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));
$first2 = substr($content, 0, 2);
$first3 = substr($content, 0, 3);
$first4 = substr($content, 0, 3);
$encodType = "";
if ($first3 == UTF8_BOM)
$encodType = 'UTF-8 BOM';
else if ($first4 == UTF32_BIG_ENDIAN_BOM)
$encodType = 'UTF-32BE';
else if ($first4 == UTF32_LITTLE_ENDIAN_BOM)
$encodType = 'UTF-32LE';
else if ($first2 == UTF16_BIG_ENDIAN_BOM)
$encodType = 'UTF-16BE';
else if ($first2 == UTF16_LITTLE_ENDIAN_BOM)
$encodType = 'UTF-16LE';
//下面的判断主要还是判断ANSI编码的·
if ($encodType == '') {//即默认创建的txt文本-ANSI编码的
$content = iconv("GBK", "UTF-8", $content);
} else if ($encodType == 'UTF-8 BOM') {//本来就是UTF-8不用转换
$content = $content;
} else {//其他的格式都转化为UTF-8就可以了
$content = iconv($encodType, "UTF-8", $content);
}
网友评论