Python: what did I wrong with Threads or Exceptions? - python

I have the following function:
def getSuggestengineResult(suggestengine, seed, tablename):
table = getTable(tablename)
for keyword_result in results[seed][suggestengine]:
i = 0
while True:
try:
allKeywords.put_item(
Item={
'keyword': keyword_result
}
)
break
except ProvisionedThroughputExceededException as pe:
if (i > 9):
addtoerrortable(keyword_result)
print(pe)
break
sleep(1)
i = i + 1
print("ProvisionedThroughputExceededException in getSugestengineResult")
The function gets started in more then one thread. I have this process and if the process works, the function should be ready in the thread. Otherwise it should try again 9 times. Now my problem:
the "print("ProvisionedThroughputExceededException in getSugestengineResult")" Never got printed. Just the exception as pe gets printed. So there is my problem? Are all the threads working on the same "i"? Or is it never possible to get to the print? I dont know what I am doin wrong ...

You have to use a specific counter if you want all your thread to have the same counter :
from multiprocessing import Lock, Process, Value
class ThreadCounter(object):
def __init__(self, initval=0):
self.val = Value('i', initval)
self.lock = Lock()
def increment(self):
with self.lock:
self.val.value += 1
def value(self):
with self.lock:
return self.val
then you can pass the counter to your function
counter=ThreadCounter(0)
def getSuggestengineResult(suggestengine, seed, tablename,counter):
...
except ProvisionedThroughputExceededException as pe:
if (counter.value() > 9):
...
counter.increment()
...
This counter will be shared with the other threads

Related

Is there a way to prevent the infinite loop after creating an iterable custom object in Python - 3.x?

