geneea-nlp-client/g3/model/token.d.ts

The TypeScript Client for Geneea Interpretor G3 API.

import { CharSpan } from "../../common/char-span";
import { UDep } from "../../common/udep";
import { UPos } from "../../common/upos";
import { Node } from "./node";
import { Paragraph } from "./paragraph";
import { Sentence } from "./sentence";
/**
 * A token including basic morphological and syntactic information.
 * A token is similar to a word, but includes punctuation.
 * Tokens have an zero-based index reflecting their position within their sentence.
 * The morphological and syntactical features might be null (deepLemma, lemma, morphTag, pos, fnc, parent),
 * or empty (children) if not requested or supported.
 */
declare class Token extends Node<Token> {
    readonly id: string;
    readonly idx: number;
    /** Text of this token, possibly after correction. */
    text: string;
    /** Cahracter span within the paragraph. */
    charSpan: CharSpan;
    /** Text of this token in the original paragraph. */
    origText: string;
    /** Character span within the original paragraph. */
    origCharSpan: CharSpan;
    /** Lemma of the token e.g. bezpecny. null if not requested/supported. */
    deepLemma: string | null;
    /** Simple lemma of the token, e.g. nejnebezpecnejsi (in Cz, includes negation and grade). Null if not requested/supported. */
    lemma: string | null;
    /** Google universal tag. Null if not requested/supported.  */
    pos: UPos | null;
    /** Morphological tag, e.g. AAMS1-...., VBD, ... Null if not requested/supported.  */
    morphTag: string | null;
    /** Universal and custom features  */
    feats: Map<string, string>;
    /** Label of the dependency edge. Null if not requested/supported. */
    fnc: UDep | null;
    /** Dependency sub-function. None if not requested/supported. */
    subFnc: string | null;
    /** Lemma info features, a list of strings.  */
    static readonly FEAT_LEMMA_INFO = "lemmaInfo";
    /** Key presence signifies it is a negated word, value = true. */
    static readonly FEAT_NEGATED = "negated";
    /** Key presence signifies it is an unknown word, value = true. */
    static readonly FEAT_UNKNOWN = "unknown";
    private constructor();
    /** Token factory method, public constructor. */
    static of(id: string, idx: number, text: string, charSpan: CharSpan, origText?: string | null, origCharSpan?: CharSpan | null, deepLemma?: string | null, lemma?: string | null, pos?: UPos | null, morphTag?: string | null, feats?: Map<string, string> | null, fnc?: UDep | null, subFnc?: string | null): Token;
    /** True iff the token form contains a negation prefix. */
    isNegated(): boolean;
    /** True iff the token is unknown to the lemmatizer. The lemma provided is the same as the token itself. */
    isUnknown(): boolean;
    /**
     * Token following of preceding this token within the sentence.
     * @param offset Relative offset. The following tokens have a positive offse,
     *    preceding a negative one. The ext token has offset = 1.
     * @returns The token at the relative offset or null if the offset is invalid.
     */
    offsetToken(offset: number): Token | null;
    /** The previous token or null if this token is sentence initial.  */
    previous(): Token | null;
    /** The next token or null if this token is sentence final. */
    next(): Token | null;
    /**
     * Full dependency function in the format `{fnc}:{subFnc}` if the sub-function is present.
     * Otherwise it's the same as `fnc`.
     */
    get fullFnc(): string | null;
    /** Converts the token to a default non-recursive string: index + text.  */
    toSimpleString(): string;
    /** Converts the token to a non-recursive string: index + [text] + [pos] + [fnc]. */
    toStringWith(text: boolean, pos: boolean, fnc: boolean): string;
    toString(): string;
}
/**
 * Tokens within a single sentence; ordered by word-order; non-empty, continuous or discontinuous.
 */
declare class TokenSupport {
    tokens: Token[];
    isContinuous: boolean;
    /**
     *
     * @param tokens The tokens of this support.
     * @param isContinuous Is this support a continuous sequence of tokens, i.e. a token span?
     */
    constructor(tokens: Token[], isContinuous: boolean);
    /**
     * Creates a TokenSupport object from a list of tokens.
     * @param tokens Non-empty list of tokens (no need for them to be sorted).
     */
    static of(tokens: Token[]): TokenSupport;
    get sentence(): Sentence;
    get paragraph(): Paragraph;
    get first(): Token;
    get last(): Token;
    get size(): number;
    get ids(): string[];
    /**
     * The character span between the first and last token relative to the enclosing paragraph;
     * for discontinuous support this includes intervening gaps.
     */
    get charSpan(): CharSpan;
    /** Offset of the first character of these tokens  within the enclosing paragraph.  */
    get firstCharParaOffset(): number;
    /** Offset of the last character of these tokens within the enclosing paragraph.  */
    get lastCharParaOffset(): number;
    /**
     * Substring of a full text as denoted by this support (before correction).
     * For discontinuous supports, the result includes the intervening gaps.
     */
    get text(): string;
    /** Breaks this token support into continuous sub-sequences of tokens. */
    spans(): TokenSupport[];
    /** The coverage texts of each of the continuous spans, ordered by word-order. */
    textSpans(): string[];
    toString(): string;
}
export { Token, TokenSupport };