PHP LZW二进制解压功能

Question

我一直在寻找在互联网和无法找到PHP的LZW压缩实现与这些JavaScript函数输出的数据的工作原理：

function lzw_encode(s) { 
    var dict = {}; 
    var data = (s + "").split(""); 
    var out = []; 
    var currChar; 
    var phrase = data[0]; 
    var code = 256; 
    for (var i=1; i<data.length; i++) { 
     currChar=data[i]; 
     if (dict[phrase + currChar] != null) { 
      phrase += currChar; 
     } 
     else { 
      out.push(phrase.length > 1 ? dict[phrase] : phrase.charCodeAt(0)); 
      dict[phrase + currChar] = code; 
      code++; 
      phrase=currChar; 
     } 
    } 
    out.push(phrase.length > 1 ? dict[phrase] : phrase.charCodeAt(0)); 
    for (var i=0; i<out.length; i++) { 
     out[i] = String.fromCharCode(out[i]); 
    } 
    return out.join(""); 
} 

function lzw_decode(s) { 
    var dict = {}; 
    var data = (s + "").split(""); 
    var currChar = data[0]; 
    var oldPhrase = currChar; 
    var out = [currChar]; 
    var code = 256; 
    var phrase; 
    debugger; 
    for (var i=1; i<data.length; i++) { 
     var currCode = data[i].charCodeAt(0); 
     if (currCode < 256) { 
      phrase = data[i]; 
     } 
     else { 
      phrase = dict[currCode] ? dict[currCode] : (oldPhrase + currChar); 
     } 
     out.push(phrase); 
     currChar = phrase.charAt(0); 
     dict[code] = oldPhrase + currChar; 
     code++; 
     oldPhrase = phrase; 
    } 
    return out.join(""); 
} 

我真的只需要一个PHP中的解压缩算法，可以与上面的压缩javascript函数一起使用。

上述lzw_encode功能编码“这是压缩函数的测试”作为“这一测试ofĈhecomprĊsionfunctěn”

我发现的库或者是越野车（HTTP：//代码.google.com/p/php-lzw /）或不输入UTC字符。

任何帮助将不胜感激，

谢谢！

Answer 1

我移植和测试，对你有PHP：

function lzw_decode($s) { 
    mb_internal_encoding('UTF-8'); 

    $dict = array(); 
    $currChar = mb_substr($s, 0, 1); 
    $oldPhrase = $currChar; 
    $out = array($currChar); 
    $code = 256; 
    $phrase = ''; 

    for ($i=1; $i < mb_strlen($s); $i++) { 
     $currCode = implode(unpack('N*', str_pad(iconv('UTF-8', 'UTF-16BE', mb_substr($s, $i, 1)), 4, "\x00", STR_PAD_LEFT))); 
     if($currCode < 256) { 
      $phrase = mb_substr($s, $i, 1); 
     } else { 
     $phrase = $dict[$currCode] ? $dict[$currCode] : ($oldPhrase.$currChar); 
     } 
     $out[] = $phrase; 
     $currChar = mb_substr($phrase, 0, 1); 
     $dict[$code] = $oldPhrase.$currChar; 
     $code++; 
     $oldPhrase = $phrase; 
    } 
    var_dump($dict); 
    return(implode($out)); 
} 

Answer 2

现在有这个PHP extension！

lzw_decompress_file('3240_05_1948-1998.tar.Z', '3240_05_1948-1998.tar'); 
$archive = new PharData('/tmp/3240_05_1948-1998.tar'); 
mkdir('unpacked'); 
$archive->extractTo('unpacked');