I'm setting up a library to spawn as many threads as I can and have them complete any task they are assigned too. When unit testing the creation of the object containing 'n' number of threads and trying to iterate over each one at the object level I am running into an infinite loop.
I fixed the pickling issue with race conditions, but now when trying to output how many threads were created in a for loop, when debugging I encounter an infinite loop.
from __future__ import print_function
try:
import sys
from threading import Thread, Lock, current_thread
from queue import Queue
except ImportError:
raise ImportError
class Worker(Thread):
""" Thread executing tasks from a given tasks queue """
def __init__(self, tasks):
Thread.__init__(self)
self.tasks = tasks
self.daemon = True
self.start()
def run(self):
while True:
func, args, kargs = self.tasks.get()
try:
# Acquire locking mechanism for threads to prevent race condition
Lock.acquire()
func(*args, **kargs)
# Release locking mechanism
Lock.release()
except Exception as e:
# An exception happened in this thread
raise e
finally:
if self.tasks is None:
# Mark process done once there are no more tasks to process
self.tasks.task_done()
class SpawnThreads:
"""Pool of threads consuming tasks from a queue."""
def __init__(self, num_threads: int):
self.tasks = Queue(num_threads)
self.num_threads = num_threads
for _ in range(self.num_threads):
Worker(self.tasks)
def __iter__(self):
return self
def __next__(self):
next_value = 0
while next_value < self.num_threads:
try:
next_value += 1
except Exception:
raise StopIteration
return next_value
def add_task(self, func, *args, **kargs):
"""Add a task to the queue."""
self.tasks.put((func, args, kargs))
def task_list(self, func, args_list):
"""Add a list of tasks to the queue."""
for args in args_list:
self.add_task(func, args)
def wait_completion(self):
""".Wait for completion of all the tasks in the queue."""
self.tasks.join()
def get_qsize(self):
"""Return the approximate size of the queue."""
return self.tasks.qsize()
def get_current_thread(self):
return current_thread()
This is the unittest to evaluate the creation of the thread spawning object and iterate and access each individual thread.
import pytest
import unittest
import SpawnThreads
#unittest
class TestThreadFactory(unittest.TestCase):
def test_spawn_threads(self):
workforce = SpawnThreads(5)
self.assertIsNotNone(workforce)
print(workforce)
for w in workforce:
print(w)
The expected output should be the address space/object, which is each thread (5 total).
More Specifically I would like to see this result 5 times in the console:
<ThreadFactory.thread_factory.SpawnThreads object at 0x0000024E851F5208>
I am getting the integer 5 returned infinitely instead of the 5 addresses of threads.
Your __next__ is definitionally always going to return 5 and never end. __next__ isn't a generator function, there is no state on entry aside from what's on self. So you always loop until next_value (a stateless local variable) is equal to self.num_threads (a value which never changes) and return it; your __next__ could simplify to just return self.num_threads, with no chance of StopIteration ever being raised (thus the infinite loop).
If you want it to return different values (specifically, each of your workers), you'll need state for that:
class SpawnThreads:
"""Pool of threads consuming tasks from a queue."""
def __init__(self, num_threads: int):
self.tasks = Queue(num_threads)
self.next_value = 0 # Initial next_value in instance state
self.num_threads = num_threads
# Store list of workers
self.workers = [Worker(self.tasks) for _ in range(self.num_threads)]
def __iter__(self):
return self
def __next__(self):
# Check if iteration has finished
if self.next_value >= self.num_threads:
raise StopIteration
retval = self.workers[self.next_value] # Save value to return to local
self.next_value += 1 # Increment state for next use
return retval # Return value
Those last three lines could be replaced with an alternative tricksy approach to avoid the local variable if you really care:
try:
return self.workers[self.next_value]
finally:
self.next_value += 1
Or even better, you could use Python built-ins to do the work for you:
class SpawnThreads:
"""Pool of threads consuming tasks from a queue."""
def __init__(self, num_threads: int):
self.tasks = Queue(num_threads)
self.num_threads = num_threads
self.workers = [Worker(self.tasks) for _ in range(self.num_threads)]
self.next_worker_iter = iter(self.workers) # Iterates workers
def __iter__(self):
return self
def __next__(self):
# Let the list iterator do the work of maintaining state,
# raising StopIteration, etc.
return next(self.next_worker_iter)
This approach is simpler, faster, and as a bonus, thread-safe, at least on CPython (if two threads iterate the same SpawnThreads instance, each of the workers will be produced exactly once, rather than values potentially being skipped or repeated).
If the goal is to make an iterable (can be iterated multiple times), not an iterator (can be iterated once from beginning to end and never again), the simplest solution is to make __iter__ return an iterator itself, removing the need for __next__ entirely:
class SpawnThreads:
"""Pool of threads consuming tasks from a queue."""
def __init__(self, num_threads: int):
self.tasks = Queue(num_threads)
self.num_threads = num_threads
self.workers = [Worker(self.tasks) for _ in range(self.num_threads)]
def __iter__(self):
# Makes this a generator function that produces each Worker once
yield from self.workers
# Alternatively:
return iter(self.workers)
# though that exposes more implementation details than anonymous generators
The problem is this method:
def __next__(self):
next_value = 0
while next_value < self.num_threads:
try:
next_value += 1
except Exception:
raise StopIteration
return next_value
It's basically the same as
def __next__(self):
return self.num_threads
As you see there isn't any iterator state, it will just return the same number forever. next_value += 1 will never throw an exception, next_value is just an integer.
To achieve what you want, just store the threads in a container and return an iterator to that container. Modify SpawnThreads:
def __init__(self, num_threads: int):
self.tasks = Queue(num_threads)
self.num_threads = num_threads
self.threads = []
for _ in range(self.num_threads):
self.threads.append(Worker(self.tasks));
def __iter__(self):
return iter(self.threads)
# remove the __next__() method

Printing an update line whenever a subprocess finishes in Python 3's multiprocessing Pool

