I'm dealing with refactoring code which extensively uses dicts in a circumstance where enums could be used. Unfortunately, to reduce typing the dict keys were abbreviated in a cryptic fashion.
In order to have more meaningful code and fewer string literals as well as a more advanced interface I translated the message dictionary based code into an Enum based code using the same messages.
The message dictionaries looked like the following:
MsgDictionary = {'none': None,
'STJ': 'start_job',
'RPS': 'report_status',
'KLJ': 'kill_job'}
ExecStates = {'none': None,
'JCNS': 'job_could_not_start',
'JSS': 'job_successfully_started',
'JSF': 'job_successfully_finished'}
This, unfortunately lead to cluttered code:
...
self.send_message(id = MsgDictionary["stj"], some_data)
...
msg = self.receive_msg()
if msg.id in (MsgDictionary['STJ'], MsgDictionary['KLJ']):
self.toggle_job()
...
I would merely like to get rid of the string accesses, the cryptic names and the low level interface, like in the following. This send_message should send the str typed value of the Enum not the Enum instance itself.
...
self.send_message(id = MessagesEnum.START_JOB, some_data)
...
msg = self.receive_msg()
if msg.id in (MessagesEnum.START_JOB, MessagesEnum.KILL_JOB):
self.toggle_job()
...
But as in the original case, undefined execution states should still be allowed. This does currently not work. The reason is to not break existing code:
e = ExecStates(None)
-> ValueError: None is not a valid ExecutionStates
And I would like to be able to compare enum instances, e.g.:
e = ExecState[START_JOB]
if e == ExecState[START_JOB]:
pass
if e == ExecState[KILL_JOB]:
pass
Using the following definitions, I believe I'm almost there:
import enum
class _BaseEnum(str, enum.Enum):
#classmethod
def values(cls) -> DictValues:
return cls.__members__.values()
def _generate_next_value_(name: str, *args: object) -> str:
return name.lower()
def __str__(self):
return str(self.value) # Use stringification to cover the None value case
class MessageEnum(_BaseEnum):
NONE = None
START_JOB = enum.auto()
REPORT_STATUS = enum.auto()
KILL_JOB = enum.auto()
class ExecutionState(_BaseEnum):
NONE = None
JOB_COULD_NOT_START = enum.auto()
JOB_SUCCESSFULLY_STARTED = enum.auto()
JOB_SUCCESSFULLY_FINISHED = enum.auto()
However, one problem still remains. How can I deal with None value as well as strings in the enumerations? In my case, all enum items gets mapped to the lowercase of the enum item name. Which is the intended functionality. However, None gets unintendedly mapped to 'None'. This in effect leads to problems at other spots in the existing code which initializes an ExecutionState instance with None. I would like to also cover this case to not break existing code.
When I add a __new__ method to the _BaseEnum,
def __new__(cls, value):
obj = str.__new__(cls)
obj._value_ = value
return obj
I loose the possibility to compare the enumeration instances as all instances compare equal to ``.
My question is, in order to solve my problem, if I can corner case the None either in the _generate_next_value_ or the __new__ method or maybe using a proxy pattern ?
Two things that should help:
in your __new__, the creation line should read obj = str.__new__(cls, value) -- that way each instance will compare equal to its lower-cased name
export your enum members to the global namespace, and use is:
START_JOB, REPORT_STATUS, KILL_JOB = MessageEnum
...
if e is START_JOB: ...
...
if msg.id in (START_JOB, KILL_JOB): ...
Other than using an external library (like maybe jsonpickle, though I haven't tried it), is there a way to get python's json module to dump a dictionary (or list, etc) that has circular references (just dropping the reference, that is)?
I only want to use json to more easily see some debug output.
Well, avoiding anything but standard modules, here's one solution which utilizes repr for handling the circular references. EDIT: For the latest, see all-purpose function for dumping any python thing in a mostly-readable manner (aka dump)
# MAGIC-NUMBER: max length is just some guess at a reasonable size, e.g. 80 cols by 100 lines
def dump(value, msg='DUMP', max_length=80 * 100, stdout=False, pick=None):
"""
Write as verbose of a description of the value as possible to logging.DEBUG.
