We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.
| Total Complexity | 274 |
| Total Lines | 1951 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like Document 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 Document, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 23 | final class Document { |
||
| 24 | /** |
||
| 25 | * This holds the whole XML file as string for serialization purposes |
||
| 26 | * @see __sleep() / __wakeup() |
||
| 27 | * |
||
| 28 | * @var string |
||
| 29 | * @access protected |
||
| 30 | */ |
||
| 31 | protected $asXML = ''; |
||
| 32 | |||
| 33 | /** |
||
| 34 | * This holds the PID for the configuration |
||
| 35 | * |
||
| 36 | * @var integer |
||
| 37 | * @access protected |
||
| 38 | */ |
||
| 39 | protected $cPid = 0; |
||
| 40 | |||
| 41 | /** |
||
| 42 | * This holds the XML file's dmdSec parts with their IDs as array key |
||
| 43 | * |
||
| 44 | * @var array |
||
| 45 | * @access protected |
||
| 46 | */ |
||
| 47 | protected $dmdSec = []; |
||
| 48 | |||
| 49 | /** |
||
| 50 | * Are the METS file's dmdSecs loaded? |
||
| 51 | * @see $dmdSec |
||
| 52 | * |
||
| 53 | * @var boolean |
||
| 54 | * @access protected |
||
| 55 | */ |
||
| 56 | protected $dmdSecLoaded = FALSE; |
||
| 57 | |||
| 58 | /** |
||
| 59 | * The extension key |
||
| 60 | * |
||
| 61 | * @var string |
||
| 62 | * @access public |
||
| 63 | */ |
||
| 64 | public static $extKey = 'dlf'; |
||
| 65 | |||
| 66 | /** |
||
| 67 | * This holds the file ID -> USE concordance |
||
| 68 | * @see _getFileGrps() |
||
| 69 | * |
||
| 70 | * @var array |
||
| 71 | * @access protected |
||
| 72 | */ |
||
| 73 | protected $fileGrps = []; |
||
| 74 | |||
| 75 | /** |
||
| 76 | * Are the file groups loaded? |
||
| 77 | * @see $fileGrps |
||
| 78 | * |
||
| 79 | * @var boolean |
||
| 80 | * @access protected |
||
| 81 | */ |
||
| 82 | protected $fileGrpsLoaded = FALSE; |
||
| 83 | |||
| 84 | /** |
||
| 85 | * This holds the configuration for all supported metadata encodings |
||
| 86 | * @see loadFormats() |
||
| 87 | * |
||
| 88 | * @var array |
||
| 89 | * @access protected |
||
| 90 | */ |
||
| 91 | protected $formats = [ |
||
| 92 | 'OAI' => [ |
||
| 93 | 'rootElement' => 'OAI-PMH', |
||
| 94 | 'namespaceURI' => 'http://www.openarchives.org/OAI/2.0/', |
||
| 95 | ], |
||
| 96 | 'METS' => [ |
||
| 97 | 'rootElement' => 'mets', |
||
| 98 | 'namespaceURI' => 'http://www.loc.gov/METS/', |
||
| 99 | ], |
||
| 100 | 'XLINK' => [ |
||
| 101 | 'rootElement' => 'xlink', |
||
| 102 | 'namespaceURI' => 'http://www.w3.org/1999/xlink', |
||
| 103 | ] |
||
| 104 | ]; |
||
| 105 | |||
| 106 | /** |
||
| 107 | * Are the available metadata formats loaded? |
||
| 108 | * @see $formats |
||
| 109 | * |
||
| 110 | * @var boolean |
||
| 111 | * @access protected |
||
| 112 | */ |
||
| 113 | protected $formatsLoaded = FALSE; |
||
| 114 | |||
| 115 | /** |
||
| 116 | * Are there any fulltext files available? |
||
| 117 | * |
||
| 118 | * @var boolean |
||
| 119 | * @access protected |
||
| 120 | */ |
||
| 121 | protected $hasFulltext = FALSE; |
||
| 122 | |||
| 123 | /** |
||
| 124 | * Last searched logical and physical page |
||
| 125 | * |
||
| 126 | * @var array |
||
| 127 | * @access protected |
||
| 128 | */ |
||
| 129 | protected $lastSearchedPhysicalPage = ['logicalPage' => NULL, 'physicalPage' => NULL]; |
||
| 130 | |||
| 131 | /** |
||
| 132 | * This holds the documents location |
||
| 133 | * |
||
| 134 | * @var string |
||
| 135 | * @access protected |
||
| 136 | */ |
||
| 137 | protected $location = ''; |
||
| 138 | |||
| 139 | /** |
||
| 140 | * This holds the logical units |
||
| 141 | * |
||
| 142 | * @var array |
||
| 143 | * @access protected |
||
| 144 | */ |
||
| 145 | protected $logicalUnits = []; |
||
| 146 | |||
| 147 | /** |
||
| 148 | * This holds the documents' parsed metadata array with their corresponding structMap//div's ID as array key |
||
| 149 | * |
||
| 150 | * @var array |
||
| 151 | * @access protected |
||
| 152 | */ |
||
| 153 | protected $metadataArray = []; |
||
| 154 | |||
| 155 | /** |
||
| 156 | * Is the metadata array loaded? |
||
| 157 | * @see $metadataArray |
||
| 158 | * |
||
| 159 | * @var boolean |
||
| 160 | * @access protected |
||
| 161 | */ |
||
| 162 | protected $metadataArrayLoaded = FALSE; |
||
| 163 | |||
| 164 | /** |
||
| 165 | * This holds the XML file's METS part as \SimpleXMLElement object |
||
| 166 | * |
||
| 167 | * @var \SimpleXMLElement |
||
| 168 | * @access protected |
||
| 169 | */ |
||
| 170 | protected $mets; |
||
| 171 | |||
| 172 | /** |
||
| 173 | * The holds the total number of pages |
||
| 174 | * |
||
| 175 | * @var integer |
||
| 176 | * @access protected |
||
| 177 | */ |
||
| 178 | protected $numPages = 0; |
||
| 179 | |||
| 180 | /** |
||
| 181 | * This holds the UID of the parent document or zero if not multi-volumed |
||
| 182 | * |
||
| 183 | * @var integer |
||
| 184 | * @access protected |
||
| 185 | */ |
||
| 186 | protected $parentId = 0; |
||
| 187 | |||
| 188 | /** |
||
| 189 | * This holds the physical structure |
||
| 190 | * |
||
| 191 | * @var array |
||
| 192 | * @access protected |
||
| 193 | */ |
||
| 194 | protected $physicalStructure = []; |
||
| 195 | |||
| 196 | /** |
||
| 197 | * This holds the physical structure metadata |
||
| 198 | * |
||
| 199 | * @var array |
||
| 200 | * @access protected |
||
| 201 | */ |
||
| 202 | protected $physicalStructureInfo = []; |
||
| 203 | |||
| 204 | /** |
||
| 205 | * Is the physical structure loaded? |
||
| 206 | * @see $physicalStructure |
||
| 207 | * |
||
| 208 | * @var boolean |
||
| 209 | * @access protected |
||
| 210 | */ |
||
| 211 | protected $physicalStructureLoaded = FALSE; |
||
| 212 | |||
| 213 | /** |
||
| 214 | * This holds the PID of the document or zero if not in database |
||
| 215 | * |
||
| 216 | * @var integer |
||
| 217 | * @access protected |
||
| 218 | */ |
||
| 219 | protected $pid = 0; |
||
| 220 | |||
| 221 | /** |
||
| 222 | * This holds the documents' raw text pages with their corresponding structMap//div's ID as array key |
||
| 223 | * |
||
| 224 | * @var array |
||
| 225 | * @access protected |
||
| 226 | */ |
||
| 227 | protected $rawTextArray = []; |
||
| 228 | |||
| 229 | /** |
||
| 230 | * Is the document instantiated successfully? |
||
| 231 | * |
||
| 232 | * @var boolean |
||
| 233 | * @access protected |
||
| 234 | */ |
||
| 235 | protected $ready = FALSE; |
||
| 236 | |||
| 237 | /** |
||
| 238 | * The METS file's record identifier |
||
| 239 | * |
||
| 240 | * @var string |
||
| 241 | * @access protected |
||
| 242 | */ |
||
| 243 | protected $recordId; |
||
| 244 | |||
| 245 | /** |
||
| 246 | * This holds the singleton object of the document |
||
| 247 | * |
||
| 248 | * @var array (\Kitodo\Dlf\Common\Document) |
||
| 249 | * @access protected |
||
| 250 | */ |
||
| 251 | protected static $registry = []; |
||
| 252 | |||
| 253 | /** |
||
| 254 | * This holds the UID of the root document or zero if not multi-volumed |
||
| 255 | * |
||
| 256 | * @var integer |
||
| 257 | * @access protected |
||
| 258 | */ |
||
| 259 | protected $rootId = 0; |
||
| 260 | |||
| 261 | /** |
||
| 262 | * Is the root id loaded? |
||
| 263 | * @see $rootId |
||
| 264 | * |
||
| 265 | * @var boolean |
||
| 266 | * @access protected |
||
| 267 | */ |
||
| 268 | protected $rootIdLoaded = FALSE; |
||
| 269 | |||
| 270 | /** |
||
| 271 | * This holds the smLinks between logical and physical structMap |
||
| 272 | * |
||
| 273 | * @var array |
||
| 274 | * @access protected |
||
| 275 | */ |
||
| 276 | protected $smLinks = ['l2p' => [], 'p2l' => []]; |
||
| 277 | |||
| 278 | /** |
||
| 279 | * Are the smLinks loaded? |
||
| 280 | * @see $smLinks |
||
| 281 | * |
||
| 282 | * @var boolean |
||
| 283 | * @access protected |
||
| 284 | */ |
||
| 285 | protected $smLinksLoaded = FALSE; |
||
| 286 | |||
| 287 | /** |
||
| 288 | * This holds the logical structure |
||
| 289 | * |
||
| 290 | * @var array |
||
| 291 | * @access protected |
||
| 292 | */ |
||
| 293 | protected $tableOfContents = []; |
||
| 294 | |||
| 295 | /** |
||
| 296 | * Is the table of contents loaded? |
||
| 297 | * @see $tableOfContents |
||
| 298 | * |
||
| 299 | * @var boolean |
||
| 300 | * @access protected |
||
| 301 | */ |
||
| 302 | protected $tableOfContentsLoaded = FALSE; |
||
| 303 | |||
| 304 | /** |
||
| 305 | * This holds the document's thumbnail location. |
||
| 306 | * |
||
| 307 | * @var string |
||
| 308 | * @access protected |
||
| 309 | */ |
||
| 310 | protected $thumbnail = ''; |
||
| 311 | |||
| 312 | /** |
||
| 313 | * Is the document's thumbnail location loaded? |
||
| 314 | * @see $thumbnail |
||
| 315 | * |
||
| 316 | * @var boolean |
||
| 317 | * @access protected |
||
| 318 | */ |
||
| 319 | protected $thumbnailLoaded = FALSE; |
||
| 320 | |||
| 321 | /** |
||
| 322 | * This holds the toplevel structure's @ID |
||
| 323 | * |
||
| 324 | * @var string |
||
| 325 | * @access protected |
||
| 326 | */ |
||
| 327 | protected $toplevelId = ''; |
||
| 328 | |||
| 329 | /** |
||
| 330 | * This holds the UID or the URL of the document |
||
| 331 | * |
||
| 332 | * @var mixed |
||
| 333 | * @access protected |
||
| 334 | */ |
||
| 335 | protected $uid = 0; |
||
| 336 | |||
| 337 | /** |
||
| 338 | * This holds the whole XML file as \SimpleXMLElement object |
||
| 339 | * |
||
| 340 | * @var \SimpleXMLElement |
||
| 341 | * @access protected |
||
| 342 | */ |
||
| 343 | protected $xml; |
||
| 344 | |||
| 345 | /** |
||
