104

作为使字符串在 URL 中可用的第一步,我试图从 PHP 字符串中的字符中删除重音符号。

我正在使用以下代码:

$input = "Fóø Bår";

setlocale(LC_ALL, "en_US.utf8");
$output = iconv("utf-8", "ascii//TRANSLIT", $input);

print($output);

我期望的输出是这样的:

F'oo Bar

但是,重音字符不会被音译,而是用问号代替:

F?? B?r

我可以在网上找到的所有内容都表明设置区域设置将解决此问题,但是我已经在这样做了。我已经检查了以下详细信息:

  1. 服务器支持我设置的语言环境(包含在由 生成的列表中locale -a
  2. 服务器的 iconv 版本支持源和目标编码(UTF-8 和 ASCII)(包含在由 生成的列表中iconv -l
  3. 输入字符串是 UTF-8 编码的(使用 PHP 的mb_check_encoding函数验证,如mercator 的回答中所建议的)
  4. 调用setlocale成功(它返回'en_US.utf8'而不是FALSE

问题的原因:

服务器使用了错误的 iconv 实现。它具有glibc版本而不是所需的libiconv版本。

请注意,某些系统上的 iconv 功能可能无法按预期工作。在这种情况下,最好安装 GNU libiconv 库。它很可能最终会得到更一致的结果。
PHP手册对iconv的介绍

PHP 使用的 iconv 实现的详细信息包含在phpinfo函数的输出中。

(我无法在我正在为此项目使用的服务器上使用正确的 iconv 库重新编译 PHP,所以我在下面接受的答案是在没有 iconv 支持的情况下删除重音最有用的答案。)

4

27 回答 27

117

WordPress的实现呢?

function remove_accents($string) {
    if ( !preg_match('/[\x80-\xff]/', $string) )
        return $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'
    );

    $string = strtr($string, $chars);

    return $string;
}

要了解此函数的作用,请查看转换表:

À => A
Á => A
 => A
à => A
Ä => A
Å => 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
Ù => U
Ú => U
Û => U
Ü => U
Ý => Y
ß => s
à => a
á => a
â => a
ã => a
ä => a
å => 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
ù => u
ú => u
û => u
ü => u
ý => y
ÿ => y
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

您可以通过简单地遍历$chars函数数组来自己生成转换表:

foreach($chars as $k=>$v) {
   printf("%s -> %s", $k, $v);
}
于 2012-05-28T21:46:20.623 回答
49

这是我发现并经常使用的一段代码:

function stripAccents($stripAccents){
  return strtr($stripAccents,'àáâãäçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝ','aaaaaceeeeiiiinooooouuuuyyAAAAACEEEEIIIINOOOOOUUUUY');
}
于 2011-06-22T17:16:25.213 回答
49

Gino 上面发布的简单函数的 UTF-8 友好版本:

function stripAccents($str) {
    return strtr(utf8_decode($str), utf8_decode('àáâãäçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝ'), 'aaaaaceeeeiiiinooooouuuuyyAAAAACEEEEIIIINOOOOOUUUUY');
}

不得不这样做,因为我的 php 文档是 UTF-8 编码的。

希望能帮助到你。

于 2012-07-31T15:45:24.483 回答
33

如果您有http://php.net/manual/en/book.intl.php可用,这解决了您的问题

$string = "Fóø Bår";
$transliterator = Transliterator::createFromRules(':: Any-Latin; :: Latin-ASCII; :: NFD; :: [:Nonspacing Mark:] Remove; :: Lower(); :: NFC;', Transliterator::FORWARD);
echo $normalized = $transliterator->transliterate($string);
于 2016-02-03T13:04:20.903 回答
18

最简单的方法是使用iconv()PHP 原生函数。

 echo iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', "Thîs îs à vêry wrong séntènce!");

 // output: This is a very wrong sentence!
于 2014-08-20T21:05:01.613 回答
16

使用时iconv,必须设置参数 locale:

function test_enc($text = 'ěščřžýáíé ĚŠČŘŽÝÁÍÉ fóø bår FÓØ BÅR æ')
{
    echo '<tt>';
    echo iconv('utf8', 'ascii//TRANSLIT', $text);
    echo '</tt><br/>';
} 

test_enc();
setlocale(LC_ALL, 'cs_CZ.utf8');
test_enc();
setlocale(LC_ALL, 'en_US.utf8');
test_enc();

产生:

????????? ????????? f?? b?r F?? B?R ae
escrzyaie ESCRZYAIE fo? bar FO? BAR ae
escrzyaie ESCRZYAIE fo? bar FO? BAR ae

