We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.
| Total Complexity | 199 |
| Total Lines | 1186 |
| Duplicated Lines | 0 % |
| Changes | 3 | ||
| Bugs | 0 | Features | 0 |
Complex classes like MetsDocument 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 MetsDocument, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 52 | final class MetsDocument extends Doc |
||
| 53 | { |
||
| 54 | /** |
||
| 55 | * Subsections / tags that may occur within `<mets:amdSec>`. |
||
| 56 | * |
||
| 57 | * @link https://www.loc.gov/standards/mets/docs/mets.v1-9.html#amdSec |
||
| 58 | * @link https://www.loc.gov/standards/mets/docs/mets.v1-9.html#mdSecType |
||
| 59 | * |
||
| 60 | * @var string[] |
||
| 61 | */ |
||
| 62 | protected const ALLOWED_AMD_SEC = ['techMD', 'rightsMD', 'sourceMD', 'digiprovMD']; |
||
| 63 | |||
| 64 | /** |
||
| 65 | * This holds the whole XML file as string for serialization purposes |
||
| 66 | * @see __sleep() / __wakeup() |
||
| 67 | * |
||
| 68 | * @var string |
||
| 69 | * @access protected |
||
| 70 | */ |
||
| 71 | protected $asXML = ''; |
||
| 72 | |||
| 73 | /** |
||
| 74 | * This maps the ID of each amdSec to the IDs of its children (techMD etc.). |
||
| 75 | * When an ADMID references an amdSec instead of techMD etc., this is used to iterate the child elements. |
||
| 76 | * |
||
| 77 | * @var string[] |
||
| 78 | * @access protected |
||
| 79 | */ |
||
| 80 | protected $amdSecChildIds = []; |
||
| 81 | |||
| 82 | /** |
||
| 83 | * Associative array of METS metadata sections indexed by their IDs. |
||
| 84 | * |
||
| 85 | * @var array |
||
| 86 | * @access protected |
||
| 87 | */ |
||
| 88 | protected $mdSec = []; |
||
| 89 | |||
| 90 | /** |
||
| 91 | * Are the METS file's metadata sections loaded? |
||
| 92 | * @see MetsDocument::$mdSec |
||
| 93 | * |
||
| 94 | * @var bool |
||
| 95 | * @access protected |
||
| 96 | */ |
||
| 97 | protected $mdSecLoaded = false; |
||
| 98 | |||
| 99 | /** |
||
| 100 | * Subset of $mdSec storing only the dmdSec entries; kept for compatibility. |
||
| 101 | * |
||
| 102 | * @var array |
||
| 103 | * @access protected |
||
| 104 | */ |
||
| 105 | protected $dmdSec = []; |
||
| 106 | |||
| 107 | /** |
||
| 108 | * The extension key |
||
| 109 | * |
||
| 110 | * @var string |
||
| 111 | * @access public |
||
| 112 | */ |
||
| 113 | public static $extKey = 'dlf'; |
||
| 114 | |||
| 115 | /** |
||
| 116 | * This holds the file ID -> USE concordance |
||
| 117 | * @see _getFileGrps() |
||
| 118 | * |
||
| 119 | * @var array |
||
| 120 | * @access protected |
||
| 121 | */ |
||
| 122 | protected $fileGrps = []; |
||
| 123 | |||
| 124 | /** |
||
| 125 | * Are the image file groups loaded? |
||
| 126 | * @see $fileGrps |
||
| 127 | * |
||
| 128 | * @var bool |
||
| 129 | * @access protected |
||
| 130 | */ |
||
| 131 | protected $fileGrpsLoaded = false; |
||
| 132 | |||
| 133 | /** |
||
| 134 | * Additional information about files (e.g., ADMID), indexed by ID. |
||
| 135 | * TODO: Consider using this for `getFileMimeType()` and `getFileLocation()`. |
||
| 136 | * @see _getFileInfos() |
||
| 137 | * |
||
| 138 | * @var array |
||
| 139 | * @access protected |
||
| 140 | */ |
||
| 141 | protected $fileInfos = []; |
||
| 142 | |||
| 143 | /** |
||
| 144 | * This holds the XML file's METS part as \SimpleXMLElement object |
||
| 145 | * |
||
| 146 | * @var \SimpleXMLElement |
||
| 147 | * @access protected |
||
| 148 | */ |
||
| 149 | protected $mets; |
||
| 150 | |||
| 151 | /** |
||
| 152 | * This holds the whole XML file as \SimpleXMLElement object |
||
| 153 | * |
||
| 154 | * @var \SimpleXMLElement |
||
| 155 | * @access protected |
||
| 156 | */ |
||
| 157 | protected $xml; |
||
| 158 | |||
| 159 | /** |
||
| 160 | * This adds metadata from METS structural map to metadata array. |
||
| 161 | * |
||
| 162 | * @access public |
||
| 163 | * |
||
| 164 | * @param array &$metadata: The metadata array to extend |
||
| 165 | * @param string $id: The "@ID" attribute of the logical structure node |
||
| 166 | * |
||
| 167 | * @return void |
||
| 168 | */ |
||
| 169 | public function addMetadataFromMets(&$metadata, $id) |
||
| 170 | { |
||
| 171 | $details = $this->getLogicalStructure($id); |
||
| 172 | if (!empty($details)) { |
||
| 173 | $metadata['mets_order'][0] = $details['order']; |
||
| 174 | $metadata['mets_label'][0] = $details['label']; |
||
| 175 | $metadata['mets_orderlabel'][0] = $details['orderlabel']; |
||
| 176 | } |
||
| 177 | } |
||
| 178 | |||
| 179 | /** |
||
| 180 | * |
||
| 181 | * {@inheritDoc} |
||
| 182 | * @see \Kitodo\Dlf\Common\Doc::establishRecordId() |
||
| 183 | */ |
||
| 184 | protected function establishRecordId($pid) |
||
| 185 | { |
||
| 186 | // Check for METS object @ID. |
||
| 187 | if (!empty($this->mets['OBJID'])) { |
||
| 188 | $this->recordId = (string) $this->mets['OBJID']; |
||
| 189 | } |
||
| 190 | // Get hook objects. |
||
| 191 | $hookObjects = Helper::getHookObjects('Classes/Common/MetsDocument.php'); |
||
| 192 | // Apply hooks. |
||
| 193 | foreach ($hookObjects as $hookObj) { |
||
| 194 | if (method_exists($hookObj, 'construct_postProcessRecordId')) { |
||
| 195 | $hookObj->construct_postProcessRecordId($this->xml, $this->recordId); |
||
| 196 | } |
||
| 197 | } |
||
| 198 | } |
||
| 199 | |||
| 200 | /** |
||
| 201 | * |
||
| 202 | * {@inheritDoc} |
||
| 203 | * @see \Kitodo\Dlf\Common\Doc::getDownloadLocation() |
||
| 204 | */ |
||
| 205 | public function getDownloadLocation($id) |
||
| 206 | { |
||
| 207 | $fileMimeType = $this->getFileMimeType($id); |
||
| 208 | $fileLocation = $this->getFileLocation($id); |
||
| 209 | if ($fileMimeType === 'application/vnd.kitodo.iiif') { |
||
| 210 | $fileLocation = (strrpos($fileLocation, 'info.json') === strlen($fileLocation) - 9) ? $fileLocation : (strrpos($fileLocation, '/') === strlen($fileLocation) ? $fileLocation . 'info.json' : $fileLocation . '/info.json'); |
||
| 211 | $conf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
| 212 | IiifHelper::setUrlReader(IiifUrlReader::getInstance()); |
||
| 213 | IiifHelper::setMaxThumbnailHeight($conf['iiifThumbnailHeight']); |
||
| 214 | IiifHelper::setMaxThumbnailWidth($conf['iiifThumbnailWidth']); |
||
| 215 | $service = IiifHelper::loadIiifResource($fileLocation); |
||
