I'd like to make a python Azure Function App (web API) to process a queue of tasks. I already setup some trigger that call this API whenever a task is inserted into the queue. As this API will process all of the current tasks in the queue, I would like to prevent the API to execute if there is other execution of this API at the time, to avoid processing conflicts.
I think of using a database locking mechanism but it doesn't look so elegant. Is there any singleton design pattern that can used in Python Azure function App for this purpose? Thanks.
I found a way to solve this problem using Azure Durable function. There are 3 types of functions in an Azure Durable Function app: Orchestration Client function, Orchestrator function, Activity functions. I just need to add some checking steps in the Orchestration Client function like the following example:
# This function an HTTP starter function for Durable Functions.
import logging
import azure.functions as func
import azure.durable_functions as df
def is_finished(runtime_status : df.models.OrchestrationRuntimeStatus):
result = False
if runtime_status is None or \
runtime_status in [df.OrchestrationRuntimeStatus.Canceled,
df.OrchestrationRuntimeStatus.Completed,
df.OrchestrationRuntimeStatus.Failed,
df.OrchestrationRuntimeStatus.Terminated]:
result = True
return result
async def main(req: func.HttpRequest, starter: str) -> func.HttpResponse:
client = df.DurableOrchestrationClient(starter)
# general azure function url : http://<APP_NAME>.azurewebsites.net/api/<FUNCTION_NAME>
# function.json -> "route": "orchestrators/{functionName}/{instanceId}"
orchestrator_instance_id = req.route_params['instanceId']
function_name = req.route_params['functionName']
INVENSYNC_ORCHESTRATOR_INSTANCE_ID = '117610EF-BC37-4E31-BFA4-205EBB3CC54E' # just select any key
if orchestrator_instance_id == INVENSYNC_ORCHESTRATOR_INSTANCE_ID:
existing_instance_status = await client.get_status(orchestrator_instance_id)
logging.info(f"InventorySyncHttpStart() - existing_instance_status = '{existing_instance_status}'.")
if existing_instance_status is None or \
is_finished(existing_instance_status.runtime_status):
logging.info(f"InventorySyncHttpStart() - existing_instance_status.runtime_status = '{existing_instance_status.runtime_status}'.")
orchestrator_instance_id = await client.start_new(function_name, orchestrator_instance_id)
logging.info(f"Started orchestration with ID = '{orchestrator_instance_id}'.")
result = client.create_check_status_response(req, orchestrator_instance_id)
else:
result = func.HttpResponse(status_code=409, body=f"An instance with ID '{orchestrator_instance_id}' already exists")
else:
result = func.HttpResponse(status_code=406, body=f"Invalid Instance ID '{orchestrator_instance_id}' in URL")
return result
Related
I'm trying to test my FastAPI endpoints by overriding the injected database using the officially recommended method in the FastAPI documentation.
The function I'm injecting the db with is a closure that allows me to build any desired database from a MongoClient by giving it the database name whilst (I assume) still working with FastAPI depends as it returns a closure function's signature. No error is thrown so I think this method is correct:
# app
def build_db(name: str):
def close():
return build_singleton_whatever(MongoClient, args....)
return close
Adding it to the endpoint:
# endpoint
#app.post("/notification/feed")
async def route_receive_notifications(db: Database = Depends(build_db("someDB"))):
...
And finally, attempting to override it in the tests:
# pytest
# test_endpoint.py
fastapi_app.dependency_overrides[app.build_db] = lambda x: lambda: x
However, the dependency doesn't seem to override at all and the test ends up creating a MongoClient with the IP of the production database as in normal execution.
So, any ideas on overriding FastAPI dependencies that are given parameters in their endpoints?
I have tried creating a mock closure function with no success:
def mock_closure(*args):
def close():
return args
return close
app.dependency_overrides[app.build_db] = mock_closure('otherDB')
And I have also tried providing the same signature, including the parameter, with still no success:
app.dependency_overrides[app.build_db('someDB')] = mock_closure('otherDB')
Edit note I'm also aware I can create a separate function that creates my desired database and use that as the dependency, but I would much prefer to use this dynamic version as it's more scalable to using more databases in my apps and avoids me writing essentially repeated functions just so they can be cleanly injected.
