// @vitest-environment node import { describe, expect, it } from 'vitest' import { aggregateBackfillRuns, buildOfficialPdfUrl, buildVodUrl, classifyOfficialTextUrl, clockToSeconds, dateRangeChunks, isLegacyDiarioUrl, legislatureForDate, matchExcerpt, normalizeSpeakerName, normalizeTranscription, officialTextUrlFallback, parseDiarioDate, parseDirectOfficialPdfUrl, parseDurationToSeconds, parseEventExcerpts, parseLegacyOfficialUrl, parseMontaPdfUrl, parseOfficialKeywords, parsePresidingOfficerTransitions, parseVodStatus, planOfficialLinkRepairs, publicationCacheKey, resolvePresidingOfficer, selectLinkSample, selectSpeechEvents, speechContentHash, speechDate, speechSourceKey, speechTimeOfDaySeconds, } from '../../scripts/lib/camaraSpeeches.mjs' const excerptHtml = ( eventId: number, { audioId, tMs, speaker, party, startTime, duration, }: { audioId: number tMs: number speaker: string party: string startTime: string duration: string }, ) => `

${speaker}

${party}
Horário - ${startTime}
Duração - ${duration}
` describe('normalizeSpeakerName', () => { it('strips accents, case and punctuation', () => { expect(normalizeSpeakerName(' Jorge Solla ')).toBe('JORGE SOLLA') expect(normalizeSpeakerName('José Ação')).toBe('JOSE ACAO') expect(normalizeSpeakerName('')).toBe('') }) }) describe('clock helpers', () => { it('parses HH:MM and HH:MM:SS', () => { expect(clockToSeconds('17:30')).toBe(63000) expect(clockToSeconds('09:28:15')).toBe(34095) expect(clockToSeconds('24:00')).toBeNull() expect(clockToSeconds('abc')).toBeNull() }) it('extracts time-of-day and date from a naive datetime', () => { expect(speechTimeOfDaySeconds('2023-02-07T17:28')).toBe(62880) expect(speechTimeOfDaySeconds('2023-02-07')).toBeNull() expect(speechDate('2023-02-07T17:28')).toBe('2023-02-07') }) }) describe('parseEventExcerpts', () => { it('reads the speaker anchors with card metadata', () => { const html = [ excerptHtml(67091, { audioId: 558641, tMs: 1675801808560, speaker: 'JORGE SOLLA', party: 'DEPUTADO (PT-BA)', startTime: '17:30', duration: '0h04\'07"', }), excerptHtml(67091, { audioId: 558641, tMs: 1675792829010, speaker: 'POMPEO DE MATTOS', party: 'DEPUTADO (PDT-RS)', startTime: '21:22', duration: '0h04\'03"', }), ].join('\n') expect(parseEventExcerpts(html, 67091)).toEqual([ { audioId: 558641, tMs: 1675801808560, speaker: 'JORGE SOLLA', party: 'DEPUTADO (PT-BA)', startTime: '17:30', duration: '0h04\'07"', }, { audioId: 558641, tMs: 1675792829010, speaker: 'POMPEO DE MATTOS', party: 'DEPUTADO (PDT-RS)', startTime: '21:22', duration: '0h04\'03"', }, ]) }) it('returns [] when the page has no excerpt anchors or the event id differs', () => { const html = excerptHtml(111, { audioId: 5, tMs: 1000, speaker: 'X', party: 'Y', startTime: '10:00', duration: '0h01\'00"', }) expect(parseEventExcerpts(html, 67091)).toEqual([]) expect(parseEventExcerpts('', 67091)).toEqual([]) }) it('degrades card metadata to null when the spans are missing', () => { const html = 'x' expect(parseEventExcerpts(html, 67091)).toEqual([ { audioId: 5, tMs: 1000, speaker: 'JORGE SOLLA', party: null, startTime: null, duration: null, }, ]) }) }) describe('buildVodUrl', () => { it('targets the async VOD endpoint with audio id and excerpt epoch', () => { expect(buildVodUrl(67091, 558641, 