What is the prefered way to deprecate a class and subclass - python

How could I deprecate a class and his subclasses in Python?
Currently I thought that __init__() would work, but it doesn't since it won't be called if I won't call super() on subclasses.
Edit:
Okai some infos are missing on my question.
I know how to use warn.warning()
Also I don't wanted to use a Decorater. I wanted to just use it on one class and if the class is invoked it should warn the user.

You are looking for warnings.warn(message[, category[, stacklevel]])
Issue a warning, or maybe ignore it or raise an exception. The
category argument, if given, must be a warning category class (see
above); it defaults to UserWarning. Alternatively message can be a
Warning instance, in which case category will be ignored and
message.class will be used. In this case the message text will be
str(message). This function raises an exception if the particular
warning issued is changed into an error by the warnings filter see
above.
From here:
import functools
import inspect
import os
import warnings
class _DeprecatedDecorator(object):
MESSAGE = "%s is #deprecated"
def __call__(self, symbol):
if not inspect.isclass(symbol):
raise TypeError("only classes can be #deprecated")
warnings.filterwarnings('default',
message=self.MESSAGE % r'\w+',
category=DeprecationWarning)
return self._wrap_class(symbol)
def _wrap_class(self, cls):
previous_ctor = cls.__init__
#functools.wraps(previous_ctor)
def new_ctor(*args, **kwargs):
self._warn(cls.__name__)
return previous_ctor(*args, **kwargs)
cls.__init__ = new_ctor
return cls
def _warn(self, name):
warnings.warn(self.MESSAGE % name, DeprecationWarning,
stacklevel=self._compute_stacklevel())
def _compute_stacklevel(self):
this_file, _ = os.path.splitext(__file__)
app_code_dir = self._get_app_code_dir()
def is_relevant(filename):
return filename.startswith(app_code_dir) and not \
filename.startswith(this_file)
stack = self._get_callstack()
stack.pop(0) # omit this function's frame
frame = None
try:
for i, frame in enumerate(stack, 1):
filename = frame.f_code.co_filename
if is_relevant(filename):
return i
finally:
del frame
del stack
return 0
def _get_app_code_dir(self):
import myapplication # root package for the app
app_dir = os.path.dirname(myapplication.__file__)
return os.path.join(app_dir, '') # ensure trailing slash
def _get_callstack(self):
frame = inspect.currentframe()
frame = frame.f_back # omit this function's frame
stack = []
try:
while frame:
stack.append(frame)
frame = frame.f_back
finally:
del frame
return stack
deprecated = _DeprecatedDecorator()
del _DeprecatedDecorator

Related

How can I tell what function called my function? [duplicate]

Python: How to get the caller's method name in the called method?
Assume I have 2 methods:
def method1(self):
...
a = A.method2()
def method2(self):
...
If I don't want to do any change for method1, how to get the name of the caller (in this example, the name is method1) in method2?
inspect.getframeinfo and other related functions in inspect can help:
>>> import inspect
>>> def f1(): f2()
...
>>> def f2():
... curframe = inspect.currentframe()
... calframe = inspect.getouterframes(curframe, 2)
... print('caller name:', calframe[1][3])
...
>>> f1()
caller name: f1
this introspection is intended to help debugging and development; it's not advisable to rely on it for production-functionality purposes.
Shorter version:
import inspect
def f1(): f2()
def f2():
print 'caller name:', inspect.stack()[1][3]
f1()
(with thanks to #Alex, and Stefaan Lippen)
This seems to work just fine:
import sys
print sys._getframe().f_back.f_code.co_name
I would use inspect.currentframe().f_back.f_code.co_name. Its use hasn't been covered in any of the prior answers which are mainly of one of three types:
Some prior answers use inspect.stack but it's known to be too slow.
Some prior answers use sys._getframe which is an internal private function given its leading underscore, and so its use is implicitly discouraged.
One prior answer uses inspect.getouterframes(inspect.currentframe(), 2)[1][3] but it's entirely unclear what [1][3] is accessing.
import inspect
from types import FrameType
from typing import cast
def demo_the_caller_name() -> str:
"""Return the calling function's name."""
# Ref: https://stackoverflow.com/a/57712700/
return cast(FrameType, cast(FrameType, inspect.currentframe()).f_back).f_code.co_name
if __name__ == '__main__':
def _test_caller_name() -> None:
assert demo_the_caller_name() == '_test_caller_name'
_test_caller_name()
Note that cast(FrameType, frame) is used to satisfy mypy.
Acknowlegement: comment by 1313e for an answer.
I've come up with a slightly longer version that tries to build a full method name including module and class.
https://gist.github.com/2151727 (rev 9cccbf)
# Public Domain, i.e. feel free to copy/paste
# Considered a hack in Python 2
import inspect
def caller_name(skip=2):
"""Get a name of a caller in the format module.class.method
`skip` specifies how many levels of stack to skip while getting caller
name. skip=1 means "who calls me", skip=2 "who calls my caller" etc.
An empty string is returned if skipped levels exceed stack height
"""
stack = inspect.stack()
start = 0 + skip
if len(stack) < start + 1:
return ''
parentframe = stack[start][0]
name = []
module = inspect.getmodule(parentframe)
# `modname` can be None when frame is executed directly in console
# TODO(techtonik): consider using __main__
if module:
name.append(module.__name__)
# detect classname
if 'self' in parentframe.f_locals:
# I don't know any way to detect call from the object method
# XXX: there seems to be no way to detect static method call - it will
# be just a function call
name.append(parentframe.f_locals['self'].__class__.__name__)
codename = parentframe.f_code.co_name
if codename != '<module>': # top level usually
name.append( codename ) # function or a method
## Avoid circular refs and frame leaks
# https://docs.python.org/2.7/library/inspect.html#the-interpreter-stack
del parentframe, stack
return ".".join(name)
Bit of an amalgamation of the stuff above. But here's my crack at it.