I use next fixtures for main db overriding to db for testing:
from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine
from settings import get_settings
#pytest.fixture()
async def get_engine():
engine = create_async_engine(get_settings().test_db_url)
yield engine
await engine.dispose()
#pytest.fixture()
async def db_session(get_engine) -> AsyncSession:
async with get_engine.begin() as connection:
async with async_session(bind=connection) as session:
yield session
await session.close()
#pytest.fixture()
def override_get_async_session(db_session: AsyncSession) -> Callable:
async def _override_get_async_session():
yield db_session
return _override_get_async_session
There are two issues with your implementation getting in your way:
As you are calling build_db right in the route_receive_notifications function definition, the latter receives nested close function as a dependency. And it's impossible to override it. To fix this you would need to avoid calling your dependency right away and still provide it with db name. For that you can either define a new dependency to inject name into build_db:
# app
def get_db_name():
return "someDB"
def build_db(name: str = Depends(get_db_name)):
...
# endpoint
#app.post("/notification/feed")
async def route_receive_notifications(db: Database = Depends(build_db)):
...
or use functools.partial (shorter but less elegant):
# endpoint
from functools import partial
#app.post("/notification/feed")
async def route_receive_notifications(db: Database = Depends(partial(build_db, "someDB"))):
...
FastAPI requires dependency overriding function to have the same signature as the original dependency. Simply switching from *args to a single parameter is enough, although using the same argument name and type makes it easier to support in future. Of course you need to provide the function itself as a value for dependency_overrides without calling it:
def mock_closure(name: str):
def close():
return name
return close
app.dependency_overrides[app.build_db] = mock_closure
Im using a HTTP trigger to trigger an Orchestrator Function that runs multiple activity functions. The Http trigger is called every few minutes to retrieve the status of the Orchestration. The activity functions require an external token for certain operations. This token is send with the HTTP trigger to the Orchestrator. To avoid using an expired token when the Orchestrator runs longer, I included an external event into the Http trigger that sends a new token on each call of the trigger, since I didn't find another way to send new data to a running Orchestrator. Now if I add the wait_for_external_event function after my activity functions in the Orchestrator everything runs properly. But if I set it before the activities are called it causes the Orchestrator to stop working. The client.get_status function of the HTTP trigger returns a failed status after the first run.
I am not sure as to why this is, from my understanding it should not make a difference as to when I wait for the external event. Is there any reason why this is happening? In the monitoring the Orchestrator is still shown as "running".
This is my http trigger:
import logging
import azure.functions as func
import azure.durable_functions as df
import json
import uuid
from azure.durable_functions.models.OrchestrationRuntimeStatus import OrchestrationRuntimeStatus
async def main(req: func.HttpRequest, starter: str) -> func.HttpResponse:
try:
client = df.DurableOrchestrationClient(starter)
params = {}
for key, value in req.params.items():
params[key] = value
for key, value in _get_json(req).items():
params[key] = value
access_token = params["accessToken"]
azure_call_id = params.get("azureCallId")
if not azure_call_id:
azure_call_id = await client.start_new('TestOrchestrator',
instance_id=None,
client_input=params)
status = await client.get_status(azure_call_id)
if status.runtime_status == OrchestrationRuntimeStatus.Pending \
or status.runtime_status == OrchestrationRuntimeStatus.Running \
or status.runtime_status == OrchestrationRuntimeStatus.ContinuedAsNew:
await client.raise_event(azure_call_id, 'RefreshToken', {'accessToken': access_token})
return response
except Exception as e:
logging.error(f"Exception caught: {str(e)}")
I have deployed a fastapi endpoint,
from fastapi import FastAPI, UploadFile
from typing import List
app = FastAPI()
#app.post('/work/test')
async def testing(files: List(UploadFile)):
for i in files:
.......
# do a lot of operations on each file
# after than I am just writing that processed data into mysql database
# cur.execute(...)
# cur.commit()
.......
