String to text

app1/Main.hs

@@ -0,0 +1,30 @@
+-- |
+-- Module      :  Main
+-- Copyright   :  © 2018 bruno cuconato
+-- License     :  LPGL-3
+--
+-- Maintainer  :  bruno cuconato <bcclaro+hackage@gmail.com>
+-- Stability   :  experimental
+-- Portability :  non-portable
+--
+-- the @hs-conllu@ executable.
+
+module Main
+  ( main )
+where
+
+import Conllu.IO (readAndPrintConllu, diffConllu)
+
+import System.Environment
+
+main :: IO ()
+-- | @validate@ : read CoNLL-U file and print it to stdout. (this will
+-- only apply the command to one file, so use your terminal's
+-- completion mechanism to apply it to several files.
+main = do
+  (c:as) <- getArgs
+  case c of
+    "validate" -> mapM_ readAndPrintConllu as
+    "diff"     -> diffConllu (as !! 0) (as !! 1)
+    _ -> return ()
+

package.yaml

@@ -0,0 +1,71 @@
+name:                hs-conllu
+version:             0.1.6
+synopsis:            Conllu validating parser and utils.
+description:         utilities to parse, print, diff, and analyse data in CoNLL-U format.
+homepage:            https://github.com/odanoburu/hs-conllu
+bug-reports:         https://github.com/odanoburu/hs-conllu/issues
+license:             LGPL-3.0-only
+license-file:        LICENSE
+author:              bruno cuconato
+maintainer:          bruno cuconato <bcclaro+haskell+hsconllu@gmail.com>
+copyright:           2021 bruno cuconato
+build-type:          Simple
+extra-doc-files:
+  - README
+  - CHANGELOG
+tested-with:   ghc == 9.2.2
+
+verbatim:
+  cabal-version: 2.0
+
+ghc-options:
+  - -Wall
+  - -Wcompat
+  - -Widentities
+  - -Wincomplete-uni-patterns
+  - -Wincomplete-record-updates
+
+default-extensions:
+  - OverloadedStrings
+  - LambdaCase
+#  - NoImplicitPrelude
+
+dependencies:
+  - aeson
+  - base >= 4.15 && < 5
+  - bytestring
+  - containers
+  - directory
+  - filepath
+  - megaparsec
+  - mtl
+  - optparse-applicative
+  - scientific
+  - string-interpolate
+  - text
+  - text-conversions
+  - text-show
+  - unordered-containers
+  - vector
+
+library:
+  source-dirs:   src
+  other-modules: []
+  exposed-modules:
+  - Conllu.DeprelTagset
+  - Conllu.Diff
+  - Conllu.IO
+  - Conllu.Parse
+  - Conllu.Print
+  - Conllu.Test
+  - Conllu.Type
+  - Conllu.UposTagset
+  - Conllu.Utils
+
+executables:
+  hs-conllu:
+    main:          Main.hs
+    source-dirs:   app1
+    dependencies:
+      - hs-conllu
+

src/Conllu/DeprelTagset.hs

@@ -13,8 +13,14 @@
 -- import qualified Conllu.DeprelTagset as D
 -- @
 
-module Conllu.DeprelTagset where
+-- TODO create the UD Taxonomy Table and enhanced dependencies
+-- < see https://universaldependencies.org/v2/conll-u.html>
+-- TODO include modifier labels, e.g. passive verbs, relative cluses, etc.
+-- TODO resolve deriving strategy
 
