Project

General

Profile

1 552 thorn
<?php
2
3 554 Ruebenwurz
// $Id$
4 552 thorn
5
/*
6
7
 Website Baker Project <http://www.websitebaker.org/>
8
 Copyright (C) 2004-2008, Ryan Djurovich
9
10
 Website Baker is free software; you can redistribute it and/or modify
11
 it under the terms of the GNU General Public License as published by
12
 the Free Software Foundation; either version 2 of the License, or
13
 (at your option) any later version.
14
15
 Website Baker is distributed in the hope that it will be useful,
16
 but WITHOUT ANY WARRANTY; without even the implied warranty of
17
 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
18
 GNU General Public License for more details.
19
20
 You should have received a copy of the GNU General Public License
21
 along with Website Baker; if not, write to the Free Software
22
 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
23
24
*/
25
26
// make the url-string for highlighting
27
function make_url_searchstring($search_match, $search_url_array) {
28
	$link = "";
29
	if ($search_match != 'exact') {
30
		$str = implode(" ", $search_url_array);
31
		$link = "?searchresult=1&amp;sstring=".urlencode($str);
32
	} else {
33
		$str = strtr($search_url_array[0], " ", "_");
34
		$link = "?searchresult=2&amp;sstring=".urlencode($str);
35
	}
36
	return $link;
37
}
38
39
// make date and time for "last modified by... on ..."-string
40
function get_page_modified($page_modified_when) {
41
	global $TEXT;
42
	if($page_modified_when > 0) {
43
		$date = gmdate(DATE_FORMAT, $page_modified_when+TIMEZONE);
44
		$time = gmdate(TIME_FORMAT, $page_modified_when+TIMEZONE);
45
	} else {
46
		$date = $TEXT['UNKNOWN'].' '.$TEXT['DATE'];
47
		$time = $TEXT['UNKNOWN'].' '.$TEXT['TIME'];
48
	}
49
	return array($date, $time);
50
}
51
52
// make username and displayname for "last modified by... on ..."-string
53
function get_page_modified_by($page_modified_by, $users) {
54
	global $TEXT;
55
	if($page_modified_by > 0) {
56
			$username = $users[$page_modified_by]['username'];
57
			$displayname = $users[$page_modified_by]['display_name'];
58
		} else {
59
			$username = "";
60
			$displayname = $TEXT['UNKNOWN'];
61
		}
62
	return array($username, $displayname);
63
}
64
65
// checks if _all_ searchwords matches
66
function is_all_matched($text, $search_words) {
67
	$all_matched = true;
68
	foreach ($search_words AS $word) {
69
		if(!preg_match('/'.$word.'/iu', $text)) {
70
			$all_matched = false;
71
			break;
72
		}
73
	}
74
	return $all_matched;
75
}
76
77
// checks if _any_ of the searchwords matches
78
function is_any_matched($text, $search_words) {
79
	$any_matched = false;
80
	$word = "(".implode("|", $search_words).")";
81
	if(preg_match('/'.$word.'/iu', $text)) {
82
		$any_matched = true;
83
	}
84
	return $any_matched;
85
}
86
87
// work-out if user is in $viewing_groups or $viewing_users
88
function is_access_denied($visibility, $viewing_groups_str, $viewing_users_str) {
89
	global $wb;
90
	$access_denied = false;
91
	if($visibility == 'private' || $visibility == 'registered') {
92
		$access_denied = true;
93
		if($wb->is_authenticated() == true) {
94
			$viewing_groups = explode(',', $viewing_groups_str);
95
			$viewing_users = explode(',', $viewing_users_str);
96
			if(in_array($wb->get_group_id(), $viewing_groups) || (in_array($wb->get_user_id(), $viewing_users))) {
97
				$access_denied = false;
98
			}
99
		}
100
	}
101
	return $access_denied;
102
}
103
104
// collects the matches from text in excerpt_array
105
function get_excerpts($text, $search_words, $max_excerpt_num) {
106
	$match_array = array();
107
	$excerpt_array = array();
108
	$word = "(".implode("|", $search_words).")";
109
110
	$text = strtr($text, array('&lt;'=>'<', '&gt;'=>'>', '&amp;'=>'&', '&quot;'=>'"', '&#39;'=>'\'', '&nbsp;'=>"\xC2\xA0"));
111
	$word = strtr($word, array('&lt;'=>'<', '&gt;'=>'>', '&amp;'=>'&', '&quot;'=>'"', '&#39;'=>'\'', '&nbsp;'=>"\xC2\xA0"));
112
	// Build the regex-string
113
	//...INVERTED EXCLAMATION MARK - INVERTED QUESTION MARK - DOUBLE EXCLAMATION MARK - INTERROBANG - EXCLAMATION QUESTION MARK - QUESTION EXCLAMATION MARK - DOUBLE QUESTION MARK - HALFWIDTH IDEOGRAPHIC FULL STOP - IDEOGRAPHIC FULL STOP - IDEOGRAPHIC COMMA
114
	$str1=".!?;"."\xC2\xA1"."\xC2\xBF"."\xE2\x80\xBC"."\xE2\x80\xBD"."\xE2\x81\x89"."\xE2\x81\x88"."\xE2\x81\x87"."\xEF\xBD\xA1"."\xE3\x80\x82"."\xE3\x80\x81";
115
	// ...DOUBLE EXCLAMATION MARK - INTERROBANG - EXCLAMATION QUESTION MARK - QUESTION EXCLAMATION MARK - DOUBLE QUESTION MARK - HALFWIDTH IDEOGRAPHIC FULL STOP - IDEOGRAPHIC FULL STOP - IDEOGRAPHIC COMMA
116
	$str2=".!?;"."\xE2\x80\xBC"."\xE2\x80\xBD"."\xE2\x81\x89"."\xE2\x81\x88"."\xE2\x81\x87"."\xEF\xBD\xA1"."\xE3\x80\x82"."\xE3\x80\x81";
117
	// "{0,200}?'.$word.'" : the '?' (ungreedy) is for performance-tuning; try a step-by-step-trace to see what i mean.
