123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547 |
- """
- 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(source, filename='<unknown>', mode='exec', *,
- type_comments=False, feature_version=None):
- """
- Parse the source into an AST node.
- Equivalent to compile(source, filename, mode, PyCF_ONLY_AST).
- Pass type_comments=True to get back type comments where the syntax allows.
- """
- flags = PyCF_ONLY_AST
- if type_comments:
- flags |= PyCF_TYPE_COMMENTS
- if isinstance(feature_version, tuple):
- major, minor = feature_version # Should be a 2-tuple.
- assert major == 3
- feature_version = minor
- elif feature_version is None:
- feature_version = -1
- # Else it should be an int giving the minor version for 3.x.
- return compile(source, filename, mode, flags,
- _feature_version=feature_version)
- 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, bytes, numbers, tuples, lists, dicts,
- sets, booleans, and None.
- """
- if isinstance(node_or_string, str):
- node_or_string = parse(node_or_string, mode='eval')
- if isinstance(node_or_string, Expression):
- node_or_string = node_or_string.body
- def _raise_malformed_node(node):
- raise ValueError(f'malformed node or string: {node!r}')
- def _convert_num(node):
- if not isinstance(node, Constant) or type(node.value) not in (int, float, complex):
- _raise_malformed_node(node)
- return node.value
- def _convert_signed_num(node):
- if isinstance(node, UnaryOp) and isinstance(node.op, (UAdd, USub)):
- operand = _convert_num(node.operand)
- if isinstance(node.op, UAdd):
- return + operand
- else:
- return - operand
- return _convert_num(node)
- def _convert(node):
- if isinstance(node, Constant):
- return node.value
- elif isinstance(node, Tuple):
- return tuple(map(_convert, node.elts))
- elif isinstance(node, List):
- return list(map(_convert, node.elts))
- elif isinstance(node, Set):
- return set(map(_convert, node.elts))
- elif isinstance(node, Dict):
- if len(node.keys) != len(node.values):
- _raise_malformed_node(node)
- return dict(zip(map(_convert, node.keys),
- map(_convert, node.values)))
- elif isinstance(node, BinOp) and isinstance(node.op, (Add, Sub)):
- left = _convert_signed_num(node.left)
- right = _convert_num(node.right)
- if isinstance(left, (int, float)) and isinstance(right, complex):
- if isinstance(node.op, Add):
- return left + right
- else:
- return left - right
- return _convert_signed_num(node)
- 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. If annotate_fields is true (by default),
- the returned string will show the names and the values for fields.
- If annotate_fields is false, the result string will be more compact by
- omitting unambiguous field names. Attributes such as line
- numbers and column offsets are not dumped by default. If this is wanted,
- include_attributes can be set to true.
- """
- def _format(node):
- if isinstance(node, AST):
- args = []
- keywords = annotate_fields
- for field in node._fields:
- try:
- value = getattr(node, field)
- except AttributeError:
- keywords = True
- else:
- if keywords:
- args.append('%s=%s' % (field, _format(value)))
- else:
- args.append(_format(value))
- if include_attributes and node._attributes:
- for a in node._attributes:
- try:
- args.append('%s=%s' % (a, _format(getattr(node, a))))
- except AttributeError:
- pass
- return '%s(%s)' % (node.__class__.__name__, ', '.join(args))
- 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`, `col_offset`, `end_lineno`, and `end_col_offset`
- attributes) from *old_node* to *new_node* if possible, and return *new_node*.
- """
- for attr in 'lineno', 'col_offset', 'end_lineno', 'end_col_offset':
- if attr in old_node._attributes and attr in new_node._attributes:
- value = getattr(old_node, attr, None)
- # end_lineno and end_col_offset are optional attributes, and they
- # should be copied whether the value is None or not.
- if value is not None or (
- hasattr(old_node, attr) and attr.startswith("end_")
- ):
- setattr(new_node, attr, value)
- 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, end_lineno, end_col_offset):
- if 'lineno' in node._attributes:
- if not hasattr(node, 'lineno'):
- node.lineno = lineno
- else:
- lineno = node.lineno
- if 'end_lineno' in node._attributes:
- if not hasattr(node, 'end_lineno'):
- node.end_lineno = end_lineno
- else:
- end_lineno = node.end_lineno
- if 'col_offset' in node._attributes:
- if not hasattr(node, 'col_offset'):
- node.col_offset = col_offset
- else:
- col_offset = node.col_offset
- if 'end_col_offset' in node._attributes:
- if not hasattr(node, 'end_col_offset'):
- node.end_col_offset = end_col_offset
- else:
- end_col_offset = node.end_col_offset
- for child in iter_child_nodes(node):
- _fix(child, lineno, col_offset, end_lineno, end_col_offset)
- _fix(node, 1, 0, 1, 0)
- return node
- def increment_lineno(node, n=1):
- """
- Increment the line number and end 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.
- """
- for child in walk(node):
- if 'lineno' in child._attributes:
- child.lineno = getattr(child, 'lineno', 0) + n
- if (
- "end_lineno" in child._attributes
- and (end_lineno := getattr(child, "end_lineno", 0)) is not None
- ):
- child.end_lineno = end_lineno + 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 *clean* is `True`, all tabs are expanded to spaces and any whitespace
- that can be uniformly removed from the second line onwards is removed.
