insightflow/auto_fix_code.py

#!/usr/bin/env python3
"""
自动代码修复脚本 - 修复 InsightFlow 项目中的常见问题
"""

import os
import re


def get_python_files(directory):
    """获取目录下所有 Python 文件"""
    python_files = []
    for root, _, files in os.walk(directory):
        for file in files:
            if file.endswith('.py'):
                python_files.append(os.path.join(root, file))
    return python_files


def fix_missing_imports(content, filepath):
    """修复缺失的导入"""
    fixes = []

    # 检查是否使用了 re 但没有导入
    if 're.search(' in content or 're.sub(' in content or 're.match(' in content:
        if 'import re' not in content:
            # 找到合适的位置添加导入
            lines = content.split('\n')
            import_idx = 0
            for i, line in enumerate(lines):
                if line.startswith('import ') or line.startswith('from '):
                    import_idx = i + 1
            lines.insert(import_idx, 'import re')
            content = '\n'.join(lines)
            fixes.append("添加缺失的 'import re'")

    # 检查是否使用了 csv 但没有导入
    if 'csv.' in content and 'import csv' not in content:
        lines = content.split('\n')
        import_idx = 0
        for i, line in enumerate(lines):
            if line.startswith('import ') or line.startswith('from '):
                import_idx = i + 1
        lines.insert(import_idx, 'import csv')
        content = '\n'.join(lines)
        fixes.append("添加缺失的 'import csv'")

    # 检查是否使用了 urllib 但没有导入
    if 'urllib.' in content and 'import urllib' not in content:
        lines = content.split('\n')
        import_idx = 0
        for i, line in enumerate(lines):
            if line.startswith('import ') or line.startswith('from '):
                import_idx = i + 1
        lines.insert(import_idx, 'import urllib.parse')
        content = '\n'.join(lines)
        fixes.append("添加缺失的 'import urllib.parse'")

    return content, fixes


def fix_bare_excepts(content):
    """修复裸异常捕获"""
    fixes = []

    # 替换裸 except:
    bare_except_pattern = r'except\s*:\s*$'
    lines = content.split('\n')
    new_lines = []
    for line in lines:
        if re.match(bare_except_pattern, line.strip()):
            # 缩进保持一致
            indent = len(line) - len(line.lstrip())
            new_line = ' ' * indent + 'except Exception:'
            new_lines.append(new_line)
            fixes.append(f"修复裸异常捕获: {line.strip()}")
        else:
            new_lines.append(line)

    content = '\n'.join(new_lines)
    return content, fixes


def fix_unused_imports(content):
    """修复未使用的导入 - 简单版本"""
    fixes = []

    # 查找导入语句
    import_pattern = r'^from\s+(\S+)\s+import\s+(.+)$'
    lines = content.split('\n')
    new_lines = []

    for line in lines:
        match = re.match(import_pattern, line)
        if match:
            module = match.group(1)
            imports = match.group(2)

            # 检查每个导入是否被使用
            imported_items = [i.strip() for i in imports.split(',')]
            used_items = []

            for item in imported_items:
                # 简单的使用检查
                item_name = item.split(' as ')[-1].strip() if ' as ' in item else item.strip()
                if item_name in content.replace(line, ''):
                    used_items.append(item)
                else:
                    fixes.append(f"移除未使用的导入: {item}")

            if used_items:
                new_lines.append(f"from {module} import {', '.join(used_items)}")
            else:
                fixes.append(f"移除整行导入: {line.strip()}")
        else:
            new_lines.append(line)

    content = '\n'.join(new_lines)
    return content, fixes


def fix_string_formatting(content):
    """统一字符串格式化为 f-string"""
    fixes = []

    # 修复 .format() 调用
    format_pattern = r'["\']([^"\']*)\{([^}]+)\}[^"\']*["\']\.format\(([^)]+)\)'

    def replace_format(match):
        template = match.group(1) + '{' + match.group(2) + '}'
        # 简单替换，实际可能需要更复杂的处理
        return f'f"{template}"'

    new_content = re.sub(format_pattern, replace_format, content)
    if new_content != content:
        fixes.append("统一字符串格式化为 f-string")
        content = new_content

    return content, fixes


def fix_pep8_formatting(content):
    """修复 PEP8 格式问题"""
    fixes = []
    lines = content.split('\n')
    new_lines = []

    for line in lines:
        original = line
        # 修复 E221: multiple spaces before operator
        line = re.sub(r'(\w+)\s{2,}=\s', r'\1 = ', line)
        # 修复 E251: unexpected spaces around keyword / parameter equals
        line = re.sub(r'(\w+)\s*=\s{2,}', r'\1 = ', line)
        line = re.sub(r'(\w+)\s{2,}=\s*', r'\1 = ', line)

        if line != original:
            fixes.append(f"修复 PEP8 格式: {original.strip()[:50]}")

        new_lines.append(line)

    content = '\n'.join(new_lines)
    return content, fixes


def fix_file(filepath):
    """修复单个文件"""
    print(f"\n处理文件: {filepath}")

    try:
        with open(filepath, encoding='utf-8') as f:
            content = f.read()
    except Exception as e:
        print(f"  无法读取文件: {e}")
        return []

    original_content = content
    all_fixes = []

    # 应用各种修复
    content, fixes = fix_missing_imports(content, filepath)
    all_fixes.extend(fixes)

    content, fixes = fix_bare_excepts(content)
    all_fixes.extend(fixes)

    content, fixes = fix_pep8_formatting(content)
    all_fixes.extend(fixes)

    # 保存修改
    if content != original_content:
        try:
            with open(filepath, 'w', encoding='utf-8') as f:
                f.write(content)
            print(f"  已修复 {len(all_fixes)} 个问题")
            for fix in all_fixes[:5]:  # 只显示前5个
                print(f"    - {fix}")
            if len(all_fixes) > 5:
                print(f"    ... 还有 {len(all_fixes) - 5} 个修复")
        except Exception as e:
            print(f"  保存文件失败: {e}")
    else:
        print("  无需修复")

    return all_fixes


def main():
    """主函数"""
    base_dir = '/root/.openclaw/workspace/projects/insightflow'
    backend_dir = os.path.join(base_dir, 'backend')

    print("=" * 60)
    print("InsightFlow 代码自动修复工具")
    print("=" * 60)

    # 获取所有 Python 文件
    files = get_python_files(backend_dir)
    print(f"\n找到 {len(files)} 个 Python 文件")

    total_fixes = 0
    fixed_files = 0

    for filepath in files:
        fixes = fix_file(filepath)
        if fixes:
            total_fixes += len(fixes)
            fixed_files += 1

    print("\n" + "=" * 60)
    print(f"修复完成: {fixed_files} 个文件, {total_fixes} 个问题")
    print("=" * 60)


if __name__ == '__main__':
    main()