Scrutinizer GitHub App not installed

We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.

Install GitHub App

GitHub Access Token became invalid

It seems like the GitHub access token used for retrieving details about this repository from GitHub became invalid. This might prevent certain types of inspections from being run (in particular, everything related to pull requests).
Please ask an admin of your repository to re-new the access token on this website.
Passed
Pull Request — master (#878)
by Beatrycze
03:52
created

MetsDocument::getAllFiles()   B

Complexity

Conditions 7
Paths 11

Size

Total Lines 34
Code Lines 20

Duplication

Lines 0
Ratio 0 %

Importance

Changes 1
Bugs 0 Features 0
Metric Value
cc 7
eloc 20
c 1
b 0
f 0
nc 11
nop 0
dl 0
loc 34
rs 8.6666
1
<?php
2
3
/**
4
 * (c) Kitodo. Key to digital objects e.V. <[email protected]>
5
 *
6
 * This file is part of the Kitodo and TYPO3 projects.
7
 *
8
 * @license GNU General Public License version 3 or later.
9
 * For the full copyright and license information, please read the
10
 * LICENSE.txt file that was distributed with this source code.
11
 */
12
13
namespace Kitodo\Dlf\Common;
14
15
use TYPO3\CMS\Core\Configuration\ExtensionConfiguration;
16
use TYPO3\CMS\Core\Database\ConnectionPool;
17
use TYPO3\CMS\Core\Database\Query\Restriction\HiddenRestriction;
18
use TYPO3\CMS\Core\Utility\GeneralUtility;
19
use Ubl\Iiif\Tools\IiifHelper;
20
use Ubl\Iiif\Services\AbstractImageService;
21
use TYPO3\CMS\Core\Log\LogManager;
22
23
/**
24
 * MetsDocument class for the 'dlf' extension.
25
 *
26
 * @author Sebastian Meyer <[email protected]>
27
 * @author Henrik Lochmann <[email protected]>
28
 * @package TYPO3
29
 * @subpackage dlf
30
 * @access public
31
 * @property int $cPid This holds the PID for the configuration
32
 * @property-read array $mdSec Associative array of METS metadata sections indexed by their IDs.
33
 * @property-read array $dmdSec Subset of `$mdSec` storing only the dmdSec entries; kept for compatibility.
34
 * @property-read array $fileGrps This holds the file ID -> USE concordance
35
 * @property-read array $fileInfos Additional information about files (e.g., ADMID), indexed by ID.
36
 * @property-read bool $hasFulltext Are there any fulltext files available?
37
 * @property-read array $metadataArray This holds the documents' parsed metadata array
38
 * @property-read \SimpleXMLElement $mets This holds the XML file's METS part as \SimpleXMLElement object
39
 * @property-read int $numPages The holds the total number of pages
40
 * @property-read int $parentId This holds the UID of the parent document or zero if not multi-volumed
41
 * @property-read array $physicalStructure This holds the physical structure
42
 * @property-read array $physicalStructureInfo This holds the physical structure metadata
43
 * @property-read int $pid This holds the PID of the document or zero if not in database
44
 * @property-read bool $ready Is the document instantiated successfully?
45
 * @property-read string $recordId The METS file's / IIIF manifest's record identifier
46
 * @property-read int $rootId This holds the UID of the root document or zero if not multi-volumed
47
 * @property-read array $smLinks This holds the smLinks between logical and physical structMap
48
 * @property-read array $tableOfContents This holds the logical structure
49
 * @property-read string $thumbnail This holds the document's thumbnail location
50
 * @property-read string $toplevelId This holds the toplevel structure's @ID (METS) or the manifest's @id (IIIF)
51
 * @property-read string $parentHref URL of the parent document (determined via mptr element), or empty string if none is available
52
 */
53
final class MetsDocument extends Doc
54
{
55
    /**
56
     * Subsections / tags that may occur within `<mets:amdSec>`.
57
     *
58
     * @link https://www.loc.gov/standards/mets/docs/mets.v1-9.html#amdSec
59
     * @link https://www.loc.gov/standards/mets/docs/mets.v1-9.html#mdSecType
60
     *
61
     * @var string[]
62
     */
63
    protected const ALLOWED_AMD_SEC = ['techMD', 'rightsMD', 'sourceMD', 'digiprovMD'];
64
65
    /**
66
     * This holds the whole XML file as string for serialization purposes
67
     * @see __sleep() / __wakeup()
68
     *
69
     * @var string
70
     * @access protected
71
     */
72
    protected $asXML = '';
73
74
    /**
75
     * This maps the ID of each amdSec to the IDs of its children (techMD etc.).
76
     * When an ADMID references an amdSec instead of techMD etc., this is used to iterate the child elements.
77
     *
78
     * @var string[]
79
     * @access protected
80
     */
81
    protected $amdSecChildIds = [];
82
83
    /**
84
     * Associative array of METS metadata sections indexed by their IDs.
85
     *
86
     * @var array
87
     * @access protected
88
     */
89
    protected $mdSec = [];
90
91
    /**
92
     * Are the METS file's metadata sections loaded?
93
     * @see MetsDocument::$mdSec
94
     *
95
     * @var bool
96
     * @access protected
97
     */
98
    protected $mdSecLoaded = false;
99
100
    /**
101
     * Subset of $mdSec storing only the dmdSec entries; kept for compatibility.
102
     *
103
     * @var array
104
     * @access protected
105
     */
106
    protected $dmdSec = [];
107
108
    /**
109
     * The extension key
110
     *
111
     * @var	string
112
     * @access public
113
     */
114
    public static $extKey = 'dlf';
115
116
    /**
117
     * This holds the file ID -> USE concordance
118
     * @see _getFileGrps()
119
     *
120
     * @var array
121
     * @access protected
122
     */
123
    protected $fileGrps = [];
124
125
    /**
126
     * Are the image file groups loaded?
127
     * @see $fileGrps
128
     *
129
     * @var bool
130
     * @access protected
131
     */
132
    protected $fileGrpsLoaded = false;
133
134
    /**
135
     * Additional information about files (e.g., ADMID), indexed by ID.
136
     * TODO: Consider using this for `getFileMimeType()` and `getFileLocation()`.
137
     * @see _getFileInfos()
138
     *
139
     * @var array
140
     * @access protected
141
     */
142
    protected $fileInfos = [];
143
144
    /**
145
     * This holds the XML file's METS part as \SimpleXMLElement object
146
     *
147
     * @var \SimpleXMLElement
148
     * @access protected
149
     */
150
    protected $mets;
151
152
    /**
153
     * This holds the whole XML file as \SimpleXMLElement object
154
     *
155
     * @var \SimpleXMLElement
156
     * @access protected
157
     */
158
    protected $xml;
159
160
    /**
161
     * URL of the parent document (determined via mptr element),
162
     * or empty string if none is available
163
     *
164
     * @var string|null
165
     * @access protected
166
     */
167
    protected $parentHref;
168
169
    /**
170
     * This adds metadata from METS structural map to metadata array.
171
     *
172
     * @access	public
173
     *
174
     * @param	array	&$metadata: The metadata array to extend
175
     * @param	string	$id: The "@ID" attribute of the logical structure node
176
     *
177
     * @return  void
178
     */
179
    public function addMetadataFromMets(&$metadata, $id)
180
    {
181
        $details = $this->getLogicalStructure($id);
182
        if (!empty($details)) {
183
            $metadata['mets_order'][0] = $details['order'];
184
            $metadata['mets_label'][0] = $details['label'];
185
            $metadata['mets_orderlabel'][0] = $details['orderlabel'];
186
        }
187
    }
188
189
    /**
190
     *
191
     * {@inheritDoc}
192
     * @see \Kitodo\Dlf\Common\Doc::establishRecordId()
193
     */
194
    protected function establishRecordId($pid)
195
    {
196
        // Check for METS object @ID.
197
        if (!empty($this->mets['OBJID'])) {
198
            $this->recordId = (string) $this->mets['OBJID'];
199
        }
200
        // Get hook objects.
201
        $hookObjects = Helper::getHookObjects('Classes/Common/MetsDocument.php');
202
        // Apply hooks.
203
        foreach ($hookObjects as $hookObj) {
204
            if (method_exists($hookObj, 'construct_postProcessRecordId')) {
205
                $hookObj->construct_postProcessRecordId($this->xml, $this->recordId);
206
            }
207
        }
208
    }
209
210
    /**
211
     *
212
     * {@inheritDoc}
213
     * @see \Kitodo\Dlf\Common\Doc::getDownloadLocation()
214
     */
215
    public function getDownloadLocation($id)
216
    {
217
        $fileMimeType = $this->getFileMimeType($id);
218
        $fileLocation = $this->getFileLocation($id);
219
        if ($fileMimeType === 'application/vnd.kitodo.iiif') {
220
            $fileLocation = (strrpos($fileLocation, 'info.json') === strlen($fileLocation) - 9) ? $fileLocation : (strrpos($fileLocation, '/') === strlen($fileLocation) ? $fileLocation . 'info.json' : $fileLocation . '/info.json');
221
            $conf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey);
222
            IiifHelper::setUrlReader(IiifUrlReader::getInstance());
223
            IiifHelper::setMaxThumbnailHeight($conf['iiifThumbnailHeight']);
224
            IiifHelper::setMaxThumbnailWidth($conf['iiifThumbnailWidth']);
225
            $service = IiifHelper::loadIiifResource($fileLocation);
226
            if ($service !== null && $service instanceof AbstractImageService) {
227
                return $service->getImageUrl();
228
            }
229
        } elseif ($fileMimeType === 'application/vnd.netfpx') {
230
            $baseURL = $fileLocation . (strpos($fileLocation, '?') === false ? '?' : '');
231
            // TODO CVT is an optional IIP server capability; in theory, capabilities should be determined in the object request with '&obj=IIP-server'
232
            return $baseURL . '&CVT=jpeg';
233
        }
234
        return $fileLocation;
235
    }
236
237
    /**
238
     * {@inheritDoc}
239
     * @see \Kitodo\Dlf\Common\Doc::getFileLocation()
240
     */
241
    public function getFileLocation($id)
242
    {
243
        $location = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file[@ID="' . $id . '"]/mets:FLocat[@LOCTYPE="URL"]');
244
        if (
245
            !empty($id)
246
            && !empty($location)
247
        ) {
248
            return (string) $location[0]->attributes('http://www.w3.org/1999/xlink')->href;
249
        } else {
250
            $this->logger->warning('There is no file node with @ID "' . $id . '"');
251
            return '';
252
        }
253
    }
254
255
    /**
256
     * {@inheritDoc}
257
     * @see \Kitodo\Dlf\Common\Doc::getFileMimeType()
258
     */
259
    public function getFileMimeType($id)
260
    {
261
        $mimetype = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file[@ID="' . $id . '"]/@MIMETYPE');
262
        if (
263
            !empty($id)
264
            && !empty($mimetype)
265
        ) {
266
            return (string) $mimetype[0];
267
        } else {
268
            $this->logger->warning('There is no file node with @ID "' . $id . '" or no MIME type specified');
269
            return '';
270
        }
271
    }
272
273
    /**
274
     * {@inheritDoc}
275
     * @see \Kitodo\Dlf\Common\Doc::getAllFiles()
276
     */
277
    public function getAllFiles()
278
    {
279
        $files = [];
280
        $fileNodes = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file');
281
        foreach ($fileNodes as $fileNode) {
282
            $fileId = (string) $fileNode->attributes()->ID;
283
            if (empty($fileId)) {
284
                continue;
285
            }
286
287
            $url = null;
288
            foreach ($fileNode->children('http://www.loc.gov/METS/')->FLocat as $locator) {
289
                if ((string) $locator->attributes()['LOCTYPE'] === 'URL') {
0 ignored issues
show
Bug introduced by
The method attributes() does not exist on null. ( Ignorable by Annotation )