# just returning "OK" to confirm data is written into mysql
return {"response" : "OK"}
I can request output from the API endpoint and its working fine for me perfectly.
Now, the biggest challenge for me to know how much time it is taking for each iteration. Because in the UI part (those who are accessing my API endpoint) I want to help them show a progress bar (TIME TAKEN) for each iteration/file being processed.
Is there any possible way for me to achieve it? If so, please help me out on how can I proceed further?
Thank you.
Approaches
Polling
The most preferred approach to track the progress of a task is polling:
After receiving a request to start a task on a backend:
Create a task object in the storage (e.g in-memory, redis and etc.). The task object must contain the following data: task ID, status (pending, completed), result, and others.
Run task in the background (coroutines, threading, multiprocessing, task queue like Celery, arq, aio-pika, dramatiq and etc.)
Response immediately the answer 202 (Accepted) by returning the previously received task ID.
Update task status:
This can be from within the task itself, if it knows about the task store and has access to it. Periodically, the task itself updates information about itself.
Or use a task monitor (Observer, producer-consumer pattern), which will monitor the status of the task and its result. And it will also update the information in the storage.
On the client side (front-end) start a polling cycle for the task status to endpoint /task/{ID}/status, which takes information from the task storage.
Streaming response
Streaming is a less convenient way of getting the status of request processing periodically. When we gradually push responses without closing the connection. It has a number of significant disadvantages, for example, if the connection is broken, you can lose information. Streaming Api is another approach than REST Api.
Websockets
You can also use websockets for real-time notifications and bidirectional communication.
Links:
Examples of polling approach for the progress bar and a more detailed description for django + celery can be found at these links:
https://www.dangtrinh.com/2013/07/django-celery-display-progress-bar-of.html
https://buildwithdjango.com/blog/post/celery-progress-bars/
I have provided simplified examples of running background tasks in FastAPI using multiprocessing here:
https://stackoverflow.com/a/63171013/13782669
Old answer:
You could run a task in the background, return its id and provide a /status endpoint that the front would periodically call. In the status response, you could return what state your task is now (for example, pending with the number of the currently processed file). I provided a few simple examples here.
Demo
Polling
Demo of the approach using asyncio tasks (single worker solution):
import asyncio
from http import HTTPStatus
from fastapi import BackgroundTasks
from typing import Dict, List
from uuid import UUID, uuid4
import uvicorn
from fastapi import FastAPI
from pydantic import BaseModel, Field
class Job(BaseModel):
uid: UUID = Field(default_factory=uuid4)
status: str = "in_progress"
progress: int = 0
result: int = None
app = FastAPI()
jobs: Dict[UUID, Job] = {} # Dict as job storage
async def long_task(queue: asyncio.Queue, param: int):
for i in range(1, param): # do work and return our progress
await asyncio.sleep(1)
await queue.put(i)
await queue.put(None)
async def start_new_task(uid: UUID, param: int) -> None:
queue = asyncio.Queue()
task = asyncio.create_task(long_task(queue, param))
while progress := await queue.get(): # monitor task progress
jobs[uid].progress = progress
jobs[uid].status = "complete"
#app.post("/new_task/{param}", status_code=HTTPStatus.ACCEPTED)
async def task_handler(background_tasks: BackgroundTasks, param: int):
new_task = Job()
jobs[new_task.uid] = new_task
background_tasks.add_task(start_new_task, new_task.uid, param)
return new_task
#app.get("/task/{uid}/status")
async def status_handler(uid: UUID):
return jobs[uid]
Adapted example for loop from question
Background processing function is defined as def and FastAPI runs it on the thread pool.
