Skip to content
Snippets Groups Projects
Commit 86187a80 authored by tho's avatar tho
Browse files

added search engine

parent f3b5a277
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Examples/Mainpage.dox
+ 5
− 3
View file @ 86187a80
......@@ -62,6 +62,8 @@
specific type of socket which returns ethernet packets directly from the network wire. By
uncommenting the last line, you may switch the interface into promiscuous mode.
\until //
We will now read packets from the socket forever, that is until the user hits Ctrl-C
\skip while
......@@ -158,9 +160,9 @@
\see \ref components \n
\ref build \n
<a href="../../Socket/doc/html/index.html"><b>libSocket API reference</b></a> \n
<a href="../../Packets/doc/html/index.html"><b>libPackets API reference</b></a> \n
<a href="../../Utils/doc/html/index.html"><b>libUtils API reference</b></a>
<a href="../../../Socket/doc/html/index.html"><b>libSocket API reference</b></a> \n
<a href="../../../Packets/doc/html/index.html"><b>libPackets API reference</b></a> \n
<a href="../../../Utils/doc/html/index.html"><b>libUtils API reference</b></a>
*/
......
doclib/Doxyfile.global
+ 1
− 0
View file @ 86187a80
......@@ -21,6 +21,7 @@ INTERNAL_DOCS = YES
SOURCE_BROWSER = YES
ALPHABETICAL_INDEX = YES
COLS_IN_ALPHA_INDEX = 3
SEARCHENGINE = YES
MACRO_EXPANSION = YES
EXPAND_ONLY_PREDEF = YES
......
doclib/doxy-header-overview.html
+ 5
− 0
View file @ 86187a80
......@@ -13,6 +13,11 @@ div.tabs ul li.$projectname a { background-color: #EDE497; }
<div id="head">
<h1>SENF Extensible Network Framework</h1>
<h2>Introduction and Overview</h2>
<div id="search">
<form action="../../doclib/search.php" method="get">
Search: <input type="text" name="query" size="20" accesskey="s"/>
</form>
</div>
</div>
<div id="content1">
......
doclib/doxy-header.html
+ 5
− 0
View file @ 86187a80
......@@ -13,6 +13,11 @@ div.tabs ul li.$projectname a { background-color: #EDE497; }
<div id="head">
<h1>SENF Extensible Network Framework</h1>
<h2>Documentation and API reference</h2>
<div id="search">
<form action="../../../doclib/search.php" method="get">
Search: <input type="text" name="query" size="20" accesskey="s"/>
</form>
</div>
</div>
<div id="content1">
......
doclib/html-munge.xsl
+ 4
− 1
View file @ 86187a80
......@@ -10,6 +10,9 @@
</xsl:copy>
</xsl:template>
<xsl:template match="li[form]">
</xsl:template>
<!-- Add 'class' attribute to some special paragraphs/lists -->
<xsl:template name="add-class">
......@@ -74,5 +77,5 @@
<xsl:with-param name="class">anchor</xsl:with-param>
</xsl:call-template>
</xsl:template>
</xsl:stylesheet>
doclib/search.php 0 → 100644
+ 64
− 0
View file @ 86187a80
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>Search</title>
<link href="../doc/html/doxygen.css" rel="stylesheet" type="text/css">
<link href="senf.css" rel="stylesheet" type="text/css">
<?php include 'search_functions.php'; ?>
</head>
<body>
<div id="head">
<h1>SENF Extensible Network Framework</h1>
<h2>Search Results</h2>
<div id="search">
<form action="search.php" method="get">
Search: <?php inputfield(); ?>
</form>
</div>
</div>
<div id="content1">
<div id="content2">
<div class="tabs menu">
<ul>
<li class="Overview"><a href="../doc/html/index.html">Overview</a></li>
