我在允许所有基于英语/拉丁语的字符（包括重音符号）但不允许使用中文/俄语字符时遇到问题。
我的第一个版本如下：
strlen($values['person_name']) != mb_strlen($values['person_name'], 'utf-8')
这个最初工作得很好，但是当冰岛/捷克名字开始发挥作用时，这个就不再工作了。
我的第二个版本如下：
preg_match("~^[a-zÀ-ÿ][\'a-zÀ-ÿ \-]*$~i", $values['person_name'])
这对于大多数情况来说似乎工作正常，但它在测试名称上给出了错误
Eliška Koňaříková
我也尝试过以下方法，但没有任何运气：
preg_match("/[^\w ]/u", $values['person_name']) //does not allow š
preg_match("/\PL/u", $values['person_name']) //does not allow š
preg_match("/^[a-zA-Z\s,.'\-\pL]+$/u", $values['person_name']) //allows š, but also allows 書
preg_match("/^[\s,.'-]*\p{L}[\p{L}\s,.'-]*$/u", $values['person_name']) //allows š, but also allows 書
preg_match("/[^a-zA-Z0-9àâáçéèèêëìîíïôòóùûüÂÊÎÔúÛÄËÏÖÜÀÆæÇÉÈŒœÙñý,. ]/u", $values['person_name']) //allows š, but also allows 書
preg_match("~^[a-zÀ-ÿ][\'a-zÀ-ÿ \-]*$~iu", $values['person_name']) //does not allow š
preg_match("/^[\p{L}-]*$/u", $values['person_name']) //allows š, but also allows 書
preg_match("/([\w ]{2,})/u", $values['person_name']) //allows š, but also allows 書
preg_match('/[^\p{Latin}0-9€, !"§$%&\/()=#|<>]/u', $values['person_name']) //allows š, but also allows 書
以上所有操作要么因提供的名称而失败，要么允许使用中文字符。
我相信对我来说最好的路线是恢复到适用于大多数字符的检查（除了捷克语名称给出错误）：
preg_match("~^[a-zÀ-ÿ][\'a-zÀ-ÿ \-]*$~i", $values['person_name'])
并手动添加不接受的捷克语字符，例如š、ň、ř等。
是否有比手动指定每个字符更干净的解决方案？
也许替换字符会更好，这只是这样做的一个示例，它不是一个完整的功能：
<?php
replace($str, $options = array())
{
// Make sure string is in UTF-8 and strip invalid UTF-8 characters
$str = mb_convert_encoding((string)$str, 'UTF-8', mb_list_encodings());
$defaults = array(
'delimiter' => '',
'limit' => null,
'lowercase' => true,
'replacements' => array(),
'transliterate' => false,
);
// Merge options
$options = array_merge($defaults, $options);
$char_map = array(
// Latin
'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', 'Ő' => 'O',
'Ø' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ű' => 'U', 'Ý' => 'Y', 'Þ' => 'TH',
'ß' => 'ss',
'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', 'ő' => 'o',
'ø' => 'o', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th',
'ÿ' => 'y',
// Latin symbols
'©' => '(c)',
// Greek
'Α' => 'A', 'Β' => 'B', 'Γ' => 'G', 'Δ' => 'D', 'Ε' => 'E', 'Ζ' => 'Z', 'Η' => 'H', 'Θ' => '8',
'Ι' => 'I', 'Κ' => 'K', 'Λ' => 'L', 'Μ' => 'M', 'Ν' => 'N', 'Ξ' => '3', 'Ο' => 'O', 'Π' => 'P',
'Ρ' => 'R', 'Σ' => 'S', 'Τ' => 'T', 'Υ' => 'Y', 'Φ' => 'F', 'Χ' => 'X', 'Ψ' => 'PS', 'Ω' => 'W',
'Ά' => 'A', 'Έ' => 'E', 'Ί' => 'I', 'Ό' => 'O', 'Ύ' => 'Y', 'Ή' => 'H', 'Ώ' => 'W', 'Ϊ' => 'I',
'Ϋ' => 'Y',
'α' => 'a', 'β' => 'b', 'γ' => 'g', 'δ' => 'd', 'ε' => 'e', 'ζ' => 'z', 'η' => 'h', 'θ' => '8',
'ι' => 'i', 'κ' => 'k', 'λ' => 'l', 'μ' => 'm', 'ν' => 'n', 'ξ' => '3', 'ο' => 'o', 'π' => 'p',
'ρ' => 'r', 'σ' => 's', 'τ' => 't', 'υ' => 'y', 'φ' => 'f', 'χ' => 'x', 'ψ' => 'ps', 'ω' => 'w',
