Develop Reference

How to perform async commit when using kafka-python

I'm using kafka-python library for my fastapi consumer app and I'm consuming messages in batch with maximum of 100 records. Since the topic has huge traffic and have only one partition, consuming, processing and committing should be as quick as possible hence I want to use commit_async(), instead of synchronous commit().
But I'm not able to find a good example of commit_async(). I'm looking for an example for commit_async() with callback so that I can log in case of commit failure. But I'm not sure what does that callback function takes as argument and what field those arguments contain.
However the docs related to commit_async mentions the arguments, I'm not completely sure how to use them.
I need help in completing my callback function on_commit(), someone please help here
Code
import logging as log
from kafka import KafkaConsumer
from message_handler_impl import MessageHandlerImpl
def on_commit():
pass
class KafkaMessageConsumer:
def __init__(self, bootstrap_servers: str, topic: str, group_id: str):
self.bootstrap_servers = bootstrap_servers
self.topic = topic
self.group_id = group_id
self.consumer = KafkaConsumer(topic, bootstrap_servers=bootstrap_servers, group_id=group_id, enable_auto_commit=False, auto_offset_reset='latest')
def consume_messages(self, max_poll_records: int,
message_handler: MessageHandlerImpl = MessageHandlerImpl()):
try:
while True:
try:
msg_pack = self.consumer.poll(max_records=max_poll_records)
for topic_partition, messages in msg_pack.items():
message_handler.process_messages(messages)
self.consumer.commit_async(callback=on_commit)
except Exception as e:
log.error("Error while consuming message due to: %s", e, exc_info=True)
finally:
log.error("Something went wrong, closing consumer...........")
self.consumer.close()
if __name__ == "__main__":
kafka_consumer = KafkaMessageConsumer("localhost:9092", "test-topic", "test-group")
kafka_consumer.consume_messages(100)

The docs are fairly clear.
Called as callback(offsets, response) with response as either an Exception or an OffsetCommitResponse struct.
def on_commit(offsets, response):
# or maybe try checking type(response)
if hasattr(response, '<some attribute unique to OffsetCommitResponse>'):
print('committed ' + str(offsets))
else:
print(response) # exception
I'm sure you could look at the source code an maybe find a unit test that covers a full example

Google Cloud Functions randomly retrying on success

I have a Google Cloud Function triggered by a PubSub. The doc states messages are acknowledged when the function end with success.
link
But randomly, the function retries (same execution ID) exactly 10 minutes after execution. It is the PubSub ack max timeout.
I also tried to get message ID and acknowledge it programmatically in Function code but the PubSub API respond there is no message to ack with that id.
In StackDriver monitoring, I see some messages not being acknowledged.
Here is my code : main.py
import base64
import logging
import traceback
from google.api_core import exceptions
from google.cloud import bigquery, error_reporting, firestore, pubsub
from sql_runner.runner import orchestrator
logging.getLogger().setLevel(logging.INFO)
def main(event, context):
bigquery_client = bigquery.Client()
firestore_client = firestore.Client()
publisher_client = pubsub.PublisherClient()
subscriber_client = pubsub.SubscriberClient()
logging.info(
'event=%s',
event
)
logging.info(
'context=%s',
context
)
try:
query_id = base64.b64decode(event.get('data',b'')).decode('utf-8')
logging.info(
'query_id=%s',
query_id
)
# inject dependencies
orchestrator(
query_id,
bigquery_client,
firestore_client,
publisher_client
)
sub_path = (context.resource['name']
.replace('topics', 'subscriptions')
.replace('function-sql-runner', 'gcf-sql-runner-europe-west1-function-sql-runner')
)
# explicitly ack message to avoid duplicates invocations
try:
subscriber_client.acknowledge(
sub_path,
[context.event_id] # message_id to ack
)
logging.warning(
'message_id %s acknowledged (FORCED)',
context.event_id
)
except exceptions.InvalidArgument as err:
# google.api_core.exceptions.InvalidArgument: 400 You have passed an invalid ack ID to the service (ack_id=982967258971474).
logging.info(
'message_id %s already acknowledged',
context.event_id
)
logging.debug(err)
except Exception as err:
# catch all exceptions and log to prevent cold boot
# report with error_reporting
error_reporting.Client().report_exception()
logging.critical(
'Internal error : %s -> %s',
str(err),
traceback.format_exc()
)
if __name__ == '__main__': # for testing
from collections import namedtuple # use namedtuple to avoid Class creation
Context = namedtuple('Context', 'event_id resource')
context = Context('666', {'name': 'projects/my-dev/topics/function-sql-runner'})
script_to_start = b' ' # launch the 1st script
script_to_start = b'060-cartes.sql'
main(
event={"data": base64.b64encode(script_to_start)},
context=context
)
Here is my code : runner.py
import logging
import os
from retry import retry
PROJECT_ID = os.getenv('GCLOUD_PROJECT') or 'my-dev'
def orchestrator(query_id, bigquery_client, firestore_client, publisher_client):
"""
if query_id empty, start the first sql script
else, call the given query_id.
Anyway, call the next script.
If the sql script is the last, no call
retrieve SQL queries from FireStore
run queries on BigQuery
"""
docs_refs = [
doc_ref.get() for doc_ref in
firestore_client.collection(u'sql_scripts').list_documents()
]
sorted_queries = sorted(docs_refs, key=lambda x: x.id)
if not bool(query_id.strip()) : # first execution
current_index = 0
else:
# find the query to run
query_ids = [ query_doc.id for query_doc in sorted_queries]
current_index = query_ids.index(query_id)
query_doc = sorted_queries[current_index]
bigquery_client.query(
query_doc.to_dict()['request'], # sql query
).result()
logging.info(
'Query %s executed',
query_doc.id
)
# exit if the current query is the last
if len(sorted_queries) == current_index + 1:
logging.info('All scripts were executed.')
return
next_query_id = sorted_queries[current_index+1].id.encode('utf-8')
publish(publisher_client, next_query_id)
#retry(tries=5)
def publish(publisher_client, next_query_id):
"""
send a message in pubsub to call the next query
this mechanism allow to run one sql script per Function instance
so as to not exceed the 9min deadline limit
"""
logging.info('Calling next query %s', next_query_id)
future = publisher_client.publish(
topic='projects/{}/topics/function-sql-runner'.format(PROJECT_ID),
data=next_query_id
)
# ensure publish is successfull
message_id = future.result()
logging.info('Published message_id = %s', message_id)
It looks like the pubsub message is not ack on success.
I do not think I have background activity in my code.
My question : why my Function is randomly retrying even when success ?