If this is a false-positive, you can also ignore this issue in your code via the ignore-call  annotation

289
                if ((string) $locator->/** @scrutinizer ignore-call */ attributes()['LOCTYPE'] === 'URL') {

This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.

This is most likely a typographical error or the method has been renamed.

Loading history...
290
                    $url = (string) $locator->attributes('http://www.w3.org/1999/xlink')->href;
291
                    break;
292
                }
293
            }
294
295
            if ($url === null) {
296
                continue;
297
            }
298
299
            $mimetype = (string) $fileNode->attributes()['MIMETYPE'];
300
            if (empty($mimetype)) {
301
                continue;
302
            }
303
304
            $files[$fileId] = [
305
                'url' => $url,
306
                'mimetype' => $mimetype,
307
            ];
308
309
        }
310
        return $files;
311
    }
312
313
    /**
314
     * {@inheritDoc}
315
     * @see \Kitodo\Dlf\Common\Doc::getLogicalStructure()
316
     */
317
    public function getLogicalStructure($id, $recursive = false)
318
    {
319
        $details = [];
320
        // Is the requested logical unit already loaded?
321
        if (
322
            !$recursive
323
            && !empty($this->logicalUnits[$id])
324
        ) {
325
            // Yes. Return it.
326
            return $this->logicalUnits[$id];
327
        } elseif (!empty($id)) {
328
            // Get specified logical unit.
329
            $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]');
330
        } else {
331
            // Get all logical units at top level.
332
            $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]/mets:div');
333
        }
334
        if (!empty($divs)) {
335
            if (!$recursive) {
336
                // Get the details for the first xpath hit.
337
                $details = $this->getLogicalStructureInfo($divs[0]);
338
            } else {
339
                // Walk the logical structure recursively and fill the whole table of contents.
340
                foreach ($divs as $div) {
341
                    $this->tableOfContents[] = $this->getLogicalStructureInfo($div, $recursive);
342
                }
343
            }
344
        }
345
        return $details;
346
    }
347
348
    /**
349
     * This gets details about a logical structure element
350
     *
351
     * @access protected
352
     *
353
     * @param \SimpleXMLElement $structure: The logical structure node
354
     * @param bool $recursive: Whether to include the child elements
355
     *
356
     * @return array Array of the element's id, label, type and physical page indexes/mptr link
357
     */
358
    protected function getLogicalStructureInfo(\SimpleXMLElement $structure, $recursive = false)
359
    {
360
        // Get attributes.
361
        foreach ($structure->attributes() as $attribute => $value) {
362
            $attributes[$attribute] = (string) $value;
363
        }
364
        // Load plugin configuration.
365
        $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey);
366
        // Extract identity information.
367
        $details = [];
368
        $details['id'] = $attributes['ID'];
369
        $details['dmdId'] = (isset($attributes['DMDID']) ? $attributes['DMDID'] : '');
370
        $details['admId'] = (isset($attributes['ADMID']) ? $attributes['ADMID'] : '');
371
        $details['order'] = (isset($attributes['ORDER']) ? $attributes['ORDER'] : '');
372
        $details['label'] = (isset($attributes['LABEL']) ? $attributes['LABEL'] : '');
373
        $details['orderlabel'] = (isset($attributes['ORDERLABEL']) ? $attributes['ORDERLABEL'] : '');
374
        $details['contentIds'] = (isset($attributes['CONTENTIDS']) ? $attributes['CONTENTIDS'] : '');
375
        $details['volume'] = '';
376
        // Set volume information only if no label is set and this is the toplevel structure element.
377
        if (
378
            empty($details['label'])
379
            && $details['id'] == $this->_getToplevelId()
380
        ) {
381
            $metadata = $this->getMetadata($details['id']);
382
            if (!empty($metadata['volume'][0])) {
383
                $details['volume'] = $metadata['volume'][0];
384
            }
385
        }
386
        $details['pagination'] = '';
387
        $details['type'] = $attributes['TYPE'];
388
        // add description for 3D objects
389
        if ($details['type'] == 'object') {
390
            $metadata = $this->getMetadata($details['id']);
391
            $details['description'] = $metadata['description'][0] ?? '';
392
        }
393
        $details['thumbnailId'] = '';
394
        // Structure depth is determined and cached on demand
395
        $details['structureDepth'] = null;
396
        // Load smLinks.
397
        $this->_getSmLinks();
398
        // Load physical structure.
399
        $this->_getPhysicalStructure();
400
        // Get the physical page or external file this structure element is pointing at.
401
        $details['points'] = '';
402
        // Is there a mptr node?
403
        if (count($structure->children('http://www.loc.gov/METS/')->mptr)) {
404
            // Yes. Get the file reference.
405
            $details['points'] = (string) $structure->children('http://www.loc.gov/METS/')->mptr[0]->attributes('http://www.w3.org/1999/xlink')->href;
406
        } elseif (
407
            !empty($this->physicalStructure)
408
            && array_key_exists($details['id'], $this->smLinks['l2p'])
409
        ) {
410
            // Link logical structure to the first corresponding physical page/track.
411
            $details['points'] = max(intval(array_search($this->smLinks['l2p'][$details['id']][0], $this->physicalStructure, true)), 1);
412
            $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']);
413
            while ($fileGrpThumb = array_shift($fileGrpsThumb)) {
414
                if (!empty($this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['files'][$fileGrpThumb])) {
415
                    $details['thumbnailId'] = $this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['files'][$fileGrpThumb];
416
                    break;
417
                }
418
            }
419
            // Get page/track number of the first page/track related to this structure element.
420
            $details['pagination'] = $this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['orderlabel'];
421
        } elseif ($details['id'] == $this->_getToplevelId()) {
422
            // Point to self if this is the toplevel structure.
423
            $details['points'] = 1;
424
            $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']);
425
            while ($fileGrpThumb = array_shift($fileGrpsThumb)) {
426
                if (
427
                    !empty($this->physicalStructure)
428
                    && !empty($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb])
429
                ) {
430
                    $details['thumbnailId'] = $this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb];
431
                    break;
432
                }
433
            }
434
        }
435
        // Get the files this structure element is pointing at.
436
        $details['files'] = [];
437
        $fileUse = $this->_getFileGrps();
438
        // Get the file representations from fileSec node.
439
        foreach ($structure->children('http://www.loc.gov/METS/')->fptr as $fptr) {
440
            // Check if file has valid @USE attribute.
441
            if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) {
0 ignored issues
show
Bug introduced by
The method attributes() does not exist on null. ( Ignorable by Annotation )

If this is a false-positive, you can also ignore this issue in your code via the ignore-call  annotation

441
            if (!empty($fileUse[(string) $fptr->/** @scrutinizer ignore-call */ attributes()->FILEID])) {

This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.

This is most likely a typographical error or the method has been renamed.

Loading history...
442
                $details['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID;
443
            }
444
        }
445
        // Keep for later usage.
446
        $this->logicalUnits[$details['id']] = $details;
447
        // Walk the structure recursively? And are there any children of the current element?
448
        if (
449
            $recursive
450
            && count($structure->children('http://www.loc.gov/METS/')->div)
451
        ) {
452
            $details['children'] = [];
453
            foreach ($structure->children('http://www.loc.gov/METS/')->div as $child) {
454
                // Repeat for all children.
455
                $details['children'][] = $this->getLogicalStructureInfo($child, true);
0 ignored issues
show
Bug introduced by
It seems like $child can also be of type null; however, parameter $structure of Kitodo\Dlf\Common\MetsDo...tLogicalStructureInfo() does only seem to accept SimpleXMLElement, maybe add an additional type check? ( Ignorable by Annotation )

If this is a false-positive, you can also ignore this issue in your code via the ignore-type  annotation

455
                $details['children'][] = $this->getLogicalStructureInfo(/** @scrutinizer ignore-type */ $child, true);
Loading history...
456
            }
457
        }
458
        return $details;
459
    }
460
461
    /**
462
     * {@inheritDoc}
463
     * @see \Kitodo\Dlf\Common\Doc::getMetadata()
464
     */
465
    public function getMetadata($id, $cPid = 0)
466
    {
467
        // Make sure $cPid is a non-negative integer.
468
        $cPid = max(intval($cPid), 0);
469
        // If $cPid is not given, try to get it elsewhere.
470
        if (
471
            !$cPid
472
            && ($this->cPid || $this->pid)
473
        ) {
474
            // Retain current PID.
475
            $cPid = ($this->cPid ? $this->cPid : $this->pid);
476
        } elseif (!$cPid) {
477
            $this->logger->warning('Invalid PID ' . $cPid . ' for metadata definitions');
478
            return [];
479
        }
480
        // Get metadata from parsed metadata array if available.
481
        if (
482
            !empty($this->metadataArray[$id])
483
            && $this->metadataArray[0] == $cPid
484
        ) {
485
            return $this->metadataArray[$id];
486
        }
487
        // Initialize metadata array with empty values.
488
        $metadata = [
489
            'title' => [],
490
            'title_sorting' => [],
491
            'description' => [],
492
            'author' => [],
493
            'holder' => [],
494
            'place' => [],
495
            'year' => [],
496
            'prod_id' => [],
497
            'record_id' => [],
498
            'opac_id' => [],
499
            'union_id' => [],
500
            'urn' => [],
501
            'purl' => [],
502
            'type' => [],
503
            'volume' => [],
504
            'volume_sorting' => [],
505
            'date' => [],
506
            'license' => [],
507
            'terms' => [],
508
            'restrictions' => [],
509
            'out_of_print' => [],
510
            'rights_info' => [],
511
            'collection' => [],
512
            'owner' => [],
513
            'mets_label' => [],
514
            'mets_orderlabel' => [],
515
            'document_format' => ['METS'],
516
        ];
517
        $mdIds = $this->getMetadataIds($id);
0 ignored issues
show
Bug introduced by
Are you sure the assignment to $mdIds is correct as $this->getMetadataIds($id) targeting Kitodo\Dlf\Common\MetsDocument::getMetadataIds() seems to always return null.

This check looks for function or method calls that always return null and whose return value is assigned to a variable.

class A
{
    function getObject()
    {
        return null;
    }

}

$a = new A();
$object = $a->getObject();

The method getObject() can return nothing but null, so it makes no sense to assign that value to a variable.

The reason is most likely that a function or method is imcomplete or has been reduced for debug purposes.