| 216 | if ($service !== null && $service instanceof AbstractImageService) { |
||
| 217 | return $service->getImageUrl(); |
||
| 218 | } |
||
| 219 | } elseif ($fileMimeType === 'application/vnd.netfpx') { |
||
| 220 | $baseURL = $fileLocation . (strpos($fileLocation, '?') === false ? '?' : ''); |
||
| 221 | // TODO CVT is an optional IIP server capability; in theory, capabilities should be determined in the object request with '&obj=IIP-server' |
||
| 222 | return $baseURL . '&CVT=jpeg'; |
||
| 223 | } |
||
| 224 | return $fileLocation; |
||
| 225 | } |
||
| 226 | |||
| 227 | /** |
||
| 228 | * {@inheritDoc} |
||
| 229 | * @see \Kitodo\Dlf\Common\Doc::getFileLocation() |
||
| 230 | */ |
||
| 231 | public function getFileLocation($id) |
||
| 232 | { |
||
| 233 | $location = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file[@ID="' . $id . '"]/mets:FLocat[@LOCTYPE="URL"]'); |
||
| 234 | if ( |
||
| 235 | !empty($id) |
||
| 236 | && !empty($location) |
||
| 237 | ) { |
||
| 238 | return (string) $location[0]->attributes('http://www.w3.org/1999/xlink')->href; |
||
| 239 | } else { |
||
| 240 | $this->logger->warning('There is no file node with @ID "' . $id . '"'); |
||
| 241 | return ''; |
||
| 242 | } |
||
| 243 | } |
||
| 244 | |||
| 245 | /** |
||
| 246 | * {@inheritDoc} |
||
| 247 | * @see \Kitodo\Dlf\Common\Doc::getFileMimeType() |
||
| 248 | */ |
||
| 249 | public function getFileMimeType($id) |
||
| 250 | { |
||
| 251 | $mimetype = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file[@ID="' . $id . '"]/@MIMETYPE'); |
||
| 252 | if ( |
||
| 253 | !empty($id) |
||
| 254 | && !empty($mimetype) |
||
| 255 | ) { |
||
| 256 | return (string) $mimetype[0]; |
||
| 257 | } else { |
||
| 258 | $this->logger->warning('There is no file node with @ID "' . $id . '" or no MIME type specified'); |
||
| 259 | return ''; |
||
| 260 | } |
||
| 261 | } |
||
| 262 | |||
| 263 | /** |
||
| 264 | * {@inheritDoc} |
||
| 265 | * @see \Kitodo\Dlf\Common\Doc::getLogicalStructure() |
||
| 266 | */ |
||
| 267 | public function getLogicalStructure($id, $recursive = false) |
||
| 268 | { |
||
| 269 | $details = []; |
||
| 270 | // Is the requested logical unit already loaded? |
||
| 271 | if ( |
||
| 272 | !$recursive |
||
| 273 | && !empty($this->logicalUnits[$id]) |
||
| 274 | ) { |
||
| 275 | // Yes. Return it. |
||
| 276 | return $this->logicalUnits[$id]; |
||
| 277 | } elseif (!empty($id)) { |
||
| 278 | // Get specified logical unit. |
||
| 279 | $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]'); |
||
| 280 | } else { |
||
| 281 | // Get all logical units at top level. |
||
| 282 | $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]/mets:div'); |
||
| 283 | } |
||
| 284 | if (!empty($divs)) { |
||
| 285 | if (!$recursive) { |
||
| 286 | // Get the details for the first xpath hit. |
||
| 287 | $details = $this->getLogicalStructureInfo($divs[0]); |
||
| 288 | } else { |
||
| 289 | // Walk the logical structure recursively and fill the whole table of contents. |
||
| 290 | foreach ($divs as $div) { |
||
| 291 | $this->tableOfContents[] = $this->getLogicalStructureInfo($div, $recursive); |
||
| 292 | } |
||
| 293 | } |
||
| 294 | } |
||
| 295 | return $details; |
||
| 296 | } |
||
| 297 | |||
| 298 | /** |
||
| 299 | * This gets details about a logical structure element |
||
| 300 | * |
||
| 301 | * @access protected |
||
| 302 | * |
||
| 303 | * @param \SimpleXMLElement $structure: The logical structure node |
||
| 304 | * @param bool $recursive: Whether to include the child elements |
||
| 305 | * |
||
| 306 | * @return array Array of the element's id, label, type and physical page indexes/mptr link |
||
| 307 | */ |
||
| 308 | protected function getLogicalStructureInfo(\SimpleXMLElement $structure, $recursive = false) |
||
| 309 | { |
||
| 310 | // Get attributes. |
||
| 311 | foreach ($structure->attributes() as $attribute => $value) { |
||
| 312 | $attributes[$attribute] = (string) $value; |
||
| 313 | } |
||
| 314 | // Load plugin configuration. |
||
| 315 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
| 316 | // Extract identity information. |
||
| 317 | $details = []; |
||
| 318 | $details['id'] = $attributes['ID']; |
||
| 319 | $details['dmdId'] = (isset($attributes['DMDID']) ? $attributes['DMDID'] : ''); |
||
| 320 | $details['admId'] = (isset($attributes['ADMID']) ? $attributes['ADMID'] : ''); |
||
| 321 | $details['order'] = (isset($attributes['ORDER']) ? $attributes['ORDER'] : ''); |
||
| 322 | $details['label'] = (isset($attributes['LABEL']) ? $attributes['LABEL'] : ''); |
||
| 323 | $details['orderlabel'] = (isset($attributes['ORDERLABEL']) ? $attributes['ORDERLABEL'] : ''); |
||
| 324 | $details['contentIds'] = (isset($attributes['CONTENTIDS']) ? $attributes['CONTENTIDS'] : ''); |
||
| 325 | $details['volume'] = ''; |
||
| 326 | // Set volume information only if no label is set and this is the toplevel structure element. |
||
| 327 | if ( |
||
| 328 | empty($details['label']) |
||
| 329 | && $details['id'] == $this->_getToplevelId() |
||
| 330 | ) { |
||
| 331 | $metadata = $this->getMetadata($details['id']); |
||
| 332 | if (!empty($metadata['volume'][0])) { |
||
| 333 | $details['volume'] = $metadata['volume'][0]; |
||
| 334 | } |
||
| 335 | } |
||
| 336 | $details['pagination'] = ''; |
||
| 337 | $details['type'] = $attributes['TYPE']; |
||
| 338 | $details['thumbnailId'] = ''; |
||
| 339 | // Load smLinks. |
||
| 340 | $this->_getSmLinks(); |
||
| 341 | // Load physical structure. |
||
| 342 | $this->_getPhysicalStructure(); |
||
| 343 | // Get the physical page or external file this structure element is pointing at. |
||
| 344 | $details['points'] = ''; |
||
| 345 | // Is there a mptr node? |
||
| 346 | if (count($structure->children('http://www.loc.gov/METS/')->mptr)) { |
||
| 347 | // Yes. Get the file reference. |
||
| 348 | $details['points'] = (string) $structure->children('http://www.loc.gov/METS/')->mptr[0]->attributes('http://www.w3.org/1999/xlink')->href; |
||
| 349 | } elseif ( |
||
| 350 | !empty($this->physicalStructure) |
||
| 351 | && array_key_exists($details['id'], $this->smLinks['l2p']) |
||
| 352 | ) { |
||
| 353 | // Link logical structure to the first corresponding physical page/track. |
||
| 354 | $details['points'] = max(intval(array_search($this->smLinks['l2p'][$details['id']][0], $this->physicalStructure, true)), 1); |