See http://stackoverflow.com/q/27830888/116891
:param value: The item of interest.
:type value: object
:param msg: Prefix for the logged item (default='DUMP')
:type msg: basestring
:param max_length: Longest allowed string length (set to None for unlimited)
:type max_length: int
:param stdout: If true, print instead of logging (default=False)
:type stdout: bool
:param pick: If specified, dump only values for these keys of the item
(value must be a dict or allow __dict__ access).
The name comes from http://underscorejs.org/#pick.
:type pick: iterable of basestring
:return: True if message dumped
:rtype: bool
"""
if not logging.getLogger().isEnabledFor(logging.DEBUG) and not stdout:
return
if pick:
d = value if isinstance(value, dict) else value.__dict__
filtered = {
property_name: d[property_name]
for property_name in pick
if property_name in d
}
value = filtered
kwargs = dict(indent=2, sort_keys=True)
try:
import json
info = json.dumps(value, **kwargs)
except:
# JSON doesn't like circular references :/
try:
string_repr = repr(value)
# Replace python primitives, single-quotes, unicode, etc
string_repr = string_repr\
.replace('None', 'null')\
.replace('True', 'true')\
.replace('False', 'false')\
.replace("u'", "'")\
.replace("'", '"')
# Replace object and function repr's like <MyObject ...>
string_repr = re.sub(r':(\s+)(<[^>]+>)', r':\1"\2"', string_repr)
# Replace tuples with lists, very naively
string_repr = string_repr.replace('(', '[').replace(')', ']')
info = json.dumps(json.loads(string_repr), **kwargs)
except:
from pprint import pformat
info = pformat(value, indent=2)
def _out(formatted_string, *format_args):
"""Format the string and output it to the correct location."""
if stdout:
print(formatted_string % format_args)
else:
logging.debug(formatted_string, *format_args)
if max_length is None or len(info) <= max_length:
_out('%s: %s', msg, info)
return True
else:
_out(
'Did not dump "%s" due to length restriction. Increase max_length if desired.', msg
)
return False
This question already has answers here:
Is it possible to index nested lists using tuples in python?
(7 answers)
Closed 7 months ago.
There are a lot of good getattr()-like functions for parsing nested dictionary structures, such as:
Finding a key recursively in a dictionary
Suppose I have a python dictionary , many nests
https://gist.github.com/mittenchops/5664038
I would like to make a parallel setattr(). Essentially, given:
cmd = 'f[0].a'
val = 'whatever'
x = {"a":"stuff"}
I'd like to produce a function such that I can assign:
x['f'][0]['a'] = val
More or less, this would work the same way as:
setattr(x,'f[0].a',val)
to yield:
>>> x
{"a":"stuff","f":[{"a":"whatever"}]}
I'm currently calling it setByDot():
setByDot(x,'f[0].a',val)
One problem with this is that if a key in the middle doesn't exist, you need to check for and make an intermediate key if it doesn't exist---ie, for the above:
>>> x = {"a":"stuff"}
>>> x['f'][0]['a'] = val
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
KeyError: 'f'
So, you first have to make:
>>> x['f']=[{}]
>>> x
{'a': 'stuff', 'f': [{}]}
>>> x['f'][0]['a']=val
>>> x
{'a': 'stuff', 'f': [{'a': 'whatever'}]}
Another is that keying for when the next item is a lists will be different than the keying when the next item is a string, ie:
>>> x = {"a":"stuff"}
>>> x['f']=['']
>>> x['f'][0]['a']=val
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
TypeError: 'str' object does not support item assignment
...fails because the assignment was for a null string instead of a null dict. The null dict will be the right assignment for every non-list in dict until the very last one---which may be a list, or a value.
A second problem, pointed out in the comments below by #TokenMacGuy, is that when you have to create a list that does not exist, you may have to create an awful lot of blank values. So,
setattr(x,'f[10].a',val)
---may mean the algorithm will have to make an intermediate like:
>>> x['f']=[{},{},{},{},{},{},{},{},{},{},{}]
>>> x['f'][10]['a']=val
to yield
>>> x
{"a":"stuff","f":[{},{},{},{},{},{},{},{},{},{},{"a":"whatever"}]}
such that this is the setter associated with the getter...
