1 <?php
2 /*
3 This code is part of GOsa (https://gosa.gonicus.de)
4 Copyright (C) 2005, Fabian Hickert
6 This program is free software; you can redistribute it and/or modify
7 it under the terms of the GNU General Public License as published by
8 the Free Software Foundation; either version 2 of the License, or
9 (at your option) any later version.
11 This program is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 GNU General Public License for more details.
16 You should have received a copy of the GNU General Public License
17 along with this program; if not, write to the Free Software
18 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
19 */
21 /* Simple class to parse the xml help file */
22 class parseXml
23 {
24 var $parser;
25 var $filename;
26 var $entries;
28 function parseXml($file)
29 {
30 $this->parser = xml_parser_create();
31 $this->filename = $file;
32 xml_set_object($this->parser, $this);
33 xml_set_element_handler($this->parser, "tag_open", "tag_close");
34 return($this->entries);
35 }
36 function parse()
37 {
38 $this->entries = array();
39 $fh= fopen($this->filename, "r");
40 $xmldata= fread($fh, 100000);
41 fclose($fh);
42 if(!xml_parse($this->parser, chop($xmldata))){
43 print(sprintf(_("XML error in guide.xml: %s at line %d"),
44 xml_error_string(xml_get_error_code($this->parser)),
45 xml_get_current_line_number($this->parser)));
46 exit;
47 }
48 return($this->entries);
49 }
50 function tag_open($parser,$tag,$attrs)
51 {
52 @$this->entries[$attrs['NAME']]=$attrs;
53 }
54 function tag_close(){; }
56 }
59 /* This function genereates the Index */
60 function genIndex()
61 {
62 global $helpobject;
63 $str = "";
64 $test = new pluglist($_SESSION['config'],NULL);
65 $current_hl = "";
66 foreach($_SESSION['helpobject']['helpconf'] as $id => $attrs){
67 $path = $test -> get_path($id);
68 $exists = true;
69 $helpdir = "../doc/guide/user/".$helpobject['lang']."/html/".preg_replace("/^.*\//i","",$path)."/";
70 if(!is_dir($helpdir)){
71 $exists = false;
72 }
73 $print_hl = false;
74 if($current_hl != $attrs['HEADLINE']){
75 $current_hl = $attrs['HEADLINE'];
76 $str .= "<h1>"._($current_hl)."</h1>";
77 }
78 $name = $attrs['NAME'];
79 $file = "index.html";
80 //$path = $plug;
81 if($exists){
82 $str .= "<p style='padding-left:20px;'><a href='?plug=".$id."'><b>"._($name)."</b></a></p>";
83 }else{
84 $str .= "<p style='padding-left:20px;'><b>"._($name)."</b> ("._("No help available for this plugin.").")</p>";
85 }
86 }
87 return (utf8_decode($str));
88 }
91 /* Some replacements */
92 $backwardlink = "<a href=\"?pg=%s\" class=\"maintitlebar\">
93 <img src='images/back.png' align=\"middle\" alt=\""._("previous")."\" border=\"0\">
94 </a>";
96 $forwardlink = "<a href=\"?pg=%s\" class=\"maintitlebar\">
97 <img src='images/forward.png' align=\"middle\" alt=\""._("next")."\" border=\"0\">
98 </a>";
100 $pre_mark = "<span style=\"background-color: #FFFC35;\">" ; // Sign words with this
101 $suf_mark = "</span>"; // and this
104 /* Define which tags musst be delete, header, navigation, banner */
105 $replacements=array();
106 $replacements['from']=array("@<!DOC.*<BODY >@si",
107 "/border=\".*\"/i",
108 "'<code.*code>'",
109 // "/alt=\".*\"/i",
110 "/<HR>/",
111 "@<ADDRESS[^>]*?>.*?ADDRESS>@si",
112 "@<\/BODY[^>]*?>.*?HTML>@si",
113 "'<TABLE.*>'",
114 "/src.*icons/i",
115 "/src=\"/i",
116 "/<H1 ALIGN=\"CENTER\">/",
117 /* picture replacements */
118 // "",
119 );
121 $replacements['to']=array("",
122 " border=\"0\" ",
123 "",
124 // "",
125 "",
126 "",
127 "",
128 "<table border=1 cellspacing=0 bgcolor=\"#E0E0E0\" width=\"95%\" align=\"center\" cellpadding=\"3\" summary=\"\">",
129 "src=\"",
130 "src=\"images/",
131 "<H1>",
132 /* picture replacements */
133 // "",
134 );
137 /* Reads all files in specified directory with contents an some inforations about the file */
138 /* Read all files with contents*/
139 /* |Folder="/var/ww...",
140 | |Fileprefix="node"
141 | | |Filesuffix=".html"
142 | | | |WithoutContent=false(This means : read content)
143 | | | | |Singlepage=false(Means read all, if w want to read single, specify its filename)"*/
144 function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
145 {
146 global $replacements;
148 $str = array(); // Temporary variable
149 $cnt = 0; // Array index creation
150 $file = ""; // Contains Filename
152 $dir = opendir($basedir);
154 $str['global']['start'] = $cnt; // collect basic informations - Startpage
155 $str['global']['basedir'] = $basedir; // collect basic informations - Basedirectory
157 /* Startime for Benchmark */
158 $start = (time()+microtime());
160 /* if singlepage == false -> Get all pages, */
161 if(!$singlepage) {
163 /* While theres is an unreaded file in our resource */
164 while (($file = readdir($dir)) !== false) {
166 if((is_dir($basedir."/".$file))&&($file != "..")&&($file[0]!=".")){
167 $str[$file]=(readfiles($basedir."/".$file."/",$prefix,$suffix,$onlyIndex,false));
168 }
170 /* Filter all files which arn't intressting */
171 if((strstr($file,$suffix))&&($file!=".")&&($file!="..")&&(strstr($file,$prefix))){
173 /* Collect informations */
174 $str[$file]=array();
175 $str[$file]['name'] = $file;
176 $str[$file]['size'] = filesize($basedir.$file);
178 /* Readfile conent too ? */
179 if(!$onlyIndex){
180 $str[$file]['content'] = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
181 $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
182 }
184 /* Include file status, for debugging, not used in script yet */
185 $str[$file]['stat'] = stat($basedir.$file);
186 $cnt++;
187 }
188 }
190 /* Only get on file*/
191 }else{
192 /* Pages read = 1 */
193 $cnt = 1;
195 /* Prepare result*/
196 $file = $singlepage;
197 $str[$file] = array();
198 $str[$file]['name'] = $file;
199 $str[$file]['size'] = filesize($basedir.$file);
201 /* If onlyIndex == true skip reading content */
202 if(!$onlyIndex){
203 $str[$file]['content'] = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
204 $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
205 }
207 /* Include file status, for debugging, not used in script yet */
208 $str[$file]['stat'] = stat($basedir.$file);
209 }
211 /* Sort to right order */
212 asort($str);
214 /* Endtime for Benchmark*/
215 $end = (time()+microtime());
216 $str['global']['cmptime'] = $end-$start;
218 /* Number of pages readed */
219 $str['global']['numpages']= $cnt;
220 closedir($dir);
221 return($str);
222 }
225 /* Read filecontent */
226 function getcontents($file)
227 {
228 $str = "" ; // Temporary variable for file contents
229 $tmp = "" ; // Temporary varibale for partitial file contents
231 /* open file and read*/
232 $fp = fopen($file,"r");
233 if($fp) {
234 while($tmp = fread($fp,512))
235 {
236 $str.= $tmp;
237 }
238 }else{
239 return(false);
240 }
241 return($str);
242 }
245 /*Remove tags */
246 function remove_unwanted_tags($str,$replacements)
247 {
248 $str=preg_replace($replacements['from'],$replacements['to'],$str);
249 return($str);
250 }
253 /*Converts the all links to specified path, is needed to get simple navigation */
254 function linkwrapper($str,$link)
255 {
256 $str = preg_replace("/HREF=\"http/i","target=\"_blank\" href=\"http",$str);
257 $str = preg_replace("/HREF=\"/","href=\"".$link."?pg=",$str);
258 $str=str_replace("HREF=\"","href=\"".$link."?pg=",$str);
259 return($str);
260 }
263 /* Search content */
264 function search($arr,$word)
265 {
266 global $minwordlength,$allowed_chars_in_searchword;
267 /* Prepare Vars */
268 $result =array(); // Search result, filename, + hits + hits per word + matches
269 $words =array(); // Temporary searchword handling
270 $useablewords =array(); // Temporary searchword handling
271 $tryword = ""; // Temporary searchword handling
272 $result['global']['maxhit'] = 0;
273 unset($_SESSION['lastresults']);
274 unset($_SESSION['parsed_search_keyword']);
275 $_SESSION['parsed_search_keyword']="";
277 error_reporting(E_ALL);
279 /* prepare searchwords */
280 $word = trim($word);
282 /* Filter all unusable chars */
283 $word = preg_replace($allowed_chars_in_searchword,"",$word);
284 $words = split(" ",str_replace("+"," ",$word));
286 /* Check all wordlengths */
287 foreach($words as $tryword){
288 $tryword = trim($tryword);
290 /* Filter words smaler than 3 chars */
291 if(strlen($tryword)>=$minwordlength) {
292 $_SESSION['parsed_search_keyword'].=$tryword." ";
293 $useablewords[]=$tryword;
294 }
295 }
297 /* Use words to search the content */
298 foreach($arr as $keys=>$vals)
299 {
300 foreach($vals as $key=>$val){
301 /* overallhits counts hits per page */
302 $overallhits=0;
304 /* Search all words */
305 foreach($useablewords as $word)
306 {
307 /* Skip key global, it contains no file data - it is a summary info*/
308 if($key!="global")
309 {
311 /* Get all hits for the word in $matches*/
312 preg_match_all("/".$word."/i",$arr[$keys][$key]['content'], $matches,PREG_OFFSET_CAPTURE);
314 /* Filter in Tag results*/
315 if(count($matches[0])){
316 foreach($matches[0] as $num=>$hit){
317 if(isset($arr[$keys][$key]['content']) && (is_in_tag($arr[$keys][$key]['content'],$hit[1]))){
318 unset($matches[0][$num]);
319 }
320 }
321 }
323 /* Count matches */
324 $overallhits=$overallhits + count($matches[0]);
326 /* Save collected data */
327 $result[$keys][$key]['hits'][$word] = count($matches[0]);
328 $result[$keys][$key]['hits']['overall']= $overallhits;
330 /* Save max hits for page */
331 if($overallhits > $result['global']['maxhit']){
332 $result['global']['maxhit']=$overallhits;
333 }
335 /* Add results for word to return value*/
336 $result[$keys][$key]['match'][$word]=array();
337 $result[$keys][$key]['match'][$word]=$matches[0];
338 }
339 }
340 }
341 }
343 /* Save result in Session, so we can mark words later, or go back to search, without searching again*/
344 $_SESSION['lastresults'] = $result;
345 return($result);
346 }
349 /* Detect 10 Best result entries, sort and call createResultEntry to create HTML output for complete list */
350 function searchlist($arr,$res,$maxresults)
351 {
352 $global = $res['global'];
353 $topten = array(); // To detect 10 best solutions
354 $ret = ""; // return value
355 unset($res['global']);
357 /* Detect 10 best Sites */
358 foreach($res as $key=>$resa)
359 foreach($resa as $keya=>$val){
360 /* Skip results with no hits */
361 if($val['hits']['overall']>0){
362 $topten[$key."/".$keya] = $val['hits']['overall'];
363 }
364 }
366 /* Sort by hit position in content, to easier mark words */
367 asort($topten);
368 $topten = array_reverse($topten);
