import { convertPDFToHTMLWithLiteParse, LiteParseHTMLOptions } from './liteparse-to-html';
import { convertPDFToHTMLWithLiteParseWasm } from './liteparse-wasm-to-html';
/**
 * Which parsing engine {@link convertPDFToHTML} runs.
 * - `"ts-block-algorithm"` (default) — the pure-TS pipeline in this file: groups
 *   pdfjs text spans into lines/blocks and renders headings/lists/code blocks.
 *   Works in Node.js, Cloudflare Workers, and browsers.
 * - `"liteparse"` — delegates to [LiteParse](https://github.com/run-llama/liteparse),
 *   a native/OCR-capable parser. Node.js only (ships a napi addon), and requires
 *   the optional `@llamaindex/liteparse` dependency to be installed.
 * - `"liteparse-wasm"` — delegates to LiteParse's WebAssembly build. Runs
 *   anywhere WASM does — browsers, Cloudflare Workers, and Node.js — and
 *   requires the optional `@llamaindex/liteparse-wasm` dependency to be
 *   installed. OCR requires passing an `ocrEngine` callback (e.g. tesseract-js).
 */
export type ParseMethod = "ts-block-algorithm" | "liteparse" | "liteparse-wasm";
/**
 * Extracts formatted text from PDF with parsing of linebreaks ,
 * page headers, footnotes, and section headings. Supports fonts, links, bold,
 * italics, lists, headings, headers, footnotes, and Table of Contents,
 * Quotes, and Code Blocks, . Removes repeated headers, links footnote anchors to the footnote,
 *  and preserves number of the PDF page with invisible I element.
 *
 * This function uses [pdfjs-serverless](https://github.com/johannschopplich/pdfjs-serverless)
 * to work in more environments than PDF.js-based tools:
 * Cloudflare workers, serverless, node.js, and front-end only.
 * @param {string} pdfURLOrBuffer - URL to a PDF file or buffer from fs.readFile
 * @param {Object} [options]
 * @param {boolean} options.addPageNumbers default=false - Adds  #  to end of each page
 * @param {boolean} options.removePageHeaders default=true - Removes repeated headers found on each page
 * @param {ParseMethod} options.method default="ts-block-algorithm" - Parsing engine to use;
 *   `"liteparse"` delegates to LiteParse (Node.js only, see {@link ParseMethod})
 * @returns {string|Object} HTML formatted text
 * @category Extract
 * @author [vtempest (2025)](https://github.com/vtempest),
 * [pdf-to-markdown (2017)](https://github.com/jzillmann/pdf-to-markdown/tree/master),
 * [pdf.js (2012-)](https://github.com/mozilla/pdf.js/releases),
 */
export declare function convertPDFToHTML(pdfURLOrBuffer: any, options?: {
    addPageNumbers?: boolean;
    addCitation?: boolean;
    method?: ParseMethod;
} & Pick<LiteParseHTMLOptions, "liteParseOptions">): Promise<{
    error: any;
    author?: undefined;
    title?: undefined;
    html?: undefined;
    format?: undefined;
} | {
    author: string;
    title: string;
    html: any;
    format: string;
    error?: undefined;
} | {
    author: any;
    title: any;
    html: string;
    format: string;
}>;
export { convertPDFToHTMLWithLiteParse };
export type { LiteParseHTMLOptions } from './liteparse-to-html';
export { convertPDFToHTMLWithLiteParseWasm };
export type { LiteParseWasmHTMLOptions } from './liteparse-wasm-to-html';
export { detectPdfNeedsOcr } from './detect-needs-ocr';
export type { DetectPdfNeedsOcrOptions, PdfOcrAssessment, } from './detect-needs-ocr';