wordmap/dist/structures/Ngram.d.ts

Multi-Lingual Word Alignment Prediction

import { Token } from "wordmap-lexer";
/**
 * Represents a set of zero or more tokens from a text.
 */
export default class Ngram {
    occurrence: number;
    occurrences: number;
    private tokens;
    private cachedKey;
    private cachedLemmaKey;
    /**
     * Returns the length of the n-gram in {@link Token}'s
     * @return {number}
     */
    readonly tokenLength: number;
    /**
     * Returns the length of the n-gram in characters.
     * This does not account for whitespace.
     * @return {number}
     */
    readonly characterLength: number;
    /**
     * Returns the position (in units of {@link Token} ) at which this n-gram appears in the sentence.
     * @return {number} - the position
     */
    readonly tokenPosition: number;
    /**
     * Returns the length of the sentence (in units of {@link Token}) in which this n-gram occurs.
     * @return {number}
     */
    readonly sentenceTokenLength: number;
    /**
     * Returns the length of the sentence (in units of character) in which this n-gram occurs.
     * This includes whitespace in the sentence
     * @return {number}
     */
    readonly sentenceCharacterLength: number;
    /**
     * Returns the position (in units of character) at which this n-gram appears in the sentence.
     * @return {number} - the position
     */
    readonly characterPosition: number;
    /**
     * Returns the n-gram key
     */
    readonly key: string;
    /**
     * Returns the n-gram lemma-based key
     */
    readonly lemmaKey: string | undefined;
    /**
     * @param {Array<Token>} [tokens=[]] - a list of tokens of which this n-gram is composed
     */
    constructor(tokens?: Token[]);
    /**
     * Checks if this n-gram contains one token
     * @return {boolean}
     */
    isUnigram(): boolean;
    /**
     * Checks if this n-gram contains two tokens
     * @return {boolean}
     */
    isBigram(): boolean;
    /**
     * Checks if this n-gram contains three tokens
     * @return {boolean}
     */
    isTrigram(): boolean;
    /**
     * Checks if this n-grams is an empty placeholder
     * @return {boolean}
     */
    isNull(): boolean;
    /**
     * Returns the tokens in this n-gram
     * @return {Token[]}
     */
    getTokens(): Token[];
    /**
     * Returns a human readable form of the n-gram
     * @return {string}
     */
    toString(): string;
    /**
     * Outputs the n-gram to json
     * @param verbose - print full metadata
     * @return {object}
     */
    toJSON(verbose?: boolean): object;
    /**
     * Checks if two n-grams are equal
     * @param {Ngram} ngram
     * @return {boolean}
     */
    equals(ngram: Ngram): boolean;
    /**
     * Checks if two n-grams look the same
     * @param {Ngram} ngram
     * @return {boolean}
     */
    looksLike(ngram: Ngram): boolean;
    /**
     * Caches the keys if they have not already been generated
     */
    private cacheKeys;
}