+module Conllu.DeprelTagset
+where  
+{-  original declaration:
 data EP
   = REF -- ^ only allowed in DEPS
   | ACL
@@ -54,4 +60,102 @@ data EP
   | ROOT
   | VOCATIVE
   | XCOMP
-  deriving (Enum, Eq, Read, Show)
+  deriving ( Show, Eq )  -- , Read,Enum ) It is not clear why Enum and Eq are required 
+-}
+
+-- Revised Universal Dependency Relations
+-- TODO include subtyped relations and Structural Categories of the dependent
+-- Universal Dependencies are represented lowercase
+-- see https://universaldependencies.org/u/dep/index.html 
+
+data EP = -- DEPREL  =
+        REF        -- ^ only allowed in DEPS
+      |  ACL        -- clausal modifier of noun (adnominal clause)
+--      | ACL RELCL           -- relative clause modifier
+      | ADVCL      -- adverbial clause modifier
+      | ADVMOD     -- adverbial modifier
+--      | ADVMOD EMPH         -- emphasizing word, intensifier
+--      | ADVMOD LMOD         -- locative adverbial modifier
+      | AMOD       -- adjectival modifier
+      | APPOS      -- appositional modifier
+      | AUX        -- auxiliary
+--      | AUX PASS   -- passive auxiliary
+      | CASE       -- case marking
+      | CC         -- coordinating conjunction
+--      | CC PRECONJ -- preconjunct
+      | CCOMP      -- clausal complement
+      | CLF        -- classifier
+      | COMPOUND   -- compound
+--      | COMPOUND LVC        -- light verb construction
+--      | COMPOUND PRT        -- phrasal verb particle
+--      | COMPOUND REDUP      -- reduplicated compounds
+--      | COMPOUND SVC        -- serial verb compounds
+      | CONJ       -- conjunct
+      | COP        -- copula
+      | CSUBJ      -- clausal subject
+ --     | CSUBJ PASS          -- clausal passive subject
+      | DEP        -- unspecified dependency
+      | DET        -- determiner
+--      | DET NUMGOV          -- pronominal quantifier governing the case of the noun
+--      | DET NUMMOD          -- pronominal quantifier agreeing in case with the noun
+--      | DET POSS            -- possessive determiner
+      | DISCOURSE  -- discourse element
+      | DISLOCATED -- dislocated elements
+      | EXPL       -- expletive
+--      | EXPL IMPERS         -- impersonal expletive
+--      | EXPL PASS           -- reflexive pronoun used in reflexive passive
+--      | EXPL PV             -- reflexive clitic with an inherently reflexive verb
+      | FIXED      -- fixed multiword expression
+      | FLAT       -- flat multiword expression
+--      | FLAT FOREIGN        -- foreign words
+--      | FLAT NAME           -- names
+      | GOESWITH   -- goes with
+      | IOBJ       -- indirect object
+      | LIST       -- list
+      | MARK       -- marker
+      | NMOD       -- nominal modifier
+--      | NMOD POSS           -- possessive nominal modifier
+--      | NMOD TMOD           -- temporal modifier
+      | NSUBJ      -- nominal subject
+ --     | NSUBJ PASS          -- passive nominal subject
+      | NUMMOD     -- numeric modifier
+ --     | NUMMOD GOV          -- numeric modifier governing the case of the noun
+      | OBJ        -- object
+      | OBL        -- oblique nominal
+--      | OBL AGENT           -- agent modifier
+--      | OBL ARG             -- oblique argument
+--      | OBL LMOD            -- locative modifier
+--      | OBL TMOD            -- temporal modifier
+      | ORPHAN     -- orphan
+      | PARATAXIS  -- parataxis
+      | PUNCT      -- punctuation
+      | REPARANDUM -- overridden disfluency
+      | ROOT       -- root
+      | VOCATIVE   -- vocative
+      | XCOMP      -- open clausal complement
+      deriving ( Show, Eq )
+
+
+  --  Structural Categories of the dependent
+{-
+type StructuralCats = [Nominals , Clauses , ModifierWords , FunctionWords]
+type Nominals       = [Nsubj , Obj , Iobj , Obl , Vocative , Expl , Dislocated , Nmod , Appos , Nummod]
+type Clauses        = [Csubj , Ccomp , Xcomp , Advcl , Acl]
+type ModifierWords  = [Advmod , Discourse , Amod]
+type FunctionWords  = [Aux , Cop , Mark , Det , Clf , Case]
+
+-- Functional Categories in relation to the head
+type FunctionalCats   = [ Core , NonCore , NominalDependent]
+type Core             = [Nsubj , Obj , Iobj , Csubj , Ccomp , Xcomp]
+type NonCore          = [Obl , Vocative , Expl , Dislocated , Advcl , Advmod , Discourse , Aux , Cop , Mark]
+type NominalDependent = [Nmod , Appos , Nummod , Acl , Amod , Det , Clf , Case]
+
+-- Relations that are not dependency relations in the narrow sense.
+type Coordination     = [ Conj , Cc]
+type MWE              = [ Fixed , Flat , Compound] -- MultiWordExpressions
+type Loose            = [ List , Parataxis]
+type Special          = [ Orphan , Goeswith , Reparandum]
+type Other            = [ Punct , Root , Dep]
+-}
+
+

src/Conllu/Diff.hs

@@ -1,4 +1,5 @@
--- |
+{-# LANGUAGE OverloadedStrings #-}
+-- -- |
 -- Module      :  Conllu.Diff
 -- Copyright   :  © 2018 bruno cuconato
 -- License     :  LPGL-3
@@ -23,10 +24,11 @@ import Conllu.Type
 import Conllu.Utils
 
 import Data.Maybe
-import Data.Ord
+import Data.Ord (comparing)
+import Data.Text (unpack) 
 
 ---
--- * type synonims
+-- * type synonyms
 -- | CoNLL-U field diff.
 type FDiff = StringPair
 
