src/Gargantext/Ngrams/Occurrences.hs

   1 {-|
   2 Module      : Gargantext.Ngrams.Occurrences
   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 {-# LANGUAGE NoImplicitPrelude #-}
  15 {-# LANGUAGE OverloadedStrings #-}
  16
  17 module Gargantext.Ngrams.Occurrences where
  18
  19 import Gargantext.Prelude
  20
  21 import Control.Monad ((>>),(>>=))
  22 import Data.String (String())
  23 import Data.Attoparsec.Text
  24 import Data.Text (Text)
  25
  26 import Data.Either.Extra(Either(..))
  27 import qualified Data.Text as T
  28 import Control.Applicative
  29
  30
  31 occurrenceParser :: Text -> Parser Bool
  32 occurrenceParser txt = manyTill anyChar (string txt) >> pure True
  33
  34 occurrencesParser :: Text -> Parser Int
  35 occurrencesParser txt = case txt of
  36                     "" -> pure 0
  37                     _  -> many (occurrenceParser txt') >>= \matches -> pure (length matches)
  38     where
  39         txt' = T.toLower txt
  40
  41 parseOccurrences :: Text -> Text -> Either String Int
  42 parseOccurrences x = parseOnly (occurrencesParser x)