => 'a', 'ç' => 'c', 'ć' => 'c', 'č' => 'c', 'ĉ' => 'c', 'ċ' => 'c',
  72. 'ď' => 'd', 'đ' => 'd', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e',
  73. 'Ä“' => 'e', 'Ä™' => 'e', 'Ä›' => 'e', 'Ä•' => 'e', 'Ä—' => 'e', 'Æ’' => 'f',
  74. 'ĝ' => 'g', 'ğ' => 'g', 'ġ' => 'g', 'ģ' => 'g', 'ĥ' => 'h', 'ħ' => 'h',
  75. 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ī' => 'i', 'ĩ' => 'i',
  76. 'ĭ' => 'i', 'į' => 'i', 'ı' => 'i', 'ĵ' => 'j', 'ķ' => 'k', 'ĸ' => 'k',
  77. 'ł' => 'l', 'ľ' => 'l', 'ĺ' => 'l', 'ļ' => 'l', 'ŀ' => 'l', 'ñ' => 'n',
  78. 'ń' => 'n', 'ň' => 'n', 'ņ' => 'n', 'ʼn' => 'n', 'ŋ' => 'n', 'ò' => 'o',
  79. 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ø' => 'o', 'ō' => 'o', 'ő' => 'o',
  80. 'ŏ' => 'o', 'ŕ' => 'r', 'ř' => 'r', 'ŗ' => 'r', 'ś' => 's', 'š' => 's',
  81. 'ť' => 't', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ū' => 'u', 'ů' => 'u',
  82. 'ű' => 'u', 'ŭ' => 'u', 'ũ' => 'u', 'ų' => 'u', 'ŵ' => 'w', 'ÿ' => 'y',
  83. 'ý' => 'y', 'ŷ' => 'y', 'ż' => 'z', 'ź' => 'z', 'ž' => 'z', 'Α' => 'A',
  84. 'Ά' => 'A', 'Ἀ' => 'A', 'Ἁ' => 'A', 'Ἂ' => 'A', 'Ἃ' => 'A', 'Ἄ' => 'A',
  85. 'Ἅ' => 'A', 'Ἆ' => 'A', 'Ἇ' => 'A', 'ᾈ' => 'A', 'ᾉ' => 'A', 'ᾊ' => 'A',
  86. 'ᾋ' => 'A', 'ᾌ' => 'A', 'ᾍ' => 'A', 'ᾎ' => 'A', 'ᾏ' => 'A', 'Ᾰ' => 'A',
  87. 'Ᾱ' => 'A', 'Ὰ' => 'A', 'ᾼ' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D',
  88. 'Ε' => 'E', 'Έ' => 'E', 'Ἐ' => 'E', 'Ἑ' => 'E', 'Ἒ' => 'E', 'Ἓ' => 'E',
  89. 'Ἔ' => 'E', 'Ἕ' => 'E', 'Ὲ' => 'E', 'Ζ' => 'Z', 'Η' => 'I', 'Ή' => 'I',
  90. 'Ἠ' => 'I', 'Ἡ' => 'I', 'Ἢ' => 'I', 'Ἣ' => 'I', 'Ἤ' => 'I', 'Ἥ' => 'I',
  91. 'Ἦ' => 'I', 'Ἧ' => 'I', 'ᾘ' => 'I', 'ᾙ' => 'I', 'ᾚ' => 'I', 'ᾛ' => 'I',
  92. 'ᾜ' => 'I', 'ᾝ' => 'I', 'ᾞ' => 'I', 'ᾟ' => 'I', 'Ὴ' => 'I', 'ῌ' => 'I',
  93. 'Θ' => 'T', 'Ι' => 'I', 'Ί' => 'I', 'Ϊ' => 'I', 'Ἰ' => 'I', 'Ἱ' => 'I',
  94. 'Ἲ' => 'I', 'Ἳ' => 'I', 'Ἴ' => 'I', 'Ἵ' => 'I', 'Ἶ' => 'I', 'Ἷ' => 'I',
  95. 'Ῐ' => 'I', 'Ῑ' => 'I', 'Ὶ' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M',
