sing_detect/core/exporters.py

"""
Export singing segments to various formats:
  - EDL (DaVinci Resolve timeline import)
  - CSV (human-readable)
  - DaVinci Resolve Markers CSV
  - JSON (programmatic)
  - ffmpeg concat script (auto-cut)
"""

import csv
import json
import os
import sys
from pathlib import Path

from utils.formats import format_timecode, seconds_to_smpte


def export_edl(segments: list, output_path: str, fps: float = 29.97,
               title: str = "Singing Segments", source_filename: str = None):
    """Export EDL file for DaVinci Resolve."""
    if source_filename:
        clip_name = source_filename
        reel_name_safe = Path(source_filename).stem[:32].replace(" ", "_")
    else:
        clip_name = None
        reel_name_safe = "001"

    rec_offset = 3600.0

    with open(output_path, "w", encoding="utf-8") as f:
        f.write(f"TITLE: {title}\n")
        f.write("FCM: NON-DROP FRAME\n\n")

        current_rec_pos = rec_offset
        for seg in segments:
            edit_num = f"{seg['index']:03d}"
            src_in = seconds_to_smpte(seg["start"], fps)
            src_out = seconds_to_smpte(seg["end"], fps)
            rec_in = seconds_to_smpte(current_rec_pos, fps)
            rec_out = seconds_to_smpte(current_rec_pos + seg["duration"], fps)

            f.write(f"{edit_num}  {reel_name_safe}  V     C        {src_in} {src_out} {rec_in} {rec_out}\n")

            if clip_name:
                f.write(f"* FROM CLIP NAME: {clip_name}\n")

            f.write(f"* COMMENT: Song {seg['index']} - Duration {seg['duration']:.0f}s\n\n")
            current_rec_pos += seg["duration"]


def export_csv(segments: list, output_path: str):
    """Export singing segments as CSV."""
    with open(output_path, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["index", "start_sec", "end_sec", "duration_sec",
                         "start_timecode", "end_timecode"])
        for seg in segments:
            writer.writerow([
                seg["index"],
                f"{seg['start']:.2f}",
                f"{seg['end']:.2f}",
                f"{seg['duration']:.1f}",
                format_timecode(seg["start"]),
                format_timecode(seg["end"]),
            ])


def export_markers_csv(segments: list, output_path: str, fps: float = 29.97):
    """Export DaVinci Resolve Markers CSV."""
    with open(output_path, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["#", "Color", "Name", "Start TC", "End TC", "Duration TC", "Notes"])
        for seg in segments:
            writer.writerow([
                seg["index"],
                "Blue",
                f"Song {seg['index']}",
                seconds_to_smpte(seg["start"], fps),
                seconds_to_smpte(seg["end"], fps),
                seconds_to_smpte(seg["duration"], fps),
                f"Duration: {seg['duration']:.0f}s",
            ])


def export_json(segments: list, output_path: str):
    """Export as JSON."""
    with open(output_path, "w", encoding="utf-8") as f:
        json.dump(segments, f, indent=2, ensure_ascii=False)


def export_ffmpeg_script(segments: list, video_path: str, output_dir: str):
    """
    Export a script that uses ffmpeg to cut and concatenate all
    singing segments into a single video file.
    """
    video_name = Path(video_path).stem
    ext = Path(video_path).suffix
    out_video = str(Path(output_dir) / f"{video_name}_singing_only{ext}")

    is_windows = os.name == "nt" or sys.platform == "win32"
    script_ext = ".bat" if is_windows else ".sh"
    script_path = str(Path(output_dir) / f"{video_name}_autocut{script_ext}")
    concat_list_path = str(Path(output_dir) / f"{video_name}_concat_list.txt")

    lines = []
    if is_windows:
        lines.append("@echo off")
        lines.append("REM Auto-generated ffmpeg script to extract singing segments")
        lines.append(f'REM Source: {video_path}')
        lines.append("")
    else:
        lines.append("#!/bin/bash")
        lines.append("# Auto-generated ffmpeg script to extract singing segments")
        lines.append(f'# Source: {video_path}')
        lines.append("")

    segment_files = []
    for seg in segments:
        seg_file = f"_seg_{seg['index']:03d}{ext}"
        seg_path = str(Path(output_dir) / seg_file)
        segment_files.append(seg_file)

        cmd = (f'ffmpeg -y -ss {seg["start"]:.2f} -i "{video_path}" '
               f'-t {seg["duration"]:.2f} -c copy "{seg_path}"')
        lines.append(f"echo Extracting Song {seg['index']}...")
        lines.append(cmd)
        lines.append("")

    lines.append("echo Creating concat list...")
    if is_windows:
        lines.append("(")
        for sf in segment_files:
            seg_path = str(Path(output_dir) / sf)
            lines.append(f"  echo file '{seg_path}'")
        lines.append(f') > "{concat_list_path}"')
    else:
        for i, sf in enumerate(segment_files):
            seg_path = str(Path(output_dir) / sf)
            op = ">" if i == 0 else ">>"
            lines.append(f"echo \"file '{seg_path}'\" {op} \"{concat_list_path}\"")

    lines.append("")
    lines.append("echo Concatenating all segments...")
    lines.append(f'ffmpeg -y -f concat -safe 0 -i "{concat_list_path}" -c copy "{out_video}"')
    lines.append("")
    lines.append("echo Cleaning up temp files...")

    for sf in segment_files:
        seg_path = str(Path(output_dir) / sf)
        if is_windows:
            lines.append(f'del "{seg_path}"')
        else:
            lines.append(f'rm -f "{seg_path}"')
    if is_windows:
        lines.append(f'del "{concat_list_path}"')
    else:
        lines.append(f'rm -f "{concat_list_path}"')

    lines.append("")
    lines.append(f'echo Done! Output: {out_video}')
    if is_windows:
        lines.append("pause")

    with open(script_path, "w", encoding="utf-8") as f:
        f.write("\n".join(lines))

    if not is_windows:
        os.chmod(script_path, 0o755)

    return script_path


def export_raw_segments(segments: list, output_path: str):
    """Export ALL raw segments (speech/music/noise) as CSV for debugging."""
    with open(output_path, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["label", "start_sec", "end_sec", "duration_sec",
                         "start_timecode", "end_timecode"])
        for label, start, end in segments:
            writer.writerow([
                label,
                f"{start:.2f}",
                f"{end:.2f}",
                f"{end - start:.1f}",
                format_timecode(start),
                format_timecode(end),
            ])