||
| 355 | $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']); |
||
| 356 | while ($fileGrpThumb = array_shift($fileGrpsThumb)) { |
||
| 357 | if (!empty($this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['files'][$fileGrpThumb])) { |
||
| 358 | $details['thumbnailId'] = $this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['files'][$fileGrpThumb]; |
||
| 359 | break; |
||
| 360 | } |
||
| 361 | } |
||
| 362 | // Get page/track number of the first page/track related to this structure element. |
||
| 363 | $details['pagination'] = $this->physicalStructureInfo[$this->smLinks['l2p'][$details['id']][0]]['orderlabel']; |
||
| 364 | } elseif ($details['id'] == $this->_getToplevelId()) { |
||
| 365 | // Point to self if this is the toplevel structure. |
||
| 366 | $details['points'] = 1; |
||
| 367 | $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']); |
||
| 368 | while ($fileGrpThumb = array_shift($fileGrpsThumb)) { |
||
| 369 | if ( |
||
| 370 | !empty($this->physicalStructure) |
||
| 371 | && !empty($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb]) |
||
| 372 | ) { |
||
| 373 | $details['thumbnailId'] = $this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb]; |
||
| 374 | break; |
||
| 375 | } |
||
| 376 | } |
||
| 377 | } |
||
| 378 | // Get the files this structure element is pointing at. |
||
| 379 | $details['files'] = []; |
||
| 380 | $fileUse = $this->_getFileGrps(); |
||
| 381 | // Get the file representations from fileSec node. |
||
| 382 | foreach ($structure->children('http://www.loc.gov/METS/')->fptr as $fptr) { |
||
| 383 | // Check if file has valid @USE attribute. |
||
| 384 | if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) { |
||
|
|
|||
| 385 | $details['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID; |
||
| 386 | } |
||
| 387 | } |
||
| 388 | // Keep for later usage. |
||
| 389 | $this->logicalUnits[$details['id']] = $details; |
||
| 390 | // Walk the structure recursively? And are there any children of the current element? |
||
| 391 | if ( |
||
| 392 | $recursive |
||
| 393 | && count($structure->children('http://www.loc.gov/METS/')->div) |
||
| 394 | ) { |
||
| 395 | $details['children'] = []; |
||
| 396 | foreach ($structure->children('http://www.loc.gov/METS/')->div as $child) { |
||
| 397 | // Repeat for all children. |
||
| 398 | $details['children'][] = $this->getLogicalStructureInfo($child, true); |
||
| 399 | } |
||
| 400 | } |
||
| 401 | return $details; |
||
| 402 | } |
||
| 403 | |||
| 404 | /** |
||
| 405 | * {@inheritDoc} |
||
| 406 | * @see \Kitodo\Dlf\Common\Doc::getMetadata() |
||
| 407 | */ |
||
| 408 | public function getMetadata($id, $cPid = 0) |
||
| 409 | { |
||
| 410 | // Make sure $cPid is a non-negative integer. |
||
| 411 | $cPid = max(intval($cPid), 0); |
||
| 412 | // If $cPid is not given, try to get it elsewhere. |
||
| 413 | if ( |
||
| 414 | !$cPid |
||
| 415 | && ($this->cPid || $this->pid) |
||
| 416 | ) { |
||
| 417 | // Retain current PID. |
||
| 418 | $cPid = ($this->cPid ? $this->cPid : $this->pid); |
||
| 419 | } elseif (!$cPid) { |
||
| 420 | $this->logger->warning('Invalid PID ' . $cPid . ' for metadata definitions'); |
||
| 421 | return []; |
||
| 422 | } |
||
| 423 | // Get metadata from parsed metadata array if available. |
||
| 424 | if ( |
||
| 425 | !empty($this->metadataArray[$id]) |
||
| 426 | && $this->metadataArray[0] == $cPid |
||
| 427 | ) { |
||
| 428 | return $this->metadataArray[$id]; |
||
| 429 | } |
||
| 430 | // Initialize metadata array with empty values. |
||
| 431 | $metadata = [ |
||
| 432 | 'title' => [], |
||
| 433 | 'title_sorting' => [], |
||
| 434 | 'author' => [], |
||
| 435 | 'place' => [], |
||
| 436 | 'year' => [], |
||
| 437 | 'prod_id' => [], |
||
| 438 | 'record_id' => [], |
||
| 439 | 'opac_id' => [], |
||
| 440 | 'union_id' => [], |
||
| 441 | 'urn' => [], |
||
| 442 | 'purl' => [], |
||
| 443 | 'type' => [], |
||
| 444 | 'volume' => [], |
||
| 445 | 'volume_sorting' => [], |
||
| 446 | 'license' => [], |
||
| 447 | 'terms' => [], |
||
| 448 | 'restrictions' => [], |
||
| 449 | 'out_of_print' => [], |
||
| 450 | 'rights_info' => [], |
||
| 451 | 'collection' => [], |
||
| 452 | 'owner' => [], |
||
| 453 | 'mets_label' => [], |
||
| 454 | 'mets_orderlabel' => [], |
||
| 455 | 'document_format' => ['METS'], |
||
| 456 | ]; |
||
| 457 | $mdIds = $this->getMetadataIds($id); |
||
| 458 | if (empty($mdIds)) { |
||
| 459 | // There is no metadata section for this structure node. |
||
| 460 | return []; |
||
| 461 | } |
||
| 462 | // Associative array used as set of available section types (dmdSec, techMD, ...) |
||
| 463 | $hasMetadataSection = []; |
||
| 464 | // Load available metadata formats and metadata sections. |
||
| 465 | $this->loadFormats(); |
||
| 466 | $this->_getMdSec(); |
||
| 467 | // Get the structure's type. |
||
| 468 | if (!empty($this->logicalUnits[$id])) { |
||
| 469 | $metadata['type'] = [$this->logicalUnits[$id]['type']]; |
||
| 470 | } else { |
||
| 471 | $struct = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]/@TYPE'); |
||
| 472 | if (!empty($struct)) { |
||
| 473 | $metadata['type'] = [(string) $struct[0]]; |
||
| 474 | } |
||
| 475 | } |
||
| 476 | foreach ($mdIds as $dmdId) { |
||
| 477 | $mdSectionType = $this->mdSec[$dmdId]['section']; |
||
| 478 | |||
| 479 | // To preserve behavior of previous Kitodo versions, extract metadata only from first supported dmdSec |
||
| 480 | // However, we want to extract, for example, all techMD sections (VIDEOMD, AUDIOMD) |
||
| 481 | if ($mdSectionType === 'dmdSec' && isset($hasMetadataSection['dmdSec'])) { |
||
| 482 | continue; |
||
| 483 | } |
||
| 484 | |||
| 485 | // Is this metadata format supported? |
||
| 486 | if (!empty($this->formats[$this->mdSec[$dmdId]['type']])) { |
||
| 487 | if (!empty($this->formats[$this->mdSec[$dmdId]['type']]['class'])) { |
||
| 488 | $class = $this->formats[$this->mdSec[$dmdId]['type']]['class']; |
||
| 489 | // Get the metadata from class. |
||
| 490 | if ( |
||
| 491 | class_exists($class) |
||
| 492 | && ($obj = GeneralUtility::makeInstance($class)) instanceof MetadataInterface |
||
| 493 | ) { |
||
| 494 | $obj->extractMetadata($this->mdSec[$dmdId]['xml'], $metadata); |
