#!/usr/bin/env bash
# Turn a video into timestamped contact sheets and scene-change frames for visual analysis.
# Optional --window START:DURATION arguments create dense 10-fps sheets around transitions.
set -euo pipefail

usage() {
  cat <<'EOF'
Usage:
  scripts/analyze_video_frames.sh VIDEO [OUTPUT_DIR] [--window START:DURATION ...]

Examples:
  scripts/analyze_video_frames.sh chapter.mp4
  scripts/analyze_video_frames.sh chapter.mp4 /tmp/chapter-analysis \
    --window 5.8:2.2 --window 15.8:2.5

Outputs:
  overview-001.jpg ...       2-fps timestamped contact sheets
  scenes/scene-001.jpg ...   frames selected by scene-change score
  scene-timestamps.txt       scene-change timestamps from FFmpeg showinfo
  window-START.jpg           10-fps contact sheet for each requested window

Environment overrides:
  OVERVIEW_FPS=2 SCENE_THRESHOLD=0.18 WINDOW_FPS=10
EOF
}

if [ "$#" -lt 1 ] || [ "${1:-}" = "-h" ] || [ "${1:-}" = "--help" ]; then
  usage
  exit $([ "$#" -lt 1 ] && echo 1 || echo 0)
fi

video=$1
shift
if [ ! -f "$video" ]; then
  echo "video not found: $video" >&2
  exit 1
fi

if [ "$#" -gt 0 ] && [[ $1 != --* ]]; then
  output_dir=$1
  shift
else
  base=$(basename "$video")
  output_dir="/tmp/${base%.*}-frames"
fi

overview_fps=${OVERVIEW_FPS:-2}
scene_threshold=${SCENE_THRESHOLD:-0.18}
window_fps=${WINDOW_FPS:-10}
windows=()
while [ "$#" -gt 0 ]; do
  case "$1" in
    --window)
      [ "$#" -ge 2 ] || { echo "--window needs START:DURATION" >&2; exit 2; }
      windows+=("$2")
      shift 2
      ;;
    *)
      echo "unknown argument: $1" >&2
      usage >&2
      exit 2
      ;;
  esac
done

mkdir -p "$output_dir/scenes"

# Six-by-six sheets keep individual frames readable while allowing videos of arbitrary length:
# tile emits additional overview-NNN images after every 36 sampled frames.
ffmpeg -hide_banner -loglevel error -y -i "$video" \
  -vf "fps=${overview_fps},scale=320:-1,drawtext=text='%{pts\\:hms}':x=8:y=8:fontsize=20:fontcolor=yellow:borderw=2,tile=6x6:padding=4:margin=4" \
  -fps_mode vfr "$output_dir/overview-%03d.jpg"

# Keep stderr because showinfo reports the original timestamps there.
ffmpeg -hide_banner -y -i "$video" \
  -vf "select='gt(scene,${scene_threshold})',showinfo" -fps_mode vfr \
  "$output_dir/scenes/scene-%03d.jpg" 2>"$output_dir/scene-showinfo.log" || true
sed -n 's/.*pts_time:\([^ ]*\).*/\1/p' "$output_dir/scene-showinfo.log" \
  >"$output_dir/scene-timestamps.txt"

for window in "${windows[@]}"; do
  start=${window%%:*}
  duration=${window#*:}
  if [ "$start" = "$window" ] || [ -z "$start" ] || [ -z "$duration" ]; then
    echo "invalid window '$window'; expected START:DURATION" >&2
    exit 2
  fi
  safe_start=${start//./_}
  # A 5x5 sheet covers 2.5 seconds at the default 10 fps. Longer windows naturally emit more sheets.
  ffmpeg -hide_banner -loglevel error -y -ss "$start" -t "$duration" -i "$video" \
    -vf "fps=${window_fps},scale=320:-1,drawtext=text='%{pts\\:hms}':x=6:y=6:fontsize=18:fontcolor=yellow:borderw=2,tile=5x5:padding=3:margin=3" \
    -fps_mode vfr "$output_dir/window-${safe_start}-%03d.jpg"
done

echo "video analysis frames: $output_dir"