There was some discussion on python-dev over the weekend about generating warnings, and Moshe Zadke posted a selfnanny that warned about methods that didn't have self as the first argument. I think these kinds of warnings are useful, and I'd like to see a more general framework for them built are Python abstract syntax originally from P2C. Ideally, they would be available as command line tools and integrated into GUIs like IDLE in some useful way. I've included a couple of quick examples I coded up last night based on the compiler package (recently re-factored) that is resident in python/nondist/src/Compiler. The analysis on the one that checks for name errors is a bit of a mess, but the overall structure seems right. I'm hoping to collect a few more examples of checkers and generalize from them to develop a framework for checking for errors and reporting them. Jeremy ------------ checkself.py ------------ """Check for methods that do not have self as the first argument""" from compiler import parseFile, walk, ast, misc class Warning: def __init__(self, filename, klass, method, lineno, msg): self.filename = filename self.klass = klass self.method = method self.lineno = lineno self.msg = msg _template = "%(filename)s:%(lineno)s %(klass)s.%(method)s: %(msg)s" def __str__(self): return self._template % self.__dict__ class NoArgsWarning(Warning): super_init = Warning.__init__ def __init__(self, filename, klass, method, lineno): self.super_init(filename, klass, method, lineno, "no arguments") class NotSelfWarning(Warning): super_init = Warning.__init__ def __init__(self, filename, klass, method, lineno, argname): self.super_init(filename, klass, method, lineno, "self slot is named %s" % argname) class CheckSelf: def __init__(self, filename): self.filename = filename self.warnings = [] self.scope = misc.Stack() def inClass(self): if self.scope: return isinstance(self.scope.top(), ast.Class) return 0 def visitClass(self, klass): self.scope.push(klass) self.visit(klass.code) self.scope.pop() return 1 def visitFunction(self, func): if self.inClass(): classname = self.scope.top().name if len(func.argnames) == 0: w = NoArgsWarning(self.filename, classname, func.name, func.lineno) self.warnings.append(w) elif func.argnames[0] != "self": w = NotSelfWarning(self.filename, classname, func.name, func.lineno, func.argnames[0]) self.warnings.append(w) self.scope.push(func) self.visit(func.code) self.scope.pop() return 1 def check(filename): global p, check p = parseFile(filename) check = CheckSelf(filename) walk(p, check) for w in check.warnings: print w if __name__ == "__main__": import sys # XXX need to do real arg processing check(sys.argv[1]) ------------ badself.py ------------ def foo(): return 12 class Foo: def __init__(): pass def foo(self, foo): pass def bar(this, that): def baz(this=that): return this return baz def bar(): class Quux: def __init__(self): self.sum = 1 def quam(x, y): self.sum = self.sum + (x * y) return Quux() ------------ checknames.py ------------ """Check for NameErrors""" from compiler import parseFile, walk from compiler.misc import Stack, Set import __builtin__ from UserDict import UserDict class Warning: def __init__(self, filename, funcname, lineno): self.filename = filename self.funcname = funcname self.lineno = lineno def __str__(self): return self._template % self.__dict__ class UndefinedLocal(Warning): super_init = Warning.__init__ def __init__(self, filename, funcname, lineno, name): self.super_init(filename, funcname, lineno) self.name = name _template = "%(filename)s:%(lineno)s %(funcname)s undefined local %(name)s" class NameError(UndefinedLocal): _template = "%(filename)s:%(lineno)s %(funcname)s undefined name %(name)s" class NameSet(UserDict): """Track names and the line numbers where they are referenced""" def __init__(self): self.data = self.names = {} def add(self, name, lineno): l = self.names.get(name, []) l.append(lineno) self.names[name] = l class CheckNames: def __init__(self, filename): self.filename = filename self.warnings = [] self.scope = Stack() self.gUse = NameSet() self.gDef = NameSet() # _locals is the stack of local namespaces # locals is the top of the stack self._locals = Stack() self.lUse = None self.lDef = None self.lGlobals = None # var declared global # holds scope,def,use,global triples for later analysis self.todo = [] def enterNamespace(self, node): ## print node.name self.scope.push(node) self.lUse = use = NameSet() self.lDef = _def = NameSet() self.lGlobals = gbl = NameSet() self._locals.push((use, _def, gbl)) def exitNamespace(self): ## print self.todo.append((self.scope.top(), self.lDef, self.lUse, self.lGlobals)) self.scope.pop() self._locals.pop() if self._locals: self.lUse, self.lDef, self.lGlobals = self._locals.top() else: self.lUse = self.lDef = self.lGlobals = None def warn(self, warning, funcname, lineno, *args): args = (self.filename, funcname, lineno) + args self.warnings.append(apply(warning, args)) def defName(self, name, lineno, local=1): ## print "defName(%s, %s, local=%s)" % (name, lineno, local) if self.lUse is None: self.gDef.add(name, lineno) elif local == 0: self.gDef.add(name, lineno) self.lGlobals.add(name, lineno) else: self.lDef.add(name, lineno) def useName(self, name, lineno, local=1): ## print "useName(%s, %s, local=%s)" % (name, lineno, local) if self.lUse is None: self.gUse.add(name, lineno) elif local == 0: self.gUse.add(name, lineno) self.lUse.add(name, lineno) else: self.lUse.add(name, lineno) def check(self): for s, d, u, g in self.todo: self._check(s, d, u, g, self.gDef) # XXX then check the globals def _check(self, scope, _def, use, gbl, globals): # check for NameError # a name is defined iff it is in def.keys() # a name is global iff it is in gdefs.keys() gdefs = UserDict() gdefs.update(globals) gdefs.update(__builtin__.__dict__) defs = UserDict() defs.update(gdefs) defs.update(_def) errors = Set() for name in use.keys(): if not defs.has_key(name): firstuse = use[name][0] self.warn(NameError, scope.name, firstuse, name) errors.add(name) # check for UndefinedLocalNameError # order == use & def sorted by lineno # elements are lineno, flag, name # flag = 0 if use, flag = 1 if def order = [] for name, lines in use.items(): if gdefs.has_key(name) and not _def.has_key(name): # this is a global ref, we can skip it continue for lineno in lines: order.append(lineno, 0, name) for name, lines in _def.items(): for lineno in lines: order.append(lineno, 1, name) order.sort() # ready contains names that have been defined or warned about ready = Set() for lineno, flag, name in order: if flag == 0: # use if not ready.has_elt(name) and not errors.has_elt(name): self.warn(UndefinedLocal, scope.name, lineno, name) ready.add(name) # don't warn again else: ready.add(name) # below are visitor methods def visitFunction(self, node, noname=0): for expr in node.defaults: self.visit(expr) if not noname: self.defName(node.name, node.lineno) self.enterNamespace(node) for name in node.argnames: self.defName(name, node.lineno) self.visit(node.code) self.exitNamespace() return 1 def visitLambda(self, node): return self.visitFunction(node, noname=1) def visitClass(self, node): for expr in node.bases: self.visit(expr) self.defName(node.name, node.lineno) self.enterNamespace(node) self.visit(node.code) self.exitNamespace() return 1 def visitName(self, node): self.useName(node.name, node.lineno) def visitGlobal(self, node): for name in node.names: self.defName(name, node.lineno, local=0) def visitImport(self, node): for name in node.names: self.defName(name, node.lineno) visitFrom = visitImport def visitAssName(self, node): self.defName(node.name, node.lineno) def check(filename): global p, checker p = parseFile(filename) checker = CheckNames(filename) walk(p, checker) checker.check() for w in checker.warnings: print w if __name__ == "__main__": import sys # XXX need to do real arg processing check(sys.argv[1]) ------------ badnames.py ------------ # XXX can we detect race conditions on accesses to global variables? # probably can (conservatively) by noting variables _created_ by # global decls in funcs import string import time def foo(x): return x + y def foo2(x): return x + z a = 4 def foo3(x): a, b = x, a def bar(x): z = x global z def bar2(x): f = string.strip a = f(x) import string return string.lower(a) def baz(x, y): return x + y + z def outer(x): def inner(y): return x + y return inner