| 346 | * This clears the static registry to prevent memory exhaustion |
||
| 347 | * |
||
| 348 | * @access public |
||
| 349 | * |
||
| 350 | * @return void |
||
| 351 | */ |
||
| 352 | public static function clearRegistry() { |
||
| 353 | // Reset registry array. |
||
| 354 | self::$registry = []; |
||
| 355 | } |
||
| 356 | |||
| 357 | /** |
||
| 358 | * This gets the location of a file representing a physical page or track |
||
| 359 | * |
||
| 360 | * @access public |
||
| 361 | * |
||
| 362 | * @param string $id: The @ID attribute of the file node |
||
| 363 | * |
||
| 364 | * @return string The file's location as URL |
||
| 365 | */ |
||
| 366 | public function getFileLocation($id) { |
||
| 373 | } |
||
| 374 | } |
||
| 375 | |||
| 376 | /** |
||
| 377 | * This gets the MIME type of a file representing a physical page or track |
||
| 378 | * |
||
| 379 | * @access public |
||
| 380 | * |
||
| 381 | * @param string $id: The @ID attribute of the file node |
||
| 382 | * |
||
| 383 | * @return string The file's MIME type |
||
| 384 | */ |
||
| 385 | public function getFileMimeType($id) { |
||
| 386 | if (!empty($id) |
||
| 387 | && ($mimetype = $this->mets->xpath('./mets:fileSec/mets:fileGrp/mets:file[@ID="'.$id.'"]/@MIMETYPE'))) { |
||
| 388 | return (string) $mimetype[0]; |
||
| 389 | } else { |
||
| 390 | Helper::devLog('There is no file node with @ID "'.$id.'" or no MIME type specified', DEVLOG_SEVERITY_WARNING); |
||
| 391 | return ''; |
||
| 392 | } |
||
| 393 | } |
||
| 394 | |||
| 395 | /** |
||
| 396 | * This is a singleton class, thus an instance must be created by this method |
||
| 397 | * |
||
| 398 | * @access public |
||
| 399 | * |
||
| 400 | * @param mixed $uid: The unique identifier of the document to parse or URL of XML file |
||
| 401 | * @param integer $pid: If > 0, then only document with this PID gets loaded |
||
| 402 | * @param boolean $forceReload: Force reloading the document instead of returning the cached instance |
||
| 403 | * |
||
| 404 | * @return \Kitodo\Dlf\Common\Document Instance of this class |
||
| 405 | */ |
||
| 406 | public static function &getInstance($uid, $pid = 0, $forceReload = FALSE) { |
||
| 407 | // Sanitize input. |
||
| 408 | $pid = max(intval($pid), 0); |
||
| 409 | if (!$forceReload) { |
||
| 410 | $regObj = md5($uid); |
||
| 411 | if (is_object(self::$registry[$regObj]) |
||
| 412 | && self::$registry[$regObj] instanceof self) { |
||
| 413 | // Check if instance has given PID. |
||
| 414 | if (!$pid |
||
| 415 | || !self::$registry[$regObj]->pid |
||
| 416 | || $pid == self::$registry[$regObj]->pid) { |
||
| 417 | // Return singleton instance if available. |
||
| 418 | return self::$registry[$regObj]; |
||
| 419 | } |
||
| 420 | } else { |
||
| 421 | // Check the user's session... |
||
| 422 | $sessionData = Helper::loadFromSession(get_called_class()); |
||
| 423 | if (is_object($sessionData[$regObj]) |
||
| 424 | && $sessionData[$regObj] instanceof self) { |
||
| 425 | // Check if instance has given PID. |
||
| 426 | if (!$pid |
||
| 427 | || !$sessionData[$regObj]->pid |
||
| 428 | || $pid == $sessionData[$regObj]->pid) { |
||
| 429 | // ...and restore registry. |
||
| 430 | self::$registry[$regObj] = $sessionData[$regObj]; |
||
| 431 | return self::$registry[$regObj]; |
||
| 432 | } |
||
| 433 | } |
||
| 434 | } |
||
| 435 | } |
||
| 436 | // Create new instance... |
||
| 437 | $instance = new self($uid, $pid); |
||
| 438 | // ...and save it to registry. |
||
| 439 | if ($instance->ready) { |
||
| 440 | self::$registry[md5($instance->uid)] = $instance; |
||
| 441 | if ($instance->uid != $instance->location) { |
||
| 442 | self::$registry[md5($instance->location)] = $instance; |
||
| 443 | } |
||
| 444 | // Load extension configuration |
||
| 445 | $extConf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf']['dlf']); |
||
| 446 | // Save registry to session if caching is enabled. |
||
| 447 | if (!empty($extConf['caching'])) { |
||
| 448 | Helper::saveToSession(self::$registry, get_class($instance)); |
||
| 449 | } |
||
| 450 | } |
||
| 451 | // Return new instance. |
||
| 452 | return $instance; |
||
| 453 | } |
||
| 454 | |||
| 455 | /** |
||
| 456 | * This gets details about a logical structure element |
||
| 457 | * |
||
| 458 | * @access public |
||
| 459 | * |
||
| 460 | * @param string $id: The @ID attribute of the logical structure node |
||
| 461 | * @param boolean $recursive: Whether to include the child elements |
||
| 462 | * |
||
| 463 | * @return array Array of the element's id, label, type and physical page indexes/mptr link |
||
| 464 | */ |
||
| 465 | public function getLogicalStructure($id, $recursive = FALSE) { |
||
| 466 | $details = []; |
||
| 467 | // Is the requested logical unit already loaded? |
||
| 468 | if (!$recursive |
||
| 469 | && !empty($this->logicalUnits[$id])) { |
||
| 470 | // Yes. Return it. |
||
| 471 | return $this->logicalUnits[$id]; |
||
| 472 | } elseif (!empty($id)) { |
||
| 473 | // Get specified logical unit. |
||
| 474 | $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="'.$id.'"]'); |
||
| 475 | } else { |
||
| 476 | // Get all logical units at top level. |
||
| 477 | $divs = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]/mets:div'); |
||
| 478 | } |
||
| 479 | if (!empty($divs)) { |
||
| 480 | if (!$recursive) { |
||
| 481 | // Get the details for the first xpath hit. |
||
| 482 | $details = $this->getLogicalStructureInfo($divs[0]); |
||
| 483 | } else { |
||
| 484 | // Walk the logical structure recursively and fill the whole table of contents. |
||
| 485 | foreach ($divs as $div) { |
||
| 486 | $this->tableOfContents[] = $this->getLogicalStructureInfo($div, TRUE); |
||
| 487 | } |
||
| 488 | } |
||
| 489 | } |
||
| 490 | return $details; |
||
| 491 | } |
||
| 492 | |||
| 493 | /** |
||
| 494 | * This gets details about a logical structure element |
||
| 495 | * |
||
| 496 | * @access protected |
||
| 497 | * |
||
| 498 | * @param \SimpleXMLElement $structure: The logical structure node |
||
| 499 | * @param boolean $recursive: Whether to include the child elements |
||
| 500 | * |
||
| 501 | * @return array Array of the element's id, label, type and physical page indexes/mptr link |
||
| 502 | */ |
||
| 503 | protected function getLogicalStructureInfo(\SimpleXMLElement $structure, $recursive = FALSE) { |
||
| 577 | } |
||
| 578 | |||
| 579 | /** |
||
| 580 | * This extracts all the metadata for a logical structure node |
||
| 581 | * |
||
| 582 | * @access public |
||
| 583 | * |
||
| 584 | * @param string $id: The @ID attribute of the logical structure node |
||
| 585 | * @param integer $cPid: The PID for the metadata definitions |
||
| 586 | * (defaults to $this->cPid or $this->pid) |
||
| 587 | * |
||
| 588 | * @return array The logical structure node's parsed metadata array |
||
| 589 | */ |
||
| 590 | public function getMetadata($id, $cPid = 0) { |
||
| 591 | // Make sure $cPid is a non-negative integer. |
||
| 592 | $cPid = max(intval($cPid), 0); |
||
| 593 | // If $cPid is not given, try to get it elsewhere. |
||
| 594 | if (!$cPid |
||
| 595 | && ($this->cPid || $this->pid)) { |
||
| 596 | // Retain current PID. |
||
| 597 | $cPid = ($this->cPid ? $this->cPid : $this->pid); |
||
| 598 | } elseif (!$cPid) { |
||
| 599 | Helper::devLog('Invalid PID '.$cPid.' for metadata definitions', DEVLOG_SEVERITY_WARNING); |
||
| 600 | return []; |
||
| 601 | } |
||
| 602 | // Get metadata from parsed metadata array if available. |
||
| 603 | if (!empty($this->metadataArray[$id]) |
||
| 604 | && $this->metadataArray[0] == $cPid) { |
||
| 605 | return $this->metadataArray[$id]; |
||
| 606 | } |
||
| 607 | // Initialize metadata array with empty values. |
||
| 608 | $metadata = [ |
||
| 609 | 'title' => [], |
||
| 610 | 'title_sorting' => [], |
||
| 611 | 'author' => [], |
||
| 612 | 'place' => [], |
||
| 613 | 'year' => [], |
||
| 614 | 'prod_id' => [], |
||
| 615 | 'record_id' => [], |
||
| 616 | 'opac_id' => [], |
||
| 617 | 'union_id' => [], |
||
| 618 | 'urn' => [], |
||
| 619 | 'purl' => [], |
||
| 620 | 'type' => [], |
||
| 621 | 'volume' => [], |
||
| 622 | 'volume_sorting' => [], |
||
| 623 | 'collection' => [], |
||
| 624 | 'owner' => [], |
||
| 625 | ]; |
||
| 626 | // Get the logical structure node's DMDID. |
||
| 627 | if (!empty($this->logicalUnits[$id])) { |
||
| 628 | $dmdId = $this->logicalUnits[$id]['dmdId']; |
||
| 629 | } else { |
||
| 630 | $dmdId = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="'.$id.'"]/@DMDID'); |
||
| 631 | $dmdId = (string) $dmdId[0]; |
||
| 632 | } |
||
| 633 | if (!empty($dmdId)) { |
||
| 634 | // Load available metadata formats and dmdSecs. |
||
| 635 | $this->loadFormats(); |
||
| 636 | $this->_getDmdSec(); |
||
| 637 | // Is this metadata format supported? |
||
| 638 | if (!empty($this->formats[$this->dmdSec[$dmdId]['type']])) { |
||
| 639 | if (!empty($this->formats[$this->dmdSec[$dmdId]['type']]['class'])) { |
||
| 640 | $class = $this->formats[$this->dmdSec[$dmdId]['type']]['class']; |
||
| 641 | // Get the metadata from class. |
||
| 642 | if (class_exists($class) |
||
| 643 | && ($obj = \TYPO3\CMS\Core\Utility\GeneralUtility::makeInstance($class)) instanceof MetadataInterface) { |
||
| 644 | $obj->extractMetadata($this->dmdSec[$dmdId]['xml'], $metadata); |
||
| 645 | } else { |
||
| 646 | Helper::devLog('Invalid class/method "'.$class.'->extractMetadata()" for metadata format "'.$this->dmdSec[$dmdId]['type'].'"', DEVLOG_SEVERITY_WARNING); |
||
| 647 | } |
||
| 648 | } |
||
| 649 | } else { |
||