<li class="libSocket"><a href="../Socket/doc/html/index.html">libSocket</a></li>
<li class="libPackets"><a href="../Packets/doc/html/index.html">libPackets</a></li>
<li class="libScheduler"><a href="../Scheduler/doc/html/index.html">libScheduler</a></li>
<li class="libUtils"><a href="../Utils/doc/html/index.html">libUtils</a></li>
<li class="Examples"><a href="../Examples/doc/html/index.html">Examples</a></li>
<li class="SENFSCons"><a href="../senfscons/doc/html/index.html">SENFSCons</a></li>
</ul>
</div>
<div class="tabs">
<ul>
<li><a href="xref.html">Open Issues</a></li>
<li><a href="http://svn.berlios.de/wsvn/senf/?op=log&rev=0&sc=0&isdir=1">SVN ChangeLog</a></li>
<li><a href="http://developer.berlios.de/projects/senf">SENF @ BerliOS</a></li>
<li><a href="http://openfacts.berlios.de/index-en.phtml?title=SENF+Network+Framework">Wiki</a></li>
</ul>
</div>
<!-- Generated by Doxygen 1.4.7 -->
<div class="tabs">
<ul>
<li><a href="index.html"><span>Main&nbsp;Page</span></a></li>
<li><a href="pages.html"><span>Related&nbsp;Pages</span></a></li>
<hr style="width:0px;border:none;clear:both;margin:0;padding:0" />
</div>
<?php search(); ?>
<hr style="width:0px;border:none;clear:both;margin:0;padding:0" />
</div>
</div>
<div id="footer">
<span>
<a href="mailto:senf-dev@lists.berlios.de">Contact: senf-dev@lists.berlios.de</a> |
Copyright &copy; 2006 Fraunhofer Gesellschaft, SatCom, Stefan Bund
</span>
</div>
</body></html>
doclib/search_functions.php 0 → 100644
+ 381
− 0
View file @ 86187a80
<?php
function search_results()
{
return "Search Results";
}
function matches_text($num)
{
if ($num==0)
{
return "Sorry, no documents matching your query.";
}
else if ($num==1)
{
return "Found <b>1</b> document matching your query.";
}
else // $num>1
{
return "Found <b>$num</b> documents matching your query. Showing best matches first.";
}
}
function report_matches()
{
return "Matches: ";
}
function inputfield()
{
$query="";
if (array_key_exists("query", $_GET))
{
$query=$_GET["query"];
}
echo "<input type=\"text\" name=\"query\" value=\"$query\" size=\"20\" accesskey=\"s\"/>";
}
function readInt($file)
{
$b1 = ord(fgetc($file)); $b2 = ord(fgetc($file));
$b3 = ord(fgetc($file)); $b4 = ord(fgetc($file));
return ($b1<<24)|($b2<<16)|($b3<<8)|$b4;
}
function readString($file)
{
$result="";
while (ord($c=fgetc($file))) $result.=$c;
return $result;
}
function readHeader($file)
{
$header =fgetc($file); $header.=fgetc($file);
$header.=fgetc($file); $header.=fgetc($file);
return $header;
}
function computeIndex($word)
{
// Fast string hashing
//$lword = strtolower($word);
//$l = strlen($lword);
//for ($i=0;$i<$l;$i++)
//{
// $c = ord($lword{$i});
// $v = (($v & 0xfc00) ^ ($v << 6) ^ $c) & 0xffff;
//}
//return $v;
// Simple hashing that allows for substring search
if (strlen($word)<2) return -1;
// high char of the index
$hi = ord($word{0});
if ($hi==0) return -1;
// low char of the index
$lo = ord($word{1});
if ($lo==0) return -1;
// return index
return $hi*256+$lo;
}
function do_search($path, $file,$word,&$statsList)
{
$index = computeIndex($word);
if ($index!=-1) // found a valid index
{
fseek($file,$index*4+4); // 4 bytes per entry, skip header
$index = readInt($file);
if ($index) // found words matching the hash key
{
$start=sizeof($statsList);
