import av
import cv2
import numpy as np
import torch
from huggingface_hub import hf_hub_download
from transformers import AutoProcessor, TvpForVideoGrounding


def pyav_decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps):
    '''
    Convert the video from its original fps to the target_fps and decode the video with PyAV decoder.
    Args:
        container (container): pyav container.
        sampling_rate (int): frame sampling rate (interval between two sampled frames).
        num_frames (int): number of frames to sample.
        clip_idx (int): if clip_idx is -1, perform random temporal sampling.
            If clip_idx is larger than -1, uniformly split the video to num_clips
            clips, and select the clip_idx-th video clip.
        num_clips (int): overall number of clips to uniformly sample from the given video.
        target_fps (int): the input video may have different fps, convert it to
            the target video fps before frame sampling.
    Returns:
        frames (tensor): decoded frames from the video. Return None if the no
            video stream was found.
        fps (float): the number of frames per second of the video.
    '''
    video = container.streams.video[0]
    fps = float(video.average_rate)
    clip_size = sampling_rate * num_frames / target_fps * fps
    delta = max(num_frames - clip_size, 0)
    start_idx = delta * clip_idx / num_clips
    end_idx = start_idx + clip_size - 1
    timebase = video.duration / num_frames
    video_start_pts = int(start_idx * timebase)
    video_end_pts = int(end_idx * timebase)
    seek_offset = max(video_start_pts - 1024, 0)
    container.seek(seek_offset, any_frame=False, backward=True, stream=video)
    frames = {}
    for frame in container.decode(video=0):
        if frame.pts < video_start_pts:
            continue
        frames[frame.pts] = frame
        if frame.pts > video_end_pts:
            break
    frames = [frames[pts] for pts in sorted(frames)]
    return frames, fps


def decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps):
    '''
    Decode the video and perform temporal sampling.
    Args:
        container (container): pyav container.
        sampling_rate (int): frame sampling rate (interval between two sampled frames).
        num_frames (int): number of frames to sample.
        clip_idx (int): if clip_idx is -1, perform random temporal sampling.
            If clip_idx is larger than -1, uniformly split the video to num_clips
            clips, and select the clip_idx-th video clip.
        num_clips (int): overall number of clips to uniformly sample from the given video.
        target_fps (int): the input video may have different fps, convert it to
            the target video fps before frame sampling.
    Returns:
        frames (tensor): decoded frames from the video.
    '''
    assert clip_idx >= -2, "Not a valied clip_idx {}".format(clip_idx)
    frames, fps = pyav_decode(container, sampling_rate, num_frames, clip_idx, num_clips, target_fps)
    clip_size = sampling_rate * num_frames / target_fps * fps
    index = np.linspace(0, clip_size - 1, num_frames)
    index = np.clip(index, 0, len(frames) - 1).astype(np.int64)
    frames = np.array([frames[idx].to_rgb().to_ndarray() for idx in index])
    frames = frames.transpose(0, 3, 1, 2)
    return frames


file = hf_hub_download(repo_id="Intel/tvp_demo", filename="AK2KG.mp4", repo_type="dataset")
model = TvpForVideoGrounding.from_pretrained("Intel/tvp-base")

decoder_kwargs = dict(
    container=av.open(file, metadata_errors="ignore"),
    sampling_rate=1,
    num_frames=model.config.num_frames,
    clip_idx=0,
    num_clips=1,
    target_fps=3,
)
raw_sampled_frms = decode(**decoder_kwargs)

text = "a person is sitting on a bed."
processor = AutoProcessor.from_pretrained("Intel/tvp-base")
model_inputs = processor(
    text=[text], videos=list(raw_sampled_frms), return_tensors="pt", max_text_length=100#, size=size
)

model_inputs["pixel_values"] = model_inputs["pixel_values"].to(model.dtype)
output = model(**model_inputs)

def get_video_duration(filename):
    cap = cv2.VideoCapture(filename)
    if cap.isOpened():
        rate = cap.get(5)
        frame_num = cap.get(7)
        duration = frame_num/rate
        return duration
    return -1

duration = get_video_duration(file)
start, end = processor.post_process_video_grounding(output.logits, duration)

print(f"The time slot of the video corresponding to the text \"{text}\" is from {start}s to {end}s")