/** * Splits a PDF into smaller PDFs of consecutive pages, so a long scanned document can be read by * an AI model in batches instead of one oversized request. */ import { PDFDocument } from 'pdf-lib'; export interface PdfBatch { /** 1-based page numbers, inclusive. */ start: number; end: number; bytes: Uint8Array; } export async function pdfPageCount(bytes: Uint8Array): Promise { const doc = await PDFDocument.load(bytes, { ignoreEncryption: true, updateMetadata: false }); return doc.getPageCount(); } /** * Yields batches of up to `pagesPerBatch` pages. A batch larger than `maxBytes` is split again * (down to a single page); a single page that is still too large is yielded as-is for the caller * to skip with a warning. */ export async function* splitPdf(bytes: Uint8Array, pagesPerBatch: number, maxBytes: number): AsyncGenerator { const src = await PDFDocument.load(bytes, { ignoreEncryption: true, updateMetadata: false }); const total = src.getPageCount(); async function build(start: number, end: number): Promise { const out = await PDFDocument.create({ updateMetadata: false }); const indices = Array.from({ length: end - start + 1 }, (_, i) => start - 1 + i); for (const page of await out.copyPages(src, indices)) out.addPage(page); return out.save({ useObjectStreams: true }); } async function* emit(start: number, end: number): AsyncGenerator { const part = await build(start, end); if (part.length <= maxBytes || start === end) { yield { start, end, bytes: part }; return; } const mid = Math.floor((start + end) / 2); yield* emit(start, mid); yield* emit(mid + 1, end); } for (let start = 1; start <= total; start += pagesPerBatch) { yield* emit(start, Math.min(total, start + pagesPerBatch - 1)); } }