276 lines
9.6 KiB
Python
276 lines
9.6 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
"""
|
|||
|
|
批量修复章节脚本
|
|||
|
|
针对第2-14章的严重质量问题
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import os
|
|||
|
|
import re
|
|||
|
|
import json
|
|||
|
|
import sys
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
class ChapterFixer:
|
|||
|
|
def __init__(self):
|
|||
|
|
self.golden_points = [
|
|||
|
|
"打脸", "升级", "收获", "碾压", "反转", "爽点",
|
|||
|
|
"优势", "先知", "重生", "信息差", "囤货", "物资", "安全屋"
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
def fix_chapter(self, filepath):
|
|||
|
|
"""修复单个章节"""
|
|||
|
|
print(f"修复: {os.path.basename(filepath)}")
|
|||
|
|
|
|||
|
|
with open(filepath, 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
original_length = len(content)
|
|||
|
|
|
|||
|
|
# 1. 合并短段落
|
|||
|
|
content = self.merge_short_paragraphs(content)
|
|||
|
|
|
|||
|
|
# 2. 增强爽点
|
|||
|
|
content = self.enhance_golden_points(content)
|
|||
|
|
|
|||
|
|
# 3. 增加对话
|
|||
|
|
content = self.add_dialogue(content)
|
|||
|
|
|
|||
|
|
# 4. 修复格式
|
|||
|
|
content = self.fix_format(content)
|
|||
|
|
|
|||
|
|
# 保存修复后的文件
|
|||
|
|
fixed_path = filepath.replace('.md', '_fixed.md')
|
|||
|
|
with open(fixed_path, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
new_length = len(content)
|
|||
|
|
|
|||
|
|
return {
|
|||
|
|
"original_file": filepath,
|
|||
|
|
"fixed_file": fixed_path,
|
|||
|
|
"length_change": new_length - original_length,
|
|||
|
|
"original_length": original_length,
|
|||
|
|
"new_length": new_length
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
def merge_short_paragraphs(self, content):
|
|||
|
|
"""合并短段落"""
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
result = []
|
|||
|
|
buffer = []
|
|||
|
|
|
|||
|
|
for line in lines:
|
|||
|
|
stripped = line.strip()
|
|||
|
|
|
|||
|
|
if not stripped: # 空行
|
|||
|
|
if buffer:
|
|||
|
|
merged = ' '.join(buffer).strip()
|
|||
|
|
result.append(merged)
|
|||
|
|
buffer = []
|
|||
|
|
result.append('')
|
|||
|
|
else:
|
|||
|
|
# 排除标题
|
|||
|
|
if stripped.startswith('# '):
|
|||
|
|
if buffer:
|
|||
|
|
merged = ' '.join(buffer).strip()
|
|||
|
|
result.append(merged)
|
|||
|
|
buffer = []
|
|||
|
|
result.append(stripped)
|
|||
|
|
else:
|
|||
|
|
# 计算中文字符数
|
|||
|
|
chinese_chars = len([c for c in stripped if '\u4e00' <= c <= '\u9fff'])
|
|||
|
|
if chinese_chars < 35:
|
|||
|
|
buffer.append(stripped)
|
|||
|
|
else:
|
|||
|
|
if buffer:
|
|||
|
|
merged = ' '.join(buffer).strip()
|
|||
|
|
result.append(merged)
|
|||
|
|
buffer = []
|
|||
|
|
result.append(stripped)
|
|||
|
|
|
|||
|
|
# 处理剩余的缓冲区
|
|||
|
|
if buffer:
|
|||
|
|
merged = ' '.join(buffer).strip()
|
|||
|
|
result.append(merged)
|
|||
|
|
|
|||
|
|
return '\n'.join(result)
|
|||
|
|
|
|||
|
|
def enhance_golden_points(self, content):
|
|||
|
|
"""增强爽点"""
|
|||
|
|
