gart/admin/api/subtitles.py

"""Legendas: dinâmicas, comuns, SRT e as configurações de estilo.

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

from __future__ import annotations

import asyncio
from pathlib import Path

from fcpxml.media_intel import media_src_to_path
from fcpxml.model_manager import (
    load_dynamic_subtitle_config,
    load_plain_subtitle_config,
    save_dynamic_subtitle_config,
    save_plain_subtitle_config,
)
from fcpxml.writer import FCPXMLModifier

from . import shared
from .shared import (
    _derived_output,
    _emit_no_change_or_error,
    _load_cached_transcript,
    _transcript_json_path,
)


def cmd_generate_dynamic_subtitles(args: dict) -> int:
    """Generate word-by-word ("karaoke") caption compound clips, one per line,
    using each media's cached transcript."""
    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
    try:
        from server import handle_generate_dynamic_subtitles

        output = _derived_output(path, "_dynamic_subtitles", args)
        contents = asyncio.run(
            handle_generate_dynamic_subtitles({**args, "filepath": path, "output_path": output})
        )
        message = "\n".join(getattr(content, "text", str(content)) for content in contents)
        if not Path(output).exists():
            shared.emit({"ok": False, "error": message})
            return 1
        shared.emit({"ok": True, "path": output, "message": message})
        return 0
    except Exception as exc:
        shared.emit({"ok": False, "error": str(exc)})
        return 1

def cmd_generate_plain_subtitles(args: dict) -> int:
    """Generate simple static editable subtitle title clips."""
    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
    try:
        from server import handle_generate_plain_subtitles

        output = _derived_output(path, "_plain_subtitles", args)
        contents = asyncio.run(
            handle_generate_plain_subtitles({**args, "filepath": path, "output_path": output})
        )
        message = "\n".join(getattr(content, "text", str(content)) for content in contents)
        if not Path(output).exists():
            return _emit_no_change_or_error(path, message)
        shared.emit({"ok": True, "path": output, "message": message})
        return 0
    except Exception as exc:
        shared.emit({"ok": False, "error": str(exc)})
        return 1

def cmd_export_srt(args: dict) -> int:
    """Write a captions .srt synced to the edited timeline.

    Each transcribed segment is mapped from its SOURCE-media timestamp to its
    real TIMELINE position (``clip_offset + (seg_start - clip_source_start)``),
    so captions only cover the frames that remain after cuts/silence removal —
    not the whole source file. One .srt is produced per media, in timeline order.
    """
    path = str(args.get("path", ""))
    output_dir = str(args.get("output_dir", "")).strip()
    if not path or not Path(path).exists():
        shared.emit({"ok": False, "error": "Arquivo de projeto não encontrado."})
        return 1
    try:
        modifier = FCPXMLModifier(path)
    except Exception as exc:
        shared.emit({"ok": False, "error": f"Erro ao ler o projeto: {exc}"})
        return 1

    # Group spine clips by media so each transcript is loaded once.
    by_media: dict[str, list] = {}
    for _, el in modifier._iter_spine_clips():
        src = modifier.resources.get(el.get("ref", ""), {}).get("src", "")
        mp = media_src_to_path(src)
        if not mp or not Path(mp).is_file():
            continue
        by_media.setdefault(mp, []).append(el)

    # Never emit a caption past the end of the project — Final Cut rejects an
    # SRT whose last cue overruns the timeline ("subtitle extends beyond project
    # duration"). Clamp every mapped cue end to this ceiling.
    timeline_total = modifier._timeline_duration().to_seconds()

    srt_paths: list[str] = []
    for mp, clips in by_media.items():
        cached = _load_cached_transcript(_transcript_json_path(mp, output_dir))
        if cached is None:
            continue
        segments = cached.get("segments") or []
        if not segments:
            continue

        rows: list[tuple[float, float, str, int]] = []
        for el in clips:
            clip_source_start = modifier.source_file_start(el).to_seconds()
            clip_duration = modifier._parse_time(el.get("duration", "0s")).to_seconds()
            clip_offset = modifier._parse_time(el.get("offset", "0s")).to_seconds()
            window_end = clip_source_start + clip_duration
            for seg_index, seg in enumerate(segments):
                seg_start = float(seg.get("start", 0.0))
                seg_end = float(seg.get("end", seg_start))
                text = seg.get("text", "").strip()
                if not text or seg_end <= seg_start:
                    continue
                # Intersect the complete source segment with this kept clip.
                # Testing only seg_start loses speech whose first words fall in
                # a removed range; interval intersection preserves the part
                # that remains and avoids duplicating a segment wholesale.
                source_start = max(seg_start, clip_source_start)
                source_end = min(seg_end, window_end)
                if source_end <= source_start:
                    continue
                tl_start = clip_offset + (source_start - clip_source_start)
                tl_end = clip_offset + (source_end - clip_source_start)
                tl_start = max(0.0, min(tl_start, timeline_total))
                tl_end = max(0.0, min(tl_end, timeline_total))
                if tl_end > tl_start:
                    rows.append((tl_start, tl_end, text, seg_index))

        if not rows:
            continue
        rows.sort(key=lambda r: (r[0], r[1], r[3]))
        # Merge only pieces from the same original Whisper segment when their
        # mapped intervals touch. Never merge unrelated speech or invent time.
        merged: list[tuple[float, float, str, int]] = []
        for row in rows:
            if merged and row[3] == merged[-1][3] and row[0] <= merged[-1][1] + 0.001:
                prev = merged[-1]
                merged[-1] = (prev[0], max(prev[1], row[1]), prev[2], prev[3])
            else:
                merged.append(row)

        blocks = []
        for index, (s, e, text, _) in enumerate(merged, 1):
            start_stamp = srt_stamp(s)
            end_stamp = srt_stamp(e)
            # Millisecond SRT precision can collapse a sub-millisecond span;
            # omit it rather than emit an invalid zero-duration cue.
            if start_stamp == end_stamp:
                continue
            blocks.append(f"{index}\n{start_stamp} --> {end_stamp}\n{text}\n")
        if not blocks:
            continue

        out = (
            Path(output_dir).expanduser() / f"{Path(mp).stem}_captions.srt"
            if output_dir
            else Path(mp).with_name(Path(mp).stem + "_captions.srt")
        )
        if output_dir:
            out.parent.mkdir(parents=True, exist_ok=True)
        try:
            out.write_text("\n".join(blocks), encoding="utf-8")
        except OSError as exc:
            shared.emit({"ok": False, "error": f"Não foi possível salvar a legenda: {exc}"})
            return 1
        srt_paths.append(str(out))

    if not srt_paths:
        shared.emit({"ok": False, "error": "Nenhuma transcrição encontrada. Transcreva o projeto primeiro."})
        return 1

    shared.emit({"ok": True, "paths": srt_paths, "message": f"{len(srt_paths)} legenda(s) .srt sincronizada(s) com o corte."})
    return 0

def srt_stamp(seconds: float) -> str:
    """Format float seconds as ``HH:MM:SS,mmm`` (SRT uses a comma).

    Uses ``floor`` (not ``round``) so a timestamp never rounds up past a frame
    boundary — an SRT cue ending on the last frame must not overrun the
    project duration, or Final Cut flags it as extending beyond the project.
    """
    ms = int((seconds if seconds > 0 else 0.0) * 1000)
    h, rem = divmod(ms, 3600000)
    m, rem = divmod(rem, 60000)
    s, ms = divmod(rem, 1000)
    return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"

def cmd_dynamic_subtitle_config(args: dict) -> int:
    """Read the persisted dynamic-subtitle style (font, size, color, layout)."""
    shared.emit({"ok": True, **load_dynamic_subtitle_config()})
    return 0

def cmd_set_dynamic_subtitle_config(args: dict) -> int:
    """Persist dynamic-subtitle style fields. Only the given fields change."""
    config = save_dynamic_subtitle_config(**{
        k: args.get(k) for k in (
            "band_height", "block_center_y", "line_gap", "font", "font_size",
            "emphasis_font", "emphasis_face", "emphasis_size",
            "active_color", "emphasis_color", "text_scale",
        )
    })
    shared.emit({"ok": True, **config})
    return 0

def cmd_plain_subtitle_config(args: dict) -> int:
    """Read the persisted simple subtitle style."""
    shared.emit({"ok": True, **load_plain_subtitle_config()})
    return 0

def cmd_set_plain_subtitle_config(args: dict) -> int:
    """Persist simple subtitle style fields. Only the given fields change."""
    config = save_plain_subtitle_config(**{
        k: args.get(k) for k in (
            "font", "font_size", "font_color", "max_words",
            "position_y", "uppercase", "keep_punctuation", "text_scale",
        )
    })
    shared.emit({"ok": True, **config})
    return 0