Replacing accented characters php
I am trying to replace accented characters with the normal replacements. Below is what I am currently doing.
$string = \"Éric Cantona\";
$strict = st
-
This worked for me:
<?php setlocale(LC_ALL, "en_US.utf8"); $val = iconv('UTF-8','ASCII//TRANSLIT',$val); ?>讨论(0) -
As an alternative (a bit more complex in nature through), have a look at how wordpress does accent removal. Made some changes below to make it run independently without referencing wordpress functions.
function mbstring_binary_safe_encoding($reset = false) { static $encodings = array(); static $overloaded = null; if (is_null($overloaded)) { $overloaded = function_exists('mb_internal_encoding') && (ini_get('mbstring.func_overload') & 2); } if (false === $overloaded) { return; } if (!$reset) { $encoding = mb_internal_encoding(); array_push($encodings, $encoding); mb_internal_encoding('ISO-8859-1'); } if ($reset && $encodings) { $encoding = array_pop($encodings); mb_internal_encoding($encoding); } } function seems_utf8($str) { mbstring_binary_safe_encoding(); $length = strlen($str); mbstring_binary_safe_encoding(true); 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[$i]) & 0xC0) != 0x80)) { return false; } } } return true; } function remove_accents($string) { if (!preg_match('/[\x80-\xff]/', $string)) { return $string; } if (seems_utf8($string)) { $chars = array( // Decompositions for Latin-1 Supplement 'ª' => 'a', 'º' => 'o', 'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE', 'Ç' => 'C', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I', 'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ý' => 'Y', 'Þ' => 'TH', 'ß' => 's', 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a', 'å' => 'a', 'æ' => 'ae', 'ç' => 'c', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ð' => 'd', 'ñ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ø' => 'o', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', 'ý' => 'y', 'þ' => 'th', 'ÿ' => 'y', 'Ø' => 'O', // Decompositions for Latin Extended-A 'Ā' => 'A', 'ā' => 'a', 'Ă' => 'A', 'ă' => 'a', 'Ą' => 'A', 'ą' => 'a', 'Ć' => 'C', 'ć' => 'c', 'Ĉ' => 'C', 'ĉ' => 'c', 'Ċ' => 'C', 'ċ' => 'c', 'Č' => 'C', 'č' => 'c', 