We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.
Total Complexity | 137 |
Total Lines | 1626 |
Duplicated Lines | 0 % |
Changes | 0 |
Complex classes like Doc often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Doc, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
54 | abstract class Doc |
||
55 | { |
||
56 | /** |
||
57 | * This holds the logger |
||
58 | * |
||
59 | * @var LogManager |
||
60 | * @access protected |
||
61 | */ |
||
62 | protected $logger; |
||
63 | |||
64 | /** |
||
65 | * This holds the PID for the configuration |
||
66 | * |
||
67 | * @var int |
||
68 | * @access protected |
||
69 | */ |
||
70 | protected $cPid = 0; |
||
71 | |||
72 | /** |
||
73 | * The extension key |
||
74 | * |
||
75 | * @var string |
||
76 | * @access public |
||
77 | */ |
||
78 | public static $extKey = 'dlf'; |
||
79 | |||
80 | /** |
||
81 | * This holds the configuration for all supported metadata encodings |
||
82 | * @see loadFormats() |
||
83 | * |
||
84 | * @var array |
||
85 | * @access protected |
||
86 | */ |
||
87 | protected $formats = [ |
||
88 | 'OAI' => [ |
||
89 | 'rootElement' => 'OAI-PMH', |
||
90 | 'namespaceURI' => 'http://www.openarchives.org/OAI/2.0/', |
||
91 | ], |
||
92 | 'METS' => [ |
||
93 | 'rootElement' => 'mets', |
||
94 | 'namespaceURI' => 'http://www.loc.gov/METS/', |
||
95 | ], |
||
96 | 'XLINK' => [ |
||
97 | 'rootElement' => 'xlink', |
||
98 | 'namespaceURI' => 'http://www.w3.org/1999/xlink', |
||
99 | ] |
||
100 | ]; |
||
101 | |||
102 | /** |
||
103 | * Are the available metadata formats loaded? |
||
104 | * @see $formats |
||
105 | * |
||
106 | * @var bool |
||
107 | * @access protected |
||
108 | */ |
||
109 | protected $formatsLoaded = false; |
||
110 | |||
111 | /** |
||
112 | * Are there any fulltext files available? This also includes IIIF text annotations |
||
113 | * with motivation 'painting' if Kitodo.Presentation is configured to store text |
||
114 | * annotations as fulltext. |
||
115 | * |
||
116 | * @var bool |
||
117 | * @access protected |
||
118 | */ |
||
119 | protected $hasFulltext = false; |
||
120 | |||
121 | /** |
||
122 | * Last searched logical and physical page |
||
123 | * |
||
124 | * @var array |
||
125 | * @access protected |
||
126 | */ |
||
127 | protected $lastSearchedPhysicalPage = ['logicalPage' => null, 'physicalPage' => null]; |
||
128 | |||
129 | /** |
||
130 | * This holds the documents location |
||
131 | * |
||
132 | * @var string |
||
133 | * @access protected |
||
134 | */ |
||
135 | protected $location = ''; |
||
136 | |||
137 | /** |
||
138 | * This holds the logical units |
||
139 | * |
||
140 | * @var array |
||
141 | * @access protected |
||
142 | */ |
||
143 | protected $logicalUnits = []; |
||
144 | |||
145 | /** |
||
146 | * This holds the documents' parsed metadata array with their corresponding |
||
147 | * structMap//div's ID (METS) or Range / Manifest / Sequence ID (IIIF) as array key |
||
148 | * |
||
149 | * @var array |
||
150 | * @access protected |
||
151 | */ |
||
152 | protected $metadataArray = []; |
||
153 | |||
154 | /** |
||
155 | * Is the metadata array loaded? |
||
156 | * @see $metadataArray |
||
157 | * |
||
158 | * @var bool |
||
159 | * @access protected |
||
160 | */ |
||
161 | protected $metadataArrayLoaded = false; |
||
162 | |||
163 | /** |
||
164 | * The holds the total number of pages |
||
165 | * |
||
166 | * @var int |
||
167 | * @access protected |
||
168 | */ |
||
169 | protected $numPages = 0; |
||
170 | |||
171 | /** |
||
172 | * This holds the UID of the parent document or zero if not multi-volumed |
||
173 | * |
||
174 | * @var int |
||
175 | * @access protected |
||
176 | */ |
||
177 | protected $parentId = 0; |
||
178 | |||
179 | /** |
||
180 | * This holds the physical structure |
||
181 | * |
||
182 | * @var array |
||
183 | * @access protected |
||
184 | */ |
||
185 | protected $physicalStructure = []; |
||
186 | |||
187 | /** |
||
188 | * This holds the physical structure metadata |
||
189 | * |
||
190 | * @var array |
||
191 | * @access protected |
||
192 | */ |
||
193 | protected $physicalStructureInfo = []; |
||
194 | |||
195 | /** |
||
196 | * Is the physical structure loaded? |
||
197 | * @see $physicalStructure |
||
198 | * |
||
199 | * @var bool |
||
200 | * @access protected |
||
201 | */ |
||
202 | protected $physicalStructureLoaded = false; |
||
203 | |||
204 | /** |
||
205 | * This holds the PID of the document or zero if not in database |
||
206 | * |
||
207 | * @var int |
||
208 | * @access protected |
||
209 | */ |
||
210 | protected $pid = 0; |
||
211 | |||
212 | /** |
||
213 | * This holds the documents' raw text pages with their corresponding |
||
214 | * structMap//div's ID (METS) or Range / Manifest / Sequence ID (IIIF) as array key |
||
215 | * |
||
216 | * @var array |
||
217 | * @access protected |
||
218 | */ |
||
219 | protected $rawTextArray = []; |
||
220 | |||
221 | /** |
||
222 | * Is the document instantiated successfully? |
||
223 | * |
||
224 | * @var bool |
||
225 | * @access protected |
||
226 | */ |
||
227 | protected $ready = false; |
||
228 | |||
229 | /** |
||
230 | * The METS file's / IIIF manifest's record identifier |
||
231 | * |
||
232 | * @var string |
||
233 | * @access protected |
||
234 | */ |
||
235 | protected $recordId; |
||
236 | |||
237 | /** |
||
238 | * This holds the singleton object of the document |
||
239 | * |
||
240 | * @var array (\Kitodo\Dlf\Common\Doc) |
||
241 | * @static |
||
242 | * @access protected |
||
243 | */ |
||
244 | protected static $registry = []; |
||
245 | |||
246 | /** |
||
247 | * This holds the UID of the root document or zero if not multi-volumed |
||
248 | * |
||
249 | * @var int |
||
250 | * @access protected |
||
251 | */ |
||
252 | protected $rootId = 0; |
||
253 | |||
254 | /** |
||
255 | * Is the root id loaded? |
||
256 | * @see $rootId |
||
257 | * |
||
258 | * @var bool |
||
259 | * @access protected |
||
260 | */ |
||
261 | protected $rootIdLoaded = false; |
||
262 | |||
263 | /** |
||
264 | * This holds the smLinks between logical and physical structMap |
||
265 | * |
||
266 | * @var array |
||
267 | * @access protected |
||
268 | */ |
||
269 | protected $smLinks = ['l2p' => [], 'p2l' => []]; |
||
270 | |||
271 | /** |
||
272 | * Are the smLinks loaded? |
||
273 | * @see $smLinks |
||
274 | * |
||
275 | * @var bool |
||
276 | * @access protected |
||
277 | */ |
||
278 | protected $smLinksLoaded = false; |
||
279 | |||
280 | /** |
||
281 | * This holds the logical structure |
||
282 | * |
||
283 | * @var array |
||
284 | * @access protected |
||
285 | */ |
||
286 | protected $tableOfContents = []; |
||
287 | |||
288 | /** |
||
289 | * Is the table of contents loaded? |
||
290 | * @see $tableOfContents |
||