def print_caller_name(stack_size=3):
def wrapper(fn):
def inner(*args, **kwargs):
import inspect
stack = inspect.stack()
modules = [(index, inspect.getmodule(stack[index][0]))
for index in reversed(range(1, stack_size))]
module_name_lengths = [len(module.__name__)
for _, module in modules]
s = '{index:>5} : {module:^%i} : {name}' % (max(module_name_lengths) + 4)
callers = ['',
s.format(index='level', module='module', name='name'),
'-' * 50]
for index, module in modules:
callers.append(s.format(index=index,
module=module.__name__,
name=stack[index][3]))
callers.append(s.format(index=0,
module=fn.__module__,
name=fn.__name__))
callers.append('')
print('\n'.join(callers))
fn(*args, **kwargs)
return inner
return wrapper
Use:
#print_caller_name(4)
def foo():
return 'foobar'
def bar():
return foo()
def baz():
return bar()
def fizz():
return baz()
fizz()
output is
level : module : name
--------------------------------------------------
3 : None : fizz
2 : None : baz
1 : None : bar
0 : __main__ : foo
You can use decorators, and do not have to use stacktrace
If you want to decorate a method inside a class
import functools
# outside ur class
def printOuterFunctionName(func):
#functools.wraps(func)
def wrapper(self):
print(f'Function Name is: {func.__name__}')
func(self)
return wrapper
class A:
#printOuterFunctionName
def foo():
pass
you may remove functools, self if it is procedural
An alternative to sys._getframe() is used by Python's Logging library to find caller information. Here's the idea:
raise an Exception
immediately catch it in an Except clause
use sys.exc_info to get Traceback frame (tb_frame).
from tb_frame get last caller's frame using f_back.
from last caller's frame get the code object that was being executed in that frame.
In our sample code it would be method1 (not method2) being executed.
From code object obtained, get the object's name -- this is caller method's name in our sample.
Here's the sample code to solve example in the question:
def method1():
method2()
def method2():
try:
raise Exception
except Exception:
frame = sys.exc_info()[2].tb_frame.f_back
print("method2 invoked by: ", frame.f_code.co_name)
# Invoking method1
method1()
Output:
method2 invoked by: method1
Frame has all sorts of details, including line number, file name, argument counts, argument type and so on. The solution works across classes and modules too.
Code:
#!/usr/bin/env python
import inspect
called=lambda: inspect.stack()[1][3]
def caller1():
print "inside: ",called()
def caller2():
print "inside: ",called()
if __name__=='__main__':
caller1()
caller2()
Output:
shahid#shahid-VirtualBox:~/Documents$ python test_func.py
inside: caller1
inside: caller2
shahid#shahid-VirtualBox:~/Documents$
I found a way if you're going across classes and want the class the method belongs to AND the method. It takes a bit of extraction work but it makes its point. This works in Python 2.7.13.
import inspect, os
class ClassOne:
def method1(self):
classtwoObj.method2()
class ClassTwo:
def method2(self):
curframe = inspect.currentframe()
calframe = inspect.getouterframes(curframe, 4)
print '\nI was called from', calframe[1][3], \
'in', calframe[1][4][0][6: -2]
# create objects to access class methods
classoneObj = ClassOne()
classtwoObj = ClassTwo()
# start the program
os.system('cls')
classoneObj.method1()
Hey mate I once made 3 methods without plugins for my app and maybe that can help you, It worked for me so maybe gonna work for you too.
def method_1(a=""):
if a == "method_2":
print("method_2")
if a == "method_3":
print("method_3")
def method_2():
method_1("method_2")
def method_3():
method_1("method_3")
method_2()

How can I split a long function into separate steps while maintaining the relationship between said steps?

I have a very long function func which takes a browser handle and performs a bunch of requests and reads a bunch of responses in a specific order:
def func(browser):
# make sure we are logged in otherwise log in
# make request to /search and check that the page has loaded
# fill form in /search and submit it
# read table of response and return the result as list of objects
Each operation require a large amount of code due to the complexity of the DOM and they tend to grow really fast.
What would be the best way to refactor this function into smaller components so that the following properties still hold:
the execution flow of the operations and/or their preconditions is guaranteed just like in the current version
the preconditions are not checked with asserts against the state, as this is a very costly operation
func can be called multiple times on the browser
?
Just wrap the three helper methods in a class, and track which methods are allowed to run in an instance.
class Helper(object):
def __init__(self):
self.a = True
self.b = False
self.c = False
def funcA(self):
if not self.A:
raise Error("Cannot run funcA now")
# do stuff here
self.a = False
self.b = True
return whatever
def funcB(self):
if not self.B:
raise Error("Cannot run funcB now")
# do stuff here
self.b = False
self.c = True
return whatever
def funcC(self):
if not self.C:
raise Error("Cannot run funcC now")
# do stuff here
self.c = False
self.a = True
return whatever
def func(...):
h = Helper()
h.funcA()
h.funcB()
h.funcC()
# etc
The only way to call a method is if its flag is true, and each method clears its own flag and sets the next method's flag before exiting. As long as you don't touch h.a et al. directly, this ensures that each method can only be called in the proper order.
Alternately, you can use a single flag that is a reference to the function currently allowed to run.
class Helper(object):
def __init__(self):
self.allowed = self.funcA
def funcA(self):
if self.allowed is not self.funcA:
raise Error("Cannot run funcA now")
# do stuff
self.allowed = self.funcB
return whatever
# etc
Here's the solution I came up with. I used a decorator (closely related to the one in this blog post) which only allows for a function to be called once.
def call_only_once(func):
def new_func(*args, **kwargs):
if not new_func._called:
try:
return func(*args, **kwargs)
finally:
new_func._called = True
else:
raise Exception("Already called this once.")
new_func._called = False
return new_func
#call_only_once
def stateA():
print 'Calling stateA only this time'
#call_only_once
def stateB():
print 'Calling stateB only this time'
#call_only_once
def stateC():
print 'Calling stateC only this time'
def state():
stateA()
stateB()
stateC()
if __name__ == "__main__":
state()
You'll see that if you re-call any of the functions, the function will throw an Exception stating that the functions have already been called.
The problem with this is that if you ever need to call state() again, you're hosed. Unless you implement these functions as private functions, I don't think you can do exactly what you want due to the nature of Python's scoping rules.
