blob: b76f210a255683710159aa1e189b0ebb067bff43 [file] [log] [blame]
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<!-- NewPage -->
<html lang="en">
<head>
<!-- Generated by javadoc -->
<title>SparkStructuredStreamingRunner (Apache Beam 2.38.0-SNAPSHOT)</title>
<link rel="stylesheet" type="text/css" href="../../../../../../stylesheet.css" title="Style">
<script type="text/javascript" src="../../../../../../script.js"></script>
</head>
<body>
<script type="text/javascript"><!--
try {
if (location.href.indexOf('is-external=true') == -1) {
parent.document.title="SparkStructuredStreamingRunner (Apache Beam 2.38.0-SNAPSHOT)";
}
}
catch(err) {
}
//-->
var methods = {"i0":9,"i1":9,"i2":9,"i3":9,"i4":10};
var tabs = {65535:["t0","All Methods"],1:["t1","Static Methods"],2:["t2","Instance Methods"],8:["t4","Concrete Methods"]};
var altColor = "altColor";
var rowColor = "rowColor";
var tableTab = "tableTab";
var activeTableTab = "activeTableTab";
</script>
<noscript>
<div>JavaScript is disabled on your browser.</div>
</noscript>
<!-- ========= START OF TOP NAVBAR ======= -->
<div class="topNav"><a name="navbar.top">
<!-- -->
</a>
<div class="skipNav"><a href="#skip.navbar.top" title="Skip navigation links">Skip navigation links</a></div>
<a name="navbar.top.firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunnerRegistrar.html" title="class in org.apache.beam.runners.spark.structuredstreaming"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../../../index.html?org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" target="_top">Frames</a></li>
<li><a href="SparkStructuredStreamingRunner.html" target="_top">No&nbsp;Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_top">
<li><a href="../../../../../../allclasses-noframe.html">All&nbsp;Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_top");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li>Nested&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li>Constr&nbsp;|&nbsp;</li>
<li><a href="#method.summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li>Constr&nbsp;|&nbsp;</li>
<li><a href="#method.detail">Method</a></li>
</ul>
</div>
<a name="skip.navbar.top">
<!-- -->
</a></div>
<!-- ========= END OF TOP NAVBAR ========= -->
<!-- ======== START OF CLASS DATA ======== -->
<div class="header">
<div class="subTitle">org.apache.beam.runners.spark.structuredstreaming</div>
<h2 title="Class SparkStructuredStreamingRunner" class="title">Class SparkStructuredStreamingRunner</h2>
</div>
<div class="contentContainer">
<ul class="inheritance">
<li>java.lang.Object</li>
<li>
<ul class="inheritance">
<li><a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html" title="class in org.apache.beam.sdk">org.apache.beam.sdk.PipelineRunner</a>&lt;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineResult</a>&gt;</li>
<li>
<ul class="inheritance">
<li>org.apache.beam.runners.spark.structuredstreaming.SparkStructuredStreamingRunner</li>
</ul>
</li>
</ul>
</li>
</ul>
<div class="description">
<ul class="blockList">
<li class="blockList">
<hr>
<br>
<pre>public final class <span class="typeNameLabel">SparkStructuredStreamingRunner</span>
extends <a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html" title="class in org.apache.beam.sdk">PipelineRunner</a>&lt;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineResult</a>&gt;</pre>
<div class="block">SparkStructuredStreamingRunner is based on spark structured streaming framework and is no more
based on RDD/DStream API. See
https://spark.apache.org/docs/latest/structured-streaming-programming-guide.html It is still
experimental, its coverage of the Beam model is partial. The SparkStructuredStreamingRunner
translate operations defined on a pipeline to a representation executable by Spark, and then
submitting the job to Spark to be executed. If we wanted to run a Beam pipeline with the default
options of a single threaded spark instance in local mode, we would do the following:
<p><code>Pipeline p = [logic for pipeline creation] SparkStructuredStreamingPipelineResult
result = (SparkStructuredStreamingPipelineResult) p.run(); </code>
<p>To create a pipeline runner to run against a different spark cluster, with a custom master url
we would do the following:
<p><code>Pipeline p = [logic for pipeline creation] SparkStructuredStreamingPipelineOptions
options = SparkPipelineOptionsFactory.create(); options.setSparkMaster("spark://host:port");
SparkStructuredStreamingPipelineResult result = (SparkStructuredStreamingPipelineResult) p.run();
</code></div>
</li>
</ul>
</div>
<div class="summary">
<ul class="blockList">
<li class="blockList">
<!-- ========== METHOD SUMMARY =========== -->
<ul class="blockList">
<li class="blockList"><a name="method.summary">
<!-- -->
</a>
<h3>Method Summary</h3>
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation">
<caption><span id="t0" class="activeTableTab"><span>All Methods</span><span class="tabEnd">&nbsp;</span></span><span id="t1" class="tableTab"><span><a href="javascript:show(1);">Static Methods</a></span><span class="tabEnd">&nbsp;</span></span><span id="t2" class="tableTab"><span><a href="javascript:show(2);">Instance Methods</a></span><span class="tabEnd">&nbsp;</span></span><span id="t4" class="tableTab"><span><a href="javascript:show(8);">Concrete Methods</a></span><span class="tabEnd">&nbsp;</span></span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Method and Description</th>
</tr>
<tr id="i0" class="altColor">
<td class="colFirst"><code>static <a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a></code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html#create--">create</a></span>()</code>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with default options.</div>
</td>
</tr>
<tr id="i1" class="rowColor">
<td class="colFirst"><code>static <a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a></code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html#create-org.apache.beam.runners.spark.structuredstreaming.SparkStructuredStreamingPipelineOptions-">create</a></span>(<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineOptions.html" title="interface in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineOptions</a>&nbsp;options)</code>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with specified options.</div>
</td>
</tr>
<tr id="i2" class="altColor">
<td class="colFirst"><code>static <a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a></code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html#fromOptions-org.apache.beam.sdk.options.PipelineOptions-">fromOptions</a></span>(<a href="../../../../../../org/apache/beam/sdk/options/PipelineOptions.html" title="interface in org.apache.beam.sdk.options">PipelineOptions</a>&nbsp;options)</code>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with specified options.</div>
</td>
</tr>
<tr id="i3" class="rowColor">
<td class="colFirst"><code>static void</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html#initAccumulators-org.apache.beam.runners.spark.structuredstreaming.SparkStructuredStreamingPipelineOptions-org.apache.spark.api.java.JavaSparkContext-">initAccumulators</a></span>(<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineOptions.html" title="interface in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineOptions</a>&nbsp;opts,
org.apache.spark.api.java.JavaSparkContext&nbsp;jsc)</code>
<div class="block">Init Metrics/Aggregators accumulators.</div>
</td>
</tr>
<tr id="i4" class="altColor">
<td class="colFirst"><code><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineResult</a></code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html#run-org.apache.beam.sdk.Pipeline-">run</a></span>(<a href="../../../../../../org/apache/beam/sdk/Pipeline.html" title="class in org.apache.beam.sdk">Pipeline</a>&nbsp;pipeline)</code>
<div class="block">Processes the given <a href="../../../../../../org/apache/beam/sdk/Pipeline.html" title="class in org.apache.beam.sdk"><code>Pipeline</code></a>, potentially asynchronously, returning a runner-specific
type of result.</div>
</td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.org.apache.beam.sdk.PipelineRunner">
<!-- -->
</a>
<h3>Methods inherited from class&nbsp;org.apache.beam.sdk.<a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html" title="class in org.apache.beam.sdk">PipelineRunner</a></h3>
<code><a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html#run-org.apache.beam.sdk.transforms.PTransform-">run</a>, <a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html#run-org.apache.beam.sdk.transforms.PTransform-org.apache.beam.sdk.options.PipelineOptions-">run</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.java.lang.Object">
<!-- -->
</a>
<h3>Methods inherited from class&nbsp;java.lang.Object</h3>
<code>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</code></li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
<div class="details">
<ul class="blockList">
<li class="blockList">
<!-- ============ METHOD DETAIL ========== -->
<ul class="blockList">
<li class="blockList"><a name="method.detail">
<!-- -->
</a>
<h3>Method Detail</h3>
<a name="create--">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>create</h4>
<pre>public static&nbsp;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a>&nbsp;create()</pre>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with default options. In particular,
against a spark instance running in local mode.</div>
<dl>
<dt><span class="returnLabel">Returns:</span></dt>
<dd>A pipeline runner with default options.</dd>
</dl>
</li>
</ul>
<a name="create-org.apache.beam.runners.spark.structuredstreaming.SparkStructuredStreamingPipelineOptions-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>create</h4>
<pre>public static&nbsp;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a>&nbsp;create(<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineOptions.html" title="interface in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineOptions</a>&nbsp;options)</pre>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with specified options.</div>
<dl>
<dt><span class="paramLabel">Parameters:</span></dt>
<dd><code>options</code> - The SparkStructuredStreamingPipelineOptions to use when executing the job.</dd>
<dt><span class="returnLabel">Returns:</span></dt>
<dd>A pipeline runner that will execute with specified options.</dd>
</dl>
</li>
</ul>
<a name="fromOptions-org.apache.beam.sdk.options.PipelineOptions-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>fromOptions</h4>
<pre>public static&nbsp;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingRunner</a>&nbsp;fromOptions(<a href="../../../../../../org/apache/beam/sdk/options/PipelineOptions.html" title="interface in org.apache.beam.sdk.options">PipelineOptions</a>&nbsp;options)</pre>
<div class="block">Creates and returns a new SparkStructuredStreamingRunner with specified options.</div>
<dl>
<dt><span class="paramLabel">Parameters:</span></dt>
<dd><code>options</code> - The PipelineOptions to use when executing the job.</dd>
<dt><span class="returnLabel">Returns:</span></dt>
<dd>A pipeline runner that will execute with specified options.</dd>
</dl>
</li>
</ul>
<a name="run-org.apache.beam.sdk.Pipeline-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>run</h4>
<pre>public&nbsp;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineResult</a>&nbsp;run(<a href="../../../../../../org/apache/beam/sdk/Pipeline.html" title="class in org.apache.beam.sdk">Pipeline</a>&nbsp;pipeline)</pre>
<div class="block"><span class="descfrmTypeLabel">Description copied from class:&nbsp;<code><a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html#run-org.apache.beam.sdk.Pipeline-">PipelineRunner</a></code></span></div>
<div class="block">Processes the given <a href="../../../../../../org/apache/beam/sdk/Pipeline.html" title="class in org.apache.beam.sdk"><code>Pipeline</code></a>, potentially asynchronously, returning a runner-specific
type of result.</div>
<dl>
<dt><span class="overrideSpecifyLabel">Specified by:</span></dt>
<dd><code><a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html#run-org.apache.beam.sdk.Pipeline-">run</a></code>&nbsp;in class&nbsp;<code><a href="../../../../../../org/apache/beam/sdk/PipelineRunner.html" title="class in org.apache.beam.sdk">PipelineRunner</a>&lt;<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineResult</a>&gt;</code></dd>
</dl>
</li>
</ul>
<a name="initAccumulators-org.apache.beam.runners.spark.structuredstreaming.SparkStructuredStreamingPipelineOptions-org.apache.spark.api.java.JavaSparkContext-">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>initAccumulators</h4>
<pre>public static&nbsp;void&nbsp;initAccumulators(<a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineOptions.html" title="interface in org.apache.beam.runners.spark.structuredstreaming">SparkStructuredStreamingPipelineOptions</a>&nbsp;opts,
org.apache.spark.api.java.JavaSparkContext&nbsp;jsc)</pre>
<div class="block">Init Metrics/Aggregators accumulators. This method is idempotent.</div>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</div>
<!-- ========= END OF CLASS DATA ========= -->
<!-- ======= START OF BOTTOM NAVBAR ====== -->
<div class="bottomNav"><a name="navbar.bottom">
<!-- -->
</a>
<div class="skipNav"><a href="#skip.navbar.bottom" title="Skip navigation links">Skip navigation links</a></div>
<a name="navbar.bottom.firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingPipelineResult.html" title="class in org.apache.beam.runners.spark.structuredstreaming"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../../../org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunnerRegistrar.html" title="class in org.apache.beam.runners.spark.structuredstreaming"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../../../index.html?org/apache/beam/runners/spark/structuredstreaming/SparkStructuredStreamingRunner.html" target="_top">Frames</a></li>
<li><a href="SparkStructuredStreamingRunner.html" target="_top">No&nbsp;Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_bottom">
<li><a href="../../../../../../allclasses-noframe.html">All&nbsp;Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_bottom");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li>Nested&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li>Constr&nbsp;|&nbsp;</li>
<li><a href="#method.summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li>Constr&nbsp;|&nbsp;</li>
<li><a href="#method.detail">Method</a></li>
</ul>
</div>
<a name="skip.navbar.bottom">
<!-- -->
</a></div>
<!-- ======== END OF BOTTOM NAVBAR ======= -->
</body>
</html>