291 | * |
||
292 | * @var bool |
||
293 | * @access protected |
||
294 | */ |
||
295 | protected $tableOfContentsLoaded = false; |
||
296 | |||
297 | /** |
||
298 | * This holds the document's thumbnail location |
||
299 | * |
||
300 | * @var string |
||
301 | * @access protected |
||
302 | */ |
||
303 | protected $thumbnail = ''; |
||
304 | |||
305 | /** |
||
306 | * Is the document's thumbnail location loaded? |
||
307 | * @see $thumbnail |
||
308 | * |
||
309 | * @var bool |
||
310 | * @access protected |
||
311 | */ |
||
312 | protected $thumbnailLoaded = false; |
||
313 | |||
314 | /** |
||
315 | * This holds the toplevel structure's @ID (METS) or the manifest's @id (IIIF) |
||
316 | * |
||
317 | * @var string |
||
318 | * @access protected |
||
319 | */ |
||
320 | protected $toplevelId = ''; |
||
321 | |||
322 | /** |
||
323 | * This holds the UID or the URL of the document |
||
324 | * |
||
325 | * @var mixed |
||
326 | * @access protected |
||
327 | */ |
||
328 | protected $uid = 0; |
||
329 | |||
330 | /** |
||
331 | * This holds the whole XML file as \SimpleXMLElement object |
||
332 | * |
||
333 | * @var \SimpleXMLElement |
||
334 | * @access protected |
||
335 | */ |
||
336 | protected $xml; |
||
337 | |||
338 | /** |
||
339 | * This clears the static registry to prevent memory exhaustion |
||
340 | * |
||
341 | * @access public |
||
342 | * |
||
343 | * @static |
||
344 | * |
||
345 | * @return void |
||
346 | */ |
||
347 | public static function clearRegistry() |
||
348 | { |
||
349 | // Reset registry array. |
||
350 | self::$registry = []; |
||
351 | } |
||
352 | |||
353 | /** |
||
354 | * This ensures that the recordId, if existent, is retrieved from the document |
||
355 | * |
||
356 | * @access protected |
||
357 | * |
||
358 | * @abstract |
||
359 | * |
||
360 | * @param int $pid: ID of the configuration page with the recordId config |
||
361 | * |
||
362 | */ |
||
363 | protected abstract function establishRecordId($pid); |
||
364 | |||
365 | /** |
||
366 | * Source document PHP object which is represented by a Document instance |
||
367 | * |
||
368 | * @access protected |
||
369 | * |
||
370 | * @abstract |
||
371 | * |
||
372 | * @return \SimpleXMLElement|IiifResourceInterface An PHP object representation of |
||
373 | * the current document. SimpleXMLElement for METS, IiifResourceInterface for IIIF |
||
374 | */ |
||
375 | protected abstract function getDocument(); |
||
376 | |||
377 | /** |
||
378 | * This gets the location of a downloadable file for a physical page or track |
||
379 | * |
||
380 | * @access public |
||
381 | * |
||
382 | * @abstract |
||
383 | * |
||
384 | * @param string $id: The @ID attribute of the file node (METS) or the @id property of the IIIF resource |
||
385 | * |
||
386 | * @return string The file's location as URL |
||
387 | */ |
||
388 | public abstract function getDownloadLocation($id); |
||
389 | |||
390 | /** |
||
391 | * This gets the location of a file representing a physical page or track |
||
392 | * |
||
393 | * @access public |
||
394 | * |
||
395 | * @abstract |
||
396 | * |
||
397 | * @param string $id: The @ID attribute of the file node (METS) or the @id property of the IIIF resource |
||
398 | * |
||
399 | * @return string The file's location as URL |
||
400 | */ |
||
401 | public abstract function getFileLocation($id); |
||
402 | |||
403 | /** |
||
404 | * This gets the MIME type of a file representing a physical page or track |
||
405 | * |
||
406 | * @access public |
||
407 | * |
||
408 | * @abstract |
||
409 | * |
||
410 | * @param string $id: The @ID attribute of the file node |
||
411 | * |
||
412 | * @return string The file's MIME type |
||
413 | */ |
||
414 | public abstract function getFileMimeType($id); |
||
415 | |||
416 | /** |
||
417 | * This is a singleton class, thus an instance must be created by this method |
||
418 | * |
||
419 | * @access public |
||
420 | * |
||
421 | * @static |
||
422 | * |
||
423 | * @param string $location: The URL of XML file or the IRI of the IIIF resource |
||
424 | * @param array $settings |
||
425 | * @param bool $forceReload: Force reloading the document instead of returning the cached instance |
||
426 | * |
||
427 | * @return \Kitodo\Dlf\Common\Doc Instance of this class, either MetsDocument or IiifManifest |
||
428 | */ |
||
429 | public static function &getInstance($location, $settings = [], $forceReload = false) |
||
430 | { |
||
431 | // Create new instance depending on format (METS or IIIF) ... |
||
432 | $instance = null; |
||
433 | $documentFormat = null; |
||
434 | $xml = null; |
||
435 | $iiif = null; |
||
436 | |||
437 | // Try to load a file from the url |
||
438 | if (GeneralUtility::isValidUrl($location)) { |
||
439 | // Load extension configuration |
||
440 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
441 | // Set user-agent to identify self when fetching XML data. |
||
442 | if (!empty($extConf['useragent'])) { |
||
443 | @ini_set('user_agent', $extConf['useragent']); |
||
444 | } |
||
445 | $content = GeneralUtility::getUrl($location); |
||
446 | if ($content !== false) { |
||
447 | $xml = Helper::getXmlFileAsString($content); |
||
448 | if ($xml !== false) { |
||
449 | /* @var $xml \SimpleXMLElement */ |
||
450 | $xml->registerXPathNamespace('mets', 'http://www.loc.gov/METS/'); |
||
451 | $xpathResult = $xml->xpath('//mets:mets'); |
||
452 | $documentFormat = !empty($xpathResult) ? 'METS' : null; |
||
453 | } else { |
||
454 | // Try to load file as IIIF resource instead. |
||
455 | $contentAsJsonArray = json_decode($content, true); |
||
456 | if ($contentAsJsonArray !== null) { |
||
457 | // Load plugin configuration. |
||
458 | $conf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
459 | IiifHelper::setUrlReader(IiifUrlReader::getInstance()); |
||
460 | IiifHelper::setMaxThumbnailHeight($conf['iiifThumbnailHeight']); |
||
461 | IiifHelper::setMaxThumbnailWidth($conf['iiifThumbnailWidth']); |
||
462 | $iiif = IiifHelper::loadIiifResource($contentAsJsonArray); |
||
463 | if ($iiif instanceof IiifResourceInterface) { |
||
464 | $documentFormat = 'IIIF'; |
||
465 | } |
||
466 | } |
||
467 | } |
||
468 | } |
||
469 | } |
||
470 | |||
471 | // Sanitize input. |
||
472 | $pid = max(intval($pid), 0); |
||
|
|||
473 | if ($documentFormat == 'METS') { |
||
474 | $instance = new MetsDocument($uid, $pid, $xml); |
||
475 | } elseif ($documentFormat == 'IIIF') { |
||
476 | $instance = new IiifManifest($uid, $pid, $iiif); |
||
477 | } |
||
478 | |||
479 | return $instance; |
||
480 | } |
||
481 | |||
482 | /** |
||
483 | * This gets details about a logical structure element |
||
484 | * |
||
485 | * @access public |
||
486 | * |
||
487 | * @abstract |
||
488 | * |
||
489 | * @param string $id: The @ID attribute of the logical structure node (METS) or |
||
490 | * the @id property of the Manifest / Range (IIIF) |
||
491 | * @param bool $recursive: Whether to include the child elements / resources |
||
492 | * |
||
493 | * @return array Array of the element's id, label, type and physical page indexes/mptr link |
||
494 | */ |
||
495 | public abstract function getLogicalStructure($id, $recursive = false); |
||
496 | |||
497 | /** |
||
498 | * This extracts all the metadata for a logical structure node |
||
499 | * |
||
500 | * @access public |
||
501 | * |
||
502 | * @abstract |
||
503 | * |
||
504 | * @param string $id: The @ID attribute of the logical structure node (METS) or the @id property |
||
505 | * of the Manifest / Range (IIIF) |
||
506 | * @param int $cPid: The PID for the metadata definitions |
||
507 | * (defaults to $this->cPid or $this->pid) |
||
508 | * |
||
509 | * @return array The logical structure node's / the IIIF resource's parsed metadata array |
||
510 | */ |
||
511 | public abstract function getMetadata($id, $cPid = 0); |
||
512 | |||
513 | /** |
||
514 | * This returns the first corresponding physical page number of a given logical page label |
||
515 | * |
||
516 | * @access public |
||
517 | * |
||
518 | * @param string $logicalPage: The label (or a part of the label) of the logical page |
||
519 | * |
||
520 | * @return int The physical page number |
||
521 | */ |
||
522 | public function getPhysicalPage($logicalPage) |
||
523 | { |
||
524 | if ( |
||
525 | !empty($this->lastSearchedPhysicalPage['logicalPage']) |
||
526 | && $this->lastSearchedPhysicalPage['logicalPage'] == $logicalPage |
||
527 | ) { |
||
528 | return $this->lastSearchedPhysicalPage['physicalPage']; |
||
529 | } else { |
||
530 | $physicalPage = 0; |
||
531 | foreach ($this->physicalStructureInfo as $page) { |
||
532 | if (strpos($page['orderlabel'], $logicalPage) !== false) { |
||
533 | $this->lastSearchedPhysicalPage['logicalPage'] = $logicalPage; |
||
534 | $this->lastSearchedPhysicalPage['physicalPage'] = $physicalPage; |
||
535 | return $physicalPage; |
||
536 | } |
||
537 | $physicalPage++; |
||
538 | } |
||
539 | } |
||
540 | return 1; |
||
541 | } |
||
542 | |||
543 | /** |
||
544 | * This extracts the OCR full text for a physical structure node / IIIF Manifest / Canvas. Text might be |
||
545 | * given as ALTO for METS or as annotations or ALTO for IIIF resources. |
||
546 | * |
||
547 | * @access public |
||
548 | * |
||
549 | * @abstract |
||
550 | * |
||
551 | * @param string $id: The @ID attribute of the physical structure node (METS) or the @id property |
||
552 | * of the Manifest / Range (IIIF) |
||
553 | * |
||
554 | * @return string The OCR full text |
||
555 | */ |
||
556 | public abstract function getFullText($id); |
||
557 | |||
558 | /** |
||
559 | * This extracts the OCR full text for a physical structure node / IIIF Manifest / Canvas from an |
||
560 | * XML full text representation (currently only ALTO). For IIIF manifests, ALTO documents have |
||
561 | * to be given in the Canvas' / Manifest's "seeAlso" property. |
||
562 | * |
||
563 | * @param string $id: The @ID attribute of the physical structure node (METS) or the @id property |
||
564 | * of the Manifest / Range (IIIF) |
||
565 | * |
||
566 | * @return string The OCR full text |
||
567 | */ |
||
568 | protected function getFullTextFromXml($id) |
||
569 | { |
||
570 | $fullText = ''; |
||
571 | // Load available text formats, ... |
||
572 | $this->loadFormats(); |
||
573 | // ... physical structure ... |
||
574 | $this->_getPhysicalStructure(); |
||
575 | // ... and extension configuration. |
||
576 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
577 | $fileGrpsFulltext = GeneralUtility::trimExplode(',', $extConf['fileGrpFulltext']); |
||
578 | if (!empty($this->physicalStructureInfo[$id])) { |
||
579 | while ($fileGrpFulltext = array_shift($fileGrpsFulltext)) { |
||
580 | if (!empty($this->physicalStructureInfo[$id]['files'][$fileGrpFulltext])) { |
||
581 | // Get full text file. |
||
582 | $fileContent = GeneralUtility::getUrl($this->getFileLocation($this->physicalStructureInfo[$id]['files'][$fileGrpFulltext])); |
||
583 | if ($fileContent !== false) { |
||
584 | $textFormat = $this->getTextFormat($fileContent); |
||
585 | } else { |
||
586 | $this->logger->warning('Couldn\'t load full text file for structure node @ID "' . $id . '"'); |
||
587 | return $fullText; |
||
588 | } |
||
589 | break; |
||
590 | } |
||
591 | } |
||
592 | } else { |
||
593 | $this->logger->warning('Invalid structure node @ID "' . $id . '"'); |
||
594 | return $fullText; |
||
595 | } |
||
596 | // Is this text format supported? |
||
597 | // This part actually differs from previous version of indexed OCR |
||
598 | if (!empty($fileContent) && !empty($this->formats[$textFormat])) { |
||
599 | $textMiniOcr = ''; |
||
600 | if (!empty($this->formats[$textFormat]['class'])) { |
||
601 | $class = $this->formats[$textFormat]['class']; |
||
602 | // Get the raw text from class. |
||
603 | if ( |
||
604 | class_exists($class) |
||
605 | && ($obj = GeneralUtility::makeInstance($class)) instanceof FulltextInterface |
||
606 | ) { |
||
607 | // Load XML from file. |
||
608 | $ocrTextXml = Helper::getXmlFileAsString($fileContent); |
||
609 | $textMiniOcr = $obj->getTextAsMiniOcr($ocrTextXml); |
||
610 | $this->rawTextArray[$id] = $textMiniOcr; |
||
611 | } else { |
||
612 | $this->logger->warning('Invalid class/method "' . $class . '->getRawText()" for text format "' . $textFormat . '"'); |
||
613 | } |
||
614 | } |
||
615 | $fullText = $textMiniOcr; |
||
616 | } else { |
||
617 | $this->logger->warning('Unsupported text format "' . $textFormat . '" in physical node with @ID "' . $id . '"'); |
||
618 | } |
||
619 | return $fullText; |
||
620 | } |
||
621 | |||
622 | /** |
||
623 | * Get format of the OCR full text |
||
624 | * |
||
625 | * @access private |
||
626 | * |
||
627 | * @param string $fileContent: content of the XML file |
||
628 | * |
||
629 | * @return string The format of the OCR full text |
||
630 | */ |
||
631 | private function getTextFormat($fileContent) |
||
632 | { |
||
633 | // Get the root element's name as text format. |
||
634 | return strtoupper(Helper::getXmlFileAsString($fileContent)->getName()); |
||
635 | } |
||
636 | |||
637 | /** |
||
638 | * This determines a title for the given document |
||
639 | * |
||
640 | * @access public |
||
641 | * |
||
642 | * @static |
||
643 | * |
||
644 | * @param int $uid: The UID of the document |
||
645 | * @param bool $recursive: Search superior documents for a title, too? |
||
646 | * |
||
647 | * @return string The title of the document itself or a parent document |
||
648 | */ |
||
649 | public static function getTitle($uid, $recursive = false) |