118
	if(preg_match_all('/(?:^|\b|['.$str1.'])([^'.$str1.']{0,200}?'.$word.'[^'.$str2.']{0,200}(?:['.$str2.']|\b|$))/isu', $text, $match_array)) {
119
		foreach($match_array[1] AS $string) {
120
			$excerpt_array[] = trim($string);
121
		}
122
	}
123
	return $excerpt_array;
124
}
125
126
// makes excerpt_array a string ready to print out
127
function prepare_excerpts($excerpt_array, $search_words, $max_excerpt_num) {
128
	// excerpts: text before and after a single excerpt, html-tag for markup
129
	$EXCERPT_BEFORE =       '...&nbsp;';
130
	$EXCERPT_AFTER =        '&nbsp;...<br />';
131
	$EXCERPT_MARKUP_START = '<b>';
132
	$EXCERPT_MARKUP_END =   '</b>';
133
	// remove duplicate matches from $excerpt_array, if any.
134
	$excerpt_array = array_unique($excerpt_array);
135
	// use the first $max_excerpt_num excerpts only
136
	if(count($excerpt_array) > $max_excerpt_num) {
137
		$excerpt_array = array_slice($excerpt_array, 0, $max_excerpt_num);
138
	}
139
	// prepare search-string
140
	$string = "(".implode("|", $search_words).")";
141
	$string = strtr($string, array('&lt;'=>'<', '&gt;'=>'>', '&amp;'=>'&', '&quot;'=>'"', '&#39;'=>'\'', '&nbsp;'=>"\xC2\xA0"));
142
	// we want markup on search-results page,
143
	// but we need some 'magic' to prevent <br />, <b>... from being highlighted
144
	$excerpt = '';
145
	foreach($excerpt_array as $str) {
146
		$excerpt .= '#,,#'.preg_replace("/($string)/iu","#,,,,#$1#,,,,,#",$str).'#,,,#';
147
	}
148
	$excerpt = strtr($excerpt, array('<'=>'&lt;', '>'=>'&gt;', '&'=>'&amp;', '"'=>'&quot;', '\''=>'&#39;'));
149
	$excerpt = strtr($excerpt, array('#,,,,#'=>$EXCERPT_MARKUP_START, '#,,,,,#'=>$EXCERPT_MARKUP_END));
150
	$excerpt = strtr($excerpt, array('#,,#'=>$EXCERPT_BEFORE, '#,,,#'=>$EXCERPT_AFTER));
151
	// prepare to write out
152
	if(DEFAULT_CHARSET != 'utf-8') {
153
		$excerpt = umlauts_to_entities($excerpt, 'UTF-8');
154
	}
155
	return $excerpt;
156
}
157
158
// work out what the link-target should be
159
function make_url_target($page_link_target, $text, $search_words) {
160
	// 1. e.g. $page_link_target=="&monthno=5&year=2007" - module-dependent target. Do nothing.
161
	// 2. $page_link_target=="#!wb_section_..." - the user wants the section-target, so do nothing.
162
	// 3. $page_link_target=="#wb_section_..." - try to find a better target, use the section-target as fallback.
