#!/usr/bin/env python3 """ inkos章节格式检查和自动修复脚本 在inkos生成章节后立即运行，确保格式标准化 """ import os import re import json import sys from pathlib import Path from typing import Dict, List, Tuple class ChapterFormatFixer: def __init__(self, config_path: str = None): self.config = self.load_config(config_path) self.problems_fixed = 0 def load_config(self, config_path: str = None) -> Dict: """加载配置""" if config_path and os.path.exists(config_path): with open(config_path, 'r', encoding='utf-8') as f: return json.load(f) # 默认配置 return { "chapter_title_map": { "0002_暗流.md": "暗流涌动", "0003_仓鼠行动.md": "仓鼠计划", "0004_粮草先行.md": "物资先行", "0005_铁壁.md": "钢铁堡垒", "0006_焊花.md": "焊光四溅", "0007_骨刺.md": "骨刺警告", "0008_暗流（2）.md": "暗流再起", "0009_对峙.md": "初次对峙", "0010_倒计时.md": "末日倒计时", "0011_筹码.md": "生存筹码", "0012_质询.md": "深夜质询", "0013_铁锈.md": "铁锈危机", "0014_断水.md": "断水危机" }, "format_rules": { "remove_bold": True, "fix_headings": True, "normalize_dialogue": True, "add_line_breaks": True, "end_with_separator": True } } def check_chapter(self, file_path: str) -> List[str]: """检查章节格式问题""" problems = [] try: with open(file_path, 'r', encoding='utf-8') as f: content = f.read() filename = os.path.basename(file_path) # 1. 检查加粗格式 if '**' in content: problems.append("包含加粗格式(**text**)") # 2. 检查多余的标题格式 if re.search(r'^##+ ', content, re.MULTILINE): problems.append("包含多余的标题格式(##)") # 3. 检查章节标题格式 if not re.search(r'^# 第\d+章 ', content, re.MULTILINE): problems.append("章节标题格式不正确") # 4. 检查段落格式 lines = content.split('\n') for i, line in enumerate(lines): if line.strip() and not line.startswith('#') and len(line.strip()) > 500: problems.append(f"第{i+1}行段落过长") # 5. 检查章节结尾 if not content.strip().endswith('---'): problems.append("章节结尾缺少分隔线(---)") return problems except Exception as e: return [f"读取文件时出错: {str(e)}"] def fix_chapter(self, file_path: str) -> Tuple[bool, str]: """修复章节格式""" try: filename = os.path.basename(file_path) # 读取内容 with open(file_path, 'r', encoding='utf-8') as f: content = f.read() original_content = content fixes_applied = [] # 1. 移除加粗格式 if self.config['format_rules']['remove_bold']: if '**' in content: content = content.replace('**', '') fixes_applied.append("移除加粗格式") # 2. 修复标题格式 if self.config['format_rules']['fix_headings']: # 移除多余的## content = re.sub(r'^##+ (.+)$', r'\1', content, flags=re.MULTILINE) # 确保章节标题格式正确 chapter_match = re.search(r'^# (第\d+章 )?(.+)$', content, re.MULTILINE) if chapter_match: chapter_num = filename.split('_')[0] chapter_num_int = int(chapter_num) # 获取优化后的标题 new_title = self.config['chapter_title_map'].get(filename, chapter_match.group(2)) # 重建标题 new_header = f"# 第{chapter_num_int}章 {new_title}" content = re.sub(r'^# .+$', new_header, content, count=1, flags=re.MULTILINE) fixes_applied.append(f"优化标题为: {new_title}") # 3. 标准化对话格式 if self.config['format_rules']['normalize_dialogue']: # 确保对话有合理分段 content = re.sub(r'([^"\n])(")([^"]+)(")([^"\n])', r'\1\n\n\2\3\4\n\n\5', content) content = re.sub(r'([^"\n])(“)([^”]+)(”)([^"\n])', r'\1\n\n\2\3\4\n\n\5', content) fixes_applied.append("标准化对话格式") # 4. 添加段落分隔 if self.config['format_rules']['add_line_breaks']: # 确保段落之间有合理空白行 paragraphs = content.split('\n\n') cleaned_paragraphs = [] for para in paragraphs: if para.strip(): cleaned_paragraphs.append(para.strip()) content = '\n\n'.join(cleaned_paragraphs) fixes_applied.append("优化段落分隔") # 5. 确保章节结尾 if self.config['format_rules']['end_with_separator']: if not content.strip().endswith('---'): content = content.rstrip() + '\n\n---' fixes_applied.append("添加章节结尾分隔线") # 6. 移除多余空白行 content = re.sub(r'\n{3,}', '\n\n', content) # 如果内容有变化，保存文件 if content != original_content: # 创建备份 backup_path = file_path + '.bak' with open(backup_path, 'w', encoding='utf-8') as f: f.write(original_content) # 写入修复后的内容 with open(file_path, 'w', encoding='utf-8') as f: f.write(content) self.problems_fixed += 1 return True, f"修复完成: {', '.join(fixes_applied)}" else: return False, "无需修复，格式已正确" except Exception as e: return False, f"修复时出错: {str(e)}" def process_directory(self, directory: str) -> Dict: """处理整个目录的章节""" results = { "total_chapters": 0, "chapters_fixed": 0, "problems_found": 0, "details": [] } for file_path in Path(directory).glob("*.md"): if file_path.name.startswith('000'): results["total_chapters"] += 1 # 检查问题 problems = self.check_chapter(str(file_path)) if problems: results["problems_found"] += len(problems) # 尝试修复 fixed, message = self.fix_chapter(str(file_path)) if fixed: results["chapters_fixed"] += 1 results["details"].append({ "chapter": file_path.name, "problems": problems, "fixed": fixed, "message": message }) return results def monitor_and_fix(self, directory: str, interval: int = 60): """监控目录并自动修复新章节""" import time from watchdog.observers import Observer from watchdog.events import FileSystemEventHandler class ChapterHandler(FileSystemEventHandler): def __init__(self, fixer): self.fixer = fixer def on_created(self, event): if event.is_directory: return if event.src_path.endswith('.md') and os.path.basename(event.src_path).startswith('000'): print(f"📝 检测到新章节: {os.path.basename(event.src_path)}") time.sleep(2) # 等待文件完全写入 # 检查并修复 problems = self.fixer.check_chapter(event.src_path) if problems: print(f" 发现格式问题: {problems}") fixed, message = self.fixer.fix_chapter(event.src_path) if fixed: print(f" ✅ 自动修复: {message}") print(f"🔍 开始监控目录: {directory}") print(" 等待inkos生成新章节...") event_handler = ChapterHandler(self) observer = Observer() observer.schedule(event_handler, directory, recursive=False) observer.start() try: while True: time.sleep(interval) except KeyboardInterrupt: observer.stop() observer.join() def main(): """主函数""" import argparse parser = argparse.ArgumentParser(description="inkos章节格式检查和修复工具") parser.add_argument("action", choices=["check", "fix", "monitor"], help="操作类型") parser.add_argument("--directory", default="/root/.openclaw/workspace/tomato-novel/books/末日重生-开局囤货十亿物资/chapters", help="章节目录") parser.add_argument("--config", help="配置文件路径") args = parser.parse_args() fixer = ChapterFormatFixer(args.config) if args.action == "check": print(f"🔍 检查章节格式: {args.directory}") results = fixer.process_directory(args.directory) print(f"\n📊 检查结果:") print(f" 总章节数: {results['total_chapters']}") print(f" 发现问题: {results['problems_found']}个") print(f" 已修复章节: {results['chapters_fixed']}个") if results['details']: print(f"\n📋 详细报告:") for detail in results['details']: status = "✅ 已修复" if detail['fixed'] else "⚠️ 未修复" print(f" {detail['chapter']}: {status}") if detail['problems']: print(f" 问题: {', '.join(detail['problems'])}") if detail['message']: print(f" 消息: {detail['message']}") elif args.action == "fix": print(f"🛠️ 修复章节格式: {args.directory}") results = fixer.process_directory(args.directory) print(f"\n✅ 修复完成:") print(f" 总章节数: {results['total_chapters']}") print(f" 发现问题: {results['problems_found']}个") print(f" 已修复章节: {results['chapters_fixed']}个") if results['chapters_fixed'] > 0: print(f"\n📝 修复详情:") for detail in results['details']: if detail['fixed']: print(f" {detail['chapter']}: {detail['message']}") elif args.action == "monitor": print("🔄 启动格式监控模式") print(" 此模式将持续监控目录，自动修复inkos生成的新章节") print(" 按 Ctrl+C 停止监控") fixer.monitor_and_fix(args.directory) if __name__ == "__main__": main()