- """
- if not isinstance(node, (AsyncFunctionDef, FunctionDef, ClassDef, Module)):
- raise TypeError("%r can't have docstrings" % node.__class__.__name__)
- if not(node.body and isinstance(node.body[0], Expr)):
- return None
- node = node.body[0].value
- if isinstance(node, Str):
- text = node.s
- elif isinstance(node, Constant) and isinstance(node.value, str):
- text = node.value
- else:
- return None
- if clean:
- import inspect
- text = inspect.cleandoc(text)
- return text
- def _splitlines_no_ff(source):
- """Split a string into lines ignoring form feed and other chars.
- This mimics how the Python parser splits source code.
- """
- idx = 0
- lines = []
- next_line = ''
- while idx < len(source):
- c = source[idx]
- next_line += c
- idx += 1
- # Keep \r\n together
- if c == '\r' and idx < len(source) and source[idx] == '\n':
- next_line += '\n'
- idx += 1
- if c in '\r\n':
- lines.append(next_line)
- next_line = ''
- if next_line:
- lines.append(next_line)
- return lines
- def _pad_whitespace(source):
- r"""Replace all chars except '\f\t' in a line with spaces."""
- result = ''
- for c in source:
- if c in '\f\t':
- result += c
- else:
- result += ' '
- return result
- def get_source_segment(source, node, *, padded=False):
- """Get source code segment of the *source* that generated *node*.
- If some location information (`lineno`, `end_lineno`, `col_offset`,
- or `end_col_offset`) is missing, return None.
- If *padded* is `True`, the first line of a multi-line statement will
- be padded with spaces to match its original position.
- """
- try:
- lineno = node.lineno - 1
- end_lineno = node.end_lineno - 1
- col_offset = node.col_offset
- end_col_offset = node.end_col_offset
- except AttributeError:
- return None
- lines = _splitlines_no_ff(source)
- if end_lineno == lineno:
- return lines[lineno].encode()[col_offset:end_col_offset].decode()
- if padded:
- padding = _pad_whitespace(lines[lineno].encode()[:col_offset].decode())
- else:
- padding = ''
- first = padding + lines[lineno].encode()[col_offset:].decode()
- last = lines[end_lineno].encode()[:end_col_offset].decode()
- lines = lines[lineno+1:end_lineno]
- lines.insert(0, first)
- lines.append(last)
- return ''.join(lines)
- def walk(node):
- """
- Recursively yield all descendant nodes in the tree starting at *node*
- (including *node* itself), 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)
- def visit_Constant(self, node):
- value = node.value
- type_name = _const_node_type_names.get(type(value))
- if type_name is None:
- for cls, name in _const_node_type_names.items():
- if isinstance(value, cls):
- type_name = name
- break
- if type_name is not None:
- method = 'visit_' + type_name
- try:
- visitor = getattr(self, method)
- except AttributeError:
- pass
- else:
- import warnings
- warnings.warn(f"{method} is deprecated; add visit_Constant",
- PendingDeprecationWarning, 2)
- return visitor(node)
- return self.generic_visit(node)
- 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 Subscript(
- value=Name(id='data', ctx=Load()),
- slice=Index(value=Str(s=node.id)),
- ctx=node.ctx
- )
- 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):
- 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
- # The following code is for backward compatibility.
- # It will be removed in future.
- def _getter(self):
- return self.value
- def _setter(self, value):
- self.value = value
- Constant.n = property(_getter, _setter)
- Constant.s = property(_getter, _setter)
- class _ABC(type):
- def __instancecheck__(cls, inst):
- if not isinstance(inst, Constant):
- return False
- if cls in _const_types:
- try:
- value = inst.value
- except AttributeError:
- return False
- else:
- return (
- isinstance(value, _const_types[cls]) and
- not isinstance(value, _const_types_not.get(cls, ()))
- )
- return type.__instancecheck__(cls, inst)
- def _new(cls, *args, **kwargs):
- for key in kwargs:
- if key not in cls._fields:
- # arbitrary keyword arguments are accepted
- continue
- pos = cls._fields.index(key)
- if pos < len(args):
- raise TypeError(f"{cls.__name__} got multiple values for argument {key!r}")
- if cls in _const_types:
- return Constant(*args, **kwargs)
- return Constant.__new__(cls, *args, **kwargs)
- class Num(Constant, metaclass=_ABC):
- _fields = ('n',)
- __new__ = _new
- class Str(Constant, metaclass=_ABC):
- _fields = ('s',)
- __new__ = _new
- class Bytes(Constant, metaclass=_ABC):
- _fields = ('s',)
- __new__ = _new
- class NameConstant(Constant, metaclass=_ABC):
- __new__ = _new
- class Ellipsis(Constant, metaclass=_ABC):
- _fields = ()
- def __new__(cls, *args, **kwargs):
- if cls is Ellipsis:
- return Constant(..., *args, **kwargs)
- return Constant.__new__(cls, *args, **kwargs)
- _const_types = {
- Num: (int, float, complex),
- Str: (str,),
- Bytes: (bytes,),
- NameConstant: (type(None), bool),
- Ellipsis: (type(...),),
- }
- _const_types_not = {
- Num: (bool,),
- }
- _const_node_type_names = {
- bool: 'NameConstant', # should be before int
- type(None): 'NameConstant',
- int: 'Num',
- float: 'Num',
- complex: 'Num',
- str: 'Str',
- bytes: 'Bytes',
- type(...): 'Ellipsis',
- }
|