项目理解skill-v1

codebase_architecture_analyzer_v1/scripts/extract_dependencies.py

@@ -0,0 +1,167 @@
+#!/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()