php 读取 和 生成 unicode csv 文件的例子

=======先介绍下BOM==============

Bytes  Encoding Form
EF BB BF UTF-8
FF FE UTF-16 aka UCS-2, little endian
FE FF UTF-16 aka UCS-2, big endian
00 00 FF FE UTF-32 aka UCS-4, little endian.
00 00 FE FF UTF-32 aka UCS-4, big-endian.

=======================

读取 unicode csv 文件

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);
}

生成 unicode csv （此php文件一定要是无BOM的UTF-8编码文件）

?View Code PHP
$content=iconv("UTF-8","UTF-16LE",$content);
$content = "＼xFF＼xFE".$content; //添加BOM
header("Content-type: text/csv;charset=UTF-16LE") ;
header("Content-Disposition: attachment; filename=test.csv");
 
再介绍一个 操作 ANSI 编码 以 "," 隔开的 操作类
 
// 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));
 
 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';
 }
?>