nerf 0.2.0 → 0.2.1

raw patch · 2 files changed

+56/−2 lines, 2 files

Files

NLP/Nerf/Dict/PNET.hs +53/−0
nerf.cabal +3/−2

+ NLP/Nerf/Dict/PNET.hs view

@@ -0,0 +1,53 @@+{-# LANGUAGE OverloadedStrings #-}++-- | Polish Named Entity Triggers <http://zil.ipipan.waw.pl/PNET> dictionary.++module NLP.Nerf.Dict.PNET+( parsePNET+, readPNET+, Typ (..)+, hasTyp+, Entry (..)+) where++import qualified Data.Text as T+import qualified Data.Text.Lazy as L+import qualified Data.Text.Lazy.IO as L++-- | Trigger type.+data Typ+    = Internal+    | External+    deriving (Show, Eq, Ord)++readTyp :: T.Text -> Typ+readTyp "int" = Internal+readTyp "ext" = External+readTyp x     = error $ "readTyp: typ " ++ T.unpack x ++ " unknown"++-- | PNET entry.+data Entry = Entry+    { orth      :: T.Text+    , base      :: T.Text+    , tag       :: T.Text+    , typ       :: Typ+    , neTyp     :: T.Text+    , example   :: T.Text }++-- | Does entry represents a trigger of the given type?+hasTyp :: Typ -> Entry -> Bool+hasTyp x = (==x) . typ++parseLine :: L.Text -> Entry+parseLine line = case map L.toStrict (L.split (=='\t') line) of+    [_orth, _base, _tag, _typ, _neTyp, _example] ->+        Entry _orth _base _tag (readTyp _typ) _neTyp _example+    _   -> error $ "parseLine: invalid row \"" ++ L.unpack line ++ "\""++-- | Parse dictionary into a list of entries.+parsePNET :: L.Text -> [Entry]+parsePNET = map parseLine . L.lines++-- | Read dictionary from the file.+readPNET :: FilePath -> IO [Entry]+readPNET = fmap parsePNET . L.readFile

nerf.cabal view

@@ -1,5 +1,5 @@ name:               nerf-version:            0.2.0+version:            0.2.1 synopsis:           Nerf, the named entity recognition tool based on linear-chain CRFs description:     The package provides the named entity recognition (NER) tool divided into a@@ -49,6 +49,7 @@       , NLP.Nerf.Dict       , NLP.Nerf.Dict.Base       , NLP.Nerf.Dict.PNEG+      , NLP.Nerf.Dict.PNET       , NLP.Nerf.Dict.NELexicon       , NLP.Nerf.Dict.Prolexbase @@ -56,7 +57,7 @@  source-repository head     type: git-    location: git://github.com/kawu/nerf.git+    location: https://github.com/kawu/nerf.git  executable nerf   hs-source-dirs: ., tools