1675801808560)).toBe( 'https://www.camara.leg.br/evento-legislativo/67091/video-sob-demanda?idAudio=558641&trecho=1675801808560', ) }) }) describe('parseVodStatus', () => { it('normalizes the PRONTO payload', () => { expect( parseVodStatus({ estado: 'PRONTO', video: { titulo: 'Jorge Solla', subtitulo: 'DEPUTADO (PT-BA)', duracao: '0:04:07', horario: "17h30'08''", linkParaDownload: 'https://vod.camara.leg.br/vod/download?p=abc.mp4', linkParaReproducao: 'https://vod.camara.leg.br/videos/abc.mp4', }, }), ).toEqual({ state: 'PRONTO', video: { title: 'Jorge Solla', subtitle: 'DEPUTADO (PT-BA)', duration: '0:04:07', clock: "17h30'08''", downloadUrl: 'https://vod.camara.leg.br/vod/download?p=abc.mp4', playbackUrl: 'https://vod.camara.leg.br/videos/abc.mp4', }, }) }) it('handles GERANDO/INDISPONIVEL and malformed input', () => { expect(parseVodStatus({ estado: 'GERANDO', video: null })).toEqual({ state: 'GERANDO', video: null, }) expect(parseVodStatus({ estado: 'INDISPONIVEL', video: null })).toEqual({ state: 'INDISPONIVEL', video: null, }) expect(parseVodStatus(null)).toEqual({ state: 'DESCONHECIDO', video: null }) }) }) describe('selectSpeechEvents', () => { const events: Array<{ id: number; dataHoraInicio: string }> = [ { id: 1, dataHoraInicio: '2023-02-07T15:00' }, { id: 2, dataHoraInicio: '2023-02-07T20:00' }, { id: 3, dataHoraInicio: '2023-02-08T15:00' }, ] it('keeps only the speech date and sorts nearest-first', () => { const selected = selectSpeechEvents(events, '2023-02-07T17:28') expect(selected.map((e) => e.id)).toEqual([1, 2]) }) it('is empty when nothing matches the date', () => { expect(selectSpeechEvents(events, '2020-01-01T10:00')).toEqual([]) }) }) describe('matchExcerpt', () => { const excerpts = [ { audioId: 1, tMs: 100, speaker: 'JORGE SOLLA', party: 'DEPUTADO (PT-BA)', startTime: '09:28', duration: null, }, { audioId: 2, tMs: 200, speaker: 'JORGE SOLLA', party: 'DEPUTADO (PT-BA)', startTime: '17:30', duration: null, }, { audioId: 3, tMs: 300, speaker: 'OUTRO', party: null, startTime: '09:00', duration: null, }, ] it('picks the speaker excerpt nearest the speech time (accent-insensitive)', () => { expect(matchExcerpt(excerpts, '2016-03-10T09:28', 'Jorge Solla')?.audioId).toBe(1) expect(matchExcerpt(excerpts, '2023-02-07T17:28', 'Jorge Solla')?.audioId).toBe(2) }) it('returns null when the speaker is absent or empty', () => { expect(matchExcerpt(excerpts, '2016-03-10T09:28', 'Fulano de Tal')).toBeNull() expect(matchExcerpt(excerpts, '2016-03-10T09:28', '')).toBeNull() }) it('prefers an excerpt with a clock over one without', () => { const withMissing = [ { audioId: 9, tMs: 1, speaker: 'JORGE SOLLA', party: null, startTime: null, duration: null }, ...excerpts, ] expect(matchExcerpt(withMissing, '2016-03-10T09:28', 'Jorge Solla')?.audioId).toBe(1) }) }) describe('speechSourceKey', () => { it('joins datetime, type and phase into the stable identity', () => { expect( speechSourceKey({ dataHoraInicio: '2023-02-07T17:28', tipoDiscurso: 'BREVES COMUNICAÇÕES', faseEvento: { titulo: 'Breves Comunicações' }, }), ).toBe('2023-02-07T17:28|BREVES COMUNICAÇÕES|Breves Comunicações') }) it('degrades missing parts to empty strings', () => { expect(speechSourceKey({})).toBe('||') expect(speechSourceKey(null)).toBe('||') }) }) describe('speechContentHash', () => { it('is