import time
from http import HTTPStatus
from fastapi import BackgroundTasks, UploadFile, File
from typing import Dict, List
from uuid import UUID, uuid4
from fastapi import FastAPI
from pydantic import BaseModel, Field
class Job(BaseModel):
uid: UUID = Field(default_factory=uuid4)
status: str = "in_progress"
processed_files: List[str] = Field(default_factory=list)
app = FastAPI()
jobs: Dict[UUID, Job] = {}
def process_files(task_id: UUID, files: List[UploadFile]):
for i in files:
time.sleep(5) # pretend long task
# ...
# do a lot of operations on each file
# then append the processed file to a list
# ...
jobs[task_id].processed_files.append(i.filename)
jobs[task_id].status = "completed"
#app.post('/work/test', status_code=HTTPStatus.ACCEPTED)
async def work(background_tasks: BackgroundTasks, files: List[UploadFile] = File(...)):
new_task = Job()
jobs[new_task.uid] = new_task
background_tasks.add_task(process_files, new_task.uid, files)
return new_task
#app.get("/work/{uid}/status")
async def status_handler(uid: UUID):
return jobs[uid]
Streaming
async def process_files_gen(files: List[UploadFile]):
for i in files:
time.sleep(5) # pretend long task
# ...
# do a lot of operations on each file
# then append the processed file to a list
# ...
yield f"{i.filename} processed\n"
yield f"OK\n"
#app.post('/work/stream/test', status_code=HTTPStatus.ACCEPTED)
async def work(files: List[UploadFile] = File(...)):
return StreamingResponse(process_files_gen(files))
Below is solution which uses uniq identifiers and globally available dictionary which holds information about the jobs:
NOTE: Code below is safe to use until you use dynamic keys values ( In sample uuid in use) and keep application within single process.
To start the app create a file main.py
Run uvicorn main:app --reload
Create job entry by accessing http://127.0.0.1:8000/
Repeat step 3 to create multiple jobs
Go to http://127.0.0.1/status page to see page statuses.
Go to http://127.0.0.1/status/{identifier} to see progression of the job by the job id.
Code of app:
from fastapi import FastAPI, UploadFile
import uuid
from typing import List
import asyncio
context = {'jobs': {}}
app = FastAPI()
async def do_work(job_key, files=None):
iter_over = files if files else range(100)
for file, file_number in enumerate(iter_over):
jobs = context['jobs']
job_info = jobs[job_key]
job_info['iteration'] = file_number
job_info['status'] = 'inprogress'
await asyncio.sleep(1)
pending_jobs[job_key]['status'] = 'done'
#app.post('/work/test')
async def testing(files: List[UploadFile]):
identifier = str(uuid.uuid4())
context[jobs][identifier] = {}
asyncio.run_coroutine_threadsafe(do_work(identifier, files), loop=asyncio.get_running_loop())
return {"identifier": identifier}
#app.get('/')
async def get_testing():
identifier = str(uuid.uuid4())
context['jobs'][identifier] = {}
asyncio.run_coroutine_threadsafe(do_work(identifier), loop=asyncio.get_running_loop())
return {"identifier": identifier}
#app.get('/status')
def status():
return {
'all': list(context['jobs'].values()),
}
#app.get('/status/{identifier}')
async def status(identifier):
return {
"status": context['jobs'].get(identifier, 'job with that identifier is undefined'),
}
I'm calling a Google Cloud Function that returns an Operation object implementing the google.longrunning.Operations interface. I want to poll this operation from another Python process that will only receive the operation name (will not have access to the operation object itself). So I need something like:
operation = getOperation(operationName)
isdone = operation.done()
AFAIK, you can't do the first step above. I haven't found it here: https://google-cloud-python.readthedocs.io/en/stable/core/operation.html
I would like to do what is explained in the docs about the google.longrunning interface (https://cloud.google.com/speech-to-text/docs/reference/rpc/google.longrunning#google.longrunning.Operations.GetOperation):
rpc GetOperation(GetOperationRequest) returns (Operation)
Where the GetOperationRequest simply requires the operation name. Is there a way to "re-create" an operation using functions from the google-cloud-python library?
Update for more recent clients. You need to refresh the operation using the OperationClient:
For updating an existing operation you will need to pass the channel across to the OperationClient.
