import {
  isLink,
  isMention,
  isTag,
} from '../src/client/types/app/bsky/richtext/facet.js'
import { AtpAgent, RichText, RichTextSegment } from '../src/index.js'

describe('detectFacets', () => {
  const agent = new AtpAgent({ service: 'http://localhost' })

  // Mock handle resolution
  agent.com.atproto.identity.resolveHandle = async (params) => ({
    success: true,
    headers: {},
    data: { did: `did:fake:${params?.handle}` },
  })

  const inputs = [
    'no mention',
    '@handle.com middle end',
    'start @handle.com end',
    'start middle @handle.com',
    '@handle.com @handle.com @handle.com',
    '@full123-chars.test',
    'not@right',
    '@handle.com!@#$chars',
    '@handle.com\n@handle.com',
    'parenthetical (@handle.com)',
    '👨‍👩‍👧‍👧 @handle.com 👨‍👩‍👧‍👧',

    'start https://middle.com end',
    'start https://middle.com/foo/bar end',
    'start https://middle.com/foo/bar?baz=bux end',
    'start https://middle.com/foo/bar?baz=bux#hash end',
    'https://start.com/foo/bar?baz=bux#hash middle end',
    'start middle https://end.com/foo/bar?baz=bux#hash',
    'https://newline1.com\nhttps://newline2.com',
    '👨‍👩‍👧‍👧 https://middle.com 👨‍👩‍👧‍👧',

    'start middle.com end',
    'start middle.com/foo/bar end',
    'start middle.com/foo/bar?baz=bux end',
    'start middle.com/foo/bar?baz=bux#hash end',
    'start.com/foo/bar?baz=bux#hash middle end',
    'start middle end.com/foo/bar?baz=bux#hash',
    'newline1.com\nnewline2.com',
    'a example.com/index.php php link',
    'a trailing bsky.app: colon',

    'not.. a..url ..here',
    'e.g.',
    'something-cool.jpg',
    'website.com.jpg',
    'e.g./foo',
    'website.com.jpg/foo',

    'Classic article https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/',
    'Classic article https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/ ',
    'https://foo.com https://bar.com/whatever https://baz.com',
    'punctuation https://foo.com, https://bar.com/whatever; https://baz.com.',
    'parenthentical (https://foo.com)',
    'except for https://foo.com/thing_(cool)',
  ]
  const outputs: string[][][] = [
    [['no mention']],
    [['@handle.com', 'did:fake:handle.com'], [' middle end']],
    [['start '], ['@handle.com', 'did:fake:handle.com'], [' end']],
    [['start middle '], ['@handle.com', 'did:fake:handle.com']],
    [
      ['@handle.com', 'did:fake:handle.com'],
      [' '],
      ['@handle.com', 'did:fake:handle.com'],
      [' '],
      ['@handle.com', 'did:fake:handle.com'],
    ],
    [['@full123-chars.test', 'did:fake:full123-chars.test']],
    [['not@right']],
    [['@handle.com', 'did:fake:handle.com'], ['!@#$chars']],
    [
      ['@handle.com', 'did:fake:handle.com'],
      ['\n'],
      ['@handle.com', 'did:fake:handle.com'],
    ],
    [['parenthetical ('], ['@handle.com', 'did:fake:handle.com'], [')']],
    [['👨‍👩‍👧‍👧 '], ['@handle.com', 'did:fake:handle.com'], [' 👨‍👩‍👧‍👧']],

    [['start '], ['https://middle.com', 'https://middle.com'], [' end']],
    [
      ['start '],
      ['https://middle.com/foo/bar', 'https://middle.com/foo/bar'],
      [' end'],
    ],
    [
      ['start '],
      [
        'https://middle.com/foo/bar?baz=bux',
        'https://middle.com/foo/bar?baz=bux',
      ],
      [' end'],
    ],
    [
      ['start '],
      [
        'https://middle.com/foo/bar?baz=bux#hash',
        'https://middle.com/foo/bar?baz=bux#hash',
      ],
      [' end'],
    ],
    [
      [
        'https://start.com/foo/bar?baz=bux#hash',
        'https://start.com/foo/bar?baz=bux#hash',
      ],
      [' middle end'],
    ],
    [
      ['start middle '],
      [
        'https://end.com/foo/bar?baz=bux#hash',
        'https://end.com/foo/bar?baz=bux#hash',
      ],
    ],
    [
      ['https://newline1.com', 'https://newline1.com'],
      ['\n'],
      ['https://newline2.com', 'https://newline2.com'],
    ],
    [['👨‍👩‍👧‍👧 '], ['https://middle.com', 'https://middle.com'], [' 👨‍👩‍👧‍👧']],

    [['start '], ['middle.com', 'https://middle.com'], [' end']],
    [
      ['start '],
      ['middle.com/foo/bar', 'https://middle.com/foo/bar'],
      [' end'],
    ],
    [
      ['start '],
      ['middle.com/foo/bar?baz=bux', 'https://middle.com/foo/bar?baz=bux'],
      [' end'],
    ],
    [
      ['start '],
      [
        'middle.com/foo/bar?baz=bux#hash',
        'https://middle.com/foo/bar?baz=bux#hash',
      ],
      [' end'],
    ],
    [
      [
        'start.com/foo/bar?baz=bux#hash',
        'https://start.com/foo/bar?baz=bux#hash',
      ],
      [' middle end'],
    ],
    [
      ['start middle '],
      ['end.com/foo/bar?baz=bux#hash', 'https://end.com/foo/bar?baz=bux#hash'],
    ],
    [
      ['newline1.com', 'https://newline1.com'],
      ['\n'],
      ['newline2.com', 'https://newline2.com'],
    ],
    [
      ['a '],
      ['example.com/index.php', 'https://example.com/index.php'],
      [' php link'],
    ],
    [['a trailing '], ['bsky.app', 'https://bsky.app'], [': colon']],

    [['not.. a..url ..here']],
    [['e.g.']],
    [['something-cool.jpg']],
    [['website.com.jpg']],
    [['e.g./foo']],
    [['website.com.jpg/foo']],

    [
      ['Classic article '],
      [
        'https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/',
        'https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/',
      ],
    ],
    [
      ['Classic article '],
      [
        'https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/',
        'https://socket3.wordpress.com/2018/02/03/designing-windows-95s-user-interface/',
      ],
      [' '],
    ],
    [
      ['https://foo.com', 'https://foo.com'],
      [' '],
      ['https://bar.com/whatever', 'https://bar.com/whatever'],
      [' '],
      ['https://baz.com', 'https://baz.com'],
    ],
    [
      ['punctuation '],
      ['https://foo.com', 'https://foo.com'],
      [', '],
      ['https://bar.com/whatever', 'https://bar.com/whatever'],
      ['; '],
      ['https://baz.com', 'https://baz.com'],
      ['.'],
    ],
    [['parenthentical ('], ['https://foo.com', 'https://foo.com'], [')']],
    [
      ['except for '],
      ['https://foo.com/thing_(cool)', 'https://foo.com/thing_(cool)'],
    ],
  ]
  it('correctly handles a set of text inputs', async () => {
    for (let i = 0; i < inputs.length; i++) {
      const input = inputs[i]
      const rt = new RichText({ text: input })
      await rt.detectFacets(agent)
      expect(Array.from(rt.segments(), segmentToOutput)).toEqual(outputs[i])
    }
  })

  describe('correctly detects tags inline', () => {
    const inputs: [
      string,
      string[],
      { byteStart: number; byteEnd: number }[],
    ][] = [
      ['#a', ['a'], [{ byteStart: 0, byteEnd: 2 }]],
      [
        '#a #b',
        ['a', 'b'],
        [
          { byteStart: 0, byteEnd: 2 },
          { byteStart: 3, byteEnd: 5 },
        ],
      ],
      ['#1', [], []],
      ['#1a', ['1a'], [{ byteStart: 0, byteEnd: 3 }]],
      ['#tag', ['tag'], [{ byteStart: 0, byteEnd: 4 }]],
      ['body #tag', ['tag'], [{ byteStart: 5, byteEnd: 9 }]],
      ['#tag body', ['tag'], [{ byteStart: 0, byteEnd: 4 }]],
      ['body #tag body', ['tag'], [{ byteStart: 5, byteEnd: 9 }]],
      ['body #1', [], []],
      ['body #1a', ['1a'], [{ byteStart: 5, byteEnd: 8 }]],
      ['body #a1', ['a1'], [{ byteStart: 5, byteEnd: 8 }]],
      ['#', [], []],
      ['#?', [], []],
      ['text #', [], []],
      ['text # text', [], []],
      [
        'body #thisisa64characterstring_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa',
        ['thisisa64characterstring_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'],
        [{ byteStart: 5, byteEnd: 70 }],
      ],
      [
        'body #thisisa65characterstring_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaab',
        [],
        [],
      ],
      [
        'body #thisisa64characterstring_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa!',
        ['thisisa64characterstring_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'],
        [{ byteStart: 5, byteEnd: 70 }],
      ],
      [
        'its a #double#rainbow',
        ['double#rainbow'],
        [{ byteStart: 6, byteEnd: 21 }],
      ],
      ['##hashash', ['#hashash'], [{ byteStart: 0, byteEnd: 9 }]],
      ['##', [], []],
      ['some #n0n3s@n5e!', ['n0n3s@n5e'], [{ byteStart: 5, byteEnd: 15 }]],
      [
        'works #with,punctuation',
        ['with,punctuation'],
        [{ byteStart: 6, byteEnd: 23 }],
      ],
      [
        'strips trailing #punctuation, #like. #this!',
        ['punctuation', 'like', 'this'],
        [
          { byteStart: 16, byteEnd: 28 },
          { byteStart: 30, byteEnd: 35 },
          { byteStart: 37, byteEnd: 42 },
        ],
      ],
      [
        'strips #multi_trailing___...',
        ['multi_trailing'],
        [{ byteStart: 7, byteEnd: 22 }],
      ],
      [
        'works with #🦋 emoji, and #butter🦋fly',
        ['🦋', 'butter🦋fly'],
        [
          { byteStart: 11, byteEnd: 16 },
          { byteStart: 28, byteEnd: 42 },
        ],
      ],
      [
        '#same #same #but #diff',
        ['same', 'same', 'but', 'diff'],
        [
          { byteStart: 0, byteEnd: 5 },
          { byteStart: 6, byteEnd: 11 },
          { byteStart: 12, byteEnd: 16 },
          { byteStart: 17, byteEnd: 22 },
        ],
      ],
      ['this #️⃣tag should not be a tag', [], []],
      [
        'this ##️⃣tag should be a tag',
        ['#️⃣tag'],
        [
          {
            byteStart: 5,
            byteEnd: 16,
          },
        ],
      ],
      [
        'this #t\nag should be a tag',
        ['t'],
        [
          {
            byteStart: 5,
            byteEnd: 7,
          },
        ],
      ],
      ['no match (\\u200B): #​', [], []],
      ['no match (\\u200Ba): #​a', [], []],
      ['match (a\\u200Bb): #a​b', ['a'], [{ byteStart: 18, byteEnd: 20 }]],
      ['match (ab\\u200B): #ab​', ['ab'], [{ byteStart: 18, byteEnd: 21 }]],
      ['no match (\\u20e2tag): #⃢tag', [], []],
      ['no match (a\\u20e2b): #a⃢b', ['a'], [{ byteStart: 21, byteEnd: 23 }]],
      [
        'match full width number sign (tag): ＃tag',
        ['tag'],
        [{ byteStart: 36, byteEnd: 42 }],
      ],
      [
        'match full width number sign (tag): ＃#️⃣tag',
        ['#️⃣tag'],
        [{ byteStart: 36, byteEnd: 49 }],
      ],
      ['no match 1?: #1?', [], []],
    ]

