#!/usr/bin/env python3
"""
最终格式修复脚本
确保所有章节都有正确的Markdown格式
"""

import os
import re

CHAPTERS_DIR = "/root/.openclaw/workspace/projects/末日重生_囤货/chapters"

def final_fix_format(content, filename):
    """
    最终的格式修复
    """
    lines = content.split('\n')
    
    # 1. 提取章节编号和标题
    chapter_num = "1"
    chapter_title = "未命名"
    
    # 从文件名提取
    match = re.search(r'ch(\d+)-第\d+章\s+(.+)\.md', filename)
    if match:
        chapter_num = match.group(1)
        chapter_title = match.group(2).strip()
    
    # 2. 构建标准开头
    standard_start = f"# 第{chapter_num}章 {chapter_title}\n\n"
    
    # 3. 清理所有行
    cleaned_lines = []
    for line in lines:
        # 移除开头的多余空格
        line = line.strip()
        
        # 跳过空行（后面会统一添加）
        if not line:
            continue
        
        # 移除多余的加粗标记
        line = re.sub(r'^\*\*(.*?)\*\*$', r'\1', line)
        
        # 修复中文标点格式
        line = re.sub(r'\s*([，。！？；：])\s*', r'\1', line)
        
        cleaned_lines.append(line)
    
    # 4. 重新组合为段落
    paragraphs = []
    current_para = []
    
    for line in cleaned_lines:
        if line.startswith('#') or line.startswith('【爽点'):
            # 保存当前段落
            if current_para:
                paragraphs.append(' '.join(current_para))
                current_para = []
            paragraphs.append(line)
        else:
            current_para.append(line)
    
    # 最后一个段落
    if current_para:
        paragraphs.append(' '.join(current_para))
    
    # 5. 确保爽点部分在最后
    shuangdian_paras = []
    other_paras = []
    
    for para in paragraphs:
        if '【爽点' in para:
            shuangdian_paras.append(para)
        else:
            other_paras.append(para)
    
    # 6. 合并所有段落
    result = standard_start
    
    # 添加其他段落
    for para in other_paras:
        if para.startswith('#') and para != standard_start.strip():
            result += para + '\n\n'
        else:
            result += para + '\n\n'
    
    # 添加爽点段落
    if shuangdian_paras:
        result += '\n\n'.join(shuangdian_paras) + '\n'
    
    # 7. 清理格式
    # 确保段落间有空行
    result = re.sub(r'\n{3,}', '\n\n', result)
    
    # 移除多余的空格
    result = re.sub(r'[ \t]{2,}', ' ', result)
    
    # 确保章节标题后有空行
    result = re.sub(r'^# .+\n(?!\n)', r'\g<0>\n', result, flags=re.MULTILINE)
    
    return result.strip() + '\n'

def main():
    print("执行最终格式修复...")
    
    chapter_files = [f for f in os.listdir(CHAPTERS_DIR) if f.endswith('.md')]
    
    for filename in sorted(chapter_files, key=lambda x: int(re.search(r'ch(\d+)', x).group(1)) if re.search(r'ch(\d+)', x) else 0):
        filepath = os.path.join(CHAPTERS_DIR, filename)
        
        print(f"修复: {filename}")
        
        with open(filepath, 'r', encoding='utf-8') as f:
            content = f.read()
        
        # 跳过已经修复过的文件
        if content.startswith('# 第'):
            print(f"  ✓ 格式已正确")
            continue
        
        # 创建备份
        backup_path = filepath + '.final.bak'
        with open(backup_path, 'w', encoding='utf-8') as f:
            f.write(content)
        
        # 应用最终修复
        fixed_content = final_fix_format(content, filename)
        
        with open(filepath, 'w', encoding='utf-8') as f:
            f.write(fixed_content)
        
        print(f"  ✓ 已完成最终修复")
    
    print("\n所有章节格式修复完成！")

if __name__ == '__main__':
    main()