feat(assessment): auto comprehensive assessment - rules engine from college scoring standard, per-semester stats, manual overrides, word export

This commit is contained in:
root
2026-10-17 15:40:07 +08:00
parent a0e2ded426
commit 49d8400722
2395 changed files with 1306906 additions and 94 deletions
@@ -0,0 +1 @@
# This directory is a Python package.
@@ -0,0 +1,51 @@
# Copyright 2009 Brian Quinlan. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""Execute computations asynchronously using threads or processes."""
__author__ = 'Brian Quinlan (brian@sweetapp.com)'
from concurrent.futures._base import (FIRST_COMPLETED,
FIRST_EXCEPTION,
ALL_COMPLETED,
CancelledError,
TimeoutError,
InvalidStateError,
BrokenExecutor,
Future,
Executor,
wait,
as_completed)
lazy from .process import ProcessPoolExecutor
lazy from .thread import ThreadPoolExecutor
__all__ = [
'FIRST_COMPLETED',
'FIRST_EXCEPTION',
'ALL_COMPLETED',
'CancelledError',
'TimeoutError',
'InvalidStateError',
'BrokenExecutor',
'Future',
'Executor',
'wait',
'as_completed',
'ProcessPoolExecutor',
'ThreadPoolExecutor',
]
try:
import _interpreters
except ImportError:
_interpreters = None
if _interpreters:
lazy from .interpreter import InterpreterPoolExecutor # noqa: F401
__all__.append('InterpreterPoolExecutor')
def __dir__():
return __all__ + ['__author__', '__doc__']
@@ -0,0 +1,707 @@
# Copyright 2009 Brian Quinlan. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
__author__ = 'Brian Quinlan (brian@sweetapp.com)'
import collections
import logging
import threading
import time
import types
import weakref
from itertools import islice
FIRST_COMPLETED = 'FIRST_COMPLETED'
FIRST_EXCEPTION = 'FIRST_EXCEPTION'
ALL_COMPLETED = 'ALL_COMPLETED'
_AS_COMPLETED = '_AS_COMPLETED'
# Possible future states (for internal use by the futures package).
PENDING = 'PENDING'
RUNNING = 'RUNNING'
# The future was cancelled by the user...
CANCELLED = 'CANCELLED'
# ...and _Waiter.add_cancelled() was called by a worker.
CANCELLED_AND_NOTIFIED = 'CANCELLED_AND_NOTIFIED'
FINISHED = 'FINISHED'
_STATE_TO_DESCRIPTION_MAP = {
PENDING: "pending",
RUNNING: "running",
CANCELLED: "cancelled",
CANCELLED_AND_NOTIFIED: "cancelled",
FINISHED: "finished"
}
# Logger for internal use by the futures package.
LOGGER = logging.getLogger("concurrent.futures")
class Error(Exception):
"""Base class for all future-related exceptions."""
pass
class CancelledError(Error):
"""The Future was cancelled."""
pass
TimeoutError = TimeoutError # make local alias for the standard exception
class InvalidStateError(Error):
"""The operation is not allowed in this state."""
pass
class _Waiter(object):
"""Provides the event that wait() and as_completed() block on."""
def __init__(self):
self.event = threading.Event()
self.finished_futures = []
def add_result(self, future):
self.finished_futures.append(future)
def add_exception(self, future):
self.finished_futures.append(future)
def add_cancelled(self, future):
self.finished_futures.append(future)
class _AsCompletedWaiter(_Waiter):
"""Used by as_completed()."""
def __init__(self):
super(_AsCompletedWaiter, self).__init__()
self.lock = threading.Lock()
def add_result(self, future):
with self.lock:
super(_AsCompletedWaiter, self).add_result(future)
self.event.set()
def add_exception(self, future):
with self.lock:
super(_AsCompletedWaiter, self).add_exception(future)
self.event.set()
def add_cancelled(self, future):
with self.lock:
super(_AsCompletedWaiter, self).add_cancelled(future)
self.event.set()
class _FirstCompletedWaiter(_Waiter):
"""Used by wait(return_when=FIRST_COMPLETED)."""
def add_result(self, future):
super().add_result(future)
self.event.set()
def add_exception(self, future):
super().add_exception(future)
self.event.set()
def add_cancelled(self, future):
super().add_cancelled(future)
self.event.set()
class _AllCompletedWaiter(_Waiter):
"""Used by wait(return_when=FIRST_EXCEPTION and ALL_COMPLETED)."""
def __init__(self, num_pending_calls, stop_on_exception):
self.num_pending_calls = num_pending_calls
self.stop_on_exception = stop_on_exception
self.lock = threading.Lock()
super().__init__()
def _decrement_pending_calls(self):
with self.lock:
self.num_pending_calls -= 1
if not self.num_pending_calls:
self.event.set()
def add_result(self, future):
super().add_result(future)
self._decrement_pending_calls()
def add_exception(self, future):
super().add_exception(future)
if self.stop_on_exception:
self.event.set()
else:
self._decrement_pending_calls()
def add_cancelled(self, future):
super().add_cancelled(future)
self._decrement_pending_calls()
class _AcquireFutures(object):
"""A context manager that does an ordered acquire of Future conditions."""
def __init__(self, futures):
self.futures = sorted(futures, key=id)
def __enter__(self):
for future in self.futures:
future._condition.acquire()
def __exit__(self, *args):
for future in self.futures:
future._condition.release()
def _create_and_install_waiters(fs, return_when):
if return_when == _AS_COMPLETED:
waiter = _AsCompletedWaiter()
elif return_when == FIRST_COMPLETED:
waiter = _FirstCompletedWaiter()
else:
pending_count = sum(
f._state not in [CANCELLED_AND_NOTIFIED, FINISHED] for f in fs)
if return_when == FIRST_EXCEPTION:
waiter = _AllCompletedWaiter(pending_count, stop_on_exception=True)
elif return_when == ALL_COMPLETED:
waiter = _AllCompletedWaiter(pending_count, stop_on_exception=False)
else:
raise ValueError("Invalid return condition: %r" % return_when)
for f in fs:
f._waiters.append(waiter)
return waiter
def _yield_finished_futures(fs, waiter, ref_collect):
"""
Iterate on the list *fs*, yielding finished futures one by one in
reverse order.