| 650 | Helper::devLog('Unsupported metadata format "'.$this->dmdSec[$dmdId]['type'].'" in dmdSec with @ID "'.$dmdId.'"', DEVLOG_SEVERITY_WARNING); |
||
| 651 | return []; |
||
| 652 | } |
||
| 653 | // Get the structure's type. |
||
| 654 | if (!empty($this->logicalUnits[$id])) { |
||
| 655 | $metadata['type'] = [$this->logicalUnits[$id]['type']]; |
||
| 656 | } else { |
||
| 657 | $struct = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="'.$id.'"]/@TYPE'); |
||
| 658 | $metadata['type'] = [(string) $struct[0]]; |
||
| 659 | } |
||
| 660 | // Get the additional metadata from database. |
||
| 661 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 662 | 'tx_dlf_metadata.index_name AS index_name,tx_dlf_metadataformat.xpath AS xpath,tx_dlf_metadataformat.xpath_sorting AS xpath_sorting,tx_dlf_metadata.is_sortable AS is_sortable,tx_dlf_metadata.default_value AS default_value,tx_dlf_metadata.format AS format', |
||
| 663 | 'tx_dlf_metadata,tx_dlf_metadataformat,tx_dlf_formats', |
||
| 664 | 'tx_dlf_metadata.pid='.$cPid |
||
| 665 | .' AND tx_dlf_metadataformat.pid='.$cPid |
||
| 666 | .' AND ((tx_dlf_metadata.uid=tx_dlf_metadataformat.parent_id AND tx_dlf_metadataformat.encoded=tx_dlf_formats.uid AND tx_dlf_formats.type='.$GLOBALS['TYPO3_DB']->fullQuoteStr($this->dmdSec[$dmdId]['type'], 'tx_dlf_formats').') OR tx_dlf_metadata.format=0)' |
||
| 667 | .Helper::whereClause('tx_dlf_metadata', TRUE) |
||
| 668 | .Helper::whereClause('tx_dlf_metadataformat') |
||
| 669 | .Helper::whereClause('tx_dlf_formats'), |
||
| 670 | '', |
||
| 671 | '', |
||
| 672 | '' |
||
| 673 | ); |
||
| 674 | // We need a \DOMDocument here, because SimpleXML doesn't support XPath functions properly. |
||
| 675 | $domNode = dom_import_simplexml($this->dmdSec[$dmdId]['xml']); |
||
| 676 | $domXPath = new \DOMXPath($domNode->ownerDocument); |
||
| 677 | $this->registerNamespaces($domXPath); |
||
| 678 | // OK, now make the XPath queries. |
||
| 679 | while ($resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result)) { |
||
| 680 | // Set metadata field's value(s). |
||
| 681 | if ($resArray['format'] > 0 |
||
| 682 | && !empty($resArray['xpath']) |
||
| 683 | && ($values = $domXPath->evaluate($resArray['xpath'], $domNode))) { |
||
| 684 | if ($values instanceof \DOMNodeList |
||
| 685 | && $values->length > 0) { |
||
| 686 | $metadata[$resArray['index_name']] = []; |
||
| 687 | foreach ($values as $value) { |
||
| 688 | $metadata[$resArray['index_name']][] = trim((string) $value->nodeValue); |
||
| 689 | } |
||
| 690 | } elseif (!($values instanceof \DOMNodeList)) { |
||
| 691 | $metadata[$resArray['index_name']] = [trim((string) $values)]; |
||
| 692 | } |
||
| 693 | } |
||
| 694 | // Set default value if applicable. |
||
| 695 | // '!empty($resArray['default_value'])' is not possible, because '0' is a valid default value. |
||
| 696 | // Setting an empty default value creates a lot of empty fields within the index. |
||
| 697 | // These empty fields are then shown within the search facets as 'empty'. |
||
| 698 | if (empty($metadata[$resArray['index_name']][0]) |
||
| 699 | && strlen($resArray['default_value']) > 0) { |
||
| 700 | $metadata[$resArray['index_name']] = [$resArray['default_value']]; |
||
| 701 | } |
||
| 702 | // Set sorting value if applicable. |
||
| 703 | if (!empty($metadata[$resArray['index_name']]) |
||
| 704 | && $resArray['is_sortable']) { |
||
| 705 | if ($resArray['format'] > 0 |
||
| 706 | && !empty($resArray['xpath_sorting']) |
||
| 707 | && ($values = $domXPath->evaluate($resArray['xpath_sorting'], $domNode))) { |
||
| 708 | if ($values instanceof \DOMNodeList |
||
| 709 | && $values->length > 0) { |
||
| 710 | $metadata[$resArray['index_name'].'_sorting'][0] = trim((string) $values->item(0)->nodeValue); |
||
| 711 | } elseif (!($values instanceof \DOMNodeList)) { |
||
| 712 | $metadata[$resArray['index_name'].'_sorting'][0] = trim((string) $values); |
||
| 713 | } |
||
| 714 | } |
||
| 715 | if (empty($metadata[$resArray['index_name'].'_sorting'][0])) { |
||
| 716 | $metadata[$resArray['index_name'].'_sorting'][0] = $metadata[$resArray['index_name']][0]; |
||
| 717 | } |
||
| 718 | } |
||
| 719 | } |
||
| 720 | // Set title to empty string if not present. |
||
| 721 | if (empty($metadata['title'][0])) { |
||
| 722 | $metadata['title'][0] = ''; |
||
| 723 | $metadata['title_sorting'][0] = ''; |
||
| 724 | } |
||
| 725 | // Add collections from database to toplevel element if document is already saved. |
||
| 726 | if (\TYPO3\CMS\Core\Utility\MathUtility::canBeInterpretedAsInteger($this->uid) |
||
| 727 | && $id == $this->_getToplevelId()) { |
||
| 728 | $result = $GLOBALS['TYPO3_DB']->exec_SELECT_mm_query( |
||
| 729 | 'tx_dlf_collections.index_name AS index_name', |
||
| 730 | 'tx_dlf_documents', |
||
| 731 | 'tx_dlf_relations', |
||
| 732 | 'tx_dlf_collections', |
||
| 733 | 'AND tx_dlf_collections.pid='.intval($cPid) |
||
| 734 | .' AND tx_dlf_documents.uid='.intval($this->uid) |
||
| 735 | .' AND tx_dlf_relations.ident='.$GLOBALS['TYPO3_DB']->fullQuoteStr('docs_colls', 'tx_dlf_relations') |
||
| 736 | .' AND tx_dlf_collections.sys_language_uid IN (-1,0)' |
||
| 737 | .Helper::whereClause('tx_dlf_documents') |
||
| 738 | .Helper::whereClause('tx_dlf_collections'), |
||
| 739 | 'tx_dlf_collections.index_name', |
||
| 740 | '', |
||
| 741 | '' |
||
| 742 | ); |
||
| 743 | while ($resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result)) { |
||
| 744 | if (!in_array($resArray['index_name'], $metadata['collection'])) { |
||
| 745 | $metadata['collection'][] = $resArray['index_name']; |
||
| 746 | } |
||
| 747 | } |
||
| 748 | } |
||
| 749 | } else { |
||
| 750 | // There is no dmdSec for this structure node. |
||
| 751 | return []; |
||
| 752 | } |
||
| 753 | return $metadata; |
||
| 754 | } |
||
| 755 | |||
| 756 | /** |
||
| 757 | * This returns the first corresponding physical page number of a given logical page label |
||
| 758 | * |
||
| 759 | * @access public |
||
| 760 | * |
||
| 761 | * @param string $logicalPage: The label (or a part of the label) of the logical page |
||
| 762 | * |
||
| 763 | * @return integer The physical page number |
||
| 764 | */ |
||
| 765 | public function getPhysicalPage($logicalPage) { |
||
| 766 | if (!empty($this->lastSearchedPhysicalPage['logicalPage']) |
||
| 767 | && $this->lastSearchedPhysicalPage['logicalPage'] == $logicalPage) { |
||
| 768 | return $this->lastSearchedPhysicalPage['physicalPage']; |
||
| 769 | } else { |
||
| 770 | $physicalPage = 0; |
||
| 771 | foreach ($this->physicalStructureInfo as $page) { |
||
| 772 | if (strpos($page['orderlabel'], $logicalPage) !== FALSE) { |
||
| 773 | $this->lastSearchedPhysicalPage['logicalPage'] = $logicalPage; |
||
| 774 | $this->lastSearchedPhysicalPage['physicalPage'] = $physicalPage; |
||
| 775 | return $physicalPage; |
||
| 776 | } |
||
| 777 | $physicalPage++; |
||
| 778 | } |
||
| 779 | } |
||
| 780 | return 1; |
||
| 781 | } |
||
| 782 | |||
| 783 | /** |
||
| 784 | * This extracts the raw text for a physical structure node |
||
| 785 | * |
||
| 786 | * @access public |
||
| 787 | * |
||
| 788 | * @param string $id: The @ID attribute of the physical structure node |
||
| 789 | * |
||
| 790 | * @return string The physical structure node's raw text |
||
| 791 | */ |
||
| 792 | public function getRawText($id) { |
||
| 793 | $rawText = ''; |
||
| 794 | // Get text from raw text array if available. |
||
| 795 | if (!empty($this->rawTextArray[$id])) { |
||
| 796 | return $this->rawTextArray[$id]; |
||
| 797 | } |
||
| 798 | // Load fileGrps and check for fulltext files. |
||
| 799 | $this->_getFileGrps(); |
||
| 800 | if ($this->hasFulltext) { |
||
| 801 | // Load available text formats, ... |
||
| 802 | $this->loadFormats(); |
||
| 803 | // ... physical structure ... |
||
| 804 | $this->_getPhysicalStructure(); |
||
| 805 | // ... and extension configuration. |
||
| 806 | $extConf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf'][self::$extKey]); |
||
| 807 | if (!empty($this->physicalStructureInfo[$id])) { |
||
| 808 | // Get fulltext file. |
||
| 809 | $file = $this->getFileLocation($this->physicalStructureInfo[$id]['files'][$extConf['fileGrpFulltext']]); |
||
| 810 | // Turn off libxml's error logging. |
||
| 811 | $libxmlErrors = libxml_use_internal_errors(TRUE); |
||
| 812 | // Disables the functionality to allow external entities to be loaded when parsing the XML, must be kept. |
||
| 813 | $previousValueOfEntityLoader = libxml_disable_entity_loader(TRUE); |
||
| 814 | // Load XML from file. |
||
| 815 | $rawTextXml = simplexml_load_string(\TYPO3\CMS\Core\Utility\GeneralUtility::getUrl($file)); |
||
| 816 | // Reset entity loader setting. |
||
| 817 | libxml_disable_entity_loader($previousValueOfEntityLoader); |
||
| 818 | // Reset libxml's error logging. |
||
| 819 | libxml_use_internal_errors($libxmlErrors); |
||
| 820 | // Get the root element's name as text format. |
||
| 821 | $textFormat = strtoupper($rawTextXml->getName()); |
||
| 822 | } else { |
||
| 823 | Helper::devLog('Invalid structure node @ID "'.$id.'"', DEVLOG_SEVERITY_WARNING); |
||
| 824 | return $rawText; |
||
| 825 | } |
||
| 826 | // Is this text format supported? |
||
| 827 | if (!empty($this->formats[$textFormat])) { |
||
| 828 | if (!empty($this->formats[$textFormat]['class'])) { |
||
| 829 | $class = $this->formats[$textFormat]['class']; |
||
| 830 | // Get the raw text from class. |
||
| 831 | if (class_exists($class) |
||
| 832 | && ($obj = \TYPO3\CMS\Core\Utility\GeneralUtility::makeInstance($class)) instanceof FulltextInterface) { |
||
| 833 | $rawText = $obj->getRawText($rawTextXml); |
||
| 834 | $this->rawTextArray[$id] = $rawText; |
||
| 835 | } else { |
||
| 836 | Helper::devLog('Invalid class/method "'.$class.'->getRawText()" for text format "'.$textFormat.'"', DEVLOG_SEVERITY_WARNING); |
||
| 837 | } |
||
| 838 | } |
||
| 839 | } else { |
||
| 840 | Helper::devLog('Unsupported text format "'.$textFormat.'" in physical node with @ID "'.$id.'"', DEVLOG_SEVERITY_WARNING); |
||
| 841 | } |
||
| 842 | } |
||
| 843 | return $rawText; |
||
| 844 | } |
||
| 845 | |||
| 846 | /** |
||
| 847 | * This determines a title for the given document |
||
| 848 | * |
||
| 849 | * @access public |
||
| 850 | * |
||
| 851 | * @param integer $uid: The UID of the document |
||
| 852 | * @param boolean $recursive: Search superior documents for a title, too? |
||
| 853 | * |
||
| 854 | * @return string The title of the document itself or a parent document |
||
| 855 | */ |
||
| 856 | public static function getTitle($uid, $recursive = FALSE) { |
||
| 857 | $title = ''; |
||
| 858 | // Sanitize input. |
||
| 859 | $uid = max(intval($uid), 0); |
||
| 860 | if ($uid) { |
||
| 861 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 862 | 'tx_dlf_documents.title,tx_dlf_documents.partof', |
||
| 863 | 'tx_dlf_documents', |
||
| 864 | 'tx_dlf_documents.uid='.$uid |
||
| 865 | .Helper::whereClause('tx_dlf_documents'), |
||
| 866 | '', |
||
| 867 | '', |
||
| 868 | '1' |
||
| 869 | ); |
||
| 870 | if ($GLOBALS['TYPO3_DB']->sql_num_rows($result)) { |
||
| 871 | // Get title information. |
||
| 872 | list ($title, $partof) = $GLOBALS['TYPO3_DB']->sql_fetch_row($result); |
||
| 873 | // Search parent documents recursively for a title? |
||
| 874 | if ($recursive |
||
| 875 | && empty($title) |
||
| 876 | && intval($partof) |
||
| 877 | && $partof != $uid) { |
||
| 878 | $title = self::getTitle($partof, TRUE); |
||
| 879 | } |
||
| 880 | } else { |
||
| 881 | Helper::devLog('No document with UID '.$uid.' found or document not accessible', DEVLOG_SEVERITY_WARNING); |
||
| 882 | } |
||
| 883 | } else { |
||
| 884 | Helper::devLog('Invalid UID '.$uid.' for document', DEVLOG_SEVERITY_ERROR); |
||
| 885 | } |
||
| 886 | return $title; |
||
| 887 | } |
||
| 888 | |||
| 889 | /** |
||
| 890 | * This extracts all the metadata for the toplevel logical structure node |
||
| 891 | * |
||
| 892 | * @access public |
||
| 893 | * |
||
| 894 | * @param integer $cPid: The PID for the metadata definitions |
||
| 895 | * |
||
| 896 | * @return array The logical structure node's parsed metadata array |
||
| 897 | */ |
||
| 898 | public function getTitledata($cPid = 0) { |
||
| 899 | $titledata = $this->getMetadata($this->_getToplevelId(), $cPid); |
||
| 900 | // Set record identifier for METS file if not present. |
||
| 901 | if (is_array($titledata) |
||
| 902 | && array_key_exists('record_id', $titledata)) { |
||
| 903 | if (!empty($this->recordId) |
||
| 904 | && !in_array($this->recordId, $titledata['record_id'])) { |
||
| 905 | array_unshift($titledata['record_id'], $this->recordId); |
||
| 906 | } |
||
| 907 | } |
||
| 908 | return $titledata; |
||
| 909 | } |
||
| 910 | |||
| 911 | /** |
||
| 912 | * This sets some basic class properties |
||
| 913 | * |
||
| 914 | * @access protected |
||
| 915 | * |
||
| 916 | * @return void |
||
| 917 | */ |
||
| 918 | protected function init() { |
||
| 919 | // Get METS node from XML file. |
||
| 920 | $this->registerNamespaces($this->xml); |
||
| 921 | $mets = $this->xml->xpath('//mets:mets'); |
||
| 922 | if ($mets) { |
||
| 923 | $this->mets = $mets[0]; |
||
| 924 | // Register namespaces. |
||
| 925 | $this->registerNamespaces($this->mets); |
||
| 926 | } else { |
||
| 927 | Helper::devLog('No METS part found in document with UID '.$this->uid, DEVLOG_SEVERITY_ERROR); |
||
| 928 | } |
||
| 929 | } |
||
| 930 | |||
| 931 | /** |
||
| 932 | * Load XML file from URL |
||
| 933 | * |
||
| 934 | * @access protected |
||
| 935 | * |
||
| 936 | * @param string $location: The URL of the file to load |
||
| 937 | * |
||
| 938 | * @return boolean TRUE on success or FALSE on failure |
||
| 939 | */ |
||
| 940 | protected function load($location) { |
||
| 941 | // Load XML file. |
||
| 942 | if (\TYPO3\CMS\Core\Utility\GeneralUtility::isValidUrl($location)) { |
||
| 943 | // Load extension configuration |
||
| 944 | $extConf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf']['dlf']); |
||
| 945 | // Set user-agent to identify self when fetching XML data. |
||
| 946 | if (!empty($extConf['useragent'])) { |
||
| 947 | @ini_set('user_agent', $extConf['useragent']); |
||
|
1 ignored issue
–
show
|
|||
| 948 | } |
||
| 949 | // Turn off libxml's error logging. |
||
| 950 | $libxmlErrors = libxml_use_internal_errors(TRUE); |
||
| 951 | // Disables the functionality to allow external entities to be loaded when parsing the XML, must be kept |
||
| 952 | $previousValueOfEntityLoader = libxml_disable_entity_loader(TRUE); |
||
| 953 | // Load XML from file. |
||
| 954 | $xml = simplexml_load_string(\TYPO3\CMS\Core\Utility\GeneralUtility::getUrl($location)); |
||
| 955 | // reset entity loader setting |
||
| 956 | libxml_disable_entity_loader($previousValueOfEntityLoader); |
||
| 957 | // Reset libxml's error logging. |
||
| 958 | libxml_use_internal_errors($libxmlErrors); |
||
| 959 | // Set some basic properties. |
||
| 960 | if ($xml !== FALSE) { |
||
| 961 | $this->xml = $xml; |
||
| 962 | return TRUE; |
||
| 963 | } else { |
||
| 964 | Helper::devLog('Could not load XML file from "'.$location.'"', DEVLOG_SEVERITY_ERROR); |
||
| 965 | } |
||
| 966 | } else { |
||
| 967 | Helper::devLog('Invalid file location "'.$location.'" for document loading', DEVLOG_SEVERITY_ERROR); |
||
| 968 | } |
||
| 969 | return FALSE; |
||
| 970 | } |
||
| 971 | |||
| 972 | /** |
||
| 973 | * Register all available data formats |
||
| 974 | * |
||
| 975 | * @access protected |
||
| 976 | * |
||
| 977 | * @return void |
||
| 978 | */ |
||
| 979 | protected function loadFormats() { |
||
| 980 | if (!$this->formatsLoaded) { |
||
| 981 | // Get available data formats from database. |
||
| 982 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 983 | 'tx_dlf_formats.type AS type,tx_dlf_formats.root AS root,tx_dlf_formats.namespace AS namespace,tx_dlf_formats.class AS class', |
||
| 984 | 'tx_dlf_formats', |
||
| 985 | 'tx_dlf_formats.pid=0' |
||
| 986 | .Helper::whereClause('tx_dlf_formats'), |
||
| 987 | '', |
||
| 988 | '', |
||
| 989 | '' |
||
| 990 | ); |
||
| 991 | while ($resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result)) { |
||
| 992 | // Update format registry. |
||
| 993 | $this->formats[$resArray['type']] = [ |
||
| 994 | 'rootElement' => $resArray['root'], |
||
| 995 | 'namespaceURI' => $resArray['namespace'], |
||
| 996 | 'class' => $resArray['class'] |
||
| 997 | ]; |
||
| 998 | } |
||
| 999 | $this->formatsLoaded = TRUE; |
||
| 1000 | } |
||
| 1001 | } |
||
| 1002 | |||
| 1003 | /** |
||
| 1004 | * Register all available namespaces for a \SimpleXMLElement object |
||
| 1005 | * |
||
| 1006 | * @access public |
||
| 1007 | * |
||
| 1008 | * @param \SimpleXMLElement|\DOMXPath &$obj: \SimpleXMLElement or \DOMXPath object |
||
| 1009 | * |
||
| 1010 | * @return void |
||
| 1011 | */ |
||
| 1012 | public function registerNamespaces(&$obj) { |
||
| 1013 | $this->loadFormats(); |
||
| 1014 | // Do we have a \SimpleXMLElement or \DOMXPath object? |
||
| 1015 | if ($obj instanceof \SimpleXMLElement) { |
||
| 1016 | $method = 'registerXPathNamespace'; |
||
| 1017 | } elseif ($obj instanceof \DOMXPath) { |
||
| 1018 | $method = 'registerNamespace'; |
||
| 1019 | } else { |
||
| 1020 | Helper::devLog('Given object is neither a SimpleXMLElement nor a DOMXPath instance', DEVLOG_SEVERITY_ERROR); |
||
| 1021 | return; |
||
| 1022 | } |
||
| 1023 | // Register metadata format's namespaces. |
||
| 1024 | foreach ($this->formats as $enc => $conf) { |
||
| 1025 | $obj->$method(strtolower($enc), $conf['namespaceURI']); |
||
| 1026 | } |
||
| 1027 | } |
||
| 1028 | |||
| 1029 | /** |
||
| 1030 | * This saves the document to the database and index |
||
| 1031 | * |
||
| 1032 | * @access public |
||
| 1033 | * |
||
| 1034 | * @param integer $pid: The PID of the saved record |
||
| 1035 | * @param integer $core: The UID of the Solr core for indexing |
||
| 1036 | * |
||
| 1037 | * @return boolean TRUE on success or FALSE on failure |
||
| 1038 | */ |
||
| 1039 | public function save($pid = 0, $core = 0) { |
||
| 1040 | if (TYPO3_MODE !== 'BE') { |
||
| 1041 | Helper::devLog('Saving a document is only allowed in the backend', DEVLOG_SEVERITY_ERROR); |
||
| 1042 | return FALSE; |
||
| 1043 | } |
||
| 1044 | // Make sure $pid is a non-negative integer. |
||
| 1045 | $pid = max(intval($pid), 0); |
||
| 1046 | // Make sure $core is a non-negative integer. |
||
| 1047 | $core = max(intval($core), 0); |
||
| 1048 | // If $pid is not given, try to get it elsewhere. |
||
| 1049 | if (!$pid |
||
| 1050 | && $this->pid) { |
||
| 1051 | // Retain current PID. |
||
| 1052 | $pid = $this->pid; |
||
| 1053 | } elseif (!$pid) { |
||
| 1054 | Helper::devLog('Invalid PID '.$pid.' for document saving', DEVLOG_SEVERITY_ERROR); |
||
| 1055 | return FALSE; |
||
| 1056 | } |
||
| 1057 | // Set PID for metadata definitions. |
||
| 1058 | $this->cPid = $pid; |
||
| 1059 | // Set UID placeholder if not updating existing record. |
||
| 1060 | if ($pid != $this->pid) { |
||
| 1061 | $this->uid = uniqid('NEW'); |
||
| 1062 | } |
