aboutsummaryrefslogtreecommitdiff
path: root/lib/dokuwiki/inc/search.php
blob: 2b9a51fb36b107006c20a100c5823e37181008ec (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
<?php
/**
 * DokuWiki search functions
 *
 * @license    GPL 2 (http://www.gnu.org/licenses/gpl.html)
 * @author     Andreas Gohr <andi@splitbrain.org>
 */

if(!defined('DOKU_INC')) die('meh.');
require_once(DOKU_INC.'inc/common.php');

/**
 * recurse direcory
 *
 * This function recurses into a given base directory
 * and calls the supplied function for each file and directory
 *
 * @param   array ref $data The results of the search are stored here
 * @param   string    $base Where to start the search
 * @param   callback  $func Callback (function name or arayy with object,method)
 * @param   string    $dir  Current directory beyond $base
 * @param   int       $lvl  Recursion Level
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search(&$data,$base,$func,$opts,$dir='',$lvl=1){
    $dirs   = array();
    $files  = array();

    //read in directories and files
    $dh = @opendir($base.'/'.$dir);
    if(!$dh) return;
    while(($file = readdir($dh)) !== false){
        if(preg_match('/^[\._]/',$file)) continue; //skip hidden files and upper dirs
        if(is_dir($base.'/'.$dir.'/'.$file)){
            $dirs[] = $dir.'/'.$file;
            continue;
        }
        $files[] = $dir.'/'.$file;
    }
    closedir($dh);
    sort($files);
    sort($dirs);

    //give directories to userfunction then recurse
    foreach($dirs as $dir){
        if (call_user_func_array($func, array(&$data,$base,$dir,'d',$lvl,$opts))){
            search($data,$base,$func,$opts,$dir,$lvl+1);
        }
    }
    //now handle the files
    foreach($files as $file){
        call_user_func_array($func, array(&$data,$base,$file,'f',$lvl,$opts));
    }
}

/**
 * Wrapper around call_user_func_array.
 *
 * @deprecated
 */
function search_callback($func,&$data,$base,$file,$type,$lvl,$opts){
    return call_user_func_array($func, array(&$data,$base,$file,$type,$lvl,$opts));
}

/**
 * The following functions are userfunctions to use with the search
 * function above. This function is called for every found file or
 * directory. When a directory is given to the function it has to
 * decide if this directory should be traversed (true) or not (false)
 * The function has to accept the following parameters:
 *
 * &$data - Reference to the result data structure
 * $base  - Base usually $conf['datadir']
 * $file  - current file or directory relative to $base
 * $type  - Type either 'd' for directory or 'f' for file
 * $lvl   - Current recursion depht
 * $opts  - option array as given to search()
 *
 * return values for files are ignored
 *
 * All functions should check the ACL for document READ rights
 * namespaces (directories) are NOT checked as this would break
 * the recursion (You can have an nonreadable dir over a readable
 * one deeper nested) also make sure to check the file type (for example
 * in case of lockfiles).
 */

/**
 * Searches for pages beginning with the given query
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function search_qsearch(&$data,$base,$file,$type,$lvl,$opts){
    $opts = array(
            'idmatch'   => '(^|:)'.preg_quote($opts['query'],'/').'/',
            'listfiles' => true,
            'pagesonly' => true,
            );
    return search_universal($data,$base,$file,$type,$lvl,$opts);
}

/**
 * Build the browsable index of pages
 *
 * $opts['ns'] is the current namespace
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_index(&$data,$base,$file,$type,$lvl,$opts){
    global $conf;
    $return = true;

    $item = array();

    if($type == 'd' && !preg_match('#^'.$file.'(/|$)#','/'.$opts['ns'])){
        //add but don't recurse
        $return = false;
    }elseif($type == 'f' && ($opts['nofiles'] || substr($file,-4) != '.txt')){
        //don't add
        return false;
    }

    $id = pathID($file);

    if($type=='d' && $conf['sneaky_index'] && auth_quickaclcheck($id.':') < AUTH_READ){
        return false;
    }

    //check hidden
    if(isHiddenPage($id)){
        return false;
    }

    //check ACL
    if($type=='f' && auth_quickaclcheck($id) < AUTH_READ){
        return false;
    }

    $data[]=array( 'id'    => $id,
            'type'  => $type,
            'level' => $lvl,
            'open'  => $return );
    return $return;
}

/**
 * List all namespaces
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_namespaces(&$data,$base,$file,$type,$lvl,$opts){
    $opts = array(
            'listdirs' => true,
            );
    return search_universal($data,$base,$file,$type,$lvl,$opts);
}

/**
 * List all mediafiles in a namespace
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_media(&$data,$base,$file,$type,$lvl,$opts){

    //we do nothing with directories
    if($type == 'd') {
        if(!$opts['depth']) return true; // recurse forever
        $depth = substr_count($file,'/');
        if($depth >= $opts['depth']) return false; // depth reached
        return true;
    }

    $info         = array();
    $info['id']   = pathID($file,true);
    if($info['id'] != cleanID($info['id'])){
        if($opts['showmsg'])
            msg(hsc($info['id']).' is not a valid file name for DokuWiki - skipped',-1);
        return false; // skip non-valid files
    }

    //check ACL for namespace (we have no ACL for mediafiles)
    $info['perm'] = auth_quickaclcheck(getNS($info['id']).':*');
    if(!$opts['skipacl'] && $info['perm'] < AUTH_READ){
        return false;
    }

    //check pattern filter
    if($opts['pattern'] && !@preg_match($opts['pattern'], $info['id'])){
        return false;
    }

    $info['file']     = basename($file);
    $info['size']     = filesize($base.'/'.$file);
    $info['mtime']    = filemtime($base.'/'.$file);
    $info['writable'] = is_writable($base.'/'.$file);
    if(preg_match("/\.(jpe?g|gif|png)$/",$file)){
        $info['isimg'] = true;
        require_once(DOKU_INC.'inc/JpegMeta.php');
        $info['meta']  = new JpegMeta($base.'/'.$file);
    }else{
        $info['isimg'] = false;
    }
    if($opts['hash']){
        $info['hash'] = md5(io_readFile(wikiFN($info['id']),false));
    }

    $data[] = $info;

    return false;
}

/**
 * This function just lists documents (for RSS namespace export)
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_list(&$data,$base,$file,$type,$lvl,$opts){
    //we do nothing with directories
    if($type == 'd') return false;
    //only search txt files
    if(substr($file,-4) == '.txt'){
        //check ACL
        $id = pathID($file);
        if(auth_quickaclcheck($id) < AUTH_READ){
            return false;
        }
        $data[]['id'] = $id;
    }
    return false;
}

/**
 * Quicksearch for searching matching pagenames
 *
 * $opts['query'] is the search query
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_pagename(&$data,$base,$file,$type,$lvl,$opts){
    //we do nothing with directories
    if($type == 'd') return true;
    //only search txt files
    if(substr($file,-4) != '.txt') return true;

    //simple stringmatching
    if (!empty($opts['query'])){
        if(strpos($file,$opts['query']) !== false){
            //check ACL
            $id = pathID($file);
            if(auth_quickaclcheck($id) < AUTH_READ){
                return false;
            }
            $data[]['id'] = $id;
        }
    }
    return true;
}

/**
 * Just lists all documents
 *
 * $opts['depth']   recursion level, 0 for all
 * $opts['hash']    do md5 sum of content?
 * $opts['skipacl'] list everything regardless of ACL
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function search_allpages(&$data,$base,$file,$type,$lvl,$opts){
    //we do nothing with directories
    if($type == 'd'){
        if(!$opts['depth']) return true; // recurse forever
        $parts = explode('/',ltrim($file,'/'));
        if(count($parts) == $opts['depth']) return false; // depth reached
        return true;
    }

