Work around python's json module not liking circular references - python

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

Related

How to limit the permitted values that can be passed to a method parameter (Using Type Hinting to allow Static Code Analysis)

In Python 3, I want to limit the permitted values that are passed to this method:
my_request(protocol_type, url)
Using type hinting I can write:
my_request(protocol_type: str, url: str)
so the protocol and url are limited to strings, but how can I validate that protocol_type accepts only limited set of values, e.g. 'http' and 'https'?
One way is to write code in the method to validate that the value passed in is 'http' or 'https', something in the lines of:
if (protocol_type == 'http') or (protocol_type == 'https'):
Do Something
else:
Throw an exception
Which will work fine during runtime, but doesn't provide an indication of a problem while writing the code.
This is why I prefer using Enum and the type-hinting mechanism that Pycharm and mypy implement.
For the code example below you will get a warning in Pycharm from its code-inspection, see attached screenshot.
The screenshot shows that if you enter a value that is not enum you will get the "Expected Type:..." warning.
Code:
"""Test of ENUM"""
from enum import Enum
class ProtocolEnum(Enum):
"""
ENUM to hold the allowed values for protocol
"""
HTTP: str = 'http'
HTTPS: str = 'https'
def try_protocol_enum(protocol: ProtocolEnum) -> None:
"""
Test of ProtocolEnum
:rtype: None
:param protocol: a ProtocolEnum value allows for HTTP or HTTPS only
:return:
"""
print(type(protocol))
print(protocol.value)
print(protocol.name)
try_protocol_enum(ProtocolEnum.HTTP)
try_protocol_enum('https')
Output:
<enum 'ProtocolEnum'>
http
HTTP
I guess you can use decorators, I have a similar situation but I wanted to validate the parameter types:
def accepts(*types):
"""
Enforce parameter types for function
Modified from https://stackoverflow.com/questions/15299878/how-to-use-python-decorators-to-check-function-arguments
:param types: int, (int,float), if False, None or [] will be skipped
"""
def check_accepts(f):
def new_f(*args, **kwds):
for (a, t) in zip(args, types):
if t:
assert isinstance(a, t), \
"arg %r does not match %s" % (a, t)
return f(*args, **kwds)
new_f.func_name = f.__name__
return new_f
return check_accepts
And then use as:
#accepts(Decimal)
def calculate_price(monthly_item_price):
...
You can modify my decorator to achieve what you want.
You can just check if the input is correct in the function:
def my_request(protocol_type: str, url: str):
if protocol_type in ('http', 'https'):
# Do x
else:
return 'Invalid Input' # or raise an error
Why not use a Literal for the method argument?
def my_request(protocol_type: Literal["http","https"], url: str):
Use an if statement that raises an exception if protocol_type isn't in a list of allowed values :
allowed_protocols = ['http', 'https']
if protocol_type not in allowed_protocols:
raise ValueError()

How to safely unpack dict in python?

I have a wrapper class - it's an abstraction that I return from backend to frontend.
from typing import NamedTuple
class NewsItem(NamedTuple):
id: str
title: str
content: str
service: str
published_at: datetime
#classmethod
def from_payload(cls, payload) -> 'NewsItem':
return cls(**payload)
For example, when I get data from elastic I convert it to NewsItem:
return [NewsItem.from_payload(hit['_source'])
for hit in result['hits']['hits']]
The problem is I don't want to fail because of unknown fields that can come from elastic. How to ignore them (or put into a separate dedicated attribute list NewsItem.extra)?
I think the most elegant way is to use ._fields of NewsItem:
#classmethod
def from_payload(cls, payload) -> 'NewsItem':
return cls(*(payload[field] for field in cls._fields))
If you want to keep extras, you would need to do some work (field extra declared as extra: dict = {}):
#classmethod
def from_payload(cls, payload) -> 'NewsItem':
fields_no_extra = set(cls._fields) - {'extra'}
extra_fields = payload.keys() - fields_no_extra
extras = {field: payload[field] for field in extra_fields}
data = {field: payload[field] for field in fields_no_extra}
data['extra'] = extras
return cls(**data)
You can optimize this further, too much computation with sets;)
Of course my solutions do not handle case where payload doesn't contain all of the fields of the NewsItem
You can use **kwargs to let your __init__ take an arbitrary number of keyword arguments ("kwargs" means "keyword arguments") and discard unnecessary arguments:
class NewsItem(NamedTuple):
id: str
title: str
content: str
service: str
published_at: datetime
#classmethod
def from_payload(cls, id=None, title=None, content=None, service=None, published_at=None, **kwargs) -> 'NewsItem':
return cls(id, title, content, service, published_at)
Alternative solution with introspection NamedTuple class attributes (see #MOROZILnic answer + comment)
Since your problem is with the unknown key's you can use get method of the dictionary to safely ignore unknown keys.
For get method, first argument is the key you are looking for and the second argument is the Default value which will be returned when the key is not found.
so, do the following
return [NewsItem.from_payload(hit['_source'])
for hit in result.get('hits',{}).get('hits',"NOT FOUND"):
The above is just a example. do modify what you want to get when the hit does not have the key you want.