Edit
You can also remove the else in the decorator and your function will always return None.
Here a snippet I used once for my state machine
class StateMachine(object):
def __init__(self):
self.handlers = {}
self.start_state = None
self.end_states = []
def add_state(self, name, handler, end_state=0):
name = name.upper()
self.handlers[name] = handler
if end_state:
self.end_states.append(name)
def set_start(self, name):
# startup state
self.start_state = name
def run(self, **kw):
"""
Run
:param kw:
:return:
"""
# the first .run call call the first handler with kw keywords
# each registered handler should returns the following handler and the needed kw
try:
handler = self.handlers[self.start_state]
except:
raise InitializationError("must call .set_start() before .run()")
while True:
(new_state, kw) = handler(**kw)
if isinstance(new_state, str):
if new_state in self.end_states:
print("reached ", new_state)
break
else:
handler = self.handlers[new_state]
elif hasattr(new_state, "__call__"):
handler = new_state
else:
return
The use
class MyParser(StateMachine):
def __init__(self):
super().__init__()
# define handlers
# we can define many handler as we want
self.handlers["begin_parse"] = self.begin_parse
# define the startup handler
self.set_start("begin_parse")
def end(self, **kw):
logging.info("End of parsing ")
# no callable handler => end
return None, None
def second(self, **kw):
logging.info("second ")
# do something
# if condition is reach the call `self.end` handler
if ...:
return self.end, {}
def begin_parse(self, **kw):
logging.info("start of parsing ")
# long process until the condition is reach then call the `self.second` handler with kw new keywords
while True:
kw = {}
if ...:
return self.second, kw
# elif other cond:
# return self.other_handler, kw
# elif other cond 2:
# return self.other_handler 2, kw
else:
return self.end, kw
# start the state machine
MyParser().run()
will print
INFO:root:start of parsing
INFO:root:second
INFO:root:End of parsing
You could use local functions in your func function. Ok, they are still declared inside one single global function, but Python is nice enough to still give you access to them for tests.
Here is one example of one function declaring and executing 3 (supposedly heavy) subfunctions. It takes one optional parameter test that when set to TEST prevent actual execution but instead gives external access to individual sub-functions and to a local variable:
def func(test=None):
glob = []
def partA():
glob.append('A')
def partB():
glob.append('B')
def partC():
glob.append('C')
if (test == 'TEST'):
global testA, testB, testC, testCR
testA, testB, testC, testCR = partA, partB, partC, glob
return None
partA()
partB()
partC()
return glob
When you call func, the 3 parts are executed in sequence. But if you first call func('TEST'), you can then access the local glob variable as testCR, and the 3 subfunctions as testA, testB and testC. This way you can still test individually the 3 parts with well defined input and control their output.
I would insist on the suggestion given by #user3159253 in his comment on the original question:
If the sole purpose is readability I would split the func into three "private" > or "protected" ones (i.e. _func1 or __func1) and a private or protected property > which keeps the state shared between the functions.
This makes a lot of sense to me and seems more usual amongst object oriented programming than the other options. Consider this example as an alternative:
Your class (teste.py):
class Test:
def __init__(self):
self.__environment = {} # Protected information to be shared
self.public_stuff = 'public info' # Accessible to outside callers
def func(self):
print "Main function"
self.__func_a()
self.__func_b()
self.__func_c()
print self.__environment
def __func_a(self):
self.__environment['function a says'] = 'hi'
def __func_b(self):
self.__environment['function b says'] = 'hello'
def __func_c(self):
self.__environment['function c says'] = 'hey'
Other file:
from teste import Test
t = Test()
t.func()
This will output:
Main function says hey guys
{'function a says': 'hi', 'function b says': 'hello', 'function c says': 'hey'}
If you try to call one of the protected functions, an error occurs:
Traceback (most recent call last):
File "C:/Users/Lucas/PycharmProjects/testes/other.py", line 6, in <module>
t.__func_a()
AttributeError: Test instance has no attribute '__func_a'
Same thing if you try to access the protected environment variable:
Traceback (most recent call last):
File "C:/Users/Lucas/PycharmProjects/testes/other.py", line 5, in <module>
print t.__environment
AttributeError: Test instance has no attribute '__environment'
In my view this is the most elegant, simple and readable way to solve your problem, let me know if it fits your needs :)

Python observer/observable library [duplicate]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
Are there any exemplary examples of the GoF Observer implemented in Python? I have a bit code which currently has bits of debugging code laced through the key class (currently generating messages to stderr if a magic env is set). Additionally, the class has an interface for incrementally return results as well as storing them (in memory) for post processing. (The class itself is a job manager for concurrently executing commands on remote machines over ssh).
Currently the usage of the class looks something like:
job = SSHJobMan(hostlist, cmd)
job.start()
while not job.done():
for each in job.poll():
incrementally_process(job.results[each])
time.sleep(0.2) # or other more useful work
post_process(job.results)
An alernative usage model is:
job = SSHJobMan(hostlist, cmd)
job.wait() # implicitly performs a start()
process(job.results)
This all works fine for the current utility. However it does lack flexibility. For example I currently support a brief output format or a progress bar as incremental results, I also support
brief, complete and "merged message" outputs for the post_process() function.
However, I'd like to support multiple results/output streams (progress bar to the terminal, debugging and warnings to a log file, outputs from successful jobs to one file/directory, error messages and other results from non-successful jobs to another, etc).
This sounds like a situation that calls for Observer ... have instances of my class accept registration from other objects and call them back with specific types of events as they occur.
I'm looking at PyPubSub since I saw several references to that in SO related questions. I'm not sure I'm ready to add the external dependency to my utility but I could see value in using their interface as a model for mine if that's going to make it easier for others to use. (The project is intended as both a standalone command line utility and a class for writing other scripts/utilities).
In short I know how to do what I want ... but there are numerous ways to accomplish it. I want suggestions on what's most likely to work for other users of the code in the long run.
The code itself is at: classh.
However it does lack flexibility.
Well... actually, this looks like a good design to me if an asynchronous API is what you want. It usually is. Maybe all you need is to switch from stderr to Python's logging module, which has a sort of publish/subscribe model of its own, what with Logger.addHandler() and so on.