Cloud Functions does not guarantee that your functions will run exactly once. According to the documentation, background functions, including pubsub functions, are given an at-least-once guarantee:
Background functions are invoked at least once. This is because of the
asynchronous nature of handling events, in which there is no caller
that waits for the response. The system might, in rare circumstances,
invoke a background function more than once in order to ensure
delivery of the event. If a background function invocation fails with
an error, it will not be invoked again unless retries on failure are
enabled for that function.
Your code will need to expect that it could possibly receive an event more than once. As such, your code should be idempotent:
To make sure that your function behaves correctly on retried execution
attempts, you should make it idempotent by implementing it so that an
event results in the desired results (and side effects) even if it is
delivered multiple times. In the case of HTTP functions, this also
means returning the desired value even if the caller retries calls to
the HTTP function endpoint. See Retrying Background Functions for more
information on how to make your function idempotent.

Python - Poloniex Push API

I am trying to get live data in Python 2.7.13 from Poloniex through the push API.
I read many posts (including How to connect to poloniex.com websocket api using a python library) and I arrived to the following code:
from autobahn.twisted.wamp import ApplicationSession
from autobahn.twisted.wamp import ApplicationRunner
from twisted.internet.defer import inlineCallbacks
import six
class PoloniexComponent(ApplicationSession):
def onConnect(self):
self.join(self.config.realm)
#inlineCallbacks
def onJoin(self, details):
def onTicker(*args):
print("Ticker event received:", args)
try:
yield self.subscribe(onTicker, 'ticker')
except Exception as e:
print("Could not subscribe to topic:", e)
def main():
runner = ApplicationRunner(six.u("wss://api.poloniex.com"), six.u("realm1"))
runner.run(PoloniexComponent)
if __name__ == "__main__":
main()
Now, when I run the code, it looks like it's running successfully, but I don't know where I am getting the data. I have two questions:
I would really appreciate if someone could walk me through the process of subscribing and getting ticker data, that I will elaborate in python, from step 0: I am running the program on Spyder on Windows. Am I supposed to activate somehow Crossbar?
How do I quit the connection? I simply killed the process with Ctrl+c and now when I try to run it agan, I get the error: ReactorNonRestartable.

