diff --git a/Dockerfile b/Dockerfile index 6b871db84..20fe839da 100644 --- a/Dockerfile +++ b/Dockerfile @@ -54,6 +54,9 @@ RUN NODE_OPTIONS=--max-old-space-size=8192 pnpm build # name; see the note there for why guessing was wrong. RUN node -p "require('/app/node_modules/pdfjs-dist/package.json').version" \ > /app/.pdfjs-version +# The same for @napi-rs/canvas, whose native binary must match its JS loader. +RUN node -p "require('/app/node_modules/@napi-rs/canvas/package.json').version" \ + > /app/.canvas-version # ── Stage 3: Production runner ───────────────────────────── FROM node:22-alpine@sha256:16e22a550f3863206a3f701448c45f7912c6896a62de43add43bb9c86130c3e2 AS runner @@ -120,21 +123,41 @@ RUN node -e "require.resolve('pg-boss'); require.resolve('pg')" # @napi-rs/canvas" → "Cannot polyfill DOMMatrix" → rasterize ReferenceError); # (2) @napi-rs/canvas's own loader then resolves its platform binary. Hoist BOTH # the canvas package and the musl binary package to /app/node_modules/@napi-rs -# via symlink into the .pnpm store, and also drop the prebuilt .node into the -# canvas dir so the loader's local-file fallback (`require('./skia..node')`) -# is belt-and-suspenders. Per-arch buildx installs only the matching musl triple. +# via symlink into the .pnpm store, and drop the prebuilt .node into the canvas +# dir: the loader tries that local file (`require('./skia..node')`) +# before the platform package, so it decides which binary runs. +# +# Hoist the version the app pins, by name, exactly like pdfjs-dist below. The +# store holds a second, older canvas that pdf-parse's own pdfjs-dist pulls in, +# and this step used to take whichever `find | head -1` returned first. It +# returned the old binary, which then sat next to the new loader: rendering +# still worked, but `loadImage` called an `Image.decode` the old binary does +# not have, and every preview thumbnail failed with "image.decode is not a +# function". Name the version, and fail the build when the binary that lands +# in the canvas dir is not that version's. +COPY --from=builder /app/.canvas-version /tmp/.canvas-version RUN set -e; \ - CANVAS_DIR="$(find /app/node_modules/.pnpm -maxdepth 4 -type d -path '*@napi-rs+canvas@*/node_modules/@napi-rs/canvas' 2>/dev/null | head -1)"; \ - MUSL_DIR="$(find /app/node_modules/.pnpm -maxdepth 4 -type d -path '*@napi-rs+canvas-linux-*-musl@*/node_modules/@napi-rs/canvas-linux-*-musl' 2>/dev/null | head -1)"; \ - NODE_BIN="$(find /app/node_modules/.pnpm -maxdepth 5 -name 'skia.linux-*-musl.node' 2>/dev/null | head -1)"; \ - if [ -n "$CANVAS_DIR" ]; then \ - mkdir -p /app/node_modules/@napi-rs; \ - ln -sfn "$CANVAS_DIR" /app/node_modules/@napi-rs/canvas; \ - [ -n "$MUSL_DIR" ] && ln -sfn "$MUSL_DIR" "/app/node_modules/@napi-rs/$(basename "$MUSL_DIR")"; \ - [ -n "$NODE_BIN" ] && cp "$NODE_BIN" "$CANVAS_DIR/"; \ - chown -R nextjs:nodejs /app/node_modules/@napi-rs; \ - echo "canvas hoisted for pdfjs: $CANVAS_DIR (musl=$MUSL_DIR)"; \ - else echo "WARN: @napi-rs/canvas not found; PDF rasterization will degrade to local text"; fi + CANVAS_VERSION="$(cat /tmp/.canvas-version)"; \ + rm -f /tmp/.canvas-version; \ + CANVAS_DIR="/app/node_modules/.pnpm/@napi-rs+canvas@${CANVAS_VERSION}/node_modules/@napi-rs/canvas"; \ + MUSL_DIR="$(find /app/node_modules/.pnpm -maxdepth 4 -type d -path "*@napi-rs+canvas-linux-*-musl@${CANVAS_VERSION}/node_modules/@napi-rs/canvas-linux-*-musl" 2>/dev/null | head -1)"; \ + if [ ! -d "$CANVAS_DIR" ] || [ -z "$MUSL_DIR" ]; then \ + echo "ERROR: pinned @napi-rs/canvas@${CANVAS_VERSION} or its musl binary did not reach the traced image."; \ + echo "Present instead:"; \ + find /app/node_modules/.pnpm -maxdepth 1 -name '@napi-rs+canvas*' 2>/dev/null; \ + exit 1; \ + fi; \ + NODE_BIN="$(find "$MUSL_DIR" -maxdepth 1 -name 'skia.linux-*-musl.node' | head -1)"; \ + [ -n "$NODE_BIN" ] || { echo "ERROR: no skia binary in $MUSL_DIR"; exit 1; }; \ + mkdir -p /app/node_modules/@napi-rs; \ + ln -sfn "$CANVAS_DIR" /app/node_modules/@napi-rs/canvas; \ + ln -sfn "$MUSL_DIR" "/app/node_modules/@napi-rs/$(basename "$MUSL_DIR")"; \ + cp "$NODE_BIN" "$CANVAS_DIR/"; \ + chown -R nextjs:nodejs /app/node_modules/@napi-rs; \ + BIN_VERSION="$(node -p "require('$MUSL_DIR/package.json').version")"; \ + [ "$BIN_VERSION" = "$CANVAS_VERSION" ] || { echo "ERROR: canvas binary is $BIN_VERSION, loader is $CANVAS_VERSION"; exit 1; }; \ + cmp -s "$NODE_BIN" "$CANVAS_DIR/$(basename "$NODE_BIN")" || { echo "ERROR: the canvas dir holds a different binary"; exit 1; }; \ + echo "canvas hoisted for pdfjs: $CANVAS_DIR (binary $BIN_VERSION from $MUSL_DIR)" # pdfjs-dist is `serverExternalPackages` (NOT