Google Git
Sign in
apache / flink-web / a229405453080b7f70a9d04fae5e6d22129d20bc / . / content / flink-applications.html
blob: a3e7d60e10efce9f8e18bf6cb185d0384fdf8bde [file] [log] [blame]
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1">
<!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags -->
<title>Apache Flink: What is Apache Flink? — Applications</title>
<link rel="shortcut icon" href="/favicon.ico" type="image/x-icon">
<link rel="icon" href="/favicon.ico" type="image/x-icon">
<!-- Bootstrap -->
<link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
<link rel="stylesheet" href="/css/flink.css">
<link rel="stylesheet" href="/css/syntax.css">
<!-- Blog RSS feed -->
<link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Apache Flink Blog: RSS feed" />
<!-- jQuery (necessary for Bootstrap's JavaScript plugins) -->
<!-- We need to load Jquery in the header for custom google analytics event tracking-->
<script src="/js/jquery.min.js"></script>
<!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
<!--[if lt IE 9]>
<script src="https://oss.maxcdn.com/html5shiv/3.7.2/html5shiv.min.js"></script>
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
<![endif]-->
</head>
<body>
<!-- Main content. -->
<div class="container">
<div class="row">
<div id="sidebar" class="col-sm-3">
<!-- Top navbar. -->
<nav class="navbar navbar-default">
<!-- The logo. -->
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<div class="navbar-logo">
<a href="/">
<img alt="Apache Flink" src="/img/flink-header-logo.svg" width="147px" height="73px">
</a>
</div>
</div><!-- /.navbar-header -->
<!-- The navigation links. -->
<div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1">
<ul class="nav navbar-nav navbar-main">
<!-- First menu section explains visitors what Flink is -->
<!-- What is Stream Processing? -->
<!--
<li><a href="/streamprocessing1.html">What is Stream Processing?</a></li>
-->
<!-- What is Flink? -->
<li><a href="/flink-architecture.html">What is Apache Flink?</a></li>
<ul class="nav navbar-nav navbar-subnav">
<li >
<a href="/flink-architecture.html">Architecture</a>
</li>
<li class="active">
<a href="/flink-applications.html">Applications</a>
</li>
<li >
<a href="/flink-operations.html">Operations</a>
</li>
</ul>
<!-- What is Stateful Functions? -->
<li><a href="/stateful-functions.html">What is Stateful Functions?</a></li>
<!-- Use cases -->
<li><a href="/usecases.html">Use Cases</a></li>
<!-- Powered by -->
<li><a href="/poweredby.html">Powered By</a></li>
&nbsp;
<!-- Second menu section aims to support Flink users -->
<!-- Downloads -->
<li><a href="/downloads.html">Downloads</a></li>
<!-- Getting Started -->
<li class="dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#">Getting Started<span class="caret"></span></a>
<ul class="dropdown-menu">
<li><a href="https://ci.apache.org/projects/flink/flink-docs-release-1.11/getting-started/index.html" target="_blank">With Flink <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-release-2.1/getting-started/project-setup.html" target="_blank">With Flink Stateful Functions <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li><a href="/training.html">Training Course</a></li>
</ul>
</li>
<!-- Documentation -->
<li class="dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#">Documentation<span class="caret"></span></a>
<ul class="dropdown-menu">
<li><a href="https://ci.apache.org/projects/flink/flink-docs-release-1.11" target="_blank">Flink 1.11 (Latest stable release) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li><a href="https://ci.apache.org/projects/flink/flink-docs-master" target="_blank">Flink Master (Latest Snapshot) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-release-2.1" target="_blank">Flink Stateful Functions 2.1 (Latest stable release) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-master" target="_blank">Flink Stateful Functions Master (Latest Snapshot) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
</ul>
</li>
<!-- getting help -->
<li><a href="/gettinghelp.html">Getting Help</a></li>
<!-- Blog -->
<li><a href="/blog/"><b>Flink Blog</b></a></li>
<!-- Flink-packages -->
<li>
<a href="https://flink-packages.org" target="_blank">flink-packages.org <small><span class="glyphicon glyphicon-new-window"></span></small></a>
</li>
&nbsp;
<!-- Third menu section aim to support community and contributors -->
<!-- Community -->
<li><a href="/community.html">Community &amp; Project Info</a></li>
<!-- Roadmap -->
<li><a href="/roadmap.html">Roadmap</a></li>
<!-- Contribute -->
<li><a href="/contributing/how-to-contribute.html">How to Contribute</a></li>
<!-- GitHub -->
<li>
<a href="https://github.com/apache/flink" target="_blank">Flink on GitHub <small><span class="glyphicon glyphicon-new-window"></span></small></a>
</li>
&nbsp;
<!-- Language Switcher -->
<li>
<a href="/zh/flink-applications.html">中文版</a>
</li>
</ul>
<ul class="nav navbar-nav navbar-bottom">
<hr />
<!-- Twitter -->
<li><a href="https://twitter.com/apacheflink" target="_blank">@ApacheFlink <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<!-- Visualizer -->
<li class=" hidden-md hidden-sm"><a href="/visualizer/" target="_blank">Plan Visualizer <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<hr />
