使用linux系统下的GBK.gz和UTF-8.gz文件,实现gbk到utf8之间的相互转换

时间:2021-05-13 14:06:32

 GBK 转 UTF-8 (trans.php) :

#!/usr/bin/php
<?php
define('GBK', '/usr/share/i18n/charmaps/GBK.gz');
define('UTF8', '/usr/share/i18n/charmaps/UTF-8.gz');
define('INPUT_FILE', 't.txt');
define('OUTPUT_FILE', 'a.txt');
$source = file_get_contents(INPUT_FILE);
$source_utf8 = '';
$len = strlen($source);
for($i = 0; $i < $len; $i++) :
    if(ord($source{$i}) < 128) :
        $source_utf8 .= $source{$i};
        continue;
    endif;
    $word_gbk = '/x'.base_convert(unpack('C', $source{$i})[1], 10, 16).'/x'.base_convert(unpack('C', $source{$i+1})[1], 10, 16);
    $i ++;
    $word_unicode = exec('gzip -dc '.GBK.' |awk \'/CJK/ { if ($2 == "'.$word_gbk.'") print $1}\'');
    $word_unicode = (int) base_convert(str_replace(array('<U', '>'), '', $word_unicode), 16, 10);
    for($j = 1; $line = exec('gzip -dc '.UTF8.' |grep "<CJK>"|sed -n '.$j.'p'); $j++) {    
        list($unicode_wrap, $utf8_code) = explode(' ', $line);
        list($unicode_wrap_min, $unicode_wrap_max) = explode('..', $unicode_wrap);
        $unicode_wrap_min = (int) base_convert(str_replace(array('<U', '>'), '', $unicode_wrap_min), 16, 10);
        $unicode_wrap_max = (int) base_convert(str_replace(array('<U', '>'), '', $unicode_wrap_max), 16, 10);
        if($word_unicode > $unicode_wrap_min and $word_unicode < $unicode_wrap_max) break;
    }
    foreach(str_split($utf8_code, 4) as $key => $char) {
        if($key == 2)
            $source_utf8 .= pack('C', (int) base_convert(substr($char, 2, 2), 16, 10) + ($word_unicode - $unicode_wrap_min));
        else
            $source_utf8 .= pack('C', (int) base_convert(substr($char, 2, 2), 16, 10));
    }
endfor;
file_put_contents(OUTPUT_FILE, $source_utf8);
?>

测试文件内容 t.txt:

sdf啊4h海星kdi3大小k35

输出文件内容 a.txt:

sdf啊4h海星kdi3大小k35

执行命令: php ./trans.php

查看结果:hexdump -C t.txt && hexdump -C a.txt

00000000  73 64 66 b0 a1 34 68 ba  a3 d0 c7 6b 64 69 33 b4  |sdf..4h....kdi3.|
00000010  f3 d0 a1 6b 33 35                                 |...k35|
00000016
00000000  73 64 66 e5 95 8a 34 68  e6 b5 b7 e6 98 9f 6b 64  |sdf...4h......kd|
00000010  69 33 e5 a4 a7 e5 b0 8f  6b 33 35                 |i3......k35|
0000001b

utf-8 转 gbk 待续。。。