| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="../../../"> |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.io.kinesis — Apache Beam 2.67.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="../../../_static/jquery.js?v=5d32c60e"></script> |
| <script src="../../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="../../../_static/documentation_options.js?v=959b4fbe"></script> |
| <script src="../../../_static/doctools.js?v=9a2dae69"></script> |
| <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="../../../_static/js/theme.js"></script> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| <div class="wy-grid-for-nav"> |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../index.html" class="icon icon-home"> |
| Apache Beam |
| </a> |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| </div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu"> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" > |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../index.html">Apache Beam</a> |
| </nav> |
| |
| <div class="wy-nav-content"> |
| <div class="rst-content"> |
| <div role="navigation" aria-label="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="../../../index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="../../index.html">Module code</a></li> |
| <li class="breadcrumb-item active">apache_beam.io.kinesis</li> |
| <li class="wy-breadcrumbs-aside"> |
| </li> |
| </ul> |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for apache_beam.io.kinesis</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""PTransforms for supporting Kinesis streaming in Python pipelines.</span> |
| |
| <span class="sd"> These transforms are currently supported by Beam Flink and Spark portable</span> |
| <span class="sd"> runners.</span> |
| |
| <span class="sd"> **Setup**</span> |
| |
| <span class="sd"> Transforms provided in this module are cross-language transforms</span> |
| <span class="sd"> implemented in the Beam Java SDK. During the pipeline construction, Python SDK</span> |
| <span class="sd"> will connect to a Java expansion service to expand these transforms.</span> |
| <span class="sd"> To facilitate this, a small amount of setup is needed before using these</span> |
| <span class="sd"> transforms in a Beam Python pipeline.</span> |
| |
| <span class="sd"> There are several ways to setup cross-language Kinesis transforms.</span> |
| |
| <span class="sd"> * Option 1: use the default expansion service</span> |
| <span class="sd"> * Option 2: specify a custom expansion service</span> |
| |
| <span class="sd"> See below for details regarding each of these options.</span> |
| |
| <span class="sd"> *Option 1: Use the default expansion service*</span> |
| |
| <span class="sd"> This is the recommended and easiest setup option for using Python Kinesis</span> |
| <span class="sd"> transforms. This option is only available for Beam 2.25.0 and later.</span> |
| |
| <span class="sd"> This option requires following pre-requisites before running the Beam</span> |
| <span class="sd"> pipeline.</span> |
| |
| <span class="sd"> * Install Java runtime in the computer from where the pipeline is constructed</span> |
| <span class="sd"> and make sure that 'java' command is available or set JAVA_HOME environment</span> |
| <span class="sd"> variable.</span> |
| |
| <span class="sd"> In this option, Python SDK will either download (for released Beam version) or</span> |
| <span class="sd"> build (when running from a Beam Git clone) a expansion service jar and use</span> |
| <span class="sd"> that to expand transforms. Currently Kinesis transforms use the</span> |
| <span class="sd"> 'beam-sdks-java-io-amazon-web-services2-expansion-service' jar for this</span> |
| <span class="sd"> purpose.</span> |
| |
| <span class="sd"> *Option 2: specify a custom expansion service*</span> |
| |
| <span class="sd"> In this option, you startup your own expansion service and provide that as</span> |
| <span class="sd"> a parameter when using the transforms provided in this module.</span> |
| |
| <span class="sd"> This option requires following pre-requisites before running the Beam</span> |
| <span class="sd"> pipeline.</span> |
| |
| <span class="sd"> * Startup your own expansion service.</span> |
| <span class="sd"> * Update your pipeline to provide the expansion service address when</span> |
| <span class="sd"> initiating Kinesis transforms provided in this module.</span> |
| |
| <span class="sd"> Flink Users can use the built-in Expansion Service of the Flink Runner's</span> |
| <span class="sd"> Job Server. If you start Flink's Job Server, the expansion service will be</span> |
| <span class="sd"> started on port 8097. For a different address, please set the</span> |
| <span class="sd"> expansion_service parameter.</span> |
| |
| <span class="sd"> **More information**</span> |
| |
| <span class="sd"> For more information regarding cross-language transforms see:</span> |
| <span class="sd"> - https://beam.apache.org/roadmap/portability/</span> |
| |
| <span class="sd"> For more information specific to Flink runner see:</span> |
| <span class="sd"> - https://beam.apache.org/documentation/runners/flink/</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">time</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam</span><span class="w"> </span><span class="kn">import</span> <span class="n">BeamJarExpansionService</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam</span><span class="w"> </span><span class="kn">import</span> <span class="n">ExternalTransform</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam</span><span class="w"> </span><span class="kn">import</span> <span class="n">NamedTupleBasedPayloadBuilder</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'WriteToKinesis'</span><span class="p">,</span> |
| <span class="s1">'ReadDataFromKinesis'</span><span class="p">,</span> |
| <span class="s1">'InitialPositionInStream'</span><span class="p">,</span> |
| <span class="s1">'WatermarkPolicy'</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">default_io_expansion_service</span><span class="p">():</span> |
| <span class="k">return</span> <span class="n">BeamJarExpansionService</span><span class="p">(</span> |
| <span class="s1">'sdks:java:io:amazon-web-services2:expansion-service:shadowJar'</span><span class="p">)</span> |
| |
| |
| <span class="n">WriteToKinesisSchema</span> <span class="o">=</span> <span class="n">NamedTuple</span><span class="p">(</span> |
| <span class="s1">'WriteToKinesisSchema'</span><span class="p">,</span> |
| <span class="p">[</span> |
| <span class="p">(</span><span class="s1">'stream_name'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'aws_access_key'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'aws_secret_key'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'region'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'partition_key'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'service_endpoint'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'verify_certificate'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'aggregation_enabled'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'aggregation_max_bytes'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'aggregation_max_buffered_time'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'aggregation_shard_refresh_interval'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">],</span> |
| <span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="WriteToKinesis"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.WriteToKinesis">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">WriteToKinesis</span><span class="p">(</span><span class="n">ExternalTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> An external PTransform which writes byte array stream to Amazon Kinesis.</span> |
| |
| <span class="sd"> Experimental; no backwards compatibility guarantees.</span> |
| <span class="sd"> """</span> |
| <span class="n">URN</span> <span class="o">=</span> <span class="s1">'beam:transform:org.apache.beam:kinesis_write:v2'</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">stream_name</span><span class="p">,</span> |
| <span class="n">aws_access_key</span><span class="p">,</span> |
| <span class="n">aws_secret_key</span><span class="p">,</span> |
| <span class="n">region</span><span class="p">,</span> |
| <span class="n">partition_key</span><span class="p">,</span> |
| <span class="n">service_endpoint</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">verify_certificate</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">producer_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">aggregation_enabled</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">aggregation_max_bytes</span><span class="o">=</span><span class="mi">51200</span><span class="p">,</span> |
| <span class="n">aggregation_max_buffered_time</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> |
| <span class="n">aggregation_shard_refresh_interval</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Initializes a write operation to Kinesis.</span> |
| |
| <span class="sd"> :param stream_name: Kinesis stream name.</span> |
| <span class="sd"> :param aws_access_key: Kinesis access key.</span> |
| <span class="sd"> :param aws_secret_key: Kinesis access key secret.</span> |
| <span class="sd"> :param region: AWS region. Example: 'us-east-1'.</span> |
| <span class="sd"> :param service_endpoint: Kinesis service endpoint</span> |
| <span class="sd"> :param verify_certificate: Enable or disable certificate verification.</span> |
| <span class="sd"> Never set to False on production. True by default.</span> |
| <span class="sd"> :param partition_key: Specify default partition key.</span> |
| <span class="sd"> :param producer_properties: (Deprecated) This option no longer is available</span> |
| <span class="sd"> since the AWS IOs upgraded to v2. Trying to set it will lead to an</span> |
| <span class="sd"> error. For more info, see https://github.com/apache/beam/issues/33430.</span> |
| <span class="sd"> :param expansion_service: The address (host:port) of the ExpansionService.</span> |
| <span class="sd"> :param aggregation_enabled: Enable or disable aggregation.</span> |
| <span class="sd"> :param aggregation_max_bytes: Maximum number of bytes to buffer before</span> |
| <span class="sd"> sending a batch of records. Defaults to 51200.</span> |
| <span class="sd"> :param aggregation_max_buffered_time: Maximum time(millisecond) to buffer</span> |