For example, backing up a Firestore datastore.
from google.cloud import firestore_admin_v1
from google.api_core import operations_v1, grpc_helpers
import time
def main():
client = firestore_admin_v1.FirestoreAdminClient()
channel = grpc_helpers.create_channel(client.SERVICE_ADDRESS)
api = operations_v1.OperationsClient(channel)
db_path = client.database_path('myproject', 'mydb')
operation = client.export_documents(db_path)
current_status = api.get_operation(operation.name)
while current_status.done == False:
time.sleep(5)
current_status = api.get_operation(operation.name)
print('waiting to complete')
print('operation done')
In my case, The AutoML Tables Client didn't have a SERVICE_ADDRESS or SCOPE properties, so I can't create a new gRPC channel.
But using the existing one in the client seems to work!
from google.api_core import operations_v1
from google.cloud.automl_v1beta1 import TablesClient
automl_tables_client = TablesClient(
credentials=...,
project=...,
region=...,
)
operation_name = ""
grpc_channel = automl_tables_client.auto_ml_client.transport._channel
api_client = operations_v1.OperationsClient(grpc_channel)
response = api_client.get_operation(operation_name)
You can use the get_operation method of the "Long-Running Operations Client":
from google.api_core import operations_v1
api = operations_v1.OperationsClient()
name = ...
response = api.get_operation(name)
I am trying to build a small site with the server push functionality on Flask micro-web framework, but I did not know if there is a framework to work with directly.
I used Juggernaut, but it seems to be not working with redis-py in current version, and Juggernaut has been deprecated recently.
Does anyone has a suggestion with my case?
Have a look at Server-Sent Events. Server-Sent Events is a
browser API that lets you keep open a socket to your server, subscribing to a
stream of updates. For more Information read Alex MacCaw (Author of
Juggernaut) post on why he kills juggernaut and why the simpler
Server-Sent Events are in manny cases the better tool for the job than
Websockets.
The protocol is really easy. Just add the mimetype text/event-stream to your
response. The browser will keep the connection open and listen for updates. An Event
sent from the server is a line of text starting with data: and a following newline.
data: this is a simple message
<blank line>
If you want to exchange structured data, just dump your data as json and send the json over the wire.
An advantage is that you can use SSE in Flask without the need for an extra
Server. There is a simple chat application example on github which
uses redis as a pub/sub backend.
def event_stream():
pubsub = red.pubsub()
pubsub.subscribe('chat')
for message in pubsub.listen():
print message
yield 'data: %s\n\n' % message['data']
#app.route('/post', methods=['POST'])
def post():
message = flask.request.form['message']
user = flask.session.get('user', 'anonymous')
now = datetime.datetime.now().replace(microsecond=0).time()
red.publish('chat', u'[%s] %s: %s' % (now.isoformat(), user, message))
#app.route('/stream')
def stream():
return flask.Response(event_stream(),
mimetype="text/event-stream")
You do not need to use gunicron to run the
example app. Just make sure to use threading when running the app, because
otherwise the SSE connection will block your development server:
if __name__ == '__main__':
app.debug = True
app.run(threaded=True)
On the client side you just need a Javascript handler function which will be called when a new
message is pushed from the server.
var source = new EventSource('/stream');
source.onmessage = function (event) {
alert(event.data);
};
Server-Sent Events are supported by recent Firefox, Chrome and Safari browsers.
Internet Explorer does not yet support Server-Sent Events, but is expected to support them in
Version 10. There are two recommended Polyfills to support older browsers
EventSource.js
jquery.eventsource
Redis is overkill: use Server-Sent Events (SSE)
Late to the party (as usual), but IMHO using Redis may be overkill.
As long as you're working in Python+Flask, consider using generator functions as described in this excellent article by Panisuan Joe Chasinga. The gist of it is:
In your client index.html
var targetContainer = document.getElementById("target_div");
var eventSource = new EventSource("/stream")
eventSource.onmessage = function(e) {
targetContainer.innerHTML = e.data;
};
...
