duckling/Duckling/Ordinal/TR/Rules.hs
Julien Odent bf89e34365 Relicense to BSD3
Reviewed By: JoelMarcey

Differential Revision: D15439223

fbshipit-source-id: c5af3cb06318748142fe503945b38beffadfc28a
2019-05-22 10:46:39 -07:00

95 lines
2.1 KiB
Haskell
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

-- Copyright (c) 2016-present, Facebook, Inc.
-- All rights reserved.
--
-- This source code is licensed under the BSD-style license found in the
-- LICENSE file in the root directory of this source tree.
{-# LANGUAGE GADTs #-}
{-# LANGUAGE OverloadedStrings #-}
module Duckling.Ordinal.TR.Rules
( rules ) where
import Data.HashMap.Strict (HashMap)
import qualified Data.HashMap.Strict as HashMap
import Data.Text (Text)
import qualified Data.Text as Text
import Prelude
import Data.String
import Duckling.Dimensions.Types
import Duckling.Numeral.Helpers (parseInt)
import Duckling.Ordinal.Helpers
import Duckling.Regex.Types
import Duckling.Types
ordinals :: [Text]
ordinals =
[ "birinci"
, "ikinci"
, "üçüncü"
, "dördüncü"
, "beşinci"
, "altıncı"
, "yedinci"
, "sekizinci"
, "dokuzuncu"
, "onuncu"
, "on birinci"
, "on ikinci"
, "on üçüncü"
, "on dördüncü"
, "on beşinci"
, "on altıncı"
, "on yedinci"
, "on sekizinci"
, "on dokuzuncu"
, "yirminci"
, "yirmi birinci"
, "yirmi ikinci"
, "yirmi üçüncü"
, "yirmi dördüncü"
, "yirmi beşinci"
, "yirmi altıncı"
, "yirmi yedinci"
, "yirmi sekizinci"
, "yirmi dokuzuncu"
, "otuzuncu"
, "otuz birinci"
]
ordinalsHashMap :: HashMap Text Int
ordinalsHashMap = HashMap.fromList $ zip ordinals [1..]
ruleOrdinalsFirstst :: Rule
ruleOrdinalsFirstst = Rule
{ name = "ordinals (first..31st)"
, pattern =
[ regex . Text.unpack $
Text.concat [ "(", Text.intercalate "|" ordinals, ")" ]
]
, prod = \tokens -> case tokens of
(Token RegexMatch (GroupMatch (match:_)):_) ->
ordinal <$> HashMap.lookup (Text.toLower match) ordinalsHashMap
_ -> Nothing
}
ruleOrdinalDigits :: Rule
ruleOrdinalDigits = Rule
{ name = "ordinal (digits)"
, pattern =
[ regex "0*(\\d+) ?('?)(inci|nci|ıncı|ncı|uncu|ncu|üncü|ncü|.)"
]
, prod = \tokens -> case tokens of
(Token RegexMatch (GroupMatch (match:_)):_) ->
ordinal <$> parseInt match
_ -> Nothing
}
rules :: [Rule]
rules =
[ ruleOrdinalDigits
, ruleOrdinalsFirstst
]