Source

gd-websites / wiki / inc / pageutils.php

Full commit
  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
<?php
/**
 * Utilities for handling pagenames
 *
 * @license    GPL 2 (http://www.gnu.org/licenses/gpl.html)
 * @author     Andreas Gohr <andi@splitbrain.org>
 * @todo       Combine similar functions like {wiki,media,meta}FN()
 */

/**
 * Fetch the an ID from request
 *
 * Uses either standard $_REQUEST variable or extracts it from
 * the full request URI when userewrite is set to 2
 *
 * For $param='id' $conf['start'] is returned if no id was found.
 * If the second parameter is true (default) the ID is cleaned.
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function getID($param='id',$clean=true){
  global $conf;

  $id = isset($_REQUEST[$param]) ? $_REQUEST[$param] : null;

  //construct page id from request URI
  if(empty($id) && $conf['userewrite'] == 2){
    //get the script URL
    if($conf['basedir']){
      $relpath = '';
      if($param != 'id') {
        $relpath = 'lib/exe/';
      }
      $script = $conf['basedir'].$relpath.basename($_SERVER['SCRIPT_FILENAME']);
    }elseif($_SERVER['DOCUMENT_ROOT'] && $_SERVER['SCRIPT_FILENAME']){
      $script = preg_replace ('/^'.preg_quote($_SERVER['DOCUMENT_ROOT'],'/').'/','',
                              $_SERVER['SCRIPT_FILENAME']);
      $script = '/'.$script;
    }else{
      $script = $_SERVER['SCRIPT_NAME'];
    }

    //clean script and request (fixes a windows problem)
    $script  = preg_replace('/\/\/+/','/',$script);
    $request = preg_replace('/\/\/+/','/',$_SERVER['REQUEST_URI']);

    //remove script URL and Querystring to gain the id
    if(preg_match('/^'.preg_quote($script,'/').'(.*)/',$request, $match)){
      $id = preg_replace ('/\?.*/','',$match[1]);
    }
    $id = urldecode($id);
    //strip leading slashes
    $id = preg_replace('!^/+!','',$id);
  }

  // Namespace autolinking from URL
  if(substr($id,-1) == ':' || ($conf['useslash'] && substr($id,-1) == '/')){
    if(page_exists($id.$conf['start'])){
      // start page inside namespace
      $id = $id.$conf['start'];
    }elseif(page_exists($id.noNS(cleanID($id)))){
      // page named like the NS inside the NS
      $id = $id.noNS(cleanID($id));
    }elseif(page_exists($id)){
      // page like namespace exists
      $id = substr($id,0,-1);
    }else{
      // fall back to default
      $id = $id.$conf['start'];
    }
    header("Location: ".wl($id,'',true));
  }

  if($clean) $id = cleanID($id);
  if(empty($id) && $param=='id') $id = $conf['start'];

  return $id;
}

/**
 * Remove unwanted chars from ID
 *
 * Cleans a given ID to only use allowed characters. Accented characters are
 * converted to unaccented ones
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 * @param  string  $raw_id    The pageid to clean
 * @param  boolean $ascii     Force ASCII
 */
function cleanID($raw_id,$ascii=false){
  global $conf;
  global $lang;
  static $sepcharpat = null;

  global $cache_cleanid;
  $cache = & $cache_cleanid;

  // check if it's already in the memory cache
  if (isset($cache[$raw_id])) {
    return $cache[$raw_id];
    }

  $sepchar = $conf['sepchar'];
  if($sepcharpat == null) // build string only once to save clock cycles
    $sepcharpat = '#\\'.$sepchar.'+#';

  $id = trim($raw_id);
  $id = utf8_strtolower($id);

  //alternative namespace seperator
  $id = strtr($id,';',':');
  if($conf['useslash']){
    $id = strtr($id,'/',':');
  }else{
    $id = strtr($id,'/',$sepchar);
  }

  if($conf['deaccent'] == 2 || $ascii) $id = utf8_romanize($id);
  if($conf['deaccent'] || $ascii) $id = utf8_deaccent($id,-1);

  //remove specials
  $id = utf8_stripspecials($id,$sepchar,'\*');

  if($ascii) $id = utf8_strip($id);

  //clean up
  $id = preg_replace($sepcharpat,$sepchar,$id);
  $id = preg_replace('#:+#',':',$id);
  $id = trim($id,':._-');
  $id = preg_replace('#:[:\._\-]+#',':',$id);

  $cache[$raw_id] = $id;
  return($id);
}

/**
 * Return namespacepart of a wiki ID
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function getNS($id){
  $pos = strrpos($id,':');
  if($pos!==false){
    return substr($id,0,$pos);
  }
  return false;
}

/**
 * Returns the ID without the namespace
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function noNS($id) {
  $pos = strrpos($id, ':');
  if ($pos!==false) {
    return substr($id, $pos+1);
  } else {
    return $id;
  }
}

/**
* Returns the current namespace
*
* @author Nathan Fritz <fritzn@crown.edu>
*/
function curNS($id) {
    return noNS(getNS($id));
}

/**
* Returns the ID without the namespace or current namespace for 'start' pages
*
* @author Nathan Fritz <fritzn@crown.edu>
*/
function noNSorNS($id) {
    global $conf;

    $p = noNS($id);
    if ($p == $conf['start']) {
        $p = curNS($id);
        if ($p == false) {
            return noNS($id);
        }
    }
    return $p;
}

/**
 *  Wiki page existence check
 *
 *  parameters as for wikiFN
 *
 *  @author Chris Smith <chris@jalakai.co.uk>
 */
function page_exists($id,$rev='',$clean=true) {
  return @file_exists(wikiFN($id,$rev,$clean));
}

/**
 * returns the full path to the datafile specified by ID and optional revision
 *
 * The filename is URL encoded to protect Unicode chars
 *
 * @param  $raw_id  string   id of wikipage
 * @param  $rev     string   page revision, empty string for current
 * @param  $clean   bool     flag indicating that $raw_id should be cleaned.  Only set to false
 *                           when $id is guaranteed to have been cleaned already.
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function wikiFN($raw_id,$rev='',$clean=true){
  global $conf;

  global $cache_wikifn;
  $cache = & $cache_wikifn;

  if (isset($cache[$raw_id]) && isset($cache[$raw_id][$rev])) {
    return $cache[$raw_id][$rev];
  }

  $id = $raw_id;

  if ($clean) $id = cleanID($id);
  $id = str_replace(':','/',$id);
  if(empty($rev)){
    $fn = $conf['datadir'].'/'.utf8_encodeFN($id).'.txt';
  }else{
    $fn = $conf['olddir'].'/'.utf8_encodeFN($id).'.'.$rev.'.txt';
    if($conf['compression']){
      //test for extensions here, we want to read both compressions
       if (@file_exists($fn . '.gz')){
          $fn .= '.gz';
       }else if(@file_exists($fn . '.bz2')){
          $fn .= '.bz2';
       }else{
          //file doesnt exist yet, so we take the configured extension
          $fn .= '.' . $conf['compression'];
       }
    }
  }

  if (!isset($cache[$raw_id])) { $cache[$raw_id] = array(); }
  $cache[$raw_id][$rev] = $fn;
  return $fn;
}

/**
 * Returns the full path to the file for locking the page while editing.
 *
 * @author Ben Coburn <btcoburn@silicodon.net>
 */
function wikiLockFN($id) {
  global $conf;
  return $conf['lockdir'].'/'.md5(cleanID($id)).'.lock';
}


/**
 * returns the full path to the meta file specified by ID and extension
 *
 * The filename is URL encoded to protect Unicode chars
 *
 * @author Steven Danz <steven-danz@kc.rr.com>
 */
function metaFN($id,$ext){
  global $conf;
  $id = cleanID($id);
  $id = str_replace(':','/',$id);
  $fn = $conf['metadir'].'/'.utf8_encodeFN($id).$ext;
  return $fn;
}

