webapp/bookstack
1
0
Fork 0
mirror of https://github.com/BookStackApp/BookStack.git synced 2025-07-31 15:24:31 +03:00
Code Activity

Searching: Added custom tokenizer that considers soft delimiters.

Browse Source 
This changes indexing so that a.b now indexes as "a", "b" AND "a.b"
instead of just the first two, for periods and hypens, so terms
containing those characters can be searched within.

Adds hypens as a delimiter - #2095
This commit is contained in:
Dan Brown
2025-02-14 19:01:51 +00:00
parent 45a15b4792
commit f4449928f8
4 changed files with 121 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/Search/SearchIndexingTest.php
View File

@ -74,4 +74,20 @@ class SearchIndexingTest extends TestCase
$this->assertEquals(3, $scoreByTerm->get('Animal'));
$this->assertEquals(3, $scoreByTerm->get('SuperImportant'));
}
public function test_terms_containing_punctuation_within_retain_original_form_and_split_form_in_index()
{
$page = $this->entities->newPage(['html' => '<p>super.duper awesome-beans big- barry cheese.</p><p>biscuits</p><p>a-bs</p>']);
$scoreByTerm = $page->searchTerms()->pluck('score', 'term');
$expected = ['super', 'duper', 'super.duper', 'awesome-beans', 'awesome', 'beans', 'big', 'barry', 'cheese', 'biscuits', 'a-bs', 'a', 'bs'];
foreach ($expected as $term) {
$this->assertNotNull($scoreByTerm->get($term), "Failed asserting that \"$term\" is indexed");
}
$nonExpected = ['big-', 'big-barry', 'cheese.', 'cheese.biscuits'];
foreach ($nonExpected as $term) {
$this->assertNull($scoreByTerm->get($term), "Failed asserting that \"$term\" is not indexed");
}
}
}