||
650 | { |
||
651 | $title = ''; |
||
652 | // Sanitize input. |
||
653 | $uid = max(intval($uid), 0); |
||
654 | if ($uid) { |
||
655 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
656 | ->getQueryBuilderForTable('tx_dlf_documents'); |
||
657 | |||
658 | $result = $queryBuilder |
||
659 | ->select( |
||
660 | 'tx_dlf_documents.title', |
||
661 | 'tx_dlf_documents.partof' |
||
662 | ) |
||
663 | ->from('tx_dlf_documents') |
||
664 | ->where( |
||
665 | $queryBuilder->expr()->eq('tx_dlf_documents.uid', $uid), |
||
666 | Helper::whereExpression('tx_dlf_documents') |
||
667 | ) |
||
668 | ->setMaxResults(1) |
||
669 | ->execute(); |
||
670 | |||
671 | if ($resArray = $result->fetch()) { |
||
672 | // Get title information. |
||
673 | $title = $resArray['title']; |
||
674 | $partof = $resArray['partof']; |
||
675 | // Search parent documents recursively for a title? |
||
676 | if ( |
||
677 | $recursive |
||
678 | && empty($title) |
||
679 | && intval($partof) |
||
680 | && $partof != $uid |
||
681 | ) { |
||
682 | $title = self::getTitle($partof, true); |
||
683 | } |
||
684 | } else { |
||
685 | Helper::log('No document with UID ' . $uid . ' found or document not accessible', LOG_SEVERITY_WARNING); |
||
686 | } |
||
687 | } else { |
||
688 | Helper::log('Invalid UID ' . $uid . ' for document', LOG_SEVERITY_ERROR); |
||
689 | } |
||
690 | return $title; |
||
691 | } |
||
692 | |||
693 | /** |
||
694 | * This extracts all the metadata for the toplevel logical structure node / resource |
||
695 | * |
||
696 | * @access public |
||
697 | * |
||
698 | * @param int $cPid: The PID for the metadata definitions |
||
699 | * |
||
700 | * @return array The logical structure node's / resource's parsed metadata array |
||
701 | */ |
||
702 | public function getTitledata($cPid = 0) |
||
703 | { |
||
704 | $titledata = $this->getMetadata($this->_getToplevelId(), $cPid); |
||
705 | // Add information from METS structural map to titledata array. |
||
706 | if ($this instanceof MetsDocument) { |
||
707 | $this->addMetadataFromMets($titledata, $this->_getToplevelId()); |
||
708 | } |
||
709 | // Set record identifier for METS file / IIIF manifest if not present. |
||
710 | if ( |
||
711 | is_array($titledata) |
||
712 | && array_key_exists('record_id', $titledata) |
||
713 | ) { |
||
714 | if ( |
||
715 | !empty($this->recordId) |
||
716 | && !in_array($this->recordId, $titledata['record_id']) |
||
717 | ) { |
||
718 | array_unshift($titledata['record_id'], $this->recordId); |
||
719 | } |
||
720 | } |
||
721 | return $titledata; |
||
722 | } |
||
723 | |||
724 | /** |
||
725 | * Traverse a logical (sub-) structure tree to find the structure with the requested logical id and return it's depth. |
||
726 | * |
||
727 | * @access protected |
||
728 | * |
||
729 | * @param array $structure: logical structure array |
||
730 | * @param int $depth: current tree depth |
||
731 | * @param string $logId: ID of the logical structure whose depth is requested |
||
732 | * |
||
733 | * @return int|bool: false if structure with $logId is not a child of this substructure, |
||
734 | * or the actual depth. |
||
735 | */ |
||
736 | protected function getTreeDepth($structure, $depth, $logId) |
||
737 | { |
||
738 | foreach ($structure as $element) { |
||
739 | if ($element['id'] == $logId) { |
||
740 | return $depth; |
||
741 | } elseif (array_key_exists('children', $element)) { |
||
742 | $foundInChildren = $this->getTreeDepth($element['children'], $depth + 1, $logId); |
||
743 | if ($foundInChildren !== false) { |
||
744 | return $foundInChildren; |
||
745 | } |
||
746 | } |
||
747 | } |
||
748 | return false; |
||
749 | } |
||
750 | |||
751 | /** |
||
752 | * Get the tree depth of a logical structure element within the table of content |
||
753 | * |
||
754 | * @access public |
||
755 | * |
||
756 | * @param string $logId: The id of the logical structure element whose depth is requested |
||
757 | * @return int|bool tree depth as integer or false if no element with $logId exists within the TOC. |
||
758 | */ |
||
759 | public function getStructureDepth($logId) |
||
760 | { |
||
761 | return $this->getTreeDepth($this->_getTableOfContents(), 1, $logId); |
||
762 | } |
||
763 | |||
764 | /** |
||
765 | * This sets some basic class properties |
||
766 | * |
||
767 | * @access protected |
||
768 | * |
||
769 | * @abstract |
||
770 | * |
||
771 | * @return void |
||
772 | */ |
||
773 | protected abstract function init(); |
||
774 | |||
775 | /** |
||
776 | * Reuse any document object that might have been already loaded to determine wether document is METS or IIIF |
||
777 | * |
||
778 | * @access protected |
||
779 | * |
||
780 | * @abstract |
||
781 | * |
||
782 | * @param \SimpleXMLElement|IiifResourceInterface $preloadedDocument: any instance that has already been loaded |
||
783 | * |
||
784 | * @return bool true if $preloadedDocument can actually be reused, false if it has to be loaded again |
||
785 | */ |
||
786 | protected abstract function setPreloadedDocument($preloadedDocument); |
||
787 | |||
788 | /** |
||
789 | * METS/IIIF specific part of loading a location |
||
790 | * |
||
791 | * @access protected |
||
792 | * |
||
793 | * @abstract |
||
794 | * |
||
795 | * @param string $location: The URL of the file to load |
||
796 | * |
||
797 | * @return bool true on success or false on failure |
||
798 | */ |
||
799 | protected abstract function loadLocation($location); |
||
800 | |||
801 | /** |
||
802 | * Load XML file / IIIF resource from URL |
||
803 | * |
||
804 | * @access protected |
||
805 | * |
||
806 | * @param string $location: The URL of the file to load |
||
807 | * |
||
808 | * @return bool true on success or false on failure |
||
809 | */ |
||
810 | protected function load($location) |
||
811 | { |
||
812 | // Load XML / JSON-LD file. |
||
813 | if (GeneralUtility::isValidUrl($location)) { |
||
814 | // Load extension configuration |
||
815 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
816 | // Set user-agent to identify self when fetching XML / JSON-LD data. |
||
817 | if (!empty($extConf['useragent'])) { |
||
818 | @ini_set('user_agent', $extConf['useragent']); |
||
819 | } |
||
820 | // the actual loading is format specific |
||
821 | return $this->loadLocation($location); |
||
822 | } else { |
||
823 | $this->logger->error('Invalid file location "' . $location . '" for document loading'); |
||
824 | } |
||
825 | return false; |
||
826 | } |
||
827 | |||
828 | /** |
||
829 | * Analyze the document if it contains any fulltext that needs to be indexed. |
||
830 | * |
||
831 | * @access protected |
||
832 | * |
||
833 | * @abstract |
||
834 | */ |
||
835 | protected abstract function ensureHasFulltextIsSet(); |
||
