用户友好的网址来自功能

时间:2011-04-01 17:55:20

标签: php

我有一些困难,处理只为网址生成英文字符的cms,我需要让它适合葡萄牙,一个处理特殊字符的拉丁国家。

创建链接的功能是:

    function generateSafeUrls($url = '') {
    ## normalize accented characters
    $url = strtr($url, "\xA1\xAA\xBA\xBF\xC0\xC1\xC2\xC3\xC5\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF\xD0\xD1\xD2\xD3\xD4\xD5\xD8\xD9\xDA\xDB\xDD\xE0\xE1\xE2\xE3\xE5\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF\xF0\xF1\xF2\xF3\xF4\xF5\xF8\xF9\xFA\xFB\xFD\xFF\ã", "_ao_AAAAACEEEEIIIIDNOOOOOUUUYaaaaaceeeeiiiidnooooouuuyy"); 
    ## further character processing
    $url = strtr($url, array("\xC4"=>"Ae", "\xC6"=>"AE", "\xD6"=>"Oe", "\xDC"=>"Ue", "\xDE"=>"TH", "\xDF"=>"ss", "\xE4"=>"ae", "\xE6"=>"ae", "\xF6"=>"oe", "\xFC"=>"ue", "\xFE"=>"th", "\ã"=>"a"));
    ## make sure its only english and dashes
    $search = array("/[^a-zA-Z0-9\/]/", "/--+/");
    $replace = array("-", "-");
    $url = preg_replace($search, $replace, $url);
    ## return safe url
    return($url);
}

我可以看到该函数用“ - ”替换空格,如果函数将“ç”替换为“ç”,将“ã”替换为“a”等等,那将会很棒。问题是,我对如何制作它没有任何线索。

我不想让你像我一直说的那样工作,给我提示和提示,我将非常感激;)

亲切的问候你们所有人!谢谢!

2 个答案:

答案 0 :(得分:1)

此功能应该已经这样做了。 \ xE7是“ç”

的ascii

请参阅:http://www.laughtergenealogy.com/bin/header/ascii.html

答案 1 :(得分:1)

这是我的:

/**
 * Creates a URL friendly string.
 *
 * Takes a "title" string as input and creates a human-friendly URL string with either
 * a dash or an underscore as the word separator.
 *
 * @param  string
 * @param  string  dash or underscore
 * @param  bool
 * @return string
 */
if (!function_exists('friendlyUrl')) {
    function friendlyUrl($string, $separator = 'dash', $lowercase = TRUE) {
        if ($separator == 'dash') {
            $search = '_';
            $replace = '-';
        }
        else {
            $search = '-';
            $replace = '_';
        }

        if (function_exists('convertAccentsAndSpecialToNormal')) {
            $string = convertAccentsAndSpecialToNormal($string);
        }

        $trans = array(
                        '/&\#\d+?;/i'       => '',
                        '/&\S+?;/i'         => '',
                        '/\.+/i'            => '',
                        '/\s+/'             => $replace,
                        '/\/+/'             => $replace,
                        '/[^a-z0-9\-\._]/i' => '',
                        '/'. $replace .'+/' => $replace,
                        '/'. $replace .'$/' => $replace,
                        '/^'. $replace .'/' => $replace,
                        '/\.+$/'            => ''
        );

        $string = strip_tags($string);
        $string = preg_replace(array_keys($trans), array_values($trans), $string);

        if ($lowercase === TRUE) {
            $string = strtolower($string);
        }

        return trim(stripslashes($string));
    }
}


/**
 * Replaces special characters in a string with their "non-special" counterpart.
 *
 * Useful for friendly URLs.
 *
 * @param   string
 * @return  string
 */
function convertAccentsAndSpecialToNormal($string) {
    $table = array(
        'À'=>'A', 'Á'=>'A', 'Â'=>'A', 'Ã'=>'A', 'Ä'=>'A', 'Å'=>'A', 'Ă'=>'A', 'Ā'=>'A', 'Ą'=>'A', 'Æ'=>'A', 'Ǽ'=>'A',
        'à'=>'a', 'á'=>'a', 'â'=>'a', 'ã'=>'a', 'ä'=>'a', 'å'=>'a', 'ă'=>'a', 'ā'=>'a', 'ą'=>'a', 'æ'=>'a', 'ǽ'=>'a',

        'Þ'=>'B', 'þ'=>'b', 'ß'=>'Ss',

        'Ç'=>'C', 'Č'=>'C', 'Ć'=>'C', 'Ĉ'=>'C', 'Ċ'=>'C',
        'ç'=>'c', 'č'=>'c', 'ć'=>'c', 'ĉ'=>'c', 'ċ'=>'c',

        'Đ'=>'Dj', 'Ď'=>'D', 'Đ'=>'D',
        'đ'=>'dj', 'ď'=>'d',

        'È'=>'E', 'É'=>'E', 'Ê'=>'E', 'Ë'=>'E', 'Ĕ'=>'E', 'Ē'=>'E', 'Ę'=>'E', 'Ė'=>'E',
        'è'=>'e', 'é'=>'e', 'ê'=>'e', 'ë'=>'e', 'ĕ'=>'e', 'ē'=>'e', 'ę'=>'e', 'ė'=>'e',

        'Ĝ'=>'G', 'Ğ'=>'G', 'Ġ'=>'G', 'Ģ'=>'G',
        'ĝ'=>'g', 'ğ'=>'g', 'ġ'=>'g', 'ģ'=>'g',

