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']]=$attrs;
53 }
54 function tag_close(){; }
56 }
59 /* This function genereates the Index */
60 function genIndex($arr)
61 {
62 global $helpobject;
63 $str = "";
64 $test = new pluglist($_SESSION['config'],NULL);
65 foreach($_SESSION['helpobject']['helpconf'] as $id => $attrs){
66 $path = $test -> get_path($id);
67 $exists = true;
68 $helpdir = "../doc/guide/user/".$helpobject['lang']."/html/".preg_replace("/^.*\//i","",$path)."/";
69 if(!is_dir($helpdir)){
70 $exists = false;
71 }
72 $print_hl = false;
73 if($current_hl != $attrs['HEADLINE']){
74 $current_hl = $attrs['HEADLINE'];
75 $str .= "<h1>"._($current_hl)."</h1>";
76 }
77 $name = $attrs['NAME'];
78 $file = "index.html";
79 $path = $plug;
80 if($exists){
81 $str .= "<p style='padding-left:20px;'><a href='?plug=".$id."'><b>".$name."</b></a></p>";
82 }else{
83 $str .= "<p style='padding-left:20px;'><b>".$name."</b> ("._("No help available for this plugin.").")</p>";
84 }
85 }
86 return utf8_decode($str);
87 }
90 /* Some replacements */
91 $backwardlink = "<a href=\"?pg=%s\" class=\"maintitlebar\">
92 <img src='images/back.png' align=\"middle\" alt=\""._("previous")."\" border=\"0\">
93 </a>";
95 $forwardlink = "<a href=\"?pg=%s\" class=\"maintitlebar\">
96 <img src='images/forward.png' align=\"middle\" alt=\""._("next")."\" border=\"0\">
97 </a>";
99 $pre_mark = "<span style=\"background-color: #FFFC35;\">" ; // Sign words with this
100 $suf_mark = "</span>"; // and this
103 /* Define which tags musst be delete, header, navigation, banner */
104 $replacements=array();
105 $replacements['from']=array("@<!DOC.*<BODY >@si",
106 "/border=\".*\"/i",
107 "'<code.*code>'",
108 // "/alt=\".*\"/i",
109 "/<HR>/",
110 "@<ADDRESS[^>]*?>.*?ADDRESS>@si",
111 "@<\/BODY[^>]*?>.*?HTML>@si",
112 "'<TABLE.*>'",
113 "/src.*icons/i",
114 "/src=\"/i",
115 "/<H1 ALIGN=\"CENTER\">/",
116 /* picture replacements */
117 // "",
118 );
120 $replacements['to']=array("",
121 " border=\"0\" ",
122 "",
123 // "",
124 "",
125 "",
126 "",
127 "<table border=1 cellspacing=0 bgcolor=\"#E0E0E0\" width=\"95%\" align=\"center\" cellpadding=\"3\" summary=\"\">",
128 "src=\"",
129 "src=\"images/",
130 "<H1>",
131 /* picture replacements */
132 // "",
133 );
136 /* Reads all files in specified directory with contents an some inforations about the file */
137 /* Read all files with contents*/
138 /* |Folder="/var/ww...",
139 | |Fileprefix="node"
140 | | |Filesuffix=".html"
141 | | | |WithoutContent=false(This means : read content)
142 | | | | |Singlepage=false(Means read all, if w want to read single, specify its filename)"*/
143 function readfiles($basedir,$prefix,$suffix,$onlyIndex,$singlepage=false)
144 {
145 global $replacements;
147 $str = array(); // Temporary variable
148 $cnt = 0; // Array index creation
149 $file = ""; // Contains Filename
151 $dir = opendir($basedir);
153 $str['global']['start'] = $cnt; // collect basic informations - Startpage
154 $str['global']['basedir'] = $basedir; // collect basic informations - Basedirectory
156 /* Startime for Benchmark */
157 $start = (time()+microtime());
159 /* if singlepage == false -> Get all pages, */
160 if(!$singlepage) {
162 /* While theres is an unreaded file in our resource */
163 while (($file = readdir($dir)) !== false) {
165 if((is_dir($basedir."/".$file))&&($file != "..")&&($file[0]!=".")){
166 $str[$file]=(readfiles($basedir."/".$file."/",$prefix,$suffix,$onlyIndex,false));
167 }
169 /* Filter all files which arn't intressting */