另一个语言环境,然后是 cs_CZ 和 en_US 我还没有安装,我无法测试它。

在 C# 中,我看到了使用转换为 unicode 规范化形式的解决方案 - 重音被拆分出来,然后通过非间距 unicode 类别进行过滤。

于 2011-04-30T05:58:50.583 回答
10

确实是口味问题。转换此类字母的方式有很多种。

function replaceAccents($str)
{
  $a = 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', 'Ý', 'ß', 'à', 'á', 'â', 'ã', 'ä', 'å', 'æ', 'ç', 'è', 'é', 'ê', 'ë', 'ì', 'í', 'î', 'ï', 'ñ', 'ò', 'ó', 'ô', 'õ', 'ö', 'ø', 'ù', 'ú', 'û', 'ü', 'ý', 'ÿ', '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', 'Ŵ', 'ŵ', 'Ŷ', 'ŷ', 'Ÿ', 'Ź', 'ź', 'Ż', 'ż', 'Ž', 'ž', 'ſ', 'ƒ', 'Ơ', 'ơ', 'Ư', 'ư', 'Ǎ', 'ǎ', 'Ǐ', 'ǐ', 'Ǒ', 'ǒ', 'Ǔ', 'ǔ', 'Ǖ', 'ǖ', 'Ǘ', 'ǘ', 'Ǚ', 'ǚ', 'Ǜ', 'ǜ', 'Ǻ', 'ǻ', 'Ǽ', 'ǽ', 'Ǿ', 'ǿ');
  $b = array('A', 'A', 'A', 'A', 'A', 'A', 'AE', 'C', 'E', 'E', 'E', 'E', 'I', 'I', 'I', 'I', 'D', 'N', 'O', 'O', 'O', 'O', 'O', 'O', 'U', 'U', 'U', 'U', 'Y', 's', 'a', 'a', 'a', 'a', 'a', 'a', 'ae', 'c', 'e', 'e', 'e', 'e', 'i', 'i', 'i', 'i', 'n', 'o', 'o', 'o', 'o', 'o', 'o', 'u', 'u', 'u', 'u', 'y', 'y', 'A', 'a', 'A', 'a', 'A', 'a', 'C', 'c', 'C', 'c', 'C', 'c', 'C', 'c', 'D', 'd', 'D', 'd', 'E', 'e', 'E', 'e', 'E', 'e', 'E', 'e', 'E', 'e', 'G', 'g', 'G', 'g', 'G', 'g', 'G', 'g', 'H', 'h', 'H', 'h', 'I', 'i', 'I', 'i', 'I', 'i', 'I', 'i', 'I', 'i', 'IJ', 'ij', 'J', 'j', 'K', 'k', 'L', 'l', 'L', 'l', 'L', 'l', 'L', 'l', 'l', 'l', 'N', 'n', 'N', 'n', 'N', 'n', 'n', 'O', 'o', 'O', 'o', 'O', 'o', 'OE', 'oe', 'R', 'r', 'R', 'r', 'R', 'r', 'S', 's', 'S', 's', 'S', 's', 'S', 's', 'T', 't', 'T', 't', 'T', 't', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'W', 'w', 'Y', 'y', 'Y', 'Z', 'z', 'Z', 'z', 'Z', 'z', 's', 'f', 'O', 'o', 'U', 'u', 'A', 'a', 'I', 'i', 'O', 'o', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'A', 'a', 'AE', 'ae', 'O', 'o');
  return str_replace($a, $b, $str);
}
于 2012-10-09T20:01:39.930 回答
9

我认为这里的问题是您的编码将 ä 和 å 考虑为与“a”不同的符号。事实上,strtr 的 PHP 文档提供了一个以丑陋的方式去除重音的示例:(

http://ie2.php.net/strtr

于 2009-06-19T12:21:09.667 回答
7

这是我通常用来删除重音的一个简单功能:

function str_without_accents($str, $charset='utf-8')
{
    $str = htmlentities($str, ENT_NOQUOTES, $charset);

    $str = preg_replace('#&([A-za-z])(?:acute|cedil|caron|circ|grave|orn|ring|slash|th|tilde|uml);#', '\1', $str);
    $str = preg_replace('#&([A-za-z]{2})(?:lig);#', '\1', $str); // pour les ligatures e.g. '&oelig;'
    $str = preg_replace('#&[^;]+;#', '', $str); // supprime les autres caractères

    return $str;   // or add this : mb_strtoupper($str); for uppercase :)
}
于 2015-09-14T10:36:26.177 回答
6

您可以使用 urlencode。不完全符合您的要求(删除重音符号),但会给您一个 url 可用字符串

$output = urlencode ($input);

在 Perl 中,我可以使用翻译正则表达式,但我想不出 PHP 等价物

$input =~ tr/áâàå/aaaa/;

ETC...

你可以使用 preg_replace 来做到这一点

$patterns[0] = '/[á|â|à|å|ä]/';
$patterns[1] = '/[ð|é|ê|è|ë]/';
$patterns[2] = '/[í|î|ì|ï]/';
$patterns[3] = '/[ó|ô|ò|ø|õ|ö]/';
$patterns[4] = '/[ú|û|ù|ü]/';
$patterns[5] = '/æ/';
$patterns[6] = '/ç/';
$patterns[7] = '/ß/';
$replacements[0] = 'a';
$replacements[1] = 'e';
$replacements[2] = 'i';
$replacements[3] = 'o';
$replacements[4] = 'u';
$replacements[5] = 'ae';
$replacements[6] = 'c';
$replacements[7] = 'ss';

$output = preg_replace($patterns, $replacements, $input);

(请注意,这是在星期五中午记忆之后从迷雾中的啤酒中输入的,因此可能不是 100% 正确)

或者您可以制作一个哈希表并以此为基础进行替换。

于 2009-06-19T13:05:56.613 回答
3

我刚刚创建了一个基于阅读该线程和另一个线程的 removeAccents 方法(如何删除重音符号并将字母转换为“普通”ASCII 字符?)。

方法在这里:https ://github.com/lingtalfi/Bat/blob/master/StringTool.md#removeaccents

测试在这里:https ://github.com/lingtalfi/Bat/blob/master/btests/StringTool/removeAccents/stringTool.removeAccents.test.php ,

