diff options
author | Georg Brandl <georg@python.org> | 2008-06-10 07:45:28 (GMT) |
---|---|---|
committer | Georg Brandl <georg@python.org> | 2008-06-10 07:45:28 (GMT) |
commit | 8509db5a21abc43086a0b9f6727a89f25ac7d2eb (patch) | |
tree | adce5bbb0264cb1c5ca6ac5f120c503b708ff32b /Lib | |
parent | df7036d2fac9cb6b6f79bed2b2e0fbe9166f2e5f (diff) | |
download | cpython-8509db5a21abc43086a0b9f6727a89f25ac7d2eb.zip cpython-8509db5a21abc43086a0b9f6727a89f25ac7d2eb.tar.gz cpython-8509db5a21abc43086a0b9f6727a89f25ac7d2eb.tar.bz2 |
Add the "ast" module, containing helpers to ease use of the "_ast" classes.
Diffstat (limited to 'Lib')
-rw-r--r-- | Lib/ast.py | 300 | ||||
-rw-r--r-- | Lib/test/test_ast.py | 109 |
2 files changed, 400 insertions, 9 deletions
diff --git a/Lib/ast.py b/Lib/ast.py new file mode 100644 index 0000000..cc4a4b8 --- /dev/null +++ b/Lib/ast.py @@ -0,0 +1,300 @@ +# -*- coding: utf-8 -*- +""" + ast + ~~~ + + The `ast` module helps Python applications to process trees of the Python + abstract syntax grammar. The abstract syntax itself might change with + each Python release; this module helps to find out programmatically what + the current grammar looks like and allows modifications of it. + + An abstract syntax tree can be generated by passing `ast.PyCF_ONLY_AST` as + a flag to the `compile()` builtin function or by using the `parse()` + function from this module. The result will be a tree of objects whose + classes all inherit from `ast.AST`. + + A modified abstract syntax tree can be compiled into a Python code object + using the built-in `compile()` function. + + Additionally various helper functions are provided that make working with + the trees simpler. The main intention of the helper functions and this + module in general is to provide an easy to use interface for libraries + that work tightly with the python syntax (template engines for example). + + + :copyright: Copyright 2008 by Armin Ronacher. + :license: Python License. +""" +from _ast import * + + +def parse(expr, filename='<unknown>', mode='exec'): + """ + Parse an expression into an AST node. + Equivalent to compile(expr, filename, mode, PyCF_ONLY_AST). + """ + return compile(expr, filename, mode, PyCF_ONLY_AST) + + +def literal_eval(node_or_string): + """ + Safely evaluate an expression node or a string containing a Python + expression. The string or node provided may only consist of the following + Python literal structures: strings, numbers, tuples, lists, dicts, booleans, + and None. + """ + _safe_names = {'None': None, 'True': True, 'False': False} + if isinstance(node_or_string, basestring): + node_or_string = parse(node_or_string, mode='eval') + if isinstance(node_or_string, Expression): + node_or_string = node_or_string.body + def _convert(node): + if isinstance(node, Str): + return node.s + elif isinstance(node, Num): + return node.n + elif isinstance(node, Tuple): + return tuple(map(_convert, node.elts)) + elif isinstance(node, List): + return list(map(_convert, node.elts)) + elif isinstance(node, Dict): + return dict((_convert(k), _convert(v)) for k, v + in zip(node.keys, node.values)) + elif isinstance(node, Name): + if node.id in _safe_names: + return _safe_names[node.id] + raise ValueError('malformed string') + return _convert(node_or_string) + + +def dump(node, annotate_fields=True, include_attributes=False): + """ + Return a formatted dump of the tree in *node*. This is mainly useful for + debugging purposes. The returned string will show the names and the values + for fields. This makes the code impossible to evaluate, so if evaluation is + wanted *annotate_fields* must be set to False. Attributes such as line + numbers and column offsets are dumped by default. If this is wanted, + *include_attributes* can be set to True. + """ + def _format(node): + if isinstance(node, AST): + fields = [(a, _format(b)) for a, b in iter_fields(node)] + rv = '%s(%s' % (node.__class__.__name__, ', '.join( + ('%s=%s' % field for field in fields) + if annotate_fields else + (b for a, b in fields) + )) + if include_attributes and node._attributes: + rv += fields and ', ' or ' ' + rv += ', '.join('%s=%s' % (a, _format(getattr(node, a))) + for a in node._attributes) + return rv + ')' + elif isinstance(node, list): + return '[%s]' % ', '.join(_format(x) for x in node) + return repr(node) + if not isinstance(node, AST): + raise TypeError('expected AST, got %r' % node.__class__.__name__) + return _format(node) + + +def copy_location(new_node, old_node): + """ + Copy source location (`lineno` and `col_offset` attributes) from + *old_node* to *new_node* if possible, and return *new_node*. + """ + for attr in 'lineno', 'col_offset': + if attr in old_node._attributes and attr in new_node._attributes \ + and hasattr(old_node, attr): + setattr(new_node, attr, getattr(old_node, attr)) + return new_node + + +def fix_missing_locations(node): + """ + When you compile a node tree with compile(), the compiler expects lineno and + col_offset attributes for every node that supports them. This is rather + tedious to fill in for generated nodes, so this helper adds these attributes + recursively where not already set, by setting them to the values of the + parent node. It works recursively starting at *node*. + """ + def _fix(node, lineno, col_offset): + if 'lineno' in node._attributes: + if not hasattr(node, 'lineno'): + node.lineno = lineno + else: + lineno = node.lineno + if 'col_offset' in node._attributes: + if not hasattr(node, 'col_offset'): + node.col_offset = col_offset + else: + col_offset = node.col_offset + for child in iter_child_nodes(node): + _fix(child, lineno, col_offset) + _fix(node, 1, 0) + return node + + +def increment_lineno(node, n=1): + """ + Increment the line number of each node in the tree starting at *node* by *n*. + This is useful to "move code" to a different location in a file. + """ + if 'lineno' in node._attributes: + node.lineno = getattr(node, 'lineno', 0) + n + for child in walk(node): + if 'lineno' in child._attributes: + child.lineno = getattr(child, 'lineno', 0) + n + return node + + +def iter_fields(node): + """ + Yield a tuple of ``(fieldname, value)`` for each field in ``node._fields`` + that is present on *node*. + """ + for field in node._fields: + try: + yield field, getattr(node, field) + except AttributeError: + pass + + +def iter_child_nodes(node): + """ + Yield all direct child nodes of *node*, that is, all fields that are nodes + and all items of fields that are lists of nodes. + """ + for name, field in iter_fields(node): + if isinstance(field, AST): + yield field + elif isinstance(field, list): + for item in field: + if isinstance(item, AST): + yield item + + +def get_docstring(node, clean=True): + """ + Return the docstring for the given node or None if no docstring can + be found. If the node provided does not have docstrings a TypeError + will be raised. + """ + if not isinstance(node, (FunctionDef, ClassDef, Module)): + raise TypeError("%r can't have docstrings" % node.__class__.__name__) + if node.body and isinstance(node.body[0], Expr) and \ + isinstance(node.body[0].value, Str): + if clean: + import inspect + return inspect.cleandoc(node.body[0].value.s) + return node.body[0].value.s + + +def walk(node): + """ + Recursively yield all child nodes of *node*, in no specified order. This is + useful if you only want to modify nodes in place and don't care about the + context. + """ + from collections import deque + todo = deque([node]) + while todo: + node = todo.popleft() + todo.extend(iter_child_nodes(node)) + yield node + + +class NodeVisitor(object): + """ + A node visitor base class that walks the abstract syntax tree and calls a + visitor function for every node found. This function may return a value + which is forwarded by the `visit` method. + + This class is meant to be subclassed, with the subclass adding visitor + methods. + + Per default the visitor functions for the nodes are ``'visit_'`` + + class name of the node. So a `TryFinally` node visit function would + be `visit_TryFinally`. This behavior can be changed by overriding + the `visit` method. If no visitor function exists for a node + (return value `None`) the `generic_visit` visitor is used instead. + + Don't use the `NodeVisitor` if you want to apply changes to nodes during + traversing. For this a special visitor exists (`NodeTransformer`) that + allows modifications. + """ + + def visit(self, node): + """Visit a node.""" + method = 'visit_' + node.