#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
检查字幕和音频文件的对应关系
"""

import os
import sqlite3
import re


def check_subtitle_audio_match():
    """
    检查字幕和音频文件的对应关系
    """
    # 获取字幕数据
    db_path = r"\\ll\\d\\xtrssvjj\\dpd.db"
    conn = sqlite3.connect(db_path)
    cur = conn.cursor()
    
    cur.execute("SELECT idx, cn, en FROM srts WHERE adid=? ORDER BY idx", (8407,))
    srtsdata = cur.fetchall()
    conn.close()
    
    print(f"数据库中有 {len(srtsdata)} 条字幕记录")
    print("\n前10条字幕:")
    for idx, cn, en in srtsdata[:10]:
        print(f"idx: {idx}, cn: {cn}, en: {en}")
    
    # 检查TTS音频文件
    tts_dir = "我们需要知识分子吗_思考_tts"
    tts_files = []
    for filename in os.listdir(tts_dir):
        if filename.endswith('.mp3') and filename.startswith('tts_'):
            match = re.match(r'tts_(\d+)\.mp3', filename)
            if match:
                idx = int(match.group(1))
                tts_files.append((idx, filename))
    
    tts_files.sort(key=lambda x: x[0])
    print(f"\nTTS音频文件: {len(tts_files)} 个")
    print("前10个TTS音频文件:")
    for idx, filename in tts_files[:10]:
        print(f"idx: {idx}, filename: {filename}")
    
    # 检查中文音频文件
    seg_dir = "我们需要知识分子吗_思考_segments"
    seg_files = []
    for filename in os.listdir(seg_dir):
        if filename.endswith('.mp3') and filename.startswith('seg'):
            match = re.match(r'seg(\d+)-', filename)
            if match:
                idx = int(match.group(1))
                seg_files.append((idx, filename))
    
    seg_files.sort(key=lambda x: x[0])
    print(f"\n中文音频文件: {len(seg_files)} 个")
    print("前10个中文音频文件:")
    for idx, filename in seg_files[:10]:
        print(f"idx: {idx}, filename: {filename}")
    
    # 检查图片文件
    img_dir = "我们需要知识分子吗_思考_images"
    img_files = []
    for filename in os.listdir(img_dir):
        if filename.endswith('.png') and filename.startswith('vertical_subtitle_'):
            match = re.match(r'vertical_subtitle_(\d+)\.png', filename)
            if match:
                idx = int(match.group(1))
                img_files.append((idx, filename))
    
    img_files.sort(key=lambda x: x[0])
    print(f"\n图片文件: {len(img_files)} 个")
    print("前10个图片文件:")
    for idx, filename in img_files[:10]:
        print(f"idx: {idx}, filename: {filename}")


if __name__ == "__main__":
    check_subtitle_audio_match()