@@ -45,7 +47,7 @@ diffW = any isJust . printFieldDiffs
 
 diffWs :: [CW a] -> [CW a] -> [WDiff a]
 -- | filters the different word pairs.
-diffWs ws1 ws2 = filter diffW $ zip ws1 ws2
+diffWs ws1 ws2 = Prelude.filter diffW $ zip ws1 ws2
 
 diffS :: (Sent, Sent) -> SDiff AW
 -- | diffs the sentence pair's words.
@@ -79,8 +81,10 @@ sentId :: Sent -> Maybe Index
 -- | try to find an index in a sentence's metadata looking for
 -- 'sent_id = n'.
 sentId s =
-  let mi = lookup "sent_id " $ _meta s
-      i = fromMaybe "0" mi
+--  let myHashMap = fromList $ _meta s
+--      mi = myHashMap !? "sent_id"
+  let mi = lookup "sent_id" $ _meta s
+      i = unpack $ fromMaybe "0" mi
   in safeRead i :: Maybe Index
 
 pairSents :: [Sent] -> [Sent] -> [(Sent, Sent)]
@@ -89,7 +93,7 @@ pairSents = pairSentsBy $ comparing sentId
 
 ---
 -- * printing functions
-printFieldDiffs :: WDiff a -> [Maybe StringPair]
+printFieldDiffs :: WDiff a -> [Maybe (String, String)]
 -- | list of maybe differing fields in a pair of words.
 printFieldDiffs (w1, w2) = fmap (diffField w1 w2) pfs
   where
@@ -110,14 +114,14 @@ printFieldDiffs (w1, w2) = fmap (diffField w1 w2) pfs
       , showM . _misc
       ]
 
-printWDiff :: WDiff a -> [StringPair]
+printWDiff :: WDiff a -> [(String, String)]
 -- | list of differing fields in a pair of words.
 printWDiff = catMaybes . printFieldDiffs
 
-printSDiff :: SDiff a -> [[StringPair]]
+printSDiff :: SDiff a -> [[(String,String)]]
 -- | list of differing words in a sentence.
 printSDiff = fmap printWDiff
 
-printDDiff :: DDiff a -> [[[StringPair]]]
+printDDiff :: DDiff a -> [[[(String,String)]]]
 -- | list of lists of differing words in sentences.
 printDDiff = fmap printSDiff

src/Conllu/IO.hs

@@ -9,19 +9,30 @@
 --
 -- Defines major IO functions.
 
-module Conllu.IO where
+module Conllu.IO
+(
+  readAndPrintConllu,
+  diffConllu,
+  readDirectory,
+  readConlluFile
+)
+where
 
 ---
 -- imports
-import Conllu.Type
-import Conllu.Utils
-import Conllu.Parse
-import Conllu.Print
-import Conllu.Diff
+import Conllu.Type (Doc, Sent)
+import Conllu.Utils (if')
+import Conllu.Parse (Parser, sentence, parseConlluWith)
+import Conllu.Print (printDoc)
+import Conllu.Diff (diffSs, printDDiff)
 
-import System.Directory
-import System.FilePath
+import System.Directory (listDirectory, doesFileExist, doesDirectoryExist) --, getDirectoryContents)
+import System.FilePath ((</>))  -- Combine two paths with a path separator
 
+-- import Control.Monad (forM) --GVF added for RWH getRecursiveContents at end
+import Data.Functor (($>))
+import qualified Data.Text.IO as TIO
+-- import qualified Data.Text as T
 
 -- * read functions
 
@@ -32,9 +43,9 @@ import System.FilePath
 readConlluFileWith :: Parser Sent -> FilePath -> IO Doc
 -- | reads a file with a customized parser.
 readConlluFileWith p f = do
-  ds <- readFile f
+  ds <- TIO.readFile f
   case parseConlluWith p f ds of
-    Left err -> putStr err *> return []
+    Left err -> putStr err $> []
     Right d -> return d
 
 readDirectoryWith :: Parser Sent -> FilePath -> IO [Doc]
@@ -70,14 +81,14 @@ readConllu = readConlluWith sentence
 -- * write
 writeConlluFile :: FilePath -> Doc -> IO ()
 -- | writes a CoNLL-U file to disk.
-writeConlluFile fp = writeFile fp . printDoc
+writeConlluFile fp = TIO.writeFile fp . printDoc
 
 ---
 -- * print
 readAndPrintConllu :: FilePath -> IO ()
 -- | reads and prints the CoNLL-U files given.
 readAndPrintConllu fp = do
-  readConlluFile fp >>= putStr . printDoc
+  readConlluFile fp >>= TIO.putStrLn . printDoc
   return ()
 
 ---