bundled — the bundled copy's render # path breaks in the standalone image), so the server does a runtime bare diff --git a/src/__tests__/canvas-binary-hoist-guard.test.ts b/src/__tests__/canvas-binary-hoist-guard.test.ts new file mode 100644 index 000000000..d230fab26 --- /dev/null +++ b/src/__tests__/canvas-binary-hoist-guard.test.ts @@ -0,0 +1,65 @@ +/** + * Structural guard: the runtime image puts the @napi-rs/canvas native binary + * of the version the app pins next to that version's loader. + * + * ## The failure this freezes (GitHub #1124) + * + * The pnpm store holds two canvas versions: the one in package.json and an + * older one that pdf-parse's own pdfjs-dist pulls in. The runner stage picked + * the musl binary with `find | head -1`, got the old one, and copied it into + * the new loader's directory, where the loader looks first. PDF rendering + * still worked, so nothing looked wrong; `loadImage` called an + * `Image.decode` the old binary lacks, and every preview thumbnail failed + * with "image.decode is not a function" on both architectures. + * + * ## What it proves and what it does not + * + * The builder records the resolved canvas version, the runner hoists by that + * name, and the build stops when the copied binary's package is a different + * version. Whether the binary loads is proved when the image runs; this file + * reads the Dockerfile only. + */ +import { readFileSync } from "node:fs"; +import { join } from "node:path"; + +import { describe, expect, it } from "vitest"; + +const DOCKERFILE = readFileSync(join(process.cwd(), "Dockerfile"), "utf8"); + +function stage(name: string): string { + const start = DOCKERFILE.search(new RegExp(`^FROM .* AS ${name}$`, "m")); + expect(start, `the Dockerfile has a ${name} stage`).toBeGreaterThan(0); + const next = DOCKERFILE.slice(start + 1).search(/^FROM /m); + return next < 0 + ? DOCKERFILE.slice(start) + : DOCKERFILE.slice(start, start + 1 + next); +} + +describe("canvas binary hoist", () => { + it("records the resolved canvas version in the builder", () => { + expect(stage("builder")).toMatch( + /require\('\/app\/node_modules\/@napi-rs\/canvas\/package\.json'\)\.version"[\s\\]*>\s*\/app\/\.canvas-version/, + ); + }); + + it("hoists the loader and the musl binary of that version only", () => { + const runner = stage("runner"); + expect(runner).toContain( + "COPY --from=builder /app/.canvas-version /tmp/.canvas-version", + ); + expect(runner).toContain( + 'CANVAS_DIR="/app/node_modules/.pnpm/@napi-rs+canvas@${CANVAS_VERSION}/', + ); + expect(runner).toContain("canvas-linux-*-musl@${CANVAS_VERSION}/"); + // A version-blind pick is the defect: any `canvas…@*` glob decides by + // readdir order which of the store's copies wins. + expect(runner).not.toMatch(/@napi-rs\+canvas[^"'\s]*@\*/); + }); + + it("fails the build when the copied binary is another version", () => { + const runner = stage("runner"); + expect(runner).toMatch( + /\[ "\$BIN_VERSION" = "\$CANVAS_VERSION" \] \|\| \{[^}]*exit 1; \}/, + ); + }); +}); diff --git a/src/lib/documents/__tests__/native-canvas-support.test.ts b/src/lib/documents/__tests__/native-canvas-support.test.ts index df978c965..df282df1d 100644 --- a/src/lib/documents/__tests__/native-canvas-support.test.ts +++ b/src/lib/documents/__tests__/native-canvas-support.test.ts @@ -115,6 +115,6 @@ describe("generateThumbnail behind a closed gate", () => { Buffer.from([0xff, 0xd8, 0xff]), "image/jpeg", ); - expect(result).toEqual({ ok: false }); + expect(result).toEqual({ ok: false, reason: "native-canvas-unsupported" }); }); }); diff --git a/src/lib/documents/__tests__/prepare-vision-raster-failure.test.ts b/src/lib/documents/__tests__/prepare-vision-raster-failure.test.ts index 05af83fdc..3e01f2d75 100644 --- a/src/lib/documents/__tests__/prepare-vision-raster-failure.test.ts +++ b/src/lib/documents/__tests__/prepare-vision-raster-failure.test.ts @@ -1,5 +1,7 @@ import { describe, expect, it, vi } from "vitest"; import { Buffer } from "node:buffer"; +import { readFileSync } from "node:fs"; +import { join } from "node:path"; /** * Refs #776 — the raster-failed chain, end to end through the REAL @@ -68,4 +70,17 @@ describe("raster-failed end to end (#776)", () => { const vision = await prepareVisionInput(DOC as never, true); expect(vision).toMatchObject({ ok: true }); }); + + it("a PDF whose pages all render blank is rasterFailed, not an image of nothing (#1124)", async () => { + // Text in render mode 3 only: pdfjs opens it and draws an empty page. + // Before the blank-page guard this went to the provider as one white + // JPEG and came back as a near-empty transcript indexed as a