All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 33s
- Drag-to-reorder for class materials, folders, quiz questions and deck cards. Pointer-based so touch works, plus keyboard (arrows/Home/End) with screen-reader announcements. - Timed exams get a wall-clock deadline. The server refuses late answers, submits overdue exams with what was saved, and the countdown keeps running while the page is closed. - Shared quiz sessions keep a frozen copy of their questions and flag later owner edits. - Scanned PDFs are read in cached 8-page batches with real page numbers (pdf-lib), removing the 30 MB whole-file limit. Compatible providers now receive PDFs as file parts. - Semantic search: embeddings for OpenAI, Gemini, Ollama and compatible servers, background indexing into chunk_vectors (migration 2), hybrid keyword + vector ranking for search, the assistant and focused generation, and a Settings -> AI section. 181 tests pass locally and in the Docker test stage on Node 24. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
49 lines
1.8 KiB
TypeScript
49 lines
1.8 KiB
TypeScript
/**
|
|
* 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<number> {
|
|
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<PdfBatch> {
|
|
const src = await PDFDocument.load(bytes, { ignoreEncryption: true, updateMetadata: false });
|
|
const total = src.getPageCount();
|
|
|
|
async function build(start: number, end: number): Promise<Uint8Array> {
|
|
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<PdfBatch> {
|
|
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));
|
|
}
|
|
}
|