blob: d47622315b260747ff06421ddce35cf7fa48b5ed [file]
<!DOCTYPE html>
<html >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>pyspark.streaming.kinesis &#8212; PySpark 4.1.0-preview2 documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "light";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=e353d410970836974a52" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=e353d410970836974a52" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=e353d410970836974a52" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.1.2/css/all.min.css?digest=e353d410970836974a52" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" />
<link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52" />
<script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
<script src="../../../_static/jquery.js"></script>
<script src="../../../_static/underscore.js"></script>
<script src="../../../_static/doctools.js"></script>
<script src="../../../_static/clipboard.min.js"></script>
<script src="../../../_static/copybutton.js"></script>
<script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
<script>DOCUMENTATION_OPTIONS.pagename = '_modules/pyspark/streaming/kinesis';</script>
<script>
DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://spark.apache.org/static/versions.json';
DOCUMENTATION_OPTIONS.theme_switcher_version_match = '4.1.0-preview2';
</script>
<link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/streaming/kinesis.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="None">
<!-- Matomo -->
<script type="text/javascript">
var _paq = window._paq = window._paq || [];
/* tracker methods like "setCustomDimension" should be called before "trackPageView" */
_paq.push(["disableCookies"]);
_paq.push(['trackPageView']);
_paq.push(['enableLinkTracking']);
(function() {
var u="https://analytics.apache.org/";
_paq.push(['setTrackerUrl', u+'matomo.php']);
_paq.push(['setSiteId', '40']);
var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
})();
</script>
<!-- End Matomo Code -->
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<a class="skip-link" href="#main-content">Skip to main content</a>
<input type="checkbox"
class="sidebar-toggle"
name="__primary"
id="__primary"/>
<label class="overlay overlay-primary" for="__primary"></label>
<input type="checkbox"
class="sidebar-toggle"
name="__secondary"
id="__secondary"/>
<label class="overlay overlay-secondary" for="__secondary"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search the docs ..."
aria-label="Search the docs ..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<nav class="bd-header navbar navbar-expand-lg bd-navbar">
<div class="bd-header__inner bd-page-width">
<label class="sidebar-toggle primary-toggle" for="__primary">
<span class="fa-solid fa-bars"></span>
</label>
<div class="navbar-header-items__start">
<div class="navbar-item">
<a class="navbar-brand logo" href="../../../index.html">
<img src="https://spark.apache.org/images/spark-logo.png" class="logo__image only-light" alt="Logo image"/>
<script>document.write(`<img src="https://spark.apache.org/images/spark-logo-rev.svg" class="logo__image only-dark" alt="Logo image"/>`);</script>
</a></div>
</div>
<div class="col-lg-9 navbar-header-items">
<div class="me-auto navbar-header-items__center">
<div class="navbar-item"><nav class="navbar-nav">
<p class="sidebar-header-items__title"
role="heading"
aria-level="1"
aria-label="Site Navigation">
Site Navigation
</p>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../index.html">
Overview
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../getting_started/index.html">
Getting Started
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../tutorial/index.html">
Tutorials
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../user_guide/index.html">
User Guide
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../reference/index.html">
API Reference
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../development/index.html">
Development
</a>
</li>
<div class="nav-item dropdown">
<button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
More
</button>
<div class="dropdown-menu">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../migration_guide/index.html">
Migration Guides
</a>
</li>
</div>
</div>
</ul>
</nav></div>
</div>
<div class="navbar-header-items__end">
<div class="navbar-item navbar-persistent--container">
<script>
document.write(`
<button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
</button>
`);
</script>
</div>
<div class="navbar-item">
<script>
document.write(`
<div class="version-switcher__container dropdown">
<button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown">
4.1.0-preview2 <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div class="version-switcher__menu dropdown-menu list-group-flush py-0">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div>
`);
</script></div>
<div class="navbar-item">
<script>
document.write(`
<button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span>