    //only search txt files
    if(substr($file,-4) != '.txt') return true;

    $item['id']   = pathID($file);
    if(!$opts['skipacl'] && auth_quickaclcheck($item['id']) < AUTH_READ){
        return false;
    }

    $item['rev']   = filemtime($base.'/'.$file);
    $item['mtime'] = $item['rev'];
    $item['size']  = filesize($base.'/'.$file);
    if($opts['hash']){
        $item['hash'] = md5(trim(rawWiki($item['id'])));
    }

    $data[] = $item;
    return true;
}

/**
 * Search for backlinks to a given page
 *
 * $opts['ns']    namespace of the page
 * $opts['name']  name of the page without namespace
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 * @deprecated Replaced by ft_backlinks()
 */
function search_backlinks(&$data,$base,$file,$type,$lvl,$opts){
    //we do nothing with directories
    if($type == 'd') return true;
    //only search txt files
    if(substr($file,-4) != '.txt') return true;

    //absolute search id
    $sid = cleanID($opts['ns'].':'.$opts['name']);

    //current id and namespace
    $cid = pathID($file);
    $cns = getNS($cid);

    //check ACL
    if(auth_quickaclcheck($cid) < AUTH_READ){
        return false;
    }

    //fetch instructions
    require_once(DOKU_INC.'inc/parserutils.php');
    $instructions = p_cached_instructions($base.$file,true);
    if(is_null($instructions)) return false;

    //check all links for match
    foreach($instructions as $ins){
        if($ins[0] == 'internallink' || ($conf['camelcase'] && $ins[0] == 'camelcaselink') ){
            $mid = $ins[1][0];
            resolve_pageid($cns,$mid,$exists); //exists is not used
            if($mid == $sid){
                //we have a match - finish
                $data[]['id'] = $cid;
                break;
            }
        }
    }

    return false;
}

/**
 * Fulltextsearch
 *
 * $opts['query'] is the search query
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 * @deprecated - fulltext indexer is used instead
 */
function search_fulltext(&$data,$base,$file,$type,$lvl,$opts){
    //we do nothing with directories
    if($type == 'd') return true;
    //only search txt files
    if(substr($file,-4) != '.txt') return true;

    //check ACL
    $id = pathID($file);
    if(auth_quickaclcheck($id) < AUTH_READ){
        return false;
    }

    //create regexp from queries
    $poswords = array();
    $negwords = array();
    $qpreg = preg_split('/\s+/',$opts['query']);

    foreach($qpreg as $word){
        switch(substr($word,0,1)){
            case '-':
                if(strlen($word) > 1){  // catch single '-'
                    array_push($negwords,preg_quote(substr($word,1),'#'));
                }
                break;
            case '+':
                if(strlen($word) > 1){  // catch single '+'
                    array_push($poswords,preg_quote(substr($word,1),'#'));
                }
                break;
            default:
                array_push($poswords,preg_quote($word,'#'));
                break;
        }
    }

    // a search without any posword is useless
    if (!count($poswords)) return true;

    $reg  = '^(?=.*?'.join(')(?=.*?',$poswords).')';
            $reg .= count($negwords) ? '((?!'.join('|',$negwords).').)*$' : '.*$';
            search_regex($data,$base,$file,$reg,$poswords);
            return true;
            }

            /**
             * Reference search
             * This fuction searches for existing references to a given media file
             * and returns an array with the found pages. It doesn't pay any
             * attention to ACL permissions to find every reference. The caller
             * must check if the user has the appropriate rights to see the found
             * page and eventually have to prevent the result from displaying.
             *
             * @param array  $data Reference to the result data structure
             * @param string $base Base usually $conf['datadir']
             * @param string $file current file or directory relative to $base
             * @param char   $type Type either 'd' for directory or 'f' for file
             * @param int    $lvl  Current recursion depht
             * @param mixed  $opts option array as given to search()
             *
             * $opts['query'] is the demanded media file name
             *
             * @author  Andreas Gohr <andi@splitbrain.org>
             * @author  Matthias Grimm <matthiasgrimm@users.sourceforge.net>
             */
function search_reference(&$data,$base,$file,$type,$lvl,$opts){
    global $conf;