Loading history...
518
        if (empty($mdIds)) {
519
            // There is no metadata section for this structure node.
520
            return [];
521
        }
522
        // Associative array used as set of available section types (dmdSec, techMD, ...)
523
        $hasMetadataSection = [];
524
        // Load available metadata formats and metadata sections.
525
        $this->loadFormats();
526
        $this->_getMdSec();
527
        // Get the structure's type.
528
        if (!empty($this->logicalUnits[$id])) {
529
            $metadata['type'] = [$this->logicalUnits[$id]['type']];
530
        } else {
531
            $struct = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]/@TYPE');
532
            if (!empty($struct)) {
533
                $metadata['type'] = [(string) $struct[0]];
534
            }
535
        }
536
        foreach ($mdIds as $dmdId) {
0 ignored issues
show
Bug introduced by
The expression $mdIds of type void is not traversable.
Loading history...
537
            $mdSectionType = $this->mdSec[$dmdId]['section'];
538
539
            // To preserve behavior of previous Kitodo versions, extract metadata only from first supported dmdSec
540
            // However, we want to extract, for example, all techMD sections (VIDEOMD, AUDIOMD)
541
            if ($mdSectionType === 'dmdSec' && isset($hasMetadataSection['dmdSec'])) {
542
                continue;
543
            }
544
545
            // Is this metadata format supported?
546
            if (!empty($this->formats[$this->mdSec[$dmdId]['type']])) {
547
                if (!empty($this->formats[$this->mdSec[$dmdId]['type']]['class'])) {
548
                    $class = $this->formats[$this->mdSec[$dmdId]['type']]['class'];
549
                    // Get the metadata from class.
550
                    if (
551
                        class_exists($class)
552
                        && ($obj = GeneralUtility::makeInstance($class)) instanceof MetadataInterface
553
                    ) {
554
                        $obj->extractMetadata($this->mdSec[$dmdId]['xml'], $metadata);
555
                    } else {
556
                        $this->logger->warning('Invalid class/method "' . $class . '->extractMetadata()" for metadata format "' . $this->mdSec[$dmdId]['type'] . '"');
557
                    }
558
                }
559
            } else {
560
                $this->logger->notice('Unsupported metadata format "' . $this->mdSec[$dmdId]['type'] . '" in ' . $mdSectionType . ' with @ID "' . $dmdId . '"');
561
                // Continue searching for supported metadata with next @DMDID.
562
                continue;
563
            }
564
            // Get the additional metadata from database.
565
            $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class)
566
                ->getQueryBuilderForTable('tx_dlf_metadata');
567
            // Get hidden records, too.
568
            $queryBuilder
569
                ->getRestrictions()
570
                ->removeByType(HiddenRestriction::class);
571
            // Get all metadata with configured xpath and applicable format first.
572
            $resultWithFormat = $queryBuilder
573
                ->select(
574
                    'tx_dlf_metadata.index_name AS index_name',
575
                    'tx_dlf_metadataformat_joins.xpath AS xpath',
576
                    'tx_dlf_metadataformat_joins.xpath_sorting AS xpath_sorting',
577
                    'tx_dlf_metadata.is_sortable AS is_sortable',
578
                    'tx_dlf_metadata.default_value AS default_value',
579
                    'tx_dlf_metadata.format AS format'
580
                )
581
                ->from('tx_dlf_metadata')
582
                ->innerJoin(
583
                    'tx_dlf_metadata',
584
                    'tx_dlf_metadataformat',
585
                    'tx_dlf_metadataformat_joins',
586
                    $queryBuilder->expr()->eq(
587
                        'tx_dlf_metadataformat_joins.parent_id',
588
                        'tx_dlf_metadata.uid'
589
                    )
590
                )
591
                ->innerJoin(
592
                    'tx_dlf_metadataformat_joins',
593
                    'tx_dlf_formats',
594
                    'tx_dlf_formats_joins',
595
                    $queryBuilder->expr()->eq(
596
                        'tx_dlf_formats_joins.uid',
597
                        'tx_dlf_metadataformat_joins.encoded'
598
                    )
599
                )
600
                ->where(
601
                    $queryBuilder->expr()->eq('tx_dlf_metadata.pid', intval($cPid)),
602
                    $queryBuilder->expr()->eq('tx_dlf_metadata.l18n_parent', 0),
603
                    $queryBuilder->expr()->eq('tx_dlf_metadataformat_joins.pid', intval($cPid)),
604
                    $queryBuilder->expr()->eq('tx_dlf_formats_joins.type', $queryBuilder->createNamedParameter($this->mdSec[$dmdId]['type']))
605
                )
606
                ->execute();
607
            // Get all metadata without a format, but with a default value next.
608
            $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class)
609
                ->getQueryBuilderForTable('tx_dlf_metadata');
610
            // Get hidden records, too.
611
            $queryBuilder
612
                ->getRestrictions()
613
                ->removeByType(HiddenRestriction::class);
614
            $resultWithoutFormat = $queryBuilder
615
                ->select(
616
                    'tx_dlf_metadata.index_name AS index_name',
617
                    'tx_dlf_metadata.is_sortable AS is_sortable',
618
                    'tx_dlf_metadata.default_value AS default_value',
619
                    'tx_dlf_metadata.format AS format'
620
                )
621
                ->from('tx_dlf_metadata')
622
                ->where(
623
                    $queryBuilder->expr()->eq('tx_dlf_metadata.pid', intval($cPid)),
624
                    $queryBuilder->expr()->eq('tx_dlf_metadata.l18n_parent', 0),
625
                    $queryBuilder->expr()->eq('tx_dlf_metadata.format', 0),
626
                    $queryBuilder->expr()->neq('tx_dlf_metadata.default_value', $queryBuilder->createNamedParameter(''))
627
                )
628
                ->execute();
629
            // Merge both result sets.
630
            $allResults = array_merge($resultWithFormat->fetchAll(), $resultWithoutFormat->fetchAll());
631
            // We need a \DOMDocument here, because SimpleXML doesn't support XPath functions properly.
632
            $domNode = dom_import_simplexml($this->mdSec[$dmdId]['xml']);
633
            $domXPath = new \DOMXPath($domNode->ownerDocument);
0 ignored issues
show
Bug introduced by
It seems like $domNode->ownerDocument can also be of type null; however, parameter $document of DOMXPath::__construct() does only seem to accept DOMDocument, maybe add an additional type check? ( Ignorable by Annotation )

If this is a false-positive, you can also ignore this issue in your code via the ignore-type  annotation

