concraft-pl 0.7.3 → 0.7.4

raw patch · 3 files changed

+21/−14 lines, 3 filesdep ~aesondep ~mtldep ~textPVP ok

version bump matches the API change (PVP)

Dependency ranges changed: aeson, mtl, text, transformers

API changes (from Hackage documentation)

Files

• changelog +3/−0
• concraft-pl.cabal +5/−5
• src/NLP/Concraft/Polish/Maca.hs +13/−9

@@ -1,5 +1,8 @@ -*-change-log-*- +0.7.4	Nov 2014+	* Ignore non-printable characters for compatibility with Maca+ 0.7.0	Nov 2013 	* Output guessing results for unknown words  	* Allow "--noana" option in the client/server mode

@@ -1,5 +1,5 @@ name:               concraft-pl-version:            0.7.3+version:            0.7.4 synopsis:           Morphological tagger for Polish description:     A morphological tagger for Polish based on the concraft library.@@ -28,12 +28,12 @@       , sgd                     >= 0.3.3    && < 0.4       , containers              >= 0.4      && < 0.6       , bytestring              >= 0.9      && < 0.11-      , text                    >= 0.11     && < 1.2-      , aeson                   >= 0.6      && < 0.8+      , text                    >= 0.11     && < 1.3+      , aeson                   >= 0.6      && < 0.9       , binary                  >= 0.5      && < 0.8       , process                 >= 1.1      && < 1.3-      , mtl                     >= 2.0      && < 2.2-      , transformers            >= 0.2      && < 0.4+      , mtl                     >= 2.0      && < 2.3+      , transformers            >= 0.2      && < 0.5       , network                 >= 2.3      && < 2.7       , lazy-io                 >= 0.1      && < 0.2       , split                   >= 0.2      && < 0.3

@@ -213,29 +213,33 @@ putMaca x (MacaPool c) = writeChan c x  --- | Analyse paragraph with Maca.--- The function is thread-safe.+-- | Analyse paragraph with Maca.  The function is thread-safe.  As a+-- pre-processing step, all non-printable characters are removed from+-- the input (based on empirical observations, Maca behaves likewise). macaPar :: MacaPool -> T.Text -> IO [Sent Tag]-macaPar pool par = do+macaPar pool par0 = do+    let par = T.filter C.isPrint par0     maca <- popMaca pool     doMacaPar maca par `finally` putMaca maca pool  -------------------------------- Weight-----------------------------+------------------------------------------------------------+-- Weight: a number of non-space characters+------------------------------------------------------------  --- | A number of non-space characters in a text.+-- | A weight of a text. textWeight :: T.Text -> Int+-- textWeight = T.length . T.filter C.isAlphaNum textWeight = T.length . T.filter (not . C.isSpace)+-- textWeight = T.length . T.filter ((&&) <$> not . C.isSpace <*> C.isPrint)  --- | A number of non-space characters in a sentence.+-- | A weight of a segment. segWeight :: Seg t -> Int segWeight = textWeight . orth . word  --- | A number of non-space characters in a sentence.+-- | A weight of a sentence. sentWeight :: Sent t -> Int sentWeight = sum . map segWeight