summaryrefslogtreecommitdiff
path: root/corpus/support/token_patterns
diff options
context:
space:
mode:
authorChris Dyer <cdyer@allegro.clab.cs.cmu.edu>2013-01-21 17:28:19 -0500
committerChris Dyer <cdyer@allegro.clab.cs.cmu.edu>2013-01-21 17:28:19 -0500
commitee681f3d0337dc3d93c25de373a50fbda69252fe (patch)
tree66a89cdc31969aa36440bb7061fbe39f2ffdd4f6 /corpus/support/token_patterns
parente1f71a6ce868d116f04082b697a8d61afcd625f1 (diff)
tokenizer support for utf8 patterns
Diffstat (limited to 'corpus/support/token_patterns')
-rw-r--r--corpus/support/token_patterns1
1 files changed, 1 insertions, 0 deletions
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)\.$/