<span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span>
<span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span>
</button>
`);
</script></div>
<div class="navbar-item"><ul class="navbar-icon-links navbar-nav"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span>
<label class="sr-only">GitHub</label></a>
</li>
<li class="nav-item">
<a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span>
<label class="sr-only">PyPI</label></a>
</li>
</ul></div>
</div>
</div>
<div class="navbar-persistent--mobile">
<script>
document.write(`
<button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
</button>
`);
</script>
</div>
</div>
</nav>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar hide-on-wide">
<div class="sidebar-header-items sidebar-primary__section">
<div class="sidebar-header-items__center">
<div class="navbar-item"><nav class="navbar-nav">
<p class="sidebar-header-items__title"
role="heading"
aria-level="1"
aria-label="Site Navigation">
Site Navigation
</p>
<ul class="bd-navbar-elements navbar-nav">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../index.html">
Overview
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../getting_started/index.html">
Getting Started
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../tutorial/index.html">
Tutorials
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../user_guide/index.html">
User Guide
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../reference/index.html">
API Reference
</a>
</li>
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../development/index.html">
Development
</a>
</li>
<div class="nav-item dropdown">
<button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false">
More
</button>
<div class="dropdown-menu">
<li class="nav-item">
<a class="nav-link nav-internal" href="../../../migration_guide/index.html">
Migration Guides
</a>
</li>
</div>
</div>
</ul>
</nav></div>
</div>
<div class="sidebar-header-items__end">
<div class="navbar-item">
<script>
document.write(`
<div class="version-switcher__container dropdown">
<button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown">
4.1.0-preview2 <!-- this text may get changed later by javascript -->
<span class="caret"></span>
</button>
<div class="version-switcher__menu dropdown-menu list-group-flush py-0">
<!-- dropdown will be populated by javascript on page load -->
</div>
</div>
`);
</script></div>
<div class="navbar-item">
<script>
document.write(`
<button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span>
<span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span>
<span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span>
</button>
`);
</script></div>
<div class="navbar-item"><ul class="navbar-icon-links navbar-nav"
aria-label="Icon Links">
<li class="nav-item">
<a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span>
<label class="sr-only">GitHub</label></a>
</li>
<li class="nav-item">
<a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span>
<label class="sr-only">PyPI</label></a>
</li>
</ul></div>
</div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main">
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item">
<nav aria-label="Breadcrumbs">
<ul class="bd-breadcrumbs" role="navigation" aria-label="Breadcrumb">
<li class="breadcrumb-item breadcrumb-home">
<a href="../../../index.html" class="nav-link" aria-label="Home">
<i class="fa-solid fa-home"></i>
</a>
</li>
<li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li>
<li class="breadcrumb-item active" aria-current="page">pyspark.streaming.kinesis</li>
</ul>
</nav>
</div>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article" role="main">
<h1>Source code for pyspark.streaming.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 &quot;License&quot;); 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 &quot;AS IS&quot; 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="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">overload</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">TypeVar</span><span class="p">,</span> <span class="n">Union</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.serializers</span><span class="w"> </span><span class="kn">import</span> <span class="n">NoOpSerializer</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.storagelevel</span><span class="w"> </span><span class="kn">import</span> <span class="n">StorageLevel</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.streaming</span><span class="w"> </span><span class="kn">import</span> <span class="n">DStream</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.streaming.context</span><span class="w"> </span><span class="kn">import</span> <span class="n">StreamingContext</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.util</span><span class="w"> </span><span class="kn">import</span> <span class="n">_print_missing_jar</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;KinesisUtils&quot;</span><span class="p">,</span> <span class="s2">&quot;InitialPositionInStream&quot;</span><span class="p">,</span> <span class="s2">&quot;MetricsLevel&quot;</span><span class="p">,</span> <span class="s2">&quot;utf8_decoder&quot;</span><span class="p">]</span>
<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="p">,</span> <span class="n">TRIM_HORIZON</span> <span class="o">=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">class</span><span class="w"> </span><span class="nc">MetricsLevel</span><span class="p">:</span>
<span class="n">DETAILED</span><span class="p">,</span> <span class="n">SUMMARY</span><span class="p">,</span> <span class="n">NONE</span> <span class="o">=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">&quot;T&quot;</span><span class="p">)</span>
<span class="k">def</span><span class="w"> </span><span class="nf">utf8_decoder</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bytes</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Decode the unicode as UTF-8&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">s</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">&quot;utf-8&quot;</span><span class="p">)</span>
<span class="k">class</span><span class="w"> </span><span class="nc">KinesisUtils</span><span class="p">:</span>
<span class="nd">@staticmethod</span>
<span class="nd">@overload</span>
<span class="k">def</span><span class="w"> </span><span class="nf">createStream</span><span class="p">(</span>
<span class="n">ssc</span><span class="p">:</span> <span class="n">StreamingContext</span><span class="p">,</span>
<span class="n">kinesisAppName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">streamName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">endpointUrl</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">regionName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">initialPositionInStream</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">metricsLevel</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">MetricsLevel</span><span class="o">.</span><span class="n">DETAILED</span><span class="p">,</span>
<span class="n">storageLevel</span><span class="p">:</span> <span class="n">StorageLevel</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">awsAccessKeyId</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">awsSecretKey</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="o">*</span><span class="p">,</span>
<span class="n">stsAssumeRoleArn</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">stsSessionName</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">stsExternalId</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DStream[Optional[str]]&quot;</span><span class="p">:</span>
<span class="o">...</span>
<span class="nd">@staticmethod</span>
<span class="nd">@overload</span>
<span class="k">def</span><span class="w"> </span><span class="nf">createStream</span><span class="p">(</span>
<span class="n">ssc</span><span class="p">:</span> <span class="n">StreamingContext</span><span class="p">,</span>
<span class="n">kinesisAppName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">streamName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">endpointUrl</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">regionName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">initialPositionInStream</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">metricsLevel</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">MetricsLevel</span><span class="o">.</span><span class="n">DETAILED</span><span class="p">,</span>
<span class="n">storageLevel</span><span class="p">:</span> <span class="n">StorageLevel</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">awsAccessKeyId</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">awsSecretKey</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">decoder</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Optional</span><span class="p">[</span><span class="nb">bytes</span><span class="p">]],</span> <span class="n">T</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">stsAssumeRoleArn</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">stsSessionName</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="n">stsExternalId</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="o">=</span> <span class="o">...</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DStream[T]&quot;</span><span class="p">:</span>
<span class="o">...</span>
<div class="viewcode-block" id="KinesisUtils.createStream"><a class="viewcode-back" href="../../../reference/api/pyspark.streaming.kinesis.KinesisUtils.createStream.html#pyspark.streaming.kinesis.KinesisUtils.createStream">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span><span class="w"> </span><span class="nf">createStream</span><span class="p">(</span>
<span class="n">ssc</span><span class="p">:</span> <span class="n">StreamingContext</span><span class="p">,</span>
