Skip to content

Commit 3b9961f

Browse files
committed
don't capitalize 'ⱬ'
Up until at least 2008, MediaWiki didn't capitalize this character: https://en.wikipedia.org/wiki/%E2%B1%AC?oldid=453440263&action=history
1 parent 5c18d75 commit 3b9961f

File tree

1 file changed

+2
-1
lines changed

1 file changed

+2
-1
lines changed

core/src/main/scala/org/dbpedia/extraction/util/RichString.scala

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ object RichString
1414
{
1515
implicit def wrapString(str : String) = new RichString(str)
1616

17-
private val dontCapitalize = Array('ß', 'fi', 'ff', 'fl', 'ffi', 'ffl', 'ſt', 'st')
17+
private val dontCapitalize = Array('ß', 'fi', 'ff', 'fl', 'ffi', 'ffl', 'ſt', 'st', 'ⱬ')
1818

1919
// sort array so we can use binary search
2020
{ sort(dontCapitalize) }
@@ -36,6 +36,7 @@ class RichString(str : String)
3636
* 'ffl' -> "FFL"
3737
* 'ſt' -> "ST"
3838
* 'st' -> "ST"
39+
* 'ⱬ' -> "Ⱬ"
3940
*
4041
* TODO: there are probably many other cases. Maybe we should use Character.toUpperCase()
4142
* instead of String.toUpperCase()? What would MediaWiki do?

0 commit comments

Comments
 (0)