I ran into a lot of issues using Poloniex with Python2.7 but finally came to a solution that hopefully helps you.
I found that Poloniex has pulled support for the original WAMP socket endpoint so I would probably stray from this method altogether. Maybe this is the entirety of the answer you need but if not here is an alternate way to get ticker information.
The code that ended up working best for me is actually from the post you linked to above but there was some info regarding currency pair ids I found elsewhere.
import websocket
import thread
import time
import json
def on_message(ws, message):
print(message)
def on_error(ws, error):
print(error)
def on_close(ws):
print("### closed ###")
def on_open(ws):
print("ONOPEN")
def run(*args):
# ws.send(json.dumps({'command':'subscribe','channel':1001}))
ws.send(json.dumps({'command':'subscribe','channel':1002}))
# ws.send(json.dumps({'command':'subscribe','channel':1003}))
# ws.send(json.dumps({'command':'subscribe','channel':'BTC_XMR'}))
while True:
time.sleep(1)
ws.close()
print("thread terminating...")
thread.start_new_thread(run, ())
if __name__ == "__main__":
websocket.enableTrace(True)
ws = websocket.WebSocketApp("wss://api2.poloniex.com/",
on_message = on_message,
on_error = on_error,
on_close = on_close)
ws.on_open = on_open
ws.run_forever()
I commented out the lines that pull data you don't seem to want, but for reference here is some more info from that previous post:
1001 = trollbox (you will get nothing but a heartbeat)
1002 = ticker
1003 = base coin 24h volume stats
1010 = heartbeat
'MARKET_PAIR' = market order books
Now you should get some data that looks something like this:
[121,"2759.99999999","2759.99999999","2758.000000‌​00","0.02184376","12‌​268375.01419869","44‌​95.18724321",0,"2767‌​.80020000","2680.100‌​00000"]]
This is also annoying because the "121" at the beginning is the currency pair id, and this is undocumented and also unanswered in the other stack overflow question referred to here.
However, if you visit this url: https://poloniex.com/public?command=returnTicker it seems the id is shown as the first field, so you could create your own mapping of id->currency pair or parse the data by the ids you want from this.
Alternatively, something as simple as:
import urllib
import urllib2
import json
ret = urllib2.urlopen(urllib2.Request('https://poloniex.com/public?command=returnTicker'))
print json.loads(ret.read())
will return to you the data that you want, but you'll have to put it in a loop to get constantly updating information. Not sure of your needs once the data is received so I will leave the rest up to you.
Hope this helps!

I made, with the help of other posts, the following code to get the latest data using Python 3.x. I hope this helps you:
#TO SAVE THE HISTORICAL DATA (X MINUTES/HOURS) OF EVERY CRYPTOCURRENCY PAIR IN POLONIEX:
from poloniex import Poloniex
import pandas as pd
from time import time
import os
api = Poloniex(jsonNums=float)
#Obtains the pairs of cryptocurrencies traded in poloniex
pairs = [pair for pair in api.returnTicker()]
i = 0
while i < len(pairs):
#Available candle periods: 5min(300), 15min(900), 30min(1800), 2hr(7200), 4hr(14400), and 24hr(86400)
raw = api.returnChartData(pairs[i], period=86400, start=time()-api.YEAR*10)
df = pd.DataFrame(raw)
# adjust dates format and set dates as index
df['date'] = pd.to_datetime(df["date"], unit='s')
df.set_index('date', inplace=True)
# Saves the historical data of every pair in a csv file
path=r'C:\x\y\Desktop\z\folder_name'
df.to_csv(os.path.join(path,r'%s.csv' % pairs[i]))
i += 1

Generate http error from python3 requests

I have a simple long poll thing using python3 and the requests package. It currently looks something like:
def longpoll():
session = requests.Session()
while True:
try:
fetched = session.get(MyURL)
input = base64.b64decode(fetched.content)
output = process(data)
session.put(MyURL, data=base64.b64encode(response))
except Exception as e:
print(e)
time.sleep(10)
There is a case where instead of processing the input and puting the result, I'd like to raise an http error. Is there a simple way to do this from the high level Session interface? Or do I have to drill down to use the lower level objects?

Since You have control over the server you may want to reverse the 2nd call
Here is an example using bottle to recive the 2nd poll
def longpoll():
session = requests.Session()
while True: #I'm guessing that the server does not care that we call him a lot of times ...
try:
session.post(MyURL, {"ip_address": my_ip_address}) # request work or I'm alive
#input = base64.b64decode(fetched.content)
#output = process(data)
#session.put(MyURL, data=base64.b64encode(response))
except Exception as e:
print(e)
time.sleep(10)
#bottle.post("/process")
def process_new_work():
data = bottle.request.json()
output = process(data) #if an error is thrown an HTTP error will be returned by the framework
return output
This way the server will get the output or an bad HTTP status

Does requests_cache automatically update cache on update of info?

I have a very unreliable API that I request using Python. I have been thinking about using requests_cache and setting expire_after to be 999999999999 like I have seen other people do.
The only problem is, I do not know if when the API works again, that if the data is updated. If requests_cache will automatically auto-update and delete the old entry.
I have tried reading the docs but I cannot really see this anywhere.

requests_cache will not update until the expire_after time has passed. In that case it will not detect that your API is back to a working state.
I note that the project has since added an option that I implemented in the past; you can now set the old_data_on_error option when configuring the cache; see the CachedSession documentation:
old_data_on_error – If True it will return expired cached response if update fails.
It would reuse existing cache data in case a backend update fails, rather than delete that data.
In the past, I created my own requests_cache session setup (plus small patch) that would reuse cached values beyond expire_after if the backend gave a 500 error or timed out (using short timeouts) to deal with a problematic API layer, rather than rely on expire_after:
import logging
from datetime import (
datetime,
timedelta
)
from requests.exceptions import (
ConnectionError,
Timeout,
)
from requests_cache.core import (
dispatch_hook,
CachedSession,
)
log = logging.getLogger(__name__)
# Stop logging from complaining if no logging has been configured.
log.addHandler(logging.NullHandler())
class FallbackCachedSession(CachedSession):
"""Cached session that'll reuse expired cache data on timeouts
This allows survival in case the backend is down, living of stale
data until it comes back.
"""
def send(self, request, **kwargs):
# this *bypasses* CachedSession.send; we want to call the method
# CachedSession.send() would have delegated to!
session_send = super(CachedSession, self).send
if (self._is_cache_disabled or
request.method not in self._cache_allowable_methods):
response = session_send(request, **kwargs)
response.from_cache = False
return response
cache_key = self.cache.create_key(request)
def send_request_and_cache_response(stale=None):
try:
response = session_send(request, **kwargs)
except (Timeout, ConnectionError):
if stale is None:
raise
log.warning('No response received, reusing stale response for '
'%s', request.url)
return stale
if stale is not None and response.status_code == 500:
log.warning('Response gave 500 error, reusing stale response '
'for %s', request.url)
return stale
if response.status_code in self._cache_allowable_codes:
self.cache.save_response(cache_key, response)
response.from_cache = False
return response
response, timestamp = self.cache.get_response_and_time(cache_key)
if response is None:
return send_request_and_cache_response()
if self._cache_expire_after is not None:
is_expired = datetime.utcnow() - timestamp > self._cache_expire_after
if is_expired:
self.cache.delete(cache_key)
# try and get a fresh response, but if that fails reuse the
# stale one
return send_request_and_cache_response(stale=response)
# dispatch hook here, because we've removed it before pickling
response.from_cache = True
response = dispatch_hook('response', request.hooks, response, **kwargs)
return response
def basecache_delete(self, key):
# We don't really delete; we instead set the timestamp to
# datetime.min. This way we can re-use stale values if the backend
# fails
try:
if key not in self.responses:
key = self.keys_map[key]
self.responses[key] = self.responses[key][0], datetime.min
except KeyError:
return
from requests_cache.backends.base import BaseCache
BaseCache.delete = basecache_delete
The above subclass of CachedSession bypasses the original send() method to instead go directly to the original requests.Session.send() method, to return existing cached value even if the timeout has passed but the backend has failed. Deletion is disabled in favour of setting the timeout value to 0, so we can still reuse that old value if a new request fails.
Use the FallbackCachedSession instead of a regular CachedSession object.
If you wanted to use requests_cache.install_cache(), make sure to pass in FallbackCachedSession to that function in the session_factory keyword argument:
import requests_cache
requests_cache.install_cache(
'cache_name', backend='some_backend', expire_after=180,
session_factory=FallbackCachedSession)
My approach is a little more comprehensive than what requests_cache implemented some time after I hacked together the above; my version will fall back to a stale response even if you explicitly marked it as deleted before.

Try to do something like that:
class UnreliableAPIClient:
def __init__(self):
self.some_api_method_cached = {} # we will store results here
def some_api_method(self, param1, param2)
params_hash = "{0}-{1}".format(param1, param2) # need to identify input
try:
result = do_call_some_api_method_with_fail_probability(param1, param2)
self.some_api_method_cached[params_hash] = result # save result
except:
result = self.some_api_method_cached[params_hash] # resort to cached result
if result is None:
raise # reraise exception if nothing cached
return result
Of course you can make simple decorator with that, up to you - http://www.artima.com/weblogs/viewpost.jsp?thread=240808