<?php
/*
   This code is part of GOsa (https://gosa.gonicus.de)
   Copyright (C) 2005, Fabian Hickert

   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.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */


/******************************************* 
  Only function definition will follow here
/*******************************************


/* Reads all files in specified directory with contents an some inforations about the file */
/* Read all files with contents*/
/*                 |Folder="/var/ww...",
                   |        |Fileprefix="node"
                   |        |       |Filesuffix=".html"
                   |        |       |       |WithoutContent=false(This means : read content)
                   |        |       |       |          |Singlepage=false(Means read all, if w want to read single, specify its filename)"*/
function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
{
  global $replacements;

  $str    = array();  // Temporary variable
  $cnt    = 0;        // Array index creation
  $file   = "";       // Contains Filename

  $dir = opendir($basedir);

  $str['global']['start']       = $cnt;     // collect basic informations - Startpage
  $str['global']['basedir']     = $basedir; // collect basic informations - Basedirectory

  /* Startime for Benchmark */ 
  $start =   (time()+microtime());

  /* if singlepage == false -> Get all pages, */
  if(!$singlepage) {

    /* While theres is an unreaded file in our resource */
    while (($file = readdir($dir)) !== false) {

      /* Filter all files which arn't intressting */
      if((strstr($file,$suffix))&&($file!=".")&&($file!="..")&&(strstr($file,$prefix))){

        /* Collect informations */
        $str[$file]=array();
        $str[$file]['name']   = $file;
        $str[$file]['size']   = filesize($basedir.$file);

        /* Readfile conent too ? */
        if(!$onlyIndex){
          $str[$file]['content']  = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
          $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
        }

        /* Include file status, for debugging, not used in script yet */
        $str[$file]['stat']   = stat($basedir.$file);
        $cnt++;
      }
    }

    /* Only get on file*/
  }else{
    /* Pages read = 1 */       
    $cnt = 1;

    /* Prepare result*/
    $file                 = $singlepage;
    $str[$file]           = array();
    $str[$file]['name']   = $file;
    $str[$file]['size']   = filesize($basedir.$file);

    /* If onlyIndex == true skip reading content */
    if(!$onlyIndex){
      $str[$file]['content']  = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
      $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
    }

    /* Include file status, for debugging, not used in script yet */
    $str[$file]['stat']   = stat($basedir.$file);
  }

  /* Sort to  right order */
  asort($str);

  /* Endtime for Benchmark*/
  $end = (time()+microtime());
  $str['global']['cmptime'] = $end-$start;

  /* Number of pages readed */
  $str['global']['numpages']= $cnt;
  closedir($dir);
  return($str);
}


/* Read filecontent */
function getcontents($file)
{
  $str = "" ;   // Temporary variable for file contents 
  $tmp = "" ;   // Temporary varibale for partitial file contents

  /* open file and read*/
  $fp = fopen($file,"r");
  if($fp) {
    while($tmp = fread($fp,512))
    {
      $str.=  $tmp;
    }
  }else{
    return(false);
  }
  return($str);
}


/*Remove tags */
function remove_unwanted_tags($str,$replacements)
{
  $str=preg_replace($replacements['from'],$replacements['to'],$str);
  return($str);
}


/*Converts the all links to specified path, is needed to get simple navigation */
function linkwrapper($str,$link)
{
  $str = preg_replace("/HREF=\"http/i","target=\"_blank\" href=\"http",$str);
  $str = preg_replace("/HREF=\"/","href=\"".$link."?pg=",$str);
//  $str=str_replace("HREF=\"","href=\"".$link."?pg=",$str);  
  return($str);
}


/* Search content */
function search($arr,$word)
{
  global $minwordlength,$allowed_chars_in_searchword;
  /* Prepare Vars */ 
  $result                     =array(); // Search result, filename, + hits + hits per word + matches 
  $words                      =array(); // Temporary searchword handling
  $useablewords               =array(); // Temporary searchword handling
  $tryword                    = "";     // Temporary searchword handling
  $result['global']['maxhit'] = 0;
  unset($_SESSION['lastresults']);
  unset($_SESSION['parsed_search_keyword']);
  $_SESSION['parsed_search_keyword']="";

  /* prepare searchwords */
  $word   = trim($word);

  /* Filter all unusable chars */
  $word   = preg_replace($allowed_chars_in_searchword,"",$word);
  $words  = split(" ",str_replace("+"," ",$word));

  /* Check all wordlengths */
  foreach($words as $tryword){
    $tryword = trim($tryword);

    /* Filter words smaler than 3 chars */
    if(strlen($tryword)>=$minwordlength) {
      $_SESSION['parsed_search_keyword'].=$tryword." ";
      $useablewords[]=$tryword;
    }
  }

  /* Use words to search the content */
  foreach($arr as $key=>$val)
  {
    /* overallhits counts hits per page */
    $overallhits=0;

    /* Search all words */
    foreach($useablewords as $word)
    {
      /* Skip key global, it contains no file data - it is a summary info*/
      if($key!="global")
      {
        /* Get all hits for the word in $matches*/
        preg_match_all("/".$word."/i",$arr[$key]['content'], $matches,PREG_OFFSET_CAPTURE);

