src/Gargantext/Text/List.hs

   1 {-|
   2 Module      : Gargantext.Text.Ngrams.Lists
   3 Description :
   4 Copyright   : (c) CNRS, 2017-Present
   5 License     : AGPL + CECILL v3
   6 Maintainer  : team@gargantext.org
   7 Stability   : experimental
   8 Portability : POSIX
   9
  10 Here is a longer description of this module, containing some
  11 commentary with @some markup@.
  12
  13 -}
  14
  15 {-# LANGUAGE NoImplicitPrelude #-}
  16 {-# LANGUAGE OverloadedStrings #-}
  17
  18 module Gargantext.Text.List
  19   where
  20
  21 import Data.Text (Text)
  22 import qualified Data.Text as DT
  23 import Gargantext.Prelude
  24
  25 -- | TODO normalize text
  26
  27 -- | TODO Order the seperators in probability of apparition
  28 separators :: [Text]
  29 separators = [" ", ",", ".", "?", "!", "\""]
  30
  31 isIn :: Text -> Text -> Bool
  32 isIn term context = any (\x   -> DT.isInfixOf x context)
  33                         $ map (\sep -> term <> sep) separators
  34
  35 ------------------------------------------------------------------------
  36 --graph :: [Ngrams] -> [Ngrams]
  37 --graph ngs = filter (\ng -> _ngramsListName ng == Just Graph) ngs
  38 --
  39 --candidates :: [Ngrams] -> [Ngrams]
  40 --candidates ngs = filter (\ng -> _ngramsListName ng == Just Candidate) ngs
  41 --
  42 --stop :: [Ngrams] -> [Ngrams]
  43 --stop ngs = filter (\ng -> _ngramsListName ng == Just Stop) ngs
  44 ------------------------------------------------------------------------
  45 -- | Attoparsec solution to index test
  46 --import Data.Attoparsec.ByteString (Parser, parseOnly, try, string
  47 --                                  , takeTill, take
  48 --                                  , manyTill, many1)
  49 --import Data.Attoparsec.ByteString.Char8 (anyChar, isEndOfLine)
  50 --import Data.ByteString (ByteString, concat)
  51 --import Data.ByteString.Char8 (pack)
  52 --import Control.Applicative
  53 -- | Attoparsec version
  54 --indexParser :: (ByteString -> b) -> ByteString -> Parser b
  55 --indexParser form2label x = do
  56 --    _  <- manyTill anyChar (string x)
  57 --    pure $ form2label x
  58
  59 --doIndex :: Applicative f => ByteString -> ByteString -> f (Either String [ByteString]
  60 --doIndex f x txt = pure $ parseOnly (many $ indexParser f x) txt
  61 ------------------------------------------------------------------------
  62
  63