||
| 495 | } else { |
||
| 496 | $this->logger->warning('Invalid class/method "' . $class . '->extractMetadata()" for metadata format "' . $this->mdSec[$dmdId]['type'] . '"'); |
||
| 497 | } |
||
| 498 | } |
||
| 499 | } else { |
||
| 500 | $this->logger->notice('Unsupported metadata format "' . $this->mdSec[$dmdId]['type'] . '" in ' . $mdSectionType . ' with @ID "' . $dmdId . '"'); |
||
| 501 | // Continue searching for supported metadata with next @DMDID. |
||
| 502 | continue; |
||
| 503 | } |
||
| 504 | // Get the additional metadata from database. |
||
| 505 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
| 506 | ->getQueryBuilderForTable('tx_dlf_metadata'); |
||
| 507 | // Get hidden records, too. |
||
| 508 | $queryBuilder |
||
| 509 | ->getRestrictions() |
||
| 510 | ->removeByType(HiddenRestriction::class); |
||
| 511 | // Get all metadata with configured xpath and applicable format first. |
||
| 512 | $resultWithFormat = $queryBuilder |
||
| 513 | ->select( |
||
| 514 | 'tx_dlf_metadata.index_name AS index_name', |
||
| 515 | 'tx_dlf_metadataformat_joins.xpath AS xpath', |
||
| 516 | 'tx_dlf_metadataformat_joins.xpath_sorting AS xpath_sorting', |
||
| 517 | 'tx_dlf_metadata.is_sortable AS is_sortable', |
||
| 518 | 'tx_dlf_metadata.default_value AS default_value', |
||
| 519 | 'tx_dlf_metadata.format AS format' |
||
| 520 | ) |
||
| 521 | ->from('tx_dlf_metadata') |
||
| 522 | ->innerJoin( |
||
| 523 | 'tx_dlf_metadata', |
||
| 524 | 'tx_dlf_metadataformat', |
||
| 525 | 'tx_dlf_metadataformat_joins', |
||
| 526 | $queryBuilder->expr()->eq( |
||
| 527 | 'tx_dlf_metadataformat_joins.parent_id', |
||
| 528 | 'tx_dlf_metadata.uid' |
||
| 529 | ) |
||
| 530 | ) |
||
| 531 | ->innerJoin( |
||
| 532 | 'tx_dlf_metadataformat_joins', |
||
| 533 | 'tx_dlf_formats', |
||
| 534 | 'tx_dlf_formats_joins', |
||
| 535 | $queryBuilder->expr()->eq( |
||
| 536 | 'tx_dlf_formats_joins.uid', |
||
| 537 | 'tx_dlf_metadataformat_joins.encoded' |
||
| 538 | ) |
||
| 539 | ) |
||
| 540 | ->where( |
||
| 541 | $queryBuilder->expr()->eq('tx_dlf_metadata.pid', intval($cPid)), |
||
| 542 | $queryBuilder->expr()->eq('tx_dlf_metadata.l18n_parent', 0), |
||
| 543 | $queryBuilder->expr()->eq('tx_dlf_metadataformat_joins.pid', intval($cPid)), |
||
| 544 | $queryBuilder->expr()->eq('tx_dlf_formats_joins.type', $queryBuilder->createNamedParameter($this->mdSec[$dmdId]['type'])) |
||
| 545 | ) |
||
| 546 | ->execute(); |
||
| 547 | // Get all metadata without a format, but with a default value next. |
||
| 548 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
| 549 | ->getQueryBuilderForTable('tx_dlf_metadata'); |
||
| 550 | // Get hidden records, too. |
||
| 551 | $queryBuilder |
||
| 552 | ->getRestrictions() |
||
| 553 | ->removeByType(HiddenRestriction::class); |
||
| 554 | $resultWithoutFormat = $queryBuilder |
||
| 555 | ->select( |
||
| 556 | 'tx_dlf_metadata.index_name AS index_name', |
||
| 557 | 'tx_dlf_metadata.is_sortable AS is_sortable', |
||
| 558 | 'tx_dlf_metadata.default_value AS default_value', |
||
| 559 | 'tx_dlf_metadata.format AS format' |
||
| 560 | ) |
||
| 561 | ->from('tx_dlf_metadata') |
||
| 562 | ->where( |
||
| 563 | $queryBuilder->expr()->eq('tx_dlf_metadata.pid', intval($cPid)), |
||
| 564 | $queryBuilder->expr()->eq('tx_dlf_metadata.l18n_parent', 0), |
||
| 565 | $queryBuilder->expr()->eq('tx_dlf_metadata.format', 0), |
||
| 566 | $queryBuilder->expr()->neq('tx_dlf_metadata.default_value', $queryBuilder->createNamedParameter('')) |
||
| 567 | ) |
||
| 568 | ->execute(); |
||
| 569 | // Merge both result sets. |
||
| 570 | $allResults = array_merge($resultWithFormat->fetchAll(), $resultWithoutFormat->fetchAll()); |
||
| 571 | // We need a \DOMDocument here, because SimpleXML doesn't support XPath functions properly. |
||
| 572 | $domNode = dom_import_simplexml($this->mdSec[$dmdId]['xml']); |
||
| 573 | $domXPath = new \DOMXPath($domNode->ownerDocument); |
||
| 574 | $this->registerNamespaces($domXPath); |
||
| 575 | // OK, now make the XPath queries. |
||
| 576 | foreach ($allResults as $resArray) { |
||
| 577 | // Set metadata field's value(s). |
||
| 578 | if ( |
||
| 579 | $resArray['format'] > 0 |
||
| 580 | && !empty($resArray['xpath']) |
||
| 581 | && ($values = $domXPath->evaluate($resArray['xpath'], $domNode)) |
||
| 582 | ) { |
||
| 583 | if ( |
||
| 584 | $values instanceof \DOMNodeList |
||
| 585 | && $values->length > 0 |
||
| 586 | ) { |
||
| 587 | $metadata[$resArray['index_name']] = []; |
||
| 588 | foreach ($values as $value) { |
||
| 589 | $metadata[$resArray['index_name']][] = trim((string) $value->nodeValue); |
||
| 590 | } |
||
| 591 | } elseif (!($values instanceof \DOMNodeList)) { |
||
| 592 | $metadata[$resArray['index_name']] = [trim((string) $values)]; |
||
| 593 | } |
||
| 594 | } |
||
| 595 | // Set default value if applicable. |
||
| 596 | if ( |
||
| 597 | empty($metadata[$resArray['index_name']][0]) |
||
| 598 | && strlen($resArray['default_value']) > 0 |
||
| 599 | ) { |
||
| 600 | $metadata[$resArray['index_name']] = [$resArray['default_value']]; |
||
| 601 | } |
||
| 602 | // Set sorting value if applicable. |
||
| 603 | if ( |
||
| 604 | !empty($metadata[$resArray['index_name']]) |
||
| 605 | && $resArray['is_sortable'] |
||
| 606 | ) { |
||
| 607 | if ( |
||
| 608 | $resArray['format'] > 0 |
||
| 609 | && !empty($resArray['xpath_sorting']) |
||
| 610 | && ($values = $domXPath->evaluate($resArray['xpath_sorting'], $domNode)) |
||
| 611 | ) { |
||
| 612 | if ( |
||
| 613 | $values instanceof \DOMNodeList |
||
| 614 | && $values->length > 0 |
||
| 615 | ) { |
||
| 616 | $metadata[$resArray['index_name'] . '_sorting'][0] = trim((string) $values->item(0)->nodeValue); |
||
| 617 | } elseif (!($values instanceof \DOMNodeList)) { |
||
| 618 | $metadata[$resArray['index_name'] . '_sorting'][0] = trim((string) $values); |
||
| 619 | } |
||
| 620 | } |
||
| 621 | if (empty($metadata[$resArray['index_name'] . '_sorting'][0])) { |
||
| 622 | $metadata[$resArray['index_name'] . '_sorting'][0] = $metadata[$resArray['index_name']][0]; |
||
| 623 | } |
||
| 624 | } |
||
| 625 | } |
||
| 626 | |||
| 627 | $hasMetadataSection[$mdSectionType] = true; |
||
| 628 | } |
||
| 629 | // Set title to empty string if not present. |
||
| 630 | if (empty($metadata['title'][0])) { |