I'm using Python's multiprocessing library to process a list of inputs with the built-in map() method. Here's the relevant code segment:
subp_pool = Pool(self.subprocesses)
cases = subp_pool.map(self.get_case, input_list)
return cases
The function to be run in parallel is self.get_case(), and the list of inputs is input_list.
I wish to print a progress prompt to the standard output in the following format:
Working (25/100 cases processed)
How can I update a local variable inside the class that contains the Pool, so that whenever a subprocess finishes, the variable is incremented by 1 (and then printed to the standard output)?
There's no way to do this using multiprocessing.map, because it doesn't alert the main process about anything until it's completed all its tasks. However, you can get similar behavior by using apply_async in tandem with the callback keyword argument:
from multiprocessing.dummy import Pool
from functools import partial
import time
class Test(object):
def __init__(self):
self.count = 0
self.threads = 4
def get_case(self, x):
time.sleep(x)
def callback(self, total, x):
self.count += 1
print("Working ({}/{}) cases processed.".format(self.count, total))
def do_async(self):
thread_pool = Pool(self.threads)
input_list = range(5)
callback = partial(self.callback, len(input_list))
tasks = [thread_pool.apply_async(self.get_case, (x,),
callback=callback) for x in input_list]
return [task.get() for task in tasks]
if __name__ == "__main__":
t = Test()
t.do_async()
Call the print_data() from the get_case() method and you are done.
from threading import Lock
Class A(object):
def __init__(self):
self.mutex = Lock()
self.count = 0
def print_data(self):
self.mutex.acquire()
try:
self.count += 1
print('Working (' + str(self.count) + 'cases processed)')
finally:
self.mutex.release()