success. + vi.mocked(decryptDocumentContent).mockReturnValue( + readFileSync( + join(process.cwd(), "tests/fixtures/pdf/invisible-text-only.pdf"), + ) as never, + ); + const vision = await prepareVisionInput(DOC as never, false); + expect(vision).toEqual({ ok: false, reason: "rasterFailed" }); + }); }); diff --git a/src/lib/documents/__tests__/rasterize-pdf-cleanup.test.ts b/src/lib/documents/__tests__/rasterize-pdf-cleanup.test.ts index 4e0d2cdba..bdafb0bfa 100644 --- a/src/lib/documents/__tests__/rasterize-pdf-cleanup.test.ts +++ b/src/lib/documents/__tests__/rasterize-pdf-cleanup.test.ts @@ -18,9 +18,16 @@ vi.mock("pdfjs-dist/legacy/build/pdf.mjs", () => ({ canvasFactory: { create: () => ({ canvas: { + width: 1, + height: 1, toBuffer: () => Buffer.from([0xff, 0xd8]), }, - context: {}, + // One black pixel: an inked page, so the blank-page guard passes. + context: { + getImageData: () => ({ + data: new Uint8ClampedArray([0, 0, 0, 255]), + }), + }, }), }, getPage: async () => ({ diff --git a/src/lib/documents/__tests__/rasterize-pdf-font-data.test.ts b/src/lib/documents/__tests__/rasterize-pdf-font-data.test.ts new file mode 100644 index 000000000..86fd7c5fe --- /dev/null +++ b/src/lib/documents/__tests__/rasterize-pdf-font-data.test.ts @@ -0,0 +1,155 @@ +import { Buffer } from "node:buffer"; +import { existsSync, readFileSync } from "node:fs"; +import { join } from "node:path"; + +import { createCanvas, loadImage } from "@napi-rs/canvas"; +import { beforeEach, describe, expect, it, vi } from "vitest"; + +/** + * GitHub #1124 — PDFs from older OCRmyPDF archives got no thumbnail and an + * image-only vision read of them came back nearly empty. + * + * The runtime image has no system fonts. pdfjs was opened without its own + * font data and told to lean on system fonts, so any text it could not draw + * from an embedded program (a non-embedded standard font, or an embedded + * program it cannot parse) came out as nothing, and the page that reached + * the provider was the background alone. A workstation hides this because + * its own fonts stand in, so the rendering assertions below are regression + * guards here and the container is where they were proven red; the option + * and registration assertions are red on any host. + * + * Fixtures (`tests/fixtures/pdf/`, synthetic text only): + * - `ocrmypdf11-two-images-type1c.pdf` — the reporter's shape: PDF 1.7, + * pikepdf producer, one 630.5 x 861.6 pt page with a 150 ppi RGB JPEG and + * a 75 ppi RGB Flate image, Type 1C Helvetica and Palatino-Roman, and an + * invisible OCR text layer. + * - `fallback-fonts.pdf` — a letter in non-embedded Helvetica and in a + * Type 1C Palatino-Roman whose program pdfjs cannot parse. + * - `invisible-text-only.pdf` — text in render mode 3 and nothing else, so + * every page renders blank. + */ + +const { annotate, registerFromPath } = vi.hoisted(() => ({ + annotate: vi.fn(), + registerFromPath: vi.fn(), +})); +vi.mock("@/lib/logging/context", () => ({ annotate })); + +const getDocumentOptions: Record[] = []; +vi.mock("pdfjs-dist/legacy/build/pdf.mjs", async (importActual) => { + const actual = + await importActual(); + return { + ...actual, + getDocument: (opts: Record) => { + getDocumentOptions.push(opts); + return actual.getDocument(opts as never); + }, + }; +}); +vi.mock("@napi-rs/canvas", async (importActual) => { + const actual = await importActual(); + return { + ...actual, + GlobalFonts: { + ...actual.GlobalFonts, + registerFromPath: (path: string, alias?: string) => { + registerFromPath(path, alias); + return actual.GlobalFonts.registerFromPath(path, alias); + }, + }, + }; +}); + +import * as raster from "../rasterize-pdf"; +import { generateThumbnail } from "../thumbnail"; + +const FIXTURES = join(process.cwd(), "tests", "fixtures", "pdf"); +const fixture = (name: string) => readFileSync(join(FIXTURES, name)); + +/** Share of dark pixels in a JPEG, measured the way the rasterizer does. */ +async function inkOf(base64: string): Promise { + const image = await loadImage(Buffer.from(base64, "base64")); + const canvas = createCanvas(image.width, image.height); + const ctx = canvas.getContext("2d"); + ctx.drawImage(image, 0, 0); + const { data } = ctx.getImageData(0, 0, image.width, image.height); + let dark = 0; + for (let i = 0; i < data.length; i += 4) { + if (data[i]! + data[i + 1]! + data[i + 2]! < 384) dark++; + } + return dark / (data.length / 4); +} + +beforeEach(() => { + annotate.mockClear(); + registerFromPath.mockClear(); + getDocumentOptions.length = 0; + raster.