pdfdataextract/dist/pdfdataextractor.d.ts

Extract data from a pdf with pure javascript

import { CanvasApi, CanvasApiConstructor } from './canvasapi';
import { OcrApi, OcrApiConstructor } from './ocrapi';
import { PdfPageData } from './pdfpagedata';
import { VerbosityLevel, Permissions, Outline, MetadataInfo, Sort } from './types';
export type PdfDataExtractorOptions = {
    /**
     * password for a password-protected PDF
     *
     * @type {string}
     */
    password?: string;
    /**
     * the logging level
     *
     * @type {VerbosityLevel}
     */
    verbosity?: VerbosityLevel;
    /**
     * the canvas api used for rendering
     *
     * @type {CanvasApiConstructor}
     */
    canvasApi?: CanvasApiConstructor<CanvasApi>;
    /**
     * the ocr api used for text detection
     *
     * @type {OcrApiConstructor}
     */
    ocrApi?: OcrApiConstructor<OcrApi>;
};
/**
 * the extractor for the data of the pdf
 */
export declare class PdfDataExtractor {
    private readonly pdf_document;
    private readonly canvasApi;
    private readonly ocrApi;
    private constructor();
    /**
     * get the extractor for the data
     *
     * @param {Uint8Array} data - the binary data file
     * @param {PdfDataExtractorOptions} [options={}] - the options on how to open the data in the extractor
     * @returns {Promise<PdfDataExtractor>} a promise that is resolved with a {PdfDataExtractor} object to pull the extracted data from
     */
    static get(data: Uint8Array, options?: PdfDataExtractorOptions): Promise<PdfDataExtractor>;
    /**
     * get the fingerprint
     *
     * @returns {string | null} the fingerprint
     */
    get fingerprint(): string | null;
    /**
     * get the number of pages
     *
     * @returns {string} the number of pages
     */
    get pages(): number;
    /**
     * get the permission flags
     *
     * @returns {Promise<Permissions | null>} a promise that is resolved with a {Permissions | null} object that contains the permission flags for the PDF
     */
    getPermissions(): Promise<Permissions | null>;
    /**
     * get the text
     *
     * @param {number|number[]|((pageNumber: number) => boolean)} [pages] - can either be the number of pages to be read,
     * a number array with the specific pages (sorted by page number)
     * or a filter function (return true to parse the page)
     * @param {boolean|Sort} [sort=false] - sort the text by text coordinates
     * @returns {Promise<string[]>} a promise that is resolved with a {string[]} array with the extracted text per page
     */
    getText(pages?: number | number[] | ((pageNumber: number) => boolean), sort?: boolean | Sort): Promise<string[]>;
    /**
     * get the text
     *
     * @param {number|number[]|((pageNumber: number) => boolean)} [pages] - can either be the number of pages to be read,
     * a number array with the specific pages (sorted by page number)
     * or a filter function (return true to parse the page)
     * @returns {Promise<string[]>} a promise that is resolved with a {string[]} array with the extracted text per page
     */
    getPageData(pages?: number | number[] | ((pageNumber: number) => boolean)): Promise<(PdfPageData | null)[]>;
    /**
     * get the outline/bookmarks
     *
     * @returns {Promise<Outline[]>} a promise that is resolved with a {Outline[]} array with information from the tree outline
     */
    getOutline(): Promise<Outline[] | null>;
    /**
     * get the metadata
     *
     * @returns {Promise<MetadataInfo | null>} a promise that is resolved with a {MetadataInfo | null} object with information from the metadata section
     */
    getMetadata(): Promise<MetadataInfo | null>;
    /**
     * close the extractor
     *
     * @returns {Promise<void>} a promise that is resolved when destruction is completed
     */
    close(): Promise<void>;
}