generated from coulomb/repo-seed
tegwick
d54daf2e61
Completes the PDF review slice end-to-end. After this commit a user can
open a fixture, select text, save an evidence item with commentary, see
it in the sidebar, reload the page, click the item, and the viewer
scrolls to the passage.
- T03 src/source/pdf/{fingerprint,extract,ingest}.ts + 39 fixture tests
- SHA-256 fingerprint over a fresh ArrayBuffer (TS BufferSource-safe)
- PDF.js text extract; per-page normalize then join with "\n\n"
- PageMap + OffsetMap (gap-free coverage); pageLength = end - start
- Updated manifest's Betriebskosten quote to one PDF.js extracts cleanly
- T04 src/anchor/selectors/{create,resolve}.ts + 25 unit + 7 fixture tests
- createSelectors emits the maximal redundant set (TextQuote +
TextPosition + PdfRect + PdfPageText when available)
- resolveSelectors implements the SharedContracts §7 ladder; confidence
1.0 (pos+quote) → 0.7 (rect-only) → 0 (unresolved)
- Cross-module integration test moved to tests/integration/ to honor
the anchor↛source boundary lint rule
- T05 engine: sync event bus over the closed §4 vocabulary, Map-backed
repos, services, createEngine() composition root, 12 tests
- T06 work + app: three-pane shell (CollectionList | ViewerShell |
EvidenceSidebar) wired through EngineProvider; EngineContext lives in
src/work/ to respect the work↛app boundary; SpikeApp deleted
- T07 AnnotationToolbar: pendingSelection in context; Save runs
createSelectors → engine.annotations.create → engine.evidence.create
- T08 click-to-reopen + localStorage persistence
- scrollToAnnotation state in context with a version counter so a
second click on the same item re-fires the viewer scroll
- captureSnapshot/restoreSnapshot/attachPersister/restoreFromStorage;
restore bypasses services to avoid event-loops
- active-document id persisted alongside the snapshot so reload lands
on the same fixture; ADR-0005 written
- 9 persistence tests
- T09 tests/integration/app-prd-scenario.dom.test.tsx
- end-to-end happy-dom test of PRD scenario steps 1-8 through the real
React tree; viewer + ingest mocked per ADR-0004's headless-Chromium
limitation. Fixed memo-deps bug in EvidenceSidebar/ViewerShell where
useEngineEventTick values were not included in the useMemo deps,
leaving stale memoization across event-driven re-renders
- vitest.config.ts: happy-dom for *.dom.test.{ts,tsx} files
- noEmit added to tsconfig so tsc -b doesn't litter src/ with .js outputs
Gates: typecheck ✓ lint ✓ test 109/109 across 11 files ✓ build ✓
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
73 lines
2.7 KiB
TypeScript
73 lines
2.7 KiB
TypeScript
/**
|
|
* Integration round-trip: ingest → createSelectors → resolveSelectors.
|
|
*
|
|
* This test crosses the source ↔ anchor boundary, which the
|
|
* `boundaries/element-types` lint rule (correctly) forbids inside `src/`.
|
|
* It lives under `tests/integration/` so it can verify the end-to-end
|
|
* MVP contract without weakening the production-code boundary.
|
|
*
|
|
* CE-WP-0002-T04 contract:
|
|
* For each fixture+known-quote pair, create selectors then immediately
|
|
* resolve them; resolution must succeed with confidence ≥ 0.9.
|
|
*/
|
|
|
|
import { readFileSync } from "node:fs";
|
|
import { dirname, resolve } from "node:path";
|
|
import { createRequire } from "node:module";
|
|
import { fileURLToPath } from "node:url";
|
|
import { beforeAll, describe, expect, it } from "vitest";
|
|
|
|
import { ingestPdf } from "@source/pdf/ingest";
|
|
import { createSelectors, resolveSelectors } from "@anchor/selectors";
|
|
import type { PdfSelectionCapture } from "@anchor/types";
|
|
import manifest from "../../fixtures/pdfs/manifest.json" with { type: "json" };
|
|
|
|
const __dirname = dirname(fileURLToPath(import.meta.url));
|
|
const FIXTURE_DIR = resolve(__dirname, "../../fixtures/pdfs");
|
|
|
|
interface Fixture {
|
|
id: string;
|
|
filename: string;
|
|
known_good_quote: string;
|
|
known_good_quote_page: number;
|
|
}
|
|
|
|
const FIXTURES: readonly Fixture[] = manifest.fixtures;
|
|
|
|
beforeAll(async () => {
|
|
const pdfjs = await import("pdfjs-dist");
|
|
const require = createRequire(import.meta.url);
|
|
pdfjs.GlobalWorkerOptions.workerSrc = require.resolve(
|
|
"pdfjs-dist/legacy/build/pdf.worker.mjs",
|
|
);
|
|
});
|
|
|
|
describe("create + resolve round-trip — fixture corpus", () => {
|
|
for (const fixture of FIXTURES) {
|
|
it(`${fixture.id}: known-good quote round-trips with confidence ≥ 0.9`, async () => {
|
|
const bytes = new Uint8Array(readFileSync(resolve(FIXTURE_DIR, fixture.filename)));
|
|
const { representation } = await ingestPdf(bytes, { filename: fixture.filename });
|
|
|
|
const capture: PdfSelectionCapture = {
|
|
kind: "pdf",
|
|
text: fixture.known_good_quote,
|
|
page: fixture.known_good_quote_page,
|
|
rects: [{ x: 0.1, y: 0.2, width: 0.5, height: 0.04 }],
|
|
};
|
|
|
|
const selectors = createSelectors(capture, representation);
|
|
const resolution = resolveSelectors(selectors, representation);
|
|
|
|
expect(resolution.status).toBe("resolved");
|
|
expect(resolution.confidence).toBeGreaterThanOrEqual(0.9);
|
|
|
|
const span = resolution.candidates[0]?.textPosition;
|
|
expect(span).toBeDefined();
|
|
const text = representation.canonicalText ?? "";
|
|
expect(text.slice(span!.start, span!.end)).toBe(fixture.known_good_quote);
|
|
|
|
expect(resolution.candidates[0]?.page).toBe(fixture.known_good_quote_page);
|
|
});
|
|
}
|
|
});
|