633
            $domXPath = new \DOMXPath(/** @scrutinizer ignore-type */ $domNode->ownerDocument);
Loading history...
634
            $this->registerNamespaces($domXPath);
635
            // OK, now make the XPath queries.
636
            foreach ($allResults as $resArray) {
637
                // Set metadata field's value(s).
638
                if (
639
                    $resArray['format'] > 0
640
                    && !empty($resArray['xpath'])
641
                    && ($values = $domXPath->evaluate($resArray['xpath'], $domNode))
642
                ) {
643
                    if (
644
                        $values instanceof \DOMNodeList
645
                        && $values->length > 0
646
                    ) {
647
                        $metadata[$resArray['index_name']] = [];
648
                        foreach ($values as $value) {
649
                            $metadata[$resArray['index_name']][] = trim((string) $value->nodeValue);
650
                        }
651
                    } elseif (!($values instanceof \DOMNodeList)) {
652
                        $metadata[$resArray['index_name']] = [trim((string) $values)];
653
                    }
654
                }
655
                // Set default value if applicable.
656
                if (
657
                    empty($metadata[$resArray['index_name']][0])
658
                    && strlen($resArray['default_value']) > 0
659
                ) {
660
                    $metadata[$resArray['index_name']] = [$resArray['default_value']];
661
                }
662
                // Set sorting value if applicable.
663
                if (
664
                    !empty($metadata[$resArray['index_name']])
665
                    && $resArray['is_sortable']
666
                ) {
667
                    if (
668
                        $resArray['format'] > 0
669
                        && !empty($resArray['xpath_sorting'])
670
                        && ($values = $domXPath->evaluate($resArray['xpath_sorting'], $domNode))
671
                    ) {
672
                        if (
673
                            $values instanceof \DOMNodeList
674
                            && $values->length > 0
675
                        ) {
676
                            $metadata[$resArray['index_name'] . '_sorting'][0] = trim((string) $values->item(0)->nodeValue);
677
                        } elseif (!($values instanceof \DOMNodeList)) {
678
                            $metadata[$resArray['index_name'] . '_sorting'][0] = trim((string) $values);
679
                        }
680
                    }
681
                    if (empty($metadata[$resArray['index_name'] . '_sorting'][0])) {
682
                        $metadata[$resArray['index_name'] . '_sorting'][0] = $metadata[$resArray['index_name']][0];
683
                    }
684
                }
685
            }
686
687
            $hasMetadataSection[$mdSectionType] = true;
688
        }
689
        // Set title to empty string if not present.
690
        if (empty($metadata['title'][0])) {
691
            $metadata['title'][0] = '';
692
            $metadata['title_sorting'][0] = '';
693
        }
694
        // Set title_sorting to title as default.
695
        if (empty($metadata['title_sorting'][0])) {
696
            $metadata['title_sorting'][0] = $metadata['title'][0];
697
        }
698
        // Set date to empty string if not present.
699
        if (empty($metadata['date'][0])) {
700
            $metadata['date'][0] = '';
701
        }
702
        // Files are not expected to reference a dmdSec
703
        if (isset($this->fileInfos[$id]) || isset($hasMetadataSection['dmdSec'])) {
704
            return $metadata;
705
        } else {
706
            $this->logger->warning('No supported descriptive metadata found for logical structure with @ID "' . $id . '"');
707
            return [];
708
        }
709
    }
710
711
    /**
712
     * Get IDs of (descriptive and administrative) metadata sections
713
     * referenced by node of given $id. The $id may refer to either
714
     * a logical structure node or to a file.
715
     *
716
     * @access protected
717
     * @param string $id: The "@ID" attribute of the file node
718
     * @return void
719
     */
720
    protected function getMetadataIds($id)
721
    {
722
        // Load amdSecChildIds concordance
723
        $this->_getMdSec();
724
        $this->_getFileInfos();
725
726
        // Get DMDID and ADMID of logical structure node
727
        if (!empty($this->logicalUnits[$id])) {
728
            $dmdIds = $this->logicalUnits[$id]['dmdId'] ?? '';
729
            $admIds = $this->logicalUnits[$id]['admId'] ?? '';
730
        } else {
731
            $mdSec = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]')[0];
732
            if ($mdSec) {
0 ignored issues
show
introduced by
$mdSec is of type SimpleXMLElement, thus it always evaluated to true.
Loading history...
733
                $dmdIds = (string) $mdSec->attributes()->DMDID;
734
                $admIds = (string) $mdSec->attributes()->ADMID;
735
            } else if (isset($this->fileInfos[$id])) {
736
                $dmdIds = $this->fileInfos[$id]['dmdId'];
737
                $admIds = $this->fileInfos[$id]['admId'];
738
            } else {
739
                $dmdIds = '';
740
                $admIds = '';
741
            }
742
        }
743
744
        // Handle multiple DMDIDs/ADMIDs
745
        $allMdIds = explode(' ', $dmdIds);
746
747
        foreach (explode(' ', $admIds) as $admId) {
748
            if (isset($this->mdSec[$admId])) {
749
                // $admId references an actual metadata section such as techMD
750
                $allMdIds[] = $admId;
751
            } elseif (isset($this->amdSecChildIds[$admId])) {
752
                // $admId references a <mets:amdSec> element. Resolve child elements.
753
                foreach ($this->amdSecChildIds[$admId] as $childId) {
0 ignored issues
show
Bug introduced by
The expression $this->amdSecChildIds[$admId] of type string is not traversable.
Loading history...
754
                    $allMdIds[] = $childId;
755
                }
756
            }
757
        }
758
759
        return array_filter($allMdIds, function ($element) {
0 ignored issues
show
Bug Best Practice introduced by
The expression return array_filter($all...ion(...) { /* ... */ }) returns the type array which is incompatible with the documented return type void.
Loading history...
760
            return !empty($element);
761
        });
762
    }
763
764
    /**
765
     * {@inheritDoc}
766
     * @see \Kitodo\Dlf\Common\Doc::getFullText()
767
     */
768
    public function getFullText($id)
769
    {
770
        $fullText = '';
771
772
        // Load fileGrps and check for full text files.
773
        $this->_getFileGrps();
774
        if ($this->hasFulltext) {
775
            $fullText = $this->getFullTextFromXml($id);
776
        }
777
        return $fullText;
778
    }
779
780
    /**
781
     * {@inheritDoc}
782
     * @see Doc::getStructureDepth()
783
     */
784
    public function getStructureDepth($logId)
785
    {
786
        if (isset($this->logicalUnits[$logId]['structureDepth'])) {
787
            return $this->logicalUnits[$logId]['structureDepth'];
788
        }
789
790
        $ancestors = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $logId . '"]/ancestor::*');
791
        if (!empty($ancestors)) {
792
            $structureDepth = count($ancestors);
793
        } else {
794
            $structureDepth = 0;
795
        }
796
797
        // NOTE: Don't just set $this->logicalUnits[$logId] here, because it may not yet be loaded
798
        if (isset($this->logicalUnits[$logId])) {
799
            $this->logicalUnits[$logId]['structureDepth'] = $structureDepth;
800
        }
801
802
        return $structureDepth;
803
    }
804
805
    /**
806
     * {@inheritDoc}
807
     * @see \Kitodo\Dlf\Common\Doc::init()
808
     */
809
    protected function init($location)
810
    {
811
        $this->logger = GeneralUtility::makeInstance(LogManager::class)->getLogger(get_class($this));
