Hashar has uploaded a new change for review.

  https://gerrit.wikimedia.org/r/71718


Change subject: test word boundaries in devanagari words
......................................................................

test word boundaries in devanagari words

Follow up on bug report.  This highlight PCRE would only detects
devanagari word boundaries while in unicode mode (PCRE modifier u).

bug: 46773
Change-Id: I9ecce62f3ed909da4b5e3c325695ee514dd4256c
---
A tests/phpunit/includes/bug46773Test.php
1 file changed, 41 insertions(+), 0 deletions(-)


  git pull ssh://gerrit.wikimedia.org:29418/mediawiki/core 
refs/changes/18/71718/1

diff --git a/tests/phpunit/includes/bug46773Test.php 
b/tests/phpunit/includes/bug46773Test.php
new file mode 100644
index 0000000..5294767
--- /dev/null
+++ b/tests/phpunit/includes/bug46773Test.php
@@ -0,0 +1,41 @@
+<?php
+/**
+ * Test regex wordboundary (\b) with devanagari words
+ */
+class bug46773Test extends MediaWikiTestCase {
+
+       /**
+        * @dataProvider provideWordPatternsInMarathi
+        */
+       function testRegexBoundariesDevanagari( $expected, $pattern, $subject ) 
{
+               if($expected) {
+                       $this->assertRegexp( $pattern, $subject );
+               } else {
+                       $this->assertNotRegexp( $pattern, $subject );
+               }
+       }
+
+       /**
+        * @dataProvider provideWordPatternsInMarathi
+        */
+       function testRegexBoundariesDevanagariInUnicodeMode( $expected, 
$pattern, $subject ) {
+               $pattern .= 'u';  # enable unicode mode
+               $this->testRegexBoundariesDevanagari( $expected, $pattern, 
$subject );
+       }
+
+       function provideWordPatternsInMarathi () {
+               # See https://bugzilla.wikimedia.org/46773
+
+               # FIXME make sure the tests are what they are meant to be
+               $MATCH = true;
+               $REJECT = false;
+
+               return array(
+                       # match?, pattern, subject
+                       array( $REJECT, '/तू\b/', 'तूप' ),
+                       array( $REJECT, '/\bतू/', 'धातू' ),
+                       array( $REJECT, '/\bतू\b/', 'दुकानातून' ),
+               );
+       }
+
+}

-- 
To view, visit https://gerrit.wikimedia.org/r/71718
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings

Gerrit-MessageType: newchange
Gerrit-Change-Id: I9ecce62f3ed909da4b5e3c325695ee514dd4256c
Gerrit-PatchSet: 1
Gerrit-Project: mediawiki/core
Gerrit-Branch: master
Gerrit-Owner: Hashar <[email protected]>

_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits

Reply via email to