Php UTF文件编码识别

用于判断文件是否使用UTF编码

<?php
// Unicode BOM is U+FEFF, but after encoded, it will look like this.
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));

/**
*@return 返回UTF编码格式
*
*/
function detect_utf_encoding($filename) {
   
    $text = file_get_contents($filename);
    $first2 = substr($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';
}


?>