<div id="target_div">Watch this space...</div>
In your Flask server:
def get_message():
'''this could be any function that blocks until data is ready'''
time.sleep(1.0)
s = time.ctime(time.time())
return s
#app.route('/')
def root():
return render_template('index.html')
#app.route('/stream')
def stream():
def eventStream():
while True:
# wait for source data to be available, then push it
yield 'data: {}\n\n'.format(get_message())
return Response(eventStream(), mimetype="text/event-stream")
As a follow-up to #peter-hoffmann's answer, I've written a Flask extension specifically to handle server-sent events. It's called Flask-SSE, and it's available on PyPI. To install it, run:
$ pip install flask-sse
You can use it like this:
from flask import Flask
from flask_sse import sse
app = Flask(__name__)
app.config["REDIS_URL"] = "redis://localhost"
app.register_blueprint(sse, url_prefix='/stream')
#app.route('/send')
def send_message():
sse.publish({"message": "Hello!"}, type='greeting')
return "Message sent!"
And to connect to the event stream from Javascript, it works like this:
var source = new EventSource("{{ url_for('sse.stream') }}");
source.addEventListener('greeting', function(event) {
var data = JSON.parse(event.data);
// do what you want with this data
}, false);
Documentation is available on ReadTheDocs. Note that you'll need a running Redis server to handle pub/sub.
As a committer of https://github.com/WolfgangFahl/pyFlaskBootstrap4 i ran into the same need and created a flask blueprint for Server Sent Events that has no dependency to redis.
This solutions builds on the other answers that have been given here in the past.
https://github.com/WolfgangFahl/pyFlaskBootstrap4/blob/main/fb4/sse_bp.py has the source code (see also sse_bp.py below).
There are unit tests at https://github.com/WolfgangFahl/pyFlaskBootstrap4/blob/main/tests/test_sse.py
The idea is that you can use different modes to create your SSE stream:
by providing a function
by providing a generator
by using a PubSub helper class
by using the PubSub helper class and use pydispatch at the same time.
As of 2021-02-12 this is alpha code which i want to share nevertheless. Please comment here or as issues in the project.
There is a demo at http://fb4demo.bitplan.com/events and a description of the example use e.g. for a progress bar or time display at: http://wiki.bitplan.com/index.php/PyFlaskBootstrap4#Server_Sent_Events
example client javascript/html code
<div id="event_div">Watch this space...</div>
<script>
function fillContainerFromSSE(id,url) {
var targetContainer = document.getElementById(id);
var eventSource = new EventSource(url)
eventSource.onmessage = function(e) {
targetContainer.innerHTML = e.data;
};
};
fillContainerFromSSE("event_div","/eventfeed");
</script>
example server side code
def getTimeEvent(self):
'''
get the next time stamp
'''
time.sleep(1.0)
s=datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S')
return s
def eventFeed(self):
'''
create a Server Sent Event Feed
'''
sse=self.sseBluePrint
# stream from the given function
return sse.streamFunc(self.getTimeEvent)
sse_bp.py
'''
Created on 2021-02-06
#author: wf
'''
from flask import Blueprint, Response, request, abort,stream_with_context
from queue import Queue
from pydispatch import dispatcher
import logging
class SSE_BluePrint(object):
'''
a blueprint for server side events
'''
def __init__(self,app,name:str,template_folder:str=None,debug=False,withContext=False):
'''
Constructor
'''
self.name=name
self.debug=debug
self.withContext=False
if template_folder is not None:
self.template_folder=template_folder
else:
self.template_folder='templates'
self.blueprint=Blueprint(name,__name__,template_folder=self.template_folder)
self.app=app
app.register_blueprint(self.blueprint)
#self.app.route('/sse/<channel>')
def subscribe(channel):
def events():
PubSub.subscribe(channel)
self.stream(events)
def streamSSE(self,ssegenerator):
'''
stream the Server Sent Events for the given SSE generator
'''
response=None
if self.withContext:
if request.headers.get('accept') == 'text/event-stream':
response=Response(stream_with_context(ssegenerator), content_type='text/event-stream')
else:
response=abort(404)
else:
response= Response(ssegenerator, content_type='text/event-stream')
return response
def streamGen(self,gen):
'''
stream the results of the given generator
'''
ssegen=self.generateSSE(gen)
return self.streamSSE(ssegen)
def streamFunc(self,func,limit=-1):
'''
stream a generator based on the given function
Args:
func: the function to convert to a generator
limit (int): optional limit of how often the generator should be applied - 1 for endless
Returns:
an SSE Response stream
'''
gen=self.generate(func,limit)
return self.streamGen(gen)
def generate(self,func,limit=-1):
'''
create a SSE generator from a given function
Args:
func: the function to convert to a generator
limit (int): optional limit of how often the generator should be applied - 1 for endless
Returns:
a generator for the function
'''
count=0
while limit==-1 or count<limit:
# wait for source data to be available, then push it
count+=1
result=func()
yield result
def generateSSE(self,gen):
for result in gen:
yield 'data: {}\n\n'.format(result)
def enableDebug(self,debug:bool):
'''
set my debugging
Args:
debug(bool): True if debugging should be switched on
'''
self.debug=debug
if self.debug:
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s.%(msecs)03d %(levelname)s:\t%(message)s', datefmt='%Y-%m-%d %H:%M:%S')
def publish(self, message:str, channel:str='sse', debug=False):
"""
Publish data as a server-sent event.
Args:
message(str): the message to send
channel(str): If you want to direct different events to different
clients, you may specify a channel for this event to go to.
Only clients listening to the same channel will receive this event.
Defaults to "sse".
debug(bool): if True enable debugging
"""
return PubSub.publish(channel=channel, message=message,debug=debug)
def subscribe(self,channel,limit=-1,debug=False):
def stream():
for message in PubSub.subscribe(channel,limit,debug=debug):
yield str(message)
return self.streamGen(stream)
class PubSub:
'''
redis pubsub duck replacement
'''
pubSubByChannel={}
def __init__(self,channel:str='sse',maxsize:int=15, debug=False,dispatch=False):
'''
Args:
channel(string): the channel name
maxsize(int): the maximum size of the queue
debug(bool): whether debugging should be switched on
dispatch(bool): if true use the pydispatch library - otherwise only a queue
'''
self.channel=channel
self.queue=Queue(maxsize=maxsize)
self.debug=debug
self.receiveCount=0
self.dispatch=False
if dispatch:
dispatcher.connect(self.receive,signal=channel,sender=dispatcher.Any)
#staticmethod
def reinit():
'''
reinitialize the pubSubByChannel dict
'''
PubSub.pubSubByChannel={}
#staticmethod
def forChannel(channel):
'''
return a PubSub for the given channel
Args:
channel(str): the id of the channel
Returns:
PubSub: the PubSub for the given channel
'''
if channel in PubSub.pubSubByChannel:
pubsub=PubSub.pubSubByChannel[channel]
else:
pubsub=PubSub(channel)
PubSub.pubSubByChannel[channel]=pubsub
return pubsub
#staticmethod
def publish(channel:str,message:str,debug=False):
'''
publish a message via the given channel
Args:
channel(str): the id of the channel to use
message(str): the message to publish/send
Returns:
PubSub: the pub sub for the channel
'''
pubsub=PubSub.forChannel(channel)
pubsub.debug=debug
pubsub.send(message)
return pubsub
#staticmethod
def subscribe(channel,limit=-1,debug=False):
'''
subscribe to the given channel
Args:
channel(str): the id of the channel to use
limit(int): limit the maximum amount of messages to be received
debug(bool): if True debugging info is printed
'''
pubsub=PubSub.forChannel(channel)
pubsub.debug=debug
return pubsub.listen(limit)
def send(self,message):
'''
send the given message
'''
sender=object();
if self.dispatch:
dispatcher.send(signal=self.channel,sender=sender,msg=message)
else:
self.receive(sender,message)
def receive(self,sender,message):
'''
receive a message
'''
if sender is not None:
self.receiveCount+=1;
if self.debug:
logging.debug("received %d:%s" % (self.receiveCount,message))
self.queue.put(message)
def listen(self,limit=-1):
'''
listen to my channel
this is a generator for the queue content of received messages
Args:
limit(int): limit the maximum amount of messages to be received
Return:
generator: received messages to be yielded
'''
if limit>0 and self.receiveCount>limit:
return
yield self.queue.get()
def unsubscribe(self):
'''
unsubscribe me
'''
if self.dispatch:
dispatcher.disconnect(self.receive, signal=self.channel)
pass