utils.py

import re
import os


class VideoSubFinderUtils:
    """VideoSubFinder工具类"""
    
    @staticmethod
    def parse_filename(filename):
        """
        解析VideoSubFinder生成的文件名，提取时间戳
        支持格式如: 0_00_18_320__0_00_19_279_*.jpeg
        """
        # 优先处理 VideoSubFinder 文件格式 "0_00_18_320__0_00_19_279_*.jpeg"
        # 我们需要匹配一个以数字和下划线开头，双下划线分隔的模式
        # 正则表达式：(\d+)_(\d+)_(\d+)_(\d+)__(\d+)_(\d+)_(\d+)_(\d+).*
        # '.*' 用于匹配文件名后面的任意字符，避免使用 rsplit
        match = re.search(r'(\d+)_(\d+)_(\d+)_(\d+)__(\d+)_(\d+)_(\d+)_(\d+)', filename)
        if match:
            # 提取第一个时间戳的各部分
            h1, m1, s1, ms1 = map(int, match.groups()[:4])
            # 提取第二个时间戳的各部分
            h2, m2, s2, ms2 = map(int, match.groups()[4:])

            # 格式化为 hh:mm:ss,mmm
            start_time = f"{h1:02d}:{m1:02d}:{s1:02d},{ms1:03d}"
            end_time = f"{h2:02d}:{m2:02d}:{s2:02d},{ms2:03d}"

            return start_time, end_time

        # 如果需要，可以在这里添加其他匹配规则
        # 例如，你可以将原代码中第一个匹配规则放在这里
        match_other = re.search(r'(\d{2}-\d{2}-\d{2}-\d{3})_(\d{2}-\d{2}-\d{2}-\d{3})', filename)
        if match_other:
            start_str = match_other.group(1).replace('-', ':').replace(':', ',', 2)
            end_str = match_other.group(2).replace('-', ':').replace(':', ',', 2)
            return start_str, end_str

        # 最后，添加一个通用的、不那么精确的匹配规则
        # 注意: 如果这个规则会误匹配，最好删除或修改
        match_generic = re.search(r'(\d+)_(\d+)', filename)
        if match_generic:
            start_ms = int(match_generic.group(1)) * 10
            end_ms = int(match_generic.group(2)) * 10
            # 这里为了演示，我们先不处理
            pass

        raise ValueError("Could not extract timestamp from filename.")

    @staticmethod
    def format_milliseconds(ms):
        """将毫秒数转换为 'hh:mm:ss,mmm' 格式"""
        hours = ms // 3600000
        ms %= 3600000
        minutes = ms // 60000
        ms %= 60000
        seconds = ms // 1000
        milliseconds = ms % 1000
        return f"{hours:02d}:{minutes:02d}:{seconds:02d},{milliseconds:03d}"

    @staticmethod
    def get_image_files(directory):
        """获取目录中的所有图像文件"""
        image_extensions = ('.png', '.bmp', '.jpg', '.jpeg')
        return sorted([f for f in os.listdir(directory) if f.lower().endswith(image_extensions)])