Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
Total | |
0.00% |
0 / 6 |
n/a |
0 / 0 |
CRAP | n/a |
0 / 0 |
1 | <?php |
2 | |
3 | /** |
4 | * Romanian (ro) stop words with ș & ț (commas) instead of ş & ţ (cedillas) |
5 | * for Elasticsearch analysis config. |
6 | * Adapted from the list used by Lucene: |
7 | * - https://github.com/apache/lucene/blob/main/lucene/analysis/common/src/resources/org/apache/lucene/analysis/ro/stopwords.txt |
8 | * which was originally created by Jacques Savoy under the BSD license: |
9 | * - http://members.unine.ch/jacques.savoy/clef/roumanianST.txt |
10 | */ |
11 | |
12 | $romanianCommaStopwords = [ |
13 | 'acești', 'aceștia', 'aș', 'așadar', 'ăștia', 'ați', 'aveți', 'câți', 'cîți', 'deși', |
14 | 'ești', 'fiți', 'îți', 'mulți', 'niște', 'noștri', 'și', 'sînteți', 'sunteți', 'ți', |
15 | 'ție', 'toți', 'totuși', 'voștri', |
16 | ]; |
17 | |
18 | return $romanianCommaStopwords; |