Before yielding a future, *waiter* is removed from its waiters
and the future is removed from each set in the collection of sets
*ref_collect*.
The aim of this function is to avoid keeping stale references after
the future is yielded and before the iterator resumes.
"""
while fs:
f = fs[-1]
for futures_set in ref_collect:
futures_set.remove(f)
with f._condition:
f._waiters.remove(waiter)
del f
# Careful not to keep a reference to the popped value
yield fs.pop()
def as_completed(fs, timeout=None):
"""An iterator over the given futures that yields each as it completes.
Args:
fs: The sequence of Futures (possibly created by different
Executors) to iterate over.
timeout: The maximum number of seconds to wait. If None, then
there is no limit on the wait time.
Returns:
An iterator that yields the given Futures as they complete
(finished or cancelled). If any given Futures are duplicated,
they will be returned once.
Raises:
TimeoutError: If the entire result iterator could not be generated
before the given timeout.
"""
if timeout is not None:
end_time = timeout + time.monotonic()
fs = set(fs)
total_futures = len(fs)
with _AcquireFutures(fs):
finished = set(
f for f in fs
if f._state in [CANCELLED_AND_NOTIFIED, FINISHED])
pending = fs - finished
waiter = _create_and_install_waiters(fs, _AS_COMPLETED)
finished = list(finished)
try:
yield from _yield_finished_futures(finished, waiter,
ref_collect=(fs,))
while pending:
if timeout is None:
wait_timeout = None
else:
wait_timeout = end_time - time.monotonic()
if wait_timeout < 0:
raise TimeoutError(
'%d (of %d) futures unfinished' % (
len(pending), total_futures))
waiter.event.wait(wait_timeout)
with waiter.lock:
finished = waiter.finished_futures
waiter.finished_futures = []
waiter.event.clear()
# reverse to keep finishing order
finished.reverse()
yield from _yield_finished_futures(finished, waiter,
ref_collect=(fs, pending))
finally:
# Remove waiter from unfinished futures
for f in fs:
with f._condition:
f._waiters.remove(waiter)
DoneAndNotDoneFutures = collections.namedtuple(
'DoneAndNotDoneFutures', 'done not_done')
def wait(fs, timeout=None, return_when=ALL_COMPLETED):
"""Wait for the futures in the given sequence to complete.
Args:
fs: The sequence of Futures (possibly created by different
Executors) to wait upon.
timeout: The maximum number of seconds to wait. If None, then
there is no limit on the wait time.
return_when: Indicates when this function should return.
The options are:
FIRST_COMPLETED - Return when any future finishes or is
cancelled.
FIRST_EXCEPTION - Return when any future finishes by raising an
exception. If no future raises an exception
then it is equivalent to ALL_COMPLETED.
ALL_COMPLETED - Return when all futures finish or are
cancelled.
Returns:
A named 2-tuple of sets. The first set, named 'done', contains the
futures that completed (is finished or cancelled) before the wait
completed. The second set, named 'not_done', contains uncompleted
futures. Duplicate futures given to *fs* are removed and will be
returned only once.
"""
fs = set(fs)
with _AcquireFutures(fs):
done = {f for f in fs
if f._state in [CANCELLED_AND_NOTIFIED, FINISHED]}
not_done = fs - done
if (return_when == FIRST_COMPLETED) and done:
return DoneAndNotDoneFutures(done, not_done)
elif (return_when == FIRST_EXCEPTION) and done:
if any(f for f in done
if not f.cancelled() and f.exception() is not None):
return DoneAndNotDoneFutures(done, not_done)
if len(done) == len(fs):
return DoneAndNotDoneFutures(done, not_done)
waiter = _create_and_install_waiters(fs, return_when)
waiter.event.wait(timeout)
for f in fs:
with f._condition:
f._waiters.remove(waiter)
done.update(waiter.finished_futures)
return DoneAndNotDoneFutures(done, fs - done)
def _result_or_cancel(fut, timeout=None):
try:
try:
return fut.result(timeout)
finally:
fut.cancel()
finally:
# Break a reference cycle with the exception in self._exception
del fut
class Future(object):
"""Represents the result of an asynchronous computation."""
def __init__(self):
"""Initializes the future. Should not be called by clients."""
self._condition = threading.Condition()
self._state = PENDING
self._result = None
self._exception = None
self._waiters = []
self._done_callbacks = []
def _invoke_callbacks(self):
for callback in self._done_callbacks:
try:
callback(self)
except Exception:
LOGGER.exception('exception calling callback for %r', self)
def __repr__(self):
with self._condition:
if self._state == FINISHED:
if self._exception:
return '<%s at %#x state=%s raised %s>' % (
self.__class__.__name__,
id(self),
_STATE_TO_DESCRIPTION_MAP[self._state],
self._exception.__class__.__name__)
else:
return '<%s at %#x state=%s returned %s>' % (
self.__class__.__name__,
id(self),
_STATE_TO_DESCRIPTION_MAP[self._state],
self._result.__class__.__name__)
return '<%s at %#x state=%s>' % (
self.__class__.__name__,
id(self),
_STATE_TO_DESCRIPTION_MAP[self._state])
def cancel(self):
"""Cancel the future if possible.
Returns True if the future was cancelled, False otherwise. A future
cannot be cancelled if it is running or has already completed.