这是迄今为止测试的内容:

$a = [
    // easy
    '',
    'a',
    'après',
    'dédé fait la fête ?',
    // hard
    'àáâãäçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝ',
    'ŻŹĆŃĄŚŁĘÓżźćńąśłęó',
    'qqqqŻŹĆŃĄŚŁĘÓżźćńąśłęóqqq',
    'ŠŽšžŸÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝàáâãäåçèéêëìíîïðñòóôõöøùúûüýÿ',       
    'ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝàáâãäåçèéêëìíîïñòóôõöøùúûüýÿ',
    'ĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģĤĥĦħĨĩĪīĬĭĮįİĴĵĶķ',
    'ĹĺĻļĽľĿŀŁłŃńŅņŇňʼnŌōŎŏŐőŔŕŖŗŘřŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵŶŷŸŹźŻżŽž',
    'ſƒƠơƯưǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜǺǻǾǿ',
    'Ǽǽ',
];

它只转换强调的东西(字母/连字/cédilles/一些字母通过/...?)。

下面是方法的内容:(https://github.com/lingtalfi/Bat/blob/master/StringTool.php#L83

public static function removeAccents($str)
{
    static $map = [
        // single letters
        'à' => 'a',
        'á' => 'a',
        'â' => 'a',
        'ã' => 'a',
        'ä' => 'a',
        'ą' => 'a',
        'å' => 'a',
        'ā' => 'a',
        'ă' => 'a',
        'ǎ' => 'a',
        'ǻ' => 'a',
        'À' => 'A',
        'Á' => 'A',
        'Â' => 'A',
        'Ã' => 'A',
        'Ä' => 'A',
        'Ą' => 'A',
        'Å' => 'A',
        'Ā' => 'A',
        'Ă' => 'A',
        'Ǎ' => 'A',
        'Ǻ' => 'A',


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

        'ď' => 'd',
        'đ' => 'd',
        'Ð' => 'D',
        'Ď' => 'D',
        'Đ' => 'D',


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

        'ƒ' => 'f',


        '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',
        'ĩ' => 'i',
        'ī' => 'i',
        'ĭ' => 'i',
        'į' => 'i',
        'ſ' => 'i',
        'ǐ' => 'i',
        'Ì' => 'I',
        'Í' => 'I',
        'Î' => 'I',
        'Ï' => 'I',
        'Ĩ' => 'I',
        'Ī' => 'I',
        'Ĭ' => 'I',
        'Į' => 'I',
        'İ' => 'I',
        'Ǐ' => 'I',

        'ĵ' => 'j',
        'Ĵ' => 'J',

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


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


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

        'ò' => 'o',
        'ó' => 'o',
        'ô' => 'o',
        'õ' => 'o',
        'ö' => 'o',
        'ð' => 'o',
        'ø' => 'o',
        'ō' => 'o',
        'ŏ' => 'o',
        'ő' => 'o',
        'ơ' => 'o',
        'ǒ' => 'o',
        'ǿ' => 'o',
        'Ò' => 'O',
        'Ó' => 'O',
        'Ô' => 'O',
        'Õ' => 'O',
        'Ö' => 'O',
        'Ø' => 'O',
        'Ō' => 'O',
        'Ŏ' => 'O',
        'Ő' => 'O',
        'Ơ' => 'O',
        'Ǒ' => 'O',
        'Ǿ' => 'O',


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


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

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


        'ù' => 'u',
        'ú' => 'u',
        'û' => 'u',
        'ü' => 'u',
        'ũ' => 'u',
        'ū' => 'u',
        'ŭ' => 'u',
        'ů' => 'u',
        'ű' => 'u',
        'ų' => 'u',
        'ư' => 'u',
        'ǔ' => 'u',
        'ǖ' => 'u',
        'ǘ' => 'u',
        'ǚ' => 'u',
        'ǜ' => 'u',
        'Ù' => 'U',
        'Ú' => 'U',
        'Û' => 'U',
        'Ü' => 'U',
        'Ũ' => 'U',
        'Ū' => 'U',
        'Ŭ' => 'U',
        'Ů' => 'U',
        'Ű' => 'U',
        'Ų' => 'U',
        'Ư' => 'U',
        'Ǔ' => 'U',
        'Ǖ' => 'U',
        'Ǘ' => 'U',
        'Ǚ' => 'U',
        'Ǜ' => 'U',


        'ŵ' => 'w',
        'Ŵ' => 'W',

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

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


        // accentuated ligatures
        'Ǽ' => 'A',
        'ǽ' => 'a',
    ];
    return strtr($str, $map);
}
于 2016-01-07T07:36:23.937 回答
3

这个有什么问题?适用于 UTF8

function strip_accents($s){
  return str_replace(
    explode(' ', preg_replace('/ +/', ' ', 'č ć ž š đ  Č Ć Ž Š Đ  à á â ã ä ç è é ê ë ì í î ï ñ ò ó ô õ ö ù ú û ü ý ÿ À Á Â Ã Ä Ç È É Ê Ë Ì Í Î Ï Ñ Ò Ó Ô Õ Ö Ù Ú Û Ü Ý')),
    explode(' ', preg_replace('/ +/', ' ', 'c c z s dj C C Z S DJ a a a a a c e e e e i i i i n o o o o o u u u u y y A A A A A C E E E E I I I I N O O O O O U U U U Y')),
    $s);
}

