AeroFetch/test/indexer.test.ts

import { describe, it, expect } from 'vitest'
import {
  classifySource,
  buildMediaItems,
  mergeItemsPreservingState,
  buildFeedUrl,
  isYouTubeFeedUrl,
  parseRssVideoIds,
  entryUrl,
  fmtDuration,
  stripTabSuffix,
  stableSourceId,
  type RawEntry
} from '../src/main/indexerCore'
import type { MediaItem } from '@shared/ipc'

describe('classifySource', () => {
  it('classifies channel handle / id / c / user forms and strips the tab', () => {
    expect(classifySource('https://www.youtube.com/@LinusTechTips')).toEqual({
      kind: 'channel',
      base: 'https://www.youtube.com/@LinusTechTips'
    })
    expect(classifySource('https://youtube.com/@Foo/videos')).toEqual({
      kind: 'channel',
      base: 'https://www.youtube.com/@Foo'
    })
    expect(classifySource('https://www.youtube.com/channel/UC123/playlists')?.base).toBe(
      'https://www.youtube.com/channel/UC123'
    )
    expect(classifySource('https://www.youtube.com/c/SomeName')?.kind).toBe('channel')
    expect(classifySource('https://www.youtube.com/user/Legacy')?.kind).toBe('channel')
  })

  it('classifies a playlist by its list= param and canonicalises it', () => {
    expect(classifySource('https://www.youtube.com/playlist?list=PL_abc')).toEqual({
      kind: 'playlist',
      base: 'https://www.youtube.com/playlist?list=PL_abc'
    })
    // a watch URL that also carries list= is treated as the playlist
    expect(classifySource('https://www.youtube.com/watch?v=xyz&list=PLfoo')?.kind).toBe('playlist')
  })

  it('returns null for a lone video, a bad URL, or a non-YouTube host', () => {
    expect(classifySource('https://www.youtube.com/watch?v=dQw4w9WgXcQ')).toBeNull()
    expect(classifySource('not a url')).toBeNull()
    expect(classifySource('ftp://example.com/@chan')).toBeNull()
    expect(classifySource('https://vimeo.com/channels/staffpicks')).toBeNull()
  })
})

describe('entryUrl', () => {
  it('prefers an explicit http(s) url, else builds a watch url from the id', () => {
    expect(entryUrl({ url: 'https://youtu.be/abc' })).toBe('https://youtu.be/abc')
    expect(entryUrl({ webpage_url: 'https://x/y' })).toBe('https://x/y')
    expect(entryUrl({ id: 'vid123' })).toBe('https://www.youtube.com/watch?v=vid123')
  })
  it('rejects a non-http url and returns null when nothing usable is present', () => {
    expect(entryUrl({ url: 'javascript:alert(1)' })).toBeNull()
    expect(entryUrl({})).toBeNull()
  })
  it('percent-encodes an untrusted id rather than splicing it raw (audit T2)', () => {
    expect(entryUrl({ id: 'ab cd&x=1' })).toBe('https://www.youtube.com/watch?v=ab%20cd%26x%3D1')
    expect(entryUrl({ id: 'vid123' })).toBe('https://www.youtube.com/watch?v=vid123') // unchanged
  })
})

describe('fmtDuration', () => {
  it('formats seconds as M:SS or H:MM:SS', () => {
    expect(fmtDuration(0)).toBe('0:00')
    expect(fmtDuration(75)).toBe('1:15')
    expect(fmtDuration(3661)).toBe('1:01:01')
    expect(fmtDuration(undefined)).toBeUndefined()
    expect(fmtDuration(NaN)).toBeUndefined()
  })
})

describe('stripTabSuffix', () => {
  it('strips a trailing " - <Tab>" suffix only', () => {
    expect(stripTabSuffix('Creator - Videos')).toBe('Creator')
    expect(stripTabSuffix('Creator - Playlists')).toBe('Creator')
    expect(stripTabSuffix('Just A Name')).toBe('Just A Name')
    expect(stripTabSuffix('Tech - Tips')).toBe('Tech - Tips') // 'Tips' isn't a tab
    expect(stripTabSuffix(undefined)).toBeUndefined()
  })
})

describe('stableSourceId', () => {
  it('is deterministic and 8 hex chars', () => {
    const a = stableSourceId('https://www.youtube.com/@Foo')
    expect(a).toMatch(/^[0-9a-f]{8}$/)
    expect(stableSourceId('https://www.youtube.com/@Foo')).toBe(a)
    expect(stableSourceId('https://www.youtube.com/@Bar')).not.toBe(a)
  })
})

describe('buildMediaItems', () => {
  const vids = (...ids: string[]): RawEntry[] => ids.map((id) => ({ id, title: `T-${id}` }))

  it('files videos under their playlist with 1-based per-playlist index', () => {
    const items = buildMediaItems('src1', [{ title: 'Series A', entries: vids('a', 'b') }], [])
    expect(items).toHaveLength(2)
    expect(items[0]).toMatchObject({
      id: 'src1:a',
      sourceId: 'src1',
      videoId: 'a',
      playlistTitle: 'Series A',
      playlistIndex: 1,
      downloaded: false
    })
    expect(items[1]).toMatchObject({ videoId: 'b', playlistIndex: 2 })
  })

  it('dedups across playlists — the first playlist a video appears in wins', () => {
    const items = buildMediaItems(
      'src1',
      [
        { title: 'First', entries: vids('x', 'y') },
        { title: 'Second', entries: vids('y', 'z') }
      ],
      []
    )
    expect(items.map((i) => i.videoId)).toEqual(['x', 'y', 'z'])
    expect(items.find((i) => i.videoId === 'y')?.playlistTitle).toBe('First')
  })

  it('falls back to the synthetic Uploads folder for videos in no playlist', () => {
    const items = buildMediaItems('src1', [{ title: 'P', entries: vids('a') }], vids('a', 'b'))
    // 'a' already filed under P; only 'b' becomes an Uploads item
    expect(items).toHaveLength(2)
    expect(items.find((i) => i.videoId === 'a')?.playlistTitle).toBe('P')
    const b = items.find((i) => i.videoId === 'b')
    expect(b).toMatchObject({ playlistTitle: 'Uploads', playlistIndex: 2 })
  })

  it('skips entries with no id or no resolvable URL', () => {
    const items = buildMediaItems('src1', [{ title: 'P', entries: [{ title: 'no id' }] }], [])
    expect(items).toHaveLength(0)
  })
})

describe('mergeItemsPreservingState', () => {
  const item = (videoId: string, over: Partial<MediaItem> = {}): MediaItem => ({
    id: `s:${videoId}`,
    sourceId: 's',
    videoId,
    title: videoId,
    url: `https://youtube.com/watch?v=${videoId}`,
    playlistTitle: 'P',
    playlistIndex: 1,
    downloaded: false,
    ...over
  })

  it('carries downloaded state forward for videos already on disk', () => {
    const existing = [item('a', { downloaded: true, downloadedAt: 111, filePath: 'C:/a.mp4' })]
    const fresh = [item('a'), item('b')]
    const { items, newCount } = mergeItemsPreservingState(existing, fresh)
    expect(newCount).toBe(1) // only 'b' is new
    expect(items.find((i) => i.videoId === 'a')).toMatchObject({
      downloaded: true,
      downloadedAt: 111,
      filePath: 'C:/a.mp4'
    })
    expect(items.find((i) => i.videoId === 'b')?.downloaded).toBe(false)
  })

  it('adopts the fresh membership/order and drops vanished videos', () => {
    const existing = [item('a', { downloaded: true }), item('gone', { downloaded: true })]
    const fresh = [item('a', { playlistTitle: 'Moved', playlistIndex: 5 })]
    const { items, newCount } = mergeItemsPreservingState(existing, fresh)
    expect(items).toHaveLength(1) // 'gone' dropped
    expect(newCount).toBe(0)
    // fresh playlist assignment wins, but downloaded state is preserved
    expect(items[0]).toMatchObject({ playlistTitle: 'Moved', playlistIndex: 5, downloaded: true })
  })

  it('counts every video as new on a first index (empty existing)', () => {
    const { newCount } = mergeItemsPreservingState([], [item('a'), item('b'), item('c')])
    expect(newCount).toBe(3)
  })
})

describe('buildFeedUrl', () => {
  it('builds a channel feed by channel_id and a playlist feed by playlist_id', () => {
    expect(buildFeedUrl('channel', 'UCabc')).toBe(
      'https://www.youtube.com/feeds/videos.xml?channel_id=UCabc'
    )
    expect(buildFeedUrl('playlist', 'PLxyz')).toBe(
      'https://www.youtube.com/feeds/videos.xml?playlist_id=PLxyz'
    )
  })
  it('returns undefined when the id is missing', () => {
    expect(buildFeedUrl('channel', undefined)).toBeUndefined()
  })
})

describe('isYouTubeFeedUrl (audit T7 — SSRF guard)', () => {
  it('accepts a youtube feeds URL (www optional) and what buildFeedUrl produces', () => {
    expect(isYouTubeFeedUrl('https://www.youtube.com/feeds/videos.xml?channel_id=UCabc')).toBe(true)
    expect(isYouTubeFeedUrl('https://youtube.com/feeds/videos.xml?playlist_id=PLxyz')).toBe(true)
    expect(isYouTubeFeedUrl(buildFeedUrl('channel', 'UCabc')!)).toBe(true)
    expect(isYouTubeFeedUrl(buildFeedUrl('playlist', 'PLxyz')!)).toBe(true)
  })

  it('rejects internal/arbitrary hosts, wrong scheme, and wrong path (SSRF vectors)', () => {
    expect(isYouTubeFeedUrl('http://169.254.169.254/latest/meta-data/')).toBe(false) // cloud metadata
    expect(isYouTubeFeedUrl('http://localhost:8080/admin')).toBe(false)
    expect(isYouTubeFeedUrl('https://evil.com/feeds/videos.xml')).toBe(false)
    expect(isYouTubeFeedUrl('https://notyoutube.com.evil.com/feeds/videos.xml')).toBe(false)
    expect(isYouTubeFeedUrl('http://www.youtube.com/feeds/videos.xml')).toBe(false) // not https
    expect(isYouTubeFeedUrl('https://www.youtube.com/watch?v=x')).toBe(false) // wrong path
    expect(isYouTubeFeedUrl('file:///etc/passwd')).toBe(false)
    expect(isYouTubeFeedUrl('not a url')).toBe(false)
  })
})

describe('parseRssVideoIds', () => {
  it('extracts every <yt:videoId> from a feed body, in order', () => {
    const xml = `
      <feed><entry><yt:videoId>aaa111</yt:videoId></entry>
      <entry><yt:videoId> bbb222 </yt:videoId></entry></feed>`
    expect(parseRssVideoIds(xml)).toEqual(['aaa111', 'bbb222'])
  })
  it('returns an empty array for a feed with no entries', () => {
    expect(parseRssVideoIds('<feed></feed>')).toEqual([])
  })
})