>>> getByDot(x,"f[10].a")
"whatever"
More importantly, the intermediates should /not/ overwrite values that already exist.
Below is the junky idea I have so far---I can identify the lists versus dicts and other data types, and create them where they do not exist. However, I don't see (a) where to put the recursive call, or (b) how to 'build' the deep object as I iterate through the list, and (c) how to distinguish the /probing/ I'm doing as I construct the deep object from the /setting/ I have to do when I reach the end of the stack.
def setByDot(obj,ref,newval):
ref = ref.replace("[",".[")
cmd = ref.split('.')
numkeys = len(cmd)
count = 0
for c in cmd:
count = count+1
while count < numkeys:
if c.find("["):
idstart = c.find("[")
numend = c.find("]")
try:
deep = obj[int(idstart+1:numend-1)]
except:
obj[int(idstart+1:numend-1)] = []
deep = obj[int(idstart+1:numend-1)]
else:
try:
deep = obj[c]
except:
if obj[c] isinstance(dict):
obj[c] = {}
else:
obj[c] = ''
deep = obj[c]
setByDot(deep,c,newval)
This seems very tricky because you kind of have to look-ahead to check the type of the /next/ object if you're making place-holders, and you have to look-behind to build a path up as you go.
UPDATE
I recently had this question answered, too, which might be relevant or helpful.
I have separated this out into two steps. In the first step, the query string is broken down into a series of instructions. This way the problem is decoupled, we can view the instructions before running them, and there is no need for recursive calls.
def build_instructions(obj, q):
"""
Breaks down a query string into a series of actionable instructions.
Each instruction is a (_type, arg) tuple.
arg -- The key used for the __getitem__ or __setitem__ call on
the current object.
_type -- Used to determine the data type for the value of
obj.__getitem__(arg)
If a key/index is missing, _type is used to initialize an empty value.
In this way _type provides the ability to
"""
arg = []
_type = None
instructions = []
for i, ch in enumerate(q):
if ch == "[":
# Begin list query
if _type is not None:
arg = "".join(arg)
if _type == list and arg.isalpha():
_type = dict
instructions.append((_type, arg))
_type, arg = None, []
_type = list
elif ch == ".":
# Begin dict query
if _type is not None:
arg = "".join(arg)
if _type == list and arg.isalpha():
_type = dict
instructions.append((_type, arg))
_type, arg = None, []
_type = dict
elif ch.isalnum():
if i == 0:
# Query begins with alphanum, assume dict access
_type = type(obj)
# Fill out args
arg.append(ch)
else:
TypeError("Unrecognized character: {}".format(ch))
if _type is not None:
# Finish up last query
instructions.append((_type, "".join(arg)))
return instructions
For your example
>>> x = {"a": "stuff"}
>>> print(build_instructions(x, "f[0].a"))
[(<type 'dict'>, 'f'), (<type 'list'>, '0'), (<type 'dict'>, 'a')]
The expected return value is simply the _type (first item) of the next tuple in the instructions. This is very important because it allows us to correctly initialize/reconstruct missing keys.
This means that our first instruction operates on a dict, either sets or gets the key 'f', and is expected to return a list. Similarly, our second instruction operates on a list, either sets or gets the index 0 and is expected to return a dict.
Now let's create our _setattr function. This gets the proper instructions and goes through them, creating key-value pairs as necessary. Finally, it also sets the val we give it.
def _setattr(obj, query, val):
"""
This is a special setattr function that will take in a string query,
interpret it, add the appropriate data structure to obj, and set val.
We only define two actions that are available in our query string:
.x -- dict.__setitem__(x, ...)
[x] -- list.__setitem__(x, ...) OR dict.__setitem__(x, ...)
the calling context determines how this is interpreted.
"""
instructions = build_instructions(obj, query)
for i, (_, arg) in enumerate(instructions[:-1]):
_type = instructions[i + 1][0]
obj = _set(obj, _type, arg)
_type, arg = instructions[-1]
_set(obj, _type, arg, val)
def _set(obj, _type, arg, val=None):
"""
Helper function for calling obj.__setitem__(arg, val or _type()).