__class__.__name__ + visitor = getattr(self, method, self.generic_visit) + return visitor(node) + + def generic_visit(self, node): + """Called if no explicit visitor function exists for a node.""" + for field, value in iter_fields(node): + if isinstance(value, list): + for item in value: + if isinstance(item, AST): + self.visit(item) + elif isinstance(value, AST): + self.visit(value) + + +class NodeTransformer(NodeVisitor): + """ + A :class:`NodeVisitor` subclass that walks the abstract syntax tree and + allows modification of nodes. + + The `NodeTransformer` will walk the AST and use the return value of the + visitor methods to replace or remove the old node. If the return value of + the visitor method is ``None``, the node will be removed from its location, + otherwise it is replaced with the return value. The return value may be the + original node in which case no replacement takes place. + + Here is an example transformer that rewrites all occurrences of name lookups + (``foo``) to ``data['foo']``:: + + class RewriteName(NodeTransformer): + + def visit_Name(self, node): + return copy_location(Subscript( + value=Name(id='data', ctx=Load()), + slice=Index(value=Str(s=node.id)), + ctx=node.ctx + ), node) + + Keep in mind that if the node you're operating on has child nodes you must + either transform the child nodes yourself or call the :meth:`generic_visit` + method for the node first. + + For nodes that were part of a collection of statements (that applies to all + statement nodes), the visitor may also return a list of nodes rather than + just a single node. + + Usually you use the transformer like this:: + + node = YourTransformer().visit(node) + """ + + def generic_visit(self, node): + for field, old_value in iter_fields(node): + old_value = getattr(node, field, None) + if isinstance(old_value, list): + new_values = [] + for value in old_value: + if isinstance(value, AST): + value = self.visit(value) + if value is None: + continue + elif not isinstance(value, AST): + new_values.extend(value) + continue + new_values.append(value) + old_value[:] = new_values + elif isinstance(old_value, AST): + new_node = self.visit(old_value) + if new_node is None: + delattr(node, field) + else: + setattr(node, field, new_node) + return node diff --git a/Lib/test/test_ast.py b/Lib/test/test_ast.py index 9d2bd66..00a5aae 100644 --- a/Lib/test/test_ast.py +++ b/Lib/test/test_ast.py @@ -1,6 +1,6 @@ import sys, itertools, unittest from test import test_support -import _ast +import ast def to_tuple(t): if t is None or isinstance(t, (basestring, int, long, complex)): @@ -123,9 +123,9 @@ eval_tests = [ class AST_Tests(unittest.TestCase): def _assert_order(self, ast_node, parent_pos): - if not isinstance(ast_node, _ast.AST) or ast_node._fields is None: + if not isinstance(ast_node, ast.AST) or ast_node._fields is None: return - if isinstance(ast_node, (_ast.expr, _ast.stmt, _ast.excepthandler)): + if isinstance(ast_node, (ast.expr, ast.stmt, ast.excepthandler)): node_pos = (ast_node.lineno, ast_node.col_offset) self.assert_(node_pos >= parent_pos) parent_pos = (ast_node.lineno, ast_node.col_offset) @@ -142,29 +142,29 @@ class AST_Tests(unittest.TestCase): (single_tests, single_results, "single"), (eval_tests, eval_results, "eval")): for i, o in itertools.izip(input, output): - ast_tree = compile(i, "?", kind, _ast.PyCF_ONLY_AST) + ast_tree = compile(i, "?", kind, ast.PyCF_ONLY_AST) self.assertEquals(to_tuple(ast_tree), o) self._assert_order(ast_tree, (0, 0)) def test_nodeclasses(self): - x = _ast.BinOp(1, 2, 3, lineno=0) + x = ast.BinOp(1, 2, 3, lineno=0) self.assertEquals(x.left, 1) self.assertEquals(x.op, 2) self.assertEquals(x.right, 3) self.assertEquals(x.lineno, 0) # node raises exception when not given enough arguments - self.assertRaises(TypeError, _ast.BinOp, 1, 2) + self.assertRaises(TypeError, ast.BinOp, 1, 2) # can set attributes through kwargs too - x = _ast.BinOp(left=1, op=2, right=3, lineno=0) + x = ast.BinOp(left=1, op=2, right=3, lineno=0) self.assertEquals(x.left, 