163
	// 4. $page_link_target=="" - do nothing
164
	if(version_compare(PHP_VERSION, '4.3.0', ">=") && substr($page_link_target,0,12)=='#wb_section_') {
165
		$word = '('.implode('|', $search_words).')';
166
		preg_match('/'.$word.'/iu', $text, $match, PREG_OFFSET_CAPTURE);
167
		if($match && is_array($match[0])) {
168
			$x=$match[0][1];
169
			// is there an anchor nearby?
170
			if (preg_match_all('/<(?:[^>]+id|\s*a[^>]+name)\s*=\s*"(.*)"/iuU', $text, $match, PREG_OFFSET_CAPTURE)) {
171
				$anchor='';
172
				foreach($match[1] AS $array) {
173
					if($array[1] > $x) {
174
						break;
175
					}
176
					$anchor = $array[0];
177
				}
178
				if($anchor != '') {
179
					$page_link_target = '#'.$anchor;
180
				}
181
			}
182
		}
183
	}
184
	elseif(substr($page_link_target,0,13)=='#!wb_section_') {
185
		$page_link_target = '#'.substr($page_link_target, 2);
186
	}
187
	return $page_link_target;
188
}
189
190
// wrapper for compatibility with old print_excerpt()
191
function print_excerpt($page_link, $page_link_target, $page_title, $page_description, $page_modified_when, $page_modified_by, $text, $max_excerpt_num, $func_vars, $pic_link="") {
192
	$mod_vars = array(
193
		'page_link' => $page_link,
194
		'page_link_target' => $page_link_target,
195
		'page_title' => $page_title,
196
		'page_description' => $page_description,
197
		'page_modified_when' => $page_modified_when,
198
		'page_modified_by' => $page_modified_by,
199
		'text' => $text,
200
		'max_excerpt_num' => $max_excerpt_num,
201
		'pic_link' => $pic_link
202
	);
203
	print_excerpt2($mod_vars, $func_vars);
204
}
205
206
/* These functions can be used in module-supplied search_funcs
207
 * -----------------------------------------------------------
208
 * print_excerpt2() - the main-function to use in all search_funcs
209
 * print_excerpt() - wrapper for compatibility-reason. Use print_excerpt2() instead.
210
 * list_files_dirs() - lists all files and dirs below a given directory
211
 * clear_filelist() - keeps only wanted or removes unwanted entries in file-list.
212
 */
213
214
// prints the excerpts for one section
215
function print_excerpt2($mod_vars, $func_vars) {
216
	extract($func_vars, EXTR_PREFIX_ALL, 'func');
217
	extract($mod_vars, EXTR_PREFIX_ALL, 'mod');
218
	global $TEXT;
219
	// check $mod_...vars
220
	if(!isset($mod_page_link))          $mod_page_link = $func_page_link;
221
	if(!isset($mod_page_link_target))   $mod_page_link_target = "";
222
	if(!isset($mod_page_title))         $mod_page_title = $func_page_title;
223
	if(!isset($mod_page_description))   $mod_page_description = $func_page_description;
224
	if(!isset($mod_page_modified_when)) $mod_page_modified_when = $func_page_modified_when;
225
	if(!isset($mod_page_modified_by))   $mod_page_modified_by = $func_page_modified_by;
226
	if(!isset($mod_text))               $mod_text = "";
227
	if(!isset($mod_max_excerpt_num))    $mod_max_excerpt_num = $func_default_max_excerpt;
228
	if(!isset($mod_pic_link))           $mod_pic_link = "";
229
	if(!isset($mod_no_highlight))       $mod_no_highlight = false;
230
	if($mod_text == "") // nothing to do
231
		{ return false; }
232
	if($mod_no_highlight) // no highlighting
233
		{ $mod_page_link_target = "&nohighlight".$mod_page_link_target; }
234
235
	// prepare the text (part 1): remove lf and cr, convert \" to ", remove comments, style, scripting and unnecessary whitespace, convert to utf8
236
	$mod_text = strtr($mod_text, array("\x0D\x0A" => ' ', "\x0D" => ' ', "\x0A" => ' ', '\"' => '"'));
237
	$mod_text = preg_replace('/(<!--.*?-->|<style.*?<\/style>|<script.*?<\/script>|\s+)/i', ' ', $mod_text);
238 668 thorn
	// remove email-addresses
239
	$mod_text = preg_replace('/\b[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,4}\b/', ' ', $mod_text);
240 552 thorn
	$mod_text = entities_to_umlauts($mod_text, 'UTF-8');
241
242
	// make the link from $mod_page_link, add target
243
	$link = "";
244
	$link = page_link($mod_page_link);
245
	$link .= make_url_searchstring($func_search_match, $func_search_url_array);
246
	$link .= make_url_target($mod_page_link_target, $mod_text, $func_search_words);
247
248
	// prepare the text (part 2): convert some special tags to '.', strip tags
249
	$mod_text = preg_replace('/<(br( \/)?|dt|\/dd|\/?(h[1-6]|tr|table|p|li|ul|pre|code|div|hr))[^>]*>/i', '.', $mod_text);
250
	$mod_text = strip_tags($mod_text);
251
252
// unhtmlspecialchars
253
//	$mod_text = strtr($mod_text, array('&lt;'=>'<', '&gt;'=>'>', '&amp;'=>'&', '&quot;'=>'"', '&#39;'=>'\'', '&nbsp;'=>"\xC2\xA0"));
254
//	$tmp_words = array();
255
//	foreach($func_search_words as $w) {
256
//		$tmp_words[] = strtr($w, array('&lt;'=>'<', '&gt;'=>'>', '&amp;'=>'&', '&quot;'=>'"', '&#39;'=>'\'', '&nbsp;'=>"\xC2\xA0"));
257
//	}
258
//	$func_search_words = $tmp_words;
259
260
	// Do a fast scan over $mod_text first. This will speedup things a lot.
