"""Parse a Python module and describe its classes and functions.
Parse enough of a Python file to recognize imports and class and
function definitions, and to find out the superclasses of a class.
The interface consists of a single function:
readmodule_ex(module, path=None)
where module is the name of a Python module, and path is an optional
list of directories where the module is to be searched. If present,
path is prepended to the system search path sys.path. The return value
is a dictionary. The keys of the dictionary are the names of the
classes and functions defined in the module (including classes that are
defined via the from XXX import YYY construct). The values are
instances of classes Class and Function. One special key/value pair is
present for packages: the key '__path__' has a list as its value which
contains the package search path.
Classes and Functions have a common superclass: _Object. Every instance
has the following attributes:
module -- name of the module;
name -- name of the object;
file -- file in which the object is defined;
lineno -- line in the file where the object's definition starts;
parent -- parent of this object, if any;
children -- nested objects contained in this object.
The 'children' attribute is a dictionary mapping names to objects.
Instances of Function describe functions with the attributes from _Object.
Instances of Class describe classes with the attributes from _Object,
super -- list of super classes (Class instances if possible);
methods -- mapping of method names to beginning line numbers.
If the name of a super class is not recognized, the corresponding
entry in the list of super classes is not a class instance but a
string giving the name of the super class. Since import statements
are recognized and imported modules are scanned as well, this
from token import NAME, DEDENT, OP
__all__ = ["readmodule", "readmodule_ex", "Class", "Function"]
_modules = {} # Initialize cache of modules we've seen.
"Information about Python class or function."
def __init__(self, module, name, file, lineno, parent):
def _addchild(self, name, obj):
self.children[name] = obj
"Information about a Python function, including methods."
def __init__(self, module, name, file, lineno, parent=None):
_Object.__init__(self, module, name, file, lineno, parent)
"Information about a Python class."
def __init__(self, module, name, super, file, lineno, parent=None):
_Object.__init__(self, module, name, file, lineno, parent)
self.super = [] if super is None else super
def _addmethod(self, name, lineno):
self.methods[name] = lineno
def _nest_function(ob, func_name, lineno):
"Return a Function after nesting within ob."
newfunc = Function(ob.module, func_name, ob.file, lineno, ob)
ob._addchild(func_name, newfunc)
if isinstance(ob, Class):
ob._addmethod(func_name, lineno)
def _nest_class(ob, class_name, lineno, super=None):
"Return a Class after nesting within ob."
newclass = Class(ob.module, class_name, super, ob.file, lineno, ob)
ob._addchild(class_name, newclass)
def readmodule(module, path=None):
"""Return Class objects for the top-level classes in module.
This is the original interface, before Functions were added.
for key, value in _readmodule(module, path or []).items():
if isinstance(value, Class):
def readmodule_ex(module, path=None):
"""Return a dictionary with all functions and classes in module.
Search for module in PATH + sys.path.
If possible, include imported superclasses.
Do this by reading source, without importing (and executing) it.
return _readmodule(module, path or [])
def _readmodule(module, path, inpackage=None):
"""Do the hard work for readmodule[_ex].
If inpackage is given, it must be the dotted name of the package in
which we are searching for a submodule, and then PATH must be the
package search path; otherwise, we are searching for a top-level
module, and path is combined with sys.path.
# Compute the full module name (prepending inpackage if set).
if inpackage is not None:
fullmodule = "%s.%s" % (inpackage, module)
if fullmodule in _modules:
return _modules[fullmodule]
# Initialize the dict for this module's contents.
# Check if it is a built-in module; we don't do much for these.
if module in sys.builtin_module_names and inpackage is None:
# Check for a dotted module name.
parent = _readmodule(package, path, inpackage)
if inpackage is not None:
package = "%s.%s" % (inpackage, package)
if not '__path__' in parent:
raise ImportError('No package named {}'.format(package))
return _readmodule(submodule, parent['__path__'], package)
# Search the path for the module.
if inpackage is not None:
search_path = path + sys.path
spec = importlib.util._find_spec_from_path(fullmodule, search_path)
raise ModuleNotFoundError(f"no module named {fullmodule!r}", name=fullmodule)
_modules[fullmodule] = tree
if spec.submodule_search_locations is not None:
tree['__path__'] = spec.submodule_search_locations
source = spec.loader.get_source(fullmodule)
except (AttributeError, ImportError):
# If module is not Python source, we cannot do anything.
fname = spec.loader.get_filename(fullmodule)
return _create_tree(fullmodule, path, fname, source, tree, inpackage)
def _create_tree(fullmodule, path, fname, source, tree, inpackage):
"""Return the tree for a particular module.
