mindee/src/pdf/pdfUtils.js

Mindee Client Library for Node.js

import tmp from "tmp";
import * as fs from "node:fs";
import { MindeePdfError } from "../errors/index.js";
import { loadOptionalDependency } from "../dependency/index.js";
import { logger } from "../logger.js";
function getConcatenatedText(pages) {
    return pages.flatMap(page => page.content.map(item => item.str)).join(" ");
}
/**
 * Extracts text from a full PDF document.
 *
 * @returns A Promise containing the extracted text as a string.
 * @param pdfBuffer PDF handle, as a buffer.
 */
export async function extractTextFromPdf(pdfBuffer) {
    const pdfJsExtract = await loadOptionalDependency("pdf.js-extract", "PDF text extraction");
    const pdfJs = pdfJsExtract.pdfjs || pdfJsExtract;
    const pdfExtract = new pdfJs.PDFExtract();
    const options = {};
    const pdf = await new Promise((resolve, reject) => {
        pdfExtract.extractBuffer(pdfBuffer, options, (err, result) => {
            if (err)
                reject(err);
            if (result === undefined)
                reject(new MindeePdfError("Couldn't process result."));
            else
                resolve(result);
        });
    });
    const pages = pdf.pages.map((page, index) => ({
        pageNumber: index + 1,
        content: page.content.map((item) => ({
            str: item.str,
            x: item.x,
            y: item.y,
            width: item.width,
            height: item.height,
            fontName: item.fontName,
        })),
    }));
    return {
        pages,
        getConcatenatedText: () => getConcatenatedText(pages),
    };
}
/**
 * Checks if a PDF contains source text.
 *
 * @param pdfData Buffer representing the content of the PDF file.
 *
 * @returns A Promise containing a boolean indicating if the PDF has source text.
 */
export async function hasSourceText(pdfData) {
    const text = await extractTextFromPdf(pdfData);
    return text.getConcatenatedText().trim().length > 0;
}
/**
 * Rasterizes a PDF page.
 *
 * @param pdfData Buffer representation of the entire PDF file.
 * @param index Index of the page to rasterize.
 * @param quality Quality to apply during rasterization.
 * @return Buffer containing the rasterized image data.
 */
export async function rasterizePage(pdfData, index, quality = 85) {
    const popplerImport = await loadOptionalDependency("node-poppler", "Image Processing");
    const poppler = popplerImport.default || popplerImport;
    const popplerInstance = new poppler.Poppler();
    const tmpPdf = tmp.fileSync();
    const tempPdfPath = tmpPdf.name;
    const antialiasOption = "best";
    try {
        await fs.promises.writeFile(tempPdfPath, pdfData);
        const options = {
            antialias: antialiasOption,
            firstPageToConvert: index,
            lastPageToConvert: index,
            jpegFile: true,
            jpegOptions: `quality=${quality}`,
            singleFile: true
        };
        const jpegBuffer = await popplerInstance.pdfToCairo(tempPdfPath, undefined, options);
        await fs.promises.unlink(tempPdfPath);
        return Buffer.from(jpegBuffer, "binary");
    }
    catch (error) {
        logger.error("Error rasterizing PDF:", error);
        throw error;
    }
    finally {
        tmpPdf.removeCallback();
    }
}