'Ď' => 'D', 'ď' => 'd', 'Đ' => 'D', 'đ' => 'd', 'Ē' => 'E', 'ē' => 'e', 'Ĕ' => 'E', 'ĕ' => 'e', 'Ė' => 'E', 'ė' => 'e', 'Ę' => 'E', 'ę' => 'e', 'Ě' => 'E', 'ě' => 'e', 'Ĝ' => 'G', 'ĝ' => 'g', 'Ğ' => 'G', 'ğ' => 'g', 'Ġ' => 'G', 'ġ' => 'g', 'Ģ' => 'G', 'ģ' => 'g', 'Ĥ' => 'H', 'ĥ' => 'h', 'Ħ' => 'H', 'ħ' => 'h', 'Ĩ' => 'I', 'ĩ' => 'i', 'Ī' => 'I', 'ī' => 'i', 'Ĭ' => 'I', 'ĭ' => 'i', 'Į' => 'I', 'į' => 'i', 'İ' => 'I', 'ı' => 'i', 'IJ' => 'IJ', 'ij' => 'ij', 'Ĵ' => 'J', 'ĵ' => 'j', 'Ķ' => 'K', 'ķ' => 'k', 'ĸ' => 'k', 'Ĺ' => 'L', 'ĺ' => 'l', 'Ļ' => 'L', 'ļ' => 'l', 'Ľ' => 'L', 'ľ' => 'l', 'Ŀ' => 'L', 'ŀ' => 'l', 'Ł' => 'L', 'ł' => 'l', 'Ń' => 'N', 'ń' => 'n', 'Ņ' => 'N', 'ņ' => 'n', 'Ň' => 'N', 'ň' => 'n', 'ʼn' => 'n', 'Ŋ' => 'N', 'ŋ' => 'n', 'Ō' => 'O', 'ō' => 'o', 'Ŏ' => 'O', 'ŏ' => 'o', 'Ő' => 'O', 'ő' => 'o', 'Œ' => 'OE', 'œ' => 'oe', 'Ŕ' => 'R', 'ŕ' => 'r', 'Ŗ' => 'R', 'ŗ' => 'r', 'Ř' => 'R', 'ř' => 'r', 'Ś' => 'S', 'ś' => 's', 'Ŝ' => 'S', 'ŝ' => 's', 'Ş' => 'S', 'ş' => 's', 'Š' => 'S', 'š' => 's', 'Ţ' => 'T', 'ţ' => 't', 'Ť' => 'T', 'ť' => 't', 'Ŧ' => 'T', 'ŧ' => 't', 'Ũ' => 'U', 'ũ' => 'u', 'Ū' => 'U', 'ū' => 'u', 'Ŭ' => 'U', 'ŭ' => 'u', 'Ů' => 'U', 'ů' => 'u', 'Ű' => 'U', 'ű' => 'u', 'Ų' => 'U', 'ų' => 'u', 'Ŵ' => 'W', 'ŵ' => 'w', 'Ŷ' => 'Y', 'ŷ' => 'y', 'Ÿ' => 'Y', 'Ź' => 'Z', 'ź' => 'z', 'Ż' => 'Z', 'ż' => 'z', 'Ž' => 'Z', 'ž' => 'z', 'ſ' => 's', // Decompositions for Latin Extended-B 'Ș' => 'S', 'ș' => 's', 'Ț' => 'T', 'ț' => 't', // Euro Sign '€' => 'E', // GBP (Pound) Sign '£' => '', // Vowels with diacritic (Vietnamese) // unmarked 'Ơ' => 'O', 'ơ' => 'o', 'Ư' => 'U', 'ư' => 'u', // grave accent 'Ầ' => 'A', 'ầ' => 'a', 'Ằ' => 'A', 'ằ' => 'a', 'Ề' => 'E', 'ề' => 'e', 'Ồ' => 'O', 'ồ' => 'o', 'Ờ' => 'O', 'ờ' => 'o', 'Ừ' => 'U', 'ừ' => 'u', 'Ỳ' => 'Y', 'ỳ' => 'y', // hook 'Ả' => 'A', 'ả' => 'a', 'Ẩ' => 'A', 'ẩ' => 'a', 'Ẳ' => 'A', 'ẳ' => 'a', 'Ẻ' => 'E', 'ẻ' => 'e', 'Ể' => 'E', 'ể' => 'e', 'Ỉ' => 'I', 'ỉ' => 'i', 'Ỏ' => 'O', 'ỏ' => 'o', 'Ổ' => 'O', 'ổ' => 'o', 'Ở' => 'O', 'ở' => 'o', 'Ủ' => 'U', 'ủ' => 'u', 'Ử' => 'U', 'ử' => 'u', 'Ỷ' => 'Y', 'ỷ' => 'y', // tilde 'Ẫ' => 'A', 'ẫ' => 'a', 'Ẵ' => 'A', 'ẵ' => 'a', 'Ẽ' => 'E', 'ẽ' => 'e', 'Ễ' => 'E', 'ễ' => 'e', 'Ỗ' => 