不使用它可以更快preg_replace,但速度不是我的目标。

于 2020-05-29T14:31:10.693 回答
2

我同意乔治布洛克的评论。

如果你找到一种方法让 //TRANSLIT 工作,你可以建立友好的 URL:

  1. 使用 iconv 和 //TRANSLIT ñ => n~
    • 删除单词中的非字母数字非空白字符:$url = preg_replace( '/(\w)[^\w\s](\w)/', '$1$2', $url );
    • 替换剩余的分离:$url = preg_replace( '/[^a-z0-9]+/', '-', $url );
    • 删除双/领先/跟踪:$url = preg_replace( '-',例如'/(?:(^|\-)\-+|\-$)/', '', $url );

如果您无法使其工作,请将 setp 1 替换为基于 strtr/字符的替换,例如 Xetius 的解决方案。

于 2009-06-19T13:47:54.173 回答
2

我无法重现您的问题。我得到了预期的结果。

您究竟是如何使用mb_detect_encoding()来验证您的字符串实际上是 UTF-8 的?

如果我只是调用mb_detect_encoding($input)字符串的 UTF-8 和 ISO-8859-1 编码版本,它们都返回“UTF-8”,因此该函数不是特别可靠。

iconv()当它得到错误编码的字符串并且只回显“F”时给我一个 PHP“通知”,但这可能只是因为不同的 PHP/iconv 设置/版本(?)。

我建议您mb_check_encoding($input, "utf-8")先尝试调用以验证您的字符串确实是 UTF-8。我想可能不是。

于 2009-06-19T14:10:49.743 回答
2

将 Cazuma Nii Cavalcanti 的实现与 Junior Mayhé 的字符列表合并,希望能为你们中的一些人节省一些时间。

function stripAccents($str) {
    return strtr(utf8_decode($str), utf8_decode('ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝßàáâãäåæçèéêëìíîïñòóôõöøùúûüýÿĀāĂ㥹ĆćĈĉĊċČčĎďĐđĒēĔĕĖėĘęĚěĜĝĞğĠġĢģĤĥĦħĨĩĪīĬĭĮįİıIJijĴĵĶķĹĺĻļĽľĿŀŁłŃńŅņŇňʼnŌōŎŏŐőŒœŔŕŖŗŘřŚśŜŝŞşŠšŢţŤťŦŧŨũŪūŬŭŮůŰűŲųŴŵŶŷŸŹźŻżŽžſƒƠơƯưǍǎǏǐǑǒǓǔǕǖǗǘǙǚǛǜǺǻǼǽǾǿ'), 'AAAAAAAECEEEEIIIIDNOOOOOOUUUUYsaaaaaaaeceeeeiiiinoooooouuuuyyAaAaAaCcCcCcCcDdDdEeEeEeEeEeGgGgGgGgHhHhIiIiIiIiIiIJijJjKkLlLlLlLlllNnNnNnnOoOoOoOEoeRrRrRrSsSsSsSsTtTtTtUuUuUuUuUuUuWwYyYZzZzZzsfOoUuAaIiOoUuUuUuUuUuAaAEaeOo');
}
于 2013-11-08T10:59:55.037 回答
2

在 laravel 中,您可以简单地使用str_slug($accentedPhrase) ,如果您关心破折号 (-),这种方法可以用空格代替str_replace('-', ' ', str_slug($accentedPhrase))

于 2018-09-30T14:24:51.893 回答
2

如果主要任务只是在 URL 中使用字符串,为什么不使用slugyfier呢?

composer require cocur/slugify

然后

use Cocur\Slugify\Slugify;

$slugify = new Slugify();
echo $slugify->slugify('Fóø Bår');

它还为流行的框架提供了许多桥梁。例如,您可以使用Doctrine Extensions Sluggable行为为 DB 中的每个实体自动生成唯一的 slug 并在 URL 中使用它。

如果您只想消除所有口音,则可以使用规则集来满足要求。

于 2020-03-06T09:12:17.433 回答
1

像这样的东西?

$arrSearch  = explode(","," ,ç,æ, œ, á,é,í,ó,ú,à,è,ì,ò,ù,ä,ë,ï,ö,ü,ÿ,â,ê,î,ô,û,å,e,i,ø,u");

$arrReplace = explode(",","_,c,ae,oe,a,e,i,o,u,a,e,i,o,u,a,e,i,o,u,y,a,e,i,o,u,a,e,i,o,u");

$output = str_replace($arrSearch, $arrReplace, $input);
于 2019-08-27T08:31:47.103 回答
1

这个答案我在这里有以下提示,所以它不是我的。它适用于我使用 LATIN1 或 UTF-8。如果您使用其他字符集,您可能应该将它们添加到mb_detect_encoding函数中。可能还需要正确的环境设置。

function NoAccents($s){
        return iconv(mb_detect_encoding($s,'UTF-8, ASCII, ISO-8859-1'),'ASCII//TRANSLIT//INGORE',$s);
}
于 2020-08-08T00:07:48.200 回答
0