If you do want to support observers, my advice is to keep it simple. You really only need a few lines of code.
class Event(object):
pass
class Observable(object):
def __init__(self):
self.callbacks = []
def subscribe(self, callback):
self.callbacks.append(callback)
def fire(self, **attrs):
e = Event()
e.source = self
for k, v in attrs.items():
setattr(e, k, v)
for fn in self.callbacks:
fn(e)
Your Job class can subclass Observable. When something of interest happens, call self.fire(type="progress", percent=50) or the like.
I think people in the other answers overdo it. You can easily achieve events in Python with less than 15 lines of code.
You simple have two classes: Event and Observer. Any class that wants to listen for an event, needs to inherit Observer and set to listen (observe) for a specific event. When an Event is instantiated and fired, all observers listening to that event will run the specified callback functions.
class Observer():
_observers = []
def __init__(self):
self._observers.append(self)
self._observables = {}
def observe(self, event_name, callback):
self._observables[event_name] = callback
class Event():
def __init__(self, name, data, autofire = True):
self.name = name
self.data = data
if autofire:
self.fire()
def fire(self):
for observer in Observer._observers:
if self.name in observer._observables:
observer._observables[self.name](self.data)
Example:
class Room(Observer):
def __init__(self):
print("Room is ready.")
Observer.__init__(self) # Observer's init needs to be called
def someone_arrived(self, who):
print(who + " has arrived!")
room = Room()
room.observe('someone arrived', room.someone_arrived)
Event('someone arrived', 'Lenard')
Output:
Room is ready.
Lenard has arrived!
A few more approaches...
Example: the logging module
Maybe all you need is to switch from stderr to Python's logging module, which has a powerful publish/subscribe model.
It's easy to get started producing log records.
# producer
import logging
log = logging.getLogger("myjobs") # that's all the setup you need
class MyJob(object):
def run(self):
log.info("starting job")
n = 10
for i in range(n):
log.info("%.1f%% done" % (100.0 * i / n))
log.info("work complete")
On the consumer side there's a bit more work. Unfortunately configuring logger output takes, like, 7 whole lines of code to do. ;)
# consumer
import myjobs, sys, logging
if user_wants_log_output:
ch = logging.StreamHandler(sys.stderr)
ch.setLevel(logging.INFO)
formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(message)s")
ch.setFormatter(formatter)
myjobs.log.addHandler(ch)
myjobs.log.setLevel(logging.INFO)
myjobs.MyJob().run()
On the other hand there's an amazing amount of stuff in the logging package. If you ever need to send log data to a rotating set of files, an email address, and the Windows Event Log, you're covered.
Example: simplest possible observer
But you don't need to use any library at all. An extremely simple way to support observers is to call a method that does nothing.
# producer
class MyJob(object):
def on_progress(self, pct):
"""Called when progress is made. pct is the percent complete.
By default this does nothing. The user may override this method
or even just assign to it."""
pass
def run(self):
n = 10
for i in range(n):
self.on_progress(100.0 * i / n)
self.on_progress(100.0)
# consumer
import sys, myjobs
job = myjobs.MyJob()
job.on_progress = lambda pct: sys.stdout.write("%.1f%% done\n" % pct)
job.run()
Sometimes instead of writing a lambda, you can just say job.on_progress = progressBar.update, which is nice.
This is about as simple as it gets. One drawback is that it doesn't naturally support multiple listeners subscribing to the same events.
Example: C#-like events
With a bit of support code, you can get C#-like events in Python. Here's the code:
# glue code
class event(object):
def __init__(self, func):
self.__doc__ = func.__doc__
self._key = ' ' + func.__name__
def __get__(self, obj, cls):
try:
return obj.__dict__[self._key]
except KeyError, exc:
be = obj.__dict__[self._key] = boundevent()
return be
class boundevent(object):
def __init__(self):
self._fns = []
def __iadd__(self, fn):
self._fns.append(fn)
return self
def __isub__(self, fn):
self._fns.remove(fn)
return self
def __call__(self, *args, **kwargs):
for f in self._fns[:]:
f(*args, **kwargs)
The producer declares the event using a decorator:
# producer
class MyJob(object):
#event
def progress(pct):
"""Called when progress is made. pct is the percent complete."""
def run(self):
n = 10
for i in range(n+1):
self.progress(100.0 * i / n)
#consumer
import sys, myjobs
job = myjobs.MyJob()
job.progress += lambda pct: sys.stdout.write("%.1f%% done\n" % pct)
job.run()
This works exactly like the "simple observer" code above, but you can add as many listeners as you like using +=. (Unlike C#, there are no event handler types, you don't have to new EventHandler(foo.bar) when subscribing to an event, and you don't have to check for null before firing the event. Like C#, events do not squelch exceptions.)
How to choose
If logging does everything you need, use that. Otherwise do the simplest thing that works for you. The key thing to note is that you don't need to take on a big external dependency.
How about an implementation where objects aren't kept alive just because they're observing something? Below please find an implementation of the observer pattern with the following features:
Usage is pythonic. To add an observer to a bound method .bar of instance foo, just do foo.bar.addObserver(observer).
Observers are not kept alive by virtue of being observers. In other words, the observer code uses no strong references.
No sub-classing necessary (descriptors ftw).
Can be used with unhashable types.
Can be used as many times you want in a single class.
(bonus) As of today the code exists in a proper downloadable, installable package on github.
Here's the code (the github package or PyPI package have the most up to date implementation):
import weakref
import functools
class ObservableMethod(object):
"""
A proxy for a bound method which can be observed.
I behave like a bound method, but other bound methods can subscribe to be
called whenever I am called.
"""
def __init__(self, obj, func):
self.func = func
functools.update_wrapper(self, func)
self.objectWeakRef = weakref.ref(obj)
self.callbacks = {} #observing object ID -> weak ref, methodNames
def addObserver(self, boundMethod):
"""
Register a bound method to observe this ObservableMethod.
The observing method will be called whenever this ObservableMethod is
called, and with the same arguments and keyword arguments. If a
boundMethod has already been registered to as a callback, trying to add
it again does nothing. In other words, there is no way to sign up an
observer to be called back multiple times.
