php检测文件/字符串编码方法

code_detect.php

--------------

<?php

/*
* 可识别txt类型的文件，如果文本文件的内容为Ansi则返回EUC-CN，如果内容为utf-8则返回UTF-8

* 能识别的编码有： UTF-8,UTF-16BE,UTF-16LE,UTF-32BE,UTF-32LE,EUC-CN(ANSI)
*/

define ('UTF32_BIG_ENDIAN_BOM'   , chr(0x00) . chr(0x00) . chr(0xFE) . chr(0xFF));
define ('UTF32_LITTLE_ENDIAN_BOM', chr(0xFF) . chr(0xFE) . chr(0x00) . chr(0x00));
define ('UTF16_BIG_ENDIAN_BOM'   , chr(0xFE) . chr(0xFF));
define ('UTF16_LITTLE_ENDIAN_BOM', chr(0xFF) . chr(0xFE));
define ('UTF8_BOM'               , chr(0xEF) . chr(0xBB) . chr(0xBF));

class Encode_Core {
/**

* 文件分析方法来检查UNICODE文件，ANSI文件没有文件头，此处不分析

*/

  private function detect_utf_encoding($text) {

    $first2 = substr($text, 0, 2);

    $first3 = substr($text, 0, 3);

    $first4 = substr($text, 0, 3);

    if ($first3 == UTF8_BOM) return 'UTF-8';

    elseif ($first4 == UTF32_BIG_ENDIAN_BOM) return 'UTF-32BE';

    elseif ($first4 == UTF32_LITTLE_ENDIAN_BOM) return 'UTF-32LE';

    elseif ($first2 == UTF16_BIG_ENDIAN_BOM) return 'UTF-16BE';

    elseif ($first2 == UTF16_LITTLE_ENDIAN_BOM) return 'UTF-16LE';

  }

/**

* 取得编码

* @param string $str

* @return string $encoding

*/

  public static function get_encoding($str){

    $ary = array();

    $ary[] = 'UTF-8';

    $ary[] = 'ASCII';

    $ary[] = 'EUC-CN';

    $ary[] = 'JIS';//日文编码

    $ary[] = 'GB2312';//简体码

    $ary[] = 'BIG5';//繁体码

    $encoding=mb_detect_encoding($str, $ary);

    if(empty($encoding)){

      $encoding= self::detect_utf_encoding($str);

    }

    return $encoding;

  }

}

-------------------------------

test.php

-------------------------------------

include('code_detect.php');
$detect = new Encode_Core();

 
$path = 'D:/Program Files/Apache/htdocs/ctunes/music_upload/music/G/Zw_2_2/1.lrc';

$lrc = file_get_contents( $path );
$encode = $detect->get_encoding($lrc);
echo $encode;
file_put_contents( $path . '.txt', iconv($encode, 'UTF-8', $lrc) );


$path = 'D:/Program Files/Apache/htdocs/ctunes/music_upload/music/G/Zw_2_2/2.lrc';
$lrc = file_get_contents( $path );
$encode = $detect->get_encoding($lrc);
echo $encode;
file_put_contents( $path .'.txt' , iconv($encode, "UTF-8", $lrc));
 
--------------------

显示

EUC-CNUTF-8

--------------

查看另存为了文件正常显示

 

 

这种方法是使用头文件来判断;

另外一种方法是先转换成另一种编码,再转回来,比较原字符跟经过二次转换的是不是一样,不是一样就判断编码错误,一样就证明编码判断正确,这种方法要使用for来达到循环来测试,效力有点低,