generated from coulomb/repo-seed
tegwick
2a7b05c190
T01: shared engine types (Document, Selector union, Annotation, EvidenceItem, branded IDs with newId factory) per wiki/SharedContracts.md §1-§3. T02: react-pdf-highlighter-plus v1.1.4 spike behind the §5 DocumentViewerAdapter contract in src/anchor/. Pure round-trip math extracted to pdf-selector-math.ts with 11 unit tests proving lossless capture → selectors → JSON → restored-rects. ADR-0004 accepted; full user-flow Playwright verification deferred to T09. Adds Vite app shell (index.html, src/app/SpikeApp.tsx) so the spike is exercisable via pnpm dev. tsconfig --noEmit prevents tsc -b from littering src/ with stray .js outputs. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
112 lines
4.1 KiB
TypeScript
112 lines
4.1 KiB
TypeScript
/**
|
|
* Round-trip tests for the spike's pure transformation layer.
|
|
*
|
|
* These tests are CE-WP-0002-T02's machine-verifiable evidence that the
|
|
* adapter's data round-trip is lossless: a captured PDF selection becomes
|
|
* a `Selector[]`, the `Selector[]` round-trips through JSON
|
|
* (localStorage-equivalent), and the reconstructed PDF rect + page match
|
|
* the original. The browser-side selection-capture path is exercised in
|
|
* T09 against production code.
|
|
*/
|
|
|
|
import { describe, expect, it } from "vitest";
|
|
import {
|
|
findPdfRectSelector,
|
|
findTextQuoteSelector,
|
|
selectorsFromPdfCapture,
|
|
unionRect,
|
|
} from "./pdf-selector-math";
|
|
import type { PdfSelectionCapture } from "./types";
|
|
import type { NormalizedRect, Selector } from "@shared/selector";
|
|
|
|
const SAMPLE_CAPTURE: PdfSelectionCapture = {
|
|
kind: "pdf",
|
|
text: "Mitglied beim Lohnsteuerhilfeverein Vereinigte Lohnsteuerhilfe e.V.",
|
|
page: 1,
|
|
rects: [
|
|
{ x: 0.12, y: 0.34, width: 0.55, height: 0.02 },
|
|
{ x: 0.12, y: 0.37, width: 0.31, height: 0.02 },
|
|
],
|
|
boundingRect: { x: 0.12, y: 0.34, width: 0.55, height: 0.05 },
|
|
};
|
|
|
|
describe("selectorsFromPdfCapture", () => {
|
|
it("produces a TextQuoteSelector and PdfRectSelector from a normal capture", () => {
|
|
const sels = selectorsFromPdfCapture(SAMPLE_CAPTURE);
|
|
expect(sels.map((s) => s.type)).toEqual(["TextQuoteSelector", "PdfRectSelector"]);
|
|
});
|
|
|
|
it("includes the verbatim quote on the TextQuoteSelector", () => {
|
|
const tq = findTextQuoteSelector(selectorsFromPdfCapture(SAMPLE_CAPTURE));
|
|
expect(tq?.exact).toBe(SAMPLE_CAPTURE.text);
|
|
});
|
|
|
|
it("preserves page + rects 1:1 on the PdfRectSelector", () => {
|
|
const rect = findPdfRectSelector(selectorsFromPdfCapture(SAMPLE_CAPTURE));
|
|
expect(rect?.page).toBe(SAMPLE_CAPTURE.page);
|
|
expect(rect?.rects).toEqual(SAMPLE_CAPTURE.rects);
|
|
});
|
|
|
|
it("omits TextQuoteSelector when text is empty", () => {
|
|
const sels = selectorsFromPdfCapture({ ...SAMPLE_CAPTURE, text: "" });
|
|
expect(sels.map((s) => s.type)).toEqual(["PdfRectSelector"]);
|
|
});
|
|
|
|
it("omits PdfRectSelector when no rects are present", () => {
|
|
const sels = selectorsFromPdfCapture({ ...SAMPLE_CAPTURE, rects: [] });
|
|
expect(sels.map((s) => s.type)).toEqual(["TextQuoteSelector"]);
|
|
});
|
|
});
|
|
|
|
describe("Selector[] JSON round-trip", () => {
|
|
it("survives JSON.stringify/parse without loss (the localStorage path)", () => {
|
|
const original = selectorsFromPdfCapture(SAMPLE_CAPTURE);
|
|
const blob = JSON.stringify(original);
|
|
const restored = JSON.parse(blob) as Selector[];
|
|
expect(restored).toEqual(original);
|
|
});
|
|
|
|
it("the restored PdfRectSelector still resolves to the same page and rects", () => {
|
|
const restored = JSON.parse(JSON.stringify(selectorsFromPdfCapture(SAMPLE_CAPTURE))) as Selector[];
|
|
const rect = findPdfRectSelector(restored);
|
|
expect(rect).not.toBeNull();
|
|
expect(rect?.page).toBe(SAMPLE_CAPTURE.page);
|
|
expect(rect?.rects).toEqual(SAMPLE_CAPTURE.rects);
|
|
});
|
|
});
|
|
|
|
describe("unionRect", () => {
|
|
it("returns null for an empty input", () => {
|
|
expect(unionRect([])).toBeNull();
|
|
});
|
|
|
|
it("returns the single rect when given exactly one", () => {
|
|
const r: NormalizedRect = { x: 0.1, y: 0.2, width: 0.3, height: 0.4 };
|
|
const u = unionRect([r]);
|
|
expect(u).not.toBeNull();
|
|
expect(u!.x).toBeCloseTo(r.x, 9);
|
|
expect(u!.y).toBeCloseTo(r.y, 9);
|
|
expect(u!.width).toBeCloseTo(r.width, 9);
|
|
expect(u!.height).toBeCloseTo(r.height, 9);
|
|
});
|
|
|
|
it("computes the bounding box of multi-line text rects", () => {
|
|
const u = unionRect(SAMPLE_CAPTURE.rects);
|
|
expect(u).not.toBeNull();
|
|
expect(u!.x).toBeCloseTo(0.12, 5);
|
|
expect(u!.y).toBeCloseTo(0.34, 5);
|
|
expect(u!.width).toBeCloseTo(0.55, 5);
|
|
expect(u!.height).toBeCloseTo(0.05, 5);
|
|
});
|
|
|
|
it("is order-independent", () => {
|
|
const reversed = [...SAMPLE_CAPTURE.rects].reverse();
|
|
const forward = unionRect(SAMPLE_CAPTURE.rects)!;
|
|
const back = unionRect(reversed)!;
|
|
expect(back.x).toBeCloseTo(forward.x, 9);
|
|
expect(back.y).toBeCloseTo(forward.y, 9);
|
|
expect(back.width).toBeCloseTo(forward.width, 9);
|
|
expect(back.height).toBeCloseTo(forward.height, 9);
|
|
});
|
|
});
|