stable for the same content and differs otherwise', () => { expect(speechContentHash('Sumário', 'Transcrição')).toBe( speechContentHash('Sumário', 'Transcrição'), ) expect(speechContentHash('Sumário', 'Transcrição')).not.toBe( speechContentHash('Outro sumário', 'Transcrição'), ) expect(speechContentHash(null, null)).toHaveLength(12) }) }) describe('parseOfficialKeywords', () => { it('splits newline-separated groups and comma-separated keywords', () => { expect(parseOfficialKeywords('Saúde, SUS\r\nEducação\r\n\r\nEscola')).toEqual([ 'Saúde', 'SUS', 'Educação', 'Escola', ]) // Live Câmara shape: one group per line, keywords joined by commas. expect(parseOfficialKeywords('Governo federal,reconstrução,Política pública')).toEqual([ 'Governo federal', 'reconstrução', 'Política pública', ]) expect(parseOfficialKeywords(null)).toEqual([]) }) }) describe('legislatureForDate', () => { it('maps dates to the legislature ranges at the boundaries', () => { expect(legislatureForDate('2023-02-01')).toBe('57') expect(legislatureForDate('2023-01-31')).toBe('56') expect(legislatureForDate('2015-02-01')).toBe('55') expect(legislatureForDate('2015-01-31')).toBe('54') expect(legislatureForDate('2011-01-01')).toBe('54') }) it('returns null outside the supported range or for invalid input', () => { expect(legislatureForDate('2010-12-31')).toBeNull() expect(legislatureForDate('')).toBeNull() expect(legislatureForDate('2023-2-1')).toBeNull() }) }) describe('parseDurationToSeconds', () => { it('parses the excerpt card and VOD spellings', () => { expect(parseDurationToSeconds('0h04\'03"')).toBe(243) expect(parseDurationToSeconds('1h00\'00"')).toBe(3600) expect(parseDurationToSeconds('0:04:07')).toBe(247) expect(parseDurationToSeconds('4:07')).toBe(247) }) it('rejects empty, malformed and out-of-range values', () => { expect(parseDurationToSeconds('')).toBeNull() expect(parseDurationToSeconds(null)).toBeNull() expect(parseDurationToSeconds('abc')).toBeNull() expect(parseDurationToSeconds('1::30')).toBeNull() expect(parseDurationToSeconds('1:99:99')).toBeNull() expect(parseDurationToSeconds('0h99\'00"')).toBeNull() expect(parseDurationToSeconds('1:99')).toBeNull() }) }) describe('parsePresidingOfficerTransitions', () => { const transitionHtml = (heading: string, times: number[]) => `

${heading}

` it('reads the transition groups, using the newest clip of each as the change moment', () => { const html = [ transitionHtml( 'Troca da mesa Presidente Bohn Gass por Participante Pompeo de Mattos', [1675815220717, 1675814951403], ), transitionHtml( 'Troca da mesa Presidente Pompeo de Mattos por Participante Bohn Gass', [1675814710153], ), ].join('\n') expect(parsePresidingOfficerTransitions(html)).toEqual([ { from: 'Pompeo de Mattos', to: 'Bohn Gass', tMs: 1675814710153 }, { from: 'Bohn Gass', to: 'Pompeo de Mattos', tMs: 1675815220717 }, ]) }) it('returns [] when the page has no transitions or the markup changes', () => { const html = excerptHtml(67091, { audioId: 5, tMs: 1000, speaker: 'JORGE SOLLA', party: 'DEPUTADO (PT-BA)', startTime: '17:30', duration: '0h01\'00"', }) expect(parsePresidingOfficerTransitions(html)).toEqual([]) expect(parsePresidingOfficerTransitions('')).toEqual([]) }) }) describe('resolvePresidingOfficer', () => { // Real