__resetPdfjsAssetsForTests(); +}); + +describe("rasterizePdf font and decoder data (#1124)", () => { + it("gives pdfjs its font, CMap and wasm directories and no system fonts", async () => { + const result = await raster.rasterizePdf(fixture("fallback-fonts.pdf"), 1); + expect(result.ok).toBe(true); + const opts = getDocumentOptions.at(-1)!; + expect(opts.useSystemFonts).toBe(false); + for (const [key, probe] of [ + ["standardFontDataUrl", "FoxitSerif.pfb"], + ["standardFontDataUrl", "LiberationSans-Regular.ttf"], + ["cMapUrl", "UniJIS-UTF16-H.bcmap"], + ["wasmUrl", "openjpeg.wasm"], + ] as const) { + expect(typeof opts[key], key).toBe("string"); + expect(existsSync(`${opts[key] as string}${probe}`), probe).toBe(true); + } + expect(opts.cMapPacked).toBe(true); + }); + + it("registers a fallback face for every generic family pdfjs falls back to", async () => { + await raster.rasterizePdf(fixture("fallback-fonts.pdf"), 1); + const families = new Set(registerFromPath.mock.calls.map((c) => c[1])); + expect(families).toEqual(new Set(["sans-serif", "serif", "monospace"])); + for (const [path] of registerFromPath.mock.calls) { + expect(existsSync(path as string)).toBe(true); + } + }); + + it("renders the OCRmyPDF page with its scan and its text", async () => { + const result = await raster.rasterizePdf( + fixture("ocrmypdf11-two-images-type1c.pdf"), + ); + expect(result.ok).toBe(true); + if (!result.ok) return; + expect(result.images).toHaveLength(1); + expect(await inkOf(result.images[0]!.dataBase64)).toBeGreaterThan(0.005); + }); + + it("renders a letter whose fonts pdfjs has to substitute", async () => { + const result = await raster.rasterizePdf(fixture("fallback-fonts.pdf")); + expect(result.ok).toBe(true); + if (!result.ok) return; + expect(await inkOf(result.images[0]!.dataBase64)).toBeGreaterThan(0.001); + }); + + it("reports a document whose every page renders blank as render-failed", async () => { + const result = await raster.rasterizePdf( + fixture("invisible-text-only.pdf"), + ); + expect(result).toEqual({ ok: false, reason: "render-failed" }); + expect(annotate).toHaveBeenCalledWith({ + action: { name: "documents.rasterize.failed" }, + meta: { reason: "blank_pages", pages: 1 }, + }); + }); +}); + +describe("generateThumbnail on the OCRmyPDF shape (#1124)", () => { + it("produces a preview of the first page", async () => { + const result = await generateThumbnail( + fixture("ocrmypdf11-two-images-type1c.pdf"), + "application/pdf", + ); + expect(result.ok).toBe(true); + }); +}); diff --git a/src/lib/documents/__tests__/thumbnail.test.ts b/src/lib/documents/__tests__/thumbnail.test.ts index 59a03ab64..05a2630d6 100644 --- a/src/lib/documents/__tests__/thumbnail.test.ts +++ b/src/lib/documents/__tests__/thumbnail.test.ts @@ -126,19 +126,19 @@ describe("generateThumbnail", () => { it("returns { ok: false } for an unsupported MIME type", async () => { await expect( generateThumbnail(Buffer.from("plain text"), "text/plain"), - ).resolves.toEqual({ ok: false }); + ).resolves.toEqual({ ok: false, reason: "unsupported-type" }); }); it("returns { ok: false } and never throws on malformed image bytes", async () => { await expect( generateThumbnail(Buffer.from("not a real image"), "image/png"), - ).resolves.toEqual({ ok: false }); + ).resolves.toEqual({ ok: false, reason: "error" }); }); it("returns { ok: false } on a malformed PDF", async () => { await expect( generateThumbnail(Buffer.from("not a pdf"), "application/pdf"), - ).resolves.toEqual({ ok: false }); + ).resolves.toEqual({ ok: false, reason: "raster-failed" }); }); it("refuses a decompression bomb before decoding (pixel cap)", async () => { @@ -153,6 +153,7 @@ describe("generateThumbnail", () => { bomb.writeUInt32BE(30_000, 20); // height await expect(generateThumbnail(bomb, "image/png")).resolves.toEqual({ ok: false, + reason: "pixel-cap", }); }); @@ -164,6 +165,6 @@ describe("generateThumbnail", () => { loadImageMock.mockResolvedValueOnce({ width: 30_000, height: 30_000 }); await expect( generateThumbnail(Buffer.from("desynced jpeg bytes"), "image/jpeg"), - ).resolves.toEqual({ ok: false }); + ).resolves.toEqual({ ok: false, reason: "pixel-cap" }); }); }); diff --git a/src/lib/documents/rasterize-pdf.ts b/src/lib/documents/rasterize-pdf.ts index f61e74fc3..452ddfae5 100644 --- a/src/lib/documents/rasterize-pdf.ts +++ b/src/lib/documents/rasterize-pdf.ts @@ -31,6 +31,9 @@ * preserves the "a bad document never aborts an upload/batch" contract. */ import { Buffer } from "node:buffer"; +import { existsSync } from "node:fs"; +import { createRequire } from "node:module"; +import { dirname, join } from "node:path"; import { annotate } from "@/lib/logging/context"; @@ -60,6 +63,14 @@ export const RASTER_TARGET_LONG_EDGE = 1600; /** JPEG quality (0-100). ~80 keeps text legible at a fraction of PNG's bytes. */ export const RASTER_JPEG_QUALITY = 80; +/** + * A rendered page counts as blank when fewer than this share of its pixels + * are dark. One short line of 16 pt text on an A4 page is ~0.1 %; a page + * number alone sits near this floor. A page set that is blank throughout is + * not a reading of the document, whatever the provider would make of it. + */ +export const RASTER_MIN_INK_RATIO = 0.0001; + /** One rasterized page, shaped as a vision `input_image` part. */ export interface RasterImage { mediaType: "image/jpeg"; @@ -98,9 +109,17 @@ interface PdfCanvas { height: number; toBuffer(mime: "image/jpeg", quality?: number): Buffer; } +interface PdfContext2D { + getImageData( + x: number, + y: number, + width: number, + height: number, + ): { data: Uint8ClampedArray }; +} interface PdfCanvasAndContext { canvas: PdfCanvas; - context: unknown; + context: PdfContext2D; } interface PdfCanvasFactory { create(width: number, height: number): PdfCanvasAndContext; @@ -125,12 +144,127 @@ interface PdfLoadingTask { destroy(): Promise; } interface PdfjsModule { - getDocument(opts: { - data: Uint8Array; - verbosity?: number; - isEvalSupported?: boolean; - useSystemFonts?: boolean; - }): PdfLoadingTask; + getDocument(opts: PdfDocumentOptions): PdfLoadingTask; +} +interface PdfDocumentOptions { + data: Uint8Array; + verbosity?: number; + isEvalSupported?: boolean; + useSystemFonts?: boolean; + standardFontDataUrl?: string; + cMapUrl?: string; + cMapPacked?: boolean; + wasmUrl?: string; +} +interface GlobalFontsLike { + registerFromPath(path: string, nameAlias?: string): unknown; +} + +/** + * Where pdfjs finds the data it does not carry in its JS: the standard 14 + * fonts (a PDF that names Helvetica or Times without embedding them), the + * CMaps (CID fonts with a predefined encoding), and the wasm image decoders + * (JPEG 2000, JBIG2). In a browser pdfjs fetches these from a URL; under Node + * they are read from disk, and without a directory pdfjs simply draws the text + * without glyphs. + * + * The runtime image carries no system fonts at all, so nothing else catches + * that: a letter set in a non-embedded font rendered as an empty page in the + * container while it rendered correctly on a workstation, where the operating + * system's fonts stood in. The image-only provider then read the empty page + * and returned a line of nothing. + * + * Resolved from the working directory with Node's own resolution, which is + * what finds the hoisted `node_modules/pdfjs-dist` in the standalone image + * and the pnpm link in a checkout. The specifier is assembled at runtime so + * the bundler leaves the lookup alone. The ICC profile option is not set: its + * loader needs a synchronous XMLHttpRequest that Node lacks, and pdfjs falls + * back to each colour space's alternate. + */ +export interface PdfjsAssets { + standardFontDataUrl: string; + cMapUrl: string; + wasmUrl: string; + /** The Liberation Sans faces registered as the generic fallback families. */ + fallbackFonts: string[]; +} + +let cachedAssets: PdfjsAssets | null | undefined; + +export function resolvePdfjsAssets(): PdfjsAssets | null { + if (cachedAssets !== undefined) return cachedAssets; + cachedAssets = null; + try { + const anchor = createRequire(join(process.cwd(), "package.json")); + const root = dirname( + anchor.resolve(["pdfjs-dist", "package.json"].join("/")), + ); + const fonts = join(root, "standard_fonts"); + const assets: PdfjsAssets = { + standardFontDataUrl: `${fonts}/`, + cMapUrl: `${join(root, "cmaps")}/`, + wasmUrl: `${join(root, "wasm")}/`, + fallbackFonts: [ + "LiberationSans-Regular.ttf", + "LiberationSans-Bold.ttf", + "LiberationSans-Italic.ttf", + "LiberationSans-BoldItalic.ttf", + ].map((file) => join(fonts, file)), + }; + if ( + existsSync(join(fonts, "FoxitSerif.pfb")) && + existsSync(join(root, "cmaps", "UniJIS-UTF16-H.bcmap")) && + existsSync(join(root, "wasm", "openjpeg.wasm")) && + assets.fallbackFonts.every((file) => existsSync(file)) + ) { + cachedAssets = assets; + } + } catch { + // Unresolvable: render without the data, as before, and say so below. + } + return cachedAssets; +} + +let fallbackFamiliesRegistered = false; + +/** + * Give the canvas a face for the generic families pdfjs falls back to. + * + * When pdfjs cannot use a font program (a damaged or unsupported embedded + * font, or a non-embedded face outside the standard 14) it draws the text + * with the canvas' own `fillText` under the PDF's font name and a generic + * family. With no system fonts in the image that text vanished. Registering + * Liberation