    it.each(inputs)('%s', async (input, tags, indices) => {
      const rt = new RichText({ text: input })
      await rt.detectFacets(agent)

      const detectedTags: string[] = []
      const detectedIndices: { byteStart: number; byteEnd: number }[] = []

      for (const { facet } of rt.segments()) {
        if (!facet) continue
        for (const feature of facet.features) {
          if (isTag(feature)) {
            detectedTags.push(feature.tag)
          }
        }
        detectedIndices.push(facet.index)
      }

      expect(detectedTags).toEqual(tags)
      expect(detectedIndices).toEqual(indices)
    })
  })

  describe('correctly detects cashtags inline', () => {
    const inputs: [
      string,
      string[],
      { byteStart: number; byteEnd: number }[],
    ][] = [
      ['$AAPL', ['$AAPL'], [{ byteStart: 0, byteEnd: 5 }]],
      ['$aapl', ['$AAPL'], [{ byteStart: 0, byteEnd: 5 }]], // normalized to uppercase
      ['$A', ['$A'], [{ byteStart: 0, byteEnd: 2 }]],
      ['$a', ['$A'], [{ byteStart: 0, byteEnd: 2 }]], // single char normalized
      [
        '$BTC $ETH',
        ['$BTC', '$ETH'],
        [
          { byteStart: 0, byteEnd: 4 },
          { byteStart: 5, byteEnd: 9 },
        ],
      ],
      ['$100', [], []], // starts with digit - not a cashtag
      ['$GOOGL', ['$GOOGL'], [{ byteStart: 0, byteEnd: 6 }]], // 5 chars - max length
      ['$TOOLONG', [], []], // >5 chars
      ['check $LEGO now', ['$LEGO'], [{ byteStart: 6, byteEnd: 11 }]],
      ['($GOOG)', ['$GOOG'], [{ byteStart: 1, byteEnd: 6 }]],
      ['$AAPL.', ['$AAPL'], [{ byteStart: 0, byteEnd: 5 }]], // trailing punctuation
      [
        '$AAPL, $MSFT!',
        ['$AAPL', '$MSFT'],
        [
          { byteStart: 0, byteEnd: 5 },
          { byteStart: 7, byteEnd: 12 },
        ],
      ],
      ['no$SPACE', [], []], // must have leading space or start
      ['$', [], []], // just dollar sign
      ['$ AAPL', [], []], // space after $
      ['$123ABC', [], []], // starts with digit
      ['$ABC12', ['$ABC12'], [{ byteStart: 0, byteEnd: 6 }]], // digits after letters OK (5 chars)
      ['$ABC123', [], []], // 6 chars - too long
    ]

    it.each(inputs)('%s', (input, tags, indices) => {
      const rt = new RichText({ text: input })
      rt.detectFacetsWithoutResolution()

      const detectedTags: string[] = []
      const detectedIndices: { byteStart: number; byteEnd: number }[] = []

      for (const { facet } of rt.segments()) {
        if (!facet) continue
        for (const feature of facet.features) {
          if (isTag(feature) && feature.tag.startsWith('$')) {
            detectedTags.push(feature.tag)
          }
        }
        if (
          facet.features.some(
            (f) => isTag(f) && (f as any).tag?.startsWith('$'),
          )
        ) {
          detectedIndices.push(facet.index)
        }
      }

      expect(detectedTags).toEqual(tags)
      expect(detectedIndices).toEqual(indices)
    })
  })
})

function segmentToOutput(segment: RichTextSegment): string[] {
  if (segment.facet) {
    return [
      segment.text,
      segment.facet?.features.map((f) => {
        if (isMention(f)) return f.did
        if (isLink(f)) return f.uri
        return undefined
      })?.[0] || '',
    ]
  }
  return [segment.text]
}