transition groups of event 67091 (2023-02-07), newest-clip times. const transitions = [ { from: 'Bohn Gass', to: 'Pompeo de Mattos', tMs: 1675815220717 }, { from: 'Gilberto Nascimento', to: 'Pompeo de Mattos', tMs: 1675800828283 }, { from: 'Pompeo de Mattos', to: 'Adriana Ventura', tMs: 1675804114707 }, { from: 'Adriana Ventura', to: 'Pompeo de Mattos', tMs: 1675804616513 }, { from: 'Pompeo de Mattos', to: 'Bohn Gass', tMs: 1675814710153 }, ] it('returns the incoming officer of the latest transition before the moment', () => { // Solla spoke at 17:28 BRT (20:28 UTC) — Gilberto→Pompeo at 17:13 BRT. expect(resolvePresidingOfficer(transitions, Date.parse('2023-02-07T20:28:00Z'))).toBe( 'Pompeo de Mattos', ) // After Bohn→Pompeo (21:13 BRT), Pompeo presided again. expect(resolvePresidingOfficer(transitions, Date.parse('2023-02-08T00:16:00Z'))).toBe( 'Pompeo de Mattos', ) }) it('returns the outgoing officer before the first transition', () => { expect(resolvePresidingOfficer(transitions, Date.parse('2023-02-07T19:00:00Z'))).toBe( 'Gilberto Nascimento', ) }) it('returns null without transitions or a usable moment', () => { expect(resolvePresidingOfficer([], 1675801680000)).toBeNull() expect(resolvePresidingOfficer(transitions, Number.NaN)).toBeNull() }) }) describe('normalizeTranscription', () => { it('accepts the OpenAI-compat segments shape', () => { expect( normalizeTranscription({ text: 'olá mundo', language: 'pt', duration: 12.5, segments: [ { start: 0, end: 2.7, text: ' olá' }, { start: 2.91, end: 4.1, text: ' mundo' }, ], }), ).toEqual({ text: 'olá mundo', language: 'pt', duration: 12.5, segments: [ { start: 0, end: 2.7, text: 'olá' }, { start: 2.91, end: 4.1, text: 'mundo' }, ], }) }) it('accepts the native chunks shape and drops invalid entries', () => { const result = normalizeTranscription({ chunks: [ { timestamp: [0, 1.5], text: 'a' }, { timestamp: [null, null], text: 'lixo' }, { timestamp: [2, 3], text: '' }, ], language: 'pt', }) expect(result.segments).toEqual([{ start: 0, end: 1.5, text: 'a' }]) expect(result.text).toBe('a') }) it('degrades on malformed input', () => { expect(normalizeTranscription(null)).toEqual({ text: '', language: null, duration: null, segments: [], }) }) it('keeps a missing duration as null instead of 0', () => { expect(normalizeTranscription({ duration: null, segments: [] }).duration).toBeNull() expect(normalizeTranscription({ duration: '', segments: [] }).duration).toBeNull() expect(normalizeTranscription({ duration: 12, segments: [] }).duration).toBe(12) }) it('prefers segments over chunks when both are present', () => { const result = normalizeTranscription({ segments: [{ start: 0, end: 1, text: 'seg' }], chunks: [{ timestamp: [2, 3], text: 'chunk' }], }) expect(result.segments).toEqual([{ start: 0, end: 1, text: 'seg' }]) }) }) describe('aggregateBackfillRuns', () => { it('sums the numeric blocks of every legislature and keeps the first LLM sample error', () => { const combined = aggregateBackfillRuns([ { totals: { listed: 10, processed: 10, created: 8, updated: 2, withExcerpt: 9, withoutExcerpt: 1, withSegments: 8, failed: 1, }, asr: { calls: 8, audioSeconds: 480, elapsedMs: 9000, failures: 0 }, llm: { calls: 10, used: 10, failed: 0, totalTokens: 1000, estimatedCostUsd: 0.01, sampleError: null, }, elapsedMs: 12_000, }, { totals: { listed: 5, processed: 5, created: 0, updated: 5, withExcerpt: 5, withoutExcerpt: 0, withSegments: 5, failed: 0, }, asr: { calls: 0, audioSeconds: 0, elapsedMs: 0, failures: 0 }, llm: { calls: 5, used: 4, failed: 1, totalTokens: 400, estimatedCostUsd: 0.004, sampleError: 'timeout', }, elapsedMs: 3_000, }, ]) expect(combined.totals).toEqual({ listed: 15, processed: 15, created: 8, updated: 7, withExcerpt: 14, withoutExcerpt: 1, withSegments: 13, failed: 1, }) expect(combined.asr).toEqual({ calls: 8, audioSeconds: 480, elapsedMs: 9000, failures: 0 }) expect(combined.llm.calls).toBe(15) expect(combined.llm.used).toBe(14) expect(combined.llm.failed).toBe(1) expect(combined.llm.totalTokens).toBe(1400) expect(combined.llm.estimatedCostUsd).toBeCloseTo(0.014, 6) expect(combined.llm.sampleError).toBe('timeout') expect(combined.elapsedMs).toBe(15_000) }) it('returns zeroed blocks for an empty/absent run list', () => { expect(aggregateBackfillRuns([]).totals.processed).toBe(0) expect(aggregateBackfillRuns(undefined).asr.audioSeconds).toBe(0) expect(aggregateBackfillRuns(undefined).llm.sampleError).toBeNull() expect(aggregateBackfillRuns(undefined).elapsedMs).toBe(0) }) }) describe('selectLinkSample', () => { const rows = [ { id: 1, legislature: '57', speechAt: '2023-03-01T10:00', vodPlaybackUrl: 'https://vod/1', vodDownloadUrl: 'https://vod/1.mp4', }, { id: 2, legislature: '57', speechAt: '2023-02-01T10:00', vodPlaybackUrl: null, vodDownloadUrl: null, }, { id: 3, legislature: '57', speechAt: '2023-04-01T10:00', vodPlaybackUrl: 'https://vod/3', vodDownloadUrl: null, }, { id: 4, legislature: '56', speechAt: '2021-02-01T10:00', vodPlaybackUrl: 'https://vod/4', vodDownloadUrl: 'https://vod/4.mp4', }, ] it('picks up to n linked speeches per legislature, skipping link-less rows', () => { expect( selectLinkSample(rows, 1) .map((row) => row.id) .sort(), ).toEqual([1, 4]) expect( selectLinkSample(rows, 5) .map((row) => row.id) .sort(), ).toEqual([1, 3, 4]) }) it('spreads the picks over a legislature larger than n', () => { const many = Array.from({ length: 6 }, (_, index) => ({ id: index + 1, legislature: '55', speechAt: `2016-0${index + 1}-01T10:00`, vodPlaybackUrl: `https://vod/${index + 1}`, vodDownloadUrl: null, })) expect( selectLinkSample(many, 2) .map((row) => row.id) .sort(), ).toEqual([1, 4]) expect( selectLinkSample(many, 3) .map((row) => row.id) .sort(), ).toEqual([1, 3, 5]) }) it('is deterministic for the same rows', () => { expect(selectLinkSample(rows, 2)).toEqual(selectLinkSample(rows, 2)) }) it('returns an empty sample when nothing carries a link', () => { expect( selectLinkSample( [{ id: 9, legislature: '55', speechAt: null, vodPlaybackUrl: null, vodDownloadUrl: null }], 3, ), ).toEqual([]) }) }) describe('dateRangeChunks', () => { it('splits a multi-year range into non-overlapping calendar years', () => { expect(dateRangeChunks('2015-02-01', '2019-01-31')).toEqual([ ['2015-02-01', '2015-12-31'], ['2016-01-01', '2016-12-31'], ['2017-01-01', '2017-12-31'], ['2018-01-01', '2018-12-31'], ['2019-01-01', '2019-01-31'], ]) }) it('handles a single day and an exact year without spilling over', () => { expect(dateRangeChunks('2023-02-07', '2023-02-07')).toEqual([['2023-02-07', '2023-02-07']]) expect(dateRangeChunks('2023-01-01', '2023-12-31')).toEqual([['2023-01-01', '2023-12-31']]) }) it('returns no chunks for malformed dates', () => { expect(dateRangeChunks('2023-1-1', '2023-12-31')).toEqual([]) expect(dateRangeChunks('', '2023-12-31')).toEqual([]) }) it('splits by month when asked, with the right month length', () => { expect(dateRangeChunks('2018-01-01', '2018-03-15', 'month')).toEqual([ ['2018-01-01', '2018-01-31'], ['2018-02-01', '2018-02-28'], ['2018-03-01', '2018-03-15'], ]) expect(dateRangeChunks('2024-02-01', '2024-02-29', 'month')).toEqual([ ['2024-02-01', '2024-02-29'], ]) }) }) // Real URLs measured on 2026-09-14 (see docs/plans/acervo-abrir-fonte-pdf-oficial.md). const legacyGovUrl = 'https://imagem.camara.gov.br/dc_20b.asp?largura=&altura=&tipoForm=diarios' + '&selCodColecaoCsv=D&Datain=8%2F2%2F2023&txPagina=73&txSuplemento=&enviar=Pesquisar' const legacyGovUrl75 = legacyGovUrl.replace('txPagina=73', 'txPagina=75') const montaPdfUrl = 'https://imagem.camara.leg.br/montaPdf.asp?narquivo=DCD0020230208000210000.PDF&npagina=73' const directPdfUrl = 'https://imagem.camara.leg.br/Imagem/d/pdf/DCD0020230208000210000.PDF' describe('parseDiarioDate', () => { it('parses the Datain spelling into ISO', () => { expect(parseDiarioDate('25/6/2020')).toBe('2020-06-25') expect(parseDiarioDate('8/2/2023')).toBe('2023-02-08') expect(parseDiarioDate('28/09/2011')).toBe('2011-09-28') }) it('rejects what is not a real date', () => { expect(parseDiarioDate('2023-02-08')).toBeNull() expect(parseDiarioDate('32/1/2023')).toBeNull() expect(parseDiarioDate('31/2/2023')).toBeNull() expect(parseDiarioDate('1/13/2023')).toBeNull() expect(parseDiarioDate('')).toBeNull() }) }) describe('isLegacyDiarioUrl', () => { it('recognizes the legacy endpoints even with malformed params', () => { expect(isLegacyDiarioUrl(legacyGovUrl)).toBe(true) expect(isLegacyDiarioUrl(montaPdfUrl)).toBe(true) expect(isLegacyDiarioUrl('https://imagem.camara.leg.br/dc_20b.asp?Datain=xx')).toBe(true) }) it('rejects direct PDFs and foreign URLs', () => { expect(isLegacyDiarioUrl(directPdfUrl)).toBe(false) expect(isLegacyDiarioUrl('https://example.com/dc_20b.asp?Datain=8/2/2023')).toBe(false) expect(isLegacyDiarioUrl(null)).toBe(false) }) }) describe('parseLegacyOfficialUrl', () => { it('extracts publication, page and a .leg.br lookup URL from the legacy link', () => { expect(parseLegacyOfficialUrl(legacyGovUrl)).toEqual({ lookupUrl: 'https://imagem.camara.leg.br/dc_20b.asp?largura=&altura=&tipoForm=diarios' + '&selCodColecaoCsv=D&Datain=8%2F2%2F2023&txPagina=73&txSuplemento=&enviar=Pesquisar', publication: { date: '2023-02-08', collection: 'D', supplement: null }, page: 73, }) }) it('keeps a .leg.br host and reports a missing page', () => { const parsed = parseLegacyOfficialUrl( 'https://imagem.camara.leg.br/dc_20.asp?Datain=1/3/2023&txPagina=', ) expect(parsed?.lookupUrl).toContain('imagem.camara.leg.br') expect(parsed?.page).toBeNull() }) it('normalizes the stale J and empty collection codes to D', () => { const staleJ = 'https://imagem.camara.gov.br/dc_20b.asp?largura=&altura=&tipoForm=diarios' + '&selCodColecaoCsv=J&Datain=10%2F10%2F2019&txPagina=147&txSuplemento=&enviar=Pesquisar' const parsedJ = parseLegacyOfficialUrl(staleJ) expect(parsedJ?.publication).toEqual({ date: '2019-10-10', collection: 'D', supplement: null }) expect(parsedJ?.lookupUrl).toContain('selCodColecaoCsv=D') expect(parsedJ?.lookupUrl).not.toContain('selCodColecaoCsv=J') const parsedEmpty = parseLegacyOfficialUrl( staleJ.replace('selCodColecaoCsv=J', 'selCodColecaoCsv='), ) expect(parsedEmpty?.publication.collection).toBe('D') expect(parsedEmpty?.lookupUrl).toContain('selCodColecaoCsv=D') }) it('keeps a collection that is not a known stale alias', () => { const parsed = parseLegacyOfficialUrl( legacyGovUrl.replace('selCodColecaoCsv=D', 'selCodColecaoCsv=S'), ) expect(parsed?.publication.collection).toBe('S') expect(parsed?.lookupUrl).toContain('selCodColecaoCsv=S') }) it('returns null for non-legacy or dateless URLs', () => { expect(parseLegacyOfficialUrl(directPdfUrl)).toBeNull() expect(parseLegacyOfficialUrl('https://imagem.camara.leg.br/dc_20b.asp?Datain=xx')).toBeNull() expect(parseLegacyOfficialUrl(null)).toBeNull() }) }) describe('parseMontaPdfUrl', () => { it('parses the relative redirect target and the absolute one', () => { expect(parseMontaPdfUrl('montaPdf.asp?narquivo=DCD0020230208000210000.PDF&npagina=73')).toEqual( { archiveFileName: 'DCD0020230208000210000.PDF', page: 73, }, ) expect(parseMontaPdfUrl(montaPdfUrl)).toEqual({ archiveFileName: 'DCD0020230208000210000.PDF', page: 73, }) expect(parseMontaPdfUrl('montaPdf.asp?narquivo=DCD0020230208000210000.PDF')?.page).toBeNull() }) it('rejects an unsafe archive name and non-montaPdf URLs', () => { expect(parseMontaPdfUrl('montaPdf.asp?narquivo=../../etc/passwd&npagina=1')).toBeNull() expect(parseMontaPdfUrl(directPdfUrl)).toBeNull() }) }) describe('buildOfficialPdfUrl', () => { it('builds the direct PDF URL with the page fragment when known', () => { expect(buildOfficialPdfUrl('DCD0020230208000210000.PDF', 73)).toBe( 'https://imagem.camara.leg.br/Imagem/d/pdf/DCD0020230208000210000.PDF#page=73', ) expect(buildOfficialPdfUrl('DCD28SET2011.pdf')).toBe( 'https://imagem.camara.leg.br/Imagem/d/pdf/DCD28SET2011.pdf', ) }) it('omits an invalid page and refuses an empty archive name', () => { expect(buildOfficialPdfUrl('DCD0020230208000210000.PDF', 0)).toBe(directPdfUrl) expect(buildOfficialPdfUrl('', 10)).toBeNull() }) }) describe('parseDirectOfficialPdfUrl', () => { it('parses the archive name and the page fragment', () => { expect(parseDirectOfficialPdfUrl(`${directPdfUrl}#page=73`)).toEqual({ archiveFileName: 'DCD0020230208000210000.PDF', page: 73, }) expect(parseDirectOfficialPdfUrl(directPdfUrl)).toEqual({ archiveFileName: 'DCD0020230208000210000.PDF', page: null, }) expect( parseDirectOfficialPdfUrl('https://imagem.camara.leg.br/Imagem/d/pdf/DCD28SET2011.pdf'), ).toEqual({ archiveFileName: 'DCD28SET2011.pdf', page: null }) }) it('returns null outside the Câmara PDF path', () => { expect(parseDirectOfficialPdfUrl(legacyGovUrl)).toBeNull() expect(parseDirectOfficialPdfUrl('https://example.com/Imagem/d/pdf/x.PDF')).toBeNull() }) }) describe('classifyOfficialTextUrl', () => { it('classifies none, direct, legacy and montaPdf', () => { expect(classifyOfficialTextUrl(null)).toBe('none') expect(classifyOfficialTextUrl(' ')).toBe('none') expect(classifyOfficialTextUrl(directPdfUrl)).toBe('direct') expect(classifyOfficialTextUrl(`${directPdfUrl}#page=129`)).toBe('direct') expect(classifyOfficialTextUrl(legacyGovUrl)).toBe('legacy') expect(classifyOfficialTextUrl(montaPdfUrl)).toBe('montaPdf') }) it('classifies everything else as unknown', () => { expect(classifyOfficialTextUrl('https://example.com/discurso')).toBe('unknown') expect(classifyOfficialTextUrl('https://imagem.camara.leg.br/outro.asp?x=1')).toBe('unknown') expect(classifyOfficialTextUrl('https://imagem.camara.leg.br/dc_20b.asp?Datain=xx')).toBe( 'unknown', ) expect(classifyOfficialTextUrl('lixo')).toBe('unknown') }) }) describe('officialTextUrlFallback', () => { it('preserves a stored direct PDF and nulls everything else', () => { expect(officialTextUrlFallback(`${directPdfUrl}#page=73`)).toBe(`${directPdfUrl}#page=73`) expect(officialTextUrlFallback(legacyGovUrl)).toBeNull() expect(officialTextUrlFallback(montaPdfUrl)).toBeNull() expect(officialTextUrlFallback(null)).toBeNull() }) }) describe('publicationCacheKey', () => { it('keys by date, collection and supplement', () => { expect(publicationCacheKey({ date: '2023-02-08', collection: 'D', supplement: null })).toBe( '2023-02-08-D', ) expect(publicationCacheKey({ date: '2020-06-25', collection: 'D', supplement: '1' })).toBe( '2020-06-25-D-s1', ) expect(publicationCacheKey({ date: '2023-02-08', collection: null, supplement: '' })).toBe( '2023-02-08', ) }) it('returns null without a valid date', () => { expect(publicationCacheKey({ date: '08/02/2023', collection: 'D' })).toBeNull() expect(publicationCacheKey(null)).toBeNull() }) }) describe('planOfficialLinkRepairs', () => { it('groups legacy rows by publication and separates the other classes', () => { const malformedLegacyUrl = 'https://imagem.camara.leg.br/dc_20b.asp?Datain=xx' const plan = planOfficialLinkRepairs([ { id: 1, officialTextUrl: legacyGovUrl, speechAt: '2023-02-08T10:00', legislature: '57', }, { id: 2, officialTextUrl: legacyGovUrl75, speechAt: '2023-02-08T11:00', legislature: '57', }, { id: 3, officialTextUrl: directPdfUrl, speechAt: null, legislature: null }, { id: 4, officialTextUrl: null, speechAt: null, legislature: null }, { id: 5, officialTextUrl: montaPdfUrl, speechAt: null, legislature: null }, { id: 6, officialTextUrl: 'https://example.com/discurso', speechAt: null, legislature: null }, { id: 7, officialTextUrl: malformedLegacyUrl }, ]) expect(plan.groups).toHaveLength(1) expect(plan.groups[0].key).toBe('2023-02-08-D') expect(plan.groups[0].publication).toEqual({ date: '2023-02-08', collection: 'D', supplement: null, }) expect(plan.groups[0].rows.map((row: { id: number }) => row.id)).toEqual([1, 2]) expect(plan.groups[0].rows.map((row: { page: number | null }) => row.page)).toEqual([73, 75]) expect(plan.directUpdates).toEqual([ { id: 5, previousUrl: montaPdfUrl, nextUrl: `${directPdfUrl}#page=73`, speechAt: null, legislature: null, }, ]) expect(plan.alreadyDirect).toBe(1) expect(plan.none).toBe(1) expect(plan.unknown.map((row: { id: number }) => row.id)).toEqual([6]) expect(plan.unresolvable).toEqual([ { id: 7, previousUrl: malformedLegacyUrl, speechAt: null, legislature: null, }, ]) }) it('tolerates an empty scan', () => { expect(planOfficialLinkRepairs(null)).toEqual({ groups: [], directUpdates: [], alreadyDirect: 0, unknown: [], unresolvable: [], none: 0, }) }) })