欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

php中big5转utf8乱码怎么办?

程序员文章站 2022-03-09 13:19:37
...

php中big5转utf8乱码的解决办法:首先生成tab文件,并生成时要保证tab文件不存在;然后将指定页面转码测试;接着打印出文字库;最后big5转【utf-8】即可。

php中big5转utf8乱码怎么办?

php中big5转utf8乱码的解决办法:

第一步:生成tab文件,生成时要保证tab文件不存在才可以

writebig5UnicodeFile();

第二步:指定页面转码测试

testCode();

第三步:打印出文字库

printfCode();

<?php
//生成big5-unicode 编码文件
function loadBig5(){
    $fp = fopen( './big5-unicode.txt', 'r' );
    $big5_unicode_arr = array();
    while($one_line = fgets($fp)) {
        $one_line_arr = explode("\t",$one_line);
        $big5 = hexdec(trim($one_line_arr[0]));
        $unicode = trim($one_line_arr[1]);
        if(strpos($unicode,',')) {
            $unicode = ltrim(explode(',',$unicode)[0],'<');
        }
        
        $big5_unicode_arr[$big5] = hexdec($unicode);
    }
    
    return $big5_unicode_arr;
}
 
//追加形式写入文件
function putContent($content) {
    static $fp;
    if(!isset($fp)) {
        $fp = fopen( './big5-unicode-new.tab', 'a+' );
    }
    
    fwrite($fp,$content);
}
 
//生成tab文件
function writebig5UnicodeFile() {
    $big5_unicode_arr = loadBig5();
    $big5_unicod_content = array();
    $min = 2000;
    $max = 0;
    $max_unicode = 0;
    foreach($big5_unicode_arr as $big5 => $unicode) {
        $h = floor($big5/256);
        $l = $big5%256;
        $index = ($h-135)*256*3+$l*3;
        
        if($index<$min) {
            $min = $index;
        }
        
        if($max<$index) {
            $max = $index;
        }
        
        if($unicode>$max_unicode) {
            $max_unicode = $unicode;
        }
        
        $h_1 = floor($unicode/65536);
        $h_2 = floor($unicode/256);
        $h_3 = $unicode%256;
        
        $big5_unicod_content[$index] = chr($h_1).chr($h_2).chr($h_3);
    }
    
    for($i=0;$i<=$max;$i=$i+3) {
        if(!isset($big5_unicod_content[$i])) {
            $big5_unicod_content[$i] = chr(0).chr(0).chr(0);
        }
    }
    
    for($i=0;$i<=$max;$i=$i+3) {
        if(strlen($big5_unicod_content[$i]) == 3) {
            putContent($big5_unicod_content[$i]);
        }else{
            die('error');
        }
    }
}
 
//测试编辑结果
function testCode() {
    $content = file_get_contents( './temlate_2.html');
    echo b2u($content);
}
 
//打印出编码库文字
function printfCode() {
    $fp = fopen( './big5-unicode-new.tab', 'r' );
    $len = filesize('./big5-unicode-new.tab');
    $x = 0;
    $outstr = array();
    //     fseek( $fp, 21000 - 900 + 42*3);
    for($i=$x=0;$i<$len;$i=$i+3) {
        $uni = fread( $fp, 3 );
        $codenum = ord($uni[0])*65536 + ord($uni[1])*256 + ord($uni[2]);
        if($codenum == 0) {
            $outstr[$x++] = ' ';
        }elseif( $codenum < 0x80 ) {
            $outstr[$x++] = chr($codenum);
        }elseif($codenum < 0x800) {
            $outstr[$x++] = chr( 192 + $codenum / 64 );
            $outstr[$x++] = chr( 128 + $codenum % 64 );
 
        }elseif($codenum < 0x10000){
            $outstr[$x++] = chr( 224 + floor($codenum / 4096 ));
            $codenum = $codenum%4096;
            $outstr[$x++] = chr( 128 + floor($codenum / 64 ));
            $outstr[$x++] = chr( 128 + ($codenum % 64) );
        }else{
            $outstr[$x++] = chr( 240 + floor($codenum / 262144 ));
            $codenum = $codenum%262144;
            $outstr[$x++] = chr( 128 + floor($codenum / 4096 ));
            $codenum = $codenum%4096;
            $outstr[$x++] = chr( 128 + ($codenum / 64) );
            $outstr[$x++] = chr( 128 + ($codenum % 64) );
        }
    }
 
    echo join( '', $outstr);
}
 
//big5 转 utf-8
function b2u( $instr ) {
    $fp = fopen( './big5-unicode-new.tab', 'r' );
    $len = strlen($instr);
    $outstr = '';
    for( $i = $x = 0 ; $i < $len ; $i++ ) {
        $h = ord($instr[$i]);
        if( $h >= 135 ) {
            $l = ord($instr[$i+1]);
            
            fseek( $fp, ($h-135)*256*3+$l*3 );
            $uni = fread( $fp, 3 );
            
            $codenum = ord($uni[0])*65536 + ord($uni[1])*256 + ord($uni[2]);
            
            if($codenum == 0) {
                $outstr[$x++] = ' ';
            }elseif( $codenum < 0x80 ) {
                $outstr[$x++] = chr($codenum);
            }elseif($codenum < 0x800) {
                $outstr[$x++] = chr( 192 + $codenum / 64 );
                $outstr[$x++] = chr( 128 + $codenum % 64 );
                
            }elseif($codenum < 0x10000){
                $outstr[$x++] = chr( 224 + floor($codenum / 4096 ));
                $codenum = $codenum%4096;
                $outstr[$x++] = chr( 128 + floor($codenum / 64 ));
                $outstr[$x++] = chr( 128 + ($codenum % 64) );
            }else{
                $outstr[$x++] = chr( 240 + floor($codenum / 262144 ));
                $codenum = $codenum%262144;
                $outstr[$x++] = chr( 128 + floor($codenum / 4096 ));
                $codenum = $codenum%4096;
                $outstr[$x++] = chr( 128 + ($codenum / 64) );
                $outstr[$x++] = chr( 128 + ($codenum % 64) );
            }
            $i++;
        }
        else
            $outstr[$x++] = $instr[$i];
    }
    fclose($fp);
    if( $instr != '' )
        return join( '', $outstr);
}

相关学习推荐:PHP编程从入门到精通

以上就是php中big5转utf8乱码怎么办?的详细内容,更多请关注其它相关文章!

相关标签: php big5转utf8