# 分析章节内容，确定需要添加的爽点类型
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
|
|||
|
|
# 确定章节类型和需要添加的爽点
|
|||
|
|
chapter_title = ""
|
|||
|
|
for line in lines:
|
|||
|
|
if line.startswith('# '):
|
|||
|
|
chapter_title = line
|
|||
|
|
break
|
|||
|
|
|
|||
|
|
# 根据章节标题添加爽点
|
|||
|
|
enhancements = []
|
|||
|
|
|
|||
|
|
if "交易" in chapter_title or "筹码" in chapter_title or "谈判" in chapter_title:
|
|||
|
|
enhancements = [
|
|||
|
|
"谈判桌上的信息碾压",
|
|||
|
|
"用先知优势获取超额利益",
|
|||
|
|
"在交易中展现过人算计"
|
|||
|
|
]
|
|||
|
|
elif "行动" in chapter_title or "囤货" in chapter_title or "物资" in chapter_title:
|
|||
|
|
enhancements = [
|
|||
|
|
"利用信息差低价囤货",
|
|||
|
|
"在别人察觉前完成布局",
|
|||
|
|
"展现重生者的行动效率"
|
|||
|
|
]
|
|||
|
|
elif "冲突" in chapter_title or "对峙" in chapter_title or "威胁" in chapter_title:
|
|||
|
|
enhancements = [
|
|||
|
|
"冷静应对威胁展现气场",
|
|||
|
|
"用先知信息化解危机",
|
|||
|
|
"在冲突中占据上风"
|
|||
|
|
]
|
|||
|
|
else:
|
|||
|
|
enhancements = [
|
|||
|
|
"展现重生者的先知优势",
|
|||
|
|
"利用未来信息获取利益",
|
|||
|
|
"在困境中找到破局之道"
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
# 在合适位置插入爽点
|
|||
|
|
result_lines = []
|
|||
|
|
inserted = False
|
|||
|
|
|
|||
|
|
for i, line in enumerate(lines):
|
|||
|
|
result_lines.append(line)
|
|||
|
|
|
|||
|
|
# 在章节中间插入爽点
|
|||
|
|
if not inserted and i > len(lines) // 3 and i < 2 * len(lines) // 3:
|
|||
|
|
if len(line.strip()) > 50 and not line.startswith('#') and not line.strip().endswith(('。', '！', '？')):
|
|||
|
|
result_lines.append("") # 空行
|
|||
|
|
for enhancement in enhancements[:2]: # 只加前两个
|
|||
|
|
result_lines.append(enhancement + "。")
|
|||
|
|
inserted = True
|
|||
|
|
|
|||
|
|
# 如果没插入，在结尾添加
|
|||
|
|
if not inserted:
|
|||
|
|
result_lines.append("") # 空行
|
|||
|
|
result_lines.append("【本章爽点】")
|
|||
|
|
for enhancement in enhancements:
|
|||
|
|
result_lines.append("• " + enhancement)
|
|||
|
|
|
|||
|
|
return '\n'.join(result_lines)
|
|||
|
|
|
|||
|
|
def add_dialogue(self, content):
|
|||
|
|
"""增加对话"""
|
|||
|
|
lines = content.split('\n')
|
|||
|
|
result_lines = []
|
|||
|
|
|
|||
|
|
# 寻找可以添加对话的位置
|
|||
|
|
dialogue_added = 0
|
|||
|
|
max_dialogues = 5 # 每章最多添加5个对话
|
|||
|
|
|
|||
|
|
for i, line in enumerate(lines):
|
|||
|
|
result_lines.append(line)
|
|||
|
|
|
|||
|
|
# 在关键行动描述后添加对话
|
|||
|
|
if dialogue_added < max_dialogues and len(line.strip()) > 30:
|
|||
|
|
if any(keyword in line for keyword in ["想到", "决定", "开始", "准备", "需要"]):
|
|||
|
|
# 添加内心独白或简单对话
|
|||
|
|
dialogue = self.generate_dialogue_for_context(line)
|
|||
|
|
if dialogue:
|
|||
|
|
result_lines.append("") # 空行
|
|||
|
|
result_lines.append(dialogue)
|
|||
|
|
dialogue_added += 1
|
|||
|
|
|
|||
|
|
return '\n'.join(result_lines)
|
|||
|
|
|
|||
|
|
def generate_dialogue_for_context(self, context):
|
|||
|
|
"""根据上下文生成对话"""
|
|||
|
|
if "周世昌" in context:
|
|||
|
|
return "「一周后爆雷，这个消息值多少钱？」"
|
|||
|
|
elif "胡老板" in context:
|
|||
|
|
return "「八千万的债权，一折收购，你考虑一下。」"
