spark-instrumented-optimizer/python/pyspark/streaming/kinesis.py
itholic 236c6c9f7c [SPARK-33253][PYTHON][DOCS] Migration to NumPy documentation style in Streaming (pyspark.streaming.*)
### What changes were proposed in this pull request?

This PR proposes to migrate to [NumPy documentation style](https://numpydoc.readthedocs.io/en/latest/format.html), see also [SPARK-33243](https://issues.apache.org/jira/browse/SPARK-33243).

### Why are the changes needed?

For better documentation as text itself, and generated HTMLs

### Does this PR introduce _any_ user-facing change?

Yes, they will see a better format of HTMLs, and better text format. See [SPARK-33243](https://issues.apache.org/jira/browse/SPARK-33243).

### How was this patch tested?

Manually tested via running ./dev/lint-python.

Closes #30346 from itholic/SPARK-32085.

Lead-authored-by: itholic <haejoon309@naver.com>
Co-authored-by: Hyukjin Kwon <gurwls223@gmail.com>
Signed-off-by: HyukjinKwon <gurwls223@apache.org>
2020-11-16 10:44:57 +09:00

123 lines
5.3 KiB
Python

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from pyspark.serializers import NoOpSerializer
from pyspark.storagelevel import StorageLevel
from pyspark.streaming import DStream
from pyspark.util import _print_missing_jar
__all__ = ['KinesisUtils', 'InitialPositionInStream', 'utf8_decoder']
def utf8_decoder(s):
""" Decode the unicode as UTF-8 """
if s is None:
return None
return s.decode('utf-8')
class KinesisUtils(object):
@staticmethod
def createStream(ssc, kinesisAppName, streamName, endpointUrl, regionName,
initialPositionInStream, checkpointInterval,
storageLevel=StorageLevel.MEMORY_AND_DISK_2,
awsAccessKeyId=None, awsSecretKey=None, decoder=utf8_decoder,
stsAssumeRoleArn=None, stsSessionName=None, stsExternalId=None):
"""
Create an input stream that pulls messages from a Kinesis stream. This uses the
Kinesis Client Library (KCL) to pull messages from Kinesis.
Parameters
----------
ssc : :class:`StreamingContext`
StreamingContext object
kinesisAppName : str
Kinesis application name used by the Kinesis Client Library (KCL) to
update DynamoDB
streamName : str
Kinesis stream name
endpointUrl : str
Url of Kinesis service (e.g., https://kinesis.us-east-1.amazonaws.com)
regionName : str
Name of region used by the Kinesis Client Library (KCL) to update
DynamoDB (lease coordination and checkpointing) and CloudWatch (metrics)
initialPositionInStream : int
In the absence of Kinesis checkpoint info, this is the
worker's initial starting position in the stream. The
values are either the beginning of the stream per Kinesis'
limit of 24 hours (InitialPositionInStream.TRIM_HORIZON) or
the tip of the stream (InitialPositionInStream.LATEST).
checkpointInterval : int
Checkpoint interval(in seconds) for Kinesis checkpointing. See the Kinesis
Spark Streaming documentation for more details on the different
types of checkpoints.
storageLevel : :class:`pyspark.StorageLevel`, optional
Storage level to use for storing the received objects (default is
StorageLevel.MEMORY_AND_DISK_2)
awsAccessKeyId : str, optional
AWS AccessKeyId (default is None. If None, will use
DefaultAWSCredentialsProviderChain)
awsSecretKey : str, optional
AWS SecretKey (default is None. If None, will use
DefaultAWSCredentialsProviderChain)
decoder : function, optional
A function used to decode value (default is utf8_decoder)
stsAssumeRoleArn : str, optional
ARN of IAM role to assume when using STS sessions to read from
the Kinesis stream (default is None).
stsSessionName : str, optional
Name to uniquely identify STS sessions used to read from Kinesis
stream, if STS is being used (default is None).
stsExternalId : str, optional
External ID that can be used to validate against the assumed IAM
role's trust policy, if STS is being used (default is None).
Returns
-------
A DStream object
Notes
-----
The given AWS credentials will get saved in DStream checkpoints if checkpointing
is enabled. Make sure that your checkpoint directory is secure.
"""
jlevel = ssc._sc._getJavaStorageLevel(storageLevel)
jduration = ssc._jduration(checkpointInterval)
try:
helper = ssc._jvm.org.apache.spark.streaming.kinesis.KinesisUtilsPythonHelper()
except TypeError as e:
if str(e) == "'JavaPackage' object is not callable":
_print_missing_jar(
"Streaming's Kinesis",
"streaming-kinesis-asl",
"streaming-kinesis-asl-assembly",
ssc.sparkContext.version)
raise
jstream = helper.createStream(ssc._jssc, kinesisAppName, streamName, endpointUrl,
regionName, initialPositionInStream, jduration, jlevel,
awsAccessKeyId, awsSecretKey, stsAssumeRoleArn,
stsSessionName, stsExternalId)
stream = DStream(jstream, ssc, NoOpSerializer())
return stream.map(lambda v: decoder(v))
class InitialPositionInStream(object):
LATEST, TRIM_HORIZON = (0, 1)