812
        // Get METS node from XML file.
813
        $this->registerNamespaces($this->xml);
814
        $mets = $this->xml->xpath('//mets:mets');
815
        if (!empty($mets)) {
816
            $this->mets = $mets[0];
817
            // Register namespaces.
818
            $this->registerNamespaces($this->mets);
819
        } else {
820
            if (!empty($location)) {
821
                $this->logger->error('No METS part found in document with location "' . $location . '".');
822
            } else if (!empty($this->recordId)) {
823
                $this->logger->error('No METS part found in document with recordId "' . $this->recordId . '".');
824
            } else {
825
                $this->logger->error('No METS part found in current document.');
826
            }
827
        }
828
    }
829
830
    /**
831
     * {@inheritDoc}
832
     * @see \Kitodo\Dlf\Common\Doc::loadLocation()
833
     */
834
    protected function loadLocation($location)
835
    {
836
        $fileResource = Helper::getUrl($location);
837
        if ($fileResource !== false) {
838
            $xml = Helper::getXmlFileAsString($fileResource);
839
            // Set some basic properties.
840
            if ($xml !== false) {
841
                $this->xml = $xml;
842
                return true;
843
            }
844
        }
845
        $this->logger->error('Could not load XML file from "' . $location . '"');
846
        return false;
847
    }
848
849
    /**
850
     * {@inheritDoc}
851
     * @see \Kitodo\Dlf\Common\Doc::ensureHasFulltextIsSet()
852
     */
853
    protected function ensureHasFulltextIsSet()
854
    {
855
        // Are the fileGrps already loaded?
856
        if (!$this->fileGrpsLoaded) {
857
            $this->_getFileGrps();
858
        }
859
    }
860
861
    /**
862
     * {@inheritDoc}
863
     * @see Doc::setPreloadedDocument()
864
     */
865
    protected function setPreloadedDocument($preloadedDocument)
866
    {
867
868
        if ($preloadedDocument instanceof \SimpleXMLElement) {
869
            $this->xml = $preloadedDocument;
870
            return true;
871
        }
872
        return false;
873
    }
874
875
    /**
876
     * {@inheritDoc}
877
     * @see Doc::getDocument()
878
     */
879
    protected function getDocument()
880
    {
881
        return $this->mets;
882
    }
883
884
    /**
885
     * This builds an array of the document's metadata sections
886
     *
887
     * @access protected
888
     *
889
     * @return array Array of metadata sections with their IDs as array key
890
     */
891
    protected function _getMdSec()
892
    {
893
        if (!$this->mdSecLoaded) {
894
            $this->loadFormats();
895
896
            foreach ($this->mets->xpath('./mets:dmdSec') as $dmdSecTag) {
897
                $dmdSec = $this->processMdSec($dmdSecTag);
898
899
                if ($dmdSec !== null) {
900
                    $this->mdSec[$dmdSec['id']] = $dmdSec;
0 ignored issues
show
Bug introduced by
The property mdSec is declared read-only in Kitodo\Dlf\Common\MetsDocument.
Loading history...
901
                    $this->dmdSec[$dmdSec['id']] = $dmdSec;
902
                }
903
            }
904
905
            foreach ($this->mets->xpath('./mets:amdSec') as $amdSecTag) {
906
                $childIds = [];
907
908
                foreach ($amdSecTag->children('http://www.loc.gov/METS/') as $mdSecTag) {
909
                    if (!in_array($mdSecTag->getName(), self::ALLOWED_AMD_SEC)) {
910
                        continue;
911
                    }
912
913
                    // TODO: Should we check that the format may occur within this type (e.g., to ignore VIDEOMD within rightsMD)?
914
                    $mdSec = $this->processMdSec($mdSecTag);
915
916
                    if ($mdSec !== null) {
917
                        $this->mdSec[$mdSec['id']] = $mdSec;
918
919
                        $childIds[] = $mdSec['id'];
920
                    }
921
                }
922
923
                $amdSecId = (string) $amdSecTag->attributes()->ID;
924
                if (!empty($amdSecId)) {
925
                    $this->amdSecChildIds[$amdSecId] = $childIds;
926
                }
927
            }
928
929
            $this->mdSecLoaded = true;
930
        }
931
        return $this->mdSec;
932
    }
933
934
    protected function _getDmdSec()
935
    {
936
        $this->_getMdSec();
937
        return $this->dmdSec;
938
    }
939
940
    /**
941
     * Processes an element of METS `mdSecType`.
942
     *
943
     * @access protected
944
     *
945
     * @param \SimpleXMLElement $element
946
     *
947
     * @return array|null The processed metadata section
948
     */
949
    protected function processMdSec($element)
950
    {
951
        $mdId = (string) $element->attributes()->ID;
952
        if (empty($mdId)) {
953
            return null;
954
        }
955
956
        $this->registerNamespaces($element);
957
        if ($type = $element->xpath('./mets:mdWrap[not(@MDTYPE="OTHER")]/@MDTYPE')) {
958
            if (!empty($this->formats[(string) $type[0]])) {
959
                $type = (string) $type[0];
960
                $xml = $element->xpath('./mets:mdWrap[@MDTYPE="' . $type . '"]/mets:xmlData/' . strtolower($type) . ':' . $this->formats[$type]['rootElement']);
961
            }
962
        } elseif ($type = $element->xpath('./mets:mdWrap[@MDTYPE="OTHER"]/@OTHERMDTYPE')) {
963
            if (!empty($this->formats[(string) $type[0]])) {
964
                $type = (string) $type[0];
965
                $xml = $element->xpath('./mets:mdWrap[@MDTYPE="OTHER"][@OTHERMDTYPE="' . $type . '"]/mets:xmlData/' . strtolower($type) . ':' . $this->formats[$type]['rootElement']);
966
            }
967
        }
968
969
        if (empty($xml)) {
970
            return null;
971
        }
972
973
        $this->registerNamespaces($xml[0]);
974
975
        return [
976
            'id' => $mdId,
977
            'section' => $element->getName(),
978
            'type' => $type,
979
            'xml' => $xml[0],
0 ignored issues
show
Comprehensibility Best Practice introduced by
The variable $xml does not seem to be defined for all execution paths leading up to this point.
Loading history...
980
        ];
981
    }
982
983
    /**
984
     * This builds the file ID -> USE concordance
985
     *
986
     * @access protected
987
     *
988
     * @return array Array of file use groups with file IDs
989
     */
990
    protected function _getFileGrps()
991
    {
992
        if (!$this->fileGrpsLoaded) {
993
            // Get configured USE attributes.
994
            $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey);
995
            $useGrps = GeneralUtility::trimExplode(',', $extConf['fileGrpImages']);
996
            if (!empty($extConf['fileGrpThumbs'])) {
997
                $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']));
998
            }
999
            if (!empty($extConf['fileGrpDownload'])) {
1000
                $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpDownload']));
1001
            }
1002
            if (!empty($extConf['fileGrpFulltext'])) {
1003
                $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpFulltext']));
1004
            }
1005
            if (!empty($extConf['fileGrpAudio'])) {
1006
                $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpAudio']));
1007
            }
1008
            // Get all file groups.
1009
            $fileGrps = $this->mets->xpath('./mets:fileSec/mets:fileGrp');
1010
            if (!empty($fileGrps)) {
1011
                // Build concordance for configured USE attributes.
1012
                foreach ($fileGrps as $fileGrp) {
1013
                    if (in_array((string) $fileGrp['USE'], $useGrps)) {
1014
                        foreach ($fileGrp->children('http://www.loc.gov/METS/')->file as $file) {
1015
                            $fileId = (string) $file->attributes()->ID;
0 ignored issues
show
Bug introduced by
The method attributes() does not exist on null. ( Ignorable by Annotation )

If this is a false-positive, you can also ignore this issue in your code via the ignore-call  annotation

1015
                            $fileId = (string) $file->/** @scrutinizer ignore-call */ attributes()->ID;

This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.

This is most likely a typographical error or the method has been renamed.

Loading history...
1016
                            $this->fileGrps[$fileId] = (string) $fileGrp['USE'];
1017
                            $this->fileInfos[$fileId] = [
0 ignored issues
show
Bug introduced by
The property fileInfos is declared read-only in Kitodo\Dlf\Common\MetsDocument.
Loading history...
1018
                                'fileGrp' => (string) $fileGrp['USE'],
1019
                                'admId' => (string) $file->attributes()->ADMID,
1020
                                'dmdId' => (string) $file->attributes()->DMDID,
1021
                            ];
1022
                        }
1023
                    }
1024
                }
1025
            }
1026
            // Are there any fulltext files available?
1027
            if (
1028
                !empty($extConf['fileGrpFulltext'])
1029
                && array_intersect(GeneralUtility::trimExplode(',', $extConf['fileGrpFulltext']), $this->fileGrps) !== []
1030
            ) {
1031
                $this->hasFulltext = true;
1032
            }
1033
            $this->fileGrpsLoaded = true;
1034
        }
1035
        return $this->fileGrps;
1036
    }
1037
1038
    /**
1039
     *
1040
     * @access protected
1041
     * @return array
1042
     */
1043
    protected function _getFileInfos()
1044
    {
1045
        $this->_getFileGrps();
1046
        return $this->fileInfos;
1047
    }
1048
1049
    /**
1050
     * {@inheritDoc}
1051
     * @see \Kitodo\Dlf\Common\Doc::prepareMetadataArray()
1052
     */
1053
    protected function prepareMetadataArray($cPid)
1054
    {
1055
        $ids = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@DMDID]/@ID');
1056
        // Get all logical structure nodes with metadata.
1057
        if (!empty($ids)) {
1058
            foreach ($ids as $id) {
1059
                $this->metadataArray[(string) $id] = $this->getMetadata((string) $id, $cPid);
1060
            }
1061
        }
1062
        // Set current PID for metadata definitions.
1063
    }
1064
1065
    /**
1066
     * This returns $this->mets via __get()
1067
     *
1068
     * @access protected
1069
     *
1070
     * @return \SimpleXMLElement The XML's METS part as \SimpleXMLElement object
1071
     */
1072
    protected function _getMets()
1073
    {
1074
        return $this->mets;
1075
    }
1076
1077
    /**
1078
     * {@inheritDoc}
1079
     * @see \Kitodo\Dlf\Common\Doc::_getPhysicalStructure()
1080
     */
1081
    protected function _getPhysicalStructure()
1082
    {
1083
        // Is there no physical structure array yet?
1084
        if (!$this->physicalStructureLoaded) {
1085
            // Does the document have a structMap node of type "PHYSICAL"?
1086
            $elementNodes = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]/mets:div');
1087
            if (!empty($elementNodes)) {
1088
                // Get file groups.
1089
                $fileUse = $this->_getFileGrps();
1090
                // Get the physical sequence's metadata.
1091
                $physNode = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]');
1092
                $physSeq[0] = (string) $physNode[0]['ID'];
1093
                $this->physicalStructureInfo[$physSeq[0]]['id'] = (string) $physNode[0]['ID'];
1094
                $this->physicalStructureInfo[$physSeq[0]]['dmdId'] = (isset($physNode[0]['DMDID']) ? (string) $physNode[0]['DMDID'] : '');
1095
                $this->physicalStructureInfo[$physSeq[0]]['admId'] = (isset($physNode[0]['ADMID']) ? (string) $physNode[0]['ADMID'] : '');
1096
                $this->physicalStructureInfo[$physSeq[0]]['order'] = (isset($physNode[0]['ORDER']) ? (string) $physNode[0]['ORDER'] : '');
1097
                $this->physicalStructureInfo[$physSeq[0]]['label'] = (isset($physNode[0]['LABEL']) ? (string) $physNode[0]['LABEL'] : '');
1098
                $this->physicalStructureInfo[$physSeq[0]]['orderlabel'] = (isset($physNode[0]['ORDERLABEL']) ? (string) $physNode[0]['ORDERLABEL'] : '');
1099
                $this->physicalStructureInfo[$physSeq[0]]['type'] = (string) $physNode[0]['TYPE'];
1100
                $this->physicalStructureInfo[$physSeq[0]]['contentIds'] = (isset($physNode[0]['CONTENTIDS']) ? (string) $physNode[0]['CONTENTIDS'] : '');
1101
                // Get the file representations from fileSec node.
1102
                foreach ($physNode[0]->children('http://www.loc.gov/METS/')->fptr as $fptr) {
1103
                    // Check if file has valid @USE attribute.
1104
                    if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) {
1105
                        $this->physicalStructureInfo[$physSeq[0]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID;
1106
                    }
1107
                }
1108
                // Build the physical elements' array from the physical structMap node.
1109
                foreach ($elementNodes as $elementNode) {
1110
                    $elements[(int) $elementNode['ORDER']] = (string) $elementNode['ID'];
1111
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['id'] = (string) $elementNode['ID'];
1112
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['dmdId'] = (isset($elementNode['DMDID']) ? (string) $elementNode['DMDID'] : '');
1113
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['admId'] = (isset($elementNode['ADMID']) ? (string) $elementNode['ADMID'] : '');
1114
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['order'] = (isset($elementNode['ORDER']) ? (string) $elementNode['ORDER'] : '');
1115
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['label'] = (isset($elementNode['LABEL']) ? (string) $elementNode['LABEL'] : '');
1116
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['orderlabel'] = (isset($elementNode['ORDERLABEL']) ? (string) $elementNode['ORDERLABEL'] : '');
1117
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['type'] = (string) $elementNode['TYPE'];
1118
                    $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['contentIds'] = (isset($elementNode['CONTENTIDS']) ? (string) $elementNode['CONTENTIDS'] : '');
1119
                    // Get the file representations from fileSec node.
1120
                    foreach ($elementNode->children('http://www.loc.gov/METS/')->fptr as $fptr) {
1121
                        // Check if file has valid @USE attribute.
1122
                        if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) {
1123
                            $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID;
1124
                        }
1125
                    }
1126
                }
1127
                // Sort array by keys (= @ORDER).
1128
                if (ksort($elements)) {
1129
                    // Set total number of pages/tracks.
1130
                    $this->numPages = count($elements);
1131
                    // Merge and re-index the array to get nice numeric indexes.
1132
                    $this->physicalStructure = array_merge($physSeq, $elements);
1133
                }
1134
            }
1135
            $this->physicalStructureLoaded = true;
1136
        }
1137
        return $this->physicalStructure;
1138
    }
1139
1140
    /**
1141
     * {@inheritDoc}
1142
     * @see \Kitodo\Dlf\Common\Doc::_getSmLinks()
1143
     */
1144
    protected function _getSmLinks()
1145
    {