您可以使用数组 key => value 样式与 strtr() 一起安全地用于 UTF-8 字符,即使它们是多字节的。

function no_accent($str){
    $accents = array('À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a', 'å' => 'a', 'Ā' => 'A', 'ā' => 'a', 'Ă' => 'A', 'ă' => 'a', 'Ą' => 'A', 'ą' => 'a', 'Ç' => 'C', 'ç' => 'c', 'Ć' => 'C', 'ć' => 'c', 'Ĉ' => 'C', 'ĉ' => 'c', 'Ċ' => 'C', 'ċ' => 'c', 'Č' => 'C', 'č' => 'c', 'Ð' => 'D', 'ð' => 'd', 'Ď' => 'D', 'ď' => 'd', 'Đ' => 'D', 'đ' => 'd', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e', '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', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'Ĩ' => 'I', 'ĩ' => 'i', 'Ī' => 'I', 'ī' => 'i', 'Ĭ' => 'I', 'ĭ' => 'i', 'Į' => 'I', 'į' => 'i', 'İ' => 'I', 'ı' => 'i', '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', 'Ñ' => 'N', 'ñ' => 'n', 'Ń' => 'N', 'ń' => 'n', 'Ņ' => 'N', 'ņ' => 'n', 'Ň' => 'N', 'ň' => 'n', 'ʼn' => 'n', 'Ŋ' => 'N', 'ŋ' => 'n', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O', 'Ø' => 'O', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ø' => 'o', 'Ō' => 'O', 'ō' => 'o', 'Ŏ' => 'O', 'ŏ' => 'o', 'Ő' => 'O', 'ő' => 'o', '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', 'ſ' => 's', 'Ţ' => 'T', 'ţ' => 't', 'Ť' => 'T', 'ť' => 't', 'Ŧ' => 'T', 'ŧ' => 't', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', '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', 'Ý' => 'Y', 'ý' => 'y', 'ÿ' => 'y', 'Ŷ' => 'Y', 'ŷ' => 'y', 'Ÿ' => 'Y', 'Ź' => 'Z', 'ź' => 'z', 'Ż' => 'Z', 'ż' => 'z', 'Ž' => 'Z', 'ž' => 'z');
    return strtr($str, $accents);
}

另外,您将解码/编码保存在 UTF-8 部分。

于 2015-01-25T22:09:19.753 回答
0

remove_accents()根据最新版本Wordpress 4.3 格式的改进版功能是:

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 reset_mbstring_encoding() {
    mbstring_binary_safe_encoding( true );
}

function seems_utf8( $str ) {
    mbstring_binary_safe_encoding();
    $length = strlen($str);
    reset_mbstring_encoding();
    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
            chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
            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(134) => 'AE',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(144) => 'D', 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(158) => 'TH',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(166) => 'ae',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(176) => 'd', 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(184) => '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(190) => 'th',
            chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
            // 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',
            // Decompositions for Latin Extended-B
            chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
            chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
            // Euro Sign
            chr(226).chr(130).chr(172) => 'E',
            // GBP (Pound) Sign
            chr(194).chr(163) => '',
            // Vowels with diacritic (Vietnamese)
            // unmarked
            chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
            chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
            // grave accent
            chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
            chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
            chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
            chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
            chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
            chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
            chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
            // hook
            chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
            chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
            chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
            chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
            chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
            chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
            chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
            chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
            chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
            chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
            chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
            chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
            // tilde
            chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
            chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
            chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
            chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
            chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
            chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
            chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
            chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
            // acute accent
            chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
            chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
            chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
            chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
            chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
            chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
            // dot below
            chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
            chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
            chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
            chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
            chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
            chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
            chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
            chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
            chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
            chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
            chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
            chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
            // Vowels with diacritic (Chinese, Hanyu Pinyin)
            chr(201).chr(145) => 'a',
            // macron
            chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
            // acute accent
            chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
            // caron
            chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
            chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
            chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
            chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
            chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
            // grave accent
            chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
        );

        $string = strtr($string, $chars);
    } else {
        $chars = array();
        // 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 = array();
        $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;
}

我的回答是更新@dynamic解决方案,因为罗马尼亚语或其他语言的变音符号没有被转换。我写了最小的函数并且像一个魅力一样工作。

print_r(remove_accents('Iași, Iași County, Romania'));
于 2015-09-05T09:55:48.547 回答
0
<?php
/* 
 * Thanks:
 *   - The idea of extracting accents equiv chars with the help of the HTMLSpecialChars convertion was taking from ICanBoogie Package of 'Olivier Laviale' {@link http://www.weirdog.com/blog/php/supprimer-les-accents-des-caracteres-accentues.html}
*/
function accentCharsModifier($str){
    if(($length=mb_strlen($str,"UTF-8"))<strlen($str)){
        $i=$count=0;
        while($i<$length){
            if(strlen($c=mb_substr($str,$i,1,"UTF-8"))>1){
                $he=htmlentities($c); 
                if(($nC=preg_replace("#&([A-Za-z])(?:acute|cedil|caron|circ|grave|orn|ring|slash|th|tilde|uml);#", "\\1", $he))!=$he ||
                    ($nC=preg_replace("#&([A-Za-z]{2})(?:lig);#", "\\1", $he))!=$he ||
                    ($nC=preg_replace("#&[^;]+;#", "", $he))!=$he){
                    $str=str_replace($c,$nC,$str,$count);if($nC==""){$length=$length-$count;$i--;}
                }
            }
            $i++;
        }
    }
    return $str;
}
echo accentCharsModifier("&éôpkAÈû");
?>
于 2015-11-22T00:42:00.943 回答
0

