src/Gargantext/Core/Text/Terms/Multi/Group.hs

   1 {-|
   2 Module      : Gargantext.Core.Text.Terms.Multi.Group
   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
  11 group the tokens into extracted terms.
  12
  13 -}
  14
  15
  16 module Gargantext.Core.Text.Terms.Multi.Group (group2)
  17   where
  18
  19 import Gargantext.Core.Types
  20 import Gargantext.Prelude
  21
  22 -- | FIXME p1 and p2 not really taken into account
  23 group2 :: POS -> POS -> [TokenTag] -> [TokenTag]
  24 group2 p1 p2 (x@(TokenTag _ _ (Just p1') _):y@(TokenTag _ _ (Just p2') _):z) =
  25   if (p1 == p1') && (p2 == p2')
  26      then group2 p1 p2 (x<>y : z)
  27      -- then (x : y : group2 p1 p2 (x<>y : z))
  28      else (x : group2 p1 p2 (y:z))
  29 group2 p1 p2 (x@(TokenTag _ _ Nothing _):y) = (x: group2 p1 p2 y)
  30 group2 _ _ [x@(TokenTag _ _ (Just _) _)] = [x]
  31 group2 p1 p2 (x@(TokenTag _ _ (Just _) _):y@(TokenTag _ _ Nothing _):z) = (x:y: group2 p1 p2 (y:z))
  32 group2 _ _ [] = []