Soeren.oldag has submitted this change and it was merged.
Change subject: Fix tests and set new threshold
......................................................................
Fix tests and set new threshold
Conflicts:
includes/CrossCheck/Comparer/StringComparer.php
tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
tests/phpunit/Violations/CrossCheckViolationContextTest.php
Change-Id: I0463ab43320bf0b531c45b6a7dc2bef55803f612
---
M includes/CrossCheck/Comparer/StringComparer.php
M tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
2 files changed, 17 insertions(+), 4 deletions(-)
Approvals:
Soeren.oldag: Verified; Looks good to me, approved
diff --git a/includes/CrossCheck/Comparer/StringComparer.php
b/includes/CrossCheck/Comparer/StringComparer.php
index 0c84ab6..d20e625 100755
--- a/includes/CrossCheck/Comparer/StringComparer.php
+++ b/includes/CrossCheck/Comparer/StringComparer.php
@@ -17,7 +17,7 @@
/**
* Threshold for matching compliance in prefix/suffix similarity checks
*/
- const SIMILARITY_THRESHOLD = 0.8;
+ const SIMILARITY_THRESHOLD = 0.75;
/**
* Compares two strings with each other.
@@ -220,6 +220,4 @@
return $percentage;
}
-
-
-}
\ No newline at end of file
+}
diff --git a/tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
b/tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
index 0491277..b3db2f8 100755
--- a/tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
+++ b/tests/phpunit/CrossCheck/Comparer/StringComparerTest.php
@@ -112,6 +112,11 @@
'oobar',
CompareResult::STATUS_PARTIAL_MATCH
),
+ array(
+ 'New York City',
+ 'New York City, NY',
+ CompareResult::STATUS_PARTIAL_MATCH
+ ),
// levenshtein partial match
array(
'foobar',
@@ -131,6 +136,11 @@
array(
'Schlossstraße',
'Schloßstraße',
+ CompareResult::STATUS_PARTIAL_MATCH
+ ),
+ array(
+ 'Yoko Ono',
+ 'Yōko Ono',
CompareResult::STATUS_PARTIAL_MATCH
),
// mismatches
@@ -158,6 +168,11 @@
'Johanna von Österreich',
'Johanna',
CompareResult::STATUS_MISMATCH
+ ),
+ array(
+ 'New York',
+ 'New York, NY',
+ CompareResult::STATUS_MISMATCH
)
);
}
--
To view, visit https://gerrit.wikimedia.org/r/216674
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings
Gerrit-MessageType: merged
Gerrit-Change-Id: I0463ab43320bf0b531c45b6a7dc2bef55803f612
Gerrit-PatchSet: 2
Gerrit-Project: mediawiki/extensions/WikidataQualityExternalValidation
Gerrit-Branch: v1
Gerrit-Owner: Dominic.sauer <[email protected]>
Gerrit-Reviewer: Soeren.oldag <[email protected]>
_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits