gart/admin/api/voice.py

"""Análise de voz e aplicação das decisões de edição.

Extraído de models_api.py — a tabela de comandos segue lá.
"""

from __future__ import annotations

import asyncio
import json
import sys
from pathlib import Path

# code/ is the package root for fcpxml and server modules.
_CODE_DIR = str(Path(__file__).resolve().parent.parent / "code")
if _CODE_DIR not in sys.path:
    sys.path.insert(0, _CODE_DIR)

from fcpxml.model_manager import (
    load_hf_token,
    load_num_speakers,
    load_selected_model,
    load_transcript_language,
    load_voice_analysis_config,
    save_voice_analysis_config,
)

from . import shared
from .shared import (
    _load_cached_voice_timeline,
    _project_media_paths,
    _transcript_json_path,
    _voice_timeline_json_path,
)
from .shared import _load_cached_transcript  # noqa: E402


def cmd_analyze_voice(args: dict) -> int:
    """Build the voice timeline (transcript+diarization+acoustics -> emphasis)
    for every unique source media in the project, so `refine_voice_timeline`
    and friends have something to read without ever reopening the audio.

    Analysis only — writes _voice_timeline.json next to each media, doesn't
    touch the project XML. `path` passes through unchanged so it composes
    with the other batch steps (silence removal, captions) regardless of
    where in the list it runs.
    """
    path = str(args.get("path", ""))
    if not path or not Path(path).exists():
        shared.emit({"ok": False, "error": "Arquivo de projeto não encontrado."})
        return 1

    model = str(args.get("model", "") or load_selected_model() or "")
    language = args.get("language")
    if language is None:
        language = load_transcript_language()
    if language == "auto":
        language = None
    token = str(args.get("hf_token") or load_hf_token() or "")
    num_speakers = str(args.get("num_speakers") or load_num_speakers() or "")

    try:
        media_paths = _project_media_paths(path)
    except Exception as exc:
        shared.emit({"ok": False, "error": f"Erro ao ler o projeto: {exc}"})
        return 1
    if not media_paths:
        shared.emit({"ok": False, "error": "Nenhum arquivo de mídia acessível encontrado."})
        return 1

    from server import handle_build_voice_timeline

    messages: list[str] = []
    output_dir = str(args.get("output_dir") or "").strip()
    existing: list[Path] = []
    for mp in media_paths:
        timeline_path = _voice_timeline_json_path(mp, output_dir)
        if _load_cached_voice_timeline(timeline_path, mp) is not None:
            existing.append(timeline_path)
    if existing and len(existing) == len(media_paths) and not bool(args.get("force_reprocess", False)):
        message = "# Voice Timeline Cache\n\n"
        message += "Reaproveitando análise de voz existente. Nada foi reprocessado.\n\n"
        for timeline_path in existing:
            message += f"- **Timeline JSON**: {timeline_path}\n"
        shared.emit({
            "ok": True,
            "path": path,
            "reused": True,
            "timelines": [str(p) for p in existing],
            "message": message,
        })
        return 0

    for mp in media_paths:
        transcript_path = _transcript_json_path(mp, output_dir)
        reused_prefix = ""
        if _load_cached_transcript(transcript_path) is not None:
            reused_prefix = f"# Cache\n\nReaproveitando transcrição existente: `{transcript_path}`\n\n"
        try:
            contents = asyncio.run(handle_build_voice_timeline({
                "media_path": mp, "model": model, "language": language,
                "hf_token": token, "num_speakers": num_speakers,
                "output_dir": output_dir,
            }))
        except Exception as exc:
            shared.emit({"ok": False, "error": f"Falha analisando {Path(mp).name}: {exc}"})
            return 1
        messages.append(reused_prefix + "\n".join(getattr(c, "text", str(c)) for c in contents))

    shared.emit({"ok": True, "path": path, "message": "\n\n---\n\n".join(messages)})
    return 0

def cmd_acoustics_capability(args: dict) -> int:
    """Whether librosa (pitch/energy extraction) is installed in this venv.

    Surfaces `features_capability()` — previously computed but never
    exposed to the app, so `layers.acoustics: false` in a voice timeline
    had no explanation the user could act on.
    """
    from fcpxml.voice_features import features_capability
    ok, msg = features_capability()
    shared.emit({"ok": True, "available": ok, "message": msg})
    return 0

def cmd_voice_analysis(args: dict) -> int:
    """Read the persisted voice-analysis settings (energy/emphasis/emotion)."""
    config = load_voice_analysis_config()
    shared.emit({"ok": True, **config, "emphasis_threshold": config["emphasis_floor"]})
    return 0

def cmd_set_voice_analysis(args: dict) -> int:
    """Persist voice-analysis settings. Only the given fields change."""
    weights = args.get("emphasis_weights")
    config = save_voice_analysis_config(
        energy_threshold=args.get("energy_threshold"),
        emphasis_weights=weights if isinstance(weights, dict) else None,
        emphasis_floor=args.get("emphasis_threshold"),
        emotion_enabled=args.get("emotion_enabled"),
        emotion_sensitivity=args.get("emotion_sensitivity"),
        zoom_scale=args.get("zoom_scale"),
        zoom_mode=args.get("zoom_mode"),
        zoom_ease_in=args.get("zoom_ease_in"),
        zoom_ease_out=args.get("zoom_ease_out"),
    )
    shared.emit({"ok": True, **config})
    return 0

def cmd_apply_voice_actions(args: dict) -> int:
    """Apply a decision list (cuts/zooms/texts/markers) to the project XML.

    The list is produced by a model reading the _voice_timeline.json — this
    is the step that turns those decisions into an edit, and the one the
    batch chain was missing: without it the app could measure the voice and
    caption the result, but never cut by it.

    `actions_path` points at the JSON; either a bare list or the
    ``{"actions": [...]}`` wrapper the skill emits is accepted. Times stay in
    ORIGINAL source seconds — the handler resolves cuts first and shifts
    everything else itself.
    """
    path = str(args.get("path", ""))
    if not path or not Path(path).exists():
        shared.emit({"ok": False, "error": "Arquivo de projeto não encontrado."})
        return 1

    actions = args.get("actions")
    if actions is None:
        actions_path = str(args.get("actions_path", ""))
        if not actions_path or not Path(actions_path).exists():
            shared.emit({"ok": False, "error": "Arquivo de decisões (JSON) não encontrado."})
            return 1
        try:
            with open(actions_path, encoding="utf-8") as fh:
                loaded = json.load(fh)
        except (OSError, ValueError) as exc:
            shared.emit({"ok": False, "error": f"Erro ao ler as decisões: {exc}"})
            return 1
        actions = loaded.get("actions") if isinstance(loaded, dict) else loaded

    # The documented output format is {"source": ..., "actions": [...]} —
    # callers passing that whole object inline (e.g. the wizard pasting the
    # skill's JSON verbatim) need the same unwrap the actions_path branch
    # above already does, or a well-formed payload gets rejected as
    # "malformed" for having one extra layer of nesting.
    if isinstance(actions, dict):
        actions = actions.get("actions")

    if not isinstance(actions, list) or not actions:
        shared.emit({"ok": False, "error": "A lista de decisões está vazia ou malformada."})
        return 1

    from server import handle_apply_voice_actions

    try:
        contents = asyncio.run(handle_apply_voice_actions({
            "filepath": path,
            "actions": actions,
            "output_dir": args.get("output_dir"),
        }))
    except Exception as exc:
        shared.emit({"ok": False, "error": f"Falha ao aplicar as decisões: {exc}"})
        return 1

    message = "\n".join(getattr(c, "text", str(c)) for c in contents)
    # The handler reports dropped/rejected actions individually; hand the
    # whole report back so the app can surface them instead of only the count.
    out_path = path
    for line in message.splitlines():
        if line.startswith("- **Saved to**:"):
            out_path = line.split("`")[1] if "`" in line else path
            break
    shared.emit({"ok": True, "path": out_path, "message": message})
    return 0