| <span class="sd"> records before sending a batch of records. Defaults to 100.</span> |
| <span class="sd"> :param aggregation_shard_refresh_interval: Interval in minutes to refresh</span> |
| <span class="sd"> the shard map. Defaults to 2.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">producer_properties</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'producer_properties is no longer supported and will be removed '</span> <span class="o">+</span> |
| <span class="s1">'in a future release.'</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span> |
| <span class="n">NamedTupleBasedPayloadBuilder</span><span class="p">(</span> |
| <span class="n">WriteToKinesisSchema</span><span class="p">(</span> |
| <span class="n">stream_name</span><span class="o">=</span><span class="n">stream_name</span><span class="p">,</span> |
| <span class="n">aws_access_key</span><span class="o">=</span><span class="n">aws_access_key</span><span class="p">,</span> |
| <span class="n">aws_secret_key</span><span class="o">=</span><span class="n">aws_secret_key</span><span class="p">,</span> |
| <span class="n">region</span><span class="o">=</span><span class="n">region</span><span class="p">,</span> |
| <span class="n">partition_key</span><span class="o">=</span><span class="n">partition_key</span><span class="p">,</span> |
| <span class="n">service_endpoint</span><span class="o">=</span><span class="n">service_endpoint</span><span class="p">,</span> |
| <span class="n">verify_certificate</span><span class="o">=</span><span class="n">verify_certificate</span><span class="p">,</span> |
| <span class="n">aggregation_enabled</span><span class="o">=</span><span class="n">aggregation_enabled</span><span class="p">,</span> |
| <span class="n">aggregation_max_bytes</span><span class="o">=</span><span class="n">aggregation_max_bytes</span><span class="p">,</span> |
| <span class="n">aggregation_max_buffered_time</span><span class="o">=</span><span class="n">aggregation_max_buffered_time</span><span class="p">,</span> |
| <span class="n">aggregation_shard_refresh_interval</span><span class="o">=</span> |
| <span class="n">aggregation_shard_refresh_interval</span><span class="p">,</span> |
| <span class="p">)),</span> |
| <span class="n">expansion_service</span> <span class="ow">or</span> <span class="n">default_io_expansion_service</span><span class="p">(),</span> |
| <span class="p">)</span></div> |
| |
| |
| |
| <span class="n">ReadFromKinesisSchema</span> <span class="o">=</span> <span class="n">NamedTuple</span><span class="p">(</span> |
| <span class="s1">'ReadFromKinesisSchema'</span><span class="p">,</span> |
| <span class="p">[</span> |
| <span class="p">(</span><span class="s1">'stream_name'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'aws_access_key'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'aws_secret_key'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'region'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'service_endpoint'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'verify_certificate'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'max_num_records'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'max_read_time'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'initial_position_in_stream'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'initial_timestamp_in_stream'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'request_records_limit'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'up_to_date_threshold'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'max_capacity_per_shard'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'watermark_policy'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'watermark_idle_duration_threshold'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'rate_limit'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">],</span> |
| <span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="ReadDataFromKinesis"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.ReadDataFromKinesis">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">ReadDataFromKinesis</span><span class="p">(</span><span class="n">ExternalTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> An external PTransform which reads byte array stream from Amazon Kinesis.</span> |
| |
| <span class="sd"> Experimental; no backwards compatibility guarantees.</span> |
| <span class="sd"> """</span> |
| <span class="n">URN</span> <span class="o">=</span> <span class="s1">'beam:transform:org.apache.beam:kinesis_read_data:v2'</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">stream_name</span><span class="p">,</span> |
| <span class="n">aws_access_key</span><span class="p">,</span> |
| <span class="n">aws_secret_key</span><span class="p">,</span> |
| <span class="n">region</span><span class="p">,</span> |
