Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
99.48% |
191 / 192 |
|
95.24% |
20 / 21 |
CRAP | |
0.00% |
0 / 1 |
| MarcReader | |
99.48% |
191 / 192 |
|
95.24% |
20 / 21 |
84 | |
0.00% |
0 / 1 |
| __construct | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| setData | |
100.00% |
21 / 21 |
|
100.00% |
1 / 1 |
9 | |||
| toFormat | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
2 | |||
| getLeader | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getField | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| getFields | |
95.65% |
22 / 23 |
|
0.00% |
0 / 1 |
9 | |||
| getAllFields | |
100.00% |
24 / 24 |
|
100.00% |
1 / 1 |
5 | |||
| getSubfield | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
3 | |||
| getSubfields | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
4 | |||
| getFieldsSubfields | |
100.00% |
13 / 13 |
|
100.00% |
1 / 1 |
9 | |||
| getLinkedField | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
4 | |||
| getLinkedFields | |
100.00% |
23 / 23 |
|
100.00% |
1 / 1 |
8 | |||
| getLinkedFieldsSubfields | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
3 | |||
| getFieldLink | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| parseLinkageField | |
100.00% |
8 / 8 |
|
100.00% |
1 / 1 |
1 | |||
| getFilteredRecord | |
100.00% |
20 / 20 |
|
100.00% |
1 / 1 |
5 | |||
| getFilteringRulesForTag | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
5 | |||
| filterSubfields | |
100.00% |
12 / 12 |
|
100.00% |
1 / 1 |
6 | |||
| getWarnings | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getInternalFields | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
3 | |||
| getInternalSubfield | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
3 | |||
| 1 | <?php |
| 2 | |
| 3 | /** |
| 4 | * MARC record reader class. |
| 5 | * |
| 6 | * PHP version 7 |
| 7 | * |
| 8 | * Copyright (C) The National Library of Finland 2020-2022. |
| 9 | * |
| 10 | * This program is free software; you can redistribute it and/or modify |
| 11 | * it under the terms of the GNU General Public License version 2, |
| 12 | * as published by the Free Software Foundation. |
| 13 | * |
| 14 | * This program is distributed in the hope that it will be useful, |
| 15 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 16 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 17 | * GNU General Public License for more details. |
| 18 | * |
| 19 | * You should have received a copy of the GNU General Public License |
| 20 | * along with this program; if not, write to the Free Software |
| 21 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 22 | * |
| 23 | * @category VuFind |
| 24 | * @package MARC |
| 25 | * @author Ere Maijala <ere.maijala@helsinki.fi> |
| 26 | * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License |
| 27 | * @link https://vufind.org/wiki/development Wiki |
| 28 | */ |
| 29 | |
| 30 | namespace VuFind\Marc; |
| 31 | |
| 32 | use function in_array; |
| 33 | use function intval; |
| 34 | use function is_array; |
| 35 | use function is_string; |
| 36 | |
| 37 | /** |
| 38 | * MARC record reader class. |
| 39 | * |
| 40 | * @category VuFind |
| 41 | * @package MARC |
| 42 | * @author Ere Maijala <ere.maijala@helsinki.fi> |
| 43 | * @license http://opensource.org/licenses/gpl-2.0.php GNU General Public License |
| 44 | * @link https://vufind.org/wiki/development Wiki |
| 45 | */ |
| 46 | class MarcReader |
| 47 | { |
| 48 | /** |
| 49 | * Supported serialization formats |
| 50 | * |
| 51 | * @var array |
| 52 | */ |
| 53 | protected $serializations = [ |
| 54 | 'ISO2709' => Serialization\Iso2709::class, |
| 55 | 'JSON' => Serialization\MarcInJson::class, |
| 56 | 'MARCXML' => Serialization\MarcXml::class, |
| 57 | ]; |
| 58 | |
| 59 | /** |
| 60 | * MARC leader |
| 61 | * |
| 62 | * @var string |
| 63 | */ |
| 64 | protected $leader; |
| 65 | |
| 66 | /** |
| 67 | * MARC is stored in a multidimensional array resembling MARC-in-JSON |
| 68 | * specification by Ross Singer: |
| 69 | * [ |
| 70 | * 'leader' => '...', |
| 71 | * 'fields' => [ |
| 72 | * [ |
| 73 | * '001' => '12345' |
| 74 | * ], |
| 75 | * [ |
| 76 | * '245' => [ |
| 77 | * 'ind1' => '0', |
| 78 | * 'ind2' => '1', |
| 79 | * 'subfields' => [ |
| 80 | * ['a' => 'Title'], |
| 81 | * ['k' => 'Form'], |
| 82 | * ['k' => 'Another'], |
| 83 | * ['p' => 'Part'], |
| 84 | * ] |
| 85 | * ] |
| 86 | * ] |
| 87 | * ] |
| 88 | * ] |
| 89 | * |
| 90 | * @var array |
| 91 | * @see https://web.archive.org/web/20151112001548/http://dilettantes.code4lib.org/blog/2010/09/a-proposal-to-serialize-marc-in-json/ |
| 92 | */ |
| 93 | protected $data; |
| 94 | |
| 95 | /** |
| 96 | * Any warnings encountered when parsing a record |
| 97 | * |
| 98 | * @var array |
| 99 | */ |
| 100 | protected $warnings; |
| 101 | |
| 102 | /** |
| 103 | * Constructor |
| 104 | * |
| 105 | * @param string|array $data MARC record in one of the supported formats, or an |
| 106 | * associative array with 'leader' and 'fields' in the internal format |
| 107 | */ |
| 108 | public function __construct($data) |
| 109 | { |
| 110 | $this->setData($data); |
| 111 | } |
| 112 | |
| 113 | /** |
| 114 | * Set MARC record data |
| 115 | * |
| 116 | * @param string|array $data MARC record in one of the supported formats, or an |
| 117 | * associative array with 'leader' and 'fields' in the internal format |
| 118 | * |
| 119 | * @throws \Exception |
| 120 | * @return void |
| 121 | */ |
| 122 | public function setData($data): void |
| 123 | { |
| 124 | $this->warnings = []; |
| 125 | if (is_array($data)) { |
| 126 | if ( |
| 127 | !is_string($data['leader'] ?? null) |
| 128 | || !is_array($data['fields'] ?? null) |
| 129 | ) { |
| 130 | throw new \Exception('Invalid data array format provided'); |
| 131 | } |
| 132 | $this->data = $data; |
| 133 | return; |
| 134 | } |
| 135 | $valid = false; |
| 136 | foreach ($this->serializations as $serialization) { |
| 137 | if ($serialization::canParse($data)) { |
| 138 | $this->data = $serialization::fromString($data); |
| 139 | if (isset($this->data['warnings'])) { |
| 140 | $this->warnings = $this->data['warnings']; |
| 141 | unset($this->data['warnings']); |
| 142 | } |
| 143 | $valid = true; |
| 144 | break; |
| 145 | } |
| 146 | } |
| 147 | if (!$valid) { |
| 148 | throw new \Exception('MARC record format not recognized'); |
| 149 | } |
| 150 | // Make sure leader is 24 characters, and reset meaningless offsets: |
| 151 | if ($this->data['leader']) { |
| 152 | $leader = str_pad(substr($this->data['leader'] ?? '', 0, 24), 24); |
| 153 | $this->data['leader'] = '00000' . substr($leader, 5, 7) . '00000' |
| 154 | . substr($leader, 17); |
| 155 | } |
| 156 | } |
| 157 | |
| 158 | /** |
| 159 | * Serialize the record |
| 160 | * |
| 161 | * @param string $format Format to return (e.g. 'ISO2709' or 'MARCXML') |
| 162 | * |
| 163 | * @throws \Exception |
| 164 | * @return string |
| 165 | */ |
| 166 | public function toFormat(string $format): string |
| 167 | { |
| 168 | $serialization = $this->serializations[$format] ?? null; |
| 169 | if (null === $serialization) { |
| 170 | throw new \Exception("Unknown MARC format '$format' requested"); |
| 171 | } |
| 172 | return $serialization::toString($this->data); |
| 173 | } |
| 174 | |
| 175 | /** |
| 176 | * Return leader |
| 177 | * |
| 178 | * @return string |
| 179 | */ |
| 180 | public function getLeader(): string |
| 181 | { |
| 182 | return $this->data['leader']; |
| 183 | } |
| 184 | |
| 185 | /** |
| 186 | * Return an associative array for a data field, a string for a control field or |
| 187 | * an empty array if field does not exist |
| 188 | * |
| 189 | * @param string $fieldTag The MARC field tag to get |
| 190 | * @param array $subfieldCodes The MARC subfield codes to get, or empty for all |
| 191 | * |
| 192 | * @return array|string |
| 193 | */ |
| 194 | public function getField(string $fieldTag, ?array $subfieldCodes = null) |
| 195 | { |
| 196 | $results = $this->getFields($fieldTag, $subfieldCodes); |
| 197 | return $results[0] ?? []; |
| 198 | } |
| 199 | |
| 200 | /** |
| 201 | * Return an associative array of fields for data fields or an array of values |
| 202 | * for control fields |
| 203 | * |
| 204 | * @param string $fieldTag The MARC field tag to get |
| 205 | * @param array $subfieldCodes The MARC subfield codes to get, or empty for all. |
| 206 | * Ignored for control fields. |
| 207 | * |
| 208 | * @return array |
| 209 | */ |
| 210 | public function getFields(string $fieldTag, ?array $subfieldCodes = null): array |
| 211 | { |
| 212 | $result = []; |
| 213 | |
| 214 | foreach ($this->data['fields'] as $fieldData) { |
| 215 | if ($fieldTag && $fieldTag !== (string)key($fieldData)) { |
| 216 | continue; |
| 217 | } |
| 218 | $field = current($fieldData); |
| 219 | if (!is_array($field)) { |
| 220 | // Control field |
| 221 | $result[] = $field; |
| 222 | continue; |
| 223 | } |
| 224 | $subfields = []; |
| 225 | foreach ($field['subfields'] ?? [] as $subfield) { |
| 226 | if ( |
| 227 | $subfieldCodes |
| 228 | && !in_array((string)key($subfield), $subfieldCodes) |
| 229 | ) { |
| 230 | continue; |
| 231 | } |
| 232 | $subfields[] = [ |
| 233 | 'code' => (string)key($subfield), |
| 234 | 'data' => current($subfield), |
| 235 | ]; |
| 236 | } |
| 237 | if ($subfields) { |
| 238 | $result[] = [ |
| 239 | 'tag' => $fieldTag, |
| 240 | 'i1' => $field['ind1'], |
| 241 | 'i2' => $field['ind2'], |
| 242 | 'subfields' => $subfields, |
| 243 | ]; |
| 244 | } |
| 245 | } |
| 246 | |
| 247 | return $result; |
| 248 | } |
| 249 | |
| 250 | /** |
| 251 | * Return all fields as an array. |
| 252 | * |
| 253 | * Control fields have the following elements: |
| 254 | * - tag |
| 255 | * - data |
| 256 | * |
| 257 | * Data fields have the following elements: |
| 258 | * - tag |
| 259 | * - i1 |
| 260 | * - i2 |
| 261 | * - subfields |
| 262 | * |
| 263 | * @return array |
| 264 | */ |
| 265 | public function getAllFields() |
| 266 | { |
| 267 | $result = []; |
| 268 | |
| 269 | foreach ($this->data['fields'] as $fieldData) { |
| 270 | $tag = (string)key($fieldData); |
| 271 | $field = current($fieldData); |
| 272 | if (is_string($field)) { |
| 273 | // Control field |
| 274 | $result[] = [ |
| 275 | 'tag' => $tag, |
| 276 | 'data' => $field, |
| 277 | ]; |
| 278 | continue; |
| 279 | } |
| 280 | $subfields = []; |
| 281 | foreach ($field['subfields'] ?? [] as $subfield) { |
| 282 | $subfields[] = [ |
| 283 | 'code' => (string)key($subfield), |
| 284 | 'data' => current($subfield), |
| 285 | ]; |
| 286 | } |
| 287 | if ($subfields) { |
| 288 | $result[] = [ |
| 289 | 'tag' => $tag, |
| 290 | 'i1' => $field['ind1'], |
| 291 | 'i2' => $field['ind2'], |
| 292 | 'subfields' => $subfields, |
| 293 | ]; |
| 294 | } |
| 295 | } |
| 296 | |
| 297 | return $result; |
| 298 | } |
| 299 | |
| 300 | /** |
| 301 | * Return first subfield with the given code in the MARC field provided by |
| 302 | * getField or getFields |
| 303 | * |
| 304 | * @param array $field Result from MarcReader::getFields |
| 305 | * @param string $subfieldCode The MARC subfield code to get |
| 306 | * |
| 307 | * @return string |
| 308 | */ |
| 309 | public function getSubfield(array $field, string $subfieldCode): string |
| 310 | { |
| 311 | foreach ($field['subfields'] ?? [] as $current) { |
| 312 | if ($current['code'] == $subfieldCode) { |
| 313 | return trim($current['data']); |
| 314 | } |
| 315 | } |
| 316 | |
| 317 | return ''; |
| 318 | } |
| 319 | |
| 320 | /** |
| 321 | * Return all subfields with the given code in the MARC field provided by |
| 322 | * getField or getFields. Returns all subfields if subfieldCode is empty. |
| 323 | * |
| 324 | * @param array $field Result from MarcReader::getFields |
| 325 | * @param string $subfieldCode The MARC subfield code to get |
| 326 | * |
| 327 | * @return array |
| 328 | */ |
| 329 | public function getSubfields(array $field, string $subfieldCode = ''): array |
| 330 | { |
| 331 | $result = []; |
| 332 | foreach ($field['subfields'] ?? [] as $current) { |
| 333 | if ('' === $subfieldCode || $current['code'] == $subfieldCode) { |
| 334 | $result[] = trim($current['data']); |
| 335 | } |
| 336 | } |
| 337 | |
| 338 | return $result; |
| 339 | } |
| 340 | |
| 341 | /** |
| 342 | * Return an array of all values extracted from the specified field/subfield |
| 343 | * combination. If multiple subfields and a separator are specified, the |
| 344 | * subfields will be concatenated together in the order listed -- each entry in |
| 345 | * the array will correspond with a single MARC field. If $separator is null, |
| 346 | * the return array will contain separate entries for all subfields. |
| 347 | * |
| 348 | * @param string $fieldTag The MARC field tag to get |
| 349 | * @param array $subfieldCodes The MARC subfield codes to get |
| 350 | * @param string $separator Subfield separator string. Set to null to disable |
| 351 | * concatenation of subfields. |
| 352 | * |
| 353 | * @return array |
| 354 | */ |
| 355 | public function getFieldsSubfields( |
| 356 | string $fieldTag, |
| 357 | array $subfieldCodes, |
| 358 | ?string $separator = ' ' |
| 359 | ): array { |
| 360 | $result = []; |
| 361 | |
| 362 | foreach ($this->getInternalFields($fieldTag) as $field) { |
| 363 | if (!isset($field['subfields'])) { |
| 364 | continue; |
| 365 | } |
| 366 | $subfields = []; |
| 367 | foreach ($field['subfields'] ?? [] as $subfield) { |
| 368 | if ( |
| 369 | $subfieldCodes |
| 370 | && !in_array((string)key($subfield), $subfieldCodes) |
| 371 | ) { |
| 372 | continue; |
| 373 | } |
| 374 | if (null !== $separator) { |
| 375 | $subfields[] = current($subfield); |
| 376 | } else { |
| 377 | $result[] = current($subfield); |
| 378 | } |
| 379 | } |
| 380 | if (null !== $separator && $subfields) { |
| 381 | $result[] = implode($separator, $subfields); |
| 382 | } |
| 383 | } |
| 384 | |
| 385 | return $result; |
| 386 | } |
| 387 | |
| 388 | /** |
| 389 | * Return an associative array for a linked field such as 880 (Alternate Graphic |
| 390 | * Representation) or an empty array if field does not exist |
| 391 | * |
| 392 | * @param string $fieldTag The MARC field that contains the linked fields |
| 393 | * @param string $linkedFieldTag The linked MARC field tag to get |
| 394 | * @param string $occurrence The occurrence number to get; empty string for |
| 395 | * whatever comes first |
| 396 | * @param array $subfieldCodes The MARC subfield codes to get, or empty for all |
| 397 | * |
| 398 | * @return array |
| 399 | */ |
| 400 | public function getLinkedField( |
| 401 | string $fieldTag, |
| 402 | string $linkedFieldTag, |
| 403 | string $occurrence = '', |
| 404 | ?array $subfieldCodes = null |
| 405 | ): array { |
| 406 | $results |
| 407 | = $this->getLinkedFields($fieldTag, $linkedFieldTag, $subfieldCodes); |
| 408 | foreach ($results as $field) { |
| 409 | if (empty($occurrence) || $occurrence === $field['link']['occurrence']) { |
| 410 | return $field; |
| 411 | } |
| 412 | } |
| 413 | return []; |
| 414 | } |
| 415 | |
| 416 | /** |
| 417 | * Return an array of associative arrays for a linked field such as 880 |
| 418 | * (Alternate Graphic Representation) |
| 419 | * |
| 420 | * @param string $fieldTag The MARC field that contains the linked fields |
| 421 | * @param string $linkedFieldTag The linked MARC field tag to get |
| 422 | * @param array $subfieldCodes The MARC subfield codes to get, or empty for all |
| 423 | * |
| 424 | * @return array |
| 425 | */ |
| 426 | public function getLinkedFields( |
| 427 | string $fieldTag, |
| 428 | string $linkedFieldTag, |
| 429 | ?array $subfieldCodes = null |
| 430 | ): array { |
| 431 | $result = []; |
| 432 | |
| 433 | foreach ($this->getInternalFields($fieldTag) as $field) { |
| 434 | if (is_string($field)) { |
| 435 | // Control field |
| 436 | continue; |
| 437 | } |
| 438 | $link |
| 439 | = $this->parseLinkageField($this->getInternalSubfield($field, '6')); |
| 440 | if ($link['field'] !== $linkedFieldTag) { |
| 441 | continue; |
| 442 | } |
| 443 | $subfields = []; |
| 444 | foreach ($field['subfields'] ?? [] as $subfield) { |
| 445 | if ( |
| 446 | $subfieldCodes |
| 447 | && !in_array((string)key($subfield), $subfieldCodes) |
| 448 | ) { |
| 449 | continue; |
| 450 | } |
| 451 | $subfields[] = [ |
| 452 | 'code' => (string)key($subfield), |
| 453 | 'data' => current($subfield), |
| 454 | ]; |
| 455 | } |
| 456 | if ($subfields) { |
| 457 | $result[] = [ |
| 458 | 'tag' => $fieldTag, |
| 459 | 'i1' => $field['ind1'], |
| 460 | 'i2' => $field['ind2'], |
| 461 | 'subfields' => $subfields, |
| 462 | 'link' => $link, |
| 463 | ]; |
| 464 | } |
| 465 | } |
| 466 | |
| 467 | return $result; |
| 468 | } |
| 469 | |
| 470 | /** |
| 471 | * Return an array of all values extracted from the specified linked |
| 472 | * field/subfield combination. If multiple subfields and a separator are |
| 473 | * specified, the subfields will be concatenated together in the order listed |
| 474 | * -- each entry in the array will correspond with a single MARC field. If |
| 475 | * $separator is null, the return array will contain separate entries for all |
| 476 | * subfields. |
| 477 | * |
| 478 | * @param string $fieldTag The MARC field that contains the linked fields |
| 479 | * @param string $linkedFieldTag The linked MARC field tag to get |
| 480 | * @param array $subfieldCodes The MARC subfield codes to get |
| 481 | * @param string $separator Subfield separator string. Set to null to |
| 482 | * disable concatenation of subfields. |
| 483 | * |
| 484 | * @return array |
| 485 | */ |
| 486 | public function getLinkedFieldsSubfields( |
| 487 | string $fieldTag, |
| 488 | string $linkedFieldTag, |
| 489 | array $subfieldCodes, |
| 490 | ?string $separator = ' ' |
| 491 | ): array { |
| 492 | $result = []; |
| 493 | foreach ($this->getLinkedFields($fieldTag, $linkedFieldTag, $subfieldCodes) as $field) { |
| 494 | $subfields = $this->getSubfields($field); |
| 495 | if (null !== $separator) { |
| 496 | $result[] = implode($separator, $subfields); |
| 497 | } else { |
| 498 | $result = array_merge($result, $subfields); |
| 499 | } |
| 500 | } |
| 501 | return $result; |
| 502 | } |
| 503 | |
| 504 | /** |
| 505 | * Get linked field data from subfield 6 |
| 506 | * |
| 507 | * @param array $field Field |
| 508 | * |
| 509 | * @return array |
| 510 | */ |
| 511 | public function getFieldLink(array $field): array |
| 512 | { |
| 513 | return $this->parseLinkageField($this->getSubfield($field, '6')); |
| 514 | } |
| 515 | |
| 516 | /** |
| 517 | * Parse a linkage field |
| 518 | * |
| 519 | * @param string $link Linkage field |
| 520 | * |
| 521 | * @return array |
| 522 | */ |
| 523 | public function parseLinkageField(string $link): array |
| 524 | { |
| 525 | $linkParts = explode('/', $link, 3); |
| 526 | $targetParts = explode('-', $linkParts[0]); |
| 527 | return [ |
| 528 | 'field' => $targetParts[0], |
| 529 | 'occurrence' => $targetParts[1] ?? '', |
| 530 | 'script' => $linkParts[1] ?? '', |
| 531 | 'orientation' => $linkParts[2] ?? '', |
| 532 | ]; |
| 533 | } |
| 534 | |
| 535 | /** |
| 536 | * Return a copy of the record with the specified fields and/or subfields |
| 537 | * removed. |
| 538 | * |
| 539 | * Each rule can have the following elements: |
| 540 | * |
| 541 | * tag - Tag the rule applies to (a regular expression). |
| 542 | * subfields - Subfields codes to remove (a regular expression, optional). |
| 543 | * Default is to remove all subfields (and the field). |
| 544 | * |
| 545 | * Examples: |
| 546 | * |
| 547 | * $result = $reader->getFilteredRecord( |
| 548 | * [ |
| 549 | * [ |
| 550 | * 'tag' => '9..' |
| 551 | * ] |
| 552 | * ] |
| 553 | * ); |
| 554 | * |
| 555 | * $result = $reader->getFilteredRecord( |
| 556 | * [ |
| 557 | * [ |
| 558 | * 'tag' => '...', |
| 559 | * 'subfields' => '0' |
| 560 | * ] |
| 561 | * ] |
| 562 | * ); |
| 563 | * |
| 564 | * @param array $rules Array of filtering rules |
| 565 | * |
| 566 | * @return MarcReader |
| 567 | */ |
| 568 | public function getFilteredRecord(array $rules): MarcReader |
| 569 | { |
| 570 | $resultFields = []; |
| 571 | foreach ($this->data['fields'] as $fieldData) { |
| 572 | $tag = (string)key($fieldData); |
| 573 | $field = current($fieldData); |
| 574 | $fieldRules = $this->getFilteringRulesForTag($rules, $tag); |
| 575 | if ($fieldRules) { |
| 576 | if (is_string($field)) { |
| 577 | // Control field, filter out completely |
| 578 | continue; |
| 579 | } |
| 580 | $field['subfields'] = $this->filterSubfields( |
| 581 | $fieldRules, |
| 582 | $field['subfields'] |
| 583 | ); |
| 584 | if (!$field['subfields']) { |
| 585 | // No subfields left, drop the field |
| 586 | continue; |
| 587 | } |
| 588 | $resultFields[] = [$tag => $field]; |
| 589 | } else { |
| 590 | $resultFields[] = [$tag => $field]; |
| 591 | } |
| 592 | } |
| 593 | return new MarcReader( |
| 594 | [ |
| 595 | 'leader' => $this->data['leader'], |
| 596 | 'fields' => $resultFields, |
| 597 | ] |
| 598 | ); |
| 599 | } |
| 600 | |
| 601 | /** |
| 602 | * Get filtering rules matching a field tag |
| 603 | * |
| 604 | * @param array $rules Filtering rules |
| 605 | * @param string $tag Field tag |
| 606 | * |
| 607 | * @return array |
| 608 | */ |
| 609 | protected function getFilteringRulesForTag(array $rules, string $tag): array |
| 610 | { |
| 611 | $result = []; |
| 612 | foreach ($rules as $rule) { |
| 613 | if ( |
| 614 | preg_match('/' . $rule['tag'] . '/', $tag) |
| 615 | && (!isset($rule['subfields']) || intval($tag) >= 10) |
| 616 | ) { |
| 617 | $result[] = $rule; |
| 618 | } |
| 619 | } |
| 620 | return $result; |
| 621 | } |
| 622 | |
| 623 | /** |
| 624 | * Filter subfields |
| 625 | * |
| 626 | * @param array $rules Filtering rules |
| 627 | * @param array $subfields Subfields |
| 628 | * |
| 629 | * @return array |
| 630 | */ |
| 631 | protected function filterSubfields(array $rules, array $subfields): array |
| 632 | { |
| 633 | foreach ($rules as $rule) { |
| 634 | if (!isset($rule['subfields'])) { |
| 635 | // No subfields specified, filter out all of them |
| 636 | return []; |
| 637 | } |
| 638 | $remaining = []; |
| 639 | foreach ($subfields as $subfield) { |
| 640 | $code = (string)key($subfield); |
| 641 | if (!preg_match('/' . $rule['subfields'] . '/', $code)) { |
| 642 | $remaining[] = $subfield; |
| 643 | } |
| 644 | } |
| 645 | if (!$remaining) { |
| 646 | return []; |
| 647 | } |
| 648 | $subfields = $remaining; |
| 649 | } |
| 650 | |
| 651 | return $subfields; |
| 652 | } |
| 653 | |
| 654 | /** |
| 655 | * Get any warnings encountered when parsing a record |
| 656 | * |
| 657 | * @return array |
| 658 | */ |
| 659 | public function getWarnings(): array |
| 660 | { |
| 661 | return $this->warnings; |
| 662 | } |
| 663 | |
| 664 | /** |
| 665 | * Return fields by tag in internal format |
| 666 | * |
| 667 | * @param string $tag Field tag |
| 668 | * |
| 669 | * @return array |
| 670 | */ |
| 671 | protected function getInternalFields(string $tag): array |
| 672 | { |
| 673 | $result = []; |
| 674 | foreach ($this->data['fields'] as $field) { |
| 675 | $fieldTag = (string)key($field); |
| 676 | if ($fieldTag === $tag) { |
| 677 | $result[] = current($field); |
| 678 | } |
| 679 | } |
| 680 | return $result; |
| 681 | } |
| 682 | |
| 683 | /** |
| 684 | * Return first subfield with the given code in the internal MARC field |
| 685 | * |
| 686 | * @param array $field Internal MARC field |
| 687 | * @param string $subfieldCode The MARC subfield code to get |
| 688 | * |
| 689 | * @return string |
| 690 | */ |
| 691 | protected function getInternalSubfield( |
| 692 | array $field, |
| 693 | string $subfieldCode |
| 694 | ): string { |
| 695 | foreach ($field['subfields'] ?? [] as $subfield) { |
| 696 | if ((string)key($subfield) === $subfieldCode) { |
| 697 | return trim(current($subfield)); |
| 698 | } |
| 699 | } |
| 700 | return ''; |
| 701 | } |
| 702 | } |