||
| 631 | $metadata['title'][0] = ''; |
||
| 632 | $metadata['title_sorting'][0] = ''; |
||
| 633 | } |
||
| 634 | // Files are not expected to reference a dmdSec |
||
| 635 | if (isset($this->fileInfos[$id]) || isset($hasMetadataSection['dmdSec'])) { |
||
| 636 | return $metadata; |
||
| 637 | } else { |
||
| 638 | $this->logger->warning('No supported descriptive metadata found for logical structure with @ID "' . $id . '"'); |
||
| 639 | return []; |
||
| 640 | } |
||
| 641 | } |
||
| 642 | |||
| 643 | /** |
||
| 644 | * Get IDs of (descriptive and administrative) metadata sections |
||
| 645 | * referenced by node of given $id. The $id may refer to either |
||
| 646 | * a logical structure node or to a file. |
||
| 647 | * |
||
| 648 | * @access protected |
||
| 649 | * @param string $id: The "@ID" attribute of the file node |
||
| 650 | * @return void |
||
| 651 | */ |
||
| 652 | protected function getMetadataIds($id) |
||
| 653 | { |
||
| 654 | // Load amdSecChildIds concordance |
||
| 655 | $this->_getMdSec(); |
||
| 656 | $this->_getFileInfos(); |
||
| 657 | |||
| 658 | // Get DMDID and ADMID of logical structure node |
||
| 659 | if (!empty($this->logicalUnits[$id])) { |
||
| 660 | $dmdIds = $this->logicalUnits[$id]['dmdId'] ?? ''; |
||
| 661 | $admIds = $this->logicalUnits[$id]['admId'] ?? ''; |
||
| 662 | } else { |
||
| 663 | $mdSec = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $id . '"]')[0]; |
||
| 664 | if ($mdSec) { |
||
| 665 | $dmdIds = (string) $mdSec->attributes()->DMDID; |
||
| 666 | $admIds = (string) $mdSec->attributes()->ADMID; |
||
| 667 | } else if (isset($this->fileInfos[$id])) { |
||
| 668 | $dmdIds = $this->fileInfos[$id]['dmdId']; |
||
| 669 | $admIds = $this->fileInfos[$id]['admId']; |
||
| 670 | } else { |
||
| 671 | $dmdIds = ''; |
||
| 672 | $admIds = ''; |
||
| 673 | } |
||
| 674 | } |
||
| 675 | |||
| 676 | // Handle multiple DMDIDs/ADMIDs |
||
| 677 | $allMdIds = explode(' ', $dmdIds); |
||
| 678 | |||
| 679 | foreach (explode(' ', $admIds) as $admId) { |
||
| 680 | if (isset($this->mdSec[$admId])) { |
||
| 681 | // $admId references an actual metadata section such as techMD |
||
| 682 | $allMdIds[] = $admId; |
||
| 683 | } elseif (isset($this->amdSecChildIds[$admId])) { |
||
| 684 | // $admId references a <mets:amdSec> element. Resolve child elements. |
||
| 685 | foreach ($this->amdSecChildIds[$admId] as $childId) { |
||
| 686 | $allMdIds[] = $childId; |
||
| 687 | } |
||
| 688 | } |
||
| 689 | } |
||
| 690 | |||
| 691 | return array_filter($allMdIds, function ($element) { |
||
| 692 | return !empty($element); |
||
| 693 | }); |
||
| 694 | } |
||
| 695 | |||
| 696 | /** |
||
| 697 | * {@inheritDoc} |
||
| 698 | * @see \Kitodo\Dlf\Common\Doc::getFullText() |
||
| 699 | */ |
||
| 700 | public function getFullText($id) |
||
| 701 | { |
||
| 702 | $fullText = ''; |
||
| 703 | |||
| 704 | // Load fileGrps and check for full text files. |
||
| 705 | $this->_getFileGrps(); |
||
| 706 | if ($this->hasFulltext) { |
||
| 707 | $fullText = $this->getFullTextFromXml($id); |
||
| 708 | } |
||
| 709 | return $fullText; |
||
| 710 | } |
||
| 711 | |||
| 712 | /** |
||
| 713 | * {@inheritDoc} |
||
| 714 | * @see Doc::getStructureDepth() |
||
| 715 | */ |
||
| 716 | public function getStructureDepth($logId) |
||
| 717 | { |
||
| 718 | $ancestors = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="' . $logId . '"]/ancestor::*'); |
||
| 719 | if (!empty($ancestors)) { |
||
| 720 | return count($ancestors); |
||
| 721 | } else { |
||
| 722 | return 0; |
||
| 723 | } |
||
| 724 | } |
||
| 725 | |||
| 726 | /** |
||
| 727 | * {@inheritDoc} |
||
| 728 | * @see \Kitodo\Dlf\Common\Doc::init() |
||
| 729 | */ |
||
| 730 | protected function init($location) |
||
| 731 | { |
||
| 732 | $this->logger = GeneralUtility::makeInstance(LogManager::class)->getLogger(get_class($this)); |
||
| 733 | // Get METS node from XML file. |
||
| 734 | $this->registerNamespaces($this->xml); |
||
| 735 | $mets = $this->xml->xpath('//mets:mets'); |
||
| 736 | if (!empty($mets)) { |
||
| 737 | $this->mets = $mets[0]; |
||
| 738 | // Register namespaces. |
||
| 739 | $this->registerNamespaces($this->mets); |
||
| 740 | } else { |
||
| 741 | if (!empty($location)) { |
||
| 742 | $this->logger->error('No METS part found in document with location "' . $location . '".'); |
||
| 743 | } else if (!empty($this->recordId)) { |
||
| 744 | $this->logger->error('No METS part found in document with recordId "' . $this->recordId . '".'); |
||
| 745 | } else { |
||
| 746 | $this->logger->error('No METS part found in current document.'); |
||
| 747 | } |
||
| 748 | } |
||
| 749 | } |
||
| 750 | |||
| 751 | /** |
||
| 752 | * {@inheritDoc} |
||
| 753 | * @see \Kitodo\Dlf\Common\Doc::loadLocation() |
||
| 754 | */ |
||
| 755 | protected function loadLocation($location) |
||
| 756 | { |
||
| 757 | $fileResource = Helper::getUrl($location); |
||
| 758 | if ($fileResource !== false) { |
||
| 759 | $xml = Helper::getXmlFileAsString($fileResource); |
||
| 760 | // Set some basic properties. |
||
| 761 | if ($xml !== false) { |
||
| 762 | $this->xml = $xml; |
||
| 763 | return true; |
||
| 764 | } |
||
| 765 | } |
||
| 766 | $this->logger->error('Could not load XML file from "' . $location . '"'); |
||
| 767 | return false; |
||
| 768 | } |
||
| 769 | |||
| 770 | /** |
||
| 771 | * {@inheritDoc} |
||
| 772 | * @see \Kitodo\Dlf\Common\Doc::ensureHasFulltextIsSet() |
||
| 773 | */ |
||
| 774 | protected function ensureHasFulltextIsSet() |
||
| 775 | { |
||
| 776 | // Are the fileGrps already loaded? |
||
| 777 | if (!$this->fileGrpsLoaded) { |
||
| 778 | $this->_getFileGrps(); |
||
| 779 | } |
||
| 780 | } |
||
| 781 | |||
| 782 | /** |
||
| 783 | * {@inheritDoc} |
||
| 784 | * @see Doc::setPreloadedDocument() |
||
| 785 | */ |
||
| 786 | protected function setPreloadedDocument($preloadedDocument) |
||
| 787 | { |
||
| 788 | |||
| 789 | if ($preloadedDocument instanceof \SimpleXMLElement) { |
||
| 790 | $this->xml = $preloadedDocument; |
||
| 791 | return true; |
||
| 792 | } |
||
| 793 | return false; |
||
| 794 | } |
||
| 795 | |||
| 796 | /** |
||
| 797 | * {@inheritDoc} |
||
| 798 | * @see Doc::getDocument() |
||
| 799 | */ |
||
| 800 | protected function getDocument() |
||
| 803 | } |
||
