tokenize 0.1.2 → 0.1.3
raw patch · 2 files changed
+3/−3 lines, 2 files
Files
- NLP/Tokenize.hs +2/−2
- tokenize.cabal +1/−1
NLP/Tokenize.hs view
@@ -78,12 +78,12 @@ | True = E [Right x] -- | Split common contractions off and freeze them.--- | Currently deals with: 's, 'd, 've, 'll+-- | Currently deals with: 'm, 's, 'd, 've, 'll contractions :: Tokenizer contractions x = case catMaybes . map (splitSuffix x) $ cts of [] -> return x ((w,s):_) -> E [ Right w,Left s]- where cts = ["'s","'d","'ve","'ll"]+ where cts = ["'m","'s","'d","'ve","'ll"] splitSuffix w sfx = let w' = reverse w len = length sfx
tokenize.cabal view
@@ -7,7 +7,7 @@ -- The package version. See the Haskell package versioning policy -- (http://www.haskell.org/haskellwiki/Package_versioning_policy) for -- standards guiding when and how versions should be incremented.-Version: 0.1.2+Version: 0.1.3 -- A short (one-line) description of the package. Synopsis: Simple tokenizer for English text.