"""
with self._condition:
if self._state in [RUNNING, FINISHED]:
return False
if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
return True
self._state = CANCELLED
self._condition.notify_all()
self._invoke_callbacks()
return True
def cancelled(self):
"""Return True if the future was cancelled."""
with self._condition:
return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]
def running(self):
"""Return True if the future is currently executing."""
with self._condition:
return self._state == RUNNING
def done(self):
"""Return True if the future was cancelled or finished executing."""
with self._condition:
return self._state in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]
def __get_result(self):
if self._exception is not None:
try:
raise self._exception
finally:
# Break a reference cycle with the exception in self._exception
self = None
else:
return self._result
def add_done_callback(self, fn):
"""Attaches a callable that will be called when the future finishes.
Args:
fn: A callable that will be called with this future as its only
argument when the future completes or is cancelled. The
callable will always be called by a thread in the same
process in which it was added. If the future has already
completed or been cancelled then the callable will be
called immediately. These callables are called in the
order that they were added.
"""
with self._condition:
if self._state not in [CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED]:
self._done_callbacks.append(fn)
return
try:
fn(self)
except Exception:
LOGGER.exception('exception calling callback for %r', self)
def result(self, timeout=None):
"""Return the result of the call that the future represents.
Args:
timeout: The number of seconds to wait for the result if the
future isn't done. If None, then there is no limit on the
wait time.
Returns:
The result of the call that the future represents.
Raises:
CancelledError: If the future was cancelled.
TimeoutError: If the future didn't finish executing before the
given timeout.
Exception: If the call raised then that exception will be
raised.
"""
try:
with self._condition:
if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
raise CancelledError()
elif self._state == FINISHED:
return self.__get_result()
self._condition.wait(timeout)
if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
raise CancelledError()
elif self._state == FINISHED:
return self.__get_result()
else:
raise TimeoutError()
finally:
# Break a reference cycle with the exception in self._exception
self = None
def exception(self, timeout=None):
"""Return the exception raised by the call that the future represents.
Args:
timeout: The number of seconds to wait for the exception if the
future isn't done. If None, then there is no limit on the
wait time.
Returns:
The exception raised by the call that the future represents or
None if the call completed without raising.
Raises:
CancelledError: If the future was cancelled.
TimeoutError: If the future didn't finish executing before the
given timeout.
"""
with self._condition:
if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
raise CancelledError()
elif self._state == FINISHED:
return self._exception
self._condition.wait(timeout)
if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
raise CancelledError()
elif self._state == FINISHED:
return self._exception
else:
raise TimeoutError()
# The following methods should only be used by Executors and in tests.
def set_running_or_notify_cancel(self):
"""Mark the future as running or process any cancel notifications.
Should only be used by Executor implementations and unit tests.
If the future has been cancelled (cancel() was called and returned
True) then any threads waiting on the future completing (though
calls to as_completed() or wait()) are notified and False is
returned.
If the future was not cancelled then it is put in the running state
(future calls to running() will return True) and True is returned.
This method should be called by Executor implementations before
executing the work associated with this future. If this method
returns False then the work should not be executed.
Returns:
False if the Future was cancelled, True otherwise.
Raises:
RuntimeError: if this method was already called or if
set_result() or set_exception() was called.
"""
with self._condition:
if self._state == CANCELLED:
self._state = CANCELLED_AND_NOTIFIED
for waiter in self._waiters:
waiter.add_cancelled(self)
# self._condition.notify_all() is not necessary because
# self.cancel() triggers a notification.
return False
elif self._state == PENDING:
self._state = RUNNING
return True
else:
LOGGER.critical('Future %s in unexpected state: %s',
id(self),
self._state)
raise RuntimeError('Future in unexpected state')
def set_result(self, result):
"""Sets the return value of work associated with the future.
Should only be used by Executor implementations and unit tests.
"""
with self._condition:
if self._state in {CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED}:
raise InvalidStateError('{}: {!r}'.format(self._state, self))
self._result = result
self._state = FINISHED
for waiter in self._waiters:
waiter.add_result(self)
self._condition.notify_all()
self._invoke_callbacks()
def set_exception(self, exception):
"""Sets the result of the future as being the given exception.
Should only be used by Executor implementations and unit tests.
"""
with self._condition:
if self._state in {CANCELLED, CANCELLED_AND_NOTIFIED, FINISHED}:
raise InvalidStateError('{}: {!r}'.format(self._state, self))
self._exception = exception
self._state = FINISHED
for waiter in self._waiters:
waiter.add_exception(self)
self._condition.notify_all()
self._invoke_callbacks()
def _get_snapshot(self):
"""Get a snapshot of the future's current state.
This method atomically retrieves the state in one lock acquisition,
which is significantly faster than multiple method calls.
Returns:
Tuple of (done, cancelled, result, exception)
- done: True if the future is done (cancelled or finished)
- cancelled: True if the future was cancelled
- result: The result if available and not cancelled
- exception: The exception if available and not cancelled
"""
# Fast path: check if already finished without lock
if self._state == FINISHED:
return True, False, self._result, self._exception
# Need lock for other states since they can change
with self._condition:
# We have to check the state again after acquiring the lock
# because it may have changed in the meantime.
if self._state == FINISHED:
return True, False, self._result, self._exception
if self._state in {CANCELLED, CANCELLED_AND_NOTIFIED}:
return True, True, None, None
return False, False, None, None
__class_getitem__ = classmethod(types.GenericAlias)
class Executor(object):
"""This is an abstract base class for concrete asynchronous executors."""
def submit(self, fn, /, *args, **kwargs):
"""Submits a callable to be executed with the given arguments.
Schedules the callable to be executed as fn(*args, **kwargs) and
returns a Future instance representing the execution of the
callable.
Returns:
A Future representing the given call.
"""
raise NotImplementedError()
def map(self, fn, *iterables, timeout=None, chunksize=1, buffersize=None):
"""Returns an iterator equivalent to map(fn, iter).
Args:
fn: A callable that will take as many arguments as there are
passed iterables.
timeout: The maximum number of seconds to wait. If None, then
there is no limit on the wait time.
chunksize: The size of the chunks the iterable will be broken
into before being passed to a child process. This argument
is only used by ProcessPoolExecutor; it is ignored by
ThreadPoolExecutor.
buffersize: The number of submitted tasks whose results have not
yet been yielded. If the buffer is full, iteration over the
iterables pauses until a result is yielded from the buffer.
If None, all input elements are eagerly collected, and
a task is submitted for each.
Returns:
An iterator equivalent to: map(func, *iterables) but the calls
may be evaluated out-of-order.
Raises:
TimeoutError: If the entire result iterator could not be
generated before the given timeout.
Exception: If fn(*args) raises for any values.
"""
if buffersize is not None and not isinstance(buffersize, int):
raise TypeError("buffersize must be an integer or None")
if buffersize is not None and buffersize < 1:
raise ValueError("buffersize must be None or > 0")
if timeout is not None:
end_time = timeout + time.monotonic()
zipped_iterables = zip(*iterables)
if buffersize:
fs = collections.deque(
self.submit(fn, *args) for args in islice(zipped_iterables, buffersize)
)
else:
fs = [self.submit(fn, *args) for args in zipped_iterables]
# Use a weak reference to ensure that the executor can be garbage
# collected independently of the result_iterator closure.
executor_weakref = weakref.ref(self)
# Yield must be hidden in closure so that the futures are submitted
# before the first iterator value is required.
def result_iterator():
try:
# reverse to keep finishing order
fs.reverse()
while fs:
if (
buffersize
and (executor := executor_weakref())
and (args := next(zipped_iterables, None))
):
fs.appendleft(executor.submit(fn, *args))
# Careful not to keep a reference to the popped future
if timeout is None:
yield _result_or_cancel(fs.pop())
else:
yield _result_or_cancel(fs.pop(), end_time - time.monotonic())
finally:
for future in fs:
future.cancel()
return result_iterator()
def shutdown(self, wait=True, *, cancel_futures=False):
"""Clean-up the resources associated with the Executor.
It is safe to call this method several times. Otherwise, no other
methods can be called after this one.
Args:
wait: If True then shutdown will not return until all running
futures have finished executing and the resources used by
the executor have been reclaimed.
cancel_futures: If True then shutdown will cancel all pending
futures. Futures that are completed or running will not be
cancelled.
"""
pass
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.shutdown(wait=True)
return False
class BrokenExecutor(RuntimeError):
"""
Raised when an executor has become non-functional after a severe failure.
"""
@@ -0,0 +1,123 @@
"""Implements InterpreterPoolExecutor."""
from concurrent import interpreters
import sys
from . import thread as _thread
import traceback
def do_call(results, func, args, kwargs):
try:
return func(*args, **kwargs)
except BaseException as exc:
# Send the captured exception out on the results queue,
# but still leave it unhandled for the interpreter to handle.
try:
results.put(exc)
except interpreters.NotShareableError:
# The exception is not shareable.
print('exception is not shareable:', file=sys.stderr)
traceback.print_exception(exc)
results.put(None)
raise # re-raise
class WorkerContext(_thread.WorkerContext):
@classmethod
def prepare(cls, initializer, initargs):
def resolve_task(fn, args, kwargs):
if isinstance(fn, str):
# XXX Circle back to this later.
raise TypeError('scripts not supported')
else:
task = (fn, args, kwargs)
return task
if initializer is not None:
try:
initdata = resolve_task(initializer, initargs, {})
except ValueError:
if isinstance(initializer, str) and initargs:
raise ValueError(f'an initializer script does not take args, got {initargs!r}')
raise # re-raise
else:
initdata = None
def create_context():
return cls(initdata)
return create_context, resolve_task
def __init__(self, initdata):
self.initdata = initdata
self.interp = None
self.results = None
def __del__(self):
if self.interp is not None:
self.finalize()
def initialize(self):
assert self.interp is None, self.interp
self.interp = interpreters.create()
try:
maxsize = 0
self.results = interpreters.create_queue(maxsize)
if self.initdata:
self.run(self.initdata)
except BaseException:
self.finalize()
raise # re-raise
def finalize(self):
interp = self.interp
results = self.results
self.results = None
self.interp = None
if results is not None:
del results
if interp is not None:
interp.close()
def run(self, task):
try:
return self.interp.call(do_call, self.results, *task)
except interpreters.ExecutionFailed as wrapper:
# Wait for the exception data to show up.
exc = self.results.get()
if exc is None:
# The exception must have been not shareable.
raise # re-raise
raise exc from wrapper
class BrokenInterpreterPool(_thread.BrokenThreadPool):
"""
Raised when a worker thread in an InterpreterPoolExecutor failed initializing.
"""
class InterpreterPoolExecutor(_thread.ThreadPoolExecutor):
BROKEN = BrokenInterpreterPool
@classmethod
def prepare_context(cls, initializer, initargs):
return WorkerContext.prepare(initializer, initargs)
def __init__(self, max_workers=None, thread_name_prefix='',
initializer=None, initargs=()):
"""Initializes a new InterpreterPoolExecutor instance.
Args:
max_workers: The maximum number of interpreters that can be used
to execute the given calls.
thread_name_prefix: An optional name prefix to give our threads.
initializer: A callable or script used to initialize
each worker interpreter.
initargs: A tuple of arguments to pass to the initializer.
"""
thread_name_prefix = (thread_name_prefix or
(f"InterpreterPoolExecutor-{self._counter()}"))
super().__init__(max_workers, thread_name_prefix,
initializer, initargs)
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,274 @@
# Copyright 2009 Brian Quinlan. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""Implements ThreadPoolExecutor."""
__author__ = 'Brian Quinlan (brian@sweetapp.com)'
from concurrent.futures import _base
import itertools
import queue
import threading
import types
import weakref
import os
_threads_queues = weakref.WeakKeyDictionary()
_shutdown = False
# Lock that ensures that new workers are not created while the interpreter is
# shutting down. Must be held while mutating _threads_queues and _shutdown.
_global_shutdown_lock = threading.Lock()
def _python_exit():
global _shutdown
with _global_shutdown_lock:
_shutdown = True
items = list(_threads_queues.items())
for t, q in items:
q.put(None)
for t, q in items:
t.join()
# Register for `_python_exit()` to be called just before joining all
# non-daemon threads. This is used instead of `atexit.register()` for
# compatibility with subinterpreters, which no longer support daemon threads.
# See bpo-39812 for context.
threading._register_atexit(_python_exit)
# At fork, reinitialize the `_global_shutdown_lock` lock in the child process
if hasattr(os, 'register_at_fork'):
os.register_at_fork(before=_global_shutdown_lock.acquire,
after_in_child=_global_shutdown_lock._at_fork_reinit,
after_in_parent=_global_shutdown_lock.release)
os.register_at_fork(after_in_child=_threads_queues.clear)
class WorkerContext:
@classmethod
def prepare(cls, initializer, initargs):
if initializer is not None:
if not callable(initializer):
raise TypeError("initializer must be a callable")
def create_context():
return cls(initializer, initargs)
def resolve_task(fn, args, kwargs):
return (fn, args, kwargs)
return create_context, resolve_task
def __init__(self, initializer, initargs):
self.initializer = initializer
self.initargs = initargs
def initialize(self):
if self.initializer is not None:
self.initializer(*self.initargs)
def finalize(self):
pass
def run(self, task):
fn, args, kwargs = task
return fn(*args, **kwargs)
class _WorkItem:
def __init__(self, future, task):
self.future = future
self.task = task
def run(self, ctx):
if not self.future.set_running_or_notify_cancel():
return
try:
result = ctx.run(self.task)
except BaseException as exc:
self.future.set_exception(exc)
# Break a reference cycle with the exception 'exc'
self = None
else:
self.future.set_result(result)
__class_getitem__ = classmethod(types.GenericAlias)
def _worker(executor_reference, ctx, work_queue):
try:
ctx.initialize()
except BaseException:
_base.LOGGER.critical('Exception in initializer:', exc_info=True)
executor = executor_reference()
if executor is not None:
executor._initializer_failed()
return
try:
while True:
try:
work_item = work_queue.get_nowait()
except queue.Empty:
# attempt to increment idle count if queue is empty
executor = executor_reference()
if executor is not None:
executor._idle_semaphore.release()
del executor
work_item = work_queue.get(block=True)
if work_item is not None:
work_item.run(ctx)
# Delete references to object. See GH-60488
del work_item
continue
executor = executor_reference()
# Exit if:
# - The interpreter is shutting down OR
# - The executor that owns the worker has been collected OR
# - The executor that owns the worker has been shutdown.
if _shutdown or executor is None or executor._shutdown:
# Flag the executor as shutting down as early as possible if it
# is not gc-ed yet.
if executor is not None:
executor._shutdown = True
# Notice other workers
work_queue.put(None)
return
del executor
except BaseException:
_base.LOGGER.critical('Exception in worker', exc_info=True)
finally:
ctx.finalize()
class BrokenThreadPool(_base.BrokenExecutor):
"""
Raised when a worker thread in a ThreadPoolExecutor failed initializing.
"""
class ThreadPoolExecutor(_base.Executor):
BROKEN = BrokenThreadPool
# Used to assign unique thread names when thread_name_prefix is not supplied.
_counter = itertools.count().__next__
@classmethod
def prepare_context(cls, initializer, initargs):
return WorkerContext.prepare(initializer, initargs)
def __init__(self, max_workers=None, thread_name_prefix='',
initializer=None, initargs=(), **ctxkwargs):
"""Initializes a new ThreadPoolExecutor instance.
Args:
max_workers: The maximum number of threads that can be used to
execute the given calls.
thread_name_prefix: An optional name prefix to give our threads.
initializer: A callable used to initialize worker threads.
initargs: A tuple of arguments to pass to the initializer.
ctxkwargs: Additional arguments to cls.prepare_context().
"""
if max_workers is None:
# ThreadPoolExecutor is often used to:
# * CPU bound task which releases GIL
# * I/O bound task (which releases GIL, of course)
#
# We use process_cpu_count + 4 for both types of tasks.
# But we limit it to 32 to avoid consuming surprisingly large resource
# on many core machine.
max_workers = min(32, (os.process_cpu_count() or 1) + 4)
if max_workers <= 0:
raise ValueError("max_workers must be greater than 0")
(self._create_worker_context,
self._resolve_work_item_task,
) = type(self).prepare_context(initializer, initargs, **ctxkwargs)
self._max_workers = max_workers
self._work_queue = queue.SimpleQueue()
self._idle_semaphore = threading.Semaphore(0)
self._threads = set()
self._broken = False
self._shutdown = False
self._shutdown_lock = threading.Lock()
self._thread_name_prefix = (thread_name_prefix or
("ThreadPoolExecutor-%d" % self._counter()))
def submit(self, fn, /, *args, **kwargs):
with self._shutdown_lock, _global_shutdown_lock:
if self._broken:
raise self.BROKEN(self._broken)
if self._shutdown:
raise RuntimeError('cannot schedule new futures after shutdown')
if _shutdown:
raise RuntimeError('cannot schedule new futures after '
'interpreter shutdown')
f = _base.Future()
task = self._resolve_work_item_task(fn, args, kwargs)
w = _WorkItem(f, task)
self._work_queue.put(w)
self._adjust_thread_count()
return f
submit.__doc__ = _base.Executor.submit.__doc__
def _adjust_thread_count(self):
# if idle threads are available, don't spin new threads
if self._idle_semaphore.acquire(timeout=0):
