1
0
Fork 0
mirror of https://we.phorge.it/source/phorge.git synced 2024-11-10 08:52:39 +01:00

Tokenize datasource indexes on "(" and ")"

Summary:
Fixes T11955. Milestone names are currently tokenizing and indexing awkwardly. For example, "A (B C D)" becomes the tokens "A", "(B", "C" and "D)".

The token "(B" can't be searched for since "(" is tokenized on the client.

Instead, tokenize "A (B C D)" into "A", "B", "C", "D".

Test Plan:
  - Added unit tests.
  - Used `bin/search index --type project --force` to reindex.
  - Searched for "A", "B", "C", "D", etc., for real examples.
  - Now, found milestones more consistently.
  - Also serached for `viewer()`, `members()`, etc.

Reviewers: chad

Reviewed By: chad

Maniphest Tasks: T11955

Differential Revision: https://secure.phabricator.com/D17012
This commit is contained in:
epriestley 2016-12-09 05:28:25 -08:00
parent cde37acb4b
commit 5a95efaa4b
2 changed files with 15 additions and 1 deletions

View file

@ -141,7 +141,9 @@ abstract class PhabricatorTypeaheadDatasource extends Phobject {
return array();
}
$tokens = preg_split('/[\s\[\]-]+/u', $string);
// NOTE: Splitting on "(" and ")" is important for milestones.
$tokens = preg_split('/[\s\[\]\(\)-]+/u', $string);
$tokens = array_unique($tokens);
// Make sure we don't return the empty token, as this will boil down to a

View file

@ -27,6 +27,18 @@ final class PhabricatorTypeaheadDatasourceTestCase
$this->assertTokenization(
'[[ brackets ]] [-] ]-[ tie-fighters',
array('brackets', 'tie', 'fighters'));
$this->assertTokenization(
'viewer()',
array('viewer'));
$this->assertTokenization(
'Work (Done)',
array('work', 'done'));
$this->assertTokenization(
'A (B C D)',
array('a', 'b', 'c', 'd'));
}
private function assertTokenization($input, $expect) {