| 804 | |||
| 805 | /** |
||
| 806 | * This builds an array of the document's metadata sections |
||
| 807 | * |
||
| 808 | * @access protected |
||
| 809 | * |
||
| 810 | * @return array Array of metadata sections with their IDs as array key |
||
| 811 | */ |
||
| 812 | protected function _getMdSec() |
||
| 813 | { |
||
| 814 | if (!$this->mdSecLoaded) { |
||
| 815 | $this->loadFormats(); |
||
| 816 | |||
| 817 | foreach ($this->mets->xpath('./mets:dmdSec') as $dmdSecTag) { |
||
| 818 | $dmdSec = $this->processMdSec($dmdSecTag); |
||
| 819 | |||
| 820 | if ($dmdSec !== null) { |
||
| 821 | $this->mdSec[$dmdSec['id']] = $dmdSec; |
||
| 822 | $this->dmdSec[$dmdSec['id']] = $dmdSec; |
||
| 823 | } |
||
| 824 | } |
||
| 825 | |||
| 826 | foreach ($this->mets->xpath('./mets:amdSec') as $amdSecTag) { |
||
| 827 | $childIds = []; |
||
| 828 | |||
| 829 | foreach ($amdSecTag->children('http://www.loc.gov/METS/') as $mdSecTag) { |
||
| 830 | if (!in_array($mdSecTag->getName(), self::ALLOWED_AMD_SEC)) { |
||
| 831 | continue; |
||
| 832 | } |
||
| 833 | |||
| 834 | // TODO: Should we check that the format may occur within this type (e.g., to ignore VIDEOMD within rightsMD)? |
||
| 835 | $mdSec = $this->processMdSec($mdSecTag); |
||
| 836 | |||
| 837 | if ($mdSec !== null) { |
||
| 838 | $this->mdSec[$mdSec['id']] = $mdSec; |
||
| 839 | |||
| 840 | $childIds[] = $mdSec['id']; |
||
| 841 | } |
||
| 842 | } |
||
| 843 | |||
| 844 | $amdSecId = (string) $amdSecTag->attributes()->ID; |
||
| 845 | if (!empty($amdSecId)) { |
||
| 846 | $this->amdSecChildIds[$amdSecId] = $childIds; |
||
| 847 | } |
||
| 848 | } |
||
| 849 | |||
| 850 | $this->mdSecLoaded = true; |
||
| 851 | } |
||
| 852 | return $this->mdSec; |
||
| 853 | } |
||
| 854 | |||
| 855 | protected function _getDmdSec() |
||
| 856 | { |
||
| 857 | $this->_getMdSec(); |
||
| 858 | return $this->dmdSec; |
||
| 859 | } |
||
| 860 | |||
| 861 | /** |
||
| 862 | * Processes an element of METS `mdSecType`. |
||
| 863 | * |
||
| 864 | * @access protected |
||
| 865 | * |
||
| 866 | * @param \SimpleXMLElement $element |
||
| 867 | * |
||
| 868 | * @return array|null The processed metadata section |
||
| 869 | */ |
||
| 870 | protected function processMdSec($element) |
||
| 871 | { |
||
| 872 | $mdId = (string) $element->attributes()->ID; |
||
| 873 | if (empty($mdId)) { |
||
| 874 | return null; |
||
| 875 | } |
||
| 876 | |||
| 877 | $this->registerNamespaces($element); |
||
| 878 | if ($type = $element->xpath('./mets:mdWrap[not(@MDTYPE="OTHER")]/@MDTYPE')) { |
||
| 879 | if (!empty($this->formats[(string) $type[0]])) { |
||
| 880 | $type = (string) $type[0]; |
||
| 881 | $xml = $element->xpath('./mets:mdWrap[@MDTYPE="' . $type . '"]/mets:xmlData/' . strtolower($type) . ':' . $this->formats[$type]['rootElement']); |
||
| 882 | } |
||
| 883 | } elseif ($type = $element->xpath('./mets:mdWrap[@MDTYPE="OTHER"]/@OTHERMDTYPE')) { |
||
| 884 | if (!empty($this->formats[(string) $type[0]])) { |
||
| 885 | $type = (string) $type[0]; |
||
| 886 | $xml = $element->xpath('./mets:mdWrap[@MDTYPE="OTHER"][@OTHERMDTYPE="' . $type . '"]/mets:xmlData/' . strtolower($type) . ':' . $this->formats[$type]['rootElement']); |
||
| 887 | } |
||
| 888 | } |
||
| 889 | |||
| 890 | if (empty($xml)) { |
||
| 891 | return null; |
||
| 892 | } |
||
| 893 | |||
| 894 | $this->registerNamespaces($xml[0]); |
||
| 895 | |||
| 896 | return [ |
||
| 897 | 'id' => $mdId, |
||
| 898 | 'section' => $element->getName(), |
||
| 899 | 'type' => $type, |
||
| 900 | 'xml' => $xml[0], |
||
| 901 | ]; |
||
| 902 | } |
||
| 903 | |||
| 904 | /** |
||
| 905 | * This builds the file ID -> USE concordance |
||
| 906 | * |
||
| 907 | * @access protected |
||
| 908 | * |
||
| 909 | * @return array Array of file use groups with file IDs |
||
| 910 | */ |
||
| 911 | protected function _getFileGrps() |
||
| 912 | { |
||
| 913 | if (!$this->fileGrpsLoaded) { |
||
| 914 | // Get configured USE attributes. |
||
| 915 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
| 916 | $useGrps = GeneralUtility::trimExplode(',', $extConf['fileGrpImages']); |
||
| 917 | if (!empty($extConf['fileGrpThumbs'])) { |
||
| 918 | $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs'])); |
||
| 919 | } |
||
| 920 | if (!empty($extConf['fileGrpDownload'])) { |
||
| 921 | $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpDownload'])); |
||
| 922 | } |
||
| 923 | if (!empty($extConf['fileGrpFulltext'])) { |
||
| 924 | $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpFulltext'])); |
||
| 925 | } |
||
| 926 | if (!empty($extConf['fileGrpAudio'])) { |
||
| 927 | $useGrps = array_merge($useGrps, GeneralUtility::trimExplode(',', $extConf['fileGrpAudio'])); |
||
| 928 | } |
||
| 929 | // Get all file groups. |
||
| 930 | $fileGrps = $this->mets->xpath('./mets:fileSec/mets:fileGrp'); |
||
| 931 | if (!empty($fileGrps)) { |
||
| 932 | // Build concordance for configured USE attributes. |
||
| 933 | foreach ($fileGrps as $fileGrp) { |
||
| 934 | if (in_array((string) $fileGrp['USE'], $useGrps)) { |
||
| 935 | foreach ($fileGrp->children('http://www.loc.gov/METS/')->file as $file) { |
||
| 936 | $fileId = (string) $file->attributes()->ID; |
||
| 937 | $this->fileGrps[$fileId] = (string) $fileGrp['USE']; |
||
| 938 | $this->fileInfos[$fileId] = [ |
||
| 939 | 'fileGrp' => (string) $fileGrp['USE'], |
||
| 940 | 'admId' => (string) $file->attributes()->ADMID, |
||
| 941 | 'dmdId' => (string) $file->attributes()->DMDID, |
||
| 942 | ]; |
||
| 943 | } |
||
| 944 | } |
||
| 945 | } |
||
| 946 | } |
||
| 947 | // Are there any fulltext files available? |
||
| 948 | if ( |
||
| 949 | !empty($extConf['fileGrpFulltext']) |
||
| 950 | && array_intersect(GeneralUtility::trimExplode(',', $extConf['fileGrpFulltext']), $this->fileGrps) !== [] |
||
| 951 | ) { |
||
| 952 | $this->hasFulltext = true; |
||
| 953 | } |
||
| 954 | $this->fileGrpsLoaded = true; |
||
| 955 | } |
||
| 956 | return $this->fileGrps; |
||
| 957 | } |
||
| 958 | |||
| 959 | /** |
||
| 960 | * |
||
| 961 | * @access protected |
||
| 962 | * @return array |
||
| 963 | */ |
||
| 964 | protected function _getFileInfos() |
||
| 965 | { |
||
| 966 | $this->_getFileGrps(); |
||
| 967 | return $this->fileInfos; |
||
| 968 | } |
||
| 969 | |||
| 970 | /** |
||
| 971 | * {@inheritDoc} |