基于@Mimouni 的回答,我制作了这个函数来将重音字符串音译为非重音字符串。

/**
 * @param $str Convert string to lowercase and replace special chars to equivalents ou remove its
 * @return string
 */
function _slugify(string $string): string
{
    $str = $string; // for comparisons
    $str = _toUtf8($str); // Force to work with string in UTF-8
    $str = iconv('UTF-8', 'ASCII//TRANSLIT', $str);

    if ($str != htmlentities($string, ENT_QUOTES, 'UTF-8')) { // iconv fails
        $str = _toUtf8($string);
        $str = htmlentities($str, ENT_QUOTES, 'UTF-8');
        $str = preg_replace('#&([a-z]{1,2})(acute|cedil|circ|grave|lig|orn|ring|slash|th|tilde|uml);#i', '$1', $str);
        // Need to strip non ASCII chars or any other than a-z, A-Z, 0-9...
        $str = html_entity_decode($str, ENT_QUOTES, 'UTF-8');
        $str = preg_replace(array('#[^0-9a-z]#i', '#[ -]+#'), ' ', $str);
        $str = trim($str, ' -');
    }

    // lowercase
    $string = strtolower($str);

    return $string;
}

要将字符串转换为 UTF-8,这里我使用多字节字符串扩展。请注意,我将字符串分成几部分以避免混合内容的麻烦(我有这种情况)并逐字转换。

/**
 * @param $str string String in any encoding
 * @return string
 */
function _toUtf8(string $str_in): ?string
{
    if (!function_exists('mb_detect_encoding')) {
        throw new \Exception('The Multi Byte String extension is absent!');
    }
    $str_out = [];
    $words = explode(" ", $str_in);
    foreach ($words as $word) {
        $current_encoding = mb_detect_encoding($word, 'UTF-8, ASCII, ISO-8859-1');
        $str_out[] = mb_convert_encoding($word, 'UTF-8', $current_encoding);
    }
    return implode(" ", $str_out);
}

页脚注释:是在 Windows 命令行中传递 PHPUnit UnitTests 的唯一解决方案(语言环境问题)@gabo 解决方案应该可以工作,但不幸的是不适合我

于 2018-08-23T17:49:43.850 回答
0

结合一些答案:

/**
 * Given an utf8 string, returns an ascii string.
 * Only supports ISO-8859-1 chars, not chars like č, œ, Œ, ř, Š, š, ů, Ÿ or ž
 * @param string $utf8
 * @return string ascii
 */
function stripAccents(string $utf8): string
{
    $src = 'àáâãäåçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝ';
    $dst = 'aaaaaaceeeeiiiinooooouuuuyyAAAAACEEEEIIIINOOOOOUUUUY';
    $iso8859_1 = strtr(
        utf8_decode($utf8),
        utf8_decode($src),
        $dst
    );
    // iconv below not used for UTF-8 directly because it adds chars like ^'"`
    // which are nice to not lose info, but not very readable and not compatible with filenames
    // iconv() additionally converts chars like
    // ¡ ¢ £  ¥   ¦ §  ¨  ©  ª «  ¬   SHY ®    °  ±   ²  ³  ´ µ ¶ · ¸ ¹  º »  ¼   ½   ¾   ¿ Å Æ  Ð Ø Þ  ß  æ  ÷   ø þ
    // ! c lb yen | SS " (c) a << not SHY (R)  ^0 +/- ^2 ^3 ' u P . , ^1 o >> 1/4 1/2 3/4 ? A AE D O Th ss ae d : o th
    return iconv('ISO-8859-1', 'ASCII//TRANSLIT//IGNORE', $iso8859_1);
}
于 2022-01-18T19:10:29.730 回答
-1

我在网上偶然发现的技巧之一是使用htmlentities然后剥离编码字符:

$stripped = preg_replace('`&[^;]+;`','',htmlentities($string));

不完美,但在某些情况下它确实运作良好。

但是,您正在撰写有关创建 URL 字符串的文章,因此urlencode及其对应的urldecode可能会更好。或者,如果您正在创建查询字符串,请使用最后一个函数:http_build_query

于 2009-06-19T14:19:20.787 回答
-1

WordPress 的实现对于 UTF8 字符串来说绝对是最安全的。对于 Latin1 字符串,一个简单的 strtr 就可以完成这项工作,但请确保您将脚本保存为 LATIN1 格式,而不是 UTF-8。

