import { Ast } from 'thingtalk';
import BaseTokenizer from './tokenizer/base';
import { Phrase, Concatenation, Replaceable } from '../utils/template-string';
import { EntityMap, AnyEntity } from '../utils/entity-utils';
export interface UnitPreferenceDelegate {
    timezone: string;
    getPreferredUnit(type: string): string | undefined;
}
export interface NormalizedParameterCanonical {
    default: string;
    projection_pronoun?: string[];
    base: Array<Phrase | Concatenation>;
    base_projection: Array<Phrase | Concatenation>;
    argmin: Array<Phrase | Concatenation>;
    argmax: Array<Phrase | Concatenation>;
    filter_phrase: Array<Phrase | Concatenation>;
    enum_value: Record<string, Array<Phrase | Concatenation>>;
    enum_filter: Record<string, Array<Phrase | Concatenation>>;
    projection: Array<Phrase | Concatenation>;
}
/**
 * Base class for all code that is specific to a certain natural language
 * in Genie.
 */
export default class LanguagePack {
    ARGUMENT_NAME_OVERRIDES: {
        [key: string]: string[];
    };
    IGNORABLE_TOKENS: {
        [key: string]: string[];
    };
    _NO_SPACE_TOKENS: Set<string>;
    _NO_SPACE_AFTER_TOKENS: Set<string>;
    NO_IDEA: string[];
    CHANGE_SUBJECT_TEMPLATES: string[];
    SINGLE_DEVICE_TEMPLATES: Array<[string, RegExp | null]>;
    DEFINITE_ARTICLE_REGEXP: RegExp | undefined;
    MUST_CAPITALIZE_TOKEN: Set<string>;
    ABBREVIATIONS: any;
    protected _tokenizer: BaseTokenizer | undefined;
    /**
     * The actual locale string to use, which can be a subvariant of
     * the language implementing this language pack.
     */
    readonly locale: string;
    private _gt;
    gettext: (x: string) => string;
    _: (x: string) => string;
    constructor(locale: string);
    private _loadTranslations;
    /**
     * Return an instance of the tokenizer used by this language.
     */
    getTokenizer(): BaseTokenizer;
    private _toTemplatePhrases;
    /**
     * Apply load-time transformations to the canonical annotation of a function. This normalizes
     * the form to the expected sets of POS, and adds any automatically generated
     * plural/gender/case forms as necessary.
     */
    preprocessFunctionCanonical(canonical: unknown, forItem: 'query' | 'action' | 'stream', forSide: 'user' | 'agent', isList: boolean): Replaceable[];
    private _ensureDefaultEnumValues;
    /**
     * Apply load-time transformations to the canonical annotation of a parameter. This normalizes
     * the form to the expected sets of POS, and adds any automatically generated
     * plural/gender/case forms as necessary.
     */
    preprocessParameterCanonical(fromArgument: Ast.ArgumentDef, forSide: 'user' | 'agent'): NormalizedParameterCanonical;
    /**
     * Apply final touches to a newly generated synthetic sentence
     *
     * This function should correct coreferences, conjugations and other
     * grammar/readability issues that are too inconvenient to prevent
     * using the templates.
     */
    postprocessSynthetic(sentence: string, program: unknown, rng: (() => number) | null, forTarget: 'user' | 'agent'): string;
    /**
     * Convert a tokenized sentence back into a correctly spaced, correctly
     * punctuated sentence.
     *
     * This is a low-level method called by {@link LanguagePack.detokenizeSentence}.
     * It can be used to detokenize one token at a time.
     */
    detokenize(sentence: string, prevtoken: string | null, token: string): string;
    /**
     * Convert a tokenized sentence back into a correctly spaced, correctly
     * punctuated sentence.
     *
     * This is used for sentences presented to an MTurk worker for paraphrasing,
     * and it is used for the agent replies before they are shown to the user.
     */
    detokenizeSentence(tokens: string[]): string;
    /**
     * Retrieve the list of units to use for a given base unit. This defaults
     * to metric units, but subclasses can override to choose a different
     * unit.
     *
     * The best unit for a given value (i.e., the one with the fewest digits)
     * will be chosen to display. If there are ties, the first unit will be chosen.
     */
    protected _getPossibleUnits(baseUnit: string): string[];
    private _getBestUnit;
    private _measureFormatFallback;
    private _measureToString;
    private _numberToString;
    /**
     * Convert a date object to a user-visible string, displaying only the date part.
     *
     * @param {Date} date - the time to display
     * @return {string} the formatted time
     */
    private _dateToString;
    /**
     * Convert a date object to a user-visible string, displaying _only_ the time part.
     *
     * @param {Date} date - the time to display
     * @return {string} the formatted time
     */
    private _timeToString;
    /**
     * Convert a date object to a user-visible string, displaying both the date and the time part.
     *
     * @param {Date} date - the time to display
     * @return {string} the formatted time
     */
    private _dateAndTimeToString;
    getDefaultTemperatureUnit(): string;
    protected displayPhoneNumber(phone: string): string;
    protected displayEntity(token: string, entityValue: AnyEntity, delegate: UnitPreferenceDelegate, format?: string): string;
    /**
     * Post-process a sentence generated by the neural NLG for display to
     * the user.
     *
     * This includes true-casing, detokenizing, and replacing entity tokens
     * with actual values.
     */
    postprocessNLG(answer: string, entities: EntityMap, delegate: UnitPreferenceDelegate): string;
    /**
     * Convert a word or phrase to plural form.
     *
     * This function should return `undefined` if there is no plural form
     * of the given phrase.
     */
    pluralize(phrase: string): string | undefined;
    /**
     * Convert a word or verb phrase to past tense.
     *
     * This function should return `undefined` if there is no past tense
     * of the given phrase.
     */
    toVerbPast(phrase: string): string | undefined;
    /**
     * Convert a phrase from the side of the user to the side of the agent.
     *
     * This function takes a phrase that talks about "my devices" (uttered by
     * the user) and converts to a phrase that talks about "your devices"
     * uttered by the agent.
     */
    toAgentSideUtterance(phrase: string): string;
    /**
     * Filter out words that cannot be in the dataset, because they would be
     * either tokenized/preprocessed out or they are unlikely to be used with
     * voice.
     */
    isGoodWord(word: string): boolean;
    /**
     * Filter out phrases that should not be used as a parameter on their own.
     *
     * This is mainly used to remove phrases that would be syntatically
     * ambiguous, and would not be immediately recognized as a parameter.
     * A good rule of thumb is to filter out all phrases that consist entirely
     * of stop words.
     */
    isGoodSentence(sentence: string): boolean;
    /**
     * Check if a numeric phrase is valid for the given language.
     *
     * This covers ASCII digits as well as language-specific number systems,
     * like Arabic digits.
     */
    isGoodNumber(number: string): boolean;
    /**
     * Check if a phrase looks like a person name.
     *
     * This is a coarse check that is used to override
     * {@link LanguagePack.isGoodWord} to account for foreign person
     * names and loan words.
     */
    isGoodPersonName(word: string): boolean;
    /**
     * Check if a phrase looks like a social media user name.
     *
     * This is a coarse check that is used to override
     * {@link LanguagePack.isGoodWord} to account for foreign person
     * names and loan words.
     */
    isGoodUserName(word: string): boolean;
    /**
     * Add a definite article ("the") to the given phrase.
     *
     * If the language has no concept of definite articles, this function
     * must return `undefined`.
     */
    addDefiniteArticle(phrase: string): string | undefined;
}