word_counter.php

散列函数源代码,散列表通常是关键字和值对应的数据结构,散列函数用于把关键字映射到相应的数组索引号,由于散列表中每个元素访问到的概率不同,所以应该选用不同的散列函数,以提高程序的查找效率.

<?php

// Count words in a text
// (c) Peter Kankowski, 2008

$lines = file('php://stdin');
$words = array();

foreach($lines as $line) {
   $line = rtrim($line);
   if(preg_match('/^[IVXLC]+$/', $line) > 0) // skip a sonnet number
      continue;
   $line = preg_replace('/[^a-zA-Z\' ]/', ' ', $line); // remove punctuation
   $line = strtolower($line);
   foreach(explode(' ', $line) as $word) {
      if(strlen($word) == 0)
         continue;
      if(isset($words[$word]))
         $words[$word]++;
      else
         $words[$word] = 1;
   }
}

arsort($words, SORT_NUMERIC);

foreach($words as $word => $count) {
   //echo "$word $count\r\n";
   echo "$word\r\n";
}


?>