369 $topten = (array_slice($topten,0,$maxresults));
372 /* We have a result, an array with all content, an array with hits and position and we have the 10 best hits */
373 /* Foreach */
374 foreach($topten as $key => $hits) {
376 $ks = split("\/",$key);
377 $k1 = $ks[0];
378 $k2 = $ks[1];
380 $ret.= createResultEntry($arr[$k1][$k2],$res[$k1][$k2],$key,$global['maxhit']);
381 }
383 /* appending footer message for resultlist */
384 $ret.= "<br>
385 ".sprintf(_("%s results for your search with the keyword %s"),
386 "<b>".count($topten)."</b>",
387 "<b>".$_SESSION['parsed_search_keyword']."</b>");
388 $ret.="<br>
389 <br>";
390 return($ret);
391 }
394 /* This function marks a string with the given search result for this string*/
395 function markup_page($arr,$res)
396 {
397 global $pre_mark,$suf_mark;
399 $ret = ""; // return value
400 $repl = array();
401 $posadd = 0;
403 foreach($res['match'] as $word => $matches) {
404 foreach($matches as $matchnr=>$match) {
405 $repl[$match[1]]=$match[0];
406 }
407 }
409 ksort($repl);
411 foreach($repl as $position=>$word) {
412 $pos1 = strlen($arr);
413 $arr= markword($arr,($position+$posadd),$word,$pre_mark,$suf_mark);
414 $pos2 = strlen($arr);
415 $posadd =$posadd + ($pos2 - $pos1);
416 }
417 return($arr);
418 }
421 /* This function marks a single word with the specified prefix and suffix */
422 function markword($string,$position,$word,$prefix,$suffix)
423 {
424 $wordlength = strlen($word);
425 $wholelength = strlen($string);
427 $first = substr($string,0,$position);
428 $last = substr($string,($position+$wordlength),$wholelength);
430 return($first.$prefix.$word.$suffix.$last);
431 }
433 /* Creates HTML output for a single search result entry */
434 function createResultEntry($entry,$res,$name,$max)
435 {
436 $percentage = (int)(($res['hits']['overall'] / $max) * 100) ;
437 $color = dechex($percentage+150);
438 $color2 = dechex(150 - $percentage);
440 $entry['content'] = preg_replace("\"".$entry['headline']."\"","",$entry['content'],1);
442 if(strlen($color)==1) $color = "0".$color;
446 /* the object tag is needed for W3c */
447 $str = "<a href=\"?pg=".$name."&mark=1\" title=\"".$percentage."% ".$entry['headline']."\">
448 <object>
449 <table summary=\"\" width=\"98%\" align=\"center\">
450 <tr>
451 <td height=15>
452 <b>".utf8_encode($entry['headline'])."</b> -".utf8_encode(substr(strip_tags($entry['content']),0,120))."...
453 </td>
454 <td width=50 valign=\"top\">".progressbar($percentage,50,8)."</td>
455 </tr>
456 <tr>
457 <td colspan=2>
458 <b>
459 ".(sprintf(_("%s%% hit rate in file %s"),$percentage,$name))."
460 </b>
461 </td>
462 </tr>
463 </table>
464 </object></a>
465 ";
466 $str.= "<hr size=\"1\">";
468 return($str);
469 }
472 /*Simple function to detect if we prepare to change a tag or visible text */
473 function is_in_tag($string,$pos)
474 {
475 $pos1 = $pos2 = 0;
476 if(preg_match("/</",$string)){
477 $pos1 = strpos($string,"<",$pos);
478 }
479 if(preg_match("/>/",$string)){
480 $pos2 = strpos($string,">",$pos);
481 }
482 if ($pos1 > $pos2) {
483 return(true);
484 }else{
485 return(false);
486 }
487 }
489 /*Returns frist line of readable text, it should be the headline */
490 function getheader_from_content($str)
491 {
492 $str = strip_tags($str);
493 $pos = 0;
494 $arr = split("\n",$str);
495 foreach($arr as $possibleheadline){
496 if(strlen($possibleheadline)>=3){
497 return $possibleheadline;
498 }
499 }
500 }
502 // vim:tabstop=2:expandtab:shiftwidth=2:filetype=php:syntax:ruler:
503 ?>