计算莱文斯坦距离

Question

我正在尝试编写一个类，使用Levenshtein距离函数来比较指定文档中的文本与目录中所有其他文档的文本。

我有基本的思路，但不知道如何在PHP中编写代码。我来自C#背景，将提供尽可能详细的信息。

class ComputeLevenshtein
{
   public $filePathList = new Array(); //The array that stores the absolute path of all documents within a specified directory
   public $directory;
   public $filePath; //This is the document that will be compared for each document in a directory

    public function __construct() {
        $this->directory = //;  
       /* I'm stuck here, once a user registers, a separate directory is 
          named after the user. I need to be able to read the username 
          from the Session Variable once the user logs in. 
          I'll just have to pass it in as a parameter. 
          Do I have to create a session wrapper? 
          If it's too complex, 
          then I'll just start off with a static directory */
    }

        // Returns the array containing each filePath for every document in a directory.
        function computeFilePathList($directory) 
        {
           for each file in Directory
           {
             $filepath = file.FilePath(); //store the filepath in a variable
             $this->filePathList.add($filePath) //add the filepath to the array
           }

        }  

        function ($docFilePath) // returns the Levenshtein Distance
        {

            for each path in filePathList
            {
              $input= readDoc($docFilePath);
              $lev = levenshtein($input, readDoc($path));
            }

            return $lev;
        }

    function readDoc($docFilePath) // Returns the raw text of that doc
    {
      //I Have the code for reading the doc in a seperate function
      return $text;
    }
}

- user478636

---

为什么要重新实现 PHP 已经有的东西？php levenshtein - wkl

我不是在重新实现Levenshtein算法，只是用它来比较一个目录中文档的原始文本和其他文档列表中的文本。 - user478636

编写一个会话包装器是我个人认为的最佳选择。您可以通过创建名为User的类来实现这一点。 - greg0ire

Answer 1

这个怎么样：

class Levenshtein
{
    private $_p = array(); 

    public function __construct($input, $compare)
    {
        $this->_p['input']   = $input;
        $this->_p['compare'] = $compare; // string to check against
    }

    public function __get($property)
    {
        if (array_key_exists($property, $this->_p)) {
            return $this->_p[$property];
        }

        if (!isset($this->_p['dist']) && $property === 'dist') {
            $this->_p['dist'] = levenshtein($this->_p['input'],
                                            $this->_p['compare']);
            return $this->_p['dist'];
        }
    }
}

class DirectoryLevenshtein
{
    private $_directory;
    private $_filePath;
    private $_distances = array();

    public function __construct($directoryPath, $filePath = null)
    {
        if (!is_dir($directoryPath)) {
            throw new Exception("Path '$directoryPath' does not exist");
        }

        if (substr($directoryPath, -1) !== '/') {
            $directoryPath .= '/';
        }

        $this->_directory = $directoryPath;

        if ($filePath !== null) {
            if (!$this->setFilePath($filePath)) {
                throw new Exception("File '$filePath' is not readable");
            }
        }
    }

    public function __get($file)
    {
        if (array_key_exists($file, $this->_distances)) {
            return $this->_distances[$file];
        }

        if (is_readable($this->_directory . $file)) {
            if (empty($this->_filePath)) {
                return null;
            }

            $input   = file_get_contents($this->_filePath);
            $compare = file_get_contents($this->_directory . $file);
            $this->_distances[$file] = new Levenshtein($input, $compare);
            return $this->_distances[$file];
        }
    }

    public function getDirectoryContents()
    {
        $files = scandir($this->_directory);

        while ($files[0] === '.' || $files[0] === '..') {
            array_shift($files);
        }

        return $files;
    }

    public function setFilePath($filePath)
    {
        if (empty($this->_filePath) && is_readable($filePath)) {
            $this->_filePath = $filePath;
            return true;
        }

        return false;
    }
}

要使用它，可以按以下方式操作：

// could user session wrapper instead
$userDir = '/path/to/user/dirs/' . $_SESSION['user'];
// file to compare all files with 
$filePath = /path/to/file.txt

$dirLev = new DirectoryLevenshtein($userDir, $filePath);

// Files in directory
$files = $dirLev->getDirectoryContents();

// Distances
foreach ($files as $file) {
    echo "$file: {$dirLev->file->dist}\n";
}

- bearvrrr