import type { DocumentInitParameters, PDFPageProxy, TextItem } from 'pdfjs-dist/types/src/display/api.js';
import type { RequireExactlyOne } from 'type-fest';
export type { DocumentInitParameters } from 'pdfjs-dist/types/src/display/api.js';
/** A single page within a PDF file. */
export type PdfPage = {
    lines: string[];
};
/** Progress updates sent by the `pdfjs-dist` dependency. */
export type PdfProgressData = {
    loaded: number;
    total: number;
};
/**
 * Same as the built-in Partial type but also allows each property to be undefined. Compatible with
 * PartialAndUndefined from @augment-vir/common.
 */
export type PartialWithUndefined<T extends object> = {
    [Prop in keyof T]?: T[Prop] | undefined;
};
/** All options for reading pdf text to function. Most are optional. */
export type ReadPdfTextParams = PartialWithUndefined<{
    /** Password used to open a PDF that's password protected. */
    password: string;
    /** This callback will be periodically called while PDF reading is in progress. */
    progressCallback: (progressData: PdfProgressData) => void;
    /**
     * Set this as an absolute path to the `pdfjs-dist` directory in your `node_modules` directory.
     * This is not required for proper operation, but may help with a warning like the following:
     *
     * Warning: fetchStandardFontData: failed to fetch file "<font name>" with
     * "UnknownErrorException: The standard font "baseUrl" parameter must be specified, ensure that
     * the "standardFontDataUrl" API parameter is provided.".
     *
     * For more details see https://github.com/mozilla/pdf.js/issues/4244
     *
     * Example: /home/ubuntu/this-repo/node_modules/pdfjs-dist
     */
    pathToPdfJsDistNodeModule: string;
    /**
     * All options that the Mozilla's `pdfjs-dist` package supports. This will override any options
     * that this package passes to `pdfjs-dist`.
     */
    options: Partial<Omit<DocumentInitParameters, 'data' | 'url'>>;
}> & RequireExactlyOne<{
    /** File path to the PDF file to read. */
    filePath: NonNullable<DocumentInitParameters['url']>;
    /** URL to the PDF. */
    url: NonNullable<DocumentInitParameters['url']>;
    /** PDF file data that has already been read from a PDF file. */
    data: NonNullable<DocumentInitParameters['data']>;
}>;
/**
 * Read a PDF and convert it into lines of text.
 *
 * If a URL is used to fetch the PDF data a standard XMLHttpRequest(XHR) is used, which means it
 * must follow the same origin rules that any XHR does e.g. No cross domain requests without CORS.
 */
export declare function readPdfPages({ data, filePath, password, pathToPdfJsDistNodeModule, progressCallback, url, options, }: ReadPdfTextParams): Promise<PdfPage[]>;
/** Reads a PDF into a single string. */
export declare function readPdfText(params: ReadPdfTextParams): Promise<string>;
/** Combine all PDF pages into a single string. */
export declare function combinePagesIntoSingleString(pages: PdfPage[]): string;
/** Parse a single PDF page. */
export declare function parsePage(pdfPage: PDFPageProxy): Promise<PdfPage>;
/**
 * Parses individual text items generated by pdf.js This allows lower level control of what actually
 * gets parsed. For example, a consumer of this function may remove entire sections of the pdf text
 * prior to passing items in here. See parsePage function above for example usage.
 *
 * @param pdfItems An array of TextItem items.
 */
export declare function parsePageItems(pdfItems: TextItem[]): PdfPage;