<span class="n">kinesisAppName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">streamName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">endpointUrl</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">regionName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">initialPositionInStream</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">checkpointInterval</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
<span class="n">metricsLevel</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">MetricsLevel</span><span class="o">.</span><span class="n">DETAILED</span><span class="p">,</span>
<span class="n">storageLevel</span><span class="p">:</span> <span class="n">StorageLevel</span> <span class="o">=</span> <span class="n">StorageLevel</span><span class="o">.</span><span class="n">MEMORY_AND_DISK_2</span><span class="p">,</span>
<span class="n">awsAccessKeyId</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="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">awsSecretKey</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="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">decoder</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span>
<span class="n">Callable</span><span class="p">[[</span><span class="n">Optional</span><span class="p">[</span><span class="nb">bytes</span><span class="p">]],</span> <span class="n">T</span><span class="p">],</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Optional</span><span class="p">[</span><span class="nb">bytes</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="o">=</span> <span class="n">utf8_decoder</span><span class="p">,</span>
<span class="n">stsAssumeRoleArn</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="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">stsSessionName</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="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">stsExternalId</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="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Union</span><span class="p">[</span><span class="s2">&quot;DStream[Union[T, Optional[str]]]&quot;</span><span class="p">,</span> <span class="s2">&quot;DStream[T]&quot;</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Create an input stream that pulls messages from a Kinesis stream. This uses the</span>
<span class="sd"> Kinesis Client Library (KCL) to pull messages from Kinesis.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> ssc : :class:`StreamingContext`</span>
<span class="sd"> StreamingContext object</span>
<span class="sd"> kinesisAppName : str</span>
<span class="sd"> Kinesis application name used by the Kinesis Client Library (KCL) to</span>
<span class="sd"> update DynamoDB</span>
<span class="sd"> streamName : str</span>
<span class="sd"> Kinesis stream name</span>
<span class="sd"> endpointUrl : str</span>
<span class="sd"> Url of Kinesis service (e.g., https://kinesis.us-east-1.amazonaws.com)</span>
<span class="sd"> regionName : str</span>
<span class="sd"> Name of region used by the Kinesis Client Library (KCL) to update</span>
<span class="sd"> DynamoDB (lease coordination and checkpointing) and CloudWatch (metrics)</span>
<span class="sd"> initialPositionInStream : int</span>
<span class="sd"> In the absence of Kinesis checkpoint info, this is the</span>
<span class="sd"> worker&#39;s initial starting position in the stream. The</span>
<span class="sd"> values are either the beginning of the stream per Kinesis&#39;</span>
<span class="sd"> limit of 24 hours (InitialPositionInStream.TRIM_HORIZON) or</span>
<span class="sd"> the tip of the stream (InitialPositionInStream.LATEST).</span>
<span class="sd"> checkpointInterval : int</span>
<span class="sd"> Checkpoint interval(in seconds) for Kinesis checkpointing. See the Kinesis</span>
<span class="sd"> Spark Streaming documentation for more details on the different</span>
<span class="sd"> types of checkpoints.</span>
<span class="sd"> metricsLevel : int</span>
<span class="sd"> Level of CloudWatch PutMetrics.</span>
<span class="sd"> Can be set to either DETAILED, SUMMARY, or NONE. (default is DETAILED)</span>
<span class="sd"> storageLevel : :class:`pyspark.StorageLevel`, optional</span>
<span class="sd"> Storage level to use for storing the received objects (default is</span>
<span class="sd"> StorageLevel.MEMORY_AND_DISK_2)</span>
<span class="sd"> awsAccessKeyId : str, optional</span>
<span class="sd"> AWS AccessKeyId (default is None. If None, will use</span>
<span class="sd"> DefaultAWSCredentialsProviderChain)</span>
<span class="sd"> awsSecretKey : str, optional</span>
<span class="sd"> AWS SecretKey (default is None. If None, will use</span>
<span class="sd"> DefaultAWSCredentialsProviderChain)</span>
<span class="sd"> decoder : function, optional</span>
<span class="sd"> A function used to decode value (default is utf8_decoder)</span>
<span class="sd"> stsAssumeRoleArn : str, optional</span>
<span class="sd"> ARN of IAM role to assume when using STS sessions to read from</span>
<span class="sd"> the Kinesis stream (default is None).</span>