"""
obj = boundMethod.__self__
ID = id(obj)
if ID in self.callbacks:
s = self.callbacks[ID][1]
else:
wr = weakref.ref(obj, Cleanup(ID, self.callbacks))
s = set()
self.callbacks[ID] = (wr, s)
s.add(boundMethod.__name__)
def discardObserver(self, boundMethod):
"""
Un-register a bound method.
"""
obj = boundMethod.__self__
if id(obj) in self.callbacks:
self.callbacks[id(obj)][1].discard(boundMethod.__name__)
def __call__(self, *arg, **kw):
"""
Invoke the method which I proxy, and all of it's callbacks.
The callbacks are called with the same *args and **kw as the main
method.
"""
result = self.func(self.objectWeakRef(), *arg, **kw)
for ID in self.callbacks:
wr, methodNames = self.callbacks[ID]
obj = wr()
for methodName in methodNames:
getattr(obj, methodName)(*arg, **kw)
return result
#property
def __self__(self):
"""
Get a strong reference to the object owning this ObservableMethod
This is needed so that ObservableMethod instances can observe other
ObservableMethod instances.
"""
return self.objectWeakRef()
class ObservableMethodDescriptor(object):
def __init__(self, func):
"""
To each instance of the class using this descriptor, I associate an
ObservableMethod.
"""
self.instances = {} # Instance id -> (weak ref, Observablemethod)
self._func = func
def __get__(self, inst, cls):
if inst is None:
return self
ID = id(inst)
if ID in self.instances:
wr, om = self.instances[ID]
if not wr():
msg = "Object id %d should have been cleaned up"%(ID,)
raise RuntimeError(msg)
else:
wr = weakref.ref(inst, Cleanup(ID, self.instances))
om = ObservableMethod(inst, self._func)
self.instances[ID] = (wr, om)
return om
def __set__(self, inst, val):
raise RuntimeError("Assigning to ObservableMethod not supported")
def event(func):
return ObservableMethodDescriptor(func)
class Cleanup(object):
"""
I manage remove elements from a dict whenever I'm called.
Use me as a weakref.ref callback to remove an object's id from a dict
when that object is garbage collected.
"""
def __init__(self, key, d):
self.key = key
self.d = d
def __call__(self, wr):
del self.d[self.key]
To use this we just decorate methods we want to make observable with #event. Here's an example
class Foo(object):
def __init__(self, name):
self.name = name
#event
def bar(self):
print("%s called bar"%(self.name,))
def baz(self):
print("%s called baz"%(self.name,))
a = Foo('a')
b = Foo('b')
a.bar.addObserver(b.bar)
a.bar()
From wikipedia:
from collections import defaultdict
class Observable (defaultdict):
def __init__ (self):
defaultdict.__init__(self, object)
def emit (self, *args):
'''Pass parameters to all observers and update states.'''
for subscriber in self:
response = subscriber(*args)
self[subscriber] = response
def subscribe (self, subscriber):
'''Add a new subscriber to self.'''
self[subscriber]
def stat (self):
'''Return a tuple containing the state of each observer.'''
return tuple(self.values())
The Observable is used like this.
myObservable = Observable ()
# subscribe some inlined functions.
# myObservable[lambda x, y: x * y] would also work here.
myObservable.subscribe(lambda x, y: x * y)
myObservable.subscribe(lambda x, y: float(x) / y)
myObservable.subscribe(lambda x, y: x + y)
myObservable.subscribe(lambda x, y: x - y)
# emit parameters to each observer
myObservable.emit(6, 2)
# get updated values
myObservable.stat() # returns: (8, 3.0, 4, 12)
Based on Jason's answer, I implemented the C#-like events example as a fully-fledged python module including documentation and tests. I love fancy pythonic stuff :)
So, if you want some ready-to-use solution, you can just use the code on github.
Example: twisted log observers
To register an observer yourCallable() (a callable that accepts a dictionary) to receive all log events (in addition to any other observers):
twisted.python.log.addObserver(yourCallable)
Example: complete producer/consumer example
From Twisted-Python mailing list:
#!/usr/bin/env python
"""Serve as a sample implementation of a twisted producer/consumer
system, with a simple TCP server which asks the user how many random
integers they want, and it sends the result set back to the user, one
result per line."""
import random
from zope.interface import implements
from twisted.internet import interfaces, reactor
from twisted.internet.protocol import Factory
from twisted.protocols.basic import LineReceiver
class Producer:
"""Send back the requested number of random integers to the client."""
implements(interfaces.IPushProducer)
def __init__(self, proto, cnt):
self._proto = proto
self._goal = cnt
self._produced = 0
self._paused = False
def pauseProducing(self):
"""When we've produced data too fast, pauseProducing() will be
called (reentrantly from within resumeProducing's transport.write
method, most likely), so set a flag that causes production to pause
temporarily."""
self._paused = True
print('pausing connection from %s' % (self._proto.transport.getPeer()))
def resumeProducing(self):
self._paused = False
while not self._paused and self._produced < self._goal:
next_int = random.randint(0, 10000)
self._proto.transport.write('%d\r\n' % (next_int))
self._produced += 1
if self._produced == self._goal:
self._proto.transport.unregisterProducer()
self._proto.transport.loseConnection()
def stopProducing(self):
pass
class ServeRandom(LineReceiver):
"""Serve up random data."""
def connectionMade(self):
print('connection made from %s' % (self.transport.getPeer()))
self.transport.write('how many random integers do you want?\r\n')
def lineReceived(self, line):
cnt = int(line.strip())
producer = Producer(self, cnt)
self.transport.registerProducer(producer, True)
producer.resumeProducing()
def connectionLost(self, reason):
print('connection lost from %s' % (self.transport.getPeer()))
factory = Factory()
factory.protocol = ServeRandom
reactor.listenTCP(1234, factory)
print('listening on 1234...')
reactor.run()
OP asks "Are there any exemplary examples of the GoF Observer implemented in Python?"