How to let a Python thread finish gracefully

I'm doing a project involving data collection and logging. I have 2 threads running, a collection thread and a logging thread, both started in main. I'm trying to allow the program to be terminated gracefully when with Ctrl-C.
I'm using a threading.Event to signal to the threads to end their respective loops. It works fine to stop the sim_collectData method, but it doesn't seem to be properly stopping the logData thread. The Collection terminated print statement is never executed, and the program just stalls. (It doesn't end, just sits there).
The second while loop in logData is to make sure everything in the queue is logged. The goal is for Ctrl-C to stop the collection thread immediately, then allow the logging thread to finish emptying the queue, and only then fully terminate the program. (Right now, the data is just being printed out - eventually it's going to be logged to a database).
I don't understand why the second thread never terminates. I'm basing what I've done on this answer: Stopping a thread after a certain amount of time. What am I missing?
def sim_collectData(input_queue, stop_event):
''' this provides some output simulating the serial
data from the data logging hardware.
'''
n = 0
while not stop_event.is_set():
input_queue.put("DATA: <here are some random data> " + str(n))
stop_event.wait(random.randint(0,5))
n += 1
print "Terminating data collection..."
return
def logData(input_queue, stop_event):
n = 0
# we *don't* want to loop based on queue size because the queue could
# theoretically be empty while waiting on some data.
while not stop_event.is_set():
d = input_queue.get()
if d.startswith("DATA:"):
print d
input_queue.task_done()
n += 1
# if the stop event is recieved and the previous loop terminates,
# finish logging the rest of the items in the queue.
print "Collection terminated. Logging remaining data to database..."
while not input_queue.empty():
d = input_queue.get()
if d.startswith("DATA:"):
print d
input_queue.task_done()
n += 1
return
def main():
input_queue = Queue.Queue()
stop_event = threading.Event() # used to signal termination to the threads
print "Starting data collection thread...",
collection_thread = threading.Thread(target=sim_collectData, args=(input_queue, stop_event))
collection_thread.start()
print "Done."
print "Starting logging thread...",
logging_thread = threading.Thread(target=logData, args=(input_queue, stop_event))
logging_thread.start()
print "Done."
try:
while True:
time.sleep(10)
except (KeyboardInterrupt, SystemExit):
# stop data collection. Let the logging thread finish logging everything in the queue
stop_event.set()
main()
The problem is that your logger is waiting on d = input_queue.get() and will not check the event. One solution is to skip the event completely and invent a unique message that tells the logger to stop. When you get a signal, send that message to the queue.
import threading
import Queue
import random
import time
def sim_collectData(input_queue, stop_event):
''' this provides some output simulating the serial
data from the data logging hardware.
'''
n = 0
while not stop_event.is_set():
input_queue.put("DATA: <here are some random data> " + str(n))
stop_event.wait(random.randint(0,5))
n += 1
print "Terminating data collection..."
input_queue.put(None)
return
def logData(input_queue):
n = 0
# we *don't* want to loop based on queue size because the queue could
# theoretically be empty while waiting on some data.
while True:
d = input_queue.get()
if d is None:
input_queue.task_done()
return
if d.startswith("DATA:"):
print d
input_queue.task_done()
n += 1
def main():
input_queue = Queue.Queue()
stop_event = threading.Event() # used to signal termination to the threads
print "Starting data collection thread...",
collection_thread = threading.Thread(target=sim_collectData, args=(input_queue, stop_event))
collection_thread.start()
print "Done."
print "Starting logging thread...",
logging_thread = threading.Thread(target=logData, args=(input_queue,))
logging_thread.start()
print "Done."
try:
while True:
time.sleep(10)
except (KeyboardInterrupt, SystemExit):
# stop data collection. Let the logging thread finish logging everything in the queue
stop_event.set()
main()
I'm not an expert in threading, but in your logData function the first d=input_queue.get() is blocking, i.e., if the queue is empty it will sit an wait forever until a queue message is received. This is likely why the logData thread never terminates, it's sitting waiting forever for a queue message.
Refer to the [Python docs] to change this to a non-blocking queue read: use .get(False) or .get_nowait() - but either will require some exception handling for cases when the queue is empty.
You are calling a blocking get on your input_queue with no timeout. In either section of logData, if you call input_queue.get() and the queue is empty, it will block indefinitely, preventing the logging_thread from reaching completion.