return
# When the executor gets lost, the weakref callback will wake up
# the worker threads.
def weakref_cb(_, q=self._work_queue):
q.put(None)
num_threads = len(self._threads)
if num_threads < self._max_workers:
thread_name = '%s_%d' % (self._thread_name_prefix or self,
num_threads)
t = threading.Thread(name=thread_name, target=_worker,
args=(weakref.ref(self, weakref_cb),
self._create_worker_context(),
self._work_queue))
t.start()
self._threads.add(t)
_threads_queues[t] = self._work_queue
def _initializer_failed(self):
with self._shutdown_lock:
self._broken = ('A thread initializer failed, the thread pool '
'is not usable anymore')
# Drain work queue and mark pending futures failed
while True:
try:
work_item = self._work_queue.get_nowait()
except queue.Empty:
break
if work_item is not None:
work_item.future.set_exception(self.BROKEN(self._broken))
def shutdown(self, wait=True, *, cancel_futures=False):
with self._shutdown_lock:
self._shutdown = True
if cancel_futures:
# Drain all work items from the queue, and then cancel their
# associated futures.
while True:
try:
work_item = self._work_queue.get_nowait()
except queue.Empty:
break
if work_item is not None:
work_item.future.cancel()
# Send a wake-up to prevent threads calling
# _work_queue.get(block=True) from permanently blocking.
self._work_queue.put(None)
if wait:
for t in self._threads:
t.join()
shutdown.__doc__ = _base.Executor.shutdown.__doc__
@@ -0,0 +1,247 @@
"""Subinterpreters High Level Module."""
import threading
import weakref
import _interpreters
# aliases:
from _interpreters import (
InterpreterError, InterpreterNotFoundError, NotShareableError,
is_shareable,
)
from ._queues import (
create as create_queue,
Queue, QueueEmpty, QueueFull,
)
__all__ = [
'get_current', 'get_main', 'create', 'list_all', 'is_shareable',
'Interpreter',
'InterpreterError', 'InterpreterNotFoundError', 'ExecutionFailed',
'NotShareableError',
'create_queue', 'Queue', 'QueueEmpty', 'QueueFull',
]
_EXEC_FAILURE_STR = """
{superstr}
Uncaught in the interpreter:
{formatted}
""".strip()
class ExecutionFailed(InterpreterError):
"""An unhandled exception happened during execution.
This is raised from Interpreter.exec() and Interpreter.call().
"""
def __init__(self, excinfo):
msg = excinfo.formatted
if not msg:
if excinfo.type and excinfo.msg:
msg = f'{excinfo.type.__name__}: {excinfo.msg}'
else:
msg = excinfo.type.__name__ or excinfo.msg
super().__init__(msg)
self.excinfo = excinfo
def __str__(self):
try:
formatted = self.excinfo.errdisplay
except Exception:
return super().__str__()
else:
return _EXEC_FAILURE_STR.format(
superstr=super().__str__(),
formatted=formatted,
)
def create():
"""Return a new (idle) Python interpreter."""
id = _interpreters.create(reqrefs=True)
return Interpreter(id, _ownsref=True)
def list_all():
"""Return all existing interpreters."""
return [Interpreter(id, _whence=whence)
for id, whence in _interpreters.list_all(require_ready=True)]
def get_current():
"""Return the currently running interpreter."""
id, whence = _interpreters.get_current()
return Interpreter(id, _whence=whence)
def get_main():
"""Return the main interpreter."""
id, whence = _interpreters.get_main()
assert whence == _interpreters.WHENCE_RUNTIME, repr(whence)
return Interpreter(id, _whence=whence)
_known = weakref.WeakValueDictionary()
class Interpreter:
"""A single Python interpreter.
Attributes:
"id" - the unique process-global ID number for the interpreter
"whence" - indicates where the interpreter was created
If the interpreter wasn't created by this module
then any method that modifies the interpreter will fail,
i.e. .close(), .prepare_main(), .exec(), and .call()
"""
_WHENCE_TO_STR = {
_interpreters.WHENCE_UNKNOWN: 'unknown',
_interpreters.WHENCE_RUNTIME: 'runtime init',
_interpreters.WHENCE_LEGACY_CAPI: 'legacy C-API',
_interpreters.WHENCE_CAPI: 'C-API',
_interpreters.WHENCE_XI: 'cross-interpreter C-API',
_interpreters.WHENCE_STDLIB: '_interpreters module',
}
def __new__(cls, id, /, _whence=None, _ownsref=None):
# There is only one instance for any given ID.
if not isinstance(id, int):
raise TypeError(f'id must be an int, got {id!r}')
id = int(id)
if _whence is None:
if _ownsref:
_whence = _interpreters.WHENCE_STDLIB
else:
_whence = _interpreters.whence(id)
assert _whence in cls._WHENCE_TO_STR, repr(_whence)
if _ownsref is None:
_ownsref = (_whence == _interpreters.WHENCE_STDLIB)
try:
self = _known[id]
assert hasattr(self, '_ownsref')
except KeyError:
self = super().__new__(cls)
_known[id] = self
self._id = id
self._whence = _whence
self._ownsref = _ownsref
if _ownsref:
# This may raise InterpreterNotFoundError:
_interpreters.incref(id)
return self
def __repr__(self):
return f'{type(self).__name__}({self.id})'
def __hash__(self):
return hash(self._id)
def __del__(self):
self._decref()
# for pickling:
def __reduce__(self):
return (type(self), (self._id,))
# gh-135729: Globals might be destroyed by the time this is called, so we
# need to keep references ourself
def _decref(self, *,
InterpreterNotFoundError=InterpreterNotFoundError,
_interp_decref=_interpreters.decref,
):
if not self._ownsref:
return
self._ownsref = False
try:
_interp_decref(self._id)
except InterpreterNotFoundError:
pass
@property
def id(self):
return self._id
@property
def whence(self):
return self._WHENCE_TO_STR[self._whence]
def is_running(self):
"""Return whether or not the identified interpreter is running."""
return _interpreters.is_running(self._id)
# Everything past here is available only to interpreters created by
# interpreters.create().
def close(self):
"""Finalize and destroy the interpreter.
Attempting to destroy the current interpreter results
in an InterpreterError.
"""
return _interpreters.destroy(self._id, restrict=True)
def prepare_main(self, ns=None, /, **kwargs):
"""Bind the given values into the interpreter's __main__.
The values must be shareable.
"""
ns = dict(ns, **kwargs) if ns is not None else kwargs
_interpreters.set___main___attrs(self._id, ns, restrict=True)
def exec(self, code, /):
"""Run the given source code in the interpreter.
This is essentially the same as calling the builtin "exec"
with this interpreter, using the __dict__ of its __main__
module as both globals and locals.
There is no return value.
If the code raises an unhandled exception then an ExecutionFailed
exception is raised, which summarizes the unhandled exception.
The actual exception is discarded because objects cannot be
shared between interpreters.
This blocks the current Python thread until done. During
that time, the previous interpreter is allowed to run
in other threads.
"""
excinfo = _interpreters.exec(self._id, code, restrict=True)
if excinfo is not None:
raise ExecutionFailed(excinfo)
def _call(self, callable, args, kwargs):
res, excinfo = _interpreters.call(self._id, callable, args, kwargs, restrict=True)
if excinfo is not None:
raise ExecutionFailed(excinfo)
return res
def call(self, callable, /, *args, **kwargs):
"""Call the object in the interpreter with given args/kwargs.
Nearly all callables, args, kwargs, and return values are
supported. All "shareable" objects are supported, as are
"stateless" functions (meaning non-closures that do not use
any globals). This method will fall back to pickle.
If the callable raises an exception then the error display
(including full traceback) is sent back between the interpreters
and an ExecutionFailed exception is raised, much like what
happens with Interpreter.exec().
"""
return self._call(callable, args, kwargs)
def call_in_thread(self, callable, /, *args, **kwargs):
"""Return a new thread that calls the object in the interpreter.
The return value and any raised exception are discarded.
"""
t = threading.Thread(target=self._call, args=(callable, args, kwargs))
t.start()
return t
@@ -0,0 +1,107 @@
"""Common code between queues and channels."""
class ItemInterpreterDestroyed(Exception):
"""Raised when trying to get an item whose interpreter was destroyed."""
class classonly:
"""A non-data descriptor that makes a value only visible on the class.
This is like the "classmethod" builtin, but does not show up on
instances of the class. It may be used as a decorator.
"""
def __init__(self, value):
self.value = value
self.getter = classmethod(value).__get__
self.name = None
def __set_name__(self, cls, name):
if self.name is not None:
raise TypeError('already used')
self.name = name
def __get__(self, obj, cls):
if obj is not None:
raise AttributeError(self.name)
# called on the class
return self.getter(None, cls)
class UnboundItem:
"""Represents a cross-interpreter item no longer bound to an interpreter.
An item is unbound when the interpreter that added it to the
cross-interpreter container is destroyed.
"""
__slots__ = ()
@classonly
def singleton(cls, kind, module, name='UNBOUND'):
doc = cls.__doc__
if doc:
doc = doc.replace(
'cross-interpreter container', kind,
).replace(
'cross-interpreter', kind,
)
subclass = type(
f'Unbound{kind.capitalize()}Item',
(cls,),
{
"_MODULE": module,
"_NAME": name,
"__doc__": doc,
},
)
return object.__new__(subclass)
_MODULE = __name__
_NAME = 'UNBOUND'
def __new__(cls):
raise Exception(f'use {cls._MODULE}.{cls._NAME}')
def __repr__(self):
return f'{self._MODULE}.{self._NAME}'
# return f'interpreters._queues.UNBOUND'
UNBOUND = object.__new__(UnboundItem)
UNBOUND_ERROR = object()
UNBOUND_REMOVE = object()
_UNBOUND_CONSTANT_TO_FLAG = {
UNBOUND_REMOVE: 1,
UNBOUND_ERROR: 2,
UNBOUND: 3,
}
_UNBOUND_FLAG_TO_CONSTANT = {v: k
for k, v in _UNBOUND_CONSTANT_TO_FLAG.items()}
def serialize_unbound(unbound):
op = unbound
try:
flag = _UNBOUND_CONSTANT_TO_FLAG[op]
except KeyError:
raise NotImplementedError(f'unsupported unbound replacement op {op!r}')
return flag,
def resolve_unbound(flag, exctype_destroyed):
try:
op = _UNBOUND_FLAG_TO_CONSTANT[flag]
except KeyError:
raise NotImplementedError(f'unsupported unbound replacement op {flag!r}')
if op is UNBOUND_REMOVE:
# "remove" not possible here
raise NotImplementedError
elif op is UNBOUND_ERROR:
raise exctype_destroyed("item's original interpreter destroyed")
elif op is UNBOUND:
return UNBOUND
else:
raise NotImplementedError(repr(op))
@@ -0,0 +1,289 @@
"""Cross-interpreter Queues High Level Module."""
import queue
import time
import weakref
import _interpqueues as _queues
from . import _crossinterp
# aliases:
from _interpqueues import (
QueueError, QueueNotFoundError,
)
from ._crossinterp import (
UNBOUND_ERROR, UNBOUND_REMOVE,
)
__all__ = [
'UNBOUND', 'UNBOUND_ERROR', 'UNBOUND_REMOVE',
'create', 'list_all',
'Queue',
'QueueError', 'QueueNotFoundError', 'QueueEmpty', 'QueueFull',
'ItemInterpreterDestroyed',
]
class QueueEmpty(QueueError, queue.Empty):
"""Raised from get_nowait() when the queue is empty.
It is also raised from get() if it times out.
"""
class QueueFull(QueueError, queue.Full):
"""Raised from put_nowait() when the queue is full.
It is also raised from put() if it times out.
"""
class ItemInterpreterDestroyed(QueueError,
_crossinterp.ItemInterpreterDestroyed):
"""Raised from get() and get_nowait()."""