'O', 'ỗ' => 'o', 'Ỡ' => 'O', 'ỡ' => 'o', 'Ữ' => 'U', 'ữ' => 'u', 'Ỹ' => 'Y', 'ỹ' => 'y', // acute accent 'Ấ' => 'A', 'ấ' => 'a', 'Ắ' => 'A', 'ắ' => 'a', 'Ế' => 'E', 'ế' => 'e', 'Ố' => 'O', 'ố' => 'o', 'Ớ' => 'O', 'ớ' => 'o', 'Ứ' => 'U', 'ứ' => 'u', // dot below 'Ạ' => 'A', 'ạ' => 'a', 'Ậ' => 'A', 'ậ' => 'a', 'Ặ' => 'A', 'ặ' => 'a', 'Ẹ' => 'E', 'ẹ' => 'e', 'Ệ' => 'E', 'ệ' => 'e', 'Ị' => 'I', 'ị' => 'i', 'Ọ' => 'O', 'ọ' => 'o', 'Ộ' => 'O', 'ộ' => 'o', 'Ợ' => 'O', 'ợ' => 'o', 'Ụ' => 'U', 'ụ' => 'u', 'Ự' => 'U', 'ự' => 'u', 'Ỵ' => 'Y', 'ỵ' => 'y', // Vowels with diacritic (Chinese, Hanyu Pinyin) 'ɑ' => 'a', // macron 'Ǖ' => 'U', 'ǖ' => 'u', // acute accent 'Ǘ' => 'U', 'ǘ' => 'u', // caron 'Ǎ' => 'A', 'ǎ' => 'a', 'Ǐ' => 'I', 'ǐ' => 'i', 'Ǒ' => 'O', 'ǒ' => 'o', 'Ǔ' => 'U', 'ǔ' => 'u', 'Ǚ' => 'U', 'ǚ' => 'u', // grave accent 'Ǜ' => 'U', 'ǜ' => 'u', ); $string = strtr($string, $chars); } else { $chars = array(); // Assume ISO-8859-1 if not UTF-8 $chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e" . "\x9f\xa2\xa5\xb5\xc0\xc1\xc2" . "\xc3\xc4\xc5\xc7\xc8\xc9\xca" . "\xcb\xcc\xcd\xce\xcf\xd1\xd2" . "\xd3\xd4\xd5\xd6\xd8\xd9\xda" . "\xdb\xdc\xdd\xe0\xe1\xe2\xe3" . "\xe4\xe5\xe7\xe8\xe9\xea\xeb" . "\xec\xed\xee\xef\xf1\xf2\xf3" . "\xf4\xf5\xf6\xf8\xf9\xfa\xfb" . "\xfc\xfd\xff"; $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy"; $string = strtr($string, $chars['in'], $chars['out']); $double_chars = array(); $double_chars['in'] = array("\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe"); $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); $string = str_replace($double_chars['in'], $double_chars['out'], $string); } return $string; }讨论(0) -
I know, that question has been asked a long long time ago...
I was looking for a short and elegant solution, but couldn't find satisfaction for two reasons:
First, most of the existing solutions replace a list of characters by a list of other characters. Unfortunately, it require to use a specific encoding for the php script file itself which might be unwanted.
Second, using iconv seems to be a good way, but it's not enough as the result of a converted character could be one or two characters, or a Fatal Exception.