To fix, you will want to call input_queue.get_nowait() or pass a timeout to input_queue.get().
Here is my suggestion:
def logData(input_queue, stop_event):
n = 0
while not stop_event.is_set():
try:
d = input_queue.get_nowait()
if d.startswith("DATA:"):
print "LOG: " + d
n += 1
except Queue.Empty:
time.sleep(1)
return
You are also signalling the threads to terminate, but not waiting for them to do so. Consider doing this in your main function.
try:
while True:
time.sleep(10)
except (KeyboardInterrupt, SystemExit):
stop_event.set()
collection_thread.join()
logging_thread.join()
Based on the answer of tdelaney I created an iterator based approach. The iterator exits when the termination message is encountered. I also added a counter of how many get-calls are currently blocking and a stop-method, which sends just as many termination messages. To prevent a race condition between incrementing and reading the counter, I'm setting a stopping bit there. Furthermore I don't use None as the termination message, because it can not necessarily be compared to other data types when using a PriorityQueue.
There are two restrictions, that I had no need to eliminate. For one the stop-method first waits until the queue is empty before shutting down the threads. The second restriction is, that I did not any code to make the queue reusable after stop. The latter can probably be added quite easily, while the former requires being careful about concurrency and the context in which the code is used.
You have to decide whether you want stop to also wait for all the termination messages to be consumed. I choose to put the necessary join there, but you may just remove it.
So this is the code:
import threading, queue
from functools import total_ordering
#total_ordering
class Final:
def __repr__(self):
return "∞"
def __lt__(self, other):
return False
def __eq__(self, other):
return isinstance(other, Final)
Infty = Final()
class IterQueue(queue.Queue):
def __init__(self):
self.lock = threading.Lock()
self.stopped = False
self.getters = 0
super().__init__()
def __iter__(self):
return self
def get(self):
raise NotImplementedError("This queue may only be used as an iterator.")
def __next__(self):
with self.lock:
if self.stopped:
raise StopIteration
self.getters += 1
data = super().get()
if data == Infty:
self.task_done()
raise StopIteration
with self.lock:
self.getters -= 1
return data
def stop(self):
self.join()
self.stopped = True
with self.lock:
for i in range(self.getters):
self.put(Infty)
self.join()
class IterPriorityQueue(IterQueue, queue.PriorityQueue):
pass
Oh, and I wrote this in python 3.2. So after backporting,
import threading, Queue
from functools import total_ordering
#total_ordering
class Final:
def __repr__(self):
return "Infinity"
def __lt__(self, other):
return False
def __eq__(self, other):
return isinstance(other, Final)
Infty = Final()
class IterQueue(Queue.Queue, object):
def __init__(self):
self.lock = threading.Lock()
self.stopped = False
self.getters = 0
super(IterQueue, self).__init__()
def __iter__(self):
return self
def get(self):
raise NotImplementedError("This queue may only be used as an iterator.")
def next(self):
with self.lock:
if self.stopped:
raise StopIteration
self.getters += 1
data = super(IterQueue, self).get()
if data == Infty:
self.task_done()
raise StopIteration
with self.lock:
self.getters -= 1
return data
def stop(self):
self.join()
self.stopped = True
with self.lock:
for i in range(self.getters):
self.put(Infty)
self.join()
class IterPriorityQueue(IterQueue, Queue.PriorityQueue):
pass
you would use it as
import random
import time
def sim_collectData(input_queue, stop_event):
''' this provides some output simulating the serial
data from the data logging hardware.
'''
n = 0
while not stop_event.is_set():
input_queue.put("DATA: <here are some random data> " + str(n))
stop_event.wait(random.randint(0,5))
n += 1
print "Terminating data collection..."
return
def logData(input_queue):
n = 0
# we *don't* want to loop based on queue size because the queue could
# theoretically be empty while waiting on some data.
for d in input_queue:
if d.startswith("DATA:"):
print d
input_queue.task_done()
n += 1
def main():
input_queue = IterQueue()
stop_event = threading.Event() # used to signal termination to the threads
print "Starting data collection thread...",
collection_thread = threading.Thread(target=sim_collectData, args=(input_queue, stop_event))
collection_thread.start()
print "Done."
print "Starting logging thread...",
logging_thread = threading.Thread(target=logData, args=(input_queue,))
logging_thread.start()
print "Done."
try:
while True:
time.sleep(10)
except (KeyboardInterrupt, SystemExit):
# stop data collection. Let the logging thread finish logging everything in the queue
stop_event.set()
input_queue.stop()
main()

