请问php中如何转换中文编码?

Question

各位大虾谁帮下忙我想将一些汉字转换到编码，比如"首页" 转换后为 &#39318 ; &#39029 ;
还有一些是是繁体的比如"首頁" 转换后为&#39318 ; &#38913 ;请问转换后的这个东西是什么编码啊？怎么实现将文字转换到这个编码呢？多谢各位了
急，在线等，

Answer 1

function encode2ascii($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 = $this->utf82utf16($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 = $this->utf82utf16($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 = $this->utf82utf16($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 = $this->utf82utf16($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 = $this->utf82utf16($char);
                            $ascii .= sprintf('\u%04s', bin2hex($utf16));
                            break;
                    }
                }                return $ascii;
}function utf82utf16($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 '';
}

Answer 2

$this->utf82utf16($char);
把前面的“$this->”去掉，即：utf82utf16($char);

Answer 3

谢谢，不过这函数不行啊
echo encode2ascii('首页');
出来的是\u9996\u9875
为什么捏？应该是 &#39318 ; &#39029 ;才对啊

Answer 4

错了。
把所有的：$ascii .= sprintf('\u%04s', bin2hex($utf16));改为：$ascii .= '&#'.hexdec(bin2hex($utf16)).';';就可以了

Answer 5

完整的编码解码
<?php
class StrFormat_F10{
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);
$ascii .= '&#'.hexdec(bin2hex($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);
$ascii .= '&#'.hexdec(bin2hex($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);
$ascii .= '&#'.hexdec(bin2hex($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);
$ascii .= '&#'.hexdec(bin2hex($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);
$ascii .= '&#'.hexdec(bin2hex($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('/\&\#[0-9]{5};/i', substr($chrs, $c, 8)):
$tmpstr=substr($chrs, $c, 8);
$tmpstr=dechex(substr($tmpstr, 2, 5));
$utf16 = chr(hexdec(substr($tmpstr, 0, 2)))
   . chr(hexdec(substr($tmpstr, 2, 2)));
$utf8 .= self::utf162utf8($utf16);
$c += 7;
break; case ($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 '';
    }
}
?>