Files
gart/code/MacApp/Sources/PhraseReviewModel.swift
T
João HenriqueandClaude Sonnet 5 7b5aed79ee feat(voz): legenda por ênfase, forced align, IA local e correções de zoom/revisão
Trabalho da branch feat/revisao-enfases: pipeline de edição por voz ganha
alinhamento forçado (whisperx), roteirização por LLM local (Ollama), e a
etapa 5 (revisão de frases) passa a refletir de verdade o que é aplicado.

- generate_subtitles_by_emphasis: legenda comum cobre o clipe inteiro,
  legenda dinâmica só nas frases de ênfase, e a comum é desativada
  (enabled="0") onde a dinâmica cobre, em vez de nunca ser gerada ali.
- validate_subtitle_layout ignora títulos com enabled="0" — corrige falso
  positivo de colisão contra o que está desativado no lugar dele.
- Corrige zoom/marcador sendo descartado quando a borda encosta exatamente
  no início de um corte.
- Etapa 5 do Assistente: recarrega quando as decisões da IA mudam (com
  fresh=true, ignorando a revisão salva antiga) — resolve a dessincronia
  entre "ativa" na tela e o que já foi cortado no FCPXML.
- Etapa "Processar" reaplica as decisões da revisão (_phrase_actions.json)
  antes da cadeia de remoção de silêncio/legendas — antes, desativar uma
  frase na etapa 5 não tinha efeito nenhum no vídeo final.
- Etapa "Concluído" fundida em "Processar" — abrir no Final Cut/Finder
  aparece assim que termina, sem slide extra.
- Palavra clicável na etapa 5 agora funciona como toggle (clique de novo
  desfaz) e mostra a própria ênfase (sublinhado colorido + peso da fonte).
- fcpxml/forced_align.py, fcpxml/llm_local.py, ai_edit.py: alinhamento
  fonético via whisperx e roteirização local via Ollama/Gemma.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-21 18:26:04 -04:00

443 lines
17 KiB
Swift

import AVFoundation
import Combine
import Foundation
/// State behind the wizard's emphasis-review step.
///
/// Holds the phrases, the selection, and the player — together, because they
/// are one thing to the user: clicking a phrase moves the playhead, playing
/// moves the selection, and skipping a removed line only works if whoever owns
/// playback also knows which lines are removed.
///
/// The preview deliberately plays the *original* media and jumps over whatever
/// the edit removes, instead of rendering a cut first. Rendering to check a
/// toggle would put minutes between a decision and its result; jumping gives
/// the same reading instantly, and the real cut is generated later from the
/// exact same phrase list.
@MainActor
final class PhraseReviewModel: ObservableObject {
@Published var phrases: [ReviewPhrase] = []
@Published var selection: Int?
@Published var isLoading = false
@Published var errorMessage: String?
@Published var currentTime: Double = 0
@Published var isPlaying = false
@Published var pixelsPerSecond: Double = 40
@Published var skipRemoved = true
@Published var zooms: [ManualZoom] = []
/// In/out the editor dragged on the timeline, in source seconds.
@Published var rangeStart: Double?
@Published var rangeEnd: Double?
private(set) var source = ""
private(set) var sourcePath = ""
private(set) var duration: Double = 0
private(set) var speakers: [String] = []
private(set) var emotionAvailable = false
private(set) var player: AVPlayer?
private var voiceTimelinePath = ""
private var timeObserver: Any?
private var playbackLimit: Double?
let minPixelsPerSecond: Double = 8
let maxPixelsPerSecond: Double = 400
deinit {
if let timeObserver, let player {
player.removeTimeObserver(timeObserver)
}
}
// MARK: - Carregar
/// Builds the review from the voice timeline plus whatever the AI decided.
/// A review saved on a previous visit wins — see `cmd_build_phrase_review` —
/// UNLESS `fresh` is true, in which case that saved review is ignored and
/// `active`/`emphasis`/etc. come straight from this call's `decisionsJSON`.