<span class="sd"> stsSessionName : str, optional</span>
<span class="sd"> Name to uniquely identify STS sessions used to read from Kinesis</span>
<span class="sd"> stream, if STS is being used (default is None).</span>
<span class="sd"> stsExternalId : str, optional</span>
<span class="sd"> External ID that can be used to validate against the assumed IAM</span>
<span class="sd"> role&#39;s trust policy, if STS is being used (default is None).</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> A DStream object</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> The given AWS credentials will get saved in DStream checkpoints if checkpointing</span>
<span class="sd"> is enabled. Make sure that your checkpoint directory is secure.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">jlevel</span> <span class="o">=</span> <span class="n">ssc</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_getJavaStorageLevel</span><span class="p">(</span><span class="n">storageLevel</span><span class="p">)</span>
<span class="n">jduration</span> <span class="o">=</span> <span class="n">ssc</span><span class="o">.</span><span class="n">_jduration</span><span class="p">(</span><span class="n">checkpointInterval</span><span class="p">)</span>
<span class="n">jvm</span> <span class="o">=</span> <span class="n">ssc</span><span class="o">.</span><span class="n">_jvm</span>
<span class="k">assert</span> <span class="n">jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">helper</span> <span class="o">=</span> <span class="n">jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">streaming</span><span class="o">.</span><span class="n">kinesis</span><span class="o">.</span><span class="n">KinesisUtilsPythonHelper</span><span class="p">()</span>
<span class="k">except</span> <span class="ne">TypeError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">==</span> <span class="s2">&quot;&#39;JavaPackage&#39; object is not callable&quot;</span><span class="p">:</span>
<span class="n">_print_missing_jar</span><span class="p">(</span>
<span class="s2">&quot;Streaming&#39;s Kinesis&quot;</span><span class="p">,</span>
<span class="s2">&quot;streaming-kinesis-asl&quot;</span><span class="p">,</span>
<span class="s2">&quot;streaming-kinesis-asl-assembly&quot;</span><span class="p">,</span>
<span class="n">ssc</span><span class="o">.</span><span class="n">sparkContext</span><span class="o">.</span><span class="n">version</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">raise</span>
<span class="n">jstream</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">createStream</span><span class="p">(</span>
<span class="n">ssc</span><span class="o">.</span><span class="n">_jssc</span><span class="p">,</span>
<span class="n">kinesisAppName</span><span class="p">,</span>
<span class="n">streamName</span><span class="p">,</span>
<span class="n">endpointUrl</span><span class="p">,</span>
<span class="n">regionName</span><span class="p">,</span>
<span class="n">initialPositionInStream</span><span class="p">,</span>
<span class="n">jduration</span><span class="p">,</span>
<span class="n">metricsLevel</span><span class="p">,</span>
<span class="n">jlevel</span><span class="p">,</span>
<span class="n">awsAccessKeyId</span><span class="p">,</span>
<span class="n">awsSecretKey</span><span class="p">,</span>
<span class="n">stsAssumeRoleArn</span><span class="p">,</span>
<span class="n">stsSessionName</span><span class="p">,</span>
<span class="n">stsExternalId</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">stream</span><span class="p">:</span> <span class="n">DStream</span> <span class="o">=</span> <span class="n">DStream</span><span class="p">(</span><span class="n">jstream</span><span class="p">,</span> <span class="n">ssc</span><span class="p">,</span> <span class="n">NoOpSerializer</span><span class="p">())</span>
<span class="k">return</span> <span class="n">stream</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">decoder</span><span class="p">(</span><span class="n">v</span><span class="p">))</span></div>
</pre></div>
</article>
<footer class="bd-footer-article">
<div class="footer-article-items footer-article__inner">
<div class="footer-article-item"><!-- Previous / next buttons -->
<div class="prev-next-area">
</div></div>
</div>
</footer>
</div>
</div>
<footer class="bd-footer-content">
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52"></script>
<footer class="bd-footer">
<div class="bd-footer__inner bd-page-width">
<div class="footer-items__start">
<div class="footer-item"><p class="copyright">
Copyright @ 2025 The Apache Software Foundation, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache License, Version 2.0</a>.
</p></div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 4.5.0.
<br/>
</p>
</div>
</div>
<div class="footer-items__end">
<div class="footer-item"><p class="theme-version">
Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.13.3.
</p></div>
</div>
</div>
</footer>
</body>
</html>