Files
my-vault/.scripts/rename-chinese-to-english.py
T

409 lines
14 KiB
Python
Raw Normal View History

2026-01-05 14:26:17 +08:00
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
中文文件/目录名重命名为英文
功能:
1. 扫描所有中文文件和目录
2. 生成英文重命名映射表
3. 执行重命名
4. 更新所有引用链接
"""
import os
import re
import csv
import argparse
from pathlib import Path
from typing import List, Dict, Tuple
# 中文到英文的翻译字典
TRANSLATION_DICT = {
# 项目相关
"广汽": "GAC",
"物联网AIOT": "AIoT",
"物联网": "IoT",
"AIOT": "AIoT",
"自动驾驶": "Autonomous-Driving",
"从化应急": "Conghua-Emergency",
"公文交换": "Document-Exchange",
"商务局": "Commerce-Bureau",
"市发改委": "Municipal-Development-Reform",
"虚拟数据中心": "Virtual-Data-Center",
"增城区": "Zengcheng-District",
"番禺区": "Panyu-District",
"工信": "Industry-Info",
"道路秩序": "Road-Order",
"南电": "CSG",
"南方电网": "China-Southern-Grid",
# 文件夹名称
"城中村": "Urban-Village",
"番禺城中村": "Panyu-Urban-Village",
"番禺公文": "Panyu-Document",
"番禺信用": "Panyu-Credit",
"番禺住建": "Panyu-Housing",
"公文": "Document",
"信用": "Credit",
"住建": "Housing",
"增城区信息化项目管理系统": "Zengcheng-IT-Project-Mgmt",
# 文件名关键词
"不明确的问题": "Unclear-Issues",
"培训记录整理": "Training-Records",
"设备添加": "Device-Addition",
"测试环境": "Test-Environment",
"维护": "Maintenance",
"数据流向": "Data-Flow",
"系统架构": "System-Architecture",
"登陆": "Login",
"配置": "Configuration",
"问题处理": "Issue-Handling",
"处理": "Handling",
"升级": "Upgrade",
"漏洞处理": "Vulnerability-Fix",
"达梦": "DM-Database",
"等保问题描述": "Security-Issues",
"等保修复": "Security-Fixes",
"基线": "Baseline",
"重建主节点": "Rebuild-Master-Node",
"设备电源": "Device-Power",
"智谱清言": "ChatGLM",
"热点升级": "Hotspot-Upgrade",
"自行车": "Bicycle",
"酸黄瓜制作": "Pickled-Cucumber-Recipe",
"酸黄瓜": "Pickled-Cucumber",
"文明": "Civilization",
"摩托罗拉": "Motorola",
"产出": "Deliverables",
"架构目标": "Architecture-Goals",
"决策方法": "Decision-Methods",
"系统架构分析员知识体系": "SA-Knowledge-System",
"芹菜炒牛肉": "Celery-Beef-Stir-Fry",
"图片生成提示词模板": "Image-Prompt-Template",
"在非原生ESIM设备上申请Giffgaff ESIM": "Apply-Giffgaff-ESIM-on-Non-Native-Device",
# 网页剪藏常用词
"联想移动互联及数字家庭产品服务支持": "Lenovo-Support",
"节点访问局域网服务器的配置方法": "LAN-Server-Access-Config",
"边界路由器配置": "Border-Router-Config",
"树莓派": "Raspberry-Pi",
"机场推荐": "VPN-Recommendations",
"机场评测": "VPN-Reviews",
"软件供应商手册": "Software-Vendor-Handbook",
"解读": "Interpretation",
"关于": "About",
"软件物料清单": "SBOM",
"如何": "How-to",
"教程": "Tutorial",
"博客": "Blog",
"技术文档": "Technical-Docs",
"学习笔记": "Learning-Notes",
"使用攻略": "Guide",
"安装": "Installation",
"配置": "Config",
"实现": "Implementation",
"什麼是": "What-is",
"軟體物料清單": "SBOM",
"網路安全解決方案": "Network-Security",
"艾索科技": "AISEC",
"作为旁路网关": "Bypass-Gateway",
"不是旁路由": "",
"单臂路由": "",
"的终极设置方法": "Ultimate-Setup",
"破解迷思": "Debunking-Myths",
"少数派": "sspai",
"麒麟": "Kylin",
"离线安装": "Offline-Installation",
"报文简介": "Message-Intro",
"公开镜像仓库未授权访问": "Public-Registry-Unauth",
"数据库从": "DB-Migration-from",
"迁移到": "to",
"综合讨论区": "Discussion",
"瀚思彼岸": "HASSBIAN",
"智能家居技术论坛": "Smart-Home-Forum",
"雾凇拼音": "Rime-Ice",
"长期维护的简体词库": "Simplified-Dict",
"中国申请": "China-Application",
"中国区免费": "China-Free",
"年使用攻略": "Year-Guide",
"云": "Cloud",
"详细": "Detailed",
"注册申请图文教程": "Registration-Tutorial",
"整合": "Integration",
"软件开发实施": "Software-Dev",
"广州尚鹏": "Guangzhou-SP",
"服装生鲜家具外贸供应链开源": "Supply-Chain",
"专业实施": "Pro-Impl",
"学习经验": "Learning-Experience",
"安装和打包": "Installation-Packaging",
"权限校验": "Permission-Validation",
"官网": "Official",
"学习笔记": "Learning-Notes",
"应用": "Application",
"部署": "Deployment",
"单实例数据库": "Single-Instance-DB",
