Merge pull request #9 from AlekShu/bb-f36d

Reject duplicate documents on upload

Author: ashugaev

.github/workflows/ci.yml

@@ -87,3 +87,34 @@ jobs:
       - name: Audit production dependencies
         run: npm audit --omit=dev --audit-level=critical
 
+  e2e:
+    name: Run E2E
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Install Playwright browser
+        run: npx playwright install --with-deps chromium
+
+      - name: Run Playwright tests
+        run: npm run e2e
+
+      - name: Upload Playwright report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-report
+          path: |
+            playwright-report
+            test-results

.gitignore

@@ -6,6 +6,12 @@ dist-ssr
 
 .DS_Store
 
+# Playwright
+/playwright-report/
+/test-results/
+/blob-report/
+/playwright/.cache/
+
 *.log
 npm-debug.log*
 yarn-debug.log*

AGENTS.md

@@ -0,0 +1,6 @@
+## Verification Defaults
+
+- After every code update, run the default verification set: `npm run lint`, `npm run typecheck`, `npm test`.
+- For UI-affecting changes, also run `npm run e2e` or an equivalent live UI smoke check against the current dev server.
+- Use Spur sidecars for local runtime checks by default.
+

e2e/duplicate-documents.spec.ts

@@ -0,0 +1,38 @@
+import { createHash } from 'node:crypto'
+import { readFileSync } from 'node:fs'
+import path from 'node:path'
+
+import { expect, test } from '@playwright/test'
+
+declare global {
+    interface Window {
+        __bloodboyE2E?: {
+            reset(): Promise<void>
+            seedExactFileDuplicateScenario(fileHash: string): Promise<void>
+        }
+    }
+}
+
+const fixturePath = path.join(process.cwd(), 'e2e/fixtures/exact-duplicate.pdf')
+const fixtureHash = createHash('sha256').update(readFileSync(fixturePath)).digest('hex')
+
+test.beforeEach(async ({ page }) => {
+    await page.goto('/data')
+    await page.waitForFunction(() => typeof window.__bloodboyE2E !== 'undefined')
+})
+
+test('excludes an identical file on upload with a notification', async ({ page }) => {
+    await page.evaluate(async (fileHash) => {
+        await window.__bloodboyE2E?.seedExactFileDuplicateScenario(fileHash)
+    }, fixtureHash)
+
+    await page.reload()
+    await page.locator('input[name="file"]').setInputFiles(fixturePath)
+
+    await expect(page.getByText('File excluded as duplicate')).toBeVisible()
+    await expect(page.getByText('is identical to a file you already uploaded')).toBeVisible()
+
+    // The duplicate file is not added: the files list still shows only the seeded document.
+    await page.getByRole('tab', { name: 'Files' }).click()
+    await expect(page.getByRole('gridcell', { name: 'exact-duplicate.pdf' })).toHaveCount(1)
+})

e2e/fixtures/exact-duplicate.pdf

@@ -50,7 +50,9 @@
     "preview": "vite preview",
     "test": "vitest run",
     "test:watch": "vitest",
-    "test:ui": "vitest --ui"
+    "test:ui": "vitest --ui",
+    "e2e": "playwright test",
+    "e2e:ui": "playwright test --ui"
   },
   "dependencies": {
     "@ag-grid-community/client-side-row-model": "32.3.9",
@@ -85,6 +87,7 @@
     "zod-error": "2.0.0"
   },
   "devDependencies": {
+    "@playwright/test": "1.59.1",
     "@svgr/plugin-jsx": "8.1.0",
     "@svgr/plugin-svgo": "8.1.0",
     "@tanstack/eslint-plugin-query": "5.91.2",
@@ -113,8 +116,8 @@
     "tailwindcss": "3.4.17",
     "typescript": "5.9.3",
     "vite": "6.4.0",
-    "vitest": "2.1.8",
     "vite-plugin-svgr": "4.5.0",
-    "vite-tsconfig-paths": "5.1.4"
+    "vite-tsconfig-paths": "5.1.4",
+    "vitest": "2.1.8"
   }
 }

package-lock.json

@@ -0,0 +1,40 @@
+import { defineConfig, devices } from '@playwright/test'
+
+const baseURL = process.env.PLAYWRIGHT_BASE_URL ?? 'http://127.0.0.1:4173'
+
+export default defineConfig({
+    testDir: './e2e',
+    fullyParallel: true,
+    forbidOnly: !!process.env.CI,
+    retries: process.env.CI ? 2 : 0,
+    workers: process.env.CI ? 1 : undefined,
+    reporter: [
+        ['list'],
+        ['html', {
+            open: 'never',
+            outputFolder: 'playwright-report',
+        }],
+    ],
+    use: {
+        baseURL,
+        trace: 'retain-on-failure',
+        screenshot: 'only-on-failure',
+        video: 'retain-on-failure',
+    },
+    webServer: process.env.PLAYWRIGHT_BASE_URL
+        ? undefined
+        : {
+            command: 'npm run dev -- --host 127.0.0.1 --port 4173',
+            url: baseURL,
+            reuseExistingServer: !process.env.CI,
+            timeout: 120000,
+        },
+    projects: [
+        {
+            name: 'chromium',
+            use: {
+                ...devices['Desktop Chrome'],
+            },
+        },
+    ],
+})