Question

我已经设定了在非常有限的时间内在PHP中创建基本文本文件搜索引擎的挑战，几乎没有以前的编程知识这是一项非常艰巨的任务！

这是我们到目前为止所做的，它确实设法返回一个单词出现次数最多的文档（（s） - 如果有多个相同数量）。

问题是我们做的方式不是（至少不容易）让我们计算TF-IDF得分。 IDF已经完成，但是我们需要通过获取返回文档中的单词总数来计算TF，这就是我们遇到的问题。另一个问题是它只返回最高的文件，而我们无法让它返回每个文件的清单......即一个文件中有3个单词的“航空公司”，另外两个文件有一次他们被遗忘了，只有第一个被归还......

（剥离符号也存在一些问题，但我们解决了这个问题，尽管采用了抽取方法......）

以下是我们的内容：

<?php
$starttime = microtime();
$startarray = explode(" ", $starttime);
$starttime = $startarray[1] + $startarray[0];

if(isset($_GET['search']))
{
    $searchWord = $_GET['search'];
}
else
{
    $searchWord = null;
}

?>
<html>
<link href="style.css" rel="stylesheet" type="text/css">
<body>
<div id="wrapper">
    <div id="searchbar">
        <h1>PHP Search</h1>
        <form name='searchform' id='searchform' action='<?php echo $_SERVER['PHP_SELF']; ?>' method='get'>
          <input type='text' name='search' id='search' value='<?php echo $_GET['search']; ?>' />
            <input type='submit' value='Search' />
        </form>
        <br />
        <br />
    </div><!-- close searchbar -->
    <?php


//path to directory to scan
$directory = "./files/";

//get all image files with a .txt extension.
$files = glob("" . $directory . "*.txt");
$fileList = array();
//print each file name
foreach($files as $file)
{
$fileList[] =  $file;
}
//$fileList;


        function indexFile($file){
            $filename = $file;
            $fp = fopen($filename, 'r');
            $file_contents = fread($fp, filesize($filename));
            fclose($fp);

            $pat[0] = "/^\s+/";
            $pat[1] = "/\s{2,}/";
            $pat[2] = "/\s+\$/";
            $rep[0] = "";
            $rep[1] = " ";
            $rep[2] = "";

            $new_contents = preg_replace("/[^A-Za-z0-9\s\s+]/", "", $file_contents);
            $new_contents = preg_replace($pat, $rep, $new_contents);

            //COMMON WORDS WERE HERE
            include "commonwords.php";

            $lines = explode("\n", $new_contents);
            $lines2 = implode(" ", $lines); //string
            $lines2 = strtolower($lines2);

            //echo $lines2 . "<br><br>";

            $words = explode(" ", $lines2); //array
            //$words = $lines;
            $useful_words = array_diff($words, $commonWords);
            $useful_words = array_values($useful_words);
            print_r(count($useful_words));

            //echo '<pre>';
            $index = array_count_values($useful_words);
            arsort($index, SORT_NUMERIC);
            //print_r($index);
            //echo '</pre>';

            return $index;
        }
       // $file1 = indexFile ('airlines.txt'); //array
       // $file2 = indexFile ('africa.txt');  //array

        function merge_common_keys(){
            $arr = func_get_args();
            $num = func_num_args();

            $keys = array();
            $i = 0;
            for($i=0;$i<$num;++$i){
                $keys = array_merge($keys, array_keys($arr[$i]));
            }
            $keys = array_unique($keys);

            $merged = array();

            foreach($keys as $key){
                $merged[$key] = array();
                for($i=0;$i<$num;++$i){
                    $merged[$key][] = isset($arr[$i][$key])?$arr[$i][$key]:null;
                }
            }
            return $merged;
        }


    for ($i = 0; $i < count($fileList); $i++) {
        $fileArray[$i] = indexFile($fileList[$i]);
    }

        $merged = call_user_func_array('merge_common_keys',$fileArray);

        $searchQ = $merged[$searchWord];
        echo '<pre>';
        print_r($searchQ);
        echo '</pre>';


        //echo "hello2";
    $maxValue = 0;
    $num_docs = 0;
    $docID = array();
    $n = count($searchQ);
    for ($i=0 ; $i < $n ; $i++) {
        if ($searchQ[$i] > $maxValue) {
            $maxValue = $searchQ[$i];
            unset($docID);
            $docID[] = $i;
            //print_r(count($fileArray[$i]));
        }
        else if($searchQ[$i] == $maxValue){
            $docID[] = $i;
        }
        if (!empty($searchQ[$i])) {
            $num_docs++;
        }
    }
    print_r($n);
    print_r($num_docs);
      print_r($docID);
      if(is_array($docID)){
         for ($i = 0; $i < count($docID); $i++) {
            if ($maxValue == 1){$plural = '';}else{$plural = 's';}
            print_r ('<p><b>'.$searchWord . '</b> found in document <a href="'.$fileList[$docID[$i]].'">'.$fileList[$docID[$i]].'</a> '.$maxValue.' time'.$plural.'.</p>');
            $TF = $maxValue;
            //$TF2 = 1 + log($TF);
            echo "<br>$TF2<br>"; 
            $DF = $num_docs;
            $Non = $n / $num_docs;
            //echo "$Non";
            $IDF = (float) log10($Non);
            $TFxIDF = $TF2 * $IDF;
            //echo "$TFxIDF";
         }
      }


//1,2

//file_put_contents("demo2.txt", implode(" ", $useful_words));
if(isset($_GET['search']))
{
    $endtime = microtime();
    $endarray = explode(" ", $endtime);
    $endtime = $endarray[1] + $endarray[0];
    $totaltime = $endtime - $starttime; 
    $totaltime = round($totaltime,5);
    echo "<div id='timetaken'><p>This page loaded in $totaltime seconds.</p></div>";
}
?>
    </div><!-- close wrapper -->
</body>
</html>

Answer 1

使用str_word_count计算字数。

如何返回结果文档中的单词数以计算TF

1 个答案: