Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
0.00% |
0 / 29 |
|
0.00% |
0 / 3 |
CRAP | |
0.00% |
0 / 1 |
| QtiItemContentTokenizer | |
0.00% |
0 / 29 |
|
0.00% |
0 / 3 |
110 | |
0.00% |
0 / 1 |
| getStrings | |
0.00% |
0 / 25 |
|
0.00% |
0 / 1 |
56 | |||
| getFileReferenceSerializer | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| applyFilters | |
0.00% |
0 / 3 |
|
0.00% |
0 / 1 |
6 | |||
| 1 | <?php |
| 2 | |
| 3 | /** |
| 4 | * This program is free software; you can redistribute it and/or |
| 5 | * modify it under the terms of the GNU General Public License |
| 6 | * as published by the Free Software Foundation; under version 2 |
| 7 | * of the License (non-upgradable). |
| 8 | * |
| 9 | * This program is distributed in the hope that it will be useful, |
| 10 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 11 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 12 | * GNU General Public License for more details. |
| 13 | * |
| 14 | * You should have received a copy of the GNU General Public License |
| 15 | * along with this program; if not, write to the Free Software |
| 16 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 17 | * |
| 18 | * Copyright (c) 2014-2021 (original work) Open Assessment Technologies SA (under the project TAO-PRODUCT); |
| 19 | * |
| 20 | */ |
| 21 | |
| 22 | namespace oat\taoQtiItem\model\search; |
| 23 | |
| 24 | use core_kernel_classes_Resource; |
| 25 | use oat\generis\model\fileReference\FileReferenceSerializer; |
| 26 | use oat\generis\model\OntologyAwareTrait; |
| 27 | use oat\oatbox\service\ConfigurableService; |
| 28 | use oat\tao\model\search\tokenizer\ResourceTokenizer; |
| 29 | use oat\taoQtiItem\model\qti\Service; |
| 30 | use oat\taoQtiItem\model\search\Tokenizer\Filter\TokenFilterInterface; |
| 31 | use taoItems_models_classes_ItemsService; |
| 32 | |
| 33 | class QtiItemContentTokenizer extends ConfigurableService implements ResourceTokenizer |
| 34 | { |
| 35 | use OntologyAwareTrait; |
| 36 | |
| 37 | public const SERVICE_ID = 'taoQtiItem/QtiItemContentTokenizer'; |
| 38 | public const OPTION_FILTERS = 'data_filters'; |
| 39 | |
| 40 | /** |
| 41 | * Get tokens as string[] extracted from a QTI file |
| 42 | * XML inside qti.xml is parsed and all text is tokenized |
| 43 | * |
| 44 | * @return array |
| 45 | */ |
| 46 | public function getStrings(core_kernel_classes_Resource $resource) |
| 47 | { |
| 48 | try { |
| 49 | $ontologyFiles = $resource->getPropertyValues( |
| 50 | $this->getProperty(taoItems_models_classes_ItemsService::PROPERTY_ITEM_CONTENT) |
| 51 | ); |
| 52 | if (empty($ontologyFiles)) { |
| 53 | return []; |
| 54 | } |
| 55 | } catch (\core_kernel_classes_EmptyProperty $e) { |
| 56 | return []; |
| 57 | } |
| 58 | |
| 59 | $file = $this->getFileReferenceSerializer() |
| 60 | ->unserializeDirectory(reset($ontologyFiles)) |
| 61 | ->getFile(Service::QTI_ITEM_FILE); |
| 62 | |
| 63 | if (!$file->exists()) { |
| 64 | return []; |
| 65 | } |
| 66 | |
| 67 | $content = $file->read(); |
| 68 | if (empty($content)) { |
| 69 | return []; |
| 70 | } |
| 71 | |
| 72 | $dom = new \DOMDocument(); |
| 73 | $dom->loadXML($content); |
| 74 | $xpath = new \DOMXPath($dom); |
| 75 | |
| 76 | $textNodes = $xpath->query('//text()'); |
| 77 | unset($xpath); |
| 78 | |
| 79 | $contentStrings = []; |
| 80 | foreach ($textNodes as $textNode) { |
| 81 | if ($this->applyFilters($textNode->wholeText)) { |
| 82 | $contentStrings[] = trim($textNode->wholeText); |
| 83 | } |
| 84 | } |
| 85 | |
| 86 | return $contentStrings; |
| 87 | } |
| 88 | |
| 89 | protected function getFileReferenceSerializer(): FileReferenceSerializer |
| 90 | { |
| 91 | return $this->getServiceManager()->get(FileReferenceSerializer::SERVICE_ID); |
| 92 | } |
| 93 | |
| 94 | protected function applyFilters(string $data): string |
| 95 | { |
| 96 | /** @var TokenFilterInterface $filter */ |
| 97 | foreach ($this->getOption(self::OPTION_FILTERS, []) as $filter) { |
| 98 | $output = $filter->filter($output ?? $data); |
| 99 | } |
| 100 | return $output ?? $data; |
| 101 | } |
| 102 | } |