  96. 'Ν' => 'N', 'Ξ' => 'K', 'Ο' => 'O', 'Ό' => 'O', 'Ὀ' => 'O', 'Ὁ' => 'O',
  97. 'Ὂ' => 'O', 'Ὃ' => 'O', 'Ὄ' => 'O', 'Ὅ' => 'O', 'Ὸ' => 'O', 'Π' => 'P',
  98. 'Ρ' => 'R', 'Ῥ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Ύ' => 'Y',
  99. 'Ϋ' => 'Y', 'Ὑ' => 'Y', 'Ὓ' => 'Y', 'Ὕ' => 'Y', 'Ὗ' => 'Y', 'Ῠ' => 'Y',
  100. 'Ῡ' => 'Y', 'Ὺ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'P', 'Ω' => 'O',
  101. 'Ώ' => 'O', 'Ὠ' => 'O', 'Ὡ' => 'O', 'Ὢ' => 'O', 'Ὣ' => 'O', 'Ὤ' => 'O',
  102. 'Ὥ' => 'O', 'Ὦ' => 'O', 'Ὧ' => 'O', 'ᾨ' => 'O', 'ᾩ' => 'O', 'ᾪ' => 'O',
  103. 'ᾫ' => 'O', 'ᾬ' => 'O', 'ᾭ' => 'O', 'ᾮ' => 'O', 'ᾯ' => 'O', 'Ὼ' => 'O',
  104. 'ῼ' => 'O', 'α' => 'a', 'ά' => 'a', 'ἀ' => 'a', 'ἁ' => 'a', 'ἂ' => 'a',
  105. 'ἃ' => 'a', 'ἄ' => 'a', 'ἅ' => 'a', 'ἆ' => 'a', 'ἇ' => 'a', 'ᾀ' => 'a',
  106. 'ᾁ' => 'a', 'ᾂ' => 'a', 'ᾃ' => 'a', 'ᾄ' => 'a', 'ᾅ' => 'a', 'ᾆ' => 'a',
  107. 'ᾇ' => 'a', 'ὰ' => 'a', 'ᾰ' => 'a', 'ᾱ' => 'a', 'ᾲ' => 'a', 'ᾳ' => 'a',
  108. 'ᾴ' => 'a', 'ᾶ' => 'a', 'ᾷ' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd',
  109. 'ε' => 'e', 'έ' => 'e', 'ἐ' => 'e', 'ἑ' => 'e', 'ἒ' => 'e', 'ἓ' => 'e',
  110. 'ἔ' => 'e', 'ἕ' => 'e', 'ὲ' => 'e', 'ζ' => 'z', 'η' => 'i', 'ή' => 'i',
  111. 'ἠ' => 'i', 'ἡ' => 'i', 'ἢ' => 'i', 'ἣ' => 'i', 'ἤ' => 'i', 'ἥ' => 'i',
  112. 'ἦ' => 'i', 'ἧ' => 'i', 'ᾐ' => 'i', 'ᾑ' => 'i', 'ᾒ' => 'i', 'ᾓ' => 'i',
  113. 'ᾔ' => 'i', 'ᾕ' => 'i', 'ᾖ' => 'i', 'ᾗ' => 'i', 'ὴ' => 'i', 'ῂ' => 'i',
  114. 'ῃ' => 'i', 'ῄ' => 'i', 'ῆ' => 'i', 'ῇ' => 'i', 'θ' => 't', 'ι' => 'i',
  115. 'ί' => 'i', 'ϊ' => 'i', 'ΐ' => 'i', 'ἰ' => 'i', 'ἱ' => 'i', 'ἲ' => 'i',
  116. 'ἳ' => 'i', 'ἴ' => 'i', 'ἵ' => 'i', 'ἶ' => 'i', 'ἷ' => 'i', 'ὶ' => 'i',
  117. 'ῐ' => 'i', 'ῑ' => 'i', 'ῒ' => 'i', 'ῖ' => 'i', 'ῗ' => 'i', 'κ' => 'k',
  118. 'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => 'k', 'ο' => 'o', 'ό' => 'o',
  119. 'ὀ' => 'o', 'ὁ' => 'o', 'ὂ' => 'o', 'ὃ' => 'o', 'ὄ' => 'o', 'ὅ' => 'o',
  120. 'ὸ' => 'o', 'π' => 'p', 'ρ' => 'r', 'ῤ' => 'r', 'ῥ' => 'r', 'σ' => 's',
  121. 'ς' => 's', 'τ' => 't', 'υ' => 'y', 'ύ' => 'y', 'ϋ' => 'y', 'ΰ' => 'y',
