diff options
author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
---|---|---|
committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2013-03-03 12:06:43 +0100 |
commit | f7f9048f8e4d34682f17bfd050d238005feb3ee3 (patch) | |
tree | fa20fa16b0f5a8009a9254622b65ebeaec049399 /corpus/support/token_patterns | |
parent | 9d306b30c9abba995ba35243e5cb461bb472a61f (diff) | |
parent | 12f2eab0e7dc7167af47cddf8ef88968656277da (diff) |
Merge branch 'master' of github.com:pks/cdec-dtrain
Diffstat (limited to 'corpus/support/token_patterns')
-rw-r--r-- | corpus/support/token_patterns | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/corpus/support/token_patterns b/corpus/support/token_patterns index 8e69432b..de64fb2a 100644 --- a/corpus/support/token_patterns +++ b/corpus/support/token_patterns @@ -1,3 +1,5 @@ /^(al|el|ul|e)\-[a-z]+$/ +/^((а|А)(ль|ш)|уль)-\p{Cyrillic}+$/ +/^\p{Cyrillic}\.\p{Cyrillic}\.$/ /^(\d|\d\d|\d\d\d)\.$/ |