日期:2014-05-17  浏览次数:20540 次

php 检测文件编码类型
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));

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';
}

function getFileEncoding($str){
    $encoding=mb_detect_encoding($str);
    if(empty($encoding)){
        $encoding=detect_utf_encoding($str);
    }
    return $encoding;
}
$file = 'text1.txt';
echo getFileEncoding(file_get_contents($file));  // 输出ASCII
echo '';

$file = 'text2.txt';
echo getFileEncoding(file_get_contents($file));  // 输出UTF-8
echo '';
$file = 'text3.txt';
echo getFileEncoding(file_get_contents($file));  // 输出UTF-16LE
echo '';