像%u957f%u6c99这些是属于什么编码？

woshimajia0004 2010-07-01 11:39:12

例如：
%u957f%u6c99
%u9752%u5c9b

...
...

这些是什么编码啊？？

如何将中文字，转变成这种编码啊？

...全文

966 8 打赏收藏转发到动态举报

写回复

用AI写文章

8 条回复

切换为时间正序

请发表友善的回复…

发表回复

Dleno 2010-07-01

打赏
举报

$s = iconv('gbk', 'ucs-2', '丹东');
echo join('%u', str_split(array_pop(unpack('H*0', $s)), 4));

这种方式是可以的哈。也更简便。
注意到iconv的地方就可以了。

我发的是从以前的json.class.php里提取出来的。
只是因为它更稳定更原始，所以一直用的它。

fxs_2008 2010-07-01

打赏
举报

你看二楼的吧

我贴的是版主代码

基本思想是你要先转unicode。

但有多种转法，你的字串编码，文件编码。

不知道二楼的是否能自动识别编码？

woshimajia0004 2010-07-01

打赏
举报

[Quote=引用 2 楼 dingsongtao 的回复:]

PHP code

<?php
class StrFormat_Ascii{
static function encode($var){
$ascii = '';
$strlen_var = strlen($var);
for ($c = 0; $c < $strlen_var; ++$c) {

$ord_var……
[/Quote]

dingsongtao大哥太厉害了！！感谢！

woshimajia0004 2010-07-01

打赏
举报

[Quote=引用 4 楼 fxs_2008 的回复:]

这个应是unicode码

$s = iconv('gbk', 'ucs-2', '丹东');
echo join('%u', str_split(array_pop(unpack('H*0', $s)), 4));

老大的代码

第一部：转成二字节unicode
第二步：取unicode的四位16进制码
[/Quote]

这位大哥，你这个代码只对 "丹东" 有效，变成“丹西”就没辙了....

fxs_2008 2010-07-01

打赏
举报

这个应是unicode码

$s = iconv('gbk', 'ucs-2', '丹东');
echo join('%u', str_split(array_pop(unpack('H*0', $s)), 4));

老大的代码

第一部：转成二字节unicode
第二步：取unicode的四位16进制码

xuzuning 2010-07-01

打赏
举报

uncode

Dleno 2010-07-01

打赏
举报



<?php

class StrFormat_Ascii{

	static function encode($var){

		$ascii = '';

		$strlen_var = strlen($var);

		for ($c = 0; $c < $strlen_var; ++$c) {



			$ord_var_c = ord($var{$c});



			switch (true) {

				case $ord_var_c == 0x08:

					$ascii .= '\b';

					break;

				case $ord_var_c == 0x09:

					$ascii .= '\t';

					break;

				case $ord_var_c == 0x0A:

					$ascii .= '\n';

					break;

				case $ord_var_c == 0x0C:

					$ascii .= '\f';

					break;

				case $ord_var_c == 0x0D:

					$ascii .= '\r';

					break;



				case $ord_var_c == 0x22:

				case $ord_var_c == 0x2F:

				case $ord_var_c == 0x5C:

					$ascii .= '\\'.$var{$c};

					break;



				case (($ord_var_c >= 0x20) && ($ord_var_c <= 0x7F)):

					$ascii .= $var{$c};

					break;



				case (($ord_var_c & 0xE0) == 0xC0):

					$char = pack('C*', $ord_var_c, ord($var{$c + 1}));

					$c += 1;

					$utf16 = self::utf82utf16($char);

					$ascii .= sprintf('\u%04s', bin2hex($utf16));

					break;



				case (($ord_var_c & 0xF0) == 0xE0):

					$char = pack('C*', $ord_var_c,

								 ord($var{$c + 1}),

								 ord($var{$c + 2}));

					$c += 2;

					$utf16 = self::utf82utf16($char);

					$ascii .= sprintf('\u%04s', bin2hex($utf16));

					break;



				case (($ord_var_c & 0xF8) == 0xF0):

					$char = pack('C*', $ord_var_c,

								 ord($var{$c + 1}),

								 ord($var{$c + 2}),

								 ord($var{$c + 3}));

					$c += 3;

					$utf16 = self::utf82utf16($char);

					$ascii .= sprintf('\u%04s', bin2hex($utf16));

					break;



				case (($ord_var_c & 0xFC) == 0xF8):

					$char = pack('C*', $ord_var_c,

								 ord($var{$c + 1}),

								 ord($var{$c + 2}),

								 ord($var{$c + 3}),

								 ord($var{$c + 4}));

					$c += 4;

					$utf16 = self::utf82utf16($char);

					$ascii .= sprintf('\u%04s', bin2hex($utf16));

					break;



				case (($ord_var_c & 0xFE) == 0xFC):

