pomljs/dist/util/pdf.js

Prompt Orchestration Markup Language

import * as PDFJS from 'pdfjs-dist/legacy/build/pdf.js';

const log = console.log;
console.log = (m, ...a) => /Cannot polyfill `(DOMMatrix|Path2D)`/.test(m) ? null : log(m, ...a);
let pdfjs = PDFJS;
if (PDFJS.GlobalWorkerOptions === undefined) {
    // in esm
    pdfjs = PDFJS.default;
}
else {
    // in commonjs
    pdfjs = PDFJS;
}
pdfjs.GlobalWorkerOptions.workerSrc = 'pdfjs-dist/legacy/build/pdf.worker.js';
console.log = log; // restore original console.log
async function getNumPages(pdfBuffer) {
    const uint8Array = pdfBuffer instanceof ArrayBuffer ? new Uint8Array(pdfBuffer) : new Uint8Array(pdfBuffer);
    const loadingTask = pdfjs.getDocument({ data: uint8Array });
    const pdfDocument = await loadingTask.promise;
    return pdfDocument.numPages;
}
async function pdfParse(pdfBuffer, maxPages) {
    const uint8Array = pdfBuffer instanceof ArrayBuffer ? new Uint8Array(pdfBuffer) : new Uint8Array(pdfBuffer);
    const loadingTask = pdfjs.getDocument({ data: uint8Array });
    const pdfDocument = await loadingTask.promise;
    let fullTexts = [];
    if (maxPages == undefined) {
        maxPages = pdfDocument.numPages;
    }
    else {
        maxPages = Math.min(maxPages, pdfDocument.numPages);
    }
    for (let pageNum = 1; pageNum <= maxPages; pageNum++) {
        const page = await pdfDocument.getPage(pageNum);
        const pageText = await extractTextFromPage(page);
        fullTexts.push(pageText);
    }
    return fullTexts.join('\n\n');
}
async function extractTextFromPage(page) {
    const textContent = await page.getTextContent();
    let lastY, text = '';
    for (let item of textContent.items) {
        if (lastY == item.transform[5] || !lastY) {
            text += item.str;
        }
        else {
            text += '\n' + item.str;
        }
        lastY = item.transform[5];
    }
    return text;
}

export { getNumPages, pdfParse };
//# sourceMappingURL=pdf.js.map