解析与分析Python源码

import ast

class CodeAnalyzer(ast.NodeVisitor):
    def __init__(self):
        self.loaded = set()
        self.stored = set()
        self.deleted = set()

    def visit_Name(self, node):
        if isinstance(node.ctx, ast.Load):
            self.loaded.add(node.id)
        elif isinstance(node.ctx, ast.Store):
            self.stored.add(node.id)
        elif isinstance(node.ctx, ast.Del):
            self.deleted.add(node.id)

# Sample usage
if __name__ == '__main__':
    # Some Python code
    code = '''
    for i in range(10):
        print(i)
    del i
    '''

    # Parse into an AST
    top = ast.parse(code, mode='exec')

    # Feed the AST to analyze name usage
    c = CodeAnalyzer()
    c.visit(top)
    print('Loaded:', c.loaded)
    print('Stored:', c.stored)
    print('Deleted:', c.deleted)

如果你运行这个程序，你会得到下面这样的输出：

Loaded: {'i', 'range', 'print'}
Stored: {'i'}
Deleted: {'i'}

最后，AST可以通过 compile() 函数来编译并执行。例如：

>>> exec(compile(top,'<stdin>', 'exec'))

大部分程序员知道Python能够计算或执行字符串形式的源代码。例如：

>>> x = 42
>>> eval('2 + 3*4 + x')
56
>>> exec('for i in range(10): print(i)')
0
1
2
3
4
5
6
7
8
9
>>>
尽管如此，ast 模块能被用来将Python源码编译成一个可被分析的抽象语法树（AST）。例如：

>>> import ast
>>> ex = ast.parse('2 + 3*4 + x', mode='eval')
>>> ex
<_ast.Expression object at 0x1007473d0>
>>> ast.dump(ex)
"Expression(body=BinOp(left=BinOp(left=Num(n=2), op=Add(),
right=BinOp(left=Num(n=3), op=Mult(), right=Num(n=4))), op=Add(),
right=Name(id='x', ctx=Load())))"

>>> top = ast.parse('for i in range(10): print(i)', mode='exec')
>>> top
<_ast.Module object at 0x100747390>
>>> ast.dump(top)
"Module(body=[For(target=Name(id='i', ctx=Store()),
iter=Call(func=Name(id='range', ctx=Load()), args=[Num(n=10)],
keywords=[], starargs=None, kwargs=None),
body=[Expr(value=Call(func=Name(id='print', ctx=Load()),
args=[Name(id='i', ctx=Load())], keywords=[], starargs=None,
kwargs=None))], orelse=[])])"
>>>
分析源码树需要你自己更多的学习，它是由一系列AST节点组成的。 分析这些节点最简单的方法就是定义一个访问者类，实现很多 visit_NodeName() 方法， NodeName() 匹配那些你感兴趣的节点。下面是这样一个类，记录了哪些名字被加载、存储和删除的信息。

import ast

class CodeAnalyzer(ast.NodeVisitor):
    def __init__(self):
        self.loaded = set()
        self.stored = set()
        self.deleted = set()

    def visit_Name(self, node):
        if isinstance(node.ctx, ast.Load):
            self.loaded.add(node.id)
        elif isinstance(node.ctx, ast.Store):
            self.stored.add(node.id)
        elif isinstance(node.ctx, ast.Del):
            self.deleted.add(node.id)

# Sample usage
if __name__ == '__main__':
    # Some Python code
    code = '''
    for i in range(10):
        print(i)
    del i
    '''

    # Parse into an AST
    top = ast.parse(code, mode='exec')

    # Feed the AST to analyze name usage
    c = CodeAnalyzer()
    c.visit(top)
    print('Loaded:', c.loaded)
    print('Stored:', c.stored)
    print('Deleted:', c.deleted)
如果你运行这个程序，你会得到下面这样的输出：

Loaded: {'i', 'range', 'print'}
Stored: {'i'}
Deleted: {'i'}
最后，AST可以通过 compile() 函数来编译并执行。例如：

>>> exec(compile(top,'<stdin>', 'exec'))
0
1
2
3
4
5
6
7
8
9
>>>