php读取淘宝数据包csv文件 unicode ucs-2 utf-16 中文乱码问题解决

 因为要解决这个问题 学习了很多关于编码、字符集的内容

下面是解决方案

 

  function fopen_utf8($filename){
    $encoding='';
    $handle = fopen($filename, 'r');
    $bom = fread($handle, 2);
//    fclose($handle);
    rewind($handle);
 
    if($bom === chr(0xff).chr(0xfe)  || $bom === chr(0xfe).chr(0xff)){
            // UTF16 Byte Order Mark present
            $encoding = 'UTF-16';
    } else {
        $file_sample = fread($handle, 1000) + 'e'; //read first 1000 bytes
        // + e is a workaround for mb_string bug
        rewind($handle);
 
        $encoding = mb_detect_encoding($file_sample , 'UTF-8, UTF-7, ASCII, EUC-JP,SJIS, eucJP-win, SJIS-win, JIS, ISO-2022-JP');
    }
    if ($encoding){
        stream_filter_append($handle, 'convert.iconv.'.$encoding.'/UTF-8');
    }
    return  ($handle);
}

 

	$file='back/tmpData/20111103.csv';
  
 
  if (($handle = fopen_utf8($file, "r")) === FALSE) return;
    while (($cols = fgetcsv($handle, 1000, "\t")) !== FALSE) {
        echo $cols[0];
         
    }

 

 

参考资料

 

http://www.wenlingnet.com/index.php/125/