'ά' => 'a', 'έ' => 'e', 'ί' => 'i', 'ό' => 'o', 'ύ' => 'y', 'ή' => 'h', 'ώ' => 'w', 'ς' => 's',
'ϊ' => 'i', 'ΰ' => 'y', 'ϋ' => 'y', 'ΐ' => 'i',
// Turkish
'Ş' => 'S', 'İ' => 'I', 'Ç' => 'C', 'Ü' => 'U', 'Ö' => 'O', 'Ğ' => 'G',
'ş' => 's', 'ı' => 'i', 'ç' => 'c', 'ü' => 'u', 'ö' => 'o', 'ğ' => 'g',
// Russian
'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G', 'Д' => 'D', 'Е' => 'E', 'Ё' => 'Yo', 'Ж' => 'Zh',
'З' => 'Z', 'И' => 'I', 'Й' => 'J', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O',
'П' => 'P', 'Р' => 'R', 'С' => 'S', 'Т' => 'T', 'У' => 'U', 'Ф' => 'F', 'Х' => 'H', 'Ц' => 'C',
'Ч' => 'Ch', 'Ш' => 'Sh', 'Щ' => 'Sh', 'Ъ' => '', 'Ы' => 'Y', 'Ь' => '', 'Э' => 'E', 'Ю' => 'Yu',
'Я' => 'Ya',
'а' => 'a', 'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo', 'ж' => 'zh',
'з' => 'z', 'и' => 'i', 'й' => 'j', 'к' => 'k', 'л' => 'l', 'м' => 'm', 'н' => 'n', 'о' => 'o',
'п' => 'p', 'р' => 'r', 'с' => 's', 'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ц' => 'c',
'ч' => 'ch', 'ш' => 'sh', 'щ' => 'sh', 'ъ' => '', 'ы' => 'y', 'ь' => '', 'э' => 'e', 'ю' => 'yu',
'я' => 'ya',
// Ukrainian
'Є' => 'Ye', 'І' => 'I', 'Ї' => 'Yi', 'Ґ' => 'G',
'є' => 'ye', 'і' => 'i', 'ї' => 'yi', 'ґ' => 'g',
// Czech
'Č' => 'C', 'Ď' => 'D', 'Ě' => 'E', 'Ň' => 'N', 'Ř' => 'R', 'Š' => 'S', 'Ť' => 'T', 'Ů' => 'U',
'Ž' => 'Z',
'č' => 'c', 'ď' => 'd', 'ě' => 'e', 'ň' => 'n', 'ř' => 'r', 'š' => 's', 'ť' => 't', 'ů' => 'u',
'ž' => 'z',
// Polish
'Ą' => 'A', 'Ć' => 'C', 'Ę' => 'e', 'Ł' => 'L', 'Ń' => 'N', 'Ó' => 'o', 'Ś' => 'S', 'Ź' => 'Z',
'Ż' => 'Z',
'ą' => 'a', 'ć' => 'c', 'ę' => 'e', 'ł' => 'l', 'ń' => 'n', 'ó' => 'o', 'ś' => 's', 'ź' => 'z',
'ż' => 'z',
// Latvian
'Ā' => 'A', 'Č' => 'C', 'Ē' => 'E', 'Ģ' => 'G', 'Ī' => 'i', 'Ķ' => 'k', 'Ļ' => 'L', 'Ņ' => 'N',
'Š' => 'S', 'Ū' => 'u', 'Ž' => 'Z',
'ā' => 'a', 'č' => 'c', 'ē' => 'e', 'ģ' => 'g', 'ī' => 'i', 'ķ' => 'k', 'ļ' => 'l', 'ņ' => 'n',
'š' => 's', 'ū' => 'u', 'ž' => 'z'
);
// Make custom replacements
$str = preg_replace(array_keys($options['replacements']), $options['replacements'], $str);
// Transliterate characters to ASCII
if ($options['transliterate']) {
$str = str_replace(array_keys($char_map), $char_map, $str);
}
// Replace non-alphanumeric characters with our delimiter
$str = preg_replace('/[^\p{L}\p{Nd}]+/u', $options['delimiter'], $str);
// Remove duplicate delimiters
$str = preg_replace('/(' . preg_quote($options['delimiter'], '/') . '){2,}/', '$1', $str);
// Truncate slug to max. characters
$str = mb_substr($str, 0, ($options['limit'] ? $options['limit'] : mb_strlen($str, 'UTF-8')), 'UTF-8');
// Remove delimiter from ends
$str = trim($str, $options['delimiter']);
return $options['lowercase'] ? mb_strtolower($str, 'UTF-8') : $str;
}