/**
 * returns an array of full paths to all metafiles of a given ID
 *
 * @author Esther Brunner <esther@kaffeehaus.ch>
 */
function metaFiles($id){
   $name   = noNS($id);
   $ns     = getNS($id);
   $dir    = ($ns) ? metaFN($ns,'').'/' : metaFN($ns,'');
   $files  = array();

   $dh = @opendir($dir);
   if(!$dh) return $files;
   while(($file = readdir($dh)) !== false){
     if(strpos($file,$name.'.') === 0 && !is_dir($dir.$file))
       $files[] = $dir.$file;
   }
   closedir($dh);

   return $files;
}

/**
 * returns the full path to the mediafile specified by ID
 *
 * The filename is URL encoded to protect Unicode chars
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function mediaFN($id){
  global $conf;
  $id = cleanID($id);
  $id = str_replace(':','/',$id);
    $fn = $conf['mediadir'].'/'.utf8_encodeFN($id);
  return $fn;
}

/**
 * Returns the full filepath to a localized textfile if local
 * version isn't found the english one is returned
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function localeFN($id){
  global $conf;
  $file = DOKU_INC.'inc/lang/'.$conf['lang'].'/'.$id.'.txt';
  if(!@file_exists($file)){
    //fall back to english
    $file = DOKU_INC.'inc/lang/en/'.$id.'.txt';
  }
  return $file;
}

/**
 * Resolve relative paths in IDs
 *
 * Do not call directly use resolve_mediaid or resolve_pageid
 * instead
 *
 * Partyly based on a cleanPath function found at
 * http://www.php.net/manual/en/function.realpath.php#57016
 *
 * @author <bart at mediawave dot nl>
 */
function resolve_id($ns,$id,$clean=true){
  global $conf;

  // some pre cleaning for useslash:
  if($conf['useslash']) $id = str_replace('/',':',$id);

  // if the id starts with a dot we need to handle the
  // relative stuff
  if($id{0} == '.'){
    // normalize initial dots without a colon
    $id = preg_replace('/^(\.+)(?=[^:\.])/','\1:',$id);
    // prepend the current namespace
    $id = $ns.':'.$id;

    // cleanup relatives
    $result = array();
    $pathA  = explode(':', $id);
    if (!$pathA[0]) $result[] = '';
    foreach ($pathA AS $key => $dir) {
      if ($dir == '..') {
        if (end($result) == '..') {
          $result[] = '..';
        } elseif (!array_pop($result)) {
          $result[] = '..';
        }
      } elseif ($dir && $dir != '.') {
        $result[] = $dir;
      }
    }
    if (!end($pathA)) $result[] = '';
    $id = implode(':', $result);
  }elseif($ns !== false && strpos($id,':') === false){
    //if link contains no namespace. add current namespace (if any)
    $id = $ns.':'.$id;
  }

  if($clean) $id = cleanID($id);
  return $id;
}

/**
 * Returns a full media id
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function resolve_mediaid($ns,&$page,&$exists){
  $page   = resolve_id($ns,$page);
  $file   = mediaFN($page);
  $exists = @file_exists($file);
}

/**
 * Returns a full page id
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 */
function resolve_pageid($ns,&$page,&$exists){
  global $conf;
  $exists = false;

  //keep hashlink if exists then clean both parts
  if (strpos($page,'#')) {
    list($page,$hash) = split('#',$page,2);
  } else {
    $hash = '';
  }
  $hash = cleanID($hash);
  $page = resolve_id($ns,$page,false); // resolve but don't clean, yet

  // get filename (calls clean itself)
  $file = wikiFN($page);