Cancellable threading.Timer in Python

I am trying to write a method that counts down to a given time and unless a restart command is given, it will execute the task. But I don't think Python threading.Timer class allows for timer to be cancelable.
import threading
def countdown(action):
def printText():
print 'hello!'
t = threading.Timer(5.0, printText)
if (action == 'reset'):
t.cancel()
t.start()
I know the above code is wrong somehow. Would appreciate some kind guidance over here.
You would call the cancel method after you start the timer:
import time
import threading
def hello():
print "hello, world"
time.sleep(2)
t = threading.Timer(3.0, hello)
t.start()
var = 'something'
if var == 'something':
t.cancel()
You might consider using a while-loop on a Thread, instead of using a Timer.
Here is an example appropriated from Nikolaus Gradwohl's answer to another question:
import threading
import time
class TimerClass(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
self.event = threading.Event()
self.count = 10
def run(self):
while self.count > 0 and not self.event.is_set():
print self.count
self.count -= 1
self.event.wait(1)
def stop(self):
self.event.set()
tmr = TimerClass()
tmr.start()
time.sleep(3)
tmr.stop()
I'm not sure if I understand correctly. Do you want to write something like in this example?
>>> import threading
>>> t = None
>>>
>>> def sayHello():
... global t
... print "Hello!"
... t = threading.Timer(0.5, sayHello)
... t.start()
...
>>> sayHello()
Hello!
Hello!
Hello!
Hello!
Hello!
>>> t.cancel()
>>>
The threading.Timer class does have a cancel method, and although it won't cancel the thread, it will stop the timer from actually firing. What actually happens is that the cancel method sets a threading.Event, and the thread actually executing the threading.Timer will check that event after it's done waiting and before it actually executes the callback.
That said, timers are usually implemented without using a separate thread for each one. The best way to do it depends on what your program is actually doing (while waiting for this timer), but anything with an event loop, like GUI and network frameworks, all have ways to request a timer that is hooked into the eventloop.
Im not sure if best option but for me is woking like this:
t = timer_mgr(.....) append to list "timers.append(t)" and then after all created you can call:
for tm in timers:#threading.enumerate():
print "********", tm.cancel()
my timer_mgr() class is this:
class timer_mgr():
def __init__(self, st, t, hFunction, id, name):
self.is_list = (type(st) is list)
self.st = st
self.t = t
self.id = id
self.hFunction = hFunction
self.thread = threading.Timer(t, self.handle_function, [id])
self.thread.name = name
def handle_function(self, id):
if self.is_list:
print "run_at_time:", datetime.now()
self.hFunction(id)
dt = schedule_fixed_times(datetime.now(), self.st)
print "next:", dt
self.t = (dt-datetime.now()).total_seconds()
else:
self.t = self.st
print "run_every", self.t, datetime.now()
self.hFunction(id)
self.thread = threading.Timer(self.t, self.handle_function, [id])
self.thread.start()
def start(self):
self.thread.start()
def cancel(self):
self.thread.cancel()
Inspired by above post.
Cancelable and Resetting Timer in Python. It uses thread.
Features: Start, Stop, Restart, callback function.
Input: Timeout, sleep_chunk values, and callback_function.
Can use or inherit this class in any other program. Can also pass arguments to the callback function.
Timer should respond in middle also. Not just after completion of full sleep time. So instead of using one full sleep, using small chunks of sleep and kept checking event object in loop.
import threading
import time
class TimerThread(threading.Thread):
def __init__(self, timeout=3, sleep_chunk=0.25, callback=None, *args):
threading.Thread.__init__(self)
self.timeout = timeout
self.sleep_chunk = sleep_chunk
if callback == None:
self.callback = None
else:
self.callback = callback
self.callback_args = args
self.terminate_event = threading.Event()
self.start_event = threading.Event()
self.reset_event = threading.Event()
self.count = self.timeout/self.sleep_chunk
def run(self):
while not self.terminate_event.is_set():
while self.count > 0 and self.start_event.is_set():
# print self.count
# time.sleep(self.sleep_chunk)
# if self.reset_event.is_set():
if self.reset_event.wait(self.sleep_chunk): # wait for a small chunk of timeout
self.reset_event.clear()
self.count = self.timeout/self.sleep_chunk # reset
self.count -= 1
if self.count <= 0:
self.start_event.clear()
#print 'timeout. calling function...'
self.callback(*self.callback_args)
self.count = self.timeout/self.sleep_chunk #reset
def start_timer(self):
self.start_event.set()
def stop_timer(self):
self.start_event.clear()
self.count = self.timeout / self.sleep_chunk # reset
def restart_timer(self):
# reset only if timer is running. otherwise start timer afresh
if self.start_event.is_set():
self.reset_event.set()
else:
self.start_event.set()
def terminate(self):
self.terminate_event.set()
#=================================================================
def my_callback_function():
print 'timeout, do this...'
timeout = 6 # sec
sleep_chunk = .25 # sec
tmr = TimerThread(timeout, sleep_chunk, my_callback_function)
tmr.start()
quit = '0'
while True:
quit = raw_input("Proceed or quit: ")
if quit == 'q':
tmr.terminate()
tmr.join()
break
tmr.start_timer()
if raw_input("Stop ? : ") == 's':
tmr.stop_timer()
if raw_input("Restart ? : ") == 'r':
tmr.restart_timer()

Python generator pre-fetch?

