[Comoblog-commit] comoblog/modules/mod_search/include blog_search.inc.php,NONE,1.1

[Mark W. \(a. serialmonkey\) <mar...@us...>]

Update of /cvsroot/comoblog/comoblog/modules/mod_search/include
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv14620/mod_search/include

Added Files:
	blog_search.inc.php 
Log Message:
RFE: 1280296 - mod_search module

--- NEW FILE: blog_search.inc.php ---
<?php
include_once (dirname(__FILE__).'/../../../include/config.inc.php');

function do_search ($search_string)
{
    $search_string = strtolower($search_string);
    $posts = array();
    
    $query = "select distinct post_id from ".CFG_MYSQL_TABPREFIX."blog_search_index 
              where word like '%".$search_string."%'";
              
    $res = mysql_query($query);

    if (!$res || !mysql_num_rows($res))
      return (false);
    
    while ($row = mysql_fetch_array($res, MYSQL_NUM)) 
    {
        $post_id = $row[0];
        $post = post_details ($post_id);
        $posts[$post_id] = $post;   
    }
    
    return $posts;
}

function mass_index ()
{
   // Clear index table
   echo "Running Mass Index Function ...\n";
   echo "Removing all previous search index entries\n";
   $query = "delete from ".CFG_MYSQL_TABPREFIX."blog_search_index";
   $res = mysql_query($query);

   echo "Looping through all blog entries and indexing\n";
   // Loop through all posts
   $query = "select post_id from ".CFG_MYSQL_TABPREFIX."posts";
   $res = mysql_query($query);

    if (!$res || !mysql_num_rows($res))
    {
      echo "No posts found to index\n";
      return (false);
    }

    $cnt = 0; 

    while ($row = mysql_fetch_array($res, MYSQL_NUM))
    {
        $post_id = $row[0];
        $post = post_details($post_id);
	$post['id'] = $post_id;
        index($post);
        $cnt = $cnt + 1;
    }
    echo "Completed indexing of $cnt posts\n";
}

function unindex ($post)
{
   $query = "delete from ".CFG_MYSQL_TABPREFIX."blog_search_index where post_id = '".$post['id']."'";
   $res = mysql_query($query);
}
function index ($post) 
{
   process_text( $post['post_mail_body'], $post['post_id'] );
   process_text( $post['post_mail_subject'], $post['post_id'] );
}   

function process_text ($body, $id)
{
   $body = filter_html($body);
   $body = filter_punc($body);
   
   $pieces = explode(' ', $body);

   foreach ($pieces as $piece)
   {
        $piece = trim($piece);
        if (strlen($piece) > 3 && strcmp($piece, "") != 0 && !is_excluded($piece))
            insert_index($id, $piece);
   }
    
}

function filter_html($body)
{
    $search = array ("'<script[^>]*?>.*?</script>'si",  // Strip out javascript
                 "'<[\/\!]*?[^<>]*?>'si",          // Strip out HTML tags
                 "'([\r\n])[\s]+'",                // Strip out white space
                 "'&(quot|#34);'i",                // Replace HTML entities
                 "'&(amp|#38);'i",
                 "'&(lt|#60);'i",
                 "'&(gt|#62);'i",
                 "'&(nbsp|#160);'i",
                 "'&(iexcl|#161);'i",
                 "'&(cent|#162);'i",
                 "'&(pound|#163);'i",
                 "'&(copy|#169);'i",
                 "'&#(\d+);'e");                    // evaluate as php

    $replace = array ("",
                 "",
                 " ",
                 "\"",
                 "&",
                 "<",
                 ">",
                 " ",
                 chr(161),
                 chr(162),
                 chr(163),
                 chr(169),
                 "chr(\\1)");

    $body = preg_replace($search, $replace, $body);
    return $body;
}    

function filter_punc($body)
{
    $search = "/(,|\.|<|>|\?|\/|;|:|\"|'|{|}|\[|\]|\\\|\||=|-|_|\+|\(|\)|\*|&|\^|%|\\$|#|@|!|~|`)/";
    $replace = " ";
    $body = preg_replace ($search, $replace, $body);

    return $body;
}

function insert_index ($post_id, $word)
{
   $query = "
               insert into    ".CFG_MYSQL_TABPREFIX."blog_search_index
               (post_id, word)
               values        ('".   $post_id     ."',
                              '".   strtolower($word)    ."')";
                              
   $res = mysql_query($query);
   
}

function is_excluded($word)
{
    $excludes = explode(',', CFG_MOD_BLOG_SEARCH_EXCLUSIONS);
    
    foreach ($excludes as $exclusion)
    {
        if (strcasecmp($exclusion,$word) == 0)
            return(true);
    }   
    
    return (false);
}
?>