functions_search.php

这是php编的论坛的原代码

<?php
/***************************************************************************
*                              functions_search.php
*                              -------------------
*     begin                : Wed Sep 05 2001
*     copyright            : (C) 2002 The phpBB Group
*     email                : [e-mail]
*
*     $Id: functions_search.php,v 1.1.1.1 2003/02/11 22:27:32 wei.gao Exp $
*
****************************************************************************/

/***************************************************************************
 *
 *   This program is free software; you can redistribute it and/or modify
 *   it under the terms of the GNU General Public License as published by
 *   the Free Software Foundation; either version 2 of the License, or
 *   (at your option) any later version.
 *
 ***************************************************************************/

function clean_words($mode, &$entry, &$stopword_list, &$synonym_list)
{
	static $drop_char_match =   array('^', '$', '&', '(', ')', '<', '>', '`', '\'', '"', '|', ',', '@', '_', '?', '%', '-', '~', '+', '.', '[', ']', '{', '}', ':', '\\', '/', '=', '#', '\'', ';', '!');
	static $drop_char_replace = array(' ', ' ', ' ', ' ', ' ', ' ', ' ', '',  '',   ' ', ' ', ' ', ' ', '',  ' ', ' ', '',  ' ',  ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ' , ' ', ' ', ' ', ' ',  ' ', ' ');

	$entry = ' ' . strip_tags(strtolower($entry)) . ' ';

	if ( $mode == 'post' )
	{
		// Replace line endings by a space
		$entry = preg_replace('/[\n\r]/is', ' ', $entry); 
		// HTML entities like &nbsp;
		$entry = preg_replace('/\b&[a-z]+;\b/', ' ', $entry); 
		// Remove URL's
		$entry = preg_replace('/\b[a-z0-9]+:\/\/[a-z0-9\.\-]+(\/[a-z0-9\?\.%_\-\+=&\/]+)?/', ' ', $entry); 
		// Quickly remove BBcode.
		$entry = preg_replace('/\[img:[a-z0-9]{10,}\].*?\[\/img:[a-z0-9]{10,}\]/', ' ', $entry); 
		$entry = preg_replace('/\[\/?url(=.*?)?\]/', ' ', $entry);
		$entry = preg_replace('/\[\/?[a-z\*=\+\-]+(\:?[0-9a-z]+)?:[a-z0-9]{10,}(\:[a-z0-9]+)?=?.*?\]/', ' ', $entry);
	}
	else if ( $mode == 'search' ) 
	{
		$entry = str_replace(' +', ' and ', $entry);
		$entry = str_replace(' -', ' not ', $entry);
	}

	//
	// Filter out strange characters like ^, $, &, change "it's" to "its"
	//
	for($i = 0; $i < count($drop_char_match); $i++)
	{
		$entry =  str_replace($drop_char_match[$i], $drop_char_replace[$i], $entry);
	}

	if ( $mode == 'post' )
	{
		$entry = str_replace('*', ' ', $entry);

		// 'words' that consist of <3 or >20 characters are removed.
		$entry = preg_replace('/\b([a-z0-9]{1,2}|[a-z0-9]{21,})\b/',' ', $entry); 
	}

	if ( !empty($stopword_list) )
	{
		for ($j = 0; $j < count($stopword_list); $j++)
		{
			$stopword = trim($stopword_list[$j]);

			if ( $mode == 'post' || ( $stopword != 'not' && $stopword != 'and' && $stopword != 'or' ) )
			{
				$entry =  preg_replace('#\b' . preg_quote($stopword) . '\b#', ' ', $entry);
			}
		}
	}

	if ( !empty($synonym_list) )
	{
		for ($j = 0; $j < count($synonym_list); $j++)
		{
			list($replace_synonym, $match_synonym) = split(' ', trim(strtolower($synonym_list[$j])));
			if ( $mode == 'post' || ( $match_synonym != 'not' && $match_synonym != 'and' && $match_synonym != 'or' ) )
			{
				$entry =  preg_replace('#\b' . trim($match_synonym) . '\b#', ' ' . trim($replace_synonym) . ' ', $entry);
			}
		}
	}

	return $entry;
}

function split_words(&$entry, $mode = 'post')
{
	$rex = ( $mode == 'post' ) ? "/\b([\w钡-