隨筆檔案(496)

注意：要把php.ini中 extension=php_mbstring.dll 前的;號去掉，重啟apache就可以了。
我創建三個文件：text1.txt?? text2.txt?? text3.txt
分別以ASCII? UTF-8? UNICODE 的編碼方式保存

?

<?php
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));? // 輸出ASCII
echo '<br />';

$file = 'text2.txt';
echo getFileEncoding(file_get_contents($file));? // 輸出UTF-8
echo '<br />';

$file = 'text3.txt';
echo getFileEncoding(file_get_contents($file));? // 輸出UTF-16LE
echo '<br />';
?>