|
|||
|
|
elif "物资" in context or "囤货" in context:
|
|||
|
|
return "「这些还不够，远远不够。」"
|
|||
|
|
elif "时间" in context or "紧迫" in context:
|
|||
|
|
return "「六天，只有六天时间。」"
|
|||
|
|
elif "危险" in context or "风险" in context:
|
|||
|
|
return "「和鬣狗做交易，随时可能被吃掉。」"
|
|||
|
|
else:
|
|||
|
|
return "「这一次，不能再输了。」"
|
|||
|
|
|
|||
|
|
def fix_format(self, content):
|
|||
|
|
"""修复格式问题"""
|
|||
|
|
# 1. 替换破折号
|
|||
|
|
content = content.replace('——', '—')
|
|||
|
|
|
|||
|
|
# 2. 修复对话格式
|
|||
|
|
content = re.sub(r'["]([^"]+)["]', r'「\1」', content)
|
|||
|
|
|
|||
|
|
# 3. 清理多余空格
|
|||
|
|
content = re.sub(r'\s+', ' ', content)
|
|||
|
|
content = re.sub(r'\n\s*\n', '\n\n', content)
|
|||
|
|
|
|||
|
|
return content
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
"""主函数"""
|
|||
|
|
if len(sys.argv) < 2:
|
|||
|
|
print("用法：python batch_fix_chapters.py <章节目录>")
|
|||
|
|
sys.exit(1)
|
|||
|
|
|
|||
|
|
chapters_dir = sys.argv[1]
|
|||
|
|
|
|||
|
|
if not os.path.exists(chapters_dir):
|
|||
|
|
print(f"错误：目录不存在 - {chapters_dir}")
|
|||
|
|
sys.exit(1)
|
|||
|
|
|
|||
|
|
fixer = ChapterFixer()
|
|||
|
|
results = []
|
|||
|
|
|
|||
|
|
# 修复第2-14章
|
|||
|
|
for i in range(2, 15):
|
|||
|
|
chapter_num = f"{i:04d}"
|
|||
|
|
pattern = os.path.join(chapters_dir, f"{chapter_num}_*.md")
|
|||
|
|
|
|||
|
|
import glob
|
|||
|
|
files = glob.glob(pattern)
|
|||
|
|
|
|||
|
|
if files:
|
|||
|
|
chapter_file = files[0]
|
|||
|
|
result = fixer.fix_chapter(chapter_file)
|
|||
|
|
results.append(result)
|
|||
|
|
print(f"✅ 第{i}章修复完成: {result['length_change']:+d}字符")
|
|||
|
|
else:
|
|||
|
|
print(f"⚠️ 第{i}章文件不存在")
|
|||
|
|
|
|||
|
|
# 生成修复报告
|
|||
|
|
report = {
|
|||
|
|
"timestamp": "2026-03-30T06:29:00+08:00",
|
|||
|
|
"total_chapters_fixed": len(results),
|
|||
|
|
"chapters": results,
|
|||
|
|
"summary": {
|
|||
|
|
"total_original_length": sum(r["original_length"] for r in results),
|
|||
|
|
"total_new_length": sum(r["new_length"] for r in results),
|
|||
|
|
"total_length_change": sum(r["length_change"] for r in results),
|
|||
|
|
"avg_length_increase": sum(r["length_change"] for r in results) / len(results) if results else 0
|
|||
|
|
}
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
report_file = os.path.join(chapters_dir, "batch_fix_report.json")
|
|||
|
|
with open(report_file, 'w', encoding='utf-8') as f:
|
|||
|
|
json.dump(report, f, ensure_ascii=False, indent=2)
|
|||
|
|
|
|||
|
|
print(f"\n=== 批量修复完成 ===")
|
|||
|
|
print(f"修复章节数: {len(results)}")
|
|||
|
|
print(f"总字数变化: {report['summary']['total_length_change']:+d}字符")
|
|||
|
|
print(f"报告文件: {report_file}")
|
|||
|
|
|
|||
|
|
# 建议下一步
|
|||
|
|
print(f"\n🎯 建议下一步:")
|
|||
|
|
print("1. 检查修复后的章节质量")
|
|||
|
|
print("2. 替换原始文件: cp *_fixed.md *.md")
|
|||
|
|
print("3. 重新启动 inkos 使用新配置")
|
|||
|
|
print("4. 监控后续产出质量")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
main()
|