fix(pdf): make pdfjs survive bundling + real-PDF font fidelity (live smoke)
Live dispatch smoke against the Turbopack dev server (master's ask, 2026-09-19) caught two things unit tests cannot - they run unbundled: - Bundling pdfjs-dist broke its node fake-worker: the chunk-relative pdf.worker.mjs import 404s inside .next/dev/server/chunks. Fix: serverExternalPackages + tracing includes for legacy/ + standard_fonts/ (next.config.ts - a clearly-marked seam, same precedent as bcdcd51; the standalone output now ships the worker and font files, verified). - Real-world PDFs warned about missing standardFontDataUrl (non-embedded standard fonts silently fall back) and flooded the log with JBIG2 warnings on scanned files. Fix: standardFontsDir() + verbosity 0 in both the node ops and the headless canvas shim. Verified live end-to-end on GEB (802pp, text layer): teacher dispatch, 12-step read with vision renders, brief with accurate page citations, wake turn folding the resolution (Chapter IX, pp. 268-270) into the lesson. Scanned/DRM Polya correctly refuses to fabricate citations.
This commit is contained in:
@@ -326,8 +326,12 @@ async function renderPdfPages(
|
||||
const page = await browser.newPage();
|
||||
await page.setViewport({ width: 1200, height: 1600, deviceScaleFactor: 1 });
|
||||
await page.goto(pathToFileURL(file).href, { waitUntil: "load", timeout: 30_000 });
|
||||
// Standard-font data as a file URL (live-smoke finding 2026-09-19:
|
||||
// without it pdfjs renders non-embedded standard fonts via fallback);
|
||||
// verbosity 0 = errors only (JBIG2 noise on scanned PDFs).
|
||||
const fontsUrl = pathToFileURL(path.join(PATHS_nodeModules(), "pdfjs-dist", "standard_fonts") + path.sep).href;
|
||||
const results = await page.evaluate(
|
||||
async (b64pdf, workerUrl, pageNos, dpi) => {
|
||||
async (b64pdf, workerUrl, pageNos, dpi, fontsUrl) => {
|
||||
// window-scope dynamic import (Chrome evaluates this string in the
|
||||
// shim page, not under Node)
|
||||
const pdfjs = (await import(workerUrl)) as typeof import("pdfjs-dist");
|
||||
@@ -335,7 +339,7 @@ async function renderPdfPages(
|
||||
const bin = atob(b64pdf);
|
||||
const bytes = new Uint8Array(bin.length);
|
||||
for (let i = 0; i < bin.length; i++) bytes[i] = bin.charCodeAt(i);
|
||||
const doc = await pdfjs.getDocument({ data: bytes }).promise;
|
||||
const doc = await pdfjs.getDocument({ data: bytes, standardFontDataUrl: fontsUrl, verbosity: 0 }).promise;
|
||||
const out: Array<{ page: number; dataUrl: string; w: number; h: number }> = [];
|
||||
for (const pageNo of pageNos) {
|
||||
if (pageNo < 1 || pageNo > doc.numPages) continue;
|
||||
@@ -355,6 +359,7 @@ async function renderPdfPages(
|
||||
pdfjsUrl,
|
||||
pages,
|
||||
dpi,
|
||||
fontsUrl,
|
||||
);
|
||||
return results.map((r) => ({
|
||||
page: r.page,
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import * as fs from "node:fs/promises";
|
||||
import * as path from "node:path";
|
||||
import { fileURLToPath } from "node:url";
|
||||
|
||||
/**
|
||||
* PDF plumbing for the pdf-reader sub-agent — sources v0 (2026-09): Node
|
||||
@@ -42,12 +43,22 @@ async function loadPdfjs() {
|
||||
return pdfjs;
|
||||
}
|
||||
|
||||
/** Standard-font data dir (live-smoke finding 2026-09-19: without it pdfjs
|
||||
* warns and falls back on non-embedded standard fonts — Helvetica, Times…).
|
||||
* The node side takes a plain filesystem path. Resolved from this module's
|
||||
* location, the headless.ts PATHS_nodeModules idiom. */
|
||||
export function standardFontsDir(): string {
|
||||
return path.join(path.dirname(fileURLToPath(import.meta.url)), "..", "..", "..", "node_modules", "pdfjs-dist", "standard_fonts") + path.sep;
|
||||
}
|
||||
|
||||
async function openDocument(filePath: string) {
|
||||
const pdfjs = await loadPdfjs();
|
||||
const data = new Uint8Array(await fs.readFile(filePath));
|
||||
// The legacy build in plain node runs on a main-thread fake worker (no
|
||||
// workerSrc needed); teardown is the loading task's destroy().
|
||||
const task = pdfjs.getDocument({ data });
|
||||
// verbosity 0 = errors only — scanned PDFs (JBIG2 XObjects) otherwise
|
||||
// flood the log with per-page warnings (live-smoke finding 2026-09-19).
|
||||
const task = pdfjs.getDocument({ data, standardFontDataUrl: standardFontsDir(), verbosity: 0 });
|
||||
return { doc: await task.promise, task };
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user