UTF-8 文件编码转换工具（原地覆盖）

convert_to_utf8_interactive.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import os
import chardet

def detect_encoding(file_path):
    """检测文件编码"""
    with open(file_path, 'rb') as f:
        raw_data = f.read()
        result = chardet.detect(raw_data)
        return result['encoding']

def convert_file_inplace(file_path):
    """将文件原地转换为 UTF-8（覆盖原文件）"""
    encoding = detect_encoding(file_path)
    print(f"正在处理: {file_path} (检测编码: {encoding})")

    # 如果已经是 UTF-8 或 UTF-8 with BOM，跳过
    if encoding in ['utf-8', 'utf-8-sig']:
        print(f"✅ 已是 UTF-8 编码，跳过: {file_path}")
        return False

    try:
        # 读取原文件（使用检测到的编码）
        with open(file_path, 'r', encoding=encoding) as f:
            content = f.read()

        # 写回原文件，使用 UTF-8 编码（无 BOM）
        with open(file_path, 'w', encoding='utf-8') as f:
            f.write(content)

        print(f"✅ 已覆盖保存为 UTF-8: {file_path}")
        return True

    except Exception as e:
        print(f"❌ 转换失败 {file_path}: {e}")
        return False

def process_directory(root_dir):
    """处理指定目录下的所有支持文件，直接覆盖"""
    supported_extensions = {
        '.c', '.cpp', '.h', '.hpp', '.txt', '.py', '.js', '.html', '.xml', '.json',
        '.rc', '.def', '.inc', '.s', '.asm', '.m', '.mm'  # 常见 C/C++/资源文件
    }

    total_converted = 0
    total_skipped = 0

    for dirpath, _, filenames in os.walk(root_dir):
        for filename in filenames:
            ext = os.path.splitext(filename)[1].lower()

            if ext not in supported_extensions:
                continue

            # 跳过隐藏文件或临时文件
            if filename.startswith('.') or filename.startswith('~'):
                continue

            file_path = os.path.join(dirpath, filename)

            if convert_file_inplace(file_path):
                total_converted += 1
            else:
                total_skipped += 1

    print(f"\n🎉 处理完成！共处理 {total_converted + total_skipped} 个文件")
    print(f"✅ 成功转换（覆盖）: {total_converted} 个文件")
    print(f"❌ 跳过或失败: {total_skipped} 个文件")

def main():
    print("🚀 UTF-8 文件编码转换工具（原地覆盖）")
    print("📌 本工具将自动检测并转换非 UTF-8 编码文件为 UTF-8 格式")
    print("📌 中文内容将保持不乱码")
    print("-" * 60)

    # 获取用户输入路径
    while True:
        path = input("📁 请输入要处理的项目根目录路径（支持中文）: ").strip()
        if not path:
            print("❌ 路径不能为空，请重新输入。")
            continue
        if os.path.exists(path):
            break
        else:
            print(f"❌ 路径不存在: {path}")
            continue

    # 检查是否为目录
    if not os.path.isdir(path):
        print(f"❌ 输入的不是目录: {path}")
        exit(1)

    print(f"\n🔍 开始扫描并转换目录: {path}")
    process_directory(path)
    print("\n✨ 所有文件已处理完毕，原文件已覆盖为 UTF-8 格式。")

if __name__ == "__main__":
    main()