$count=$start;
fseek($file,$index);
$w = readString($file);
while ($w)
{
$statIdx = readInt($file);
if ($word==substr($w,0,strlen($word)))
{ // found word that matches (as substring)
$statsList[$count++]=array(
"word"=>$word,
"match"=>$w,
"index"=>$statIdx,
"full"=>strlen($w)==strlen($word),
"docs"=>array()
);
}
$w = readString($file);
}
$totalHi=0;
$totalFreqHi=0;
$totalFreqLo=0;
for ($count=$start;$count<sizeof($statsList);$count++)
{
$statInfo = &$statsList[$count];
$multiplier = 1;
// whole word matches have a double weight
if ($statInfo["full"]) $multiplier=2;
fseek($file,$statInfo["index"]);
$numDocs = readInt($file);
$docInfo = array();
// read docs info + occurrence frequency of the word
for ($i=0;$i<$numDocs;$i++)
{
$idx=readInt($file);
$freq=readInt($file);
$docInfo[$i]=array("idx" => $idx,
"freq" => $freq>>1,
"rank" => 0.0,
"hi" => $freq&1
);
if ($freq&1) // word occurs in high priority doc
{
$totalHi++;
$totalFreqHi+=$freq*$multiplier;
}
else // word occurs in low priority doc
{
$totalFreqLo+=$freq*$multiplier;
}
}
// read name and url info for the doc
for ($i=0;$i<$numDocs;$i++)
{
fseek($file,$docInfo[$i]["idx"]);
$docInfo[$i]["name"]=readString($file);
$docInfo[$i]["url"]=$path.readString($file);
}
$statInfo["docs"]=$docInfo;
}
$totalFreq=($totalHi+1)*$totalFreqLo + $totalFreqHi;
for ($count=$start;$count<sizeof($statsList);$count++)
{
$statInfo = &$statsList[$count];
$multiplier = 1;
// whole word matches have a double weight
if ($statInfo["full"]) $multiplier=2;
for ($i=0;$i<sizeof($statInfo["docs"]);$i++)
{
$docInfo = &$statInfo["docs"];
// compute frequency rank of the word in each doc
$freq=$docInfo[$i]["freq"];
if ($docInfo[$i]["hi"])
{
$statInfo["docs"][$i]["rank"]=
(float)($freq*$multiplier+$totalFreqLo)/$totalFreq;
}
else
{
$statInfo["docs"][$i]["rank"]=
(float)($freq*$multiplier)/$totalFreq;
}
}
}
}
}
return $statsList;
}
function combine_results($results,&$docs)
{
foreach ($results as $wordInfo)
{
$docsList = &$wordInfo["docs"];
foreach ($docsList as $di)
{
$key=$di["url"];
$rank=$di["rank"];
if (in_array($key, array_keys($docs)))
{
$docs[$key]["rank"]+=$rank;
}
else
{
$docs[$key] = array("url"=>$key,
"name"=>$di["name"],
"rank"=>$rank
);
}
$docs[$key]["words"][] = array(
"word"=>$wordInfo["word"],
"match"=>$wordInfo["match"],
"freq"=>$di["freq"]
);
}
}
return $docs;
}
function filter_results($docs,&$requiredWords,&$forbiddenWords)
{
$filteredDocs=array();
while (list ($key, $val) = each ($docs))
{
$words = &$docs[$key]["words"];
$copy=1; // copy entry by default
if (sizeof($requiredWords)>0)
{
foreach ($requiredWords as $reqWord)
{
$found=0;
foreach ($words as $wordInfo)
{
$found = $wordInfo["word"]==$reqWord;
if ($found) break;
}
if (!$found)
{
$copy=0; // document contains none of the required words
break;
}
}
}
if (sizeof($forbiddenWords)>0)
{
foreach ($words as $wordInfo)
{
if (in_array($wordInfo["word"],$forbiddenWords))
{
$copy=0; // document contains a forbidden word
break;
}
}
}
if ($copy) $filteredDocs[$key]=$docs[$key];
}
return $filteredDocs;
}
function compare_rank($a,$b)
{
if ($a["rank"] == $b["rank"])
{
return 0;
}
return ($a["rank"]>$b["rank"]) ? -1 : 1;
}
function sort_results($docs,&$sorted)
{
$sorted = $docs;
usort($sorted,"compare_rank");