Sans, which pdfjs ships, under `sans-serif`, `serif` and + * `monospace` makes it legible instead. Once per process. + */ +async function registerFallbackFamilies(assets: PdfjsAssets): Promise { + if (fallbackFamiliesRegistered) return; + fallbackFamiliesRegistered = true; + const { GlobalFonts } = (await import("@napi-rs/canvas")) as unknown as { + GlobalFonts: GlobalFontsLike; + }; + for (const family of ["sans-serif", "serif", "monospace"]) { + for (const file of assets.fallbackFonts) { + GlobalFonts.registerFromPath(file, family); + } + } +} + +/** Share of dark pixels on a rendered page (luminance below half). */ +function inkRatio(context: PdfContext2D, width: number, height: number) { + const { data } = context.getImageData(0, 0, width, height); + let dark = 0; + for (let i = 0; i < data.length; i += 4) { + if (data[i]! + data[i + 1]! + data[i + 2]! < 384) dark++; + } + const pixels = data.length / 4; + return pixels > 0 ? dark / pixels : 0; +} + +/** Test hook: the asset lookup and the font registration are per process. */ +export function __resetPdfjsAssetsForTests(): void { + cachedAssets = undefined; + fallbackFamiliesRegistered = false; } /** @@ -163,11 +297,31 @@ export async function rasterizePdf( const pdfjs = (await import("pdfjs-dist/legacy/build/pdf.mjs")) as unknown as PdfjsModule; + const assets = resolvePdfjsAssets(); + if (assets) { + await registerFallbackFamilies(assets); + } else { + annotate({ + action: { name: "documents.rasterize.assetsMissing" }, + meta: { reason: "pdfjs_assets_unresolved" }, + }); + } + task = pdfjs.getDocument({ data: new Uint8Array(buffer), verbosity: 0, // VerbosityLevel.ERRORS — no console spam on odd PDFs. isEvalSupported: false, // never eval font programs (defence in depth). - useSystemFonts: true, + // There are no system fonts to use: substitutes come from pdfjs' own + // standard font data and the fallback families registered above. + useSystemFonts: false, + ...(assets + ? { + standardFontDataUrl: assets.standardFontDataUrl, + cMapUrl: assets.cMapUrl, + cMapPacked: true, + wasmUrl: assets.wasmUrl, + } + : {}), }); doc = await task.promise; @@ -175,6 +329,7 @@ export async function rasterizePdf( const cap = Math.min(Math.max(1, maxPages), RASTER_MAX_PAGES); const pageCount = Math.min(doc.numPages, cap); const images: RasterImage[] = []; + let blankPages = 0; for (let pageNumber = 1; pageNumber <= pageCount; pageNumber++) { const page = await doc.getPage(pageNumber); @@ -196,6 +351,12 @@ export async function rasterizePdf( viewport, canvas: cc.canvas, }).promise; + if ( + inkRatio(cc.context, cc.canvas.width, cc.canvas.height) < + RASTER_MIN_INK_RATIO + ) { + blankPages++; + } const jpeg = cc.canvas.toBuffer("image/jpeg", RASTER_JPEG_QUALITY); images.push({ mediaType: "image/jpeg", @@ -217,9 +378,19 @@ export async function rasterizePdf( }); return { ok: false, reason: "render-failed" }; } + if (blankPages === images.length) { + // Every rendered page came out empty. Sending those to a vision model + // buys a transcript of nothing that would be indexed as a success; say + // the render failed instead, so the read reports `raster-failed`. + annotate({ + action: { name: "documents.rasterize.failed" }, + meta: { reason: "blank_pages", pages: images.length }, + }); + return { ok: false, reason: "render-failed" }; + } annotate({ action: { name: "documents.rasterize.ok" }, - meta: { pages: images.length, cappedFrom: doc.numPages }, + meta: { pages: images.length, cappedFrom: doc.numPages, blankPages }, }); return { ok: true, images, pageCount: doc.numPages }; } catch (err) { diff --git a/src/lib/documents/thumbnail.ts b/src/lib/documents/thumbnail.ts index 8d975954f..26ed69c1b 100644 --- a/src/lib/documents/thumbnail.ts +++ b/src/lib/documents/thumbnail.ts @@ -157,9 +157,23 @@ export interface Thumbnail { height: number; } +/** + * Why no preview was made. `unsupported-type` is the expected answer for an + * Office file or a text document; every other reason means a preview should + * have existed, so the thumbnail job logs it as a warning. + */ +export type ThumbnailSkipReason = + | "unsupported-type" + | "native-canvas-unsupported" + | "pixel-cap" + | "raster-failed" + | "empty-render" + | "error"; + /** Best-effort generation outcome — never an exception. */ export type ThumbnailResult = - { ok: true; thumbnail: Thumbnail } | { ok: false }; + | { ok: true; thumbnail: Thumbnail } + | { ok: false; reason: ThumbnailSkipReason }; // Minimal structural types for the slice of `@napi-rs/canvas` this module uses. // A type-only shape (erased at build) so we never eagerly evaluate the module @@ -229,7 +243,7 @@ export async function