||
| 972 | * @see \Kitodo\Dlf\Common\Doc::prepareMetadataArray() |
||
| 973 | */ |
||
| 974 | protected function prepareMetadataArray($cPid) |
||
| 975 | { |
||
| 976 | $ids = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@DMDID]/@ID'); |
||
| 977 | // Get all logical structure nodes with metadata. |
||
| 978 | if (!empty($ids)) { |
||
| 979 | foreach ($ids as $id) { |
||
| 980 | $this->metadataArray[(string) $id] = $this->getMetadata((string) $id, $cPid); |
||
| 981 | } |
||
| 982 | } |
||
| 983 | // Set current PID for metadata definitions. |
||
| 984 | } |
||
| 985 | |||
| 986 | /** |
||
| 987 | * This returns $this->mets via __get() |
||
| 988 | * |
||
| 989 | * @access protected |
||
| 990 | * |
||
| 991 | * @return \SimpleXMLElement The XML's METS part as \SimpleXMLElement object |
||
| 992 | */ |
||
| 993 | protected function _getMets() |
||
| 994 | { |
||
| 995 | return $this->mets; |
||
| 996 | } |
||
| 997 | |||
| 998 | /** |
||
| 999 | * {@inheritDoc} |
||
| 1000 | * @see \Kitodo\Dlf\Common\Doc::_getPhysicalStructure() |
||
| 1001 | */ |
||
| 1002 | protected function _getPhysicalStructure() |
||
| 1003 | { |
||
| 1004 | // Is there no physical structure array yet? |
||
| 1005 | if (!$this->physicalStructureLoaded) { |
||
| 1006 | // Does the document have a structMap node of type "PHYSICAL"? |
||
| 1007 | $elementNodes = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]/mets:div'); |
||
| 1008 | if (!empty($elementNodes)) { |
||
| 1009 | // Get file groups. |
||
| 1010 | $fileUse = $this->_getFileGrps(); |
||
| 1011 | // Get the physical sequence's metadata. |
||
| 1012 | $physNode = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]'); |
||
| 1013 | $physSeq[0] = (string) $physNode[0]['ID']; |
||
| 1014 | $this->physicalStructureInfo[$physSeq[0]]['id'] = (string) $physNode[0]['ID']; |
||
| 1015 | $this->physicalStructureInfo[$physSeq[0]]['dmdId'] = (isset($physNode[0]['DMDID']) ? (string) $physNode[0]['DMDID'] : ''); |
||
| 1016 | $this->physicalStructureInfo[$physSeq[0]]['admId'] = (isset($physNode[0]['ADMID']) ? (string) $physNode[0]['ADMID'] : ''); |
||
| 1017 | $this->physicalStructureInfo[$physSeq[0]]['order'] = (isset($physNode[0]['ORDER']) ? (string) $physNode[0]['ORDER'] : ''); |
||
| 1018 | $this->physicalStructureInfo[$physSeq[0]]['label'] = (isset($physNode[0]['LABEL']) ? (string) $physNode[0]['LABEL'] : ''); |
||
| 1019 | $this->physicalStructureInfo[$physSeq[0]]['orderlabel'] = (isset($physNode[0]['ORDERLABEL']) ? (string) $physNode[0]['ORDERLABEL'] : ''); |
||
| 1020 | $this->physicalStructureInfo[$physSeq[0]]['type'] = (string) $physNode[0]['TYPE']; |
||
| 1021 | $this->physicalStructureInfo[$physSeq[0]]['contentIds'] = (isset($physNode[0]['CONTENTIDS']) ? (string) $physNode[0]['CONTENTIDS'] : ''); |
||
| 1022 | // Get the file representations from fileSec node. |
||
| 1023 | foreach ($physNode[0]->children('http://www.loc.gov/METS/')->fptr as $fptr) { |
||
| 1024 | // Check if file has valid @USE attribute. |
||
| 1025 | if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) { |
||
| 1026 | $this->physicalStructureInfo[$physSeq[0]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID; |
||
| 1027 | } |
||
| 1028 | } |
||
| 1029 | // Build the physical elements' array from the physical structMap node. |
||
| 1030 | foreach ($elementNodes as $elementNode) { |
||
| 1031 | $elements[(int) $elementNode['ORDER']] = (string) $elementNode['ID']; |
||
| 1032 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['id'] = (string) $elementNode['ID']; |
||
| 1033 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['dmdId'] = (isset($elementNode['DMDID']) ? (string) $elementNode['DMDID'] : ''); |
||
| 1034 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['admId'] = (isset($elementNode['ADMID']) ? (string) $elementNode['ADMID'] : ''); |
||
| 1035 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['order'] = (isset($elementNode['ORDER']) ? (string) $elementNode['ORDER'] : ''); |
||
| 1036 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['label'] = (isset($elementNode['LABEL']) ? (string) $elementNode['LABEL'] : ''); |
||
| 1037 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['orderlabel'] = (isset($elementNode['ORDERLABEL']) ? (string) $elementNode['ORDERLABEL'] : ''); |
||
| 1038 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['type'] = (string) $elementNode['TYPE']; |
||
| 1039 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['contentIds'] = (isset($elementNode['CONTENTIDS']) ? (string) $elementNode['CONTENTIDS'] : ''); |
||
| 1040 | // Get the file representations from fileSec node. |
||
| 1041 | foreach ($elementNode->children('http://www.loc.gov/METS/')->fptr as $fptr) { |
||
| 1042 | // Check if file has valid @USE attribute. |
||
| 1043 | if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) { |
||
| 1044 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID; |
||
| 1045 | } |
||
| 1046 | } |
||
| 1047 | } |
||
| 1048 | // Sort array by keys (= @ORDER). |
||
| 1049 | if (ksort($elements)) { |
||
| 1050 | // Set total number of pages/tracks. |
||
| 1051 | $this->numPages = count($elements); |
||
| 1052 | // Merge and re-index the array to get nice numeric indexes. |
||
| 1053 | $this->physicalStructure = array_merge($physSeq, $elements); |
||
| 1054 | } |
||
| 1055 | } |
||
| 1056 | $this->physicalStructureLoaded = true; |
||
| 1057 | } |
||
| 1058 | return $this->physicalStructure; |
||
| 1059 | } |
||
| 1060 | |||
| 1061 | /** |
||
| 1062 | * {@inheritDoc} |
||
| 1063 | * @see \Kitodo\Dlf\Common\Doc::_getSmLinks() |
||
| 1064 | */ |
||
| 1065 | protected function _getSmLinks() |
||
| 1066 | { |
||
| 1067 | if (!$this->smLinksLoaded) { |
||
| 1068 | $smLinks = $this->mets->xpath('./mets:structLink/mets:smLink'); |
||
| 1069 | if (!empty($smLinks)) { |
||
| 1070 | foreach ($smLinks as $smLink) { |
||
| 1071 | $this->smLinks['l2p'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->from][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->to; |
||
| 1072 | $this->smLinks['p2l'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->to][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->from; |
||
| 1073 | } |
||
| 1074 | } |
||
| 1075 | $this->smLinksLoaded = true; |
||
| 1076 | } |
||
| 1077 | return $this->smLinks; |
||
| 1078 | } |
||
| 1079 | |||
| 1080 | /** |
||
| 1081 | * {@inheritDoc} |
||
| 1082 | * @see \Kitodo\Dlf\Common\Doc::_getThumbnail() |
||
| 1083 | */ |
||
| 1084 | protected function _getThumbnail($forceReload = false) |
||
| 1085 | { |
||
| 1086 | if ( |
||
| 1087 | !$this->thumbnailLoaded |
||
| 1088 | || $forceReload |
||
| 1089 | ) { |
||
| 1090 | // Retain current PID. |
||
| 1091 | $cPid = ($this->cPid ? $this->cPid : $this->pid); |
||
| 1092 | if (!$cPid) { |
||
| 1093 | $this->logger->error('Invalid PID ' . $cPid . ' for structure definitions'); |
||
| 1094 | $this->thumbnailLoaded = true; |
||
| 1095 | return $this->thumbnail; |
||
| 1096 | } |
||
| 1097 | // Load extension configuration. |
||
| 1098 | $extConf = GeneralUtility::makeInstance(ExtensionConfiguration::class)->get(self::$extKey); |
||
| 1099 | if (empty($extConf['fileGrpThumbs'])) { |
||
| 1100 | $this->logger->warning('No fileGrp for thumbnails specified'); |
||
| 1101 | $this->thumbnailLoaded = true; |
||
| 1102 | return $this->thumbnail; |
||
| 1103 | } |
||
| 1104 | $strctId = $this->_getToplevelId(); |
||
| 1105 | $metadata = $this->getTitledata($cPid); |
||
| 1106 | |||
| 1107 | $queryBuilder = GeneralUtility::makeInstance(ConnectionPool::class) |
||
| 1108 | ->getQueryBuilderForTable('tx_dlf_structures'); |
||
| 1109 | |||
| 1110 | // Get structure element to get thumbnail from. |
||
| 1111 | $result = $queryBuilder |
||
| 1112 | ->select('tx_dlf_structures.thumbnail AS thumbnail') |
||
| 1113 | ->from('tx_dlf_structures') |
||
| 1114 | ->where( |
||
| 1115 | $queryBuilder->expr()->eq('tx_dlf_structures.pid', intval($cPid)), |
||
| 1116 | $queryBuilder->expr()->eq('tx_dlf_structures.index_name', $queryBuilder->expr()->literal($metadata['type'][0])), |
||
| 1117 | Helper::whereExpression('tx_dlf_structures') |
||
| 1118 | ) |
||
| 1119 | ->setMaxResults(1) |
||
| 1120 | ->execute(); |
||
| 1121 | |||
| 1122 | $allResults = $result->fetchAll(); |
||
| 1123 | |||
| 1124 | if (count($allResults) == 1) { |
||
| 1125 | $resArray = $allResults[0]; |
||
| 1126 | // Get desired thumbnail structure if not the toplevel structure itself. |
||
| 1127 | if (!empty($resArray['thumbnail'])) { |
||
| 1128 | $strctType = Helper::getIndexNameFromUid($resArray['thumbnail'], 'tx_dlf_structures', $cPid); |
||
| 1129 | // Check if this document has a structure element of the desired type. |
||
| 1130 | $strctIds = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@TYPE="' . $strctType . '"]/@ID'); |
||
| 1131 | if (!empty($strctIds)) { |
||
| 1132 | $strctId = (string) $strctIds[0]; |
||
| 1133 | } |
||
| 1134 | } |
||
| 1135 | // Load smLinks. |
||
| 1136 | $this->_getSmLinks(); |
||
| 1137 | // Get thumbnail location. |
||
| 1138 | $fileGrpsThumb = GeneralUtility::trimExplode(',', $extConf['fileGrpThumbs']); |
||
| 1139 | while ($fileGrpThumb = array_shift($fileGrpsThumb)) { |
||
| 1140 | if ( |
||
| 1141 | $this->_getPhysicalStructure() |
||
| 1142 | && !empty($this->smLinks['l2p'][$strctId]) |
||
| 1143 | && !empty($this->physicalStructureInfo[$this->smLinks['l2p'][$strctId][0]]['files'][$fileGrpThumb]) |
||
| 1144 | ) { |
||
| 1145 | $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->smLinks['l2p'][$strctId][0]]['files'][$fileGrpThumb]); |
||
| 1146 | break; |
||
| 1147 | } elseif (!empty($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb])) { |
||
| 1148 | $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$fileGrpThumb]); |
||
| 1149 | break; |
||
| 1150 | } |
||
| 1151 | } |
||
| 1152 | } else { |
||
| 1153 | $this->logger->error('No structure of type "' . $metadata['type'][0] . '" found in database'); |
||
| 1154 | } |
||
| 1155 | $this->thumbnailLoaded = true; |
||
| 1156 | } |
||
| 1157 | return $this->thumbnail; |
||
| 1158 | } |
||
| 1159 | |||
| 1160 | /** |
||
| 1161 | * {@inheritDoc} |
||
| 1162 | * @see \Kitodo\Dlf\Common\Doc::_getToplevelId() |
||
| 1163 | */ |
||
| 1164 | protected function _getToplevelId() |
||
| 1165 | { |
||
| 1166 | if (empty($this->toplevelId)) { |
||
| 1167 | // Get all logical structure nodes with metadata, but without associated METS-Pointers. |
||
| 1168 | $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@DMDID and not(./mets:mptr)]'); |
||
| 1169 | if (!empty($divs)) { |
||
| 1170 | // Load smLinks. |
||
| 1171 | $this->_getSmLinks(); |
||
| 1172 | foreach ($divs as $div) { |
||
| 1173 | $id = (string) $div['ID']; |
||
| 1174 | // Are there physical structure nodes for this logical structure? |
||
| 1175 | if (array_key_exists($id, $this->smLinks['l2p'])) { |
||
| 1176 | // Yes. That's what we're looking for. |
||
| 1177 | $this->toplevelId = $id; |
||
| 1178 | break; |
||
| 1179 | } elseif (empty($this->toplevelId)) { |
||
| 1180 | // No. Remember this anyway, but keep looking for a better one. |
||
| 1181 | $this->toplevelId = $id; |
||
| 1182 | } |
||
| 1183 | } |
||
| 1184 | } |
||
| 1185 | } |
||
| 1186 | return $this->toplevelId; |
||
| 1187 | } |
||
| 1188 | |||
| 1189 | /** |
||
| 1190 | * This magic method is executed prior to any serialization of the object |
||
| 1191 | * @see __wakeup() |
||
| 1192 | * |
||
| 1193 | * @access public |
||
| 1194 | * |
||
| 1195 | * @return array Properties to be serialized |
||
| 1196 | */ |
||
| 1197 | public function __sleep() |
||
| 1202 | } |
||
| 1203 | |||
| 1204 | /** |
||
| 1205 | * This magic method is used for setting a string value for the object |
||
| 1206 | * |
||
| 1207 | * @access public |
||
| 1208 | * |
||
| 1209 | * @return string String representing the METS object |
||
| 1210 | */ |
||
| 1211 | public function __toString() |
||
| 1212 | { |
||
| 1213 | $xml = new \DOMDocument('1.0', 'utf-8'); |
||
| 1214 | $xml->appendChild($xml->importNode(dom_import_simplexml($this->mets), true)); |
||
| 1215 | $xml->formatOutput = true; |
||
| 1216 | return $xml->saveXML(); |
||
| 1217 | } |
||
| 1218 | |||
| 1219 | /** |
||
| 1220 | * This magic method is executed after the object is deserialized |
||
| 1221 | * @see __sleep() |
||
| 1222 | * |
||
| 1223 | * @access public |
||
| 1224 | * |
||
| 1225 | * @return void |
||
| 1226 | */ |
||
| 1227 | public function __wakeup() |
||
| 1238 | } |
||
| 1239 | } |
||
| 1240 | } |
||
| 1241 |
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.