fullmodule (full module name), inpackage+module, becomes o.module.
path is passed to recursive calls of _readmodule.
source is tokenized. Imports cause recursive calls to _readmodule.
tree is {} or {'__path__': <submodule search locations>}.
inpackage, None or string, is passed to recursive calls of _readmodule.
The effect of recursive calls is mutation of global _modules.
stack = [] # Initialize stack of (class, indent) pairs.
g = tokenize.generate_tokens(f.readline)
for tokentype, token, start, _end, _line in g:
lineno, thisindent = start
# Close previous nested classes and defs.
while stack and stack[-1][1] >= thisindent:
lineno, thisindent = start
# Close previous nested classes and defs.
while stack and stack[-1][1] >= thisindent:
tokentype, func_name, start = next(g)[0:3]
continue # Skip def with syntax error.
cur_func = _nest_function(cur_obj, func_name, lineno)
cur_func = Function(fullmodule, func_name, fname, lineno)
tree[func_name] = cur_func
stack.append((cur_func, thisindent))
lineno, thisindent = start
# Close previous nested classes and defs.
while stack and stack[-1][1] >= thisindent:
tokentype, class_name, start = next(g)[0:3]
continue # Skip class with syntax error.
# Parse what follows the class name.
tokentype, token, start = next(g)[0:3]
names = [] # Initialize list of superclasses.
super = [] # Tokens making up current superclass.
tokentype, token, start = next(g)[0:3]
if token in (')', ',') and level == 1:
# We know this super class.
# Super class form is module.class:
# look in module for class.
elif token == ',' and level == 1:
# Only use NAME and OP (== dot) tokens for type name.
elif tokentype in (NAME, OP) and level == 1:
# Expressions in the base list are not supported.
cur_obj, class_name, lineno, inherit)
cur_class = Class(fullmodule, class_name, inherit,
tree[class_name] = cur_class
stack.append((cur_class, thisindent))
elif token == 'import' and start[1] == 0:
modules = _getnamelist(g)
for mod, _mod2 in modules:
# Recursively read the imported module.
_readmodule(mod, path, inpackage)
# If we can't find or parse the imported module,
# too bad -- don't die here.
elif token == 'from' and start[1] == 0:
if not mod or token != "import":
# Recursively read the imported module.
d = _readmodule(mod, path, inpackage)
# If we can't find or parse the imported module,
# too bad -- don't die here.
# Add any classes that were defined in the imported module
# to our name space if they were mentioned in the list.
# Don't add names that start with _.
"""Return list of (dotted-name, as-name or None) tuples for token source g.
An as-name is the name that follows 'as' in an as clause.
name, token = _getname(g)
name2, token = _getname(g)
names.append((name, name2))
while token != "," and "\n" not in token:
"Return (dotted-name or None, next-token) tuple for token source g."
tokentype, token = next(g)[0:2]
if tokentype != NAME and token != '*':
tokentype, token = next(g)[0:2]
tokentype, token = next(g)[0:2]
return (".".join(parts), token)
"Print module output (default this file) for quick visual check."
path = [os.path.dirname(mod)]
mod = os.path.basename(mod)
if mod.lower().endswith(".py"):
tree = readmodule_ex(mod, path)
lineno_key = lambda a: getattr(a, 'lineno', 0)
objs = sorted(tree.values(), key=lineno_key, reverse=True)
if isinstance(obj, list):
# Value is a __path__ key.
if not hasattr(obj, 'indent'):
if isinstance(obj, _Object):
new_objs = sorted(obj.children.values(),
key=lineno_key, reverse=True)
ob.indent = obj.indent + indent_level
if isinstance(obj, Class):
.format(' ' * obj.indent, obj.name, obj.super, obj.lineno))
elif isinstance(obj, Function):
print("{}def {} {}".format(' ' * obj.indent, obj.name, obj.lineno))
if __name__ == "__main__":
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