"""
if val is not None:
# Time to set our value
_type = type(val)
if isinstance(obj, dict):
if arg not in obj:
# If key isn't in obj, initialize it with _type()
# or set it with val
obj[arg] = (_type() if val is None else val)
obj = obj[arg]
elif isinstance(obj, list):
n = len(obj)
arg = int(arg)
if n > arg:
obj[arg] = (_type() if val is None else val)
else:
# Need to amplify our list, initialize empty values with _type()
obj.extend([_type() for x in range(arg - n + 1)])
obj = obj[arg]
return obj
And just because we can, here's a _getattr function.
def _getattr(obj, query):
"""
Very similar to _setattr. Instead of setting attributes they will be
returned. As expected, an error will be raised if a __getitem__ call
fails.
"""
instructions = build_instructions(obj, query)
for i, (_, arg) in enumerate(instructions[:-1]):
_type = instructions[i + 1][0]
obj = _get(obj, _type, arg)
_type, arg = instructions[-1]
return _get(obj, _type, arg)
def _get(obj, _type, arg):
"""
Helper function for calling obj.__getitem__(arg).
"""
if isinstance(obj, dict):
obj = obj[arg]
elif isinstance(obj, list):
arg = int(arg)
obj = obj[arg]
return obj
In action:
>>> x = {"a": "stuff"}
>>> _setattr(x, "f[0].a", "test")
>>> print x
{'a': 'stuff', 'f': [{'a': 'test'}]}
>>> print _getattr(x, "f[0].a")
"test"
>>> x = ["one", "two"]
>>> _setattr(x, "3[0].a", "test")
>>> print x
['one', 'two', [], [{'a': 'test'}]]
>>> print _getattr(x, "3[0].a")
"test"
Now for some cool stuff. Unlike python, our _setattr function can set unhashable dict keys.
x = []
_setattr(x, "1.4", "asdf")
print x
[{}, {'4': 'asdf'}] # A list, which isn't hashable
>>> y = {"a": "stuff"}
>>> _setattr(y, "f[1.4]", "test") # We're indexing f with 1.4, which is a list!
>>> print y
{'a': 'stuff', 'f': [{}, {'4': 'test'}]}
>>> print _getattr(y, "f[1.4]") # Works for _getattr too
"test"
We aren't really using unhashable dict keys, but it looks like we are in our query language so who cares, right!
Finally, you can run multiple _setattr calls on the same object, just give it a try yourself.
>>> class D(dict):
... def __missing__(self, k):
... ret = self[k] = D()
... return ret
...
>>> x=D()
>>> x['f'][0]['a'] = 'whatever'
>>> x
{'f': {0: {'a': 'whatever'}}}
You can hack something together by fixing two problems:
List that automatically grows when accessed out of bounds (PaddedList)
A way to delay the decision of what to create (list of dict) until you accessed it by the first time (DictOrList)
So the code will look like this:
import collections
class PaddedList(list):
""" List that grows automatically up to the max index ever passed"""
def __init__(self, padding):
self.padding = padding
def __getitem__(self, key):
if isinstance(key, int) and len(self) <= key:
self.extend(self.padding() for i in xrange(key + 1 - len(self)))
return super(PaddedList, self).__getitem__(key)
class DictOrList(object):
""" Object proxy that delays the decision of being a List or Dict """
def __init__(self, parent):
self.parent = parent
def __getitem__(self, key):
# Type of the structure depends on the type of the key
if isinstance(key, int):
obj = PaddedList(MyDict)
else:
obj = MyDict()
# Update parent references with the selected object
parent_seq = (self.parent if isinstance(self.parent, dict)
else xrange(len(self.parent)))
for i in parent_seq:
if self == parent_seq[i]:
parent_seq[i] = obj
break
return obj[key]
class MyDict(collections.defaultdict):
def __missing__(self, key):
ret = self[key] = DictOrList(self)
return ret
def pprint_mydict(d):
""" Helper to print MyDict as dicts """
print d.__str__().replace('defaultdict(None, {', '{').replace('})', '}')
x = MyDict()
x['f'][0]['a'] = 'whatever'
y = MyDict()
y['f'][10]['a'] = 'whatever'
pprint_mydict(x)
pprint_mydict(y)
And the output of x and y will be:
{'f': [{'a': 'whatever'}]}
{'f': [{}, {}, {}, {}, {}, {}, {}, {}, {}, {}, {'a': 'whatever'}]}
The trick consist on creating a defaultdict of objects that can be either a dict or a list depending how you access it.
So when you have the assigment x['f'][10]['a'] = 'whatever' it will work the following way:
Get X['f']. It wont exist so it will return a DictOrList object for the index 'f'
Get X['f'][10]. DictOrList.getitem will be called with an integer index. The DictOrList object will replace itself in the parent collection by a PaddedList
Access the 11th element in the PaddedList will grow it by 11 elements and will return the MyDict element in that position
Assign "whatever" to x['f'][10]['a']
Both PaddedList and DictOrList are bit hacky, but after all the assignments there is no more magic, you have an structure of dicts and lists.
It is possible to synthesize recursively setting items/attributes by overriding __getitem__ to return a return a proxy that can set a value in the original function.
I happen to be working on a library that does a few things similar to this, so I was working on a class that can dynamically assign its own subclasses at instantiation. It makes working with this sort of thing easier, but if that kind of hacking makes you squeamish, you can get similar behavior by creating a ProxyObject similar to the one I create and by creating the individual classes used by the ProxyObject dynamically in the a function. Something like
class ProxyObject(object):
... #see below
def instanciateProxyObjcet(val):
class ProxyClassForVal(ProxyObject,val.__class__):
pass
return ProxyClassForVal(val)
You can use dictionary like I've used in FlexibleObject below would make that implementation significantly more efficient if this is the way you implement it. The code I will providing uses the FlexibleObject though. Right now it only supports classes that, like almost all of Python's builtin classes are capable of being generated by taking an instance of themselves as their sole argument to their __init__/__new__. In the next week or two, I'll add support for anything pickleable, and link to a github repository that contains it. Here's the code:
class FlexibleObject(object):
""" A FlexibleObject is a baseclass for allowing type to be declared
at instantiation rather than in the declaration of the class.
Usage:
class DoubleAppender(FlexibleObject):
def append(self,x):
super(self.__class__,self).append(x)
super(self.__class__,self).append(x)
instance1 = DoubleAppender(list)
instance2 = DoubleAppender(bytearray)
"""
classes = {}
def __new__(cls,supercls,*args,**kws):
if isinstance(supercls,type):
supercls = (supercls,)
else:
supercls = tuple(supercls)
if (cls,supercls) in FlexibleObject.classes:
return FlexibleObject.classes[(cls,supercls)](*args,**kws)
superclsnames = tuple([c.__name__ for c in supercls])
name = '%s%s' % (cls.__name__,superclsnames)
d = dict(cls.__dict__)
d['__class__'] = cls
if cls == FlexibleObject:
d.pop('__new__')
try:
d.pop('__weakref__')
except:
pass
d['__dict__'] = {}
newcls = type(name,supercls,d)
FlexibleObject.classes[(cls,supercls)] = newcls
return newcls(*args,**kws)
Then to use this to use this to synthesize looking up attributes and items of a dictionary-like object you can do something like this:
class ProxyObject(FlexibleObject):
#classmethod
def new(cls,obj,quickrecdict,path,attribute_marker):
self = ProxyObject(obj.__class__,obj)
self.__dict__['reference'] = quickrecdict
self.__dict__['path'] = path
self.__dict__['attr_mark'] = attribute_marker
return self
def __getitem__(self,item):
path = self.__dict__['path'] + [item]
ref = self.__dict__['reference']
return ref[tuple(path)]
def __setitem__(self,item,val):
path = self.__dict__['path'] + [item]
ref = self.__dict__['reference']
ref.dict[tuple(path)] = ProxyObject.new(val,ref,
path,self.__dict__['attr_mark'])
def __getattribute__(self,attr):
if attr == '__dict__':
return object.__getattribute__(self,'__dict__')
path = self.__dict__['path'] + [self.__dict__['attr_mark'],attr]
ref = self.__dict__['reference']
return ref[tuple(path)]
def __setattr__(self,attr,val):
path = self.__dict__['path'] + [self.__dict__['attr_mark'],attr]
ref = self.__dict__['reference']
ref.dict[tuple(path)] = ProxyObject.new(val,ref,
path,self.__dict__['attr_mark'])
class UniqueValue(object):
pass
class QuickRecursiveDict(object):
def __init__(self,dictionary={}):
self.dict = dictionary
self.internal_id = UniqueValue()
self.attr_marker = UniqueValue()
def __getitem__(self,item):
if item in self.dict:
val = self.dict[item]
try:
if val.__dict__['path'][0] == self.internal_id:
return val
else:
raise TypeError
except:
return ProxyObject.new(val,self,[self.internal_id,item],
self.attr_marker)
try:
if item[0] == self.internal_id:
return ProxyObject.new(KeyError(),self,list(item),
self.attr_marker)
except TypeError:
pass #Item isn't iterable
return ProxyObject.new(KeyError(),self,[self.internal_id,item],
self.attr_marker)
def __setitem__(self,item,val):
self.dict[item] = val
The particulars of the implementation will vary depending on what you want. It's obviously significantly easier to just override __getitem__ in the proxy than it is to override both __getitem__ and __getattribute__ or __getattr__. The syntax you are using in setbydot makes it look like you would be happiest with some solution that overrides a mixture of the two.
If you are just using the dictionary to compare values, using =,<=,>= etc. Overriding __getattribute__ works really nicely. If you are wanting to do something more sophisticated, you will probably be better off overriding __getattr__ and doing some checks in __setattr__ to determine whether you want to be synthesizing setting the attribute by setting a value in the dictionary or whether you want to be actually setting the attribute on the item you've obtained. Or you might want to handle it so that if your object has an attribute, __getattribute__ returns a proxy to that attribute and __setattr__ always just sets the attribute in the object (in which case, you can completely omit it). All of these things depend on exactly what you are trying to use the dictionary for.
You also may want to create __iter__ and the like. It takes a little bit of effort to make them, but the details should follow from the implementation of __getitem__ and __setitem__.
Finally, I'm going to briefly summarize the behavior of the QuickRecursiveDict in case it's not immediately clear from inspection. The try/excepts are just shorthand for checking to see whether the ifs can be performed. The one major defect of synthesizing the recursive setting rather than find a way to do it is that you can no longer be raising KeyErrors when you try to access a key that hasn't been set. However, you can come pretty close by returning a subclass of KeyError which is what I do in the example. I haven't tested it so I won't add it to the code, but you may want to pass in some human-readable representation of the key to KeyError.
But aside from all that it works rather nicely.
>>> qrd = QuickRecursiveDict
>>> qrd[0][13] # returns an instance of a subclass of KeyError
>>> qrd[0][13] = 9
>>> qrd[0][13] # 9
>>> qrd[0][13]['forever'] = 'young'
>>> qrd[0][13] # 9
>>> qrd[0][13]['forever'] # 'young'
>>> qrd[0] # returns an instance of a subclass of KeyError
>>> qrd[0] = 0
>>> qrd[0] # 0
>>> qrd[0][13]['forever'] # 'young'
One more caveat, the things being returned is not quite what it looks like. It's a proxy to what it looks like. If you want the int 9, you need int(qrd[0][13]) not qrd[0][13]. For ints this doesn't matter much since, +,-,= and all that bypass __getattribute__ but for lists, you would lose attributes like append if you didn't recast them. (You'd keep len and other builtin methods, just not attributes of list. You lose __len__.)
So that's it. The code's a little bit convoluted, so let me know if you have any questions. I probably can't answer them until tonight unless the answer's really brief. I wish I saw this question sooner, it's a really cool question, and I'll try to update a cleaner solution soon. I had fun trying to code a solution into the wee hours of last night. :)
hasattr(obj, attribute) is used to check if an object has the specified attribute but given an attribute is there a way to know where (all) it is defined?