This is an example in Python 3.7. This Observable class meets the requirement of creating a relationship between one observable and many observers while remaining independent of their structure.
from functools import partial
from dataclasses import dataclass, field
import sys
from typing import List, Callable
#dataclass
class Observable:
observers: List[Callable] = field(default_factory=list)
def register(self, observer: Callable):
self.observers.append(observer)
def deregister(self, observer: Callable):
self.observers.remove(observer)
def notify(self, *args, **kwargs):
for observer in self.observers:
observer(*args, **kwargs)
def usage_demo():
observable = Observable()
# Register two anonymous observers using lambda.
observable.register(
lambda *args, **kwargs: print(f'Observer 1 called with args={args}, kwargs={kwargs}'))
observable.register(
lambda *args, **kwargs: print(f'Observer 2 called with args={args}, kwargs={kwargs}'))
# Create an observer function, register it, then deregister it.
def callable_3():
print('Observer 3 NOT called.')
observable.register(callable_3)
observable.deregister(callable_3)
# Create a general purpose observer function and register four observers.
def callable_x(*args, **kwargs):
print(f'{args[0]} observer called with args={args}, kwargs={kwargs}')
for gui_field in ['Form field 4', 'Form field 5', 'Form field 6', 'Form field 7']:
observable.register(partial(callable_x, gui_field))
observable.notify('test')
if __name__ == '__main__':
sys.exit(usage_demo())
A functional approach to observer design:
def add_listener(obj, method_name, listener):
# Get any existing listeners
listener_attr = method_name + '_listeners'
listeners = getattr(obj, listener_attr, None)
# If this is the first listener, then set up the method wrapper
if not listeners:
listeners = [listener]
setattr(obj, listener_attr, listeners)
# Get the object's method
method = getattr(obj, method_name)
#wraps(method)
def method_wrapper(*args, **kwags):
method(*args, **kwags)
for l in listeners:
l(obj, *args, **kwags) # Listener also has object argument
# Replace the original method with the wrapper
setattr(obj, method_name, method_wrapper)
else:
# Event is already set up, so just add another listener
listeners.append(listener)
def remove_listener(obj, method_name, listener):
# Get any existing listeners
listener_attr = method_name + '_listeners'
listeners = getattr(obj, listener_attr, None)
if listeners:
# Remove the listener
next((listeners.pop(i)
for i, l in enumerate(listeners)
if l == listener),
None)
# If this was the last listener, then remove the method wrapper
if not listeners:
method = getattr(obj, method_name)
delattr(obj, listener_attr)
setattr(obj, method_name, method.__wrapped__)
These methods can then be used to add a listener to any class method. For example:
class MyClass(object):
def __init__(self, prop):
self.prop = prop
def some_method(self, num, string):
print('method:', num, string)
def listener_method(obj, num, string):
print('listener:', num, string, obj.prop)
my = MyClass('my_prop')
add_listener(my, 'some_method', listener_method)
my.some_method(42, 'with listener')
remove_listener(my, 'some_method', listener_method)
my.some_method(42, 'without listener')
And the output is:
method: 42 with listener
listener: 42 with listener my_prop
method: 42 without listener

How to watch for a variable change in python without dunder setattr or pdb

There is large python project where one attribute of one class just have wrong value in some place.
It should be sqlalchemy.orm.attributes.InstrumentedAttribute, but when I run tests it is constant value, let's say string.
There is some way to run python program in debug mode, and run some check (if variable changed type) after each step throught line of code automatically?
P.S. I know how to log changes of attribute of class instance with help of inspect and property decorator. Possibly here I can use this method with metaclasses...
But sometimes I need more general and powerfull solution...
Thank you.
P.P.S. I need something like there: https://stackoverflow.com/a/7669165/816449, but may be with more explanation of what is going on in that code.
Well, here is a sort of slow approach. It can be modified for watching for local variable change (just by name). Here is how it works: we do sys.settrace and analyse the value of obj.attr each step. The tricky part is that we receive 'line' events (that some line was executed) before line is executed. So, when we notice that obj.attr has changed, we are already on the next line and we can't get the previous line frame (because frames aren't copied for each line, they are modified ). So on each line event I save traceback.format_stack to watcher.prev_st and if on the next call of trace_command value has changed, we print the saved stack trace to file. Saving traceback on each line is quite an expensive operation, so you'd have to set include keyword to a list of your projects directories (or just the root of your project) in order not to watch how other libraries are doing their stuff and waste cpu.
watcher.py
import traceback
class Watcher(object):
def __init__(self, obj=None, attr=None, log_file='log.txt', include=[], enabled=False):
"""
Debugger that watches for changes in object attributes
obj - object to be watched
attr - string, name of attribute
log_file - string, where to write output
include - list of strings, debug files only in these directories.
Set it to path of your project otherwise it will take long time
to run on big libraries import and usage.
"""
self.log_file=log_file
with open(self.log_file, 'wb'): pass
self.prev_st = None
self.include = [incl.replace('\\','/') for incl in include]
if obj:
self.value = getattr(obj, attr)
self.obj = obj
self.attr = attr
self.enabled = enabled # Important, must be last line on __init__.
def __call__(self, *args, **kwargs):
kwargs['enabled'] = True
self.__init__(*args, **kwargs)
def check_condition(self):
tmp = getattr(self.obj, self.attr)
result = tmp != self.value
self.value = tmp
return result
def trace_command(self, frame, event, arg):
if event!='line' or not self.enabled:
return self.trace_command
if self.check_condition():
if self.prev_st:
with open(self.log_file, 'ab') as f:
print >>f, "Value of",self.obj,".",self.attr,"changed!"
print >>f,"###### Line:"
print >>f,''.join(self.prev_st)
if self.include:
fname = frame.f_code.co_filename.replace('\\','/')
to_include = False
for incl in self.include:
if fname.startswith(incl):
to_include = True
break
if not to_include:
return self.trace_command
self.prev_st = traceback.format_stack(frame)
return self.trace_command
import sys
watcher = Watcher()
sys.settrace(watcher.trace_command)
testwatcher.py
from watcher import watcher
import numpy as np
import urllib2
class X(object):
def __init__(self, foo):
self.foo = foo
class Y(object):
def __init__(self, x):
self.xoo = x
def boom(self):
self.xoo.foo = "xoo foo!"
def main():
x = X(50)
watcher(x, 'foo', log_file='log.txt', include =['C:/Users/j/PycharmProjects/hello'])
x.foo = 500
x.goo = 300
y = Y(x)
y.boom()
arr = np.arange(0,100,0.1)
arr = arr**2
for i in xrange(3):
print 'a'
x.foo = i
for i in xrange(1):
i = i+1
main()
There's a very simple way to do this: use watchpoints.
