feat: add record building with threshold and input validation

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-25 12:04:55 +03:00
parent d88c06d086
commit 386b88bab5
2 changed files with 184 additions and 0 deletions
@@ -0,0 +1,53 @@
+import { isVideoId } from './video-id.js';
+
+const PAGES = new Set(['home', 'watch', 'search', 'channel']);
+const MAX_TEXT = 300;
+
+export function shouldSave({ views, outlierScore }, { threshold, minViews }) {
+  return typeof outlierScore === 'number' && outlierScore >= threshold && views >= minViews;
+}
+
+const finiteOrNull = (value) => (typeof value === 'number' && Number.isFinite(value) ? value : null);
+const textOrNull = (value) => (typeof value === 'string' && value.trim() ? value.trim().slice(0, MAX_TEXT) : null);
+const urlOrNull = (value, prefix) => (typeof value === 'string' && value.startsWith(prefix) ? value : null);
+
+// Validates a message coming from the content script before anything is stored.
+export function sanitizeItem(raw) {
+  if (!raw || !isVideoId(raw.videoId)) return null;
+  const outlierScore = finiteOrNull(raw.outlierScore);
+  const views = finiteOrNull(raw.views);
+  if (outlierScore === null || outlierScore < 0 || views === null || views < 0) return null;
+  const subscribers = finiteOrNull(raw.subscribers);
+  return {
+    videoId: raw.videoId,
+    title: textOrNull(raw.title),
+    thumbnailUrl: urlOrNull(raw.thumbnailUrl, 'https://i.ytimg.com/'),
+    channelTitle: textOrNull(raw.channelTitle),
+    channelUrl: urlOrNull(raw.channelUrl, 'https://www.youtube.com/'),
+    subscribers: subscribers !== null && subscribers >= 0 ? subscribers : null,
+    views,
+    outlierScore: Math.round(outlierScore * 100) / 100,
+    isShort: raw.isShort === true,
+    page: PAGES.has(raw.page) ? raw.page : 'home',
+  };
+}
+
+export function buildRecord(item, previous, settings, now = new Date()) {
+  if (!previous && !shouldSave(item, settings)) return null;
+  const nowIso = now.toISOString();
+  return {
+    videoId: item.videoId,
+    title: item.title ?? previous?.title ?? item.videoId,
+    url: `https://www.youtube.com/watch?v=${item.videoId}`,
+    thumbnailUrl: item.thumbnailUrl ?? previous?.thumbnailUrl ?? null,
+    channelTitle: item.channelTitle ?? previous?.channelTitle ?? null,
+    channelUrl: item.channelUrl ?? previous?.channelUrl ?? null,
+    subscribers: item.subscribers ?? previous?.subscribers ?? null,
+    views: item.views,
+    outlierScore: item.outlierScore,
+    isShort: item.isShort || previous?.isShort || false,
+    foundOn: previous?.foundOn ?? item.page,
+    firstSeenAt: previous?.firstSeenAt ?? nowIso,
+    updatedAt: nowIso,
+  };
+}
@@ -0,0 +1,131 @@
+import { test } from 'node:test';
+import assert from 'node:assert/strict';
+import { buildRecord, sanitizeItem, shouldSave } from '../src/lib/record.js';
+
+const settings = { threshold: 5, minViews: 10000 };
+const NOW = new Date('2026-10-25T10:00:00.000Z');
+const NOW_ISO = NOW.toISOString();
+
+test('shouldSave accepts a video exactly at both limits', () => {
+  assert.equal(shouldSave({ views: 10000, outlierScore: 5 }, settings), true);
+});
+
+test('shouldSave rejects a low score, low views or a missing score', () => {
+  assert.equal(shouldSave({ views: 50000, outlierScore: 4.99 }, settings), false);
+  assert.equal(shouldSave({ views: 9999, outlierScore: 150 }, settings), false);
+  assert.equal(shouldSave({ views: 50000, outlierScore: null }, settings), false);
+});
+
+const raw = (over = {}) => ({
+  videoId: 'Tts9NHL8D8I',
+  title: 'Agar.io - 88k Score',
+  thumbnailUrl: 'https://i.ytimg.com/vi/Tts9NHL8D8I/hq720.jpg',
+  channelTitle: 'Wun Wun',
+  channelUrl: 'https://www.youtube.com/@wunwun9522',
+  subscribers: 571000,
+  views: 59000000,
+  outlierScore: 146.19,
+  isShort: false,
+  page: 'home',
