"""模型工作器执行模型。
改编自https://github.com/OpenGVLab/InternVL/blob/main/streamlit_demo/model_worker.py
"""
# 在导入transformers前导入torch可能导致`segmentation fault`
from transformers import AutoModel, AutoTokenizer, TextIteratorStreamer, AutoConfig

import argparse
import base64
import json
import os
import decord
import threading
import time
from io import BytesIO
from threading import Thread
import math
import requests
import torch
import torchvision.transforms as T
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
import numpy as np


IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

SIGLIP_MEAN = (0.5, 0.5, 0.5)
SIGLIP_STD = (0.5, 0.5, 0.5)


def get_seq_frames(total_num_frames, desired_num_frames=-1, stride=-1):
    """计算从视频中提取的帧索引。
    
    参数:
    total_num_frames (int): 视频总帧数。
    desired_num_frames (int): 期望提取的帧数。
    
    返回:
    list: 提取帧的索引列表。
    """
    
    assert desired_num_frames > 0 or stride > 0 and not (desired_num_frames > 0 and stride > 0)

    if stride > 0:
        return list(range(0, total_num_frames, stride))
    
    # 计算每个段的大小，从中提取一帧
    seg_size = float(total_num_frames - 1) / desired_num_frames

    seq = []
    for i in range(desired_num_frames):
        # 计算每个段的起始和结束索引
        start = int(np.round(seg_size * i))
        end = int(np.round(seg_size * (i + 1)))

        # 将段的中间索引添加到列表
        seq.append((start + end) // 2)

    return seq

def build_video_prompt(meta_list, num_frames, time_position=False):
    # 如果time_position为True，使用frame_timestamp
    # 1. 传递time_position 2. 使用环境变量TIME_POSITION
    time_position = os.environ.get("TIME_POSITION", time_position)
    prefix = f"这是一个视频:\n"
    for i in range(num_frames):
        if time_position:
            frame_txt = f"第{i+1}帧采样于{meta_list[i]:.2f}秒: <image>\n"
        else:
            frame_txt = f"第{i+1}帧: <image>\n"
        prefix += frame_txt
    return prefix

def load_video(video_path, num_frames=64, frame_cache_root=None):
    if isinstance(video_path, str):
        video = decord.VideoReader(video_path)
    elif isinstance(video_path, dict):
        assert False, '不支持输入视频路径为字典'
    fps = video.get_avg_fps()
    sampled_frames = get_seq_frames(len(video), num_frames)
    samepld_timestamps = [i / fps for i in sampled_frames]
    frames = video.get_batch(sampled_frames).asnumpy()
    images = [Image.fromarray(frame) for frame in frames]
    
    return images, build_video_prompt(samepld_timestamps, len(images), time_position=True)

def load_image(image):
    if isinstance(image, str) and os.path.exists(image):
        return Image.open(image)
    elif isinstance(image, dict):
        if 'disk_path' in image:
            return Image.open(image['disk_path'])
        elif 'base64' in image:
            return Image.open(BytesIO(base64.b64decode(image['base64'])))
        elif 'url' in image:
            response = requests.get(image['url'])
            return Image.open(BytesIO(response.content))
        elif 'bytes' in image:
            return Image.open(BytesIO(image['bytes']))
        else:
            raise ValueError(f'无效图像: {image}')
    else:
        raise ValueError(f'无效图像: {image}')

def build_transform(input_size, norm_type='imagenet'):
    if norm_type == 'imagenet':
        MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    elif norm_type == 'siglip':
        MEAN, STD = SIGLIP_MEAN, SIGLIP_STD
        
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform


def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    """之前版本主要关注比例。
    这里我们还考虑面积比例。
    """
    best_factor = float('-inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        area_ratio = (ratio[0]*ratio[1]*image_size*image_size)/ area
        """
        新面积大于原始图像面积的60%即可。
        """
        factor_based_on_area_n_ratio = min((ratio[0]*ratio[1]*image_size*image_size)/ area, 0.6)* \
                                     min(target_aspect_ratio/aspect_ratio, aspect_ratio/target_aspect_ratio)
        
        if factor_based_on_area_n_ratio > best_factor:
            best_factor = factor_based_on_area_n_ratio
            best_ratio = ratio
        
    return best_ratio


def dynamic_preprocess(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # 计算现有图像宽高比
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # 找到最接近的目标宽高比
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # 计算目标宽度和高度
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # 调整图像大小
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box =