Basically you only need to do
from watchpoints import watch
watch(your_object.attr)
That's it. Whenever the attribute is changed, it will print out the line that changed it and how it's changed. Super easy to use.
It also has more advanced features, for example, you can call pdb when the variable is changed, or use your own callback functions instead of print it to stdout.
A simpler way to watch for an object's attribute change (which can also be a module-level variable or anything accessible with getattr) would be to leverage hunter library, a flexible code tracing toolkit. To detect state changes we need a predicate which can look like the following:
import traceback
class MutationWatcher:
def __init__(self, target, attrs):
self.target = target
self.state = {k: getattr(target, k) for k in attrs}
def __call__(self, event):
result = False
for k, v in self.state.items():
current_value = getattr(self.target, k)
if v != current_value:
result = True
self.state[k] = current_value
print('Value of attribute {} has chaned from {!r} to {!r}'.format(
k, v, current_value))
if result:
traceback.print_stack(event.frame)
return result
Then given a sample code:
class TargetThatChangesWeirdly:
attr_name = 1
def some_nested_function_that_does_the_nasty_mutation(obj):
obj.attr_name = 2
def some_public_api(obj):
some_nested_function_that_does_the_nasty_mutation(obj)
We can instrument it with hunter like:
# or any other entry point that calls the public API of interest
if __name__ == '__main__':
obj = TargetThatChangesWeirdly()
import hunter
watcher = MutationWatcher(obj, ['attr_name'])
hunter.trace(watcher, stdlib=False, action=hunter.CodePrinter)
some_public_api(obj)
Running the module produces:
Value of attribute attr_name has chaned from 1 to 2
File "test.py", line 44, in <module>
some_public_api(obj)
File "test.py", line 10, in some_public_api
some_nested_function_that_does_the_nasty_mutation(obj)
File "test.py", line 6, in some_nested_function_that_does_the_nasty_mutation
obj.attr_name = 2
test.py:6 return obj.attr_name = 2
... return value: None
You can also use other actions that hunter supports. For instance, Debugger which breaks into pdb (debugger on an attribute change).
Try using __setattr__ to override the function that is called when an attribute assignment is attempted. Documentation for __setattr__
You can use the python debugger module (part of the standard library)
To use, just import pdb at the top of your source file:
import pdb
and then set a trace wherever you want to start inspecting the code:
pdb.set_trace()
You can then step through the code with n, and investigate the current state by running python commands.
def __setattr__(self, name, value):
if name=="xxx":
util.output_stack('xxxxx')
super(XXX, self).__setattr__(name, value)
This sample code helped me.

Updating a TKinter GUI from a multiprocessing calculation

I'm creating a GUI for a python simulator. The GUI provides tools to set up the simulation and run it. While the simulation is running I want to pass progress information to the GUI and have it displayed on a Label in my simulation_frame. Because the simulations need to be run with multiprocessing, I'm using a Queue to pass the updated information back to the GUI.
The way I have it set up, running the simulations blocks the Tk mainloop since I need to be able to close my Pool at the end of the call. I'm calling update_idletasks() to force the GUI to update the progress information.
This seems to me like an inelegant and potentially risky solution. Moreover, while it works in Ubuntu, it does not seem to work in Windows XP--the window goes blank after a second or so of running. I may be able to make it work in Windows by calling update() rather than update_idletasks(), but that seems even worse to me.
Is there a better solution?
The relevant code:
sims = []
queues = []
svars = []
names = []
i = 0
manager = mp.Manager()
for config in self.configs:
name, file, num = config.get()
j = 0
for _ in range(num):
#progress monitor label
q = manager.Queue()
s_var = StringVar()
label = Label(self.sim_frame, textvariable = s_var, bg = "white")
s_var.set("%d: Not Started"%i)
label.grid(row = i, column = 0, sticky = W+N)
self.sim_labels.append(label)
queues.append(q)
svars.append(s_var)
names.append("%s-%d"%(name, j))
sims.append(("%s-%d"%(name, j),file, data, verbose, q))
i += 1
j += 1
self.update()
# The progress tracking is pretty hacky.
pool = mp.Pool(parallel)
num_sims = len(sims)
#start simulating
tracker = pool.map_async(run_1_sim,sims)
while not tracker.ready():
pass
for i in range(num_sims):
q = queues[i]
try:
gen = q.get(timeout = .001)
# if the sim has updated, update the label
#print gen
svars[i].set(gen)
self.update()
except Empty:
pass
# The results of the map, if necessary
tracker.get()
def update(self):
"""
Redraws everything
"""
self.master.update_idletasks()
def run_1_sim(args):
"""
Runs one simulation with the specified args, output updates to the supplied
pipe every generation
"""
name,config,data, verbose, q = args
sim = Simulation(config, name=name, data = data)
generation = 0
q.put(sim.name + ": 0")
try:
while sim.run(verbose=verbose, log=True, generations = sim_step):
generation += sim_step
q.put(sim.name + ": " + str(generation))
except Exception as err:
print err
This may or may not be helpful to you, but it is possible to make tkinter thread-safe by ensuring that its code and methods are executed on the particular thread the root was instantiated on. One project that experimented with the concept can be found over on the Python Cookbook as recipe 577633 (Directory Pruner 2). The code below comes from lines 76 - 253 and is fairly easy to extend with widgets.
Primary Thread-safety Support
# Import several GUI libraries.
import tkinter.ttk
import tkinter.filedialog
import tkinter.messagebox
# Import other needed modules.
import queue
import _thread
import operator
################################################################################
class AffinityLoop:
"Restricts code execution to thread that instance was created on."
