src/Gargantext/Text/Terms/Multi.hs

   1 {-|
   2 Module      : Gargantext.Text.Terms.Multi
   3 Description : Multi Terms module
   4 Copyright   : (c) CNRS, 2017 - present
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9
  10 Multi-terms are ngrams where n > 1.
  11
  12 -}
  13
  14 {-# LANGUAGE NoImplicitPrelude #-}
  15
  16 module Gargantext.Text.Terms.Multi (extractTokenTags)
  17   where
  18
  19 import Data.Text hiding (map, group)
  20
  21 import Gargantext.Prelude
  22 import Gargantext.Core (Lang(..))
  23 import Gargantext.Core.Types
  24
  25 import Gargantext.Text.Terms.Multi.PosTagging
  26 import qualified Gargantext.Text.Terms.Multi.Lang.En as En
  27 import qualified Gargantext.Text.Terms.Multi.Lang.Fr as Fr
  28
  29
  30 extractTokenTags :: Lang -> Text -> IO [[TokenTag]]
  31 extractTokenTags lang s = map (group lang) <$> extractTokenTags' lang s
  32
  33
  34 extractTokenTags' :: Lang -> Text -> IO [[TokenTag]]
  35 extractTokenTags' lang t =  map tokens2tokensTags
  36                      <$> map _sentenceTokens
  37                      <$> _sentences
  38                      <$> corenlp lang t
  39
  40 ---- | This function analyses and groups (or not) ngrams according to
  41 ----   specific grammars of each language.
  42 group :: Lang -> [TokenTag] -> [TokenTag]
  43 group EN = En.group
  44 group FR = Fr.group
  45