170 if((strstr($file,$suffix))&&($file!=".")&&($file!="..")&&(strstr($file,$prefix))){
172 /* Collect informations */
173 $str[$file]=array();
174 $str[$file]['name'] = $file;
175 $str[$file]['size'] = filesize($basedir.$file);
177 /* Readfile conent too ? */
178 if(!$onlyIndex){
179 $str[$file]['content'] = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
180 $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
181 }
183 /* Include file status, for debugging, not used in script yet */
184 $str[$file]['stat'] = stat($basedir.$file);
185 $cnt++;
186 }
187 }
189 /* Only get on file*/
190 }else{
191 /* Pages read = 1 */
192 $cnt = 1;
194 /* Prepare result*/
195 $file = $singlepage;
196 $str[$file] = array();
197 $str[$file]['name'] = $file;
198 $str[$file]['size'] = filesize($basedir.$file);
200 /* If onlyIndex == true skip reading content */
201 if(!$onlyIndex){
202 $str[$file]['content'] = remove_unwanted_tags(linkwrapper(getcontents($basedir.$file),""),$replacements);
203 $str[$file]['headline'] = getheader_from_content($str[$file]['content']);
204 }
206 /* Include file status, for debugging, not used in script yet */
207 $str[$file]['stat'] = stat($basedir.$file);
208 }
210 /* Sort to right order */
211 asort($str);
213 /* Endtime for Benchmark*/
214 $end = (time()+microtime());
215 $str['global']['cmptime'] = $end-$start;
217 /* Number of pages readed */
218 $str['global']['numpages']= $cnt;
219 closedir($dir);
220 return($str);
221 }
224 /* Read filecontent */
225 function getcontents($file)
226 {
227 $str = "" ; // Temporary variable for file contents
228 $tmp = "" ; // Temporary varibale for partitial file contents
230 /* open file and read*/
231 $fp = fopen($file,"r");
232 if($fp) {
233 while($tmp = fread($fp,512))
234 {
235 $str.= $tmp;
236 }
237 }else{
238 return(false);
239 }
240 return($str);
241 }
244 /*Remove tags */
245 function remove_unwanted_tags($str,$replacements)
246 {
247 $str=preg_replace($replacements['from'],$replacements['to'],$str);
248 return($str);
249 }
252 /*Converts the all links to specified path, is needed to get simple navigation */
253 function linkwrapper($str,$link)
254 {
255 $str = preg_replace("/HREF=\"http/i","target=\"_blank\" href=\"http",$str);
256 $str = preg_replace("/HREF=\"/","href=\"".$link."?pg=",$str);
257 // $str=str_replace("HREF=\"","href=\"".$link."?pg=",$str);
258 return($str);
259 }
262 /* Search content */
263 function search($arr,$word)
264 {
265 global $minwordlength,$allowed_chars_in_searchword;
266 /* Prepare Vars */
267 $result =array(); // Search result, filename, + hits + hits per word + matches
268 $words =array(); // Temporary searchword handling
269 $useablewords =array(); // Temporary searchword handling
270 $tryword = ""; // Temporary searchword handling
271 $result['global']['maxhit'] = 0;
272 unset($_SESSION['lastresults']);
273 unset($_SESSION['parsed_search_keyword']);
274 $_SESSION['parsed_search_keyword']="";
276 error_reporting(E_ALL);
278 /* prepare searchwords */
279 $word = trim($word);
281 /* Filter all unusable chars */
282 $word = preg_replace($allowed_chars_in_searchword,"",$word);
283 $words = split(" ",str_replace("+"," ",$word));
285 /* Check all wordlengths */
286 foreach($words as $tryword){
287 $tryword = trim($tryword);
289 /* Filter words smaler than 3 chars */
290 if(strlen($tryword)>=$minwordlength) {
291 $_SESSION['parsed_search_keyword'].=$tryword." ";
292 $useablewords[]=$tryword;
293 }
294 }
296 /* Use words to search the content */
297 foreach($arr as $keys=>$vals)
298 {
