From fba0f3db9aa896807e3932f9d3323767cedd9338 Mon Sep 17 00:00:00 2001 From: Chris Dyer Date: Mon, 21 Jan 2013 17:28:19 -0500 Subject: tokenizer support for utf8 patterns --- corpus/support/token_patterns | 1 + 1 file changed, 1 insertion(+) (limited to 'corpus/support/token_patterns') diff --git a/corpus/support/token_patterns b/corpus/support/token_patterns index 8e69432b..b25ac6de 100644 --- a/corpus/support/token_patterns +++ b/corpus/support/token_patterns @@ -1,3 +1,4 @@ /^(al|el|ul|e)\-[a-z]+$/ +/^((а|А)(ль|ш)|уль)-\p{Cyrillic}+$/ /^(\d|\d\d|\d\d\d)\.$/ -- cgit v1.2.3