ppu-pdf/pdf-reader-legacy.d.ts

Easily extract text from digital PDF files with coordinate and font size included, and optionally group text by lines or render scanned pdf to canvas/png.

import "pdfjs-dist/build/pdf.worker.min.mjs";
import "./pdfjs-workaround";
import { type Canvas } from "@napi-rs/canvas";
import * as pdfjs from "pdfjs-dist/legacy/build/pdf.mjs";
import { PdfReaderCommon } from "./pdf-reader-common";
import { type CanvasMap, type CompactPageLines, type PageLines, type PageTexts, type PdfCompactLineAlgorithm, type PdfReaderOptions, type PdfScannedThreshold } from "./pdf.interface";
/**
 * PdfReaderLegacy class based on pdfjs-dist for reading and processing PDF documents.
 */
export declare class PdfReaderLegacy extends PdfReaderCommon {
    private options;
    private startIndex;
    constructor(options?: Partial<PdfReaderOptions>);
    /**
     * Opens a PDF document from a file path or an ArrayBuffer.
     * @param filename - The file path or ArrayBuffer of the PDF document.
     * @returns The opened PDFDocument instance.
     */
    open(filename: string | ArrayBuffer): Promise<pdfjs.PDFDocumentProxy>;
    /**
     * Renders all pages of a PDF document into canvases.
     * @param doc - The PDFDocumentProxy to render.
     * @returns A map of page numbers to Canvas instances.
     */
    renderAll(doc: pdfjs.PDFDocumentProxy): Promise<CanvasMap>;
    private getCanvas;
    /**
     * Extracts text from all pages of a PDF document.
     * @param doc - The PDFDocumentProxy to extract text from.
     * @returns A map of page numbers to extracted text data.
     */
    getTexts(pdf: pdfjs.PDFDocumentProxy): Promise<PageTexts>;
    private extractTexts;
    private mapTokenToPdfWord;
    private mergeTextContent;
    private filterTextContent;
    /**
     * Converts extracted text into structured lines.
     * @param pageTexts - The extracted text data from a PDF.
     * @returns A map of page numbers to structured lines.
     */
    getLinesFromTexts(pageTexts: PageTexts): PageLines;
    /**
     * Converts extracted text into compact structured lines using a specified algorithm.
     * @param pageTexts - The extracted text data from a PDF.
     * @param algorithm - The algorithm for compacting lines (default: "middleY").
     * @returns A map of page numbers to compact structured lines.
     */
    getCompactLinesFromTexts(pageTexts: PageTexts, algorithm?: PdfCompactLineAlgorithm): CompactPageLines;
    /**
     * Determines if the PDF document is scanned based on text thresholds.
     * @param pageTexts - The extracted text data from a PDF.
     * @param options - The threshold options for scanned detection.
     * @returns True if the document is likely scanned, false otherwise.
     */
    isScanned(pageTexts: PageTexts, options?: PdfScannedThreshold): boolean;
    /**
     * Saves rendered canvases as image files.
     * @param canvasMap - The map of canvases to save.
     * @param filename - The base filename for the output images.
     * @param foldername - The folder to save the images in (default: "out").
     */
    dumpCanvasMap(canvasMap: Map<number, Canvas>, filename: string, foldername?: string): Promise<void>;
    /**
     * Destroys the PDF document instance to free memory.
     * @param doc - The PDFDocumentProxy instance to destroy.
     */
    destroy(pdf: pdfjs.PDFDocumentProxy): Promise<void>;
}