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smart constructor to only allow valid `(Lang, Region)` combinations * API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility.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
88 lines
2.1 KiB
Haskell
88 lines
2.1 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.GA.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 GA Nothing}, allExamples)
|
|
|
|
allExamples :: [Example]
|
|
allExamples = concat
|
|
[ examples (simple Dollar 10)
|
|
[ "$10"
|
|
, "10$"
|
|
, "deich dollair"
|
|
]
|
|
, examples (simple Cent 10)
|
|
[ "deich ceinteanna"
|
|
]
|
|
, examples (simple Dollar 10000)
|
|
[ "$10,000"
|
|
, "10K$"
|
|
, "$10k"
|
|
]
|
|
, examples (simple EUR 10000)
|
|
[ "€10,000"
|
|
, "10K€"
|
|
, "€10k"
|
|
]
|
|
, examples (simple USD 1.23)
|
|
[ "USD1.23"
|
|
]
|
|
, examples (simple Dollar 2.23)
|
|
[ "2 dhollair agus 23 ceinteanna"
|
|
, "dhá dhollair 23 ceinteanna"
|
|
, "2 dhollair 23"
|
|
, "dhá dhollair agus 23"
|
|
]
|
|
, examples (simple EUR 20)
|
|
[ "20€"
|
|
, "20 euros"
|
|
, "20 Euro"
|
|
, "20 Euros"
|
|
, "EUR 20"
|
|
]
|
|
, examples (simple EUR 29.99)
|
|
[ "EUR29.99"
|
|
]
|
|
, examples (simple INR 20)
|
|
[ "Rs. 20"
|
|
, "Rs 20"
|
|
, "20 Rúpaí"
|
|
, "20Rs"
|
|
, "Rs20"
|
|
]
|
|
, examples (simple INR 20.43)
|
|
[ "20 Rupees 43"
|
|
, "fiche rúpaí 43"
|
|
]
|
|
, examples (simple INR 33)
|
|
[ "INR33"
|
|
]
|
|
, examples (simple Pound 9)
|
|
[ "£9"
|
|
, "naoi bpunt"
|
|
]
|
|
, examples (simple GBP 3.01)
|
|
[ "GBP3.01"
|
|
, "GBP 3.01"
|
|
]
|
|
]
|