__slots__ = '__action', '__thread'
def __init__(self):
"Initialize AffinityLoop with job queue and thread identity."
self.__action = queue.Queue()
self.__thread = _thread.get_ident()
def run(self, func, *args, **keywords):
"Run function on creating thread and return result."
if _thread.get_ident() == self.__thread:
self.__run_jobs()
return func(*args, **keywords)
else:
job = self.__Job(func, args, keywords)
self.__action.put_nowait(job)
return job.result
def __run_jobs(self):
"Run all pending jobs currently in the job queue."
while not self.__action.empty():
job = self.__action.get_nowait()
job.execute()
########################################################################
class __Job:
"Store information to run a job at a later time."
__slots__ = ('__func', '__args', '__keywords',
'__error', '__mutex', '__value')
def __init__(self, func, args, keywords):
"Initialize the job's info and ready for execution."
self.__func = func
self.__args = args
self.__keywords = keywords
self.__error = False
self.__mutex = _thread.allocate_lock()
self.__mutex.acquire()
def execute(self):
"Run the job, store any error, and return to sender."
try:
self.__value = self.__func(*self.__args, **self.__keywords)
except Exception as error:
self.__error = True
self.__value = error
self.__mutex.release()
#property
def result(self):
"Return execution result or raise an error."
self.__mutex.acquire()
if self.__error:
raise self.__value
return self.__value
################################################################################
class _ThreadSafe:
"Create a thread-safe GUI class for safe cross-threaded calls."
ROOT = tkinter.Tk
def __init__(self, master=None, *args, **keywords):
"Initialize a thread-safe wrapper around a GUI base class."
if master is None:
if self.BASE is not self.ROOT:
raise ValueError('Widget must have a master!')
self.__job = AffinityLoop() # Use Affinity() if it does not break.
self.__schedule(self.__initialize, *args, **keywords)
else:
self.master = master
self.__job = master.__job
self.__schedule(self.__initialize, master, *args, **keywords)
def __initialize(self, *args, **keywords):
"Delegate instance creation to later time if necessary."
self.__obj = self.BASE(*args, **keywords)
########################################################################
# Provide a framework for delaying method execution when needed.
def __schedule(self, *args, **keywords):
"Schedule execution of a method till later if necessary."
return self.__job.run(self.__run, *args, **keywords)
#classmethod
def __run(cls, func, *args, **keywords):
"Execute the function after converting the arguments."
args = tuple(cls.unwrap(i) for i in args)
keywords = dict((k, cls.unwrap(v)) for k, v in keywords.items())
return func(*args, **keywords)
#staticmethod
def unwrap(obj):
"Unpack inner objects wrapped by _ThreadSafe instances."
return obj.__obj if isinstance(obj, _ThreadSafe) else obj
########################################################################
# Allow access to and manipulation of wrapped instance's settings.
def __getitem__(self, key):
"Get a configuration option from the underlying object."
return self.__schedule(operator.getitem, self, key)
def __setitem__(self, key, value):
"Set a configuration option on the underlying object."
return self.__schedule(operator.setitem, self, key, value)
########################################################################
# Create attribute proxies for methods and allow their execution.
def __getattr__(self, name):
"Create a requested attribute and return cached result."
attr = self.__Attr(self.__callback, (name,))
setattr(self, name, attr)
return attr
def __callback(self, path, *args, **keywords):
"Schedule execution of named method from attribute proxy."
return self.__schedule(self.__method, path, *args, **keywords)
def __method(self, path, *args, **keywords):
"Extract a method and run it with the provided arguments."
method = self.__obj
for name in path:
method = getattr(method, name)
return method(*args, **keywords)
########################################################################
class __Attr:
"Save an attribute's name and wait for execution."
__slots__ = '__callback', '__path'
def __init__(self, callback, path):
"Initialize proxy with callback and method path."
self.__callback = callback
self.__path = path
def __call__(self, *args, **keywords):
"Run a known method with the given arguments."
return self.__callback(self.__path, *args, **keywords)
def __getattr__(self, name):
"Generate a proxy object for a sub-attribute."
if name in {'__func__', '__name__'}:
# Hack for the "tkinter.__init__.Misc._register" method.
raise AttributeError('This is not a real method!')
return self.__class__(self.__callback, self.__path + (name,))
################################################################################
# Provide thread-safe classes to be used from tkinter.
class Tk(_ThreadSafe): BASE = tkinter.Tk
class Frame(_ThreadSafe): BASE = tkinter.ttk.Frame
class Button(_ThreadSafe): BASE = tkinter.ttk.Button
class Entry(_ThreadSafe): BASE = tkinter.ttk.Entry
class Progressbar(_ThreadSafe): BASE = tkinter.ttk.Progressbar
class Treeview(_ThreadSafe): BASE = tkinter.ttk.Treeview
class Scrollbar(_ThreadSafe): BASE = tkinter.ttk.Scrollbar
class Sizegrip(_ThreadSafe): BASE = tkinter.ttk.Sizegrip
class Menu(_ThreadSafe): BASE = tkinter.Menu
class Directory(_ThreadSafe): BASE = tkinter.filedialog.Directory
class Message(_ThreadSafe): BASE = tkinter.messagebox.Message
If you read the rest of the application, you will find that it is built with the widgets defined as _ThreadSafe variants that you are used to seeing in other tkinter applications. As method calls come in from various threads, they are automatically held until it becomes possible to execute those calls on the creating thread. Note how the mainloop is replaced by way of lines 291 - 298 and 326 - 336.
Notice NoDefaltRoot & main_loop Calls
#classmethod
def main(cls):
"Create an application containing a single TrimDirView widget."
tkinter.NoDefaultRoot()
root = cls.create_application_root()
cls.attach_window_icon(root, ICON)
view = cls.setup_class_instance(root)
cls.main_loop(root)
main_loop Allows Threads To Execute
#staticmethod
def main_loop(root):
"Process all GUI events according to tkinter's settings."
target = time.clock()
while True:
try:
root.update()
except tkinter.TclError:
break
target += tkinter._tkinter.getbusywaitinterval() / 1000
time.sleep(max(target - time.clock(), 0))

Categories

Resources