def __init__(self, write_key=None, host=None, debug=False, max_queue_size=10000, send=True, on_error=None, upload_size=100, upload_interval=0.5, gzip=False, max_retries=10): require('write_key', write_key, string_types) self.queue = queue.Queue(max_queue_size) self.consumer = Consumer(self.queue, write_key, host=host, on_error=on_error, upload_size=upload_size, upload_interval=upload_interval, gzip=gzip, retries=max_retries) self.write_key = write_key self.on_error = on_error self.debug = debug self.send = send if debug: self.log.setLevel(logging.DEBUG) # if we've disabled sending, just don't start the consumer if send: # On program exit, allow the consumer thread to exit cleanly. # This prevents exceptions and a messy shutdown when the interpreter is # destroyed before the daemon thread finishes execution. However, it # is *not* the same as flushing the queue! To guarantee all messages # have been delivered, you'll still need to call flush(). atexit.register(self.join) self.consumer.start()
def __init__(self, write_key=None, debug=False, max_queue_size=10000, send=True, on_error=None): # We need a different queue type to have a client that works properly across separate processes. # This client is meant to be shared and used within celery environment (although it should work otherwise). # This will hopefully fix: https://github.com/segmentio/analytics-python/issues/51 although it is uncertain # what exactly is causing it. require('write_key', write_key, str) self.queue = JoinableQueue(max_queue_size) self.consumer = Consumer(self.queue, write_key, on_error=on_error) self.write_key = write_key self.on_error = on_error self.debug = debug self.send = send if debug: self.log.setLevel(logging.DEBUG) # if we've disabled sending, just don't start the consumer if send: self.consumer.start()
def test_upload(self): q = Queue() consumer = Consumer(q, 'testsecret') track = {'type': 'track', 'event': 'python event', 'userId': 'userId'} q.put(track) success = consumer.upload() self.assertTrue(success)
def test_max_batch_size(self): q = Queue() consumer = Consumer(q, 'testsecret', upload_size=100000, upload_interval=3) track = {'type': 'track', 'event': 'python event', 'userId': 'userId'} msg_size = len(json.dumps(track).encode()) # number of messages in a maximum-size batch n_msgs = int(475000 / msg_size) def mock_post_fn(_, data, **kwargs): res = mock.Mock() res.status_code = 200 self.assertTrue( len(data.encode()) < 500000, 'batch size (%d) exceeds 500KB limit' % len(data.encode())) return res with mock.patch('analytics.request._session.post', side_effect=mock_post_fn) as mock_post: consumer.start() for _ in range(0, n_msgs + 2): q.put(track) q.join() self.assertEqual(mock_post.call_count, 2)
def _test_request_retry(self, expected_exception, exception_count): def mock_post(*args, **kwargs): mock_post.call_count += 1 if mock_post.call_count <= exception_count: raise expected_exception mock_post.call_count = 0 with mock.patch('analytics.consumer.post', mock.Mock(side_effect=mock_post)): consumer = Consumer(None, 'testsecret') track = { 'type': 'track', 'event': 'python event', 'userId': 'userId' } # request() should succeed if the number of exceptions raised is less # than the retries paramater. if exception_count <= consumer.retries: consumer.request([track]) else: # if exceptions are raised more times than the retries parameter, # we expect the exception to be returned to the caller. try: consumer.request([track]) except type(expected_exception) as exc: self.assertEqual(exc, expected_exception) else: self.fail( "request() should raise an exception if still failing after %d retries" % consumer.retries)
def test_dropping_oversize_msg(self): q = Queue() consumer = Consumer(q, '') oversize_msg = {'m': 'x' * MAX_MSG_SIZE} q.put(oversize_msg) next = consumer.next() self.assertEqual(next, []) self.assertTrue(q.empty())
def test_next_limit(self): q = Queue() upload_size = 50 consumer = Consumer(q, '', upload_size) for i in range(10000): q.put(i) next = consumer.next() self.assertEqual(next, list(range(upload_size)))
def test_next_limit(self): q = Queue() flush_at = 50 consumer = Consumer(q, '', flush_at) for i in range(10000): q.put(i) next = consumer.next() self.assertEqual(next, list(range(flush_at)))
def test_request(cls): consumer = Consumer(None, 'testsecret') track = { 'type': 'track', 'event': 'python event', 'userId': 'userId' } consumer.request([track])
def __init__(self, write_key=None, host=None, debug=False, max_queue_size=10000, send=True, on_error=None, flush_at=100, flush_interval=0.5, gzip=False, max_retries=3, sync_mode=False, timeout=15, thread=1): require('write_key', write_key, string_types) self.queue = queue.Queue(max_queue_size) self.write_key = write_key self.on_error = on_error self.debug = debug self.send = send self.sync_mode = sync_mode self.host = host self.gzip = gzip self.timeout = timeout if debug: self.log.setLevel(logging.DEBUG) if sync_mode: self.consumers = None else: # On program exit, allow the consumer thread to exit cleanly. # This prevents exceptions and a messy shutdown when the # interpreter is destroyed before the daemon thread finishes # execution. However, it is *not* the same as flushing the queue! # To guarantee all messages have been delivered, you'll still need # to call flush(). if send: atexit.register(self.join) for n in range(thread): self.consumers = [] consumer = Consumer( self.queue, write_key, host=host, on_error=on_error, flush_at=flush_at, flush_interval=flush_interval, gzip=gzip, retries=max_retries, timeout=timeout, ) self.consumers.append(consumer) # if we've disabled sending, just don't start the consumer if send: consumer.start()
def __init__(self, write_key=None, debug=False, max_queue_size=10000, send=True, on_error=None): require('write_key', write_key, string_types) self.queue = queue.Queue(max_queue_size) self.consumer = Consumer(self.queue, write_key, on_error=on_error) self.write_key = write_key self.on_error = on_error self.debug = debug self.send = send if debug: self.log.setLevel(logging.DEBUG) # if we've disabled sending, just don't start the consumer if send: self.consumer.start()
def test_multiple_uploads_per_interval(self): # Put _flush_at*2_ items in the queue at once, then pause for # _flush_interval_. The consumer should upload 2 times. q = Queue() flush_interval = 0.5 flush_at = 10 consumer = Consumer(q, 'testsecret', flush_at=flush_at, flush_interval=flush_interval) with mock.patch('analytics.consumer.post') as mock_post: consumer.start() for i in range(0, flush_at * 2): track = { 'type': 'track', 'event': 'python event %d' % i, 'userId': 'userId' } q.put(track) time.sleep(flush_interval * 1.1) self.assertEqual(mock_post.call_count, 2)
def test_flush_interval(self): # Put _n_ items in the queue, pausing a little bit more than # _flush_interval_ after each one. # The consumer should upload _n_ times. q = Queue() flush_interval = 0.3 consumer = Consumer(q, 'testsecret', flush_at=10, flush_interval=flush_interval) with mock.patch('analytics.consumer.post') as mock_post: consumer.start() for i in range(0, 3): track = { 'type': 'track', 'event': 'python event %d' % i, 'userId': 'userId' } q.put(track) time.sleep(flush_interval * 1.1) self.assertEqual(mock_post.call_count, 3)
def test_proxies(cls): consumer = Consumer(None, 'testsecret', proxies='203.243.63.16:80') track = {'type': 'track', 'event': 'python event', 'userId': 'userId'} consumer.request([track])
def test_pause(self): consumer = Consumer(None, 'testsecret') consumer.pause() self.assertFalse(consumer.running)
def test_next(self): q = Queue() consumer = Consumer(q, '') q.put(1) next = consumer.next() self.assertEqual(next, [1])