					$char = pack('C*', $ord_var_c,

								 ord($var{$c + 1}),

								 ord($var{$c + 2}),

								 ord($var{$c + 3}),

								 ord($var{$c + 4}),

								 ord($var{$c + 5}));

					$c += 5;

					$utf16 = self::utf82utf16($char);

					$ascii .= sprintf('\u%04s', bin2hex($utf16));

					break;

			}

		}



		return $ascii;

	}

	

	static function decode($var){

		$chrs = $var;

		$utf8 = '';

		$strlen_chrs = strlen($chrs);



		for ($c = 0; $c < $strlen_chrs; $c++) {



			$substr_chrs_c_2 = substr($chrs, $c, 2);

			$ord_chrs_c = ord($chrs{$c});



			switch (true) {

				case $substr_chrs_c_2 == '\b':

					$utf8 .= chr(0x08);

					++$c;

					break;

				case $substr_chrs_c_2 == '\t':

					$utf8 .= chr(0x09);

					++$c;

					break;

				case $substr_chrs_c_2 == '\n':

					$utf8 .= chr(0x0A);

					++$c;

					break;

				case $substr_chrs_c_2 == '\f':

					$utf8 .= chr(0x0C);

					++$c;

					break;

				case $substr_chrs_c_2 == '\r':

					$utf8 .= chr(0x0D);

					++$c;

					break;



				case $substr_chrs_c_2 == '\\"':

				case $substr_chrs_c_2 == '\\\'':

				case $substr_chrs_c_2 == '\\\\':

				case $substr_chrs_c_2 == '\\/':

					if (($delim == '"' && $substr_chrs_c_2 != '\\\'') ||

					   ($delim == "'" && $substr_chrs_c_2 != '\\"')) {

						$utf8 .= $chrs{++$c};

					}

					break;



				case preg_match('/\\\u[0-9A-F]{4}/i', substr($chrs, $c, 6)):

					$utf16 = chr(hexdec(substr($chrs, ($c + 2), 2)))

						   . chr(hexdec(substr($chrs, ($c + 4), 2)));

					$utf8 .= self::utf162utf8($utf16);

					$c += 5;

					break;



				case ($ord_chrs_c >= 0x20) && ($ord_chrs_c <= 0x7F):

					$utf8 .= $chrs{$c};

					break;



				case ($ord_chrs_c & 0xE0) == 0xC0:

					$utf8 .= substr($chrs, $c, 2);

					++$c;

					break;



				case ($ord_chrs_c & 0xF0) == 0xE0:

					$utf8 .= substr($chrs, $c, 3);

					$c += 2;

					break;



				case ($ord_chrs_c & 0xF8) == 0xF0:

					$utf8 .= substr($chrs, $c, 4);

					$c += 3;

					break;



				case ($ord_chrs_c & 0xFC) == 0xF8:

					$utf8 .= substr($chrs, $c, 5);

					$c += 4;

					break;



				case ($ord_chrs_c & 0xFE) == 0xFC:

					$utf8 .= substr($chrs, $c, 6);

					$c += 5;

					break;



			}



		}



		return $utf8;	

	}



	static function utf82utf16($utf8){

        if(function_exists('mb_convert_encoding')) {

            return mb_convert_encoding($utf8, 'UTF-16', 'UTF-8');

        }



        switch(strlen($utf8)) {

            case 1:

                return $utf8;



            case 2:

                return chr(0x07 & (ord($utf8{0}) >> 2))

                     . chr((0xC0 & (ord($utf8{0}) << 6))

                         | (0x3F & ord($utf8{1})));



            case 3:

                return chr((0xF0 & (ord($utf8{0}) << 4))

                         | (0x0F & (ord($utf8{1}) >> 2)))

                     . chr((0xC0 & (ord($utf8{1}) << 6))

                         | (0x7F & ord($utf8{2})));

        }

        return '';

	}

	

	static function utf162utf8($utf16){

        if(function_exists('mb_convert_encoding')) {

            return mb_convert_encoding($utf16, 'UTF-8', 'UTF-16');

        }

        $bytes = (ord($utf16{0}) << 8) | ord($utf16{1});

        switch(true) {

            case ((0x7F & $bytes) == $bytes):

                return chr(0x7F & $bytes);



            case (0x07FF & $bytes) == $bytes:

                return chr(0xC0 | (($bytes >> 6) & 0x1F))

                     . chr(0x80 | ($bytes & 0x3F));



            case (0xFFFF & $bytes) == $bytes:

                return chr(0xE0 | (($bytes >> 12) & 0x0F))

                     . chr(0x80 | (($bytes >> 6) & 0x3F))

                     . chr(0x80 | ($bytes & 0x3F));

        }

        return '';

    }

}

?>