mirror of
https://github.com/facebook/duckling.git
synced 2024-12-23 12:13:30 +03:00
ab0ad0256e
Summary: * Locales support for the library, following `<Lang>_<Region>` with ISO 639-1 code for `<Lang>` and ISO 3166-1 alpha-2 code for `<Region>` (#33) * `Locale` opaque type (composite of `Lang` and `Region`) with `makeLocale` smart constructor to only allow valid `(Lang, Region)` combinations * API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility. * `Rules/<Lang>.hs` exposes - `langRules`: cross-locale rules for `<Lang>`, from `<Dimension>/<Lang>/Rules.hs` - `localeRules`: locale-specific rules, from `<Dimension>/<Lang>/<Region>/Rules.hs` - `defaultRules`: `langRules` + specific rules from select locales to ensure backward-compatibility * Corpus, tests & classifiers - 1 classifier per locale, with default classifier (`<Lang>_XX`) when no locale provided (backward-compatible) - Default classifiers are built on existing corpus - Locale classifiers are built on - `<Dimension>/<Lang>/Corpus.hs` exposes a common `corpus` to all locales of `<Lang>` - `<Dimension>/<Lang>/<Region>/Corpus.hs` exposes `allExamples`: a list of examples specific to the locale (following `<Dimension>/<Lang>/<Region>/Rules.hs`). - Locale classifiers use the language corpus extended with the locale examples as training set. - Locale examples need to use the same `Context` (i.e. reference time) as the language corpus. - For backward compatibility, `<Dimension>/<Lang>/Corpus.hs` can expose also `defaultCorpus`, which is `corpus` augmented with specific examples. This is controlled by `getDefaultCorpusForLang` in `Duckling.Ranking.Generate`. - Tests run against each classifier to make sure runtime works as expected. * MM/DD (en_US) vs DD/MM (en_GB) example to illustrate Reviewed By: JonCoens, blandinw Differential Revision: D6038096 fbshipit-source-id: f29c28d
121 lines
3.4 KiB
Haskell
121 lines
3.4 KiB
Haskell
-- 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. An additional grant
|
||
-- of patent rights can be found in the PATENTS file in the same directory.
|
||
|
||
{-# LANGUAGE OverloadedStrings #-}
|
||
|
||
module Duckling.AmountOfMoney.BG.Corpus
|
||
( corpus
|
||
) where
|
||
|
||
import Data.String
|
||
import Prelude
|
||
|
||
import Duckling.AmountOfMoney.Types
|
||
import Duckling.Locale
|
||
import Duckling.Resolve
|
||
import Duckling.Testing.Types
|
||
|
||
corpus :: Corpus
|
||
corpus = (testContext {locale = makeLocale BG Nothing}, allExamples)
|
||
|
||
allExamples :: [Example]
|
||
allExamples = concat
|
||
[ examples (simple BGN 1)
|
||
[ "1 лв"
|
||
, "един лев"
|
||
, "1 Лев"
|
||
]
|
||
, examples (simple BGN 10)
|
||
[ "10 лв"
|
||
, "десет лева"
|
||
, "10лв"
|
||
]
|
||
, examples (simple BGN 15.50)
|
||
[ "15лв и 50ст"
|
||
, "петнадесет лева и петдесет стотинки"
|
||
, "15 Лв и 50 Ст"
|
||
]
|
||
, examples (simple Dollar 1)
|
||
[ "$1"
|
||
, "един долар"
|
||
, "1 долар"
|
||
]
|
||
, examples (simple Dollar 10)
|
||
[ "$10"
|
||
, "$ 10"
|
||
, "10$"
|
||
, "10 Долара"
|
||
, "десет долара"
|
||
]
|
||
, examples (simple Cent 10)
|
||
[ "10 цента"
|
||
, "десет пенита"
|
||
, "десет цента"
|
||
, "10¢"
|
||
]
|
||
, examples (simple Cent 50)
|
||
[ "50 ст"
|
||
, "петдесет стотинки"
|
||
, "50ст"
|
||
]
|
||
, examples (simple Dollar 1e4)
|
||
[ "$10К"
|
||
, "10к$"
|
||
, "$10,000"
|
||
]
|
||
, examples (simple USD 3.14)
|
||
[ "USD3.14"
|
||
, "3.14US$"
|
||
, "US$ 3.14"
|
||
]
|
||
, examples (simple EUR 20)
|
||
[ "20\x20ac"
|
||
, "20 евро"
|
||
, "20 Евро"
|
||
, "EUR 20"
|
||
, "EUR 20.0"
|
||
, "20€"
|
||
, "20 €ur"
|
||
]
|
||
, examples (simple Pound 10)
|
||
[ "\x00a3\&10"
|
||
, "десет паунда"
|
||
]
|
||
, examples (simple Dollar 20.43)
|
||
[ "$20 и 43ц"
|
||
, "$20 43"
|
||
, "20 долара 43ц"
|
||
, "20 долара 43 цента"
|
||
, "двадесет долара 43 цента"
|
||
, "20 долара 43"
|
||
, "двадесет долара и 43"
|
||
]
|
||
, examples (simple GBP 3.01)
|
||
[ "GBP3.01"
|
||
, "GBP 3.01"
|
||
, "3 GBP 1 пени"
|
||
]
|
||
, examples (between Dollar (10, 20))
|
||
[ "между 10 и 20 долара"
|
||
, "от 10 до 20 долара"
|
||
, "около 10-20 долара"
|
||
, "между 10 и 20 долара"
|
||
, "около $10-$20"
|
||
, "10-20 долара"
|
||
]
|
||
, examples (under EUR 7)
|
||
[ "под седем евро"
|
||
, "по-малко от 7 Евро"
|
||
, "под 7€"
|
||
]
|
||
, examples (above Dollar 1.42)
|
||
[ "над 1 долар и четиридесет и два цента"
|
||
, "поне $1.42"
|
||
, "над 1.42 долара"
|
||
]
|
||
]
|