Assume that my code is getting the name of an attribute (or a classmethod) as string and I want to invoke classname.attribute but I don't have the classname.
One solution that comes to my mind is this
def finder(attr):
for obj in globals():
try:
if globals()[obj].__dict__[attr]:
return(globals()[obj])
except:
...
usage:
class Lime(object):
#classmethod
def lfunc(self):
print('Classic')
getattr(finder('lfunc'),'lfunc')() #Runs lfunc method of Lime class
I am quite sure that this is not the best (oe even proper way) to do it. Can someone please provide a better way.
It is always "possible". Wether it is desirable is another history.
A quick and dirty way to do it is to iterate linearly over all classes and check if any define the attribute you have. Of course, that is subject to conflicts, and it will yield the first class that has such a named attribute. If it exists in more than one, it is up to you to decide which you want:
def finder(attr):
for cls in object.__subclasses__():
if hasattr(cls, attr):
return cls
raise ValueError
Instead of searching in "globals" this searches all subclasses of "object" - thus the classes to be found don't need to be in the namespace of the module where the finder function is.
If your methods are unique in teh set of classes you are searching, though, maybe you could just assemble a mapping of all methods and use it to call them instead.
Let's suppose all your classes inehrit from a class named "Base":
mapper = {attr_name:getattr(cls, attr_name) for cls in base.__subclasses__() for attr_name, obj in cls.__dict__.items()
if isinstance(obj, classmethod) }
And you call them with mapper['attrname']()
This avoids a linear search at each method call and thus would be much better.
- EDIT -
__subclassess__ just find the direct subclasses of a class, not the inheritance tree - so it won't be usefull in "real life" - maybe it is in the specifc case the OP has in its hands.
If one needs to find things across a inheritance tree, one needs to recurse over the each subclass as well.
As for old-style classes: of course this won't work - that is one of the motives for which they are broken by default in new code.
As for non-class attributes: they can only be found inspecting instances anyway - so another method has to be thought of - does not seem to be the concern of the O.P. here.
This might help:
import gc
def checker(checkee, maxdepth = 3):
def onlyDict(ls):
return filter(lambda x: isinstance(x, dict), ls)
collection = []
toBeInspected = {}
tBI = toBeInspected
gc.collect()
for dic in onlyDict(gc.get_referrers(checkee)):
for item, value in dic.iteritems():
if value is checkee:
collection.append(item)
elif item != "checker":
tBI[item] = value
def _auxChecker(checkee, path, collection, checked, current, depth):
if current in checked: return
checked.append(current)
gc.collect()
for dic in onlyDict(gc.get_referents(current)):
for item, value in dic.iteritems():
currentPath = path + "." + item
if value is checkee:
collection.append(currentPath)
else:
try:
_auxChecker(checkee, currentPath, collection,
checked, value, depth + 1)
if depth < maxdepth else None
except TypeError:
continue
checked = []
for item, value in tBI.iteritems():
_auxChecker(checkee, item, collection, checked, value, 1)
return collection
How to use:
referrer = []
class Foo:
pass
noo = Foo()
bar = noo
import xml
import libxml2
import sys
import os
op = os.path
xml.foo = bar
foobar = noo
for x in checker(foobar, 5):
try:
y= eval(x)
referrer.append(x)
except:
continue
del x, y
ps: attributes of the checkee will not be further checked, for recursive or nested references to the checkee itself.
This should work in all circumstances, but still needs a lot of testing:
import inspect
import sys
def finder(attr, classes=None):
result = []
if classes is None:
# get all accessible classes
classes = [obj for name, obj in inspect.getmembers(
sys.modules[__name__])]
for a_class in classes:
if inspect.isclass(a_class):
if hasattr(a_class, attr):
result.append(a_class)
else:
# we check for instance attributes
if hasattr(a_class(), attr):
result.append(a_class)
try:
result += finder(attr, a_class.__subclasses__())
except:
# old style classes (that don't inherit from object) do not
# have __subclasses; not the best solution though
pass
return list(set(result)) # workaround duplicates
def main(attr):
print finder(attr)
return 0
if __name__ == "__main__":
sys.exit(main("some_attr"))