From a66b19342f105546adfb9cd9189f862e8a9c0b15 Mon Sep 17 00:00:00 2001 From: Chris Dyer Date: Mon, 29 Dec 2014 02:02:27 -0500 Subject: finnish case markings --- corpus/support/token_patterns | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'corpus') diff --git a/corpus/support/token_patterns b/corpus/support/token_patterns index e51e5e72..12558cdd 100644 --- a/corpus/support/token_patterns +++ b/corpus/support/token_patterns @@ -1,6 +1,7 @@ /^(al|el|ul|e)\-[a-z]+$/ +/\.(fi|fr|es|co\.uk|de)$/ +/:[a-zä]+$/ /^((а|А)(ль|ш)|уль)-\p{Cyrillic}+$/ -/^(юл)-\p{Cyrillic}+$/ /^\p{Cyrillic}\.\p{Cyrillic}\.$/ /^(\d|\d\d|\d\d\d)\.$/ -- cgit v1.2.3