于 2012-11-04T16:43:59.023 回答
-1
$unwanted_array = array(    '&amp;' => 'and', '&' => 'and', '@' => 'at', '©' => 'c', '®' => 'r', 
'̊'=>'','̧'=>'','̨'=>'','̄'=>'','̱'=>'',
'Á'=>'a','á'=>'a','À'=>'a','à'=>'a','Ă'=>'a','ă'=>'a','ắ'=>'a','Ắ'=>'A','Ằ'=>'A',
'ằ'=>'a','ẵ'=>'a','Ẵ'=>'A','ẳ'=>'a','Ẳ'=>'A','Â'=>'a','â'=>'a','ấ'=>'a','Ấ'=>'A',
'ầ'=>'a','Ầ'=>'a','ẩ'=>'a','Ẩ'=>'A','Ǎ'=>'a','ǎ'=>'a','Å'=>'a','å'=>'a','Ǻ'=>'a',
'ǻ'=>'a','Ä'=>'a','ä'=>'a','ã'=>'a','Ã'=>'A','Ą'=>'a','ą'=>'a','Ā'=>'a','ā'=>'a',
'ả'=>'a','Ả'=>'a','Ạ'=>'A','ạ'=>'a','ặ'=>'a','Ặ'=>'A','ậ'=>'a','Ậ'=>'A','Æ'=>'ae',
'æ'=>'ae','Ǽ'=>'ae','ǽ'=>'ae','ẫ'=>'a','Ẫ'=>'A',
'Ć'=>'c','ć'=>'c','Ĉ'=>'c','ĉ'=>'c','Č'=>'c','č'=>'c','Ċ'=>'c','ċ'=>'c','Ç'=>'c','ç'=>'c',
'Ď'=>'d','ď'=>'d','Ḑ'=>'D','ḑ'=>'d','Đ'=>'d','đ'=>'d','Ḍ'=>'D','ḍ'=>'d','Ḏ'=>'D','ḏ'=>'d','ð'=>'d','Ð'=>'D',
'É'=>'e','é'=>'e','È'=>'e','è'=>'e','Ĕ'=>'e','ĕ'=>'e','ê'=>'e','ế'=>'e','Ế'=>'E','ề'=>'e',
'Ề'=>'E','Ě'=>'e','ě'=>'e','Ë'=>'e','ë'=>'e','Ė'=>'e','ė'=>'e','Ę'=>'e','ę'=>'e','Ē'=>'e',
'ē'=>'e','ệ'=>'e','Ệ'=>'E','Ə'=>'e','ə'=>'e','ẽ'=>'e','Ẽ'=>'E','ễ'=>'e',
'Ễ'=>'E','ể'=>'e','Ể'=>'E','ẻ'=>'e','Ẻ'=>'E','ẹ'=>'e','Ẹ'=>'E',
'ƒ'=>'f',
'Ğ'=>'g','ğ'=>'g','Ĝ'=>'g','ĝ'=>'g','Ǧ'=>'G','ǧ'=>'g','Ġ'=>'g','ġ'=>'g','Ģ'=>'g','ģ'=>'g',
'H̲'=>'H','h̲'=>'h','Ĥ'=>'h','ĥ'=>'h','Ȟ'=>'H','ȟ'=>'h','Ḩ'=>'H','ḩ'=>'h','Ħ'=>'h','ħ'=>'h','Ḥ'=>'H','ḥ'=>'h',
'Ỉ'=>'I','Í'=>'i','í'=>'i','Ì'=>'i','ì'=>'i','Ĭ'=>'i','ĭ'=>'i','Î'=>'i','î'=>'i','Ǐ'=>'i','ǐ'=>'i',
'Ï'=>'i','ï'=>'i','Ḯ'=>'I','ḯ'=>'i','Ĩ'=>'i','ĩ'=>'i','İ'=>'i','Į'=>'i','į'=>'i','Ī'=>'i','ī'=>'i',
'ỉ'=>'I','Ị'=>'I','ị'=>'i','IJ'=>'ij','ij'=>'ij','ı'=>'i',
'Ĵ'=>'j','ĵ'=>'j',
'Ķ'=>'k','ķ'=>'k','Ḵ'=>'K','ḵ'=>'k',
'Ĺ'=>'l','ĺ'=>'l','Ľ'=>'l','ľ'=>'l','Ļ'=>'l','ļ'=>'l','Ł'=>'l','ł'=>'l','Ŀ'=>'l','ŀ'=>'l',
'Ń'=>'n','ń'=>'n','Ň'=>'n','ň'=>'n','Ñ'=>'N','ñ'=>'n','Ņ'=>'n','ņ'=>'n','Ṇ'=>'N','ṇ'=>'n','Ŋ'=>'n','ŋ'=>'n',
'Ó'=>'o','ó'=>'o','Ò'=>'o','ò'=>'o','Ŏ'=>'o','ŏ'=>'o','Ô'=>'o','ô'=>'o','ố'=>'o','Ố'=>'O','ồ'=>'o',
'Ồ'=>'O','ổ'=>'o','Ổ'=>'O','Ǒ'=>'o','ǒ'=>'o','Ö'=>'o','ö'=>'o','Ő'=>'o','ő'=>'o','Õ'=>'o','õ'=>'o',
'Ø'=>'o','ø'=>'o','Ǿ'=>'o','ǿ'=>'o','Ǫ'=>'O','ǫ'=>'o','Ǭ'=>'O','ǭ'=>'o','Ō'=>'o','ō'=>'o','ỏ'=>'o',
'Ỏ'=>'O','Ơ'=>'o','ơ'=>'o','ớ'=>'o','Ớ'=>'O','ờ'=>'o','Ờ'=>'O','ở'=>'o','Ở'=>'O','ợ'=>'o','Ợ'=>'O',
