related-documents/dist/related.d.ts

Find related text documents.

/**
 * Copyright 2022 Google LLC
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
import { TfIdf } from "natural";
import type { Stemmer, Tokenizer } from "natural";
export declare type serializer = (item: any) => string[];
export interface Options {
    serializer: serializer;
    weights: number[];
    stemmer?: Stemmer;
    tokenizer?: Tokenizer;
}
export declare class Related {
    private stems_;
    private tfidfs_;
    private documents_;
    private options_;
    private debug;
    constructor(documents: any[], options: Options);
    get documents(): any;
    get weights(): number[];
    set weights(weights: number[]);
    get numParts(): number;
    get stems(): string[][][];
    get tfidfs(): TfIdf[];
    get serializer(): serializer;
    set serializer(serializer: serializer);
    get tokenizer(): Tokenizer;
    set tokenizer(tokenizer: Tokenizer);
    get stemmer(): Stemmer | undefined;
    set stemmer(stemmer: Stemmer | undefined);
    private reset;
    private prepare;
    /**
     * Serialize according the {@link Options.serializer} where an object is
     * serialized into an array of strings based upon specific parts of the
     * document such as `title`, `summary`, etc.
     */
    serialize(document: any): string[];
    /**
     * Tokenize the individual serialized parts of the document.
     */
    tokenize(parts: string[]): string[][];
    /**
     * Run the stemmer over the words.
     */
    stem(parts: string[][]): string[][];
    /**
     * Convert the document into parts, each having an array of stems or words
     */
    private process;
    rank(document: any): {
        relative: number;
        absolute: number;
        document: any;
    }[];
}