| <span class="n">service_endpoint</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">verify_certificate</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_num_records</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_read_time</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">initial_position_in_stream</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">initial_timestamp_in_stream</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">request_records_limit</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">up_to_date_threshold</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_capacity_per_shard</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">watermark_policy</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">watermark_idle_duration_threshold</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">rate_limit</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Initializes a read operation from Kinesis.</span> |
| |
| <span class="sd"> :param stream_name: Kinesis stream name.</span> |
| <span class="sd"> :param aws_access_key: Kinesis access key.</span> |
| <span class="sd"> :param aws_secret_key: Kinesis access key secret.</span> |
| <span class="sd"> :param region: AWS region. Example: 'us-east-1'.</span> |
| <span class="sd"> :param service_endpoint: Kinesis service endpoint</span> |
| <span class="sd"> :param verify_certificate: Enable or disable certificate verification.</span> |
| <span class="sd"> Never set to False on production. True by default.</span> |
| <span class="sd"> :param max_num_records: Specifies to read at most a given number of records.</span> |
| <span class="sd"> Must be greater than 0.</span> |
| <span class="sd"> :param max_read_time: Specifies to read records during x milliseconds.</span> |
| <span class="sd"> :param initial_timestamp_in_stream: Specify reading beginning at the given</span> |
| <span class="sd"> timestamp in milliseconds. Must be in the past.</span> |
| <span class="sd"> :param initial_position_in_stream: Specify reading from some initial</span> |
| <span class="sd"> position in stream. Possible values:</span> |
| <span class="sd"> LATEST - Start after the most recent data record (fetch new data).</span> |
| <span class="sd"> TRIM_HORIZON - Start from the oldest available data record.</span> |
| <span class="sd"> AT_TIMESTAMP - Start from the record at or after the specified</span> |
| <span class="sd"> server-side timestamp.</span> |
| <span class="sd"> :param request_records_limit: Specifies the maximum number of records in</span> |
| <span class="sd"> GetRecordsResult returned by GetRecords call which is limited by 10K</span> |
| <span class="sd"> records. If should be adjusted according to average size of data record</span> |
| <span class="sd"> to prevent shard overloading. More at:</span> |
| <span class="sd"> docs.aws.amazon.com/kinesis/latest/APIReference/API_GetRecords.html</span> |
| <span class="sd"> :param up_to_date_threshold: Specifies how late in milliseconds records</span> |
| <span class="sd"> consumed by this source can be to still be considered on time. Defaults</span> |
| <span class="sd"> to zero.</span> |
| <span class="sd"> :param max_capacity_per_shard: Specifies the maximum number of messages per</span> |
| <span class="sd"> one shard. Defaults to 10'000.</span> |
| <span class="sd"> :param watermark_policy: Specifies the watermark policy. Possible values:</span> |
| <span class="sd"> PROCESSING_TYPE, ARRIVAL_TIME. Defaults to ARRIVAL_TIME.</span> |
| <span class="sd"> :param watermark_idle_duration_threshold: Use only when watermark policy is</span> |
| <span class="sd"> ARRIVAL_TIME. Denotes the duration for which the watermark can be idle.</span> |
| <span class="sd"> Passed in milliseconds.</span> |
| <span class="sd"> :param rate_limit: Sets fixed rate policy for given milliseconds value. By</span> |
| <span class="sd"> default there is no rate limit.</span> |
| <span class="sd"> :param expansion_service: The address (host:port) of the ExpansionService.</span> |
| <span class="sd"> """</span> |
| <span class="n">WatermarkPolicy</span><span class="o">.</span><span class="n">validate_param</span><span class="p">(</span><span class="n">watermark_policy</span><span class="p">)</span> |
| <span class="n">InitialPositionInStream</span><span class="o">.</span><span class="n">validate_param</span><span class="p">(</span><span class="n">initial_position_in_stream</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">watermark_idle_duration_threshold</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">WatermarkPolicy</span><span class="o">.</span><span class="n">ARRIVAL_TIME</span> <span class="o">==</span> <span class="n">watermark_policy</span> |
| |
| <span class="k">if</span> <span class="n">request_records_limit</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="mi">0</span> <span class="o"><</span> <span class="n">request_records_limit</span> <span class="o"><=</span> <span class="mi">10000</span> |
| |
| <span class="n">initial_timestamp_in_stream</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span> |
| <span class="n">initial_timestamp_in_stream</span><span class="p">)</span> <span class="k">if</span> <span class="n">initial_timestamp_in_stream</span> <span class="k">else</span> <span class="kc">None</span> |
| |
| <span class="k">if</span> <span class="n">initial_timestamp_in_stream</span> <span class="ow">and</span> <span class="n">initial_timestamp_in_stream</span> <span class="o"><</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">(</span> |
