"""
Benchmark different frame extraction methods to assess performance impact.

Compares:
1. OpenCV frame-based seeking (CAP_PROP_POS_FRAMES) - current method
2. OpenCV time-based seeking (CAP_PROP_POS_MSEC)
3. FFmpeg single-frame extraction (one call per frame)
4. FFmpeg batch extraction (one call for multiple frames)
5. OpenCV sequential read with skip

Usage:
    python scripts/benchmark_extraction_methods.py
"""

import json
import logging
import os
import subprocess
import sys
import tempfile
import time
from pathlib import Path
from typing import Any, Dict, List, Optional

import cv2
import numpy as np

logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)


def load_texas_config() -> Dict[str, Any]:
    """Load the saved config for Texas video."""
    config_path = Path("output/OSU_vs_Texas_01_10_25_config.json")
    with open(config_path, "r") as f:
        return json.load(f)


# =============================================================================
# Method 1: OpenCV Frame-Based Seeking (Current Method)
# =============================================================================


def benchmark_opencv_frame_seeking(video_path: str, timestamps: List[float]) -> Dict[str, Any]:
    """
    Benchmark OpenCV's CAP_PROP_POS_FRAMES seeking.
    This is the current method used in the pipeline.
    """
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        return {"error": "Failed to open video"}

    fps = cap.get(cv2.CAP_PROP_FPS)
    frames_extracted = 0

    t_start = time.perf_counter()

    for ts in timestamps:
        frame_num = int(ts * fps)
        cap.set(cv2.CAP_PROP_POS_FRAMES, frame_num)
        ret, frame = cap.read()
        if ret:
            frames_extracted += 1

    t_elapsed = time.perf_counter() - t_start
    cap.release()

    return {
        "method": "OpenCV Frame Seeking",
        "frames_requested": len(timestamps),
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / len(timestamps),
        "fps": len(timestamps) / t_elapsed,
    }


# =============================================================================
# Method 2: OpenCV Time-Based Seeking
# =============================================================================


def benchmark_opencv_time_seeking(video_path: str, timestamps: List[float]) -> Dict[str, Any]:
    """
    Benchmark OpenCV's CAP_PROP_POS_MSEC seeking.
    """
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        return {"error": "Failed to open video"}

    frames_extracted = 0

    t_start = time.perf_counter()

    for ts in timestamps:
        cap.set(cv2.CAP_PROP_POS_MSEC, ts * 1000.0)
        ret, frame = cap.read()
        if ret:
            frames_extracted += 1

    t_elapsed = time.perf_counter() - t_start
    cap.release()

    return {
        "method": "OpenCV Time Seeking",
        "frames_requested": len(timestamps),
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / len(timestamps),
        "fps": len(timestamps) / t_elapsed,
    }


# =============================================================================
# Method 3: FFmpeg Single Frame Extraction
# =============================================================================


def benchmark_ffmpeg_single_frame(video_path: str, timestamps: List[float]) -> Dict[str, Any]:
    """
    Benchmark FFmpeg extraction, one frame at a time.
    This is the slowest FFmpeg approach but most straightforward.
    """
    frames_extracted = 0

    t_start = time.perf_counter()

    for ts in timestamps:
        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
            tmp_path = tmp.name

        try:
            cmd = [
                "ffmpeg",
                "-ss",
                str(ts),
                "-i",
                str(video_path),
                "-frames:v",
                "1",
                "-q:v",
                "2",
                "-loglevel",
                "error",
                tmp_path,
                "-y",
            ]

            result = subprocess.run(cmd, capture_output=True, timeout=30)
            if result.returncode == 0:
                frame = cv2.imread(tmp_path)
                if frame is not None:
                    frames_extracted += 1
        finally:
            if os.path.exists(tmp_path):
                os.remove(tmp_path)

    t_elapsed = time.perf_counter() - t_start

    return {
        "method": "FFmpeg Single Frame",
        "frames_requested": len(timestamps),
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / len(timestamps),
        "fps": len(timestamps) / t_elapsed,
    }


# =============================================================================
# Method 4: FFmpeg Batch Extraction (select filter)
# =============================================================================


def benchmark_ffmpeg_batch_select(video_path: str, timestamps: List[float]) -> Dict[str, Any]:
    """
    Benchmark FFmpeg batch extraction using select filter.
    Extracts all frames in a single ffmpeg call using timestamp expressions.
    """
    with tempfile.TemporaryDirectory() as tmp_dir:
        t_start = time.perf_counter()

        # Build select filter expression for all timestamps
        # Use 'between' to select frames near each timestamp (within 0.02s = ~1 frame at 60fps)
        tolerance = 0.02
        conditions = [f"between(t,{ts-tolerance},{ts+tolerance})" for ts in timestamps]
        select_expr = "+".join(conditions)

        cmd = [
            "ffmpeg",
            "-i",
            str(video_path),
            "-vf",
            f"select='{select_expr}',setpts=N/TB",
            "-vsync",
            "vfr",
            "-q:v",
            "2",
            "-loglevel",
            "error",
            f"{tmp_dir}/frame_%04d.png",
            "-y",
        ]

        result = subprocess.run(cmd, capture_output=True, timeout=120)

        t_elapsed = time.perf_counter() - t_start

        # Count extracted frames
        frames_extracted = len(list(Path(tmp_dir).glob("frame_*.png")))

    return {
        "method": "FFmpeg Batch Select",
        "frames_requested": len(timestamps),
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / len(timestamps),
        "fps": len(timestamps) / t_elapsed,
        "note": "Single ffmpeg call with select filter",
    }


# =============================================================================
# Method 5: FFmpeg Segment + Sequential Read
# =============================================================================


def benchmark_ffmpeg_segment_opencv_read(video_path: str, timestamps: List[float], interval: float) -> Dict[str, Any]:
    """
    Benchmark: Extract a video segment with ffmpeg, then read sequentially with OpenCV.
    This is a hybrid approach that might give best accuracy with good speed.
    """
    if not timestamps:
        return {"error": "No timestamps provided"}

    start_ts = min(timestamps) - 1.0  # 1 second buffer
    end_ts = max(timestamps) + 1.0

    with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as tmp:
        tmp_path = tmp.name

    try:
        t_start = time.perf_counter()

        # Extract segment with ffmpeg (accurate seeking)
        cmd = [
            "ffmpeg",
            "-ss",
            str(start_ts),
            "-i",
            str(video_path),
            "-t",
            str(end_ts - start_ts),
            "-c:v",
            "libx264",
            "-preset",
            "ultrafast",
            "-crf",
            "18",
            "-an",  # No audio
            "-loglevel",
            "error",
            tmp_path,
            "-y",
        ]

        result = subprocess.run(cmd, capture_output=True, timeout=120)
        if result.returncode != 0:
            return {"error": "FFmpeg segment extraction failed"}

        t_extract = time.perf_counter() - t_start

        # Now read sequentially from the segment
        cap = cv2.VideoCapture(tmp_path)
        if not cap.isOpened():
            return {"error": "Failed to open extracted segment"}

        fps = cap.get(cv2.CAP_PROP_FPS)
        frames_extracted = 0

        # Read frames at the target interval
        t_read_start = time.perf_counter()
        frame_skip = max(1, int(interval * fps))

        current_time = 0.0
        frame_idx = 0
        while current_time < (end_ts - start_ts):
            ret, frame = cap.read()
            if not ret:
                break

            # Check if this frame is near any of our target timestamps
            actual_video_time = start_ts + current_time
            for ts in timestamps:
                if abs(actual_video_time - ts) < interval / 2:
                    frames_extracted += 1
                    break

            # Skip frames
            for _ in range(frame_skip - 1):
                cap.grab()

            current_time += interval
            frame_idx += 1

        cap.release()
        t_read = time.perf_counter() - t_read_start

        t_elapsed = time.perf_counter() - t_start

    finally:
        if os.path.exists(tmp_path):
            os.remove(tmp_path)

    return {
        "method": "FFmpeg Segment + OpenCV Read",
        "frames_requested": len(timestamps),
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "extraction_time": t_extract,
        "read_time": t_read,
        "time_per_frame": t_elapsed / len(timestamps),
        "fps": len(timestamps) / t_elapsed,
    }


# =============================================================================
# Method 6: OpenCV Sequential Read with Skip (Baseline)
# =============================================================================


def benchmark_opencv_sequential(video_path: str, start_time: float, num_frames: int, interval: float) -> Dict[str, Any]:
    """
    Benchmark OpenCV sequential reading with frame skipping.
    This avoids seeking entirely but requires reading from the start of a range.
    """
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        return {"error": "Failed to open video"}

    fps = cap.get(cv2.CAP_PROP_FPS)
    frame_skip = max(1, int(interval * fps))

    t_start = time.perf_counter()

    # Seek to start position once
    cap.set(cv2.CAP_PROP_POS_MSEC, start_time * 1000.0)

    frames_extracted = 0
    for _ in range(num_frames):
        ret, frame = cap.read()
        if not ret:
            break
        frames_extracted += 1

        # Skip frames
        for _ in range(frame_skip - 1):
            cap.grab()

    t_elapsed = time.perf_counter() - t_start
    cap.release()

    return {
        "method": "OpenCV Sequential Read",
        "frames_requested": num_frames,
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / num_frames,
        "fps": num_frames / t_elapsed,
        "note": "Single seek + sequential read with skip",
    }


# =============================================================================
# Method 7: FFmpeg pipe to OpenCV (no temp files)
# =============================================================================


def benchmark_ffmpeg_pipe(video_path: str, start_time: float, duration: float, interval: float) -> Dict[str, Any]:
    """
    Benchmark FFmpeg piping raw frames to OpenCV.
    This avoids temp files and gives accurate timestamps.
    """
    # Get video dimensions first
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        return {"error": "Failed to open video"}
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    cap.release()

    # Calculate output fps based on interval
    output_fps = 1.0 / interval

    t_start = time.perf_counter()

    cmd = [
        "ffmpeg",
        "-ss",
        str(start_time),
        "-i",
        str(video_path),
        "-t",
        str(duration),
        "-vf",
        f"fps={output_fps}",
        "-f",
        "rawvideo",
        "-pix_fmt",
        "bgr24",
        "-loglevel",
        "error",
        "-",
    ]

    process = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)

    frame_size = width * height * 3
    frames_extracted = 0

    while True:
        raw_frame = process.stdout.read(frame_size)
        if len(raw_frame) != frame_size:
            break
        frame = np.frombuffer(raw_frame, dtype=np.uint8).reshape((height, width, 3))
        frames_extracted += 1

    process.wait()
    t_elapsed = time.perf_counter() - t_start

    expected_frames = int(duration / interval)

    return {
        "method": "FFmpeg Pipe to OpenCV",
        "frames_requested": expected_frames,
        "frames_extracted": frames_extracted,
        "total_time": t_elapsed,
        "time_per_frame": t_elapsed / max(1, frames_extracted),
        "fps": frames_extracted / t_elapsed if t_elapsed > 0 else 0,
        "note": "FFmpeg pipes raw frames, no temp files",
    }


def main():
    """Run all benchmarks and compare."""
    config = load_texas_config()
    video_path = config["video_path"]

    logger.info("=" * 80)
    logger.info("FRAME EXTRACTION METHOD BENCHMARK")
    logger.info("=" * 80)
    logger.info("Video: %s", video_path)
    logger.info("")

    # Test parameters
    # Simulate typical pipeline: extract frames every 0.2s over a 60-second segment
    interval = 0.2  # seconds between frames
    segment_duration = 60.0  # seconds
    start_time = 5900.0  # Start in the problem area

    num_frames = int(segment_duration / interval)
    timestamps = [start_time + (i * interval) for i in range(num_frames)]

    logger.info("Test parameters:")
    logger.info("  Segment: %.1fs to %.1fs (%.1fs duration)", start_time, start_time + segment_duration, segment_duration)
    logger.info("  Interval: %.2fs", interval)
    logger.info("  Frames to extract: %d", num_frames)
    logger.info("")

    results = []

    # Benchmark each method
    logger.info("Running benchmarks...")
    logger.info("-" * 40)

    # 1. Current method: OpenCV frame seeking
    logger.info("  Testing OpenCV Frame Seeking...")
    r1 = benchmark_opencv_frame_seeking(video_path, timestamps)
    results.append(r1)
    logger.info("    Done: %.2fs total, %.3fs/frame", r1["total_time"], r1["time_per_frame"])

    # 2. OpenCV time seeking
    logger.info("  Testing OpenCV Time Seeking...")
    r2 = benchmark_opencv_time_seeking(video_path, timestamps)
    results.append(r2)
    logger.info("    Done: %.2fs total, %.3fs/frame", r2["total_time"], r2["time_per_frame"])

    # 3. FFmpeg single frame (only test subset - it's slow)
    subset_timestamps = timestamps[:20]  # Only test 20 frames
    logger.info("  Testing FFmpeg Single Frame (20 frames only)...")
    r3 = benchmark_ffmpeg_single_frame(video_path, subset_timestamps)
    results.append(r3)
    logger.info("    Done: %.2fs total, %.3fs/frame", r3["total_time"], r3["time_per_frame"])

    # 4. OpenCV sequential read
    logger.info("  Testing OpenCV Sequential Read...")
    r4 = benchmark_opencv_sequential(video_path, start_time, num_frames, interval)
    results.append(r4)
    logger.info("    Done: %.2fs total, %.3fs/frame", r4["total_time"], r4["time_per_frame"])

    # 5. FFmpeg pipe
    logger.info("  Testing FFmpeg Pipe to OpenCV...")
    r5 = benchmark_ffmpeg_pipe(video_path, start_time, segment_duration, interval)
    results.append(r5)
    logger.info("    Done: %.2fs total, %.3fs/frame", r5["total_time"], r5["time_per_frame"])

    logger.info("")
    logger.info("=" * 80)
    logger.info("RESULTS SUMMARY")
    logger.info("=" * 80)
    logger.info("")

    # Sort by time per frame
    results_sorted = sorted(results, key=lambda x: x.get("time_per_frame", float("inf")))

    # Find baseline (current method)
    baseline_time = r1["time_per_frame"]

    logger.info("%-30s %10s %10s %10s %10s", "Method", "Total(s)", "Per Frame", "FPS", "vs Current")
    logger.info("-" * 80)

    for r in results_sorted:
        if "error" in r:
            logger.info("%-30s ERROR: %s", r.get("method", "Unknown"), r["error"])
            continue

        speedup = baseline_time / r["time_per_frame"] if r["time_per_frame"] > 0 else 0
        speedup_str = f"{speedup:.2f}x" if speedup != 1.0 else "baseline"

        logger.info(
            "%-30s %10.2f %10.4f %10.1f %10s",
            r["method"],
            r["total_time"],
            r["time_per_frame"],
            r["fps"],
            speedup_str,
        )

    logger.info("")
    logger.info("NOTES:")
    logger.info("  - 'FFmpeg Single Frame' tested with only 20 frames (would be %.1fs for %d frames)", r3["time_per_frame"] * num_frames, num_frames)
    logger.info("  - 'FFmpeg Pipe' gives accurate timestamps AND good performance")
    logger.info("  - 'OpenCV Sequential Read' is fastest but requires contiguous segments")
    logger.info("")

    # Recommendation
    fastest_accurate = None
    for r in results_sorted:
        if r["method"] in ["FFmpeg Pipe to OpenCV", "FFmpeg Segment + OpenCV Read"]:
            fastest_accurate = r
            break

    if fastest_accurate:
        speedup = baseline_time / fastest_accurate["time_per_frame"]
        logger.info("RECOMMENDATION:")
        logger.info("  Use '%s' for accurate VFR handling", fastest_accurate["method"])
        logger.info("  Performance: %.2fx %s than current method", speedup, "faster" if speedup > 1 else "slower")


if __name__ == "__main__":
    main()