836 | |||
837 | /** |
||
838 | * Register all available data formats |
||
839 | * |
||
840 | * @access protected |
||
841 | * |
||
842 | * @return void |
||
843 | */ |
||
844 | protected function loadFormats() |
||
845 | { |
||
846 | if (!$this->formatsLoaded) { |
||
847 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
848 | ->getQueryBuilderForTable('tx_dlf_formats'); |
||
849 | |||
850 | // Get available data formats from database. |
||
851 | $result = $queryBuilder |
||
852 | ->select( |
||
853 | 'tx_dlf_formats.type AS type', |
||
854 | 'tx_dlf_formats.root AS root', |
||
855 | 'tx_dlf_formats.namespace AS namespace', |
||
856 | 'tx_dlf_formats.class AS class' |
||
857 | ) |
||
858 | ->from('tx_dlf_formats') |
||
859 | ->where( |
||
860 | $queryBuilder->expr()->eq('tx_dlf_formats.pid', 0) |
||
861 | ) |
||
862 | ->execute(); |
||
863 | |||
864 | while ($resArray = $result->fetch()) { |
||
865 | // Update format registry. |
||
866 | $this->formats[$resArray['type']] = [ |
||
867 | 'rootElement' => $resArray['root'], |
||
868 | 'namespaceURI' => $resArray['namespace'], |
||
869 | 'class' => $resArray['class'] |
||
870 | ]; |
||
871 | } |
||
872 | $this->formatsLoaded = true; |
||
873 | } |
||
874 | } |
||
875 | |||
876 | /** |
||
877 | * Register all available namespaces for a \SimpleXMLElement object |
||
878 | * |
||
879 | * @access public |
||
880 | * |
||
881 | * @param \SimpleXMLElement|\DOMXPath &$obj: \SimpleXMLElement or \DOMXPath object |
||
882 | * |
||
883 | * @return void |
||
884 | */ |
||
885 | public function registerNamespaces(&$obj) |
||
886 | { |
||
887 | // TODO Check usage. XML specific method does not seem to be used anywhere outside this class within the project, but it is public and may be used by extensions. |
||
888 | $this->loadFormats(); |
||
889 | // Do we have a \SimpleXMLElement or \DOMXPath object? |
||
890 | if ($obj instanceof \SimpleXMLElement) { |
||
891 | $method = 'registerXPathNamespace'; |
||
892 | } elseif ($obj instanceof \DOMXPath) { |
||
893 | $method = 'registerNamespace'; |
||
894 | } else { |
||
895 | $this->logger->error('Given object is neither a SimpleXMLElement nor a DOMXPath instance'); |
||
896 | return; |
||
897 | } |
||
898 | // Register metadata format's namespaces. |
||
899 | foreach ($this->formats as $enc => $conf) { |
||
900 | $obj->$method(strtolower($enc), $conf['namespaceURI']); |
||
901 | } |
||
902 | } |
||
903 | |||
904 | /** |
||
905 | * This saves the document to the database and index |
||
906 | * |
||
907 | * @access public |
||
908 | * |
||
909 | * @param int $pid: The PID of the saved record |
||
910 | * @param int $core: The UID of the Solr core for indexing |
||
911 | * @param int|string $owner: UID or index_name of owner to set while indexing |
||
912 | * |
||
913 | * @return bool true on success or false on failure |
||
914 | */ |
||
915 | public function save($pid = 0, $core = 0, $owner = null) |
||
916 | { |
||
917 | if (\TYPO3_MODE !== 'BE') { |
||
918 | $this->logger->error('Saving a document is only allowed in the backend'); |
||
919 | return false; |
||
920 | } |
||
921 | // Make sure $pid is a non-negative integer. |
||
922 | $pid = max(intval($pid), 0); |
||
923 | // Make sure $core is a non-negative integer. |
||
924 | $core = max(intval($core), 0); |
||
925 | // If $pid is not given, try to get it elsewhere. |
||
926 | if ( |
||
927 | !$pid |
||
928 | && $this->pid |
||
929 | ) { |
||
930 | // Retain current PID. |
||
931 | $pid = $this->pid; |
||
932 | } elseif (!$pid) { |
||
933 | $this->logger->error('Invalid PID ' . $pid . ' for document saving'); |
||
934 | return false; |
||
935 | } |
||
936 | // Set PID for metadata definitions. |
||
937 | $this->cPid = $pid; |
||
938 | // Set UID placeholder if not updating existing record. |
||
939 | if ($pid != $this->pid) { |
||
940 | $this->uid = uniqid('NEW'); |
||
941 | } |
||
942 | // Get metadata array. |
||
943 | $metadata = $this->getTitledata($pid); |
||
944 | // Check for record identifier. |
||
945 | if (empty($metadata['record_id'][0])) { |
||
946 | $this->logger->error('No record identifier found to avoid duplication'); |
||
947 | return false; |
||
948 | } |
||
949 | // Load plugin configuration. |
||
950 | $conf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
951 | |||
952 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
953 | ->getQueryBuilderForTable('tx_dlf_structures'); |
||
954 | |||
955 | // Get UID for structure type. |
||
956 | $result = $queryBuilder |
||
957 | ->select('tx_dlf_structures.uid AS uid') |
||
958 | ->from('tx_dlf_structures') |
||
959 | ->where( |
||
960 | $queryBuilder->expr()->eq('tx_dlf_structures.pid', intval($pid)), |
||
961 | $queryBuilder->expr()->eq('tx_dlf_structures.index_name', $queryBuilder->expr()->literal($metadata['type'][0])), |
||
962 | Helper::whereExpression('tx_dlf_structures') |
||
963 | ) |
||
964 | ->setMaxResults(1) |
||
965 | ->execute(); |
||
966 | |||
967 | if ($resArray = $result->fetch()) { |
||
968 | $structure = $resArray['uid']; |
||
969 | } else { |
||
970 | $this->logger->error('Could not identify document/structure type "' . $queryBuilder->expr()->literal($metadata['type'][0]) . '"'); |
||
971 | return false; |
||
972 | } |
||
973 | $metadata['type'][0] = $structure; |
||
974 | |||
975 | // Remove appended "valueURI" from authors' names for storing in database. |
||
976 | foreach ($metadata['author'] as $i => $author) { |
||
977 | $splitName = explode(chr(31), $author); |
||
978 | $metadata['author'][$i] = $splitName[0]; |
||
979 | } |
||
980 | |||
981 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
982 | ->getQueryBuilderForTable('tx_dlf_collections'); |
||
983 | // Get hidden records, too. |
||
984 | $queryBuilder |
||
985 | ->getRestrictions() |
||
986 | ->removeByType(HiddenRestriction::class); |
||
987 | |||
988 | // Get UIDs for collections. |
||
989 | $result = $queryBuilder |
||
990 | ->select( |
||
991 | 'tx_dlf_collections.index_name AS index_name', |
||
992 | 'tx_dlf_collections.uid AS uid' |
||
993 | ) |
||
994 | ->from('tx_dlf_collections') |
||
995 | ->where( |
||
996 | $queryBuilder->expr()->eq('tx_dlf_collections.pid', intval($pid)), |
||
997 | $queryBuilder->expr()->in('tx_dlf_collections.sys_language_uid', [-1, 0]) |
||
998 | ) |
||
999 | ->execute(); |
||
1000 | |||
1001 | $collUid = []; |
||
1002 | while ($resArray = $result->fetch()) { |
||
1003 | $collUid[$resArray['index_name']] = $resArray['uid']; |
||
1004 | } |
||
1005 | $collections = []; |
||
1006 | foreach ($metadata['collection'] as $collection) { |
||
1007 | if (!empty($collUid[$collection])) { |
||
1008 | // Add existing collection's UID. |
||
1009 | $collections[] = $collUid[$collection]; |
||
1010 | } else { |
||
1011 | // Insert new collection. |