generateThumbnail( action: { name: "documents.thumbnail.rejected" }, meta: { reason: "native_canvas_unsupported" }, }); - return { ok: false }; + return { ok: false, reason: "native-canvas-unsupported" }; } // Lazy import: keeps @napi-rs/canvas (+ transitively pdfjs on the PDF path) // out of the eager server chunk. Resolved on first generation, then cached. @@ -244,7 +258,7 @@ export async function generateThumbnail( action: { name: "documents.thumbnail.rejected" }, meta: { source: "image", reason: "pixel_cap", pixels }, }); - return { ok: false }; + return { ok: false, reason: "pixel-cap" }; } const image = await napi.loadImage(bytes); // Post-decode backstop: the header sniff returns null on any marker @@ -260,10 +274,10 @@ export async function generateThumbnail( pixels: image.width * image.height, }, }); - return { ok: false }; + return { ok: false, reason: "pixel-cap" }; } const thumb = drawScaledJpeg(napi, image); - if (!thumb) return { ok: false }; + if (!thumb) return { ok: false, reason: "empty-render" }; annotate({ action: { name: "documents.thumbnail.ok" }, meta: { source: "image", width: thumb.width, height: thumb.height }, @@ -274,11 +288,13 @@ export async function generateThumbnail( if (mimeType === "application/pdf") { // Page 1 only — a preview never renders the whole document. const raster = await rasterizePdf(bytes, 1); - if (!raster.ok || raster.images.length === 0) return { ok: false }; + if (!raster.ok || raster.images.length === 0) { + return { ok: false, reason: "raster-failed" }; + } const pageJpeg = Buffer.from(raster.images[0]!.dataBase64, "base64"); const image = await napi.loadImage(pageJpeg); const thumb = drawScaledJpeg(napi, image); - if (!thumb) return { ok: false }; + if (!thumb) return { ok: false, reason: "empty-render" }; annotate({ action: { name: "documents.thumbnail.ok" }, meta: { source: "pdf", width: thumb.width, height: thumb.height }, @@ -287,7 +303,7 @@ export async function generateThumbnail( } // Every other MIME (Office/text/TIFF/HEIC/XML/JSON) — no preview. - return { ok: false }; + return { ok: false, reason: "unsupported-type" }; } catch (err) { annotate({ action: { name: "documents.thumbnail.failed" }, @@ -297,6 +313,6 @@ export async function generateThumbnail( message: err instanceof Error ? err.message.slice(0, 300) : String(err), }, }); - return { ok: false }; + return { ok: false, reason: "error" }; } } diff --git a/src/lib/jobs/__tests__/document-thumbnail.test.ts b/src/lib/jobs/__tests__/document-thumbnail.test.ts new file mode 100644 index 000000000..4270507d1 --- /dev/null +++ b/src/lib/jobs/__tests__/document-thumbnail.test.ts @@ -0,0 +1,98 @@ +import { beforeEach, describe, expect, it, vi } from "vitest"; + +/** + * GitHub #1124 — the thumbnail job ran 355 times on one instance, left + * sixteen PDFs without a preview, and the log held not one line about it: + * the job opened no wide event, so every annotation went nowhere. Pins: each + * run is a `job.document_thumbnail` background event; a run that should have + * made a preview and did not is raised to `warn` with the reason; a type that + * never has a preview stays at info. + */ + +const { evt, findFirst, upsert, generateThumbnail, withBackgroundEvent } = + vi.hoisted(() => { + const evt = { addMeta: vi.fn(), elevateLevel: vi.fn() }; + return { + evt, + findFirst: vi.fn(), + upsert: vi.fn(), + generateThumbnail: vi.fn(), + withBackgroundEvent: vi.fn( + async (_name: string, fn: (e: typeof evt) => Promise) => + fn(evt), + ), + }; + }); + +vi.mock("@/lib/db", () => ({ + prisma: { + inboundDocument: { findFirst }, + documentThumbnail: { upsert }, + }, +})); +vi.mock("@/lib/documents/store", () => ({ + decryptDocumentContent: vi.fn(() => Buffer.from("%PDF-1.7")), + encryptThumbnail: vi.fn(() => new Uint8Array([1])), +})); +vi.mock("@/lib/documents/thumbnail", () => ({ generateThumbnail })); +vi.mock("@/lib/jobs/boss-instance", () => ({ getGlobalBoss: vi.fn() })); +vi.mock("@/lib/logging/context", () => ({ annotate: vi.fn() })); +vi.mock("@/lib/logging/background", () => ({ withBackgroundEvent })); + +import { runDocumentThumbnail } from "../document-thumbnail"; + +const DOC = { + id: "doc-1", + mimeType: "application/pdf", + contentEncrypted: new Uint8Array([1]), + contentCodec: "binary2", + thumbnail: null, +}; + +beforeEach(() => { + vi.clearAllMocks(); + findFirst.mockResolvedValue(DOC); +}); + +describe("runDocumentThumbnail wide event", () => { + it("runs inside a background event named for the job", async () => { + generateThumbnail.mockResolvedValue({ ok: false, reason: "raster-failed" }); + await runDocumentThumbnail({ userId: "user-1", documentId: "doc-1" }); + expect(withBackgroundEvent).toHaveBeenCalledWith( + "job.document_thumbnail", + expect.any(Function), + ); + expect(evt.addMeta).toHaveBeenCalledWith("document_id", "doc-1"); + }); + + it("warns with the reason when a PDF gets no preview", async () => { + generateThumbnail.mockResolvedValue({ ok: false, reason: "error" }); + await runDocumentThumbnail({ userId: "user-1", documentId: "doc-1" }); + expect(evt.elevateLevel).toHaveBeenCalledWith("warn"); + expect(evt.addMeta).toHaveBeenCalledWith( + "thumbnail_missing_reason", + "error", + ); + expect(upsert).not.toHaveBeenCalled(); + }); + + it("stays at info for a type that never has a preview", async () => { + findFirst.mockResolvedValue({ ...DOC, mimeType: "text/plain" }); + generateThumbnail.mockResolvedValue({ + ok: false, + reason: "unsupported-type", + }); + await runDocumentThumbnail({ userId: "user-1", documentId: "doc-1" }); + expect(evt.elevateLevel).not.toHaveBeenCalled(); + }); + + it("stores the preview and stays at info when one is made", async () => { + generateThumbnail.mockResolvedValue({ + ok: true, + thumbnail: { jpeg: Buffer.from([0xff, 0xd8]), width: 2, height: 3 }, + }); + await runDocumentThumbnail({ userId: "user-1", documentId: "doc-1" }); + expect(upsert).toHaveBeenCalledOnce(); + expect(evt.elevateLevel).not.toHaveBeenCalled(); + }); +}); diff --git a/src/lib/jobs/document-thumbnail.ts b/src/lib/jobs/document-thumbnail.ts index 91a8d44ed..1b0a1a91d 100644 --- a/src/lib/jobs/document-thumbnail.ts +++ b/src/lib/jobs/document-thumbnail.ts @@ -15,6 +15,12 @@ * kind icon), and `runDocumentThumbnail` returns cleanly so pg-boss does not * retry it. Only an unexpected throw (a DB hiccup) propagates for retry. * + * Each run is one background wide event (`job.document_thumbnail`). A run + * that should have produced a preview and did not is raised to `warn` with + * the reason, so a document left with its kind icon is explained in the log. + * Without the event every annotation below went nowhere: a whole class of + * PDFs went without previews for weeks and the log never said so. + * * The queue MUST be registered in the maintenance registrar * (`src/lib/jobs/reminder/register-maintenance.ts`) so pg-boss provisions it. */ @@ -25,6 +31,7 @@ import { } from "@/lib/documents/store"; import { generateThumbnail } from "@/lib/documents/thumbnail"; import { getGlobalBoss } from "@/lib/jobs/boss-instance"; +import { withBackgroundEvent } from "@/lib/logging/background"; import { annotate } from "@/lib/logging/context"; export const DOCUMENT_THUMBNAIL_QUEUE = "document-thumbnail"; @@ -49,7 +56,20 @@ export async function runDocumentThumbnail( ): Promise { const { userId, documentId } = payload; if (!userId || !documentId) return; + await withBackgroundEvent("job.document_thumbnail", async (evt) => { + evt.addMeta("document_id", documentId); + await renderThumbnail(userId, documentId, (reason) => { + evt.addMeta("thumbnail_missing_reason", reason); + evt.elevateLevel("warn"); + }); + }); +} +async function renderThumbnail( + userId: string, + documentId: string, + warn: (reason: string) => void, +): Promise { // Owner-scoped load; the blob column is selected ONLY here (the job that // renders the preview), never in the list/detail queries. Skip a document // that already has a thumbnail so a re-enqueue is a cheap no-op. @@ -84,6 +104,7 @@ export async function runDocumentThumbnail( action: { name: "documents.thumbnail.decryptFailed" }, meta: { documentId }, }); + warn("decrypt-failed"); return; } @@ -91,8 +112,11 @@ export async function runDocumentThumbnail( if (!result.ok) { annotate({ action: { name: "documents.thumbnail.run" }, - meta: { documentId, generated: false }, + meta: { documentId, generated: false, mimeType: document.mimeType }, }); + // An Office or text document has no preview by design; anything else + // was meant to get one. + if (result.reason !== "unsupported-type") warn(result.reason); return; } diff --git a/tests/fixtures/pdf/fallback-fonts.pdf b/tests/fixtures/pdf/fallback-fonts.pdf new file mode 100644 index 000000000..ee01b4fa0 Binary files /dev/null and b/tests/fixtures/pdf/fallback-fonts.pdf differ diff --git a/tests/fixtures/pdf/invisible-text-only.pdf b/tests/fixtures/pdf/invisible-text-only.pdf new file mode 100644 index 000000000..929c6870c Binary files /dev/null and b/tests/fixtures/pdf/invisible-text-only.pdf differ diff --git a/tests/fixtures/pdf/ocrmypdf11-two-images-type1c.pdf b/tests/fixtures/pdf/ocrmypdf11-two-images-type1c.pdf new file mode 100644 index 000000000..b9b9bd6a6 Binary files /dev/null and b/tests/fixtures/pdf/ocrmypdf11-two-images-type1c.pdf differ