So I wrote that small function which does the job :
function replaceAccent($string, $replacement = '_') { $alnumPattern = '/^[a-zA-Z0-9 ]+$/'; if (preg_match($alnumPattern, $string)) { return $string; } $ret = array_map( function ($chr) use ($alnumPattern, $replacement) { if (preg_match($alnumPattern, $chr)) { return $chr; } else { $chr = @iconv('ISO-8859-1', 'ASCII//TRANSLIT', $chr); if (strlen($chr) == 1) { return $chr; } elseif (strlen($chr) > 1) { $ret = ''; foreach (str_split($chr) as $char2) { if (preg_match($alnumPattern, $char2)) { $ret .= $char2; } } return $ret; } else { // replace whatever iconv fail to convert by something else return $replacement; } } }, str_split($string) ); return implode($ret); }讨论(0) -
You can use PHP strtr() function to get rid of accented characters :
$string = "Éric Cantona"; $accented_array = array('Š'=>'S', 'š'=>'s', 'Ž'=>'Z', 'ž'=>'z', 'À'=>'A', 'Á'=>'A', 'Â'=>'A', 'Ã'=>'A', 'Ä'=>'A', 'Å'=>'A', 'Æ'=>'A', 'Ç'=>'C', 'È'=>'E', 'É'=>'E','Ê'=>'E', 'Ë'=>'E', 'Ì'=>'I', 'Í'=>'I', 'Î'=>'I', 'Ï'=>'I', 'Ñ'=>'N', 'Ò'=>'O', 'Ó'=>'O', 'Ô'=>'O', 'Õ'=>'O', 'Ö'=>'O', 'Ø'=>'O', 'Ù'=>'U','Ú'=>'U', 'Û'=>'U', 'Ü'=>'U', 'Ý'=>'Y', 'Þ'=>'B', 'ß'=>'Ss', 'à'=>'a', 'á'=>'a', 'â'=>'a', 'ã'=>'a', 'ä'=>'a', 'å'=>'a', 'æ'=>'a', 'ç'=>'c','è'=>'e', 'é'=>'e', 'ê'=>'e', 'ë'=>'e', 'ì'=>'i', 'í'=>'i', 'î'=>'i', 'ï'=>'i', 'ð'=>'o', 'ñ'=>'n', 'ò'=>'o', 'ó'=>'o', 'ô'=>'o', 'õ'=>'o','ö'=>'o', 'ø'=>'o', 'ù'=>'u', 'ú'=>'u', 'û'=>'u', 'ý'=>'y', 'þ'=>'b', 'ÿ'=>'y' ); $required_str = strtr( $string, $accented_array );讨论(0) -
An updated answer based on @BurninLeo's answer
function replace_spec_char($subject) { $char_map = array( "ъ" => "-", "ь" => "-", "Ъ" => "-", "Ь" => "-", "А" => "A", "Ă" => "A", "Ǎ" => "A", "Ą" => "A", "À" => "A", "Ã" => "A", "Á" => "A", "Æ" => "A", "Â" => "A", "Å" => "A", "Ǻ" => "A", "Ā" => "A", "א" => "A", "Б" => "B", "ב" => "B", "Þ" => "B", "Ĉ" => "C", "Ć" => "C", "Ç" => "C", "Ц" => "C", "צ" => "C", "Ċ" => "C", "Č" => "C", "©" => "C", "ץ" => "C", "Д" => "D", "Ď" => "D", "Đ" => "D", "ד" => "D", "Ð" => "D", "È" => "E", "Ę" => "E", "É" => "E", "Ë" => "E", "Ê" => "E", "Е" => "E", "Ē" => "E", "Ė" => "E", "Ě" => "E", "Ĕ" => "E", "Є" => "E", "Ə" => "E", "ע" => "E", "Ф" => "F", "Ƒ" => "F", "Ğ" => "G", "Ġ" => "G", "Ģ" => "G", "Ĝ" => "G", "Г" => "G", "ג" => "G", "Ґ" => "G", "ח" => "H", "Ħ" => "H", "Х" => "H", "Ĥ" => "H", "ה" => "H", "I" => "I", "Ï" => "I", "Î" => "I", "Í" => "I", "Ì" => "I", "Į" => "I", "Ĭ" => "I", "I" => "I", "И" => "I", "Ĩ" => "I", "Ǐ" => "I", "י" => "I", "Ї" => "I", "Ī" => "I", "І" => "I", "Й" => "J", "Ĵ" => "J", "ĸ" => "K", "כ" => "K", "Ķ" => "K", "К" => "K", "ך" => "K", "Ł" => "L", "Ŀ" => "L", "Л" => "L", "Ļ" => "L", "Ĺ" => "L", "Ľ" => "L", "ל" => "L", "מ" => "M", "М" => "M", "ם" => "M", "Ñ" => "N", "Ń" => "N", "Н" => "N", "Ņ" => "N", "ן" => "N", "Ŋ" => "N", "נ" => "N", "ʼn" => "N", "Ň" => "N", "Ø" => "O", "Ó" => "O", "Ò" => "O", "Ô" => "O", "Õ" => "O", "О" => "O", "Ő" => "O", "Ŏ" => "O", "Ō" => "O", "Ǿ" => "O", "Ǒ" => "O", "Ơ" => "O", "פ" => "P", "ף" => "P", "П" => "P", "ק" => "Q", "Ŕ" => "R", "Ř" => "R", "Ŗ" => "R", "ר" => "R", "Р" => "R", "®" => "R", "Ş" => "S", "Ś" => "S", "Ș" => "S", "Š" => "S", "С" => "S", "Ŝ" => "S", "ס" => "S", "Т" => "T", "Ț" => "T", "ט" => "T", "Ŧ" => "T", "ת" => "T", "Ť" => "T", "Ţ" => "T", "Ù" => "U", "Û" => "U", "Ú" => "U", "Ū" => "U", "У" => "U", "Ũ" => "U", "Ư" => "U", "Ǔ" => "U", "Ų" => "U", "Ŭ" => "U", "Ů" => "U", "Ű" => "U", "Ǖ" => "U", "Ǜ" => "U", "Ǚ" => "U", "Ǘ" => "U", "В" => "V", "ו" => "V", "Ý" => "Y", "Ы" => "Y", "Ŷ" => "Y", "Ÿ" => "Y", "Ź" => "Z", "Ž" => "Z", "Ż" => "Z", "З" => "Z", "ז" => "Z", "а" => "a", "ă" => "a", "ǎ" => "a", "ą" => "a", "à" => "a", "ã" => "a", "á" => "a", "æ" => "a", "â" => "a", "å" => "a", "ǻ" => "a", "ā" => "a", "א" => "a", "б" => "b", "ב" => "b", "þ" => "b", "ĉ" => "c", "ć" => "c", "ç" => "c", "ц" => "c", "צ" => "c", "ċ" => "c", "č" => "c", "©" => "c", "ץ" => "c", "Ч" => "ch", "ч" => "ch", "д" => "d", "ď" => "d", "đ" => "d", "ד" => "d", "ð" => "d", "è" => "e", "ę" => "e", "é" => "e", "ë" => "e", "ê" => "e", "е" => "e", "ē" => "e", "ė" => "e", "ě" => "e", "ĕ" => "e", "є" => "e", "ə" => "e", "ע" => "e", "ф" => "f", "ƒ" => "f", "ğ" => "g", "ġ" => "g", "ģ" => "g", "ĝ" => "g", "г" => "g", "ג" => "g", "ґ" => "g", "ח" => "h", "ħ" => "h", "х" => "h", "ĥ" => "h", "ה" => "h", "i" => "i", "ï" => "i", "î" => "i", "í" => "i", "ì" => "i", "į" => "i", "ĭ" => "i", "ı" => "i", "и" => "i", "ĩ" => "i", "ǐ" => "i", "י" => "i", "ї" => "i", "ī" => "i", "і" => "i", "й" => "j", "Й" => "j", "Ĵ" => "j", "ĵ" => "j", "ĸ" => "k", "כ" => "k", "ķ" => "k", "к" => "k", "ך" => "k", "ł" => "l", "ŀ" => "l", "л" => "l", "ļ" => "l", "ĺ" => "l", "ľ" => "l", "ל" => "l", "מ" => "m", "м" => "m", "ם" => "m", "ñ" => "n", "ń" => "n", "н" => "n", "ņ" => "n", "ן" => "n", "ŋ" => "n", "נ" => "n", "ʼn" => "n", "ň" => "n", "ø" => "o", "ó" => "o", "ò" => "o", "ô" => "o", "õ" => "o", "о" => "o", "ő" => "o", "ŏ" => "o", "ō" => "o", "ǿ" => "o", "ǒ" => "o", "ơ" => "o", "פ" => "p", "ף" => "p", "п" => "p", "ק" => "q", "ŕ" => "r", "ř" => "r", "ŗ" => "r", "ר" => "r", "р" => "r", "®" => "r", "ş" => "s", "ś" => "s", "ș" => "s", "š" => "s", "с" => "s", "ŝ" => "s", "ס" => "s", "т" => "t", "ț" => "t", "ט" => "t", "ŧ" => "t", "ת" => "t", "ť" => "t", "ţ" => "t", "ù" => "u", "û" => "u", "ú" => "u", "ū" => "u", "у" => "