/// Pass `fresh: true` when the decisions themselves changed since the
/// review was last built (the caller re-pasted/regenerated the AI's JSON
/// and re-ran `apply_voice_actions`) — otherwise the saved review from the
/// PREVIOUS decisions silently wins over the fresh cut it should reflect,
/// which is exactly the desync the wizard's "active" toggle showed against
/// the just-reapplied FCPXML.
func load(voiceTimelinePath: String, decisionsJSON: String,
outputFolder: String? = nil, mediaFolder: String? = nil, fresh: Bool = false) {
self.voiceTimelinePath = voiceTimelinePath
isLoading = true
errorMessage = nil
var arguments: [String: Any] = ["voice_timeline": voiceTimelinePath]
if let outputFolder { arguments["output_dir"] = outputFolder }
if let mediaFolder { arguments["media_dir"] = mediaFolder }
if fresh { arguments["fresh"] = true }
if let data = decisionsJSON.data(using: .utf8),
let parsed = try? JSONSerialization.jsonObject(with: data) {
arguments["actions"] = parsed
}
PythonBridge.call(command: "build_phrase_review", arguments: arguments) { [weak self] result, error in
Task { @MainActor in
guard let self else { return }
self.isLoading = false
if let error {
self.errorMessage = error
return
}
guard let result, result["ok"] as? Bool == true else {
self.errorMessage = result?["error"] as? String ?? "Não foi possível montar a revisão."
return
}
self.apply(result)
}
}
}
private func apply(_ result: [String: Any]) {
source = result["source"] as? String ?? ""
// The timeline JSON stores only the media's file name; the bridge
// resolves it to something openable (see phrase_review.resolve_source).
sourcePath = result["source_path"] as? String ?? ""
duration = result["duration"] as? Double ?? 0
speakers = result["speakers"] as? [String] ?? []
emotionAvailable = result["emotion_available"] as? Bool ?? false
phrases = (result["phrases"] as? [[String: Any]] ?? []).map { ReviewPhrase(json: $0) }
zooms = (result["zooms"] as? [[String: Any]] ?? []).compactMap { ManualZoom(json: $0) }
selection = phrases.first?.id
if let errors = result["errors"] as? [String], !errors.isEmpty {
errorMessage = "A IA mandou \(errors.count) decisão(ões) que não deu para ler — o resto foi aplicado."
}
preparePlayer()
}
/// Point the preview at a media file the user chose by hand — the way out
/// when the footage moved somewhere the automatic lookup can't reach.
func useMedia(at path: String) {
sourcePath = path
preparePlayer()
}
private func preparePlayer() {
guard !sourcePath.isEmpty, FileManager.default.fileExists(atPath: sourcePath) else {
player = nil
return
}
if let timeObserver, let player {
player.removeTimeObserver(timeObserver)
self.timeObserver = nil
}
let asset = AVURLAsset(url: URL(fileURLWithPath: sourcePath))
let player = AVPlayer(playerItem: AVPlayerItem(asset: asset))
self.player = player
// 60 Hz: the same observer drives the playhead *and* decides when to
// jump a removed stretch, so its period is the worst-case amount of cut
// material that can be heard before the skip lands. At 20 Hz that was an
// audible blip on every join.
let interval = CMTime(seconds: 1.0 / 60.0, preferredTimescale: 600)
timeObserver = player.addPeriodicTimeObserver(forInterval: interval, queue: .main) { [weak self] time in
Task { @MainActor in
self?.tick(time.seconds)
}
}
}
// MARK: - Reprodução
private func tick(_ time: Double) {
currentTime = time
guard isPlaying else { return }
// Playing a single phrase or a marked range stops at its out point
// instead of running on into the rest of the take.
if let limit = playbackLimit, time >= limit {
pause()
seek(to: limit)
return
}
if skipRemoved, let jump = nextKeptTime(after: time), jump > time {
seek(to: jump)
}
if let phrase = phrase(at: time), selection != phrase.id {
selection = phrase.id
}
}
/// Where playback should resume when `time` lands on removed material.
/// Returns nil when the time is on material that survives.
func nextKeptTime(after time: Double) -> Double? {
for phrase in phrases where time >= phrase.start - 0.001 && time < phrase.end {
if !phrase.active { return phrase.end }
if time < phrase.trimStart { return phrase.trimStart }
if time >= phrase.trimEnd { return phrase.end }
return nil
}
return nil
}
func togglePlay() {
if isPlaying {
pause()
} else {
playbackLimit = nil
play()
}
}
private func play() {
guard let player else { return }
if skipRemoved, let jump = nextKeptTime(after: currentTime) { seek(to: jump) }
player.play()
isPlaying = true
}
func pause() {
player?.pause()
isPlaying = false
playbackLimit = nil
}
/// Play exactly one span and stop — how a cut is judged: in context, at
/// speed, without hunting for the out point by hand.
func playRange(from start: Double, to end: Double) {
guard end > start else { return }
seek(to: start)
playbackLimit = end
player?.play()
isPlaying = true
}
func playSelectedPhrase() {
guard let selection, let phrase = phrases.first(where: { $0.id == selection })
else { return }
playRange(from: phrase.active ? phrase.trimStart : phrase.start,
to: phrase.active ? phrase.trimEnd : phrase.end)
}
func seek(to time: Double) {
currentTime = max(0, time)
player?.seek(to: CMTime(seconds: max(0, time), preferredTimescale: 600),
toleranceBefore: .zero, toleranceAfter: .zero)
}
/// Move the playhead to a phrase and select it.
func goTo(phraseID: Int) {
guard let phrase = phrases.first(where: { $0.id == phraseID }) else { return }
selection = phraseID
seek(to: phrase.active ? phrase.trimStart : phrase.start)
}
func phrase(at time: Double) -> ReviewPhrase? {
phrases.first { time >= $0.start && time < $0.end }
}
func selectNeighbour(_ delta: Int) {
guard let selection, let index = phrases.firstIndex(where: { $0.id == selection }) else {
if let first = phrases.first { goTo(phraseID: first.id) }
return
}
let next = min(max(0, index + delta), phrases.count - 1)
goTo(phraseID: phrases[next].id)
}
// MARK: - Edições
private func update(_ id: Int, _ change: (inout ReviewPhrase) -> Void) {
guard let index = phrases.firstIndex(where: { $0.id == id }) else { return }
change(&phrases[index])
}
func setEmphasis(_ level: Int, for id: Int) {
update(id) { $0.emphasis = min(3, max(0, level)) }
}
func toggleActive(_ id: Int) {
update(id) { $0.active.toggle() }
}
func setTrack(_ track: String, for id: Int) {
update(id) { $0.track = track }
}
func setText(_ text: String, for id: Int) {
update(id) { $0.text = text }
}
/// Trim a phrase's head or tail, landing on a word boundary.
/// A trim that would swallow the whole line is refused — deactivating the
/// phrase is the way to remove it, and doing it by accident with a drag
/// would lose the emphasis decision along with the line.
func trim(_ id: Int, edge: TrimEdge, to time: Double) {
update(id) { phrase in
let snapped = phrase.snap(time, edge: edge)
switch edge {
case .start:
let value = min(max(phrase.start, snapped), phrase.trimEnd - 0.1)
if value < phrase.trimEnd { phrase.trimStart = value }
case .end:
let value = max(min(phrase.end, snapped), phrase.trimStart + 0.1)
if value > phrase.trimStart { phrase.trimEnd = value }
}
}
}
func resetTrim(_ id: Int) {
update(id) { $0.trimStart = $0.start; $0.trimEnd = $0.end }
}
/// Trim everything before/after a given word — the text-first way to cut,
/// since the editor reads the line and points at where it should begin.
/// Clicking the word that is ALREADY that edge toggles it back off —
/// the trim on that side resets to the phrase's own start/end — so the
/// same click that sets a boundary also clears it, instead of needing
/// the separate "Inteira" button for a one-sided undo.
func trimToWord(_ word: ReviewWord, edge: TrimEdge, in id: Int) {
guard let phrase = phrases.first(where: { $0.id == id }) else { return }
let epsilon = 0.001
switch edge {
case .start where abs(word.start - phrase.trimStart) < epsilon:
update(id) { $0.trimStart = $0.start }
case .end where abs(word.end - phrase.trimEnd) < epsilon:
update(id) { $0.trimEnd = $0.end }
default:
trim(id, edge: edge, to: edge == .start ? word.start : word.end)
}
}
// MARK: - Trecho marcado e zooms
var hasRange: Bool {
guard let rangeStart, let rangeEnd else { return false }
return rangeEnd - rangeStart >= ManualZoom.minimumDuration
}
var rangeSpan: (start: Double, end: Double)? {
guard let rangeStart, let rangeEnd, rangeEnd > rangeStart else { return nil }
return (rangeStart, rangeEnd)
}
func setRange(from start: Double, to end: Double) {
rangeStart = min(start, end)
rangeEnd = max(start, end)
}
func clearRange() {
rangeStart = nil
rangeEnd = nil
}
/// Add a punch-in over the marked range. Scale and ramp are not stored:
/// they come from the "Análise de Voz" settings when the edit is rendered,
/// so changing the look there restyles every zoom at once.
func addZoomForRange() {
guard let span = rangeSpan, span.end - span.start >= ManualZoom.minimumDuration
else { return }
zooms.append(ManualZoom(start: span.start, end: span.end))
zooms.sort { $0.start < $1.start }
clearRange()
}
func addZoomForPhrase(_ id: Int) {
guard let phrase = phrases.first(where: { $0.id == id }) else { return }
zooms.append(ManualZoom(start: phrase.trimStart, end: phrase.trimEnd))
zooms.sort { $0.start < $1.start }
}
func removeZoom(_ id: UUID) {
zooms.removeAll { $0.id == id }
}
func zoom(at time: Double) -> ManualZoom? {
zooms.first { time >= $0.start && time <= $0.end }
}
func setEmphasisForAll(_ level: Int) {
for index in phrases.indices where phrases[index].active {
phrases[index].emphasis = level
}
}
// MARK: - Resumo e gravação
var emphasisCount: Int { phrases.filter { $0.active && $0.emphasis >= 1 }.count }
var removedCount: Int { phrases.filter { !$0.active }.count }
var keptDuration: Double {
phrases.filter { $0.active }.reduce(0) { $0 + ($1.trimEnd - $1.trimStart) }
}
// MARK: - Tempo compactado (sem os vãos do que foi cortado)
/// Kept spans of source media, in order, each carrying the position it
/// lands at once every removed stretch between phrases is squeezed out.
/// The timeline draws and scrubs in this space so it reads like the cut
/// itself instead of the raw take with holes in it.
private var keptSegments: [(rawStart: Double, rawEnd: Double, compactStart: Double)] {
var offset = 0.0
var segments: [(Double, Double, Double)] = []
for phrase in phrases.sorted(by: { $0.start < $1.start }) where phrase.active {
guard phrase.trimEnd > phrase.trimStart else { continue }
segments.append((phrase.trimStart, phrase.trimEnd, offset))
offset += phrase.trimEnd - phrase.trimStart
}
return segments
}
/// Maps a raw source-media time to its position on the compacted timeline.
/// Time inside removed material collapses to the boundary of the nearest
/// kept segment, so cut stretches take up no space at all.
func compactTime(_ raw: Double) -> Double {
let segments = keptSegments
for segment in segments {
if raw < segment.rawStart { return segment.compactStart }
if raw <= segment.rawEnd { return segment.compactStart + (raw - segment.rawStart) }
}
guard let last = segments.last else { return 0 }
return raw >= last.rawEnd ? last.compactStart + (last.rawEnd - last.rawStart) : 0
}
/// The inverse of `compactTime`: where a click on the compacted timeline
/// lands in the raw source media, for seeking and scrubbing.
func rawTime(fromCompact compact: Double) -> Double {
let segments = keptSegments
for segment in segments {
let compactEnd = segment.compactStart + (segment.rawEnd - segment.rawStart)
if compact <= compactEnd {
return segment.rawStart + max(0, compact - segment.compactStart)
}
}
return segments.last?.rawEnd ?? 0
}
/// Persists the edited review plus the actions derived from it. Called when
/// the wizard advances — the render itself happens in the next step.
/// Persists the edited review and hands back BOTH paths it wrote:
/// `review_path` (the human-readable `_phrase_review.json`) and
/// `actions_path` (`_phrase_actions.json`, the cut/zoom list derived from
/// it — what `finalizeProcessing` needs to actually apply the review's
/// active/inactive decisions instead of just filing them away).
func save(completion: @escaping (_ reviewPath: String?, _ actionsPath: String?) -> Void) {
guard !voiceTimelinePath.isEmpty, !phrases.isEmpty else {
completion(nil, nil)
return
}
let arguments: [String: Any] = [
"voice_timeline": voiceTimelinePath,
"source": source,
"duration": duration,
"speakers": speakers,
"phrases": phrases.map { $0.asJSON },
"zooms": zooms.map { $0.asJSON },
]
PythonBridge.call(command: "save_phrase_review", arguments: arguments) { result, error in
Task { @MainActor in
if let error {
completion(nil, nil)
_ = error
return
}
completion(result?["review_path"] as? String, result?["actions_path"] as? String)
}
}
}
}