php反unicode,php – 如何反转Unicode字符串

Grapheme功能处理UTF-8字符串比mbstring和PCRE功能更正确/ Mbstring和PCRE可能会中断字符.您可以通过执行以下代码来看到它们之间的差异.

function str_to_array($string)

{

$length = grapheme_strlen($string);

$ret = [];

for ($i = 0; $i < $length; $i += 1) {

$ret[] = grapheme_substr($string, $i, 1);

}

return $ret;

}

function str_to_array2($string)

{

$length = mb_strlen($string, "UTF-8");

$ret = [];

for ($i = 0; $i < $length; $i += 1) {

$ret[] = mb_substr($string, $i, 1, "UTF-8");

}

return $ret;

}

function str_to_array3($string)

{

return preg_split('//u', $string, -1, PREG_SPLIT_NO_EMPTY);

}

function utf8_strrev($string)

{

return implode(array_reverse(str_to_array($string)));

}

function utf8_strrev2($string)

{

return implode(array_reverse(str_to_array2($string)));

}

function utf8_strrev3($string)

{

return implode(array_reverse(str_to_array3($string)));

}

// http://www.php.net/manual/en/function.grapheme-strlen.php

$string = "a\xCC\x8A" // 'LATIN SMALL LETTER A WITH RING ABOVE' (U+00E5)

."o\xCC\x88"; // 'LATIN SMALL LETTER O WITH DIAERESIS' (U+00F6)

var_dump(array_map(function($elem) { return strtoupper(bin2hex($elem)); },

[

'should be' => "o\xCC\x88"."a\xCC\x8A",

'grapheme' => utf8_strrev($string),

'mbstring' => utf8_strrev2($string),

'pcre' => utf8_strrev3($string)

]));

结果就在这里.

array(4) {

["should be"]=>

string(12) "6FCC8861CC8A"

["grapheme"]=>

string(12) "6FCC8861CC8A"

["mbstring"]=>

string(12) "CC886FCC8A61"

["pcre"]=>

string(12) "CC886FCC8A61"

}

IntlBreakIterator可以使用PHP 5.5(intl 3.0);

function utf8_strrev($str)

{

$it = IntlBreakIterator::createCodePointInstance();

$it->setText($str);

$ret = '';

$pos = 0;

$prev = 0;

foreach ($it as $pos) {

$ret = substr($str, $prev, $pos - $prev) . $ret;

$prev = $pos;

}

return $ret;

}