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

   1 {-|
   2 Module      : Gargantext.Text.Terms.Multi.Lang.En
   3 Description : English 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 Rule-based grammars are computed in this english module in order to group
  11 the tokens into extracted terms.
  12
  13 -}
  14
  15 {-# LANGUAGE NoImplicitPrelude #-}
  16 {-# LANGUAGE OverloadedStrings #-}
  17
  18 module Gargantext.Text.Terms.Multi.Lang.En (group)
  19   where
  20
  21 import Gargantext.Prelude
  22 import Gargantext.Core.Types
  23 import Gargantext.Text.Terms.Multi.Group
  24
  25 ------------------------------------------------------------------------
  26 -- | Rule grammar to group tokens
  27 group :: [TokenTag] -> [TokenTag]
  28 group [] = []
  29 group ntags = group2 NP NP
  30            $ group2 NP VB
  31 --           $ group2 NP IN
  32            $ group2 IN DT
  33 --           $ group2 VB NP
  34            $ group2 JJ NP
  35            $ group2 JJ JJ
  36            $ group2 JJ CC
  37            $ ntags
  38
  39 ------------------------------------------------------------------------
  40 --groupNgrams ((x,_,"PERSON"):(y,yy,"PERSON"):xs)             = groupNgrams ((x <> " " <> y,yy,"PERSON"):xs)
  41 --groupNgrams ((x,_,"ORGANIZATION"):(y,yy,"ORGANIZATION"):xs) = groupNgrams ((x <> " " <> y,yy,"ORGANIZATION"):xs)
  42 --groupNgrams ((x,_,"LOCATION"):(y,yy,"LOCATION"):xs)         = groupNgrams ((x <> " " <> y,yy,"LOCATION"):xs)
  43 --
  44 --groupNgrams (x:xs)                                          = (x:(groupNgrams xs))
  45