I have a generator that takes a long time for each iteration to run. Is there a standard way to have it yield a value, then generate the next value while waiting to be called again?
The generator would be called each time a button is pressed in a gui and the user would be expected to consider the result after each button press.
EDIT: a workaround might be:
def initialize():
res = next.gen()
def btn_callback()
display(res)
res = next.gen()
if not res:
return
If I wanted to do something like your workaround, I'd write a class like this:
class PrefetchedGenerator(object):
def __init__(self, generator):
self._data = generator.next()
self._generator = generator
self._ready = True
def next(self):
if not self._ready:
self.prefetch()
self._ready = False
return self._data
def prefetch(self):
if not self._ready:
self._data = self._generator.next()
self._ready = True
It is more complicated than your version, because I made it so that it handles not calling prefetch or calling prefetch too many times. The basic idea is that you call .next() when you want the next item. You call prefetch when you have "time" to kill.
Your other option is a thread..
class BackgroundGenerator(threading.Thread):
def __init__(self, generator):
threading.Thread.__init__(self)
self.queue = Queue.Queue(1)
self.generator = generator
self.daemon = True
self.start()
def run(self):
for item in self.generator:
self.queue.put(item)
self.queue.put(None)
def next(self):
next_item = self.queue.get()
if next_item is None:
raise StopIteration
return next_item
This will run separately from your main application. Your GUI should remain responsive no matter how long it takes to fetch each iteration.
No. A generator is not asynchronous. This isn't multiprocessing.
If you want to avoid waiting for the calculation, you should use the multiprocessing package so that an independent process can do your expensive calculation.
You want a separate process which is calculating and enqueueing results.
Your "generator" can then simply dequeue the available results.
You can definitely do this with generators, just create your generator so that each next call alternates between getting the next value and returning it by putting in multiple yield statements. Here is an example:
import itertools, time
def quick_gen():
counter = itertools.count().next
def long_running_func():
time.sleep(2)
return counter()
while True:
x = long_running_func()
yield
yield x
>>> itr = quick_gen()
>>> itr.next() # setup call, takes two seconds
>>> itr.next() # returns immediately
0
>>> itr.next() # setup call, takes two seconds
>>> itr.next() # returns immediately
1
Note that the generator does not automatically do the processing to get the next value, it is up to the caller to call next twice for each value. For your use case you would call next once as a setup up, and then each time the user clicks the button you would display the next value generated, then call next again for the pre-fetch.
I was after something similar. I wanted yield to quickly return a value (if it could) while a background thread processed the next, next.
import Queue
import time
import threading
class MyGen():
def __init__(self):
self.queue = Queue.Queue()
# Put a first element into the queue, and initialize our thread
self.i = 1
self.t = threading.Thread(target=self.worker, args=(self.queue, self.i))
self.t.start()
def __iter__(self):
return self
def worker(self, queue, i):
time.sleep(1) # Take a while to process
queue.put(i**2)
def __del__(self):
self.stop()
def stop(self):
while True: # Flush the queue
try:
self.queue.get(False)
except Queue.Empty:
break
self.t.join()
def next(self):
# Start a thread to compute the next next.
self.t.join()
self.i += 1
self.t = threading.Thread(target=self.worker, args=(self.queue, self.i))
self.t.start()
# Now deliver the already-queued element
while True:
try:
print "request at", time.time()
obj = self.queue.get(False)
self.queue.task_done()
return obj
except Queue.Empty:
pass
time.sleep(.001)
if __name__ == '__main__':
f = MyGen()
for i in range(5):
# time.sleep(2) # Comment out to get items as they are ready
print "*********"
print f.next()
print "returned at", time.time()
The code above gave the following results:
*********
request at 1342462505.96
1
returned at 1342462505.96
*********
request at 1342462506.96
4
returned at 1342462506.96
*********
request at 1342462507.96
9
returned at 1342462507.96
*********
request at 1342462508.96
16
returned at 1342462508.96
*********
request at 1342462509.96
25
returned at 1342462509.96

Categories