return $sorted;
}
function report_results(&$docs)
{
echo "<table cellspacing=\"2\">\n";
echo " <tr>\n";
echo " <td colspan=\"2\"><h2>".search_results()."</h2></td>\n";
echo " </tr>\n";
$numDocs = sizeof($docs);
if ($numDocs==0)
{
echo " <tr>\n";
echo " <td colspan=\"2\">".matches_text(0)."</td>\n";
echo " </tr>\n";
}
else
{
echo " <tr>\n";
echo " <td colspan=\"2\">".matches_text($numDocs);
echo "\n";
echo " </td>\n";
echo " </tr>\n";
$num=1;
foreach ($docs as $doc)
{
echo " <tr>\n";
echo " <td align=\"right\">$num.</td>";
echo "<td><a class=\"el\" href=\"".$doc["url"]."\">".$doc["name"]."</a></td>\n";
echo " <tr>\n";
echo " <td></td><td class=\"tiny\">".report_matches()." ";
foreach ($doc["words"] as $wordInfo)
{
$word = $wordInfo["word"];
$matchRight = substr($wordInfo["match"],strlen($word));
echo "<b>$word</b>$matchRight(".$wordInfo["freq"].") ";
}
echo " </td>\n";
echo " </tr>\n";
$num++;
}
}
echo "</table>\n";
}
function search()
{
if(strcmp('4.1.0', phpversion()) > 0)
{
die("Error: PHP version 4.1.0 or above required!");
}
$paths = array(
"../doc/html/",
"../Socket/doc/html/",
"../Examples/doc/html/",
"../Packets/doc/html/",
"../Utils/doc/html/",
"../Scheduler/doc/html/",
);
$files = array();
$j=0;
for ($i=0; $i<sizeof($paths); $i++) {
if (!($f=@fopen($paths[$i]."search.idx","rb")))
{
die("Error: Search index file could NOT be opened!");
continue;
}
$files[$j++] = $f;
if (readHeader($f)!="DOXS")
{
die("Error: Header of index file is invalid!");
}
}
$query="";
if (array_key_exists("query", $_GET))
{
$query=$_GET["query"];
}
//end_form($query);
echo "&nbsp;\n<div class=\"searchresults\">\n";
$results = array();
$requiredWords = array();
$forbiddenWords = array();
$foundWords = array();
$word=strtok($query," ");
while ($word) // for each word in the search query
{
if (($word{0}=='+')) { $word=substr($word,1); $requiredWords[]=$word; }
if (($word{0}=='-')) { $word=substr($word,1); $forbiddenWords[]=$word; }
if (!in_array($word,$foundWords))
{
$foundWords[]=$word;
for ($i=0; $i<sizeof($files); $i++) {
do_search($paths[$i], $files[$i], strtolower($word), $results);
}
}
$word=strtok(" ");
}
$docs = array();
combine_results($results,$docs);
// filter out documents with forbidden word or that do not contain
// required words
$filteredDocs = filter_results($docs,$requiredWords,$forbiddenWords);
// sort the results based on rank
$sorted = array();
sort_results($filteredDocs,$sorted);
// report results to the user
report_results($sorted);
echo "</div>\n";
foreach ($files as $file) {
fclose($file);
}
}
?>
doclib/senf.css
+ 9
− 3
View file @ 86187a80
......@@ -5,7 +5,7 @@ body {
}
#head {
height: 62px;
height: 72px;
border-top: 5px solid #DECD40;
border-bottom: 1px solid #AF9D00;
background: url(logo-head.png) top left no-repeat;
......@@ -27,8 +27,8 @@ body {
#head h2 {
margin: 0 0 0 100px;
padding: 4px 0 0 42px;
height: 18px;
padding: 6px 0 0 42px;
height: 26px;
background-color: #EDE497;
color: #726921;
font-size: 13px;
......@@ -36,6 +36,12 @@ body {
white-space: nowrap;
}
#search {
position: absolute;
top: 50px;
right: 10px;
}
#content1 {
padding: 0 10px 10px 0;
border-bottom: 1px solid #AF9D00;
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment

Datenschutz und Impressum