+  ...over,
+});
+
+test('sanitizeItem passes a valid item through unchanged', () => {
+  assert.deepEqual(sanitizeItem(raw()), raw());
+});
+
+test('sanitizeItem rejects items without a usable id, score or views', () => {
+  for (const bad of [
+    null,
+    undefined,
+    'x',
+    {},
+    raw({ videoId: 'short' }),
+    raw({ outlierScore: NaN }),
+    raw({ outlierScore: null }),
+    raw({ outlierScore: -1 }),
+    raw({ views: null }),
+    raw({ views: -5 }),
+    raw({ views: '5' }),
+  ]) {
+    assert.equal(sanitizeItem(bad), null, JSON.stringify(bad));
+  }
+});
+
+test('sanitizeItem nulls out unusable optional fields', () => {
+  const item = sanitizeItem(
+    raw({
+      title: '   ',
+      thumbnailUrl: 'javascript:alert(1)',
+      channelTitle: 5,
+      channelUrl: 'https://evil.example.com/@x',
+      subscribers: -3,
+      isShort: 'yes',
+      page: 'nowhere',
+    }),
+  );
+  assert.deepEqual(
+    item,
+    raw({ title: null, thumbnailUrl: null, channelTitle: null, channelUrl: null, subscribers: null, isShort: false, page: 'home' }),
+  );
+});
+
+test('sanitizeItem trims and caps the title and rounds the score', () => {
+  const item = sanitizeItem(raw({ title: `  ${'x'.repeat(400)}  `, outlierScore: 12.3456 }));
+  assert.equal(item.title.length, 300);
+  assert.equal(item.outlierScore, 12.35);
+});
+
+test('buildRecord creates a full record for a new outlier', () => {
+  assert.deepEqual(buildRecord(sanitizeItem(raw()), undefined, settings, NOW), {
+    videoId: 'Tts9NHL8D8I',
+    title: 'Agar.io - 88k Score',
+    url: 'https://www.youtube.com/watch?v=Tts9NHL8D8I',
+    thumbnailUrl: 'https://i.ytimg.com/vi/Tts9NHL8D8I/hq720.jpg',
+    channelTitle: 'Wun Wun',
+    channelUrl: 'https://www.youtube.com/@wunwun9522',
+    subscribers: 571000,
+    views: 59000000,
+    outlierScore: 146.19,
+    isShort: false,
+    foundOn: 'home',
+    firstSeenAt: NOW_ISO,
+    updatedAt: NOW_ISO,
+  });
+});
+
+test('buildRecord skips a new video below the threshold', () => {
+  assert.equal(buildRecord(sanitizeItem(raw({ outlierScore: 2 })), undefined, settings, NOW), null);
+  assert.equal(buildRecord(sanitizeItem(raw({ views: 500 })), undefined, settings, NOW), null);
+});
+
+test('buildRecord keeps updating an already saved video even below the threshold', () => {
+  const previous = buildRecord(sanitizeItem(raw()), undefined, settings, new Date('2026-10-20T00:00:00.000Z'));
+  const updated = buildRecord(sanitizeItem(raw({ outlierScore: 1.5, views: 60000000, page: 'search' })), previous, settings, NOW);
+  assert.equal(updated.outlierScore, 1.5);
+  assert.equal(updated.views, 60000000);
+  assert.equal(updated.updatedAt, NOW_ISO);
+  assert.equal(updated.firstSeenAt, '2026-10-20T00:00:00.000Z');
+  assert.equal(updated.foundOn, 'home');
+});
+
+test('buildRecord keeps known values when the new sighting lacks them', () => {
+  const previous = buildRecord(sanitizeItem(raw({ isShort: true })), undefined, settings, new Date('2026-10-20T00:00:00.000Z'));
+  const updated = buildRecord(
+    sanitizeItem(raw({ subscribers: null, channelTitle: null, channelUrl: null, thumbnailUrl: null, title: null, isShort: false })),
+    previous,
+    settings,
+    NOW,
+  );
+  assert.equal(updated.subscribers, 571000);
+  assert.equal(updated.channelTitle, 'Wun Wun');
+  assert.equal(updated.channelUrl, 'https://www.youtube.com/@wunwun9522');
+  assert.equal(updated.thumbnailUrl, 'https://i.ytimg.com/vi/Tts9NHL8D8I/hq720.jpg');
+  assert.equal(updated.title, 'Agar.io - 88k Score');
+  assert.equal(updated.isShort, true);
+});
+
+test('buildRecord falls back to the id when a new video has no title', () => {
+  const record = buildRecord(sanitizeItem(raw({ title: null })), undefined, settings, NOW);
+  assert.equal(record.title, 'Tts9NHL8D8I');
+});