Serializing Python Object to JSON Created with eulxml.xmlmap.XmlObject

I have a set of python objects that I create using eulxml.xmlmap.XmlObject (I use this method primarily because I'm working with an eXistDB server and eulxml offers a pretty easy mapping function). I am able to successfully query my eXistDB and load an xquery result set into some python objects I've created. My problem is that I then want to be able to write these objects out as JSON when I pass them to the webserver (using Angular for the front end).
I've tried using jsonpickle but it seems as though eulxml is doing some kind of lazy loading magic. A standard call to jsonpickle to serialize my object to json gives me this result:
python code:
jsonpickle.encode(myObject)
result:
"py/object": "models.alcalaPage.AlcalaPage", "context":
{"namespaces":
{"exist": "http://exist.sourceforge.net/NS/exist"}
},
"node": {
"py/object": "lxml.etree._Element",
"py/seq": [
{"py/object": "lxml.etree._Comment", "py/seq": []},
{"py/object": "lxml.etree._Element", "py/seq": []},
...
]
}...
it seems to be only outputting the type of the attribute but not the value of the attribute itself. If I change my jsonpickle code to set unpickable=False, all I get is an empty set of json (meaning that the structure is there in terms of the right number of curly braces and brackets but there is literally no data. The json output is just curly braces and brackets).
I thought perhaps if I attempted to access a value in the field and then output the json that might work (at least for the field I accessed) but no luck. I get the same result as stated above (and yes I've double checked that there is data in the object itself).
I'm sort of at a loss at this point. I could migrate to something like BeautifulSoup but it means writing A LOT more code (eulxml lets me simply specify the xpath to the value I want to fill my attribute with and bing, I'm done). Is there something I'm missing with jsonpickle? Or is there another json package I should look at? Or maybe I'm making this way more difficult than I need to and there is some other way to query an eXistDB using python and then send the information to a front end application built using Angular. I'm open to suggestions.
I'll include samples of my code below (I won't include all of it because there are probably 10+ objects I'm working with):
Sample object code with eulxml:
import jsonpickle
from eulxml.xmlmap import XmlObject
class AlcalaBase(XmlObject):
def to_xml(self):
return self.serializeDocument(pretty=True)
def to_json(self):
return jsonpickle.encode(self)
from eulxml import xmlmap
from models.alcalaBase import AlcalaBase
class AlcalaPage(AlcalaBase):
ROOT_NAME = 'page'
id = xmlmap.StringField('pageID')
archive_page_number = xmlmap.StringField('archivistsPageNumber')
year = xmlmap.IntegerField('content/#yearID')
I was able to figure out the issue (sort of). So I'm posting it here in case others have the same issue.
The problem seems to be that the attributes are not added to dict so the actual values are not being output during the json process. I wrote my to_json() method in my base class in order to output the appropriate objects. NOTE: While I tried to keep this as generic as possible, it is somewhat specific to my data structure (in that I know what to expect in given scenarios and since I'm dealing with static data, I don't have to "future proof" the solution. Anyone adopting this code should adapt it to their given scenario.
from eulxml import xmlmap
import inspect
import lxml
import json as JSON
class AlcalaBase(xmlmap.XmlObject):
def to_json(self, skipBegin=False):
json = list()
if not skipBegin:
json.append('{')
json.append(str.format('"{0}": {{', self.ROOT_NAME))
for attr, value in inspect.getmembers(self):
if (attr.find("_") == -1
and attr.find("serialize") == -1
and attr.find("context") == -1
and attr.find("node") == -1
and attr.find("schema") == -1):
if type(value) is xmlmap.fields.NodeList:
if len(value) > 0:
json.append(str.format('"{0}": [', attr))
for v in value:
json.append(v.to_json())
json.append(",")
json = json[:-1]
json.append("]")
else:
json.append(str.format('"{0}": null', attr))
elif (type(value) is xmlmap.fields.StringField
or type(value) is str
or type(value) is lxml.etree._ElementUnicodeResult):
value = JSON.dumps(value)
json.append(str.format('"{0}": {1}', attr, value))
elif (type(value) is xmlmap.fields.IntegerField
or type(value) is int
or type(value) is float):
json.append(str.format('"{0}": {1}', attr, value))
elif value is None:
json.append(str.format('"{0}": null', attr))
elif type(value) is list:
if len(value) > 0:
json.append(str.format('"{0}": [', attr))
for x in value:
json.append(x)
json.append(",")
json = json[:-1]
json.append("]")
else:
json.append(str.format('"{0}": null', attr))
else:
json.append(value.to_json(skipBegin=True))
json.append(",")
json = json[:-1]
if not skipBegin:
json.append('}')
json.append('}')
return ''.join(json)
Anything that inherits from this class will be able to serialise out to json. This also assumes that all object collections inherit from this base class (in my particular model, this is true so it's not an issue).
Yes, jsonpickle calls the dict method so that it works, you can use the following in a meta class:
class MyXmlObject(XmlObject):
#property
def __dict__(self):
d = { 'ROOT_NAME': self.ROOT_NAME }
for key, value in self._fields.items():
if isinstance(value, fields.Field):
if isinstance(value, fields.NodeListField):
d[key] = [x.__dict__ for x in getattr(self, key)]
elif isinstance(value, fields.NodeField):
d[key] = getattr(self, key).__dict__
else:
d[key] = getattr(self, key)
return d
so the dict method will directly return the values of fields

Python recursive setattr()-like function for working with nested dictionaries [duplicate]

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. :)

Python: Pickling a dict with some unpicklable items

I have an object gui_project which has an attribute .namespace, which is a namespace dict. (i.e. a dict from strings to objects.)
(This is used in an IDE-like program to let the user define his own object in a Python shell.)
I want to pickle this gui_project, along with the namespace. Problem is, some objects in the namespace (i.e. values of the .namespace dict) are not picklable objects. For example, some of them refer to wxPython widgets.
I'd like to filter out the unpicklable objects, that is, exclude them from the pickled version.
How can I do this?
(One thing I tried is to go one by one on the values and try to pickle them, but some infinite recursion happened, and I need to be safe from that.)
(I do implement a GuiProject.__getstate__ method right now, to get rid of other unpicklable stuff besides namespace.)
I would use the pickler's documented support for persistent object references. Persistent object references are objects that are referenced by the pickle but not stored in the pickle.
http://docs.python.org/library/pickle.html#pickling-and-unpickling-external-objects
ZODB has used this API for years, so it's very stable. When unpickling, you can replace the object references with anything you like. In your case, you would want to replace the object references with markers indicating that the objects could not be pickled.
You could start with something like this (untested):
import cPickle
def persistent_id(obj):
if isinstance(obj, wxObject):
return "filtered:wxObject"
else:
return None
class FilteredObject:
def __init__(self, about):
self.about = about
def __repr__(self):
return 'FilteredObject(%s)' % repr(self.about)
def persistent_load(obj_id):
if obj_id.startswith('filtered:'):
return FilteredObject(obj_id[9:])
else:
raise cPickle.UnpicklingError('Invalid persistent id')
def dump_filtered(obj, file):
p = cPickle.Pickler(file)
p.persistent_id = persistent_id
p.dump(obj)
def load_filtered(file)
u = cPickle.Unpickler(file)
u.persistent_load = persistent_load
return u.load()
Then just call dump_filtered() and load_filtered() instead of pickle.dump() and pickle.load(). wxPython objects will be pickled as persistent IDs, to be replaced with FilteredObjects at unpickling time.
You could make the solution more generic by filtering out objects that are not of the built-in types and have no __getstate__ method.
Update (15 Nov 2010): Here is a way to achieve the same thing with wrapper classes. Using wrapper classes instead of subclasses, it's possible to stay within the documented API.
from cPickle import Pickler, Unpickler, UnpicklingError
class FilteredObject:
def __init__(self, about):
self.about = about
def __repr__(self):
return 'FilteredObject(%s)' % repr(self.about)
class MyPickler(object):
def __init__(self, file, protocol=0):
pickler = Pickler(file, protocol)
pickler.persistent_id = self.persistent_id
self.dump = pickler.dump
self.clear_memo = pickler.clear_memo
def persistent_id(self, obj):
if not hasattr(obj, '__getstate__') and not isinstance(obj,
(basestring, int, long, float, tuple, list, set, dict)):
return "filtered:%s" % type(obj)
else:
return None
class MyUnpickler(object):
def __init__(self, file):
unpickler = Unpickler(file)
unpickler.persistent_load = self.persistent_load
self.load = unpickler.load
self.noload = unpickler.noload
def persistent_load(self, obj_id):
if obj_id.startswith('filtered:'):
return FilteredObject(obj_id[9:])
else:
raise UnpicklingError('Invalid persistent id')
if __name__ == '__main__':
from cStringIO import StringIO
class UnpickleableThing(object):
pass
f = StringIO()
p = MyPickler(f)
p.dump({'a': 1, 'b': UnpickleableThing()})
f.seek(0)
u = MyUnpickler(f)
obj = u.load()
print obj
assert obj['a'] == 1
assert isinstance(obj['b'], FilteredObject)
assert obj['b'].about
This is how I would do this (I did something similar before and it worked):
Write a function that determines whether or not an object is pickleable
Make a list of all the pickleable variables, based on the above function
Make a new dictionary (called D) that stores all the non-pickleable variables
For each variable in D (this only works if you have very similar variables in d)
make a list of strings, where each string is legal python code, such that
when all these strings are executed in order, you get the desired variable
Now, when you unpickle, you get back all the variables that were originally pickleable. For all variables that were not pickleable, you now have a list of strings (legal python code) that when executed in order, gives you the desired variable.
Hope this helps
I ended up coding my own solution to this, using Shane Hathaway's approach.
Here's the code. (Look for CutePickler and CuteUnpickler.) Here are the tests. It's part of GarlicSim, so you can use it by installing garlicsim and doing from garlicsim.general_misc import pickle_tools.
If you want to use it on Python 3 code, use the Python 3 fork of garlicsim.
One approach would be to inherit from pickle.Pickler, and override the save_dict() method. Copy it from the base class, which reads like this:
def save_dict(self, obj):
write = self.write
if self.bin:
write(EMPTY_DICT)
else: # proto 0 -- can't use EMPTY_DICT
write(MARK + DICT)
self.memoize(obj)
self._batch_setitems(obj.iteritems())
However, in the _batch_setitems, pass an iterator that filters out all items that you don't want to be dumped, e.g
def save_dict(self, obj):
write = self.write
if self.bin:
write(EMPTY_DICT)
else: # proto 0 -- can't use EMPTY_DICT
write(MARK + DICT)
self.memoize(obj)
self._batch_setitems(item for item in obj.iteritems()
if not isinstance(item[1], bad_type))
As save_dict isn't an official API, you need to check for each new Python version whether this override is still correct.
The filtering part is indeed tricky. Using simple tricks, you can easily get the pickle to work. However, you might end up filtering out too much and losing information that you could keep when the filter looks a little bit deeper. But the vast possibility of things that can end up in the .namespace makes building a good filter difficult.
However, we could leverage pieces that are already part of Python, such as deepcopy in the copy module.
I made a copy of the stock copy module, and did the following things:
create a new type named LostObject to represent object that will be lost in pickling.
change _deepcopy_atomic to make sure x is picklable. If it's not, return an instance of LostObject