299 foreach($vals as $key=>$val){
300 /* overallhits counts hits per page */
301 $overallhits=0;
303 /* Search all words */
304 foreach($useablewords as $word)
305 {
306 /* Skip key global, it contains no file data - it is a summary info*/
307 if($key!="global")
308 {
310 /* Get all hits for the word in $matches*/
311 preg_match_all("/".$word."/i",$arr[$keys][$key]['content'], $matches,PREG_OFFSET_CAPTURE);
313 /* Filter in Tag results*/
314 if(count($matches[0])){
315 foreach($matches[0] as $num=>$hit){
316 if(is_in_tag($arr[$key]['content'],$hit[1])) {
317 unset($matches[0][$num]);
318 }
319 }
320 }
322 /* Count matches */
323 $overallhits=$overallhits + count($matches[0]);
325 /* Save collected data */
326 $result[$keys][$key]['hits'][$word] = count($matches[0]);
327 $result[$keys][$key]['hits']['overall']= $overallhits;
329 /* Save max hits for page */
330 if($overallhits > $result['global']['maxhit']){
331 $result['global']['maxhit']=$overallhits;
332 }
334 /* Add results for word to return value*/
335 $result[$keys][$key]['match'][$word]=array();
336 $result[$keys][$key]['match'][$word]=$matches[0];
337 }
338 }
339 }
340 }
342 /* Save result in Session, so we can mark words later, or go back to search, without searching again*/
343 $_SESSION['lastresults'] = $result;
344 return($result);
345 }
348 /* Detect 10 Best result entries, sort and call createResultEntry to create HTML output for complete list */
349 function searchlist($arr,$res,$maxresults)
350 {
351 $global = $res['global'];
352 $topten = array(); // To detect 10 best solutions
353 $ret = ""; // return value
354 unset($res['global']);
356 /* Detect 10 best Sites */
357 foreach($res as $key=>$resa)
358 foreach($resa as $keya=>$val){
359 /* Skip results with no hits */
360 if($val['hits']['overall']>0){
361 $topten[$key."/".$keya] = $val['hits']['overall'];
362 }
363 }
365 /* Sort by hit position in content, to easier mark words */
366 asort($topten);
367 $topten = array_reverse($topten);
368 $topten = (array_slice($topten,0,$maxresults));
371 /* We have a result, an array with all content, an array with hits and position and we have the 10 best hits */
372 /* Foreach */
373 foreach($topten as $key => $hits) {
375 $ks = split("\/",$key);
376 $k1 = $ks[0];
377 $k2 = $ks[1];
379 $ret.= createResultEntry($arr[$k1][$k2],$res[$k1][$k2],$key,$global['maxhit']);
380 }
382 /* appending footer message for resultlist */
383 $ret.= "<br>
384 ".sprintf(_("%s results for your search with the keyword %s interpreted as %s"),
385 "<b>".count($topten)."</b>",
386 "<b>".($_SESSION['search_string'])."</b>",
387 "<b>".$_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>".$entry['headline']."</b> -".htmlentities(substr(strip_tags($entry['content']),0,120))."...
453 </td>
454 <td width=50 valign=\"top\">".progressbar($percentage,50,8)."</td>
455 </tr>
456 <tr>
457 <td colspan=2>
458 <b>
459 ".htmlentities(sprintf(_("%s%% hit rate in file %s"),$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 $pos1 = strpos($string,"<",$pos);
476 $pos2 = strpos($string,">",$pos);
478 if ($pos1 > $pos2) {
479 return(true);
480 }else{
481 return(false);
482 }
483 }
485 /*Returns frist line of readable text, it should be the headline */
486 function getheader_from_content($str)
487 {
488 $str = strip_tags($str);
489 $pos = 0;
490 $arr = split("\n",$str);
491 foreach($arr as $possibleheadline){
492 if(strlen($possibleheadline)>=3){
493 return $possibleheadline;
494 }
495 }
496 }
498 // vim:tabstop=2:expandtab:shiftwidth=2:filetype=php:syntax:ruler:
499 ?>