        /* Filter in Tag results*/
        if(count($matches[0])){
          foreach($matches[0] as $num=>$hit){
            if(is_in_tag($arr[$key]['content'],$hit[1]))  {
              unset($matches[0][$num]);    
            }    
          }
        }

        /* Count matches */
        $overallhits=$overallhits + count($matches[0]);    

        /* Save collected data */
        $result[$key]['hits'][$word]    = count($matches[0]); 
        $result[$key]['hits']['overall']= $overallhits;  

        /* Save max hits for page */
        if($overallhits > $result['global']['maxhit']){
          $result['global']['maxhit']=$overallhits;  
        }

        /* Add results for word to return value*/
        $result[$key]['match'][$word]=array();
        $result[$key]['match'][$word]=$matches[0];
      }
    }
  }

  /* Save result in Session, so we can mark words later, or go back to search, without searching again*/
  $_SESSION['lastresults'] = $result;
  return($result);
}


/* Detect 10 Best result entries, sort and call createResultEntry to create HTML output for  complete list */
function searchlist($arr,$res,$maxresults)
{
  $global = $res['global'];
  $topten = array();        // To detect 10 best solutions
  $ret    = "";             // return value
  unset($res['global']);

  /* Detect 10 best Sites */
  foreach($res as $key=>$val){

    /* Skip results with no hits */
    if($val['hits']['overall']>0){
      $topten[$key] = $val['hits']['overall']; 
    }
  }

  /* Sort by hit position in content, to easier mark words */
  asort($topten);
  $topten = array_reverse($topten);
  $topten = (array_slice($topten,0,$maxresults));

  /* We have a result, an array with all content, an array with hits and position and we have the 10 best hits */
  /* Foreach */  
  foreach($topten as $name => $hits)  {
    $ret.= createResultEntry($arr[$name],$res[$name],$name,$global['maxhit']);    
  }

  /* appending footer message for resultlist */
  $ret.= "<br>
              ".sprintf(_("%s results for your search with the keyword %s interpreted as %s"), 
                            "<b>".count($topten)."</b>", 
                            "<b>".($_SESSION['search_string'])."</b>", 
                            "<b>".$_SESSION['parsed_search_keyword']."</b>");
  $ret.="<br>
        <br>";
  return($ret);
}


/* This function marks a string with the given search result for this string*/
function markup_page($arr,$res)
{
  global $pre_mark,$suf_mark;
  
  $ret    = "";             // return value
  $repl   = array();
  $posadd = 0;

  foreach($res['match'] as $word => $matches)   {
    foreach($matches as $matchnr=>$match)   {
      $repl[$match[1]]=$match[0];
    }
  }

  ksort($repl);

  foreach($repl as $position=>$word)  {
    $pos1 = strlen($arr);
    $arr= markword($arr,($position+$posadd),$word,$pre_mark,$suf_mark);
    $pos2 = strlen($arr);
    $posadd =$posadd + ($pos2 - $pos1);
  }
  return($arr); 
}


/* This function marks a single word with the specified prefix and suffix */
function markword($string,$position,$word,$prefix,$suffix)
{
  $wordlength   = strlen($word);
  $wholelength  = strlen($string); 

  $first = substr($string,0,$position);
  $last  = substr($string,($position+$wordlength),$wholelength);  

  return($first.$prefix.$word.$suffix.$last);
} 

/* Creates HTML output for a single search result entry */
function createResultEntry($entry,$res,$name,$max)
{
  $percentage = (int)(($res['hits']['overall'] / $max) * 100) ;
  $color  = dechex($percentage+150);
  $color2 = dechex(150 - $percentage);

  $entry['content'] = preg_replace("\"".$entry['headline']."\"","",$entry['content'],1);

  if(strlen($color)==1) $color = "0".$color;


  /* the object tag is needed for W3c */
  $str =  "<a href=\"?pg=".$name."&amp;mark=1\" title=\"".$percentage."% ".$entry['headline']."\">
          <object>
          <table summary=\"\"  width=\"98%\" align=\"center\">
            <tr>
              <td height=15>
                <b>".$entry['headline']."</b> -".htmlentities( substr(strip_tags($entry['content']),0,120))."...
              </td>
              <td width=50 valign=\"top\">".progressbar($percentage,50,8)."</td>
             </tr>
             <tr>
              <td colspan=2>
                <b>
                  ".htmlentities(sprintf(_("%s%% hit rate in file %s"),$percentage,$name))."
                </b>
              </td>
            </tr>
          </table>
          </object></a>
          ";
  $str.=  "<hr size=\"1\">";

  return($str);
}


/*Simple function to detect if we prepare to change a tag or visible text */
function is_in_tag($string,$pos)
{
  $pos1 = strpos($string,"<",$pos);
  $pos2 = strpos($string,">",$pos);

  if ($pos1 > $pos2)  {
    return(true);
  }else{
    return(false);
  }
}

/*Returns frist line of readable text, it should be the headline */
function getheader_from_content($str)
{
  $str = strip_tags($str);
  $pos = 0;
  $arr = split("\n",$str);
  foreach($arr as $possibleheadline){
    if(strlen($possibleheadline)>=3){
      return $possibleheadline; 
    }
  }
}

// vim:tabstop=2:expandtab:shiftwidth=2:filetype=php:syntax:ruler:
?>