objects can define methods __reduce__ and/or __reduce_ex__ to provide hint about whether and how to pickle it. We make sure these methods will not throw exception to provide hint that it cannot be pickled.
to avoid making unnecessary copy of big object (a la actual deepcopy), we recursively check whether an object is picklable, and only make unpicklable part. For instance, for a tuple of a picklable list and and an unpickable object, we will make a copy of the tuple - just the container - but not its member list.
The following is the diff:
[~/Development/scratch/] $ diff -uN /System/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/copy.py mcopy.py
--- /System/Library/Frameworks/Python.framework/Versions/2.6/lib/python2.6/copy.py 2010-01-09 00:18:38.000000000 -0800
+++ mcopy.py 2010-11-10 08:50:26.000000000 -0800
## -157,6 +157,13 ##
cls = type(x)
+ # if x is picklable, there is no need to make a new copy, just ref it
+ try:
+ dumps(x)
+ return x
+ except TypeError:
+ pass
+
copier = _deepcopy_dispatch.get(cls)
if copier:
y = copier(x, memo)
## -179,10 +186,18 ##
reductor = getattr(x, "__reduce_ex__", None)
if reductor:
rv = reductor(2)
+ try:
+ x.__reduce_ex__()
+ except TypeError:
+ rv = LostObject, tuple()
else:
reductor = getattr(x, "__reduce__", None)
if reductor:
rv = reductor()
+ try:
+ x.__reduce__()
+ except TypeError:
+ rv = LostObject, tuple()
else:
raise Error(
"un(deep)copyable object of type %s" % cls)
## -194,7 +209,12 ##
_deepcopy_dispatch = d = {}
+from pickle import dumps
+class LostObject(object): pass
def _deepcopy_atomic(x, memo):
+ try:
+ dumps(x)
+ except TypeError: return LostObject()
return x
d[type(None)] = _deepcopy_atomic
d[type(Ellipsis)] = _deepcopy_atomic
Now back to the pickling part. You simply make a deepcopy using this new deepcopy function and then pickle the copy. The unpicklable parts have been removed during the copying process.
x = dict(a=1)
xx = dict(x=x)
x['xx'] = xx
x['f'] = file('/tmp/1', 'w')
class List():
def __init__(self, *args, **kwargs):
print 'making a copy of a list'
self.data = list(*args, **kwargs)
x['large'] = List(range(1000))
# now x contains a loop and a unpickable file object
# the following line will throw
from pickle import dumps, loads
try:
dumps(x)
except TypeError:
print 'yes, it throws'
def check_picklable(x):
try:
dumps(x)
except TypeError:
return False
return True
class LostObject(object): pass
from mcopy import deepcopy
# though x has a big List object, this deepcopy will not make a new copy of it
c = deepcopy(x)
dumps(c)
cc = loads(dumps(c))
# check loop refrence
if cc['xx']['x'] == cc:
print 'yes, loop reference is preserved'
# check unpickable part
if isinstance(cc['f'], LostObject):
print 'unpicklable part is now an instance of LostObject'
# check large object
if loads(dumps(c))['large'].data[999] == x['large'].data[999]:
print 'large object is ok'
Here is the output:
making a copy of a list
yes, it throws
yes, loop reference is preserved
unpicklable part is now an instance of LostObject
large object is ok
You see that 1) mutual pointers (between x and xx) are preserved and we do not run into infinite loop; 2) the unpicklable file object is converted to a LostObject instance; and 3) not new copy of the large object is created since it is picklable.

Categories

Resources