  122. 'ὐ' => 'y', 'ὑ' => 'y', 'ὒ' => 'y', 'ὓ' => 'y', 'ὔ' => 'y', 'ὕ' => 'y',
  123. 'ὖ' => 'y', 'ὗ' => 'y', 'ὺ' => 'y', 'ῠ' => 'y', 'ῡ' => 'y', 'ῢ' => 'y',
  124. 'ῦ' => 'y', 'ῧ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'p', 'ω' => 'o',
  125. 'ώ' => 'o', 'ὠ' => 'o', 'ὡ' => 'o', 'ὢ' => 'o', 'ὣ' => 'o', 'ὤ' => 'o',
  126. 'ὥ' => 'o', 'ὦ' => 'o', 'ὧ' => 'o', 'ᾠ' => 'o', 'ᾡ' => 'o', 'ᾢ' => 'o',
  127. 'ᾣ' => 'o', 'ᾤ' => 'o', 'ᾥ' => 'o', 'ᾦ' => 'o', 'ᾧ' => 'o', 'ὼ' => 'o',
  128. 'ῲ' => 'o', 'ῳ' => 'o', 'ῴ' => 'o', 'ῶ' => 'o', 'ῷ' => 'o', 'А' => 'A',
  129. 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'E',
  130. 'Ж' => 'Z', 'З' => 'Z', 'И' => 'I', 'Й' => 'I', 'К' => 'K', 'Л' => 'L',
  131. 'М' => 'M', 'Н' => 'N', 'О' => 'O', 'П' => 'P', 'Р' => 'R', 'С' => 'S',
  132. 'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'K', 'Ц' => 'T', 'Ч' => 'C',
  133. 'Ш' => 'S', 'Щ' => 'S', 'Ы' => 'Y', 'Э' => 'E', 'Ю' => 'Y', 'Я' => 'Y',
  134. 'а' => 'A', 'б' => 'B', 'в' => 'V', 'г' => 'G', 'д' => 'D', 'е' => 'E',
  135. 'ё' => 'E', 'ж' => 'Z', 'з' => 'Z', 'и' => 'I', 'й' => 'I', 'к' => 'K',
  136. 'л' => 'L', 'м' => 'M', 'н' => 'N', 'о' => 'O', 'п' => 'P', 'р' => 'R',
  137. 'с' => 'S', 'т' => 'T', 'у' => 'U', 'ф' => 'F', 'х' => 'K', 'ц' => 'T',
  138. 'ч' => 'C', 'ш' => 'S', 'щ' => 'S', 'ы' => 'Y', 'э' => 'E', 'ю' => 'Y',
  139. 'я' => 'Y', 'ð' => 'd', 'Ð' => 'D', 'þ' => 't', 'Þ' => 'T', 'ა' => 'a',
  140. 'ბ' => 'b', 'გ' => 'g', 'დ' => 'd', 'ე' => 'e', 'ვ' => 'v', 'ზ' => 'z',
  141. 'თ' => 't', 'ი' => 'i', 'კ' => 'k', 'ლ' => 'l', 'მ' => 'm', 'ნ' => 'n',
  142. 'ო' => 'o', 'პ' => 'p', 'ჟ' => 'z', 'რ' => 'r', 'ს' => 's', 'ტ' => 't',
  143. 'უ' => 'u', 'ფ' => 'p', 'ქ' => 'k', 'ღ' => 'g', 'ყ' => 'q', 'შ' => 's',
  144. 'ჩ' => 'c', 'ც' => 't', 'ძ' => 'd', 'წ' => 't', 'ჭ' => 'c', 'ხ' => 'k',
  145. 'ჯ' => 'j', 'ჰ' => 'h',
  146. );
  147.  
  148. return str_replace(array_keys($transliteration), array_values($transliteration), $str);
  149. }

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.