  // if ends with colon or slash we have a namespace link
  if(substr($page,-1) == ':' || ($conf['useslash'] && substr($page,-1) == '/')){
    if(page_exists($page.$conf['start'])){
      // start page inside namespace
      $page = $page.$conf['start'];
      $exists = true;
    }elseif(page_exists($page.noNS(cleanID($page)))){
      // page named like the NS inside the NS
      $page = $page.noNS(cleanID($page));
      $exists = true;
    }elseif(page_exists($page)){
      // page like namespace exists
      $page = $page;
      $exists = true;
    }else{
      // fall back to default
      $page = $page.$conf['start'];
    }
  }else{
    //check alternative plural/nonplural form
    if(!@file_exists($file)){
      if( $conf['autoplural'] ){
        if(substr($page,-1) == 's'){
          $try = substr($page,0,-1);
        }else{
          $try = $page.'s';
        }
        if(page_exists($try)){
          $page   = $try;
          $exists = true;
        }
      }
    }else{
      $exists = true;
    }
  }

  // now make sure we have a clean page
  $page = cleanID($page);

  //add hash if any
  if(!empty($hash)) $page .= '#'.$hash;
}

/**
 * Returns the name of a cachefile from given data
 *
 * The needed directory is created by this function!
 *
 * @author Andreas Gohr <andi@splitbrain.org>
 *
 * @param string $data  This data is used to create a unique md5 name
 * @param string $ext   This is appended to the filename if given
 * @return string       The filename of the cachefile
 */
function getCacheName($data,$ext=''){
  global $conf;
  $md5  = md5($data);
  $file = $conf['cachedir'].'/'.$md5{0}.'/'.$md5.$ext;
  io_makeFileDir($file);
  return $file;
}

/**
 * Checks a pageid against $conf['hidepages']
 *
 * @author Andreas Gohr <gohr@cosmocode.de>
 */
function isHiddenPage($id){
  global $conf;
  if(empty($conf['hidepages'])) return false;

  if(preg_match('/'.$conf['hidepages'].'/ui',':'.$id)){
    return true;
  }
  return false;
}

/**
 * Reverse of isHiddenPage
 *
 * @author Andreas Gohr <gohr@cosmocode.de>
 */
function isVisiblePage($id){
  return !isHiddenPage($id);
}

/**
 * Checks and sets HTTP headers for conditional HTTP requests
 *
 * @author   Simon Willison <swillison@gmail.com>
 * @link     http://simon.incutio.com/archive/2003/04/23/conditionalGet
 * @param    timestamp $timestamp lastmodified time of the cache file
 * @returns  void or void with previously header() commands executed
 */
function http_conditionalRequest($timestamp){
  // A PHP implementation of conditional get, see
  //   http://fishbowl.pastiche.org/archives/001132.html
  $last_modified = substr(gmdate('r', $timestamp), 0, -5).'GMT';
  $etag = '"'.md5($last_modified).'"';
  // Send the headers
  header("Last-Modified: $last_modified");
  header("ETag: $etag");
  // See if the client has provided the required headers
  if (isset($_SERVER['HTTP_IF_MODIFIED_SINCE'])){
    $if_modified_since = stripslashes($_SERVER['HTTP_IF_MODIFIED_SINCE']);
  }else{
    $if_modified_since = false;
  }

  if (isset($_SERVER['HTTP_IF_NONE_MATCH'])){
    $if_none_match = stripslashes($_SERVER['HTTP_IF_NONE_MATCH']);
  }else{
    $if_none_match = false;
  }

  if (!$if_modified_since && !$if_none_match){
    return;
  }

  // At least one of the headers is there - check them
  if ($if_none_match && $if_none_match != $etag) {
    return; // etag is there but doesn't match
  }

  if ($if_modified_since && $if_modified_since != $last_modified) {
    return; // if-modified-since is there but doesn't match
  }

  // Nothing has changed since their last request - serve a 304 and exit
  header('HTTP/1.0 304 Not Modified');

  // don't produce output, even if compression is on
  ob_end_clean();
  exit;
}

//Setup VIM: ex: et ts=2 enc=utf-8 :