    //we do nothing with directories
    if($type == 'd') return true;

    //only search txt files
    if(substr($file,-4) != '.txt') return true;

    //we finish after 'cnt' references found. The return value
    //'false' will skip subdirectories to speed search up.
    $cnt = $conf['refshow'] > 0 ? $conf['refshow'] : 1;
    if(count($data) >= $cnt) return false;

    $reg = '\{\{ *\:?'.$opts['query'].' *(\|.*)?\}\}';
    search_regex($data,$base,$file,$reg,array($opts['query']));
    return true;
}

/* ------------- helper functions below -------------- */

/**
 * fulltext search helper
 * searches a text file with a given regular expression
 * no ACL checks are performed. This have to be done by
 * the caller if necessary.
 *
 * @param array  $data  reference to array for results
 * @param string $base  base directory
 * @param string $file  file name to search in
 * @param string $reg   regular expression to search for
 * @param array  $words words that should be marked in the results
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 * @author  Matthias Grimm <matthiasgrimm@users.sourceforge.net>
 *
 * @deprecated - fulltext indexer is used instead
 */
function search_regex(&$data,$base,$file,$reg,$words){

    //get text
    $text = io_readfile($base.'/'.$file);
    //lowercase text (u modifier does not help with case)
    $lctext = utf8_strtolower($text);

    //do the fulltext search
    $matches = array();
    if($cnt = preg_match_all('#'.$reg.'#usi',$lctext,$matches)){
        //this is not the best way for snippet generation but the fastest I could find
        $q = $words[0];  //use first word for snippet creation
        $p = utf8_strpos($lctext,$q);
        $f = $p - 100;
        $l = utf8_strlen($q) + 200;
        if($f < 0) $f = 0;
        $snippet = '<span class="search_sep"> ... </span>'.
            htmlspecialchars(utf8_substr($text,$f,$l)).
            '<span class="search_sep"> ... </span>';
        $mark    = '('.join('|', $words).')';
        $snippet = preg_replace('#'.$mark.'#si','<strong class="search_hit">\\1</strong>',$snippet);

        $data[] = array(
                'id'       => pathID($file),
                'count'    => preg_match_all('#'.$mark.'#usi',$lctext,$matches),
                'poswords' => join(' ',$words),
                'snippet'  => $snippet,
                );
    }

    return true;
}


/**
 * fulltext sort
 *
 * Callback sort function for use with usort to sort the data
 * structure created by search_fulltext. Sorts descending by count
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 */
function sort_search_fulltext($a,$b){
    if($a['count'] > $b['count']){
        return -1;
    }elseif($a['count'] < $b['count']){
        return 1;
    }else{
        return strcmp($a['id'],$b['id']);
    }
}

/**
 * translates a document path to an ID
 *
 * @author  Andreas Gohr <andi@splitbrain.org>
 * @todo    move to pageutils
 */
function pathID($path,$keeptxt=false){
    $id = utf8_decodeFN($path);
    $id = str_replace('/',':',$id);
    if(!$keeptxt) $id = preg_replace('#\.txt$#','',$id);
    $id = preg_replace('#^:+#','',$id);
    $id = preg_replace('#:+$#','',$id);
    return $id;
}


