Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 21 additions & 2 deletions src/lib/extract-text.ts
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ export function getExtension(filename: string): string {
}

let pdfJsDomPolyfillsPromise: Promise<void> | null = null;
let pdfJsRuntimePromise: Promise<typeof import('pdfjs-dist/legacy/build/pdf.mjs')> | null = null;

async function ensurePdfJsDomPolyfills() {
const globalScope = globalThis as Record<string, unknown>;
Expand All @@ -46,9 +47,27 @@ async function ensurePdfJsDomPolyfills() {
await pdfJsDomPolyfillsPromise;
}

async function loadPdfJsRuntime() {
if (!pdfJsRuntimePromise) {
pdfJsRuntimePromise = (async () => {
await ensurePdfJsDomPolyfills();
const [pdfjs, pdfWorker] = await Promise.all([
import('pdfjs-dist/legacy/build/pdf.mjs'),
import('pdfjs-dist/legacy/build/pdf.worker.mjs'),
]);

const globalScope = globalThis as Record<string, unknown>;
globalScope.pdfjsWorker ??= pdfWorker;

return pdfjs;
})();
}

return pdfJsRuntimePromise;
}

export async function extractPdf(buffer: Buffer): Promise<ExtractResult> {
await ensurePdfJsDomPolyfills();
const pdfjs = await import('pdfjs-dist/legacy/build/pdf.mjs');
const pdfjs = await loadPdfJsRuntime();
const loadingTask = pdfjs.getDocument({
data: new Uint8Array(buffer),
useWorkerFetch: false,
Expand Down
5 changes: 5 additions & 0 deletions src/types/pdfjs-dist-worker.d.ts
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
declare module 'pdfjs-dist/legacy/build/pdf.worker.mjs' {
export const WorkerMessageHandler: {
setup(handler: unknown, port: unknown): void;
};
}
Loading