_SHARED_ONLY = 0
_PICKLED = 1
UNBOUND = _crossinterp.UnboundItem.singleton('queue', __name__)
def _serialize_unbound(unbound):
if unbound is UNBOUND:
unbound = _crossinterp.UNBOUND
return _crossinterp.serialize_unbound(unbound)
def _resolve_unbound(flag):
resolved = _crossinterp.resolve_unbound(flag, ItemInterpreterDestroyed)
if resolved is _crossinterp.UNBOUND:
resolved = UNBOUND
return resolved
def create(maxsize=0, *, unbounditems=UNBOUND):
"""Return a new cross-interpreter queue.
The queue may be used to pass data safely between interpreters.
"unbounditems" sets the default for Queue.put(); see that method for
supported values. The default value is UNBOUND, which replaces
the unbound item.
"""
unbound = _serialize_unbound(unbounditems)
unboundop, = unbound
qid = _queues.create(maxsize, unboundop, -1)
self = Queue(qid)
self._set_unbound(unboundop, unbounditems)
return self
def list_all():
"""Return a list of all open queues."""
queues = []
for qid, unboundop, _ in _queues.list_all():
self = Queue(qid)
if not hasattr(self, '_unbound'):
self._set_unbound(unboundop)
else:
assert self._unbound[0] == unboundop
queues.append(self)
return queues
_known_queues = weakref.WeakValueDictionary()
class Queue:
"""A cross-interpreter queue."""
def __new__(cls, id, /):
# There is only one instance for any given ID.
if isinstance(id, int):
id = int(id)
else:
raise TypeError(f'id must be an int, got {id!r}')
try:
self = _known_queues[id]
except KeyError:
self = super().__new__(cls)
self._id = id
_known_queues[id] = self
_queues.bind(id)
return self
def __del__(self):
try:
_queues.release(self._id)
except QueueNotFoundError:
pass
try:
del _known_queues[self._id]
except KeyError:
pass
def __repr__(self):
return f'{type(self).__name__}({self.id})'
def __hash__(self):
return hash(self._id)
# for pickling:
def __reduce__(self):
return (type(self), (self._id,))
def _set_unbound(self, op, items=None):
assert not hasattr(self, '_unbound')
if items is None:
items = _resolve_unbound(op)
unbound = (op, items)
self._unbound = unbound
return unbound
@property
def id(self):
return self._id
@property
def unbounditems(self):
try:
_, items = self._unbound
except AttributeError:
op, _ = _queues.get_queue_defaults(self._id)
_, items = self._set_unbound(op)
return items
@property
def maxsize(self):
try:
return self._maxsize
except AttributeError:
self._maxsize = _queues.get_maxsize(self._id)
return self._maxsize
def empty(self):
return self.qsize() == 0
def full(self):
return _queues.is_full(self._id)
def qsize(self):
return _queues.get_count(self._id)
def put(self, obj, block=True, timeout=None, *,
unbounditems=None,
_delay=10 / 1000, # 10 milliseconds
):
"""Add the object to the queue.
If "block" is true, this blocks while the queue is full.
For most objects, the object received through Queue.get() will
be a new one, equivalent to the original and not sharing any
actual underlying data. The notable exceptions include
cross-interpreter types (like Queue) and memoryview, where the
underlying data is actually shared. Furthermore, some types
can be sent through a queue more efficiently than others. This
group includes various immutable types like int, str, bytes, and
tuple (if the items are likewise efficiently shareable).
See interpreters.is_shareable().
"unbounditems" controls the behavior of Queue.get() for the given
object if the current interpreter (calling put()) is later
destroyed.
If "unbounditems" is None (the default) then it uses the
queue's default, set with create_queue(),
which is usually UNBOUND.
If "unbounditems" is UNBOUND_ERROR then get() will raise an
ItemInterpreterDestroyed exception if the original interpreter
has been destroyed. This does not otherwise affect the queue;
the next call to put() will work like normal, returning the next
item in the queue.
If "unbounditems" is UNBOUND_REMOVE then the item will be removed
from the queue as soon as the original interpreter is destroyed.
Be aware that this will introduce an imbalance between put()
and get() calls.
If "unbounditems" is UNBOUND then it is returned by get() in place
of the unbound item.
"""
if not block:
return self.put_nowait(obj, unbounditems=unbounditems)
if unbounditems is None:
unboundop = -1
else:
unboundop, = _serialize_unbound(unbounditems)
if timeout is not None:
timeout = int(timeout)
if timeout < 0:
raise ValueError(f'timeout value must be non-negative')
end = time.time() + timeout
while True:
try:
_queues.put(self._id, obj, unboundop)
except QueueFull:
if timeout is not None and time.time() >= end:
raise # re-raise
time.sleep(_delay)
else:
break
def put_nowait(self, obj, *, unbounditems=None):
if unbounditems is None:
unboundop = -1
else:
unboundop, = _serialize_unbound(unbounditems)
_queues.put(self._id, obj, unboundop)
def get(self, block=True, timeout=None, *,
_delay=10 / 1000, # 10 milliseconds
):
"""Return the next object from the queue.
If "block" is true, this blocks while the queue is empty.
If the next item's original interpreter has been destroyed
then the "next object" is determined by the value of the
"unbounditems" argument to put().
"""
if not block:
return self.get_nowait()
if timeout is not None:
timeout = int(timeout)
if timeout < 0:
raise ValueError(f'timeout value must be non-negative')
end = time.time() + timeout
while True:
try:
obj, unboundop = _queues.get(self._id)
except QueueEmpty:
if timeout is not None and time.time() >= end:
raise # re-raise
time.sleep(_delay)
else:
break
if unboundop is not None:
assert obj is None, repr(obj)
return _resolve_unbound(unboundop)
return obj
def get_nowait(self):
"""Return the next object from the channel.
If the queue is empty then raise QueueEmpty. Otherwise this
is the same as get().
"""
try:
obj, unboundop = _queues.get(self._id)
except QueueEmpty:
raise # re-raise
if unboundop is not None:
assert obj is None, repr(obj)
return _resolve_unbound(unboundop)
return obj
_queues._register_heap_types(Queue, QueueEmpty, QueueFull)