1) self.assertEquals(x.op, 2) self.assertEquals(x.right, 3) self.assertEquals(x.lineno, 0) # this used to fail because Sub._fields was None - x = _ast.Sub() + x = ast.Sub() def test_pickling(self): import pickle @@ -181,8 +181,99 @@ class AST_Tests(unittest.TestCase): ast2 = mod.loads(mod.dumps(ast, protocol)) self.assertEquals(to_tuple(ast2), to_tuple(ast)) + +class ASTHelpers_Test(unittest.TestCase): + + def test_parse(self): + a = ast.parse('foo(1 + 1)') + b = compile('foo(1 + 1)', '<unknown>', 'exec', ast.PyCF_ONLY_AST) + self.assertEqual(ast.dump(a), ast.dump(b)) + + def test_dump(self): + node = ast.parse('spam(eggs, "and cheese")') + self.assertEqual(ast.dump(node), + "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load()), " + "args=[Name(id='eggs', ctx=Load()), Str(s='and cheese')], " + "keywords=[], starargs=None, kwargs=None))])" + ) + self.assertEqual(ast.dump(node, annotate_fields=False), + "Module([Expr(Call(Name('spam', Load()), [Name('eggs', Load()), " + "Str('and cheese')], [], None, None))])" + ) + self.assertEqual(ast.dump(node, include_attributes=True), + "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load(), " + "lineno=1, col_offset=0), args=[Name(id='eggs', ctx=Load(), " + "lineno=1, col_offset=5), Str(s='and cheese', lineno=1, " + "col_offset=11)], keywords=[], starargs=None, kwargs=None, " + "lineno=1, col_offset=0), lineno=1, col_offset=0)])" + ) + + def test_copy_location(self): + src = ast.parse('1 + 1', mode='eval') + src.body.right = ast.copy_location(ast.Num(2), src.body.right) + self.assertEqual(ast.dump(src, include_attributes=True), + 'Expression(body=BinOp(left=Num(n=1, lineno=1, col_offset=0), ' + 'op=Add(), right=Num(n=2, lineno=1, col_offset=4), lineno=1, ' + 'col_offset=0))' + ) + + def test_fix_missing_locations(self): + src = ast.parse('write("spam")') + src.body.append(ast.Expr(ast.Call(ast.Name('spam', ast.Load()), + [ast.Str('eggs')], [], None, None))) + self.assertEqual(src, ast.fix_missing_locations(src)) + self.assertEqual(ast.dump(src, include_attributes=True), + "Module(body=[Expr(value=Call(func=Name(id='write', ctx=Load(), " + "lineno=1, col_offset=0), args=[Str(s='spam', lineno=1, " + "col_offset=6)], keywords=[], starargs=None, kwargs=None, " + "lineno=1, col_offset=0), lineno=1, col_offset=0), " + "Expr(value=Call(func=Name(id='spam', ctx=Load(), lineno=1, " + "col_offset=0), args=[Str(s='eggs', lineno=1, col_offset=0)], " + "keywords=[], starargs=None, kwargs=None, lineno=1, " + "col_offset=0), lineno=1, col_offset=0)])" + ) + + def test_increment_lineno(self): + src = ast.parse('1 + 1', mode='eval') + self.assertEqual(ast.increment_lineno(src, n=3), src) + self.assertEqual(ast.dump(src, include_attributes=True), + 'Expression(body=BinOp(left=Num(n=1, lineno=4, col_offset=0), ' + 'op=Add(), right=Num(n=1, lineno=4, col_offset=4), lineno=4, ' + 'col_offset=0))' + ) + + def test_iter_fields(self): + node = ast.parse('foo()', mode='eval') + d = dict(ast.iter_fields(node.body)) + self.assertEqual(d.pop('func').id, 'foo') + self.assertEqual(d, {'keywords': [], 'kwargs': None, + 'args': [], 'starargs': None}) + + def test_iter_child_nodes(self): + node = ast.parse("spam(23, 42, eggs='leek')", mode='eval') + self.assertEqual(len(list(ast.iter_child_nodes(node.body))), 4) + iterator = ast.iter_child_nodes(node.body) + self.assertEqual(next(iterator).id, 'spam') + self.assertEqual(next(iterator).n, 23) + self.assertEqual(next(iterator).n, 42) + self.assertEqual(ast.dump(next(iterator)), + "keyword(arg='eggs', value=Str(s='leek'))" + ) + + def test_get_docstring(self): + node = ast.parse('def foo():\n """line one\n line two"""') + self.assertEqual(ast.get_docstring(node.body[0]), + 'line one\nline two') + + def test_literal_eval(self): + self.assertEqual(ast.literal_eval('[1, 2, 3]'), [1, 2, 3]) + self.assertEqual(ast.literal_eval('{"foo": 42}'), {"foo": 42}) + self.assertEqual(ast.literal_eval('(True, False, None)'), (True, False, None)) + self.assertRaises(ValueError, ast.literal_eval, 'foo()') + + def test_main(): - test_support.run_unittest(AST_Tests) + test_support.run_unittest(AST_Tests, ASTHelpers_Test) def main(): if __name__ != '__main__': |