||
1012 | $collNewUid = uniqid('NEW'); |
||
1013 | $collData['tx_dlf_collections'][$collNewUid] = [ |
||
1014 | 'pid' => $pid, |
||
1015 | 'label' => $collection, |
||
1016 | 'index_name' => $collection, |
||
1017 | 'oai_name' => (!empty($conf['publishNewCollections']) ? Helper::getCleanString($collection) : ''), |
||
1018 | 'description' => '', |
||
1019 | 'documents' => 0, |
||
1020 | 'owner' => 0, |
||
1021 | 'status' => 0, |
||
1022 | ]; |
||
1023 | $substUid = Helper::processDBasAdmin($collData); |
||
1024 | // Prevent double insertion. |
||
1025 | unset($collData); |
||
1026 | // Add new collection's UID. |
||
1027 | $collections[] = $substUid[$collNewUid]; |
||
1028 | if (!(\TYPO3_REQUESTTYPE & \TYPO3_REQUESTTYPE_CLI)) { |
||
1029 | Helper::addMessage( |
||
1030 | htmlspecialchars(sprintf(Helper::getMessage('flash.newCollection'), $collection, $substUid[$collNewUid])), |
||
1031 | Helper::getMessage('flash.attention', true), |
||
1032 | \TYPO3\CMS\Core\Messaging\FlashMessage::INFO, |
||
1033 | true |
||
1034 | ); |
||
1035 | } |
||
1036 | } |
||
1037 | } |
||
1038 | $metadata['collection'] = $collections; |
||
1039 | |||
1040 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
1041 | ->getQueryBuilderForTable('tx_dlf_libraries'); |
||
1042 | |||
1043 | // Get UID for owner. |
||
1044 | if (empty($owner)) { |
||
1045 | $owner = empty($metadata['owner'][0]) ? $metadata['owner'][0] : 'default'; |
||
1046 | } |
||
1047 | if (!MathUtility::canBeInterpretedAsInteger($owner)) { |
||
1048 | $result = $queryBuilder |
||
1049 | ->select('tx_dlf_libraries.uid AS uid') |
||
1050 | ->from('tx_dlf_libraries') |
||
1051 | ->where( |
||
1052 | $queryBuilder->expr()->eq('tx_dlf_libraries.pid', intval($pid)), |
||
1053 | $queryBuilder->expr()->eq('tx_dlf_libraries.index_name', $queryBuilder->expr()->literal($owner)), |
||
1054 | Helper::whereExpression('tx_dlf_libraries') |
||
1055 | ) |
||
1056 | ->setMaxResults(1) |
||
1057 | ->execute(); |
||
1058 | |||
1059 | if ($resArray = $result->fetch()) { |
||
1060 | $ownerUid = $resArray['uid']; |
||
1061 | } else { |
||
1062 | // Insert new library. |
||
1063 | $libNewUid = uniqid('NEW'); |
||
1064 | $libData['tx_dlf_libraries'][$libNewUid] = [ |
||
1065 | 'pid' => $pid, |
||
1066 | 'label' => $owner, |
||
1067 | 'index_name' => $owner, |
||
1068 | 'website' => '', |
||
1069 | 'contact' => '', |
||
1070 | 'image' => '', |
||
1071 | 'oai_label' => '', |
||
1072 | 'oai_base' => '', |
||
1073 | 'opac_label' => '', |
||
1074 | 'opac_base' => '', |
||
1075 | 'union_label' => '', |
||
1076 | 'union_base' => '', |
||
1077 | ]; |
||
1078 | $substUid = Helper::processDBasAdmin($libData); |
||
1079 | // Add new library's UID. |
||
1080 | $ownerUid = $substUid[$libNewUid]; |
||
1081 | if (!(\TYPO3_REQUESTTYPE & \TYPO3_REQUESTTYPE_CLI)) { |
||
1082 | Helper::addMessage( |
||
1083 | htmlspecialchars(sprintf(Helper::getMessage('flash.newLibrary'), $owner, $ownerUid)), |
||
1084 | Helper::getMessage('flash.attention', true), |
||
1085 | \TYPO3\CMS\Core\Messaging\FlashMessage::INFO, |
||
1086 | true |
||
1087 | ); |
||
1088 | } |
||
1089 | } |
||
1090 | $owner = $ownerUid; |
||
1091 | } |
||
1092 | $metadata['owner'][0] = $owner; |
||
1093 | // Get UID of parent document. |
||
1094 | $partof = $this->getParentDocumentUidForSaving($pid, $core, $owner); |
||
1095 | // Use the date of publication or title as alternative sorting metric for parts of multi-part works. |
||
1096 | if (!empty($partof)) { |
||
1097 | if ( |
||
1098 | empty($metadata['volume'][0]) |
||
1099 | && !empty($metadata['year'][0]) |
||
1100 | ) { |
||
1101 | $metadata['volume'] = $metadata['year']; |
||
1102 | } |
||
1103 | if (empty($metadata['volume_sorting'][0])) { |
||
1104 | // If METS @ORDER is given it is preferred over year_sorting and year. |
||
1105 | if (!empty($metadata['mets_order'][0])) { |
||
1106 | $metadata['volume_sorting'][0] = $metadata['mets_order'][0]; |
||
1107 | } elseif (!empty($metadata['year_sorting'][0])) { |
||
1108 | $metadata['volume_sorting'][0] = $metadata['year_sorting'][0]; |
||
1109 | } elseif (!empty($metadata['year'][0])) { |
||
1110 | $metadata['volume_sorting'][0] = $metadata['year'][0]; |
||
1111 | } |
||
1112 | } |
||
1113 | // If volume_sorting is still empty, try to use title_sorting or METS @ORDERLABEL finally (workaround for newspapers) |
||
1114 | if (empty($metadata['volume_sorting'][0])) { |
||
1115 | if (!empty($metadata['title_sorting'][0])) { |
||
1116 | $metadata['volume_sorting'][0] = $metadata['title_sorting'][0]; |
||
1117 | } elseif (!empty($metadata['mets_orderlabel'][0])) { |
||
1118 | $metadata['volume_sorting'][0] = $metadata['mets_orderlabel'][0]; |
||
1119 | } |
||
1120 | } |
||
1121 | } |
||
1122 | |||
1123 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
1124 | ->getQueryBuilderForTable('tx_dlf_metadata'); |
||
1125 | |||
1126 | // Get metadata for lists and sorting. |
||
1127 | $result = $queryBuilder |
||
1128 | ->select( |
||
1129 | 'tx_dlf_metadata.index_name AS index_name', |
||
1130 | 'tx_dlf_metadata.is_listed AS is_listed', |
||
1131 | 'tx_dlf_metadata.is_sortable AS is_sortable' |
||
1132 | ) |
||
1133 | ->from('tx_dlf_metadata') |
||
1134 | ->where( |
||
1135 | $queryBuilder->expr()->orX( |
||
1136 | $queryBuilder->expr()->eq('tx_dlf_metadata.is_listed', 1), |
||
1137 | $queryBuilder->expr()->eq('tx_dlf_metadata.is_sortable', 1) |
||
1138 | ), |
||
1139 | $queryBuilder->expr()->eq('tx_dlf_metadata.pid', intval($pid)), |
||
1140 | Helper::whereExpression('tx_dlf_metadata') |
||
1141 | ) |
||
1142 | ->execute(); |
||
1143 | |||
1144 | $listed = []; |
||
1145 | $sortable = []; |
||
1146 | |||
1147 | while ($resArray = $result->fetch()) { |
||
1148 | if (!empty($metadata[$resArray['index_name']])) { |
||
1149 | if ($resArray['is_listed']) { |
||
1150 | $listed[$resArray['index_name']] = $metadata[$resArray['index_name']]; |
||
1151 | } |
||
1152 | if ($resArray['is_sortable']) { |
||
1153 | $sortable[$resArray['index_name']] = $metadata[$resArray['index_name']][0]; |
||
1154 | } |
||
1155 | } |
||
1156 | } |
||
1157 | // Fill data array. |
||
1158 | $data['tx_dlf_documents'][$this->uid] = [ |
||
1159 | 'pid' => $pid, |
||
1160 | $GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['starttime'] => 0, |
||
1161 | $GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['endtime'] => 0, |
||
1162 | 'prod_id' => $metadata['prod_id'][0], |
||
1163 | 'location' => $this->location, |
||
1164 | 'record_id' => $metadata['record_id'][0], |
||
1165 | 'opac_id' => $metadata['opac_id'][0], |
||
1166 | 'union_id' => $metadata['union_id'][0], |
||
1167 | 'urn' => $metadata['urn'][0], |
||
1168 | 'purl' => $metadata['purl'][0], |
||
1169 | 'title' => $metadata['title'][0], |
||
1170 | 'title_sorting' => $metadata['title_sorting'][0], |
||
1171 | 'author' => implode('; ', $metadata['author']), |
||
1172 | 'year' => implode('; ', $metadata['year']), |
||
1173 | 'place' => implode('; ', $metadata['place']), |
||
1174 | 'thumbnail' => $this->_getThumbnail(true), |
||
1175 | 'metadata' => serialize($listed), |
||
1176 | 'metadata_sorting' => serialize($sortable), |
||
1177 | 'structure' => $metadata['type'][0], |
||
1178 | 'partof' => $partof, |
||
1179 | 'volume' => $metadata['volume'][0], |
||
1180 | 'volume_sorting' => $metadata['volume_sorting'][0], |
||
1181 | 'license' => $metadata['license'][0], |
||
1182 | 'terms' => $metadata['terms'][0], |
||
1183 | 'restrictions' => $metadata['restrictions'][0], |
||
1184 | 'out_of_print' => $metadata['out_of_print'][0], |
||
1185 | 'rights_info' => $metadata['rights_info'][0], |
||
1186 | 'collections' => $metadata['collection'], |
||
1187 | 'mets_label' => $metadata['mets_label'][0], |
||
1188 | 'mets_orderlabel' => $metadata['mets_orderlabel'][0], |
||
1189 | 'mets_order' => $metadata['mets_order'][0], |
||
1190 | 'owner' => $metadata['owner'][0], |
||
1191 | 'solrcore' => $core, |
||
1192 | 'status' => 0, |
||
1193 | 'document_format' => $metadata['document_format'][0], |
||
1194 | ]; |
||
1195 | // Unhide hidden documents. |
||
1196 | if (!empty($conf['unhideOnIndex'])) { |
||
1197 | $data['tx_dlf_documents'][$this->uid][$GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['disabled']] = 0; |
||
1198 | } |
||
1199 | // Process data. |
||
1200 | $newIds = Helper::processDBasAdmin($data); |
||
1201 | // Replace placeholder with actual UID. |
||
1202 | if (strpos($this->uid, 'NEW') === 0) { |
||
1203 | $this->uid = $newIds[$this->uid]; |
||
1204 | $this->pid = $pid; |
||
1205 | $this->parentId = $partof; |
||
1206 | } |
||
1207 | if (!(\TYPO3_REQUESTTYPE & \TYPO3_REQUESTTYPE_CLI)) { |
||
1208 | Helper::addMessage( |
||
1209 | htmlspecialchars(sprintf(Helper::getMessage('flash.documentSaved'), $metadata['title'][0], $this->uid)), |
||
1210 | Helper::getMessage('flash.done', true), |
||
1211 | \TYPO3\CMS\Core\Messaging\FlashMessage::OK, |
||
1212 | true |
||
1213 | ); |
||
1214 | } |
||
1215 | // Add document to index. |
||
1216 | if ($core) { |
||
1217 | return Indexer::add($this, $core); |
||
1218 | } else { |
||
1219 | $this->logger->notice('Invalid UID "' . $core . '" for Solr core'); |
||
1220 | return false; |
||
1221 | } |
||
1222 | } |
||
1223 | |||
1224 | /** |
||
1225 | * Get the ID of the parent document if the current document has one. Also save a parent document |
||
1226 | * to the database and the Solr index if their $pid and the current $pid differ. |
||
1227 | * Currently only applies to METS documents. |
||
1228 | * |
||
1229 | * @access protected |
||
1230 | * |
||
1231 | * @abstract |
||
1232 | * |
||
1233 | * @return int The parent document's id. |
||
1234 | */ |
||
1235 | protected abstract function getParentDocumentUidForSaving($pid, $core, $owner); |
||
1236 | |||
1237 | /** |
||
1238 | * This returns $this->cPid via __get() |
||
1239 | * |
||
1240 | * @access protected |
||
1241 | * |
||
1242 | * @return int The PID of the metadata definitions |
||
1243 | */ |
||
1244 | protected function _getCPid() |
||
1245 | { |
||
1246 | return $this->cPid; |
||
1247 | } |
||
1248 | |||
1249 | /** |
||
1250 | * This returns $this->hasFulltext via __get() |
||
1251 | * |
||
1252 | * @access protected |
||
1253 | * |
||
1254 | * @return bool Are there any fulltext files available? |
||
1255 | */ |
||
1256 | protected function _getHasFulltext() |
||
1257 | { |
||
1258 | $this->ensureHasFulltextIsSet(); |
||
1259 | return $this->hasFulltext; |
||
1260 | } |
||
1261 | |||
1262 | /** |
||
1263 | * This returns $this->location via __get() |
||
1264 | * |
||
1265 | * @access protected |
||
1266 | * |
||
1267 | * @return string The location of the document |
||
1268 | */ |
||
1269 | protected function _getLocation() |
||
1270 | { |
||
1271 | return $this->location; |
||
1272 | } |
||
1273 | |||
1274 | /** |
||
1275 | * Format specific part of building the document's metadata array |
||
1276 | * |
||
1277 | * @access protected |
||
1278 | * |
||
1279 | * @abstract |
||
1280 | * |
||
1281 | * @param int $cPid |
||
1282 | */ |
||
1283 | protected abstract function prepareMetadataArray($cPid); |
||
1284 | |||
1285 | /** |
||
1286 | * This builds an array of the document's metadata |
||
1287 | * |
||
1288 | * @access protected |
||
1289 | * |
||
1290 | * @return array Array of metadata with their corresponding logical structure node ID as key |
||
1291 | */ |
||
1292 | protected function _getMetadataArray() |
||
1293 | { |
||
1294 | // Set metadata definitions' PID. |
||
1295 | $cPid = ($this->cPid ? $this->cPid : $this->pid); |
||
1296 | if (!$cPid) { |
||
1297 | $this->logger->error('Invalid PID ' . $cPid . ' for metadata definitions'); |
||
1298 | return []; |
||
1299 | } |
||
1300 | if ( |
||
1301 | !$this->metadataArrayLoaded |
||
1302 | || $this->metadataArray[0] != $cPid |
||
1303 | ) { |
||
1304 | $this->prepareMetadataArray($cPid); |
||
1305 | $this->metadataArray[0] = $cPid; |
||
1306 | $this->metadataArrayLoaded = true; |
||
1307 | } |
||
1308 | return $this->metadataArray; |
||
1309 | } |
||
1310 | |||
1311 | /** |
||
1312 | * This returns $this->numPages via __get() |
||
1313 | * |
||
1314 | * @access protected |
||
1315 | * |
||
1316 | * @return int The total number of pages and/or tracks |
||
1317 | */ |
||
1318 | protected function _getNumPages() |
||
1319 | { |
||
1320 | $this->_getPhysicalStructure(); |
||
1321 | return $this->numPages; |
||
1322 | } |
||
1323 | |||
1324 | /** |
||
1325 | * This returns $this->parentId via __get() |
||
1326 | * |
||
1327 | * @access protected |
||
1328 | * |
||
1329 | * @return int The UID of the parent document or zero if not applicable |
||
1330 | */ |
||
1331 | protected function _getParentId() |
||
1332 | { |
||
1333 | return $this->parentId; |
||
1334 | } |
||
1335 | |||
1336 | /** |
||
1337 | * This builds an array of the document's physical structure |
||
1338 | * |
||
1339 | * @access protected |
||
1340 | * |
||
1341 | * @abstract |
||
1342 | * |
||
1343 | * @return array Array of physical elements' id, type, label and file representations ordered |
||
1344 | * by @ORDER attribute / IIIF Sequence's Canvases |
||
1345 | */ |
||
1346 | protected abstract function _getPhysicalStructure(); |
||
1347 | |||
1348 | /** |
||
1349 | * This gives an array of the document's physical structure metadata |
||
1350 | * |
||
1351 | * @access protected |
||
1352 | * |
||
1353 | * @return array Array of elements' type, label and file representations ordered by @ID attribute / Canvas order |
||
1354 | */ |
||
