src/Gargantext/Text/Terms/Multi/Lang/Fr.hs

   1 {-|
   2 Module      : Gargantext.Text.Terms.Multi.Lang.Fr
   3 Description : French Grammar rules to group postag tokens.
   4 Copyright   : (c) CNRS, 2017-Present
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9
  10 This @group@ function groups horizontally ngrams in their context of
  11 sentence according to grammars specific of each language. In english, JJ
  12 is ADJectiv in french.
  13
  14 -}
  15
  16 {-# LANGUAGE NoImplicitPrelude #-}
  17 {-# LANGUAGE OverloadedStrings #-}
  18
  19 module Gargantext.Text.Terms.Multi.Lang.Fr (group)
  20   where
  21
  22 import Gargantext.Prelude
  23 import Gargantext.Core.Types
  24 import Gargantext.Text.Terms.Multi.Group (group2)
  25
  26 group :: [TokenTag] -> [TokenTag]
  27 group [] = []
  28 group ntags = group2 NP NP
  29             $ group2 NP VB
  30             -- $ group2 NP IN
  31             -- $ group2 IN DT
  32             $ group2 VB NP
  33             $ group2 JJ NP
  34             $ group2 NP JJ
  35             $ group2 JJ JJ
  36             $ group2 JJ CC
  37             $ ntags
  38
  39 ------------------------------------------------------------------------
  40 -- TODO
  41 --groupNgrams ((x,_,"PERSON"):(y,yy,"PERSON"):xs)             = groupNgrams ((x <> " " <> y,yy,"PERSON"):xs)
  42 --groupNgrams ((x,_,"ORGANIZATION"):(y,yy,"ORGANIZATION"):xs) = groupNgrams ((x <> " " <> y,yy,"ORGANIZATION"):xs)