1146
        if (!$this->smLinksLoaded) {
1147
            $smLinks = $this->mets->xpath('./mets:structLink/mets:smLink');
1148
            if (!empty($smLinks)) {
1149
                foreach ($smLinks as $smLink) {
1150
                    $this->smLinks['l2p'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->from][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->to;
1151
                    $this->smLinks['p2l'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->to][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->from;
1152
                }
1153
            }
1154
            $this->smLinksLoaded = true;
1155
        }
1156
        return $this->smLinks;
1157
    }
1158
1159
    /**
1160
     * {@inheritDoc}
1161
     * @see \Kitodo\Dlf\Common\Doc::_getThumbnail()
1162
     */
1163
    protected function _getThumbnail($forceReload = false)
1164
    {
1165
        if (
1166
            !$this->thumbnailLoaded
1167
            || $forceReload
1168
        ) {
1169
            // Retain current PID.
1170
            $cPid = ($this->cPid ? $this->cPid : $this->pid);
1171
            if (!$cPid) {
1172
                $this->logger->error('Invalid PID ' . $cPid . ' for structure definitions');
1173
                $this->thumbnailLoaded = true;
1174
                return $this->thumbnail;
1175
            }
1176
            // Load extension configuration.
1177
            $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey);
1178
            if (empty($extConf['fileGrpThumbs'])) {
1179
                $this->logger->warning('No fileGrp for thumbnails specified');
1180
                $this->thumbnailLoaded = true;
1181
                return $this->thumbnail;
1182
            }
1183
            $strctId = $this->_getToplevelId();
1184
            $metadata = $this->getTitledata($cPid);
1185
1186
            $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class)
1187
                ->getQueryBuilderForTable('tx_dlf_structures');
1188
1189
            // Get structure element to get thumbnail from.
1190
            $result = $queryBuilder
1191
                ->select('tx_dlf_structures.thumbnail AS thumbnail')
1192
                ->from('tx_dlf_structures')
1193
                ->where(
1194
                    $queryBuilder->expr()->eq('tx_dlf_structures.pid', intval($cPid)),
1195
                    $queryBuilder->expr()->eq('tx_dlf_structures.index_name', $queryBuilder->expr()->literal($metadata['type'][0])),
1196
                    Helper::whereExpression('tx_dlf_structures')
1197
                )
1198
                ->setMaxResults(1)
1199
                ->execute();
1200
1201
            $allResults = $result->fetchAll();
1202
1203
            if (count($allResults) == 1) {
1204
                $resArray = $allResults[0];
1205
                // Get desired thumbnail structure if not the toplevel structure itself.
1206
                if (!empty($resArray['thumbnail'])) {
1207
                    $strctType = Helper::getIndexNameFromUid($resArray['thumbnail'], 'tx_dlf_structures', $cPid);
1208
                    // Check if this document has a structure element of the desired type.
1209
                    $strctIds = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@TYPE="' . $strctType . '"]/@ID');
1210
                    if (!empty($strctIds)) {
1211
                        $strctId = (string) $strctIds[0];
1212
                    }
1213
                }
1214
                // Load smLinks.
1215
                $this->_getSmLinks();
1216
                // Get thumbnail location.
1217
                $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']);
1218
                while ($fileGrpThumb = array_shift($fileGrpsThumb)) {
1219
                    if (
1220
                        $this->_getPhysicalStructure()
1221
                        && !empty($this->smLinks['l2p'][$strctId])
1222
                        && !empty($this->physicalStructureInfo[$this->smLinks['l2p'][$strctId][0]]['files'][$fileGrpThumb])
1223
                    ) {
1224
                        $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->smLinks['l2p'][$strctId][0]]['files'][$fileGrpThumb]);
1225
                        break;
1226
                    } elseif (!empty($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb])) {
1227
                        $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb]);
1228
                        break;
1229
                    }
1230
                }
1231
            } else {
1232
                $this->logger->error('No structure of type "' . $metadata['type'][0] . '" found in database');
1233
            }
1234
            $this->thumbnailLoaded = true;
1235
        }
1236
        return $this->thumbnail;
1237
    }
1238
1239
    /**
1240
     * {@inheritDoc}
1241
     * @see \Kitodo\Dlf\Common\Doc::_getToplevelId()
1242
     */
1243
    protected function _getToplevelId()
1244
    {
1245
        if (empty($this->toplevelId)) {
1246
            // Get all logical structure nodes with metadata, but without associated METS-Pointers.
1247
            $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@DMDID and not(./mets:mptr)]');
1248
            if (!empty($divs)) {
1249
                // Load smLinks.
1250
                $this->_getSmLinks();
1251
                foreach ($divs as $div) {
1252
                    $id = (string) $div['ID'];
1253
                    // Are there physical structure nodes for this logical structure?
1254
                    if (array_key_exists($id, $this->smLinks['l2p'])) {
1255
                        // Yes. That's what we're looking for.
1256
                        $this->toplevelId = $id;
1257
                        break;
1258
                    } elseif (empty($this->toplevelId)) {
1259
                        // No. Remember this anyway, but keep looking for a better one.
1260
                        $this->toplevelId = $id;
1261
                    }
1262
                }
1263
            }
1264
        }
1265
        return $this->toplevelId;
1266
    }
1267
1268
    /**
1269
     * Try to determine URL of parent document.
1270
     *
1271
     * @return string|null
1272
     */
1273
    public function _getParentHref()
1274
    {
1275
        if ($this->parentHref === null) {
1276
            $this->parentHref = '';
0 ignored issues
show
Bug introduced by
The property parentHref is declared read-only in Kitodo\Dlf\Common\MetsDocument.
Loading history...
1277
1278
            // Get the closest ancestor of the current document which has a MPTR child.
1279
            $parentMptr = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $this->toplevelId . '"]/ancestor::mets:div[./mets:mptr][1]/mets:mptr');
1280
            if (!empty($parentMptr)) {
1281
                $this->parentHref = (string) $parentMptr[0]->attributes('http://www.w3.org/1999/xlink')->href;
1282
            }
1283
        }
1284
1285
        return $this->parentHref;
1286
    }
1287
1288
    /**
1289
     * This magic method is executed prior to any serialization of the object
1290
     * @see __wakeup()
1291
     *
1292
     * @access public
1293
     *
1294
     * @return array Properties to be serialized
1295
     */
1296
    public function __sleep()
1297
    {
1298
        // \SimpleXMLElement objects can't be serialized, thus save the XML as string for serialization
1299
        $this->asXML = $this->xml->asXML();
0 ignored issues
show
Documentation Bug introduced by
It seems like $this->xml->asXML() can also be of type true. However, the property $asXML is declared as type string. Maybe add an additional type check?

Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a mixed type is assigned to a property that is type hinted more strictly.

For example, imagine you have a variable $accountId that can either hold an Id object or false (if there is no account id yet). Your code now assigns that value to the id property of an instance of the Account class. This class holds a proper account, so the id value must no longer be false.

Either this assignment is in error or a type check should be added for that assignment.

class Id
{
    public $id;

    public function __construct($id)
    {
        $this->id = $id;
    }

}

class Account
{
    /** @var  Id $id */
    public $id;
}

$account_id = false;

if (starsAreRight()) {
    $account_id = new Id(42);
}

$account = new Account();
if ($account instanceof Id)
{
    $account->id = $account_id;
}
Loading history...
1300
        return ['uid', 'pid', 'recordId', 'parentId', 'asXML'];
1301
    }
1302
1303
    /**
1304
     * This magic method is used for setting a string value for the object
1305
     *
1306
     * @access public
1307
     *
1308
     * @return string String representing the METS object
1309
     */
1310
    public function __toString()
1311
    {
1312
        $xml = new \DOMDocument('1.0', 'utf-8');
1313
        $xml->appendChild($xml->importNode(dom_import_simplexml($this->mets), true));
1314
        $xml->formatOutput = true;
1315
        return $xml->saveXML();
1316
    }
1317
1318
    /**
1319
     * This magic method is executed after the object is deserialized
1320
     * @see __sleep()
1321
     *
1322
     * @access public
1323
     *
1324
     * @return void
1325
     */
1326
    public function __wakeup()
1327
    {
1328
        $xml = Helper::getXmlFileAsString($this->asXML);
1329
        if ($xml !== false) {
1330
            $this->asXML = '';
1331
            $this->xml = $xml;
1332
            // Rebuild the unserializable properties.
1333
            $this->init('');
1334
        } else {
1335
            $this->logger = GeneralUtility::makeInstance(LogManager::class)->getLogger(static::class);
1336
            $this->logger->error('Could not load XML after deserialization');
1337
        }
1338
    }
1339
}
1340