concraft-pl 0.5.0 → 0.6.0

raw patch · 4 files changed

+21/−25 lines, 4 filesPVP ok

version bump matches the API change (PVP)

API changes (from Hackage documentation)

Files

• changelog +3/−0
• concraft-pl.cabal +1/−1
• src/NLP/Concraft/Polish/Format/Plain.hs +13/−20
• src/NLP/Concraft/Polish/Morphosyntax.hs +4/−4

@@ -1,4 +1,7 @@ -*-change-log-*- +0.6.0	Nov 2013+	* Output wordform instead of "None" as a lemma for unknown words+ 0.5.0	Nov 2013 	* Restore the orth[-2] feature in the observation schema

@@ -1,5 +1,5 @@ name:               concraft-pl-version:            0.5.0+version:            0.6.0 synopsis:           Morphological tagger for Polish description:     A morphological tagger for Polish based on the concraft library.

@@ -31,9 +31,6 @@  import           NLP.Concraft.Polish.Morphosyntax -noneBase :: T.Text-noneBase = "None"- -- | Parse the text in the plain format. parsePlain :: L.Text -> [[Sent Tag]] parsePlain =@@ -85,24 +82,20 @@     doIt [form, tag, "disamb"] = Just $         (mkInterp form tag, True)     doIt xs = error $ "parseInterp: " ++ show xs-    mkInterp form tag-        | formS == noneBase = Interp Nothing tagS-        | otherwise         = Interp (Just formS) tagS-      where-        formS   = L.toStrict form-        tagS    = L.toStrict tag+    mkInterp form tag = Interp (L.toStrict form) (L.toStrict tag)  parseHeader :: L.Text -> (T.Text, Space) parseHeader xs =     let [_orth, space] = L.splitOn "\t" xs     in  (L.toStrict _orth, parseSpace space) +-- TODO: Should we represent newlines and spaces in the `Space` data type? parseSpace :: L.Text -> Space parseSpace "none"    = None parseSpace "space"   = Space-parseSpace "spaces"  = Space	-- Is it not a Maca bug?+parseSpace "spaces"  = Space	-- Multiple spaces parseSpace "newline" = NewLine-parseSpace "newlines" = NewLine -- TODO: Remove this temporary fix+parseSpace "newlines" = NewLine -- Multiple newlines parseSpace xs        = error ("parseSpace: " ++ L.unpack xs)  -----------@@ -129,7 +122,7 @@ buildWord Seg{..}     =  L.fromText orth  <> "\t"     <> buildSpace space <> "\n"-    <> buildKnown known+    <> buildKnown orth known     <> buildInterps (M.toList interps)     where Word{..} = word @@ -142,20 +135,20 @@         else "\n"     | (interp, dmb) <- interps ]   where-    buildTag    = L.fromText . tag-    buildBase x = case base x of-        Just b  -> L.fromText b-        Nothing -> L.fromText noneBase+    buildTag  = L.fromText . tag+    buildBase = L.fromText . base  buildSpace :: Space -> L.Builder buildSpace None     = "none" buildSpace Space    = "space" buildSpace NewLine  = "newline" -buildKnown :: Bool -> L.Builder-buildKnown True  = ""-buildKnown False =  "\t" <> L.fromText noneBase-                         <> "\t" <> L.fromText ign <> "\n"+buildKnown :: T.Text -> Bool -> L.Builder+buildKnown _ True = ""+buildKnown lemma False+    =  "\t" <> L.fromText lemma+    <> "\t" <> L.fromText ign+    <> "\n"   -----------

@@ -103,9 +103,8 @@       -- | A morphosyntactic interpretation.--- TODO: Should we allow `base` to be `Nothing`? data Interp t = Interp-    { base  :: Maybe T.Text+    { base  :: T.Text     , tag   :: t }     deriving (Show, Eq, Ord) @@ -173,8 +172,9 @@             ++ catMaybes         [ if tag `M.member` wSet seg             then Nothing-            else Just (Interp Nothing tag, asDmb x)-        | (tag, x) <- M.toList (X.unWMap wMap) ]+            else Just (Interp lemma tag, asDmb x)+        | let lemma = orth $ word seg   -- Default base form+        , (tag, x) <- M.toList (X.unWMap wMap) ]   --------------------------------