168 lines
5.0 KiB
Python
168 lines
5.0 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
依赖提取脚本
|
|
|
|
用法: python extract_dependencies.py [项目路径]
|
|
|
|
输出: JSON 格式的依赖信息
|
|
"""
|
|
|
|
import ast
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
from typing import Dict, List, Set
|
|
|
|
|
|
def extract_python_imports(file_path: Path) -> Set[str]:
|
|
"""从 Python 文件提取 import"""
|
|
imports = set()
|
|
|
|
try:
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
tree = ast.parse(f.read(), filename=str(file_path))
|
|
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.Import):
|
|
for alias in node.names:
|
|
# 只保留顶层包名
|
|
module = alias.name.split('.')[0]
|
|
imports.add(module)
|
|
|
|
elif isinstance(node, ast.ImportFrom):
|
|
if node.module:
|
|
module = node.module.split('.')[0]
|
|
imports.add(module)
|
|
|
|
except Exception as e:
|
|
print(f"Warning: Failed to parse {file_path}: {e}", file=sys.stderr)
|
|
|
|
return imports
|
|
|
|
|
|
def analyze_python_project(project_path: Path) -> Dict:
|
|
"""分析 Python 项目的依赖"""
|
|
all_imports = set()
|
|
file_count = 0
|
|
|
|
# 遍历所有 Python 文件
|
|
for py_file in project_path.rglob("*.py"):
|
|
# 跳过虚拟环境和 node_modules
|
|
if any(part in py_file.parts for part in ['venv', 'env', '.venv', 'node_modules', '__pycache__']):
|
|
continue
|
|
|
|
file_count += 1
|
|
imports = extract_python_imports(py_file)
|
|
all_imports.update(imports)
|
|
|
|
# 读取声明的依赖
|
|
declared_deps = set()
|
|
|
|
requirements_txt = project_path / "requirements.txt"
|
|
if requirements_txt.exists():
|
|
for line in requirements_txt.read_text(encoding='utf-8').split('\n'):
|
|
line = line.strip()
|
|
if line and not line.startswith('#'):
|
|
# 去掉版本号
|
|
dep = line.split('==')[0].split('>=')[0].split('~=')[0].strip()
|
|
declared_deps.add(dep)
|
|
|
|
pyproject_toml = project_path / "pyproject.toml"
|
|
if pyproject_toml.exists():
|
|
content = pyproject_toml.read_text(encoding='utf-8')
|
|
# 简单提取（不使用 toml 库）
|
|
in_deps = False
|
|
for line in content.split('\n'):
|
|
if '[tool.poetry.dependencies]' in line or '[project.dependencies]' in line:
|
|
in_deps = True
|
|
continue
|
|
if in_deps and line.strip().startswith('['):
|
|
break
|
|
if in_deps and '=' in line:
|
|
dep = line.split('=')[0].strip().strip('"')
|
|
if dep != 'python':
|
|
declared_deps.add(dep)
|
|
|
|
# Python 标准库（部分常见的）
|
|
stdlib = {
|
|
'os', 'sys', 'json', 'time', 'datetime', 'collections', 'itertools',
|
|
'functools', 'pathlib', 're', 'math', 'random', 'typing', 'abc',
|
|
'asyncio', 'logging', 'unittest', 'argparse', 'subprocess', 'io',
|
|
'copy', 'pickle', 'sqlite3', 'http', 'urllib', 'email', 'uuid'
|
|
}
|
|
|
|
# 区分第三方包和标准库
|
|
third_party = all_imports - stdlib
|
|
|
|
return {
|
|
"language": "Python",
|
|
"files_analyzed": file_count,
|
|
"total_imports": len(all_imports),
|
|
"third_party_imports": list(sorted(third_party)),
|
|
"declared_dependencies": list(sorted(declared_deps)),
|
|
"undeclared_usage": list(sorted(third_party - declared_deps)),
|
|
"unused_dependencies": list(sorted(declared_deps - third_party))
|
|
}
|
|
|
|
|
|
def analyze_javascript_project(project_path: Path) -> Dict:
|
|
"""分析 JavaScript 项目的依赖"""
|
|
package_json = project_path / "package.json"
|
|
|
|
if not package_json.exists():
|
|
return None
|
|
|
|
try:
|
|
import json as json_module
|
|
content = json_module.loads(package_json.read_text(encoding='utf-8'))
|
|
|
|
dependencies = content.get("dependencies", {})
|
|
dev_dependencies = content.get("devDependencies", {})
|
|
|
|
return {
|
|
"language": "JavaScript/TypeScript",
|
|
"dependencies": list(dependencies.keys()),
|
|
"dev_dependencies": list(dev_dependencies.keys()),
|
|
"total_dependencies": len(dependencies) + len(dev_dependencies)
|
|
}
|
|
|
|
except Exception as e:
|
|
print(f"Error parsing package.json: {e}", file=sys.stderr)
|
|
return None
|
|
|
|
|
|
def main():
|
|
# 获取项目路径
|
|
if len(sys.argv) > 1:
|
|
project_path = Path(sys.argv[1])
|
|
else:
|
|
project_path = Path.cwd()
|
|
|
|
if not project_path.exists():
|
|
print(f"Error: Path {project_path} does not exist", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
results = []
|
|
|
|
# 分析 Python
|
|
python_result = analyze_python_project(project_path)
|
|
if python_result["files_analyzed"] > 0:
|
|
results.append(python_result)
|
|
|
|
# 分析 JavaScript
|
|
js_result = analyze_javascript_project(project_path)
|
|
if js_result:
|
|
results.append(js_result)
|
|
|
|
# 输出结果
|
|
output = {
|
|
"project_path": str(project_path),
|
|
"analyses": results
|
|
}
|
|
|
|
print(json.dumps(output, indent=2, ensure_ascii=False))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|