'ọ'=>'o','Ọ'=>'O','ọ'=>'o','Ọ'=>'O','ộ'=>'o','Ộ'=>'O','ỗ'=>'o','Ỗ'=>'O','ỡ'=>'o','Ỡ'=>'O',
'Œ'=>'oe','œ'=>'oe',
'ĸ'=>'k',
'Ŕ'=>'r','ŕ'=>'r','Ř'=>'r','ř'=>'r','ṙ'=>'r','Ŗ'=>'r','ŗ'=>'r','Ṛ'=>'R','ṛ'=>'r','Ṟ'=>'R','ṟ'=>'r',
'S̲'=>'S','s̲'=>'s','Ś'=>'s','ś'=>'s','Ŝ'=>'s','ŝ'=>'s','Š'=>'s','š'=>'s','Ş'=>'s','ş'=>'s',
'Ṣ'=>'S','ṣ'=>'s','Ș'=>'S','ș'=>'s',
'ſ'=>'z','ß'=>'ss','Ť'=>'t','ť'=>'t','Ţ'=>'t','ţ'=>'t','Ṭ'=>'T','ṭ'=>'t','Ț'=>'T',
'ț'=>'t','Ṯ'=>'T','ṯ'=>'t','™'=>'tm','Ŧ'=>'t','ŧ'=>'t',
'Ú'=>'u','ú'=>'u','Ù'=>'u','ù'=>'u','Ŭ'=>'u','ŭ'=>'u','Û'=>'u','û'=>'u','Ǔ'=>'u','ǔ'=>'u','Ů'=>'u','ů'=>'u',
'Ü'=>'u','ü'=>'u','Ǘ'=>'u','ǘ'=>'u','Ǜ'=>'u','ǜ'=>'u','Ǚ'=>'u','ǚ'=>'u','Ǖ'=>'u','ǖ'=>'u','Ű'=>'u','ű'=>'u',
'Ũ'=>'u','ũ'=>'u','Ų'=>'u','ų'=>'u','Ū'=>'u','ū'=>'u','Ư'=>'u','ư'=>'u','ứ'=>'u','Ứ'=>'U','ừ'=>'u','Ừ'=>'U',
'ử'=>'u','Ử'=>'U','ự'=>'u','Ự'=>'U','ụ'=>'u','Ụ'=>'U','ủ'=>'u','Ủ'=>'U','ữ'=>'u','Ữ'=>'U',
'Ŵ'=>'w','ŵ'=>'w',
'Ý'=>'y','ý'=>'y','ỳ'=>'y','Ỳ'=>'Y','Ŷ'=>'y','ŷ'=>'y','ÿ'=>'y','Ÿ'=>'y','ỹ'=>'y','Ỹ'=>'Y','ỷ'=>'y','Ỷ'=>'Y',
'Z̲'=>'Z','z̲'=>'z','Ź'=>'z','ź'=>'z','Ž'=>'z','ž'=>'z','Ż'=>'z','ż'=>'z','Ẕ'=>'Z','ẕ'=>'z',
'þ'=>'p','ʼn'=>'n','А'=>'a','а'=>'a','Б'=>'b','б'=>'b','В'=>'v','в'=>'v','Г'=>'g','г'=>'g','Ґ'=>'g','ґ'=>'g',
'Д'=>'d','д'=>'d','Е'=>'e','е'=>'e','Ё'=>'jo','ё'=>'jo','Є'=>'e','є'=>'e','Ж'=>'zh','ж'=>'zh','З'=>'z','з'=>'z',
'И'=>'i','и'=>'i','І'=>'i','і'=>'i','Ї'=>'i','ї'=>'i','Й'=>'j','й'=>'j','К'=>'k','к'=>'k','Л'=>'l','л'=>'l',
'М'=>'m','м'=>'m','Н'=>'n','н'=>'n','О'=>'o','о'=>'o','П'=>'p','п'=>'p','Р'=>'r','р'=>'r','С'=>'s','с'=>'s',
'Т'=>'t','т'=>'t','У'=>'u','у'=>'u','Ф'=>'f','ф'=>'f','Х'=>'h','х'=>'h','Ц'=>'c','ц'=>'c','Ч'=>'ch','ч'=>'ch',
'Ш'=>'sh','ш'=>'sh','Щ'=>'sch','щ'=>'sch','Ъ'=>'-',
'ъ'=>'-','Ы'=>'y','ы'=>'y','Ь'=>'-','ь'=>'-',
'Э'=>'je','э'=>'je','Ю'=>'ju','ю'=>'ju','Я'=>'ja','я'=>'ja','א'=>'a','ב'=>'b','ג'=>'g','ד'=>'d','ה'=>'h','ו'=>'v',
'ז'=>'z','ח'=>'h','ט'=>'t','י'=>'i','ך'=>'k','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','נ'=>'n','ס'=>'s','ע'=>'e',
'ף'=>'p','פ'=>'p','ץ'=>'C','צ'=>'c','ק'=>'q','ר'=>'r','ש'=>'w','ת'=>'t'
);

$accentsRemoved = strtr( $stringToRemoveAccents , $unwanted_array );
于 2015-03-26T13:50:18.413 回答