/**
 * This is a very universal callback for the search() function, replacing
 * many of the former individual functions at the cost of a more complex
 * setup.
 *
 * How the function behaves, depends on the options passed in the $opts
 * array, where the following settings can be used.
 *
 * depth      int     recursion depth. 0 for unlimited
 * keeptxt    bool    keep .txt extension for IDs
 * listfiles  bool    include files in listing
 * listdirs   bool    include namespaces in listing
 * pagesonly  bool    restrict files to pages
 * skipacl    bool    do not check for READ permission
 * sneakyacl  bool    don't recurse into nonreadable dirs
 * hash       bool    create MD5 hash for files
 * meta       bool    return file metadata
 * filematch  string  match files against this regexp
 * idmatch    string  match full ID against this regexp
 * dirmatch   string  match directory against this regexp when adding
 * nsmatch    string  match namespace against this regexp when adding
 * recmatch   string  match directory against this regexp when recursing
 * showmsg    bool    warn about non-ID files
 * showhidden bool    show hidden files too
 * firsthead  bool    return first heading for pages
 *
 * @author Andreas Gohr <gohr@cosmocode.de>
 */
function search_universal(&$data,$base,$file,$type,$lvl,$opts){
    $item   = array();
    $return = true;

    // get ID and check if it is a valid one
    $item['id'] = pathID($file);
    if($item['id'] != cleanID($item['id'])){
        if($opts['showmsg'])
            msg(hsc($item['id']).' is not a valid file name for DokuWiki - skipped',-1);
        return false; // skip non-valid files
    }
    $item['ns']  = getNS($item['id']);

    if($type == 'd') {
        // decide if to recursion into this directory is wanted
        if(!$opts['depth']){
            $return = true; // recurse forever
        }else{
            $depth = substr_count($file,'/');
            if($depth >= $opts['depth']){
                $return = false; // depth reached
            }else{
                $return = true;
            }
        }
        if($return && !preg_match('/'.$opts['recmatch'].'/',$file)){
            $return = false; // doesn't match
        }
    }

    // check ACL
    if(!$opts['skipacl']){
        if($type == 'd'){
            $item['perm'] = auth_quickaclcheck($item['id'].':*');
        }else{
            $item['perm'] = auth_quickaclcheck($item['id']); //FIXME check namespace for media files
        }
    }else{
        $item['perm'] = AUTH_DELETE;
    }

    // are we done here maybe?
    if($type == 'd'){
        if(!$opts['listdirs']) return $return;
        if(!$opts['skipacl'] && $opts['sneakyacl'] && $item['perm'] < AUTH_READ) return false; //neither list nor recurse
        if($opts['dirmatch'] && !preg_match('/'.$opts['dirmatch'].'/',$file)) return $return;
        if($opts['nsmatch'] && !preg_match('/'.$opts['nsmatch'].'/',$item['ns'])) return $return;
    }else{
        if(!$opts['listfiles']) return $return;
        if(!$opts['skipacl'] && $item['perm'] < AUTH_READ) return $return;
        if($opts['pagesonly'] && (substr($file,-4) != '.txt')) return $return;
        if(!$conf['showhidden'] && isHiddenPage($id)) return $return;
        if($opts['filematch'] && !preg_match('/'.$opts['filematch'].'/',$file)) return $return;
        if($opts['idmatch'] && !preg_match('/'.$opts['idmatch'].'/',$item['id'])) return $return;
    }

    // still here? prepare the item
    $item['type']  = $type;
    $item['level'] = $lvl;
    $item['open']  = $return;

    if($opts['meta']){
        $item['file']       = basename($file);
        $item['size']       = filesize($base.'/'.$file);
        $item['mtime']      = filemtime($base.'/'.$file);
        $item['rev']        = $item['mtime'];
        $item['writable']   = is_writable($base.'/'.$file);
        $item['executable'] = is_executable($base.'/'.$file);
    }

    if($type == 'f'){
        if($opts['hash']) $item['hash'] = md5(io_readFile($base.'/'.$file,false));
        if($opts['firsthead']) $item['title'] = p_get_first_heading($item['id'],false);
    }

    // finally add the item
    $data[] = $item;
    return $return;
}

//Setup VIM: ex: et ts=4 enc=utf-8 :