1355 | protected function _getPhysicalStructureInfo() |
||
1356 | { |
||
1357 | // Is there no physical structure array yet? |
||
1358 | if (!$this->physicalStructureLoaded) { |
||
1359 | // Build physical structure array. |
||
1360 | $this->_getPhysicalStructure(); |
||
1361 | } |
||
1362 | return $this->physicalStructureInfo; |
||
1363 | } |
||
1364 | |||
1365 | /** |
||
1366 | * This returns $this->pid via __get() |
||
1367 | * |
||
1368 | * @access protected |
||
1369 | * |
||
1370 | * @return int The PID of the document or zero if not in database |
||
1371 | */ |
||
1372 | protected function _getPid() |
||
1373 | { |
||
1374 | return $this->pid; |
||
1375 | } |
||
1376 | |||
1377 | /** |
||
1378 | * This returns $this->ready via __get() |
||
1379 | * |
||
1380 | * @access protected |
||
1381 | * |
||
1382 | * @return bool Is the document instantiated successfully? |
||
1383 | */ |
||
1384 | protected function _getReady() |
||
1385 | { |
||
1386 | return $this->ready; |
||
1387 | } |
||
1388 | |||
1389 | /** |
||
1390 | * This returns $this->recordId via __get() |
||
1391 | * |
||
1392 | * @access protected |
||
1393 | * |
||
1394 | * @return mixed The METS file's / IIIF manifest's record identifier |
||
1395 | */ |
||
1396 | protected function _getRecordId() |
||
1397 | { |
||
1398 | return $this->recordId; |
||
1399 | } |
||
1400 | |||
1401 | /** |
||
1402 | * This returns $this->rootId via __get() |
||
1403 | * |
||
1404 | * @access protected |
||
1405 | * |
||
1406 | * @return int The UID of the root document or zero if not applicable |
||
1407 | */ |
||
1408 | protected function _getRootId() |
||
1409 | { |
||
1410 | if (!$this->rootIdLoaded) { |
||
1411 | if ($this->parentId) { |
||
1412 | $parent = self::getInstance($this->parentId, ['storagePid' => $this->pid]); |
||
1413 | $this->rootId = $parent->rootId; |
||
1414 | } |
||
1415 | $this->rootIdLoaded = true; |
||
1416 | } |
||
1417 | return $this->rootId; |
||
1418 | } |
||
1419 | |||
1420 | /** |
||
1421 | * This returns the smLinks between logical and physical structMap (METS) and models the |
||
1422 | * relation between IIIF Canvases and Manifests / Ranges in the same way |
||
1423 | * |
||
1424 | * @access protected |
||
1425 | * |
||
1426 | * @abstract |
||
1427 | * |
||
1428 | * @return array The links between logical and physical nodes / Range, Manifest and Canvas |
||
1429 | */ |
||
1430 | protected abstract function _getSmLinks(); |
||
1431 | |||
1432 | /** |
||
1433 | * This builds an array of the document's logical structure |
||
1434 | * |
||
1435 | * @access protected |
||
1436 | * |
||
1437 | * @return array Array of structure nodes' id, label, type and physical page indexes/mptr / Canvas link with original hierarchy preserved |
||
1438 | */ |
||
1439 | protected function _getTableOfContents() |
||
1448 | } |
||
1449 | |||
1450 | /** |
||
1451 | * This returns the document's thumbnail location |
||
1452 | * |
||
1453 | * @access protected |
||
1454 | * |
||
1455 | * @abstract |
||
1456 | * |
||
1457 | * @param bool $forceReload: Force reloading the thumbnail instead of returning the cached value |
||
1458 | * |
||
1459 | * @return string The document's thumbnail location |
||
1460 | */ |
||
1461 | protected abstract function _getThumbnail($forceReload = false); |
||
1462 | |||
1463 | /** |
||
1464 | * This returns the ID of the toplevel logical structure node |
||
1465 | * |
||
1466 | * @access protected |
||
1467 | * |
||
1468 | * @abstract |
||
1469 | * |
||
1470 | * @return string The logical structure node's ID |
||
1471 | */ |
||
1472 | protected abstract function _getToplevelId(); |
||
1473 | |||
1474 | /** |
||
1475 | * This returns $this->uid via __get() |
||
1476 | * |
||
1477 | * @access protected |
||
1478 | * |
||
1479 | * @return mixed The UID or the URL of the document |
||
1480 | */ |
||
1481 | protected function _getUid() |
||
1482 | { |
||
1483 | return $this->uid; |
||
1484 | } |
||
1485 | |||
1486 | /** |
||
1487 | * This sets $this->cPid via __set() |
||
1488 | * |
||
1489 | * @access protected |
||
1490 | * |
||
1491 | * @param int $value: The new PID for the metadata definitions |
||
1492 | * |
||
1493 | * @return void |
||
1494 | */ |
||
1495 | protected function _setCPid($value) |
||
1498 | } |
||
1499 | |||
1500 | /** |
||
1501 | * This is a singleton class, thus the constructor should be private/protected |
||
1502 | * (Get an instance of this class by calling \Kitodo\Dlf\Common\Doc::getInstance()) |
||
1503 | * |
||
1504 | * @access protected |
||
1505 | * |
||
1506 | * @param int $uid: The UID of the document to parse or URL to XML file |
||
1507 | * @param int $pid: If > 0, then only document with this PID gets loaded |
||
1508 | * @param \SimpleXMLElement|IiifResourceInterface $preloadedDocument: Either null or the \SimpleXMLElement |
||
1509 | * or IiifResourceInterface that has been loaded to determine the basic document format. |
||
1510 | * |
||
1511 | * @return void |
||
1512 | */ |
||
1513 | protected function __construct($uid, $pid, $preloadedDocument) |
||
1620 | } |
||
1621 | } |
||
1622 | |||
1623 | /** |
||
1624 | * This magic method is called each time an invisible property is referenced from the object |
||
1625 | * |
||
1626 | * @access public |
||
1627 | * |
||
1628 | * @param string $var: Name of variable to get |
||
1629 | * |
||
1630 | * @return mixed Value of $this->$var |
||
1631 | */ |
||
1632 | public function __get($var) |
||
1633 | { |
||
1634 | $method = '_get' . ucfirst($var); |
||
1635 | if ( |
||
1636 | !property_exists($this, $var) |
||
1637 | || !method_exists($this, $method) |
||
1638 | ) { |
||
1639 | $this->logger->warning('There is no getter function for property "' . $var . '"'); |
||
1640 | return; |
||
1641 | } else { |
||
1642 | return $this->$method(); |
||
1643 | } |
||
1644 | } |
||
1645 | |||
1646 | /** |
||
1647 | * This magic method is called each time an invisible property is checked for isset() or empty() |
||
1648 | * |
||
1649 | * @access public |
||
1650 | * |
||
1651 | * @param string $var: Name of variable to check |
||
1652 | * |
||
1653 | * @return bool true if variable is set and not empty, false otherwise |
||
1654 | */ |
||
1655 | public function __isset($var) |
||
1656 | { |
||
1657 | return !empty($this->__get($var)); |
||
1658 | } |
||
1659 | |||
1660 | /** |
||
1661 | * This magic method is called each time an invisible property is referenced from the object |
||
1662 | * |
||
1663 | * @access public |
||
1664 | * |
||
1665 | * @param string $var: Name of variable to set |
||
1666 | * @param mixed $value: New value of variable |
||
1667 | * |
||
1668 | * @return void |
||
1669 | */ |
||
1670 | public function __set($var, $value) |
||
1680 | } |
||
1681 | } |
||
1682 | } |
||
1683 |