"的工作学习笔记": "Work-Notes",
"集成": "Integration",
"国内镜像源列表": "China-Mirror-List",
"亲测可用": "Tested",
"技术文档": "Tech-Docs",
"安装前准备": "Pre-Installation",
"配置实例": "Config-Instance",
"数据库安装": "DB-Installation",
"技术我的一些": "My",
}
def has_chinese(text: str) -> bool:
"""检查文本是否包含中文"""
return bool(re.search(r'[\u4e00-\u9fa5]', text))
def translate_chinese(text: str, max_length: int = 50) -> str:
"""将中文翻译为英文"""
result = text
# 按长度排序,优先匹配长词组
sorted_dict = sorted(TRANSLATION_DICT.items(), key=lambda x: len(x[0]), reverse=True)
for chinese, english in sorted_dict:
result = result.replace(chinese, english)
# 移除剩余的中文(如果翻译不完整,保留拼音或删除)
result = re.sub(r'[\u4e00-\u9fa5]+', '-', result)
# 清理特殊字符
result = re.sub(r'[\u3000-\u303f\uff00-\uffef\s]+', '-', result)
result = re.sub(r'[<>:"/\\|?*]+', '-', result)
result = re.sub(r'-+', '-', result)
result = result.strip('-')
# 控制长度
if len(result) > max_length:
result = result[:max_length].rstrip('-')
return result
def scan_chinese_files_and_dirs(root_dir: Path) -> Tuple[List[Path], List[Path]]:
"""扫描所有包含中文的文件和目录"""
chinese_files = []
chinese_dirs = []
# 排除的目录
exclude_dirs = {'.git', '.obsidian', '.smart-env', 'node_modules'}
for item in root_dir.rglob('*'):
# 跳过排除的目录
if any(excl in item.parts for excl in exclude_dirs):
continue
if has_chinese(item.name):
if item.is_file():
chinese_files.append(item)
elif item.is_dir():
chinese_dirs.append(item)
# 目录按深度排序(深的在前,避免父目录先改名)
chinese_dirs.sort(key=lambda p: len(p.parts), reverse=True)
return chinese_files, chinese_dirs
def generate_mappings(files: List[Path], dirs: List[Path], root_dir: Path, max_length: int = 50) -> List[Dict]:
"""生成重命名映射"""
mappings = []
# 处理目录
for dir_path in dirs:
old_name = dir_path.name
new_name = translate_chinese(old_name, max_length)
rel_path = dir_path.relative_to(root_dir)
new_path = dir_path.parent / new_name
new_rel_path = new_path.relative_to(root_dir)
mappings.append({
'type': 'Directory',
'old_path': str(rel_path),
'new_path': str(new_rel_path),
'old_name': old_name,
'new_name': new_name,
'abs_old_path': str(dir_path),
'abs_new_path': str(new_path)
})
# 处理文件
for file_path in files:
old_name = file_path.name
stem = file_path.stem
suffix = file_path.suffix
new_stem = translate_chinese(stem, max_length - len(suffix))
new_name = new_stem + suffix
rel_path = file_path.relative_to(root_dir)
new_path = file_path.parent / new_name
new_rel_path = new_path.relative_to(root_dir)
mappings.append({
'type': 'File',
'old_path': str(rel_path),
'new_path': str(new_rel_path),
'old_name': old_name,
'new_name': new_name,
'abs_old_path': str(file_path),
'abs_new_path': str(new_path)
})
return mappings
def save_mappings(mappings: List[Dict], output_file: Path):
"""保存映射表到CSV"""
with open(output_file, 'w', encoding='utf-8', newline='') as f:
writer = csv.DictWriter(f, fieldnames=['type', 'old_path', 'new_path', 'old_name', 'new_name'])
writer.writeheader()
for mapping in mappings:
writer.writerow({
'type': mapping['type'],
'old_path': mapping['old_path'],
'new_path': mapping['new_path'],
'old_name': mapping['old_name'],
'new_name': mapping['new_name']
})
def execute_rename(mappings: List[Dict]) -> Tuple[int, int]:
"""执行重命名"""
renamed = 0
failed = 0
for mapping in mappings:
try:
old_path = Path(mapping['abs_old_path'])
new_path = Path(mapping['abs_new_path'])
if old_path.exists():
old_path.rename(new_path)
print(f"[+] {mapping['type']}: {mapping['old_name']} -> {mapping['new_name']}")