| <span class="p">):</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">'Provided timestamp emplaced not in the past.'</span><span class="p">)</span> |
| |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span> |
| <span class="n">NamedTupleBasedPayloadBuilder</span><span class="p">(</span> |
| <span class="n">ReadFromKinesisSchema</span><span class="p">(</span> |
| <span class="n">stream_name</span><span class="o">=</span><span class="n">stream_name</span><span class="p">,</span> |
| <span class="n">aws_access_key</span><span class="o">=</span><span class="n">aws_access_key</span><span class="p">,</span> |
| <span class="n">aws_secret_key</span><span class="o">=</span><span class="n">aws_secret_key</span><span class="p">,</span> |
| <span class="n">region</span><span class="o">=</span><span class="n">region</span><span class="p">,</span> |
| <span class="n">service_endpoint</span><span class="o">=</span><span class="n">service_endpoint</span><span class="p">,</span> |
| <span class="n">verify_certificate</span><span class="o">=</span><span class="n">verify_certificate</span><span class="p">,</span> |
| <span class="n">max_num_records</span><span class="o">=</span><span class="n">max_num_records</span><span class="p">,</span> |
| <span class="n">max_read_time</span><span class="o">=</span><span class="n">max_read_time</span><span class="p">,</span> |
| <span class="n">initial_position_in_stream</span><span class="o">=</span><span class="n">initial_position_in_stream</span><span class="p">,</span> |
| <span class="n">initial_timestamp_in_stream</span><span class="o">=</span><span class="n">initial_timestamp_in_stream</span><span class="p">,</span> |
| <span class="n">request_records_limit</span><span class="o">=</span><span class="n">request_records_limit</span><span class="p">,</span> |
| <span class="n">up_to_date_threshold</span><span class="o">=</span><span class="n">up_to_date_threshold</span><span class="p">,</span> |
| <span class="n">max_capacity_per_shard</span><span class="o">=</span><span class="n">max_capacity_per_shard</span><span class="p">,</span> |
| <span class="n">watermark_policy</span><span class="o">=</span><span class="n">watermark_policy</span><span class="p">,</span> |
| <span class="n">watermark_idle_duration_threshold</span><span class="o">=</span> |
| <span class="n">watermark_idle_duration_threshold</span><span class="p">,</span> |
| <span class="n">rate_limit</span><span class="o">=</span><span class="n">rate_limit</span><span class="p">,</span> |
| <span class="p">)),</span> |
| <span class="n">expansion_service</span> <span class="ow">or</span> <span class="n">default_io_expansion_service</span><span class="p">(),</span> |
| <span class="p">)</span></div> |
| |
| |
| |
| <div class="viewcode-block" id="InitialPositionInStream"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.InitialPositionInStream">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">InitialPositionInStream</span><span class="p">:</span> |
| <span class="n">LATEST</span> <span class="o">=</span> <span class="s1">'LATEST'</span> |
| <span class="n">TRIM_HORIZON</span> <span class="o">=</span> <span class="s1">'TRIM_HORIZON'</span> |
| <span class="n">AT_TIMESTAMP</span> <span class="o">=</span> <span class="s1">'AT_TIMESTAMP'</span> |
| |
| <div class="viewcode-block" id="InitialPositionInStream.validate_param"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.InitialPositionInStream.validate_param">[docs]</a> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">validate_param</span><span class="p">(</span><span class="n">param</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">param</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">InitialPositionInStream</span><span class="p">,</span> <span class="n">param</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'Invalid initial position in stream: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">param</span><span class="p">))</span></div> |
| </div> |
| |
| |
| |
| <div class="viewcode-block" id="WatermarkPolicy"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.WatermarkPolicy">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">WatermarkPolicy</span><span class="p">:</span> |
| <span class="n">PROCESSING_TYPE</span> <span class="o">=</span> <span class="s1">'PROCESSING_TYPE'</span> |
| <span class="n">ARRIVAL_TIME</span> <span class="o">=</span> <span class="s1">'ARRIVAL_TIME'</span> |
| |
| <div class="viewcode-block" id="WatermarkPolicy.validate_param"> |
| <a class="viewcode-back" href="../../../apache_beam.io.kinesis.html#apache_beam.io.kinesis.WatermarkPolicy.validate_param">[docs]</a> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">validate_param</span><span class="p">(</span><span class="n">param</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">param</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">WatermarkPolicy</span><span class="p">,</span> <span class="n">param</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'Invalid watermark policy: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">param</span><span class="p">))</span></div> |
| </div> |
| |
| </pre></div> |
| |
| </div> |
| </div> |
| <footer> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |