gart/code/MacApp/Sources/Models.swift

import Foundation

/// A curated transcription model (mirrors `fcpxml/models.json`).
struct ModelInfo: Identifiable {
    let displayName: String
    let internalName: String
    let language: String
    let storage: String
    let accuracy: Int
    let speed: Int
    var isDownloaded: Bool
    var isSelected: Bool
    var isRecommended: Bool

    var id: String { internalName }
}

/// Full catalog snapshot returned by the `catalog` command.
struct Catalog {
    var models: [ModelInfo]
    var selected: String
    var language: String
    var modelsDir: String
    var installedCount: Int
    var diarization: Bool
    var diarizationMessage: String
    var hfTokenSet: Bool
    var numSpeakers: String

    init(json: [String: Any]) {
        let recommended = Set((json["recommended"] as? [String] ?? []))
        let installed = Set((json["installed"] as? [String] ?? []))
        let selected = json["selected"] as? String ?? ""
        let rawModels = json["models"] as? [[String: Any]] ?? []
        var parsed: [ModelInfo] = []
        for m in rawModels {
            let name = m["internal_name"] as? String ?? ""
            parsed.append(ModelInfo(
                displayName: m["display_name"] as? String ?? name,
                internalName: name,
                language: m["language"] as? String ?? "",
                storage: m["storage"] as? String ?? "",
                accuracy: m["accuracy"] as? Int ?? 0,
                speed: m["speed"] as? Int ?? 0,
                isDownloaded: installed.contains(name),
                isSelected: name == selected,
                isRecommended: recommended.contains(name)
            ))
        }
        self.models = parsed
        self.selected = selected
        self.language = json["language"] as? String ?? "auto"
        self.modelsDir = json["models_dir"] as? String ?? ""
        self.installedCount = json["installed_count"] as? Int ?? 0
        self.diarization = json["diarization"] as? Bool ?? false
        self.diarizationMessage = json["diarization_message"] as? String ?? ""
        self.hfTokenSet = json["hf_token_set"] as? Bool ?? false
        self.numSpeakers = json["num_speakers"] as? String ?? ""
    }

    /// Models sorted: recommended first, then by download state, then name.
    var orderedModels: [ModelInfo] {
        models.sorted {
            if $0.isDownloaded != $1.isDownloaded { return $0.isDownloaded }
            if $0.isRecommended != $1.isRecommended { return $0.isRecommended }
            return $0.displayName < $1.displayName
        }
    }
}

/// A single transcript result from the `transcribe` command.
struct TranscriptResult {
    let media: String
    let language: String
    let words: Int
    let duration: Double
    let preview: String
    let saved: String
    let speakers: [String]

    init(json: [String: Any]) {
        media = json["media"] as? String ?? ""
        language = json["language"] as? String ?? "?"
        words = json["words"] as? Int ?? 0
        duration = json["duration"] as? Double ?? 0
        preview = json["preview"] as? String ?? ""
        saved = json["saved"] as? String ?? ""
        speakers = json["speakers"] as? [String] ?? []
    }
}

struct ZoomClip: Identifiable {
    let id: String
    let index: Int
    let name: String
    let start: Double
    let duration: Double
    let media: String
    let preview: String
    let hasTranscript: Bool

    init(json: [String: Any]) {
        id = json["id"] as? String ?? ""
        index = json["index"] as? Int ?? 0
        name = json["name"] as? String ?? "Clipe"
        start = json["start"] as? Double ?? 0
        duration = json["duration"] as? Double ?? 0
        media = json["media"] as? String ?? ""
        preview = json["preview"] as? String ?? ""
        hasTranscript = json["has_transcript"] as? Bool ?? false
    }

    var label: String {
        let time = String(format: "%02d:%02d", Int(start) / 60, Int(start) % 60)
        return "Clipe \(index + 1) · \(name) · \(time)"
    }
}

/// One word inside a phrase, with the acoustics that justify an emphasis.
struct ReviewWord: Identifiable {
    let id: Int
    let text: String
    let start: Double
    let end: Double
    let energy: Double
    let emphasis: Double

    init(id: Int, json: [String: Any]) {
        self.id = id
        text = json["text"] as? String ?? ""
        start = json["start"] as? Double ?? 0
        end = json["end"] as? Double ?? 0
        energy = json["energy"] as? Double ?? 0
        emphasis = json["emphasis"] as? Double ?? 0
    }
}

/// A phrase in the review step — one spoken line plus the decision made about
/// it. Mirrors `fcpxml/phrase_review.py`; `emphasis` is 0–3 and everything
/// mutable here is what the editor is allowed to change.
struct ReviewPhrase: Identifiable {
    let id: Int
    let start: Double
    let end: Double
    var trimStart: Double
    var trimEnd: Double
    var text: String
    let speaker: String
    var active: Bool
    var emphasis: Int
    var track: String
    let peakEmphasis: Double
    let emotion: String
    let emotionConfidence: Double
    let takeBoundary: Bool
    let gapBefore: Double
    let reason: String
    let words: [ReviewWord]

    static let trackScript = "roteiro"
    static let trackBackstage = "bastidor"

    /// Delivery emotion as the analysis names it, in the user's language plus a
    /// glyph — the label alone is too easy to skim past in a dense list.
    static func emotionLabel(_ emotion: String) -> (String, String) {
        switch emotion {
        case "excited": return ("Empolgado", "flame")
        case "tense": return ("Tenso", "bolt")
        case "calm": return ("Calmo", "leaf")
        case "reflective": return ("Reflexivo", "moon")
        default: return ("Neutro", "circle")
        }
    }

    init(json: [String: Any]) {
        id = json["index"] as? Int ?? 0
        start = json["start"] as? Double ?? 0
        end = json["end"] as? Double ?? 0
        trimStart = json["trim_start"] as? Double ?? (json["start"] as? Double ?? 0)
        trimEnd = json["trim_end"] as? Double ?? (json["end"] as? Double ?? 0)
        text = json["text"] as? String ?? ""
        speaker = json["speaker"] as? String ?? ""
        active = json["active"] as? Bool ?? true
        emphasis = json["emphasis"] as? Int ?? 0
        track = json["track"] as? String ?? ReviewPhrase.trackScript
        peakEmphasis = json["peak_emphasis"] as? Double ?? 0
        emotion = json["emotion"] as? String ?? "neutral"
        emotionConfidence = json["emotion_confidence"] as? Double ?? 0
        takeBoundary = json["take_boundary"] as? Bool ?? false
        gapBefore = json["gap_before"] as? Double ?? 0
        reason = json["reason"] as? String ?? ""
        words = (json["words"] as? [[String: Any]] ?? [])
            .enumerated().map { ReviewWord(id: $0.offset, json: $0.element) }
    }

    var asJSON: [String: Any] {
        [
            "index": id,
            "start": start,
            "end": end,
            "trim_start": trimStart,
            "trim_end": trimEnd,
            "text": text,
            "speaker": speaker,
            "active": active,
            "emphasis": emphasis,
            "track": track,
            "reason": reason,
        ]
    }

    var isBackstage: Bool { track == ReviewPhrase.trackBackstage }
    var isTrimmed: Bool { trimStart > start + 0.001 || trimEnd < end - 0.001 }
    var timecode: String {
        String(format: "%02d:%02d", Int(start) / 60, Int(start) % 60)
    }

    /// The word boundaries a trim handle is allowed to land on.
    func snap(_ time: Double, edge: TrimEdge) -> Double {
        let boundaries = words.map { edge == .start ? $0.start : $0.end }.filter { $0 > 0 }
        guard let nearest = boundaries.min(by: { abs($0 - time) < abs($1 - time) }) else {
            return time
        }
        return nearest
    }
}

enum TrimEdge { case start, end }

/// A punch-in the editor placed by hand over an arbitrary range, next to the
/// whole-phrase zoom that an emphasis level produces. It stores only *when* —
/// the scale and the ramp come from the Voice Analysis settings at render time.
struct ManualZoom: Identifiable {
    let id = UUID()
    var start: Double
    var end: Double

    /// Below this a punch-in has no room to ramp in and back out; the writer
    /// rejects the window, so offering it would place nothing.
    static let minimumDuration: Double = 0.4

    init(start: Double, end: Double) {
        self.start = start
        self.end = end
    }

    init?(json: [String: Any]) {
        guard let start = json["start"] as? Double, let end = json["end"] as? Double,
              end - start >= ManualZoom.minimumDuration
        else { return nil }
        self.start = start
        self.end = end
    }

    var asJSON: [String: Any] { ["start": start, "end": end] }
}

struct ZoomSegment: Identifiable {
    let id: Int
    let start: Double
    let end: Double
    let text: String

    init(json: [String: Any]) {
        id = json["id"] as? Int ?? 0
        start = json["start"] as? Double ?? 0
        end = json["end"] as? Double ?? 0
        text = json["text"] as? String ?? ""
    }

    var label: String {
        String(format: "%06.2f–%06.2f  %@", start, end, text)
    }
}