261
	if($func_search_match == 'all') {
262
		if(!is_all_matched($mod_text, $func_search_words)) {
263
			return false;
264
		}
265
	}
266
	elseif(!is_any_matched($mod_text, $func_search_words)) {
267
		return false;
268
	}
269
270
	// now get the excerpt
271
	$excerpt = "";
272
	$excerpt_array = array();
273
	if($mod_max_excerpt_num > 0) {
274
		if(!$excerpt_array = get_excerpts($mod_text, $func_search_words, $mod_max_excerpt_num)) {
275
			return false;
276
		}
277
		$excerpt = prepare_excerpts($excerpt_array, $func_search_words, $mod_max_excerpt_num);
278
	}
279
280
	// handle image
281
	if($mod_pic_link != "") {
282
		$excerpt = '<table width="100%" cellspacing="0" cellpadding="0" border="0"><tbody><tr><td width="110" valign="top"><a href="'.$link.'"><img src="'.WB_URL.'/'.MEDIA_DIRECTORY.$mod_pic_link.'" alt="" /></a></td><td>'.$excerpt.'</td></tr></tbody></table>';
283
	}
284
285
	// print-out the excerpt
286
	$vars = array();
287
	$values = array();
288
	list($date, $time) = get_page_modified($mod_page_modified_when);
289
	list($username, $displayname) = get_page_modified_by($mod_page_modified_by, $func_users);
290
	$vars = array('[LINK]', '[TITLE]', '[DESCRIPTION]', '[USERNAME]','[DISPLAY_NAME]','[DATE]','[TIME]','[TEXT_LAST_UPDATED_BY]','[TEXT_ON]','[EXCERPT]');
291
	$values = array(
292
		$link,
293
		$mod_page_title,
294
		$mod_page_description,
295
		$username,
296
		$displayname,
297
		$date,
298
		$time,
299
		$TEXT['LAST_UPDATED_BY'],
300
		$TEXT['ON'],
301
		$excerpt
302
	);
303
	echo str_replace($vars, $values, $func_results_loop_string);
304
	return true;
305
}
306
307
// list all files and dirs in $dir (recursive), omits '.' and '..'
308
// returns an array of two arrays ($files[] and $dirs[]).
309
// usage: list($files,$dirs) = list_files_dirs($directory);
310
//        $depth: get subdirs (true/false)
311
function list_files_dirs($dir, $depth=true, $files=array(), $dirs=array()) {
312
	$dh=opendir($dir);
313
	while(($file = readdir($dh)) !== false) {
314
		if($file == '.' || $file == '..') {
315
			continue;
316
		}
317
		if(is_dir($dir.'/'.$file)) {
318
			if($depth) {
319
				$dirs[] = $dir.'/'.$file;
320
				list($files, $dirs) = list_files_dirs($dir.'/'.$file, $depth, $files, $dirs);
321
			}
322
		} else {
323
			$files[] = $dir.'/'.$file;
324
		}
325
	}
326
	closedir($dh);
327
	natcasesort($files);
328
	natcasesort($dirs);
329
	return(array($files, $dirs));
330
}
331
332
// keeps only wanted entries in array $files. $str have to be an eregi()-compatible regex
333
function clear_filelist($files, $str, $keep=true) {
334
	// $keep = true  : remove all non-matching entries
335
	// $keep = false : remove all matching entries
336
	$c_filelist = array();
337
	if($str == '')
338
		return $files;
339
	foreach($files as $file) {
340
		if($keep) {
341
			if(eregi($str, $file)) {
342
				$c_filelist[] = $file;
343
			}
344
		} else {
345
			if(!eregi($str, $file)) {
346
				$c_filelist[] = $file;
347
			}
348
		}
349
	}
350
	return($c_filelist);
351
}
352
353
?>