",
+ /* picture replacements */
+// "",
+ );
-/*******************************************
- 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*/
@@ -51,6 +162,10 @@ function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
/* While theres is an unreaded file in our resource */
while (($file = readdir($dir)) !== false) {
+
+ if((is_dir($basedir."/".$file))&&($file != "..")&&($file[0]!=".")){
+ $str[$file]=(readfiles($basedir."/".$file."/",$prefix,$suffix,$onlyIndex,false));
+ }
/* Filter all files which arn't intressting */
if((strstr($file,$suffix))&&($file!=".")&&($file!="..")&&(strstr($file,$prefix))){
@@ -62,7 +177,8 @@ function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
/* Readfile conent too ? */
if(!$onlyIndex){
- $str[$file]['content']= remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
+ $str[$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 */
@@ -84,7 +200,8 @@ function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
/* If onlyIndex == true skip reading content */
if(!$onlyIndex){
- $str[$file]['content']= remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
+ $str[$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 */
@@ -104,6 +221,7 @@ function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
return($str);
}
+
/* Read filecontent */
function getcontents($file)
{
@@ -123,6 +241,7 @@ function getcontents($file)
return($str);
}
+
/*Remove tags */
function remove_unwanted_tags($str,$replacements)
{
@@ -130,13 +249,17 @@ function remove_unwanted_tags($str,$replacements)
return($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)
{
@@ -151,6 +274,8 @@ function search($arr,$word)
unset($_SESSION['parsed_search_keyword']);
$_SESSION['parsed_search_keyword']="";
+ error_reporting(E_ALL);
+
/* prepare searchwords */
$word = trim($word);
@@ -170,44 +295,47 @@ function search($arr,$word)
}
/* Use words to search the content */
- foreach($arr as $key=>$val)
+ foreach($arr as $keys=>$vals)
{
- /* overallhits counts hits per page */
- $overallhits=0;
+ foreach($vals 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")
+ /* Search all words */
+ foreach($useablewords as $word)
{
- /* 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][$num]);
- }
+ /* Skip key global, it contains no file data - it is a summary info*/
+ if($key!="global")
+ {
+
+ /* Get all hits for the word in $matches*/
+ preg_match_all("/".$word."/i",$arr[$keys][$key]['content'], $matches,PREG_OFFSET_CAPTURE);
+
+ /* Filter in Tag results*/
+ if(count($matches[0])){
+ foreach($matches[0] as $num=>$hit){
+ if(isset($arr[$keys][$key]['content']) && (is_in_tag($arr[$keys][$key]['content'],$hit[1]))){
+ unset($matches[0][$num]);
+ }
+ }
}
- }
- /* Count matches */
- $overallhits=$overallhits + count($matches[0]);
+ /* Count matches */
+ $overallhits=$overallhits + count($matches[0]);
- /* Save collected data */
- $result[$key]['hits'][$word] = count($matches[0]);
- $result[$key]['hits']['overall']= $overallhits;
+ /* Save collected data */
+ $result[$keys][$key]['hits'][$word] = count($matches[0]);
+ $result[$keys][$key]['hits']['overall']= $overallhits;
- /* Save max hits for page */
- if($overallhits > $result['global']['maxhit']){
- $result['global']['maxhit']=$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];
+ /* Add results for word to return value*/
+ $result[$keys][$key]['match'][$word]=array();
+ $result[$keys][$key]['match'][$word]=$matches[0];
+ }
}
}
}
@@ -217,6 +345,7 @@ function search($arr,$word)
return($result);
}
+
/* Detect 10 Best result entries, sort and call createResultEntry to create HTML output for complete list */
function searchlist($arr,$res,$maxresults)
{
@@ -226,11 +355,11 @@ function searchlist($arr,$res,$maxresults)
unset($res['global']);
/* Detect 10 best Sites */
- foreach($res as $key=>$val){
-
+ foreach($res as $key=>$resa)
+ foreach($resa as $keya=>$val){
/* Skip results with no hits */
if($val['hits']['overall']>0){
- $topten[$key] = $val['hits']['overall'];
+ $topten[$key."/".$keya] = $val['hits']['overall'];
}
}
@@ -239,22 +368,34 @@ function searchlist($arr,$res,$maxresults)
$topten = array_reverse($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,$global['maxhit']);
+ foreach($topten as $key => $hits) {
+
+ $ks = split("\/",$key);
+ $k1 = $ks[0];
+ $k2 = $ks[1];
+
+ $ret.= createResultEntry($arr[$k1][$k2],$res[$k1][$k2],$key,$global['maxhit']);
}
/* appending footer message for resultlist */
- $ret.= " ".count($topten)." - "._("Results for your search with the keyword")." ".htmlentities($_SESSION['search_string']).""._(" interpreted as ")."".$_SESSION['parsed_search_keyword']."";
-
+ $ret.= "
+ ".sprintf(_("%s results for your search with the keyword %s"),
+ "".count($topten)."",
+ "".$_SESSION['parsed_search_keyword']."");
+ $ret.="
+ ";
return($ret);
}
+
/* This function marks a string with the given search result for this string*/
function markup_page($arr,$res)
{
-global $pre_mark,$suf_mark;
+ global $pre_mark,$suf_mark;
+
$ret = ""; // return value
$repl = array();
$posadd = 0;
@@ -266,7 +407,7 @@ global $pre_mark,$suf_mark;
}
ksort($repl);
-
+
foreach($repl as $position=>$word) {
$pos1 = strlen($arr);
$arr= markword($arr,($position+$posadd),$word,$pre_mark,$suf_mark);
@@ -276,6 +417,7 @@ global $pre_mark,$suf_mark;
return($arr);
}
+
/* This function marks a single word with the specified prefix and suffix */
function markword($string,$position,$word,$prefix,$suffix)
{
@@ -288,25 +430,55 @@ function markword($string,$position,$word,$prefix,$suffix)
return($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) ;
-
- $str = "".$percentage."% "._("hit rate in following file ").$name." " ;
- $str.= substr(strip_tags($entry['content']),0,200);
- $str.= "";
+ $color = dechex($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 = "
+
+ ";
+ $str.= "";
return($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);
-
+ $pos1 = $pos2 = 0;
+ if(preg_match("/",$string)){
+ $pos1 = strpos($string,"<",$pos);
+ }
+ if(preg_match("/>/",$string)){
+ $pos2 = strpos($string,">",$pos);
+ }
if ($pos1 > $pos2) {
return(true);
}else{
@@ -314,5 +486,18 @@ function is_in_tag($string,$pos)
}
}
+/*Returns frist line of readable text, it should be the headline */
+function getheader_from_content($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:
?>