u", "ũ" => "u", "ư" => "u", "ǔ" => "u", "ų" => "u", "ŭ" => "u", "ů" => "u", "ű" => "u", "ǖ" => "u", "ǜ" => "u", "ǚ" => "u", "ǘ" => "u", "в" => "v", "ו" => "v", "ý" => "y", "ы" => "y", "ŷ" => "y", "ÿ" => "y", "ź" => "z", "ž" => "z", "ż" => "z", "з" => "z", "ז" => "z", "ſ" => "z", "™" => "tm", "@" => "at", "Ä" => "ae", "Ǽ" => "ae", "ä" => "ae", "æ" => "ae", "ǽ" => "ae", "ij" => "ij", "IJ" => "ij", "я" => "ja", "Я" => "ja", "Э" => "je", "э" => "je", "ё" => "jo", "Ё" => "jo", "ю" => "ju", "Ю" => "ju", "œ" => "oe", "Œ" => "oe", "ö" => "oe", "Ö" => "oe", "щ" => "sch", "Щ" => "sch", "ш" => "sh", "Ш" => "sh", "ß" => "ss", "Ü" => "ue", "Ж" => "zh", "ж" => "zh", ); return strtr($subject, $char_map); } $string = "Ħí ŧħə®ë, юßť å test!"; echo replace_spec_char($string);Ħí ŧħə®ë, юßť å test!=>Hi there, jusst a test!This does not mix up upper and lower case chars except for longer chars (eg: ss,ch, sch) , added @ ® ©
Also if you want to build regex matching regardless to special chars :
rss => '[rŕřŘŗŖרŔРр](?:[sșсŜšśסşСŝ][sșсŜšśסşСŝ]|[ß])'A vala implementation of this : https://code.launchpad.net/~jeremy-munsch/synapse-project/ascii-smart/+merge/277477
Here is the base list you could work with, with regex replacing (in sublime text) or small script you can build anything from this array to fill your needs.
"-" => "ъьЪЬ", "A" => "АĂǍĄÀÃÁÆÂÅǺĀא", "B" => "БבÞ", "C" => "ĈĆÇЦצĊČ©ץ", "D" => "ДĎĐדÐ", "E" => "ÈĘÉËÊЕĒĖĚĔЄƏע", "F" => "ФƑ", "G" => "ĞĠĢĜГגҐ", "H" => "חĦХĤה", "I" => "IÏÎÍÌĮĬIИĨǏיЇĪІ", "J" => "ЙĴ", "K" => "ĸכĶКך", "L" => "ŁĿЛĻĹĽל", "M" => "מМם", "N" => "ÑŃНŅןŊנʼnŇ", "O" => "ØÓÒÔÕОŐŎŌǾǑƠ", "P" => "פףП", "Q" => "ק", "R" => "ŔŘŖרР®", "S" => "ŞŚȘŠСŜס", "T" => "ТȚטŦתŤŢ", "U" => "ÙÛÚŪУŨƯǓŲŬŮŰǕǛǙǗ", "V" => "Вו", "Y" => "ÝЫŶŸ", "Z" => "ŹŽŻЗז", "a" => "аăǎąàãáæâåǻāא", "b" => "бבþ", "c" => "ĉćçцצċč©ץ", "ch" => "ч", "d" => "дďđדð", "e" => "èęéëêеēėěĕєəע", "f" => "фƒ", "g" => "ğġģĝгגґ", "h" => "חħхĥה", "i" => "iïîíìįĭıиĩǐיїīі", "j" => "йĵ", "k" => "ĸכķкך", "l" => "łŀлļĺľל", "m" => "מмם", "n" => "ñńнņןŋנʼnň", "o" => "øóòôõоőŏōǿǒơ", "p" => "פףп", "q" => "ק", "r" => "ŕřŗרр®", "s" => "şśșšсŝס", "t" => "тțטŧתťţ", "u" => "ùûúūуũưǔųŭůűǖǜǚǘ", "v" => "вו", "y" => "ýыŷÿ", "z" => "źžżзזſ", "tm" => "™", "at" => "@", "ae" => "ÄǼäæǽ", "ch" => "Чч", "ij" => "ijIJ", "j" => "йЙĴĵ", "ja" => "яЯ", "je" => "Ээ", "jo" => "ёЁ", "ju" => "юЮ", "oe" => "œŒöÖ", "sch" => "щЩ", "sh" => "шШ", "ss" => "ß", "tm" => "™", "ue" => "Ü", "zh" => "Жж"讨论(0) -
Disclaimer: I'm not supporting this answer anymore (I was blind at that time). But thanks for the up-votes =P
You can take this as basis. From WordPress, used to generate pretty urls (the entry point is the slugify() function):
/** * 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; } /** * Checks to see if a string is utf8 encoded. * * @author bmorel at ssi dot fr * * @param string $Str The string to be checked * @return bool True if $Str fits a UTF-8 model, false otherwise. */ function seems_utf8($Str) { # by bmorel at ssi dot fr $length = strlen($Str); for ($i = 0; $i < $length; $i++) { if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n = 1; # 110bbbbb elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n = 2; # 1110bbbb elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n = 3; # 11110bbb elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n = 4; # 111110bb elseif ((ord($Str[$i]) & 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[$i]) & 0xC0) != 0x80)) return false; } } return true; } function utf8_uri_encode($utf8_string, $length = 0) { $unicode = ''; $values = array(); $num_octets = 1; $unicode_length = 0; $string_length = strlen($utf8_string); for ($i = 0; $i < $string_length; $i++) { $value = ord($utf8_string[$i]); if ($value < 128) { if ($length && ($unicode_length >= $length)) break; $unicode .= chr($value); $unicode_length++; } else { if (count($values) == 0) $num_octets = ($value < 224) ? 2 : 3; $values[] = $value; if ($length && ($unicode_length + ($num_octets * 3)) > $length) break; if (count( $values ) == $num_octets) { if ($num_octets == 3) { $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]); $unicode_length += 9; } else { $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]); $unicode_length += 6; } $values = array(); $num_octets = 1; } } } return $unicode; } /** * Sanitizes title, replacing whitespace with dashes. * * Limits the output to alphanumeric characters, underscore (_) and dash (-). * Whitespace becomes a dash. * * @param string $title The title to be sanitized. * @return string The sanitized title. */ function slugify($title) { $title = strip_tags($title); // Preserve escaped octets. $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title); // Remove percent signs that are not part of an octet. $title = str_replace('%', '', $title); // Restore octets. $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title); $title = remove_accents($title); if (seems_utf8($title)) { if (function_exists('mb_strtolower')) { $title = mb_strtolower($title, 'UTF-8'); } $title = utf8_uri_encode($title, 200); } $title = strtolower($title); $title = preg_replace('/&.+?;/', '', $title); // kill entities $title = preg_replace('/[^%a-z0-9 _-]/', '', $title); $title = preg_replace('/\s+/', '-', $title); $title = preg_replace('|-+|', '-', $title); $title = trim($title, '-'); return $title; }讨论(0)
加载中...
- 热议问题