renamed += 1
else:
print(f"[!] Skip (not exist): {mapping['old_path']}")
except Exception as e:
print(f"[-] Failed: {mapping['old_path']} - {e}")
failed += 1
return renamed, failed
def update_markdown_links(root_dir: Path, mappings: List[Dict]) -> int:
"""更新 Markdown 文件中的链接"""
updated_count = 0
md_files = list(root_dir.rglob('*.md'))
# 排除某些目录
exclude_dirs = {'.git', '.obsidian', '.smart-env'}
md_files = [f for f in md_files if not any(excl in f.parts for excl in exclude_dirs)]
for md_file in md_files:
try:
content = md_file.read_text(encoding='utf-8')
original_content = content
# 更新 Wiki 链接 [[中文名]]
for mapping in mappings:
if mapping['type'] == 'File':
old_stem = Path(mapping['old_name']).stem
new_stem = Path(mapping['new_name']).stem
# Wiki 链接
content = re.sub(
rf'\[\[{re.escape(old_stem)}\]\]',
f'[[{new_stem}]]',
content
)
# 相对路径链接
old_path_escaped = re.escape(mapping['old_path'].replace('\\', '/'))
new_path_fixed = mapping['new_path'].replace('\\', '/')
content = re.sub(old_path_escaped, new_path_fixed, content)
if content != original_content:
md_file.write_text(content, encoding='utf-8')
rel_path = md_file.relative_to(root_dir)
print(f"[+] Updated: {rel_path}")
updated_count += 1
except Exception as e:
print(f"[-] Update failed: {md_file} - {e}")
return updated_count
def main():
parser = argparse.ArgumentParser(description='中文文件名重命名为英文')
parser.add_argument('--execute', action='store_true', help='执行重命名(默认为预览模式)')
parser.add_argument('--max-length', type=int, default=50, help='文件名最大长度(默认50')
args = parser.parse_args()
root_dir = Path.cwd()
mapping_file = root_dir / 'chinese-to-english-mapping.csv'
print("=== Chinese to English Rename Tool ===\n")
if args.execute:
print("[!] EXECUTE MODE: Will rename files and update links")
else:
print("[i] PREVIEW MODE: Generate mapping only, no actual rename")
print(" Use --execute to perform actual rename")
print()
# Scan
print("[*] Scanning Chinese files and directories...")
chinese_files, chinese_dirs = scan_chinese_files_and_dirs(root_dir)
print(f" Found {len(chinese_files)} Chinese files")
print(f" Found {len(chinese_dirs)} Chinese directories\n")
# Generate mappings
print("[*] Generating rename mappings...")
mappings = generate_mappings(chinese_files, chinese_dirs, root_dir, args.max_length)
save_mappings(mappings, mapping_file)
print(f" [+] Mapping saved to: {mapping_file}")
print(f" [+] Total {len(mappings)} rename tasks\n")
# Preview
print("[*] Rename Preview (first 20):")
print(f"{'Type':<10} {'Old Name':<40} {'New Name':<40}")
print("-" * 90)
for mapping in mappings[:20]:
print(f"{mapping['type']:<10} {mapping['old_name']:<40} {mapping['new_name']:<40}")
if len(mappings) > 20:
print(f"\n ... and {len(mappings) - 20} more (see full list: {mapping_file})")
print()
# Execute rename
if args.execute:
print("[*] Starting rename...")
renamed, failed = execute_rename(mappings)
print(f"\n[*] Rename complete!")
print(f" Success: {renamed}")
print(f" Failed: {failed}\n")
# Update links
print("[*] Updating Markdown links...")
updated_count = update_markdown_links(root_dir, mappings)
print(f"\n[*] Link update complete! Updated {updated_count} files\n")
else:
print("[i] Next steps:")
print(f" 1. Review mapping: {mapping_file}")
print(f" 2. If OK, run: python .scripts/rename-chinese-to-english.py --execute\n")
print("[+] Done!")
if __name__ == '__main__':
main()