        'Ĥ'=>'H', 'Ħ'=>'H',
        'ĥ'=>'h', 'ħ'=>'h',

        'Ì'=>'I', 'Í'=>'I', 'Î'=>'I', 'Ï'=>'I', 'İ'=>'I', 'Ĩ'=>'I', 'Ī'=>'I', 'Ĭ'=>'I', 'Į'=>'I',
        'ì'=>'i', 'í'=>'i', 'î'=>'i', 'ï'=>'i', 'į'=>'i', 'ĩ'=>'i', 'ī'=>'i', 'ĭ'=>'i', 'ı'=>'i',

        'Ĵ'=>'J',
        'ĵ'=>'j',

        'Ķ'=>'K',
        'ķ'=>'k', 'ĸ'=>'k',

        'Ĺ'=>'L', 'Ļ'=>'L', 'Ľ'=>'L', 'Ŀ'=>'L', 'Ł'=>'L',
        'ĺ'=>'l', 'ļ'=>'l', 'ľ'=>'l', 'ŀ'=>'l', 'ł'=>'l',

        'Ñ'=>'N', 'Ń'=>'N', 'Ň'=>'N', 'Ņ'=>'N', 'Ŋ'=>'N',
        'ñ'=>'n', 'ń'=>'n', 'ň'=>'n', 'ņ'=>'n', 'ŋ'=>'n', 'ʼn'=>'n',

        'Ò'=>'O', 'Ó'=>'O', 'Ô'=>'O', 'Õ'=>'O', 'Ö'=>'O', 'Ø'=>'O', 'Ō'=>'O', 'Ŏ'=>'O', 'Ő'=>'O', 'Œ'=>'O',
        'ò'=>'o', 'ó'=>'o', 'ô'=>'o', 'õ'=>'o', 'ö'=>'o', 'ø'=>'o', 'ō'=>'o', 'ŏ'=>'o', 'ő'=>'o', 'œ'=>'o', 'ð'=>'o',

        'Ŕ'=>'R', 'Ř'=>'R',
        'ŕ'=>'r', 'ř'=>'r', 'ŗ'=>'r',

        'Š'=>'S', 'Ŝ'=>'S', 'Ś'=>'S', 'Ş'=>'S',
        'š'=>'s', 'ŝ'=>'s', 'ś'=>'s', 'ş'=>'s',

        'Ŧ'=>'T', 'Ţ'=>'T', 'Ť'=>'T',
        'ŧ'=>'t', 'ţ'=>'t', 'ť'=>'t',

        'Ù'=>'U', 'Ú'=>'U', 'Û'=>'U', 'Ü'=>'U', 'Ũ'=>'U', 'Ū'=>'U', 'Ŭ'=>'U', 'Ů'=>'U', 'Ű'=>'U', 'Ų'=>'U',
        'ù'=>'u', 'ú'=>'u', 'û'=>'u', 'ü'=>'u', 'ũ'=>'u', 'ū'=>'u', 'ŭ'=>'u', 'ů'=>'u', 'ű'=>'u', 'ų'=>'u',

        'Ŵ'=>'W', 'Ẁ'=>'W', 'Ẃ'=>'W', 'Ẅ'=>'W',
        'ŵ'=>'w', 'ẁ'=>'w', 'ẃ'=>'w', 'ẅ'=>'w',

        'Ý'=>'Y', 'Ÿ'=>'Y', 'Ŷ'=>'Y',
        'ý'=>'y', 'ÿ'=>'y', 'ŷ'=>'y',

        'Ž'=>'Z', 'Ź'=>'Z', 'Ż'=>'Z', 'Ž'=>'Z',
        'ž'=>'z', 'ź'=>'z', 'ż'=>'z', 'ž'=>'z',

        '“'=>'"', '”'=>'"', '‘'=>"'", '’'=>"'", '•'=>'-', '…'=>'...', '—'=>'-', '–'=>'-', '¿'=>'?', '¡'=>'!', '°'=>' degrees ',
        '¼'=>' 1/4 ', '½'=>' 1/2 ', '¾'=>' 3/4 ', '⅓'=>' 1/3 ', '⅔'=>' 2/3 ', '⅛'=>' 1/8 ', '⅜'=>' 3/8 ', '⅝'=>' 5/8 ', '⅞'=>' 7/8 ',
        '÷'=>' divided by ', '×'=>' times ', '±'=>' plus-minus ', '√'=>' square root ', '∞'=>' infinity ',
        '≈'=>' almost equal to ', '≠'=>' not equal to ', '≡'=>' identical to ', '≤'=>' less than or equal to ', '≥'=>' greater than or equal to ',
        '←'=>' left ', '→'=>' right ', '↑'=>' up ', '↓'=>' down ', '↔'=>' left and right ', '↕'=>' up and down ',
        '℅'=>' care of ', '℮' => ' estimated ',
        'Ω'=>' ohm ',
        '♀'=>' female ', '♂'=>' male ',
        '©'=>' Copyright ', '®'=>' Registered ', '™' =>' Trademark ',
    );

    $string = strtr($string, $table);
    // Currency symbols: £¤¥€  - we dont bother with them for now
    $string = preg_replace("/[^\x9\xA\xD\x20-\x7F]/u", "", $string);

    return $string;
}