||
| 1063 | // Get metadata array. |
||
| 1064 | $metadata = $this->getTitledata($pid); |
||
| 1065 | // Check for record identifier. |
||
| 1066 | if (empty($metadata['record_id'][0])) { |
||
| 1067 | Helper::devLog('No record identifier found to avoid duplication', DEVLOG_SEVERITY_ERROR); |
||
| 1068 | return FALSE; |
||
| 1069 | } |
||
| 1070 | // Load plugin configuration. |
||
| 1071 | $conf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf'][self::$extKey]); |
||
| 1072 | // Get UID for user "_cli_dlf". |
||
| 1073 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1074 | 'be_users.uid AS uid', |
||
| 1075 | 'be_users', |
||
| 1076 | 'username='.$GLOBALS['TYPO3_DB']->fullQuoteStr('_cli_dlf', 'be_users') |
||
| 1077 | .\TYPO3\CMS\Backend\Utility\BackendUtility::BEenableFields('be_users') |
||
| 1078 | .\TYPO3\CMS\Backend\Utility\BackendUtility::deleteClause('be_users'), |
||
| 1079 | '', |
||
| 1080 | '', |
||
| 1081 | '1' |
||
| 1082 | ); |
||
| 1083 | if (!$GLOBALS['TYPO3_DB']->sql_num_rows($result)) { |
||
| 1084 | Helper::devLog('Backend user "_cli_dlf" not found or disabled', DEVLOG_SEVERITY_ERROR); |
||
| 1085 | return FALSE; |
||
| 1086 | } |
||
| 1087 | // Get UID for structure type. |
||
| 1088 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1089 | 'tx_dlf_structures.uid AS uid', |
||
| 1090 | 'tx_dlf_structures', |
||
| 1091 | 'tx_dlf_structures.pid='.intval($pid) |
||
| 1092 | .' AND tx_dlf_structures.index_name='.$GLOBALS['TYPO3_DB']->fullQuoteStr($metadata['type'][0], 'tx_dlf_structures') |
||
| 1093 | .Helper::whereClause('tx_dlf_structures'), |
||
| 1094 | '', |
||
| 1095 | '', |
||
| 1096 | '1' |
||
| 1097 | ); |
||
| 1098 | if ($GLOBALS['TYPO3_DB']->sql_num_rows($result)) { |
||
| 1099 | list ($structure) = $GLOBALS['TYPO3_DB']->sql_fetch_row($result); |
||
| 1100 | } else { |
||
| 1101 | Helper::devLog('Could not identify document/structure type "'.$GLOBALS['TYPO3_DB']->fullQuoteStr($metadata['type'][0], 'tx_dlf_structures').'"', DEVLOG_SEVERITY_ERROR); |
||
| 1102 | return FALSE; |
||
| 1103 | } |
||
| 1104 | $metadata['type'][0] = $structure; |
||
| 1105 | // Get UIDs for collections. |
||
| 1106 | $collections = []; |
||
| 1107 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1108 | 'tx_dlf_collections.index_name AS index_name,tx_dlf_collections.uid AS uid', |
||
| 1109 | 'tx_dlf_collections', |
||
| 1110 | 'tx_dlf_collections.pid='.intval($pid) |
||
| 1111 | .' AND tx_dlf_collections.sys_language_uid IN (-1,0)' |
||
| 1112 | .Helper::whereClause('tx_dlf_collections'), |
||
| 1113 | '', |
||
| 1114 | '', |
||
| 1115 | '' |
||
| 1116 | ); |
||
| 1117 | while ($resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result)) { |
||
| 1118 | $collUid[$resArray['index_name']] = $resArray['uid']; |
||
| 1119 | } |
||
| 1120 | foreach ($metadata['collection'] as $collection) { |
||
| 1121 | if (!empty($collUid[$collection])) { |
||
| 1122 | // Add existing collection's UID. |
||
| 1123 | $collections[] = $collUid[$collection]; |
||
| 1124 | } else { |
||
| 1125 | // Insert new collection. |
||
| 1126 | $collNewUid = uniqid('NEW'); |
||
| 1127 | $collData['tx_dlf_collections'][$collNewUid] = [ |
||
| 1128 | 'pid' => $pid, |
||
| 1129 | 'label' => $collection, |
||
| 1130 | 'index_name' => $collection, |
||
| 1131 | 'oai_name' => (!empty($conf['publishNewCollections']) ? Helper::getCleanString($collection) : ''), |
||
| 1132 | 'description' => '', |
||
| 1133 | 'documents' => 0, |
||
| 1134 | 'owner' => 0, |
||
| 1135 | 'status' => 0, |
||
| 1136 | ]; |
||
| 1137 | $substUid = Helper::processDB($collData); |
||
| 1138 | // Prevent double insertion. |
||
| 1139 | unset ($collData); |
||
| 1140 | // Add new collection's UID. |
||
| 1141 | $collections[] = $substUid[$collNewUid]; |
||
| 1142 | if ((TYPO3_REQUESTTYPE & TYPO3_REQUESTTYPE_CLI) == FALSE) { |
||
| 1143 | Helper::addMessage( |
||
| 1144 | htmlspecialchars(sprintf(Helper::getMessage('flash.newCollection'), $collection, $substUid[$collNewUid])), |
||
| 1145 | Helper::getMessage('flash.attention', TRUE), |
||
| 1146 | \TYPO3\CMS\Core\Messaging\FlashMessage::INFO, |
||
| 1147 | TRUE |
||
| 1148 | ); |
||
| 1149 | } |
||
| 1150 | } |
||
| 1151 | } |
||
| 1152 | $metadata['collection'] = $collections; |
||
| 1153 | // Get UID for owner. |
||
| 1154 | $owner = !empty($metadata['owner'][0]) ? $metadata['owner'][0] : 'default'; |
||
| 1155 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1156 | 'tx_dlf_libraries.uid AS uid', |
||
| 1157 | 'tx_dlf_libraries', |
||
| 1158 | 'tx_dlf_libraries.pid='.intval($pid) |
||
| 1159 | .' AND tx_dlf_libraries.index_name='.$GLOBALS['TYPO3_DB']->fullQuoteStr($owner, 'tx_dlf_libraries') |
||
| 1160 | .Helper::whereClause('tx_dlf_libraries'), |
||
| 1161 | '', |
||
| 1162 | '', |
||
| 1163 | '1' |
||
| 1164 | ); |
||
| 1165 | if ($GLOBALS['TYPO3_DB']->sql_num_rows($result)) { |
||
| 1166 | list ($ownerUid) = $GLOBALS['TYPO3_DB']->sql_fetch_row($result); |
||
| 1167 | } else { |
||
| 1168 | // Insert new library. |
||
| 1169 | $libNewUid = uniqid('NEW'); |
||
| 1170 | $libData['tx_dlf_libraries'][$libNewUid] = [ |
||
|
1 ignored issue
–
show
|
|||
| 1171 | 'pid' => $pid, |
||
| 1172 | 'label' => $owner, |
||
| 1173 | 'index_name' => $owner, |
||
| 1174 | 'website' => '', |
||
| 1175 | 'contact' => '', |
||
| 1176 | 'image' => '', |
||
| 1177 | 'oai_label' => '', |
||
| 1178 | 'oai_base' => '', |
||
| 1179 | 'opac_label' => '', |
||
| 1180 | 'opac_base' => '', |
||
| 1181 | 'union_label' => '', |
||
| 1182 | 'union_base' => '', |
||
| 1183 | ]; |
||
| 1184 | $substUid = Helper::processDB($libData); |
||
| 1185 | // Add new library's UID. |
||
| 1186 | $ownerUid = $substUid[$libNewUid]; |
||
| 1187 | if ((TYPO3_REQUESTTYPE & TYPO3_REQUESTTYPE_CLI) == FALSE) { |
||
| 1188 | Helper::addMessage( |
||
| 1189 | htmlspecialchars(sprintf(Helper::getMessage('flash.newLibrary'), $owner, $ownerUid)), |
||
| 1190 | Helper::getMessage('flash.attention', TRUE), |
||
| 1191 | \TYPO3\CMS\Core\Messaging\FlashMessage::INFO, |
||
| 1192 | TRUE |
||
| 1193 | ); |
||
| 1194 | } |
||
| 1195 | } |
||
| 1196 | $metadata['owner'][0] = $ownerUid; |
||
| 1197 | // Get UID of parent document. |
||
| 1198 | $partof = 0; |
||
| 1199 | // Get the closest ancestor of the current document which has a MPTR child. |
||
| 1200 | $parentMptr = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@ID="'.$this->_getToplevelId().'"]/ancestor::mets:div[./mets:mptr][1]/mets:mptr'); |
||
| 1201 | if (!empty($parentMptr[0])) { |
||
| 1202 | $parentLocation = (string) $parentMptr[0]->attributes('http://www.w3.org/1999/xlink')->href; |
||
| 1203 | if ($parentLocation != $this->location) { |
||
| 1204 | $parentDoc = self::getInstance($parentLocation, $pid); |
||
| 1205 | if ($parentDoc->ready) { |
||
| 1206 | if ($parentDoc->pid != $pid) { |
||
| 1207 | $parentDoc->save($pid, $core); |
||
| 1208 | } |
||
| 1209 | $partof = $parentDoc->uid; |
||
| 1210 | } |
||
| 1211 | } |
||
| 1212 | } |
||
| 1213 | // Use the date of publication or title as alternative sorting metric for parts of multi-part works. |
||
| 1214 | if (!empty($partof)) { |
||
| 1215 | if (empty($metadata['volume'][0]) |
||
| 1216 | && !empty($metadata['year'][0])) { |
||
| 1217 | $metadata['volume'] = $metadata['year']; |
||
| 1218 | } |
||
| 1219 | if (empty($metadata['volume_sorting'][0])) { |
||
| 1220 | if (!empty($metadata['year_sorting'][0])) { |
||
| 1221 | $metadata['volume_sorting'][0] = $metadata['year_sorting'][0]; |
||
| 1222 | } elseif (!empty($metadata['year'][0])) { |
||
| 1223 | $metadata['volume_sorting'][0] = $metadata['year'][0]; |
||
| 1224 | } |
||
| 1225 | } |
||
| 1226 | // If volume_sorting is still empty, try to use title_sorting finally (workaround for newspapers) |
||
| 1227 | if (empty($metadata['volume_sorting'][0])) { |
||
| 1228 | if (!empty($metadata['title_sorting'][0])) { |
||
| 1229 | $metadata['volume_sorting'][0] = $metadata['title_sorting'][0]; |
||
| 1230 | } |
||
| 1231 | } |
||
| 1232 | } |
||
| 1233 | // Get metadata for lists and sorting. |
||
| 1234 | $listed = []; |
||
| 1235 | $sortable = []; |
||
| 1236 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1237 | 'tx_dlf_metadata.index_name AS index_name,tx_dlf_metadata.is_listed AS is_listed,tx_dlf_metadata.is_sortable AS is_sortable', |
||
| 1238 | 'tx_dlf_metadata', |
||
| 1239 | '(tx_dlf_metadata.is_listed=1 OR tx_dlf_metadata.is_sortable=1)' |
||
| 1240 | .' AND tx_dlf_metadata.pid='.intval($pid) |
||
| 1241 | .Helper::whereClause('tx_dlf_metadata'), |
||
| 1242 | '', |
||
| 1243 | '', |
||
| 1244 | '' |
||
| 1245 | ); |
||
| 1246 | while ($resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result)) { |
||
| 1247 | if (!empty($metadata[$resArray['index_name']])) { |
||
| 1248 | if ($resArray['is_listed']) { |
||
| 1249 | $listed[$resArray['index_name']] = $metadata[$resArray['index_name']]; |
||
| 1250 | } |
||
| 1251 | if ($resArray['is_sortable']) { |
||
| 1252 | $sortable[$resArray['index_name']] = $metadata[$resArray['index_name']][0]; |
||
| 1253 | } |
||
| 1254 | } |
||
| 1255 | } |
||
| 1256 | // Fill data array. |
||
| 1257 | $data['tx_dlf_documents'][$this->uid] = [ |
||
|
1 ignored issue
–
show
|
|||
| 1258 | 'pid' => $pid, |
||
| 1259 | $GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['starttime'] => 0, |
||
| 1260 | $GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['endtime'] => 0, |
||
| 1261 | 'prod_id' => $metadata['prod_id'][0], |
||
| 1262 | 'location' => $this->location, |
||
| 1263 | 'record_id' => $metadata['record_id'][0], |
||
| 1264 | 'opac_id' => $metadata['opac_id'][0], |
||
| 1265 | 'union_id' => $metadata['union_id'][0], |
||
| 1266 | 'urn' => $metadata['urn'][0], |
||
| 1267 | 'purl' => $metadata['purl'][0], |
||
| 1268 | 'title' => $metadata['title'][0], |
||
| 1269 | 'title_sorting' => $metadata['title_sorting'][0], |
||
| 1270 | 'author' => implode('; ', $metadata['author']), |
||
| 1271 | 'year' => implode('; ', $metadata['year']), |
||
| 1272 | 'place' => implode('; ', $metadata['place']), |
||
| 1273 | 'thumbnail' => $this->_getThumbnail(TRUE), |
||
| 1274 | 'metadata' => serialize($listed), |
||
| 1275 | 'metadata_sorting' => serialize($sortable), |
||
| 1276 | 'structure' => $metadata['type'][0], |
||
| 1277 | 'partof' => $partof, |
||
| 1278 | 'volume' => $metadata['volume'][0], |
||
| 1279 | 'volume_sorting' => $metadata['volume_sorting'][0], |
||
| 1280 | 'collections' => $metadata['collection'], |
||
| 1281 | 'owner' => $metadata['owner'][0], |
||
| 1282 | 'solrcore' => $core, |
||
| 1283 | 'status' => 0, |
||
| 1284 | ]; |
||
| 1285 | // Unhide hidden documents. |
||
| 1286 | if (!empty($conf['unhideOnIndex'])) { |
||
| 1287 | $data['tx_dlf_documents'][$this->uid][$GLOBALS['TCA']['tx_dlf_documents']['ctrl']['enablecolumns']['disabled']] = 0; |
||
| 1288 | } |
||
| 1289 | // Process data. |
||
| 1290 | $newIds = Helper::processDB($data); |
||
| 1291 | // Replace placeholder with actual UID. |
||
| 1292 | if (strpos($this->uid, 'NEW') === 0) { |
||
| 1293 | $this->uid = $newIds[$this->uid]; |
||
| 1294 | $this->pid = $pid; |
||
| 1295 | $this->parentId = $partof; |
||
| 1296 | } |
||
| 1297 | if ((TYPO3_REQUESTTYPE & TYPO3_REQUESTTYPE_CLI) == FALSE) { |
||
| 1298 | Helper::addMessage( |
||
| 1299 | htmlspecialchars(sprintf(Helper::getMessage('flash.documentSaved'), $metadata['title'][0], $this->uid)), |
||
| 1300 | Helper::getMessage('flash.done', TRUE), |
||
| 1301 | \TYPO3\CMS\Core\Messaging\FlashMessage::OK, |
||
| 1302 | TRUE |
||
| 1303 | ); |
||
| 1304 | } |
||
| 1305 | // Add document to index. |
||
| 1306 | if ($core) { |
||
| 1307 | Indexer::add($this, $core); |
||
| 1308 | } else { |
||
| 1309 | Helper::devLog('Invalid UID "'.$core.'" for Solr core', DEVLOG_SEVERITY_NOTICE); |
||
| 1310 | } |
||
| 1311 | return TRUE; |
||
| 1312 | } |
||
| 1313 | |||
| 1314 | /** |
||
| 1315 | * This returns $this->cPid via __get() |
||
| 1316 | * |
||
| 1317 | * @access protected |
||
| 1318 | * |
||
| 1319 | * @return integer The PID of the metadata definitions |
||
| 1320 | */ |
||
| 1321 | protected function _getCPid() { |
||
| 1322 | return $this->cPid; |
||
| 1323 | } |
||
| 1324 | |||
| 1325 | /** |
||
| 1326 | * This builds an array of the document's dmdSecs |
||
| 1327 | * |
||
| 1328 | * @access protected |
||
| 1329 | * |
||
| 1330 | * @return array Array of dmdSecs with their IDs as array key |
||
| 1331 | */ |
||
| 1332 | protected function _getDmdSec() { |
||
| 1333 | if (!$this->dmdSecLoaded) { |
||
| 1334 | // Get available data formats. |
||
| 1335 | $this->loadFormats(); |
||
| 1336 | // Get dmdSec nodes from METS. |
||
| 1337 | $dmdIds = $this->mets->xpath('./mets:dmdSec/@ID'); |
||
| 1338 | foreach ($dmdIds as $dmdId) { |
||
| 1339 | if ($type = $this->mets->xpath('./mets:dmdSec[@ID="'.(string) $dmdId.'"]/mets:mdWrap[not(@MDTYPE="OTHER")]/@MDTYPE')) { |
||
| 1340 | if (!empty($this->formats[(string) $type[0]])) { |
||
| 1341 | $type = (string) $type[0]; |
||
| 1342 | $xml = $this->mets->xpath('./mets:dmdSec[@ID="'.(string) $dmdId.'"]/mets:mdWrap[@MDTYPE="'.$type.'"]/mets:xmlData/'.strtolower($type).':'.$this->formats[$type]['rootElement']); |
||
| 1343 | } |
||
| 1344 | } elseif ($type = $this->mets->xpath('./mets:dmdSec[@ID="'.(string) $dmdId.'"]/mets:mdWrap[@MDTYPE="OTHER"]/@OTHERMDTYPE')) { |
||
| 1345 | if (!empty($this->formats[(string) $type[0]])) { |
||
| 1346 | $type = (string) $type[0]; |
||
| 1347 | $xml = $this->mets->xpath('./mets:dmdSec[@ID="'.(string) $dmdId.'"]/mets:mdWrap[@MDTYPE="OTHER"][@OTHERMDTYPE="'.$type.'"]/mets:xmlData/'.strtolower($type).':'.$this->formats[$type]['rootElement']); |
||
| 1348 | } |
||
| 1349 | } |
||
| 1350 | if ($xml) { |
||
| 1351 | $this->dmdSec[(string) $dmdId]['type'] = $type; |
||
| 1352 | $this->dmdSec[(string) $dmdId]['xml'] = $xml[0]; |
||
| 1353 | $this->registerNamespaces($this->dmdSec[(string) $dmdId]['xml']); |
||
| 1354 | } |
||
| 1355 | } |
||
| 1356 | $this->dmdSecLoaded = TRUE; |
||
| 1357 | } |
||
| 1358 | return $this->dmdSec; |
||
| 1359 | } |
||
| 1360 | |||
| 1361 | /** |
||
| 1362 | * This builds the file ID -> USE concordance |
||
| 1363 | * |
||
| 1364 | * @access protected |
||
| 1365 | * |
||
| 1366 | * @return array Array of file use groups with file IDs |
||
| 1367 | */ |
||
| 1368 | protected function _getFileGrps() { |
||
| 1369 | if (!$this->fileGrpsLoaded) { |
||
| 1370 | // Get configured USE attributes. |
||
| 1371 | $extConf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf'][self::$extKey]); |
||
| 1372 | $useGrps = \TYPO3\CMS\Core\Utility\GeneralUtility::trimExplode(',', $extConf['fileGrps']); |
||
| 1373 | if (!empty($extConf['fileGrpThumbs'])) { |
||
| 1374 | $useGrps[] = $extConf['fileGrpThumbs']; |
||
| 1375 | } |
||
| 1376 | if (!empty($extConf['fileGrpDownload'])) { |
||
| 1377 | $useGrps[] = $extConf['fileGrpDownload']; |
||
| 1378 | } |
||
| 1379 | if (!empty($extConf['fileGrpFulltext'])) { |
||
| 1380 | $useGrps[] = $extConf['fileGrpFulltext']; |
||
| 1381 | } |
||
| 1382 | if (!empty($extConf['fileGrpAudio'])) { |
||
| 1383 | $useGrps[] = $extConf['fileGrpAudio']; |
||
| 1384 | } |
||
| 1385 | // Get all file groups. |
||
| 1386 | $fileGrps = $this->mets->xpath('./mets:fileSec/mets:fileGrp'); |
||
| 1387 | // Build concordance for configured USE attributes. |
||
| 1388 | foreach ($fileGrps as $fileGrp) { |
||
| 1389 | if (in_array((string) $fileGrp['USE'], $useGrps)) { |
||
| 1390 | foreach ($fileGrp->children('http://www.loc.gov/METS/')->file as $file) { |
||
| 1391 | $this->fileGrps[(string) $file->attributes()->ID] = (string) $fileGrp['USE']; |
||
| 1392 | } |
||
| 1393 | } |
||
| 1394 | } |
||
| 1395 | // Are there any fulltext files available? |
||
| 1396 | if (!empty($extConf['fileGrpFulltext']) |
||
| 1397 | && in_array($extConf['fileGrpFulltext'], $this->fileGrps)) { |
||
| 1398 | $this->hasFulltext = TRUE; |
||
| 1399 | } |
||
| 1400 | $this->fileGrpsLoaded = TRUE; |
||
| 1401 | } |
||
| 1402 | return $this->fileGrps; |
||
| 1403 | } |
||
| 1404 | |||
| 1405 | /** |
||
| 1406 | * This returns $this->hasFulltext via __get() |
||
| 1407 | * |
||
| 1408 | * @access protected |
||
| 1409 | * |
||
| 1410 | * @return boolean Are there any fulltext files available? |
||
| 1411 | */ |
||
| 1412 | protected function _getHasFulltext() { |
||
| 1413 | // Are the fileGrps already loaded? |
||
| 1414 | if (!$this->fileGrpsLoaded) { |
||
| 1415 | $this->_getFileGrps(); |
||
| 1416 | } |
||
| 1417 | return $this->hasFulltext; |
||
| 1418 | } |
||
| 1419 | |||
| 1420 | /** |
||
| 1421 | * This returns $this->location via __get() |
||
| 1422 | * |
||
| 1423 | * @access protected |
||
| 1424 | * |
||
| 1425 | * @return string The location of the document |
||
| 1426 | */ |
||
| 1427 | protected function _getLocation() { |
||
| 1429 | } |
||
| 1430 | |||
| 1431 | /** |
||
| 1432 | * This builds an array of the document's metadata |
||
| 1433 | * |
||
| 1434 | * @access protected |
||
| 1435 | * |
||
| 1436 | * @return array Array of metadata with their corresponding logical structure node ID as key |
||
| 1437 | */ |
||
| 1438 | protected function _getMetadataArray() { |
||
| 1458 | } |
||
| 1459 | |||
| 1460 | /** |
||
| 1461 | * This returns $this->mets via __get() |
||
| 1462 | * |
||
| 1463 | * @access protected |
||
| 1464 | * |
||
| 1465 | * @return \SimpleXMLElement The XML's METS part as \SimpleXMLElement object |
||
| 1466 | */ |
||
| 1467 | protected function _getMets() { |
||
| 1468 | return $this->mets; |
||
| 1469 | } |
||
| 1470 | |||
| 1471 | /** |
||
| 1472 | * This returns $this->numPages via __get() |
||
| 1473 | * |
||
| 1474 | * @access protected |
||
| 1475 | * |
||
| 1476 | * @return integer The total number of pages and/or tracks |
||
| 1477 | */ |
||
| 1478 | protected function _getNumPages() { |
||
| 1479 | $this->_getPhysicalStructure(); |
||
| 1480 | return $this->numPages; |
||
| 1481 | } |
||
| 1482 | |||
| 1483 | /** |
||
| 1484 | * This returns $this->parentId via __get() |
||
| 1485 | * |
||
| 1486 | * @access protected |
||
| 1487 | * |
||
| 1488 | * @return integer The UID of the parent document or zero if not applicable |
||
| 1489 | */ |
||
| 1490 | protected function _getParentId() { |
||
| 1491 | return $this->parentId; |
||
| 1492 | } |
||
| 1493 | |||
| 1494 | /** |
||
| 1495 | * This builds an array of the document's physical structure |
||
| 1496 | * |
||
| 1497 | * @access protected |
||
| 1498 | * |
||
| 1499 | * @return array Array of physical elements' id, type, label and file representations ordered by @ORDER attribute |
||
| 1500 | */ |
||
| 1501 | protected function _getPhysicalStructure() { |
||
| 1502 | // Is there no physical structure array yet? |
||
| 1503 | if (!$this->physicalStructureLoaded) { |
||
| 1504 | // Does the document have a structMap node of type "PHYSICAL"? |
||
| 1505 | $elementNodes = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]/mets:div'); |
||
| 1506 | if ($elementNodes) { |
||
| 1507 | // Get file groups. |
||
| 1508 | $fileUse = $this->_getFileGrps(); |
||
| 1509 | // Get the physical sequence's metadata. |
||
| 1510 | $physNode = $this->mets->xpath('./mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]'); |
||
| 1511 | $physSeq[0] = (string) $physNode[0]['ID']; |
||
|
1 ignored issue
–
show
|
|||
| 1512 | $this->physicalStructureInfo[$physSeq[0]]['id'] = (string) $physNode[0]['ID']; |
||
| 1513 | $this->physicalStructureInfo[$physSeq[0]]['dmdId'] = (isset($physNode[0]['DMDID']) ? (string) $physNode[0]['DMDID'] : ''); |
||
| 1514 | $this->physicalStructureInfo[$physSeq[0]]['label'] = (isset($physNode[0]['LABEL']) ? (string) $physNode[0]['LABEL'] : ''); |
||
| 1515 | $this->physicalStructureInfo[$physSeq[0]]['orderlabel'] = (isset($physNode[0]['ORDERLABEL']) ? (string) $physNode[0]['ORDERLABEL'] : ''); |
||
| 1516 | $this->physicalStructureInfo[$physSeq[0]]['type'] = (string) $physNode[0]['TYPE']; |
||
| 1517 | $this->physicalStructureInfo[$physSeq[0]]['contentIds'] = (isset($physNode[0]['CONTENTIDS']) ? (string) $physNode[0]['CONTENTIDS'] : ''); |
||
| 1518 | // Get the file representations from fileSec node. |
||
| 1519 | foreach ($physNode[0]->children('http://www.loc.gov/METS/')->fptr as $fptr) { |
||
| 1520 | // Check if file has valid @USE attribute. |
||
| 1521 | if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) { |
||
| 1522 | $this->physicalStructureInfo[$physSeq[0]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID; |
||
| 1523 | } |
||
| 1524 | } |
||
| 1525 | // Build the physical elements' array from the physical structMap node. |
||
| 1526 | foreach ($elementNodes as $elementNode) { |
||
| 1527 | $elements[(int) $elementNode['ORDER']] = (string) $elementNode['ID']; |
||
| 1528 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['id'] = (string) $elementNode['ID']; |
||
|
1 ignored issue
–
show
|
|||
| 1529 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['dmdId'] = (isset($elementNode['DMDID']) ? (string) $elementNode['DMDID'] : ''); |
||
| 1530 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['label'] = (isset($elementNode['LABEL']) ? (string) $elementNode['LABEL'] : ''); |
||
| 1531 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['orderlabel'] = (isset($elementNode['ORDERLABEL']) ? (string) $elementNode['ORDERLABEL'] : ''); |
||
| 1532 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['type'] = (string) $elementNode['TYPE']; |
||
| 1533 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['contentIds'] = (isset($elementNode['CONTENTIDS']) ? (string) $elementNode['CONTENTIDS'] : ''); |
||
| 1534 | // Get the file representations from fileSec node. |
||
| 1535 | foreach ($elementNode->children('http://www.loc.gov/METS/')->fptr as $fptr) { |
||
| 1536 | // Check if file has valid @USE attribute. |
||
| 1537 | if (!empty($fileUse[(string) $fptr->attributes()->FILEID])) { |
||
| 1538 | $this->physicalStructureInfo[$elements[(int) $elementNode['ORDER']]]['files'][$fileUse[(string) $fptr->attributes()->FILEID]] = (string) $fptr->attributes()->FILEID; |
||
| 1539 | } |
||
| 1540 | } |
||
| 1541 | } |
||
| 1542 | // Sort array by keys (= @ORDER). |
||
| 1543 | if (ksort($elements)) { |
||
| 1544 | // Set total number of pages/tracks. |
||
| 1545 | $this->numPages = count($elements); |
||
| 1546 | // Merge and re-index the array to get nice numeric indexes. |
||
| 1547 | $this->physicalStructure = array_merge($physSeq, $elements); |
||
| 1548 | } |
||
| 1549 | } |
||
| 1550 | $this->physicalStructureLoaded = TRUE; |
||
| 1551 | } |
||
| 1552 | return $this->physicalStructure; |
||
| 1553 | } |
||
| 1554 | |||
| 1555 | /** |
||
| 1556 | * This gives an array of the document's physical structure metadata |
||
| 1557 | * |
||
| 1558 | * @access protected |
||
| 1559 | * |
||
| 1560 | * @return array Array of elements' type, label and file representations ordered by @ID attribute |
||
| 1561 | */ |
||
| 1562 | protected function _getPhysicalStructureInfo() { |
||
| 1563 | // Is there no physical structure array yet? |
||
| 1564 | if (!$this->physicalStructureLoaded) { |
||
| 1565 | // Build physical structure array. |
||
| 1566 | $this->_getPhysicalStructure(); |
||
| 1567 | } |
||
| 1568 | return $this->physicalStructureInfo; |
||
| 1569 | } |
||
| 1570 | |||
| 1571 | /** |
||
| 1572 | * This returns $this->pid via __get() |
||
| 1573 | * |
||
| 1574 | * @access protected |
||
| 1575 | * |
||
| 1576 | * @return integer The PID of the document or zero if not in database |
||
| 1577 | */ |
||
| 1578 | protected function _getPid() { |
||
| 1579 | return $this->pid; |
||
| 1580 | } |
||
| 1581 | |||
| 1582 | /** |
||
| 1583 | * This returns $this->ready via __get() |
||
| 1584 | * |
||
| 1585 | * @access protected |
||
| 1586 | * |
||
| 1587 | * @return boolean Is the document instantiated successfully? |
||
| 1588 | */ |
||
| 1589 | protected function _getReady() { |
||
| 1590 | return $this->ready; |
||
| 1591 | } |
||
| 1592 | |||
| 1593 | /** |
||
| 1594 | * This returns $this->recordId via __get() |
||
| 1595 | * |
||
| 1596 | * @access protected |
||
| 1597 | * |
||
| 1598 | * @return mixed The METS file's record identifier |
||
| 1599 | */ |
||
| 1600 | protected function _getRecordId() { |
||
| 1601 | return $this->recordId; |
||
| 1602 | } |
||
| 1603 | |||
| 1604 | /** |
||
| 1605 | * This returns $this->rootId via __get() |
||
| 1606 | * |
||
| 1607 | * @access protected |
||
| 1608 | * |
||
| 1609 | * @return integer The UID of the root document or zero if not applicable |
||
| 1610 | */ |
||
| 1611 | protected function _getRootId() { |
||
| 1612 | if (!$this->rootIdLoaded) { |
||
| 1613 | if ($this->parentId) { |
||
| 1614 | $parent = self::getInstance($this->parentId, $this->pid); |
||
| 1615 | $this->rootId = $parent->rootId; |
||
| 1616 | } |
||
| 1617 | $this->rootIdLoaded = TRUE; |
||
| 1618 | } |
||
| 1619 | return $this->rootId; |
||
| 1620 | } |
||
| 1621 | |||
| 1622 | /** |
||
| 1623 | * This returns the smLinks between logical and physical structMap |
||
| 1624 | * |
||
| 1625 | * @access protected |
||
| 1626 | * |
||
| 1627 | * @return array The links between logical and physical nodes |
||
| 1628 | */ |
||
| 1629 | protected function _getSmLinks() { |
||
| 1630 | if (!$this->smLinksLoaded) { |
||
| 1631 | $smLinks = $this->mets->xpath('./mets:structLink/mets:smLink'); |
||
| 1632 | foreach ($smLinks as $smLink) { |
||
| 1633 | $this->smLinks['l2p'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->from][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->to; |
||
| 1634 | $this->smLinks['p2l'][(string) $smLink->attributes('http://www.w3.org/1999/xlink')->to][] = (string) $smLink->attributes('http://www.w3.org/1999/xlink')->from; |
||
| 1635 | } |
||
| 1636 | $this->smLinksLoaded = TRUE; |
||
| 1637 | } |
||
| 1638 | return $this->smLinks; |
||
| 1639 | } |
||
| 1640 | |||
| 1641 | /** |
||
| 1642 | * This builds an array of the document's logical structure |
||
| 1643 | * |
||
| 1644 | * @access protected |
||
| 1645 | * |
||
| 1646 | * @return array Array of structure nodes' id, label, type and physical page indexes/mptr link with original hierarchy preserved |
||
| 1647 | */ |
||
| 1648 | protected function _getTableOfContents() { |
||
| 1649 | // Is there no logical structure array yet? |
||
| 1650 | if (!$this->tableOfContentsLoaded) { |
||
| 1651 | // Get all logical structures. |
||
| 1652 | $this->getLogicalStructure('', TRUE); |
||
| 1653 | $this->tableOfContentsLoaded = TRUE; |
||
| 1654 | } |
||
| 1655 | return $this->tableOfContents; |
||
| 1656 | } |
||
| 1657 | |||
| 1658 | /** |
||
| 1659 | * This returns the document's thumbnail location |
||
| 1660 | * |
||
| 1661 | * @access protected |
||
| 1662 | * |
||
| 1663 | * @param boolean $forceReload: Force reloading the thumbnail instead of returning the cached value |
||
| 1664 | * |
||
| 1665 | * @return string The document's thumbnail location |
||
| 1666 | */ |
||
| 1667 | protected function _getThumbnail($forceReload = FALSE) { |
||
| 1668 | if (!$this->thumbnailLoaded |
||
| 1669 | || $forceReload) { |
||
| 1670 | // Retain current PID. |
||
| 1671 | $cPid = ($this->cPid ? $this->cPid : $this->pid); |
||
| 1672 | if (!$cPid) { |
||
| 1673 | Helper::devLog('Invalid PID '.$cPid.' for structure definitions', DEVLOG_SEVERITY_ERROR); |
||
| 1674 | $this->thumbnailLoaded = TRUE; |
||
| 1675 | return $this->thumbnail; |
||
| 1676 | } |
||
| 1677 | // Load extension configuration. |
||
| 1678 | $extConf = unserialize($GLOBALS['TYPO3_CONF_VARS']['EXT']['extConf'][self::$extKey]); |
||
| 1679 | if (empty($extConf['fileGrpThumbs'])) { |
||
| 1680 | Helper::devLog('No fileGrp for thumbnails specified', DEVLOG_SEVERITY_WARNING); |
||
| 1681 | $this->thumbnailLoaded = TRUE; |
||
| 1682 | return $this->thumbnail; |
||
| 1683 | } |
||
| 1684 | $strctId = $this->_getToplevelId(); |
||
| 1685 | $metadata = $this->getTitledata($cPid); |
||
| 1686 | // Get structure element to get thumbnail from. |
||
| 1687 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1688 | 'tx_dlf_structures.thumbnail AS thumbnail', |
||
| 1689 | 'tx_dlf_structures', |
||
| 1690 | 'tx_dlf_structures.pid='.intval($cPid) |
||
| 1691 | .' AND tx_dlf_structures.index_name='.$GLOBALS['TYPO3_DB']->fullQuoteStr($metadata['type'][0], 'tx_dlf_structures') |
||
| 1692 | .Helper::whereClause('tx_dlf_structures'), |
||
| 1693 | '', |
||
| 1694 | '', |
||
| 1695 | '1' |
||
| 1696 | ); |
||
| 1697 | if ($GLOBALS['TYPO3_DB']->sql_num_rows($result) > 0) { |
||
| 1698 | $resArray = $GLOBALS['TYPO3_DB']->sql_fetch_assoc($result); |
||
| 1699 | // Get desired thumbnail structure if not the toplevel structure itself. |
||
| 1700 | if (!empty($resArray['thumbnail'])) { |
||
| 1701 | $strctType = Helper::getIndexNameFromUid($resArray['thumbnail'], 'tx_dlf_structures', $cPid); |
||
| 1702 | // Check if this document has a structure element of the desired type. |
||
| 1703 | $strctIds = $this->mets->xpath('./mets:structMap[@TYPE="LOGICAL"]//mets:div[@TYPE="'.$strctType.'"]/@ID'); |
||
| 1704 | if (!empty($strctIds)) { |
||
| 1705 | $strctId = (string) $strctIds[0]; |
||
| 1706 | } |
||
| 1707 | } |
||
| 1708 | // Load smLinks. |
||
| 1709 | $this->_getSmLinks(); |
||
| 1710 | // Get thumbnail location. |
||
| 1711 | if ($this->_getPhysicalStructure() |
||
| 1712 | && !empty($this->smLinks['l2p'][$strctId])) { |
||
| 1713 | $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->smLinks['l2p'][$strctId][0]]['files'][$extConf['fileGrpThumbs']]); |
||
| 1714 | } else { |
||
| 1715 | $this->thumbnail = $this->getFileLocation($this->physicalStructureInfo[$this->physicalStructure[1]]['files'][$extConf['fileGrpThumbs']]); |
||
| 1716 | } |
||
| 1717 | } else { |
||
| 1718 | Helper::devLog('No structure of type "'.$metadata['type'][0].'" found in database', DEVLOG_SEVERITY_ERROR); |
||
| 1719 | } |
||
| 1720 | $this->thumbnailLoaded = TRUE; |
||
| 1721 | } |
||
| 1722 | return $this->thumbnail; |
||
| 1723 | } |
||
| 1724 | |||
| 1725 | /** |
||
| 1726 | * This returns the ID of the toplevel logical structure node |
||
| 1727 | * |
||
| 1728 | * @access protected |
||
| 1729 | * |
||
| 1730 | * @return string The logical structure node's ID |
||
| 1731 | */ |
||
| 1732 | protected function _getToplevelId() { |
||
| 1753 | } |
||
| 1754 | |||
| 1755 | /** |
||
| 1756 | * This returns $this->uid via __get() |
||
| 1757 | * |
||
| 1758 | * @access protected |
||
| 1759 | * |
||
| 1760 | * @return mixed The UID or the URL of the document |
||
| 1761 | */ |
||
| 1762 | protected function _getUid() { |
||
| 1763 | return $this->uid; |
||
| 1764 | } |
||
| 1765 | |||
| 1766 | /** |
||
| 1767 | * This sets $this->cPid via __set() |
||
| 1768 | * |
||
| 1769 | * @access protected |
||
| 1770 | * |
||
| 1771 | * @param integer $value: The new PID for the metadata definitions |
||
| 1772 | * |
||
| 1773 | * @return void |
||
| 1774 | */ |
||
| 1775 | protected function _setCPid($value) { |
||
| 1776 | $this->cPid = max(intval($value), 0); |
||
| 1777 | } |
||
| 1778 | |||
| 1779 | /** |
||
| 1780 | * This magic method is invoked each time a clone is called on the object variable |
||
| 1781 | * (This method is defined as private/protected because singleton objects should not be cloned) |
||
| 1782 | * |
||
| 1783 | * @access protected |
||
| 1784 | * |
||
| 1785 | * @return void |
||
| 1786 | */ |
||
| 1787 | protected function __clone() {} |
||
| 1788 | |||
| 1789 | /** |
||
| 1790 | * This is a singleton class, thus the constructor should be private/protected |
||
| 1791 | * (Get an instance of this class by calling \Kitodo\Dlf\Common\Document::getInstance()) |
||
| 1792 | * |
||
| 1793 | * @access protected |
||
| 1794 | * |
||
| 1795 | * @param integer $uid: The UID of the document to parse or URL to XML file |
||
| 1796 | * @param integer $pid: If > 0, then only document with this PID gets loaded |
||
| 1797 | * |
||
| 1798 | * @return void |
||
| 1799 | */ |
||
| 1800 | protected function __construct($uid, $pid) { |
||
| 1801 | // Prepare to check database for the requested document. |
||
| 1802 | if (\TYPO3\CMS\Core\Utility\MathUtility::canBeInterpretedAsInteger($uid)) { |
||
| 1803 | $whereClause = 'tx_dlf_documents.uid='.intval($uid).Helper::whereClause('tx_dlf_documents'); |
||
| 1804 | } else { |
||
| 1805 | // Try to load METS file. |
||
| 1806 | if (\TYPO3\CMS\Core\Utility\GeneralUtility::isValidUrl($uid) |
||
| 1807 | && $this->load($uid)) { |
||
| 1808 | // Initialize core METS object. |
||
| 1809 | $this->init(); |
||
| 1810 | if ($this->mets !== NULL) { |
||
| 1811 | // Cast to string for safety reasons. |
||
| 1812 | $location = (string) $uid; |
||
| 1813 | // Check for METS object @ID. |
||
| 1814 | if (!empty($this->mets['OBJID'])) { |
||
| 1815 | $this->recordId = (string) $this->mets['OBJID']; |
||
| 1816 | } |
||
| 1817 | // Get hook objects. |
||
| 1818 | $hookObjects = Helper::getHookObjects('Classes/Common/Document.php'); |
||
| 1819 | // Apply hooks. |
||
| 1820 | foreach ($hookObjects as $hookObj) { |
||
| 1821 | if (method_exists($hookObj, 'construct_postProcessRecordId')) { |
||
| 1822 | $hookObj->construct_postProcessRecordId($this->xml, $this->recordId); |
||
| 1823 | } |
||
| 1824 | } |
||
| 1825 | } else { |
||
| 1826 | // No METS part found. |
||
| 1827 | return; |
||
| 1828 | } |
||
| 1829 | } else { |
||
| 1830 | // Loading failed. |
||
| 1831 | return; |
||
| 1832 | } |
||
| 1833 | if (!empty($location) |
||
| 1834 | && !empty($this->recordId)) { |
||
| 1835 | // Try to match record identifier or location (both should be unique). |
||
| 1836 | $whereClause = '(tx_dlf_documents.location='.$GLOBALS['TYPO3_DB']->fullQuoteStr($location, 'tx_dlf_documents').' OR tx_dlf_documents.record_id='.$GLOBALS['TYPO3_DB']->fullQuoteStr($this->recordId, 'tx_dlf_documents').')'.Helper::whereClause('tx_dlf_documents'); |
||
| 1837 | } else { |
||
| 1838 | // Can't persistently identify document, don't try to match at all. |
||
| 1839 | $whereClause = '1=-1'; |
||
| 1840 | } |
||
| 1841 | } |
||
| 1842 | // Check for PID if needed. |
||
| 1843 | if ($pid) { |
||
| 1844 | $whereClause .= ' AND tx_dlf_documents.pid='.intval($pid); |
||
| 1845 | } |
||
| 1846 | // Get document PID and location from database. |
||
| 1847 | $result = $GLOBALS['TYPO3_DB']->exec_SELECTquery( |
||
| 1848 | 'tx_dlf_documents.uid AS uid,tx_dlf_documents.pid AS pid,tx_dlf_documents.record_id AS record_id,tx_dlf_documents.partof AS partof,tx_dlf_documents.thumbnail AS thumbnail,tx_dlf_documents.location AS location', |
||
| 1849 | 'tx_dlf_documents', |
||
| 1850 | $whereClause, |
||
| 1851 | '', |
||
| 1852 | '', |
||
| 1853 | '1' |
||
| 1854 | ); |
||
| 1855 | if ($GLOBALS['TYPO3_DB']->sql_num_rows($result) > 0) { |
||
| 1856 | list ($this->uid, $this->pid, $this->recordId, $this->parentId, $this->thumbnail, $this->location) = $GLOBALS['TYPO3_DB']->sql_fetch_row($result); |
||
| 1857 | $this->thumbnailLoaded = TRUE; |
||
| 1858 | // Load XML file if necessary... |
||
| 1859 | if ($this->mets === NULL |
||
| 1860 | && $this->load($this->location)) { |
||
| 1861 | // ...and set some basic properties. |
||
| 1862 | $this->init(); |
||
| 1863 | } |
||
| 1864 | // Do we have a METS object now? |
||
| 1865 | if ($this->mets !== NULL) { |
||
| 1866 | // Set new location if necessary. |
||
| 1867 | if (!empty($location)) { |
||
| 1868 | $this->location = $location; |
||
| 1869 | } |
||
| 1870 | // Document ready! |
||
| 1871 | $this->ready = TRUE; |
||
| 1872 | } |
||
| 1873 | } elseif ($this->mets !== NULL) { |
||
| 1874 | // Set location as UID for documents not in database. |
||
| 1875 | $this->uid = $location; |
||
| 1876 | $this->location = $location; |
||
| 1877 | // Document ready! |
||
| 1878 | $this->ready = TRUE; |
||
| 1879 | } else { |
||
| 1880 | Helper::devLog('No document with UID '.$uid.' found or document not accessible', DEVLOG_SEVERITY_ERROR); |
||
| 1881 | } |
||
| 1882 | } |
||
| 1883 | |||
| 1884 | /** |
||
| 1885 | * This magic method is called each time an invisible property is referenced from the object |
||
| 1886 | * |
||
| 1887 | * @access public |
||
| 1888 | * |
||
| 1889 | * @param string $var: Name of variable to get |
||
| 1890 | * |
||
| 1891 | * @return mixed Value of $this->$var |
||
| 1892 | */ |
||
| 1893 | public function __get($var) { |
||
| 1901 | } |
||
| 1902 | } |
||
| 1903 | |||
| 1904 | /** |
||
| 1905 | * This magic method is called each time an invisible property is referenced from the object |
||
| 1906 | * |
||
| 1907 | * @access public |
||
| 1908 | * |
||
| 1909 | * @param string $var: Name of variable to set |
||
| 1910 | * @param mixed $value: New value of variable |
||
| 1911 | * |
||
| 1912 | * @return void |
||
| 1913 | */ |
||
| 1914 | public function __set($var, $value) { |
||
| 1915 | $method = '_set'.ucfirst($var); |
||
| 1916 | if (!property_exists($this, $var) |
||
| 1917 | || !method_exists($this, $method)) { |
||
| 1918 | Helper::devLog('There is no setter function for property "'.$var.'"', DEVLOG_SEVERITY_WARNING); |
||
| 1919 | } else { |
||
| 1920 | $this->$method($value); |
||
| 1921 | } |
||
| 1922 | } |
||
| 1923 | |||
| 1924 | /** |
||
| 1925 | * This magic method is executed prior to any serialization of the object |
||
| 1926 | * @see __wakeup() |
||
| 1927 | * |
||
| 1928 | * @access public |
||
| 1929 | * |
||
| 1930 | * @return array Properties to be serialized |
||
| 1931 | */ |
||
| 1932 | public function __sleep() { |
||
| 1936 | } |
||
| 1937 | |||
| 1938 | /** |
||
| 1939 | * This magic method is used for setting a string value for the object |
||
| 1940 | * |
||
| 1941 | * @access public |
||
| 1942 | * |
||
| 1943 | * @return string String representing the METS object |
||
| 1944 | */ |
||
| 1945 | public function __toString() { |
||
| 1950 | } |
||
| 1951 | |||
| 1952 | /** |
||
| 1953 | * This magic method is executed after the object is deserialized |
||
| 1954 | * @see __sleep() |
||
| 1955 | * |
||
| 1956 | * @access public |
||
| 1957 | * |
||
| 1958 | * @return void |
||
| 1959 | */ |
||
| 1960 | public function __wakeup() { |
||
| 1974 | } |
||
| 1975 | } |
||
| 1977 |