<li><a href="https://apache.org" target="_blank">Apache Software Foundation <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
<li>
<style>
.smalllinks:link {
display: inline-block !important; background: none; padding-top: 0px; padding-bottom: 0px; padding-right: 0px; min-width: 75px;
}
</style>
<a class="smalllinks" href="https://www.apache.org/licenses/" target="_blank">License</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
<a class="smalllinks" href="https://www.apache.org/security/" target="_blank">Security</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
<a class="smalllinks" href="https://www.apache.org/foundation/sponsorship.html" target="_blank">Donate</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
<a class="smalllinks" href="https://www.apache.org/foundation/thanks.html" target="_blank">Thanks</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
</li>
</ul>
</div><!-- /.navbar-collapse -->
</nav>
</div>
<div class="col-sm-9">
<div class="row-fluid">
<div class="col-sm-12">
<h1>What is Apache Flink? — Applications</h1>
<hr />
<p>Apache Flink is a framework for stateful computations over unbounded and bounded data streams. Flink provides multiple APIs at different levels of abstraction and offers dedicated libraries for common use cases.</p>
<p>Here, we present Flink’s easy-to-use and expressive APIs and libraries.</p>
<h2 id="building-blocks-for-streaming-applications">Building Blocks for Streaming Applications</h2>
<p>The types of applications that can be built with and executed by a stream processing framework are defined by how well the framework controls <em>streams</em>, <em>state</em>, and <em>time</em>. In the following, we describe these building blocks for stream processing applications and explain Flink’s approaches to handle them.</p>
<h3 id="streams">Streams</h3>
<p>Obviously, streams are a fundamental aspect of stream processing. However, streams can have different characteristics that affect how a stream can and should be processed. Flink is a versatile processing framework that can handle any kind of stream.</p>
<ul>
<li><strong>Bounded</strong> and <strong>unbounded</strong> streams: Streams can be unbounded or bounded, i.e., fixed-sized data sets. Flink has sophisticated features to process unbounded streams, but also dedicated operators to efficiently process bounded streams.</li>
<li><strong>Real-time</strong> and <strong>recorded</strong> streams: All data are generated as streams. There are two ways to process the data. Processing it in real-time as it is generated or persisting the stream to a storage system, e.g., a file system or object store, and processed it later. Flink applications can process recorded or real-time streams.</li>
</ul>
<h3 id="state">State</h3>
<p>Every non-trivial streaming application is stateful, i.e., only applications that apply transformations on individual events do not require state. Any application that runs basic business logic needs to remember events or intermediate results to access them at a later point in time, for example when the next event is received or after a specific time duration.</p>
<div class="row front-graphic">
<img src="/img/function-state.png" width="350px" />
</div>
<p>Application state is a first-class citizen in Flink. You can see that by looking at all the features that Flink provides in the context of state handling.</p>
<ul>
<li><strong>Multiple State Primitives</strong>: Flink provides state primitives for different data structures, such as atomic values, lists, or maps. Developers can choose the state primitive that is most efficient based on the access pattern of the function.</li>
<li><strong>Pluggable State Backends</strong>: Application state is managed in and checkpointed by a pluggable state backend. Flink features different state backends that store state in memory or in <a href="https://rocksdb.org/">RocksDB</a>, an efficient embedded on-disk data store. Custom state backends can be plugged in as well.</li>
<li><strong>Exactly-once state consistency</strong>: Flink’s checkpointing and recovery algorithms guarantee the consistency of application state in case of a failure. Hence, failures are transparently handled and do not affect the correctness of an application.</li>
<li><strong>Very Large State</strong>: Flink is able to maintain application state of several terabytes in size due to its asynchronous and incremental checkpoint algorithm.</li>
<li><strong>Scalable Applications</strong>: Flink supports scaling of stateful applications by redistributing the state to more or fewer workers.</li>
</ul>
<h3 id="time">Time</h3>
<p>Time is another important ingredient of streaming applications. Most event streams have inherent time semantics because each event is produced at a specific point in time. Moreover, many common stream computations are based on time, such as windows aggregations, sessionization, pattern detection, and time-based joins. An important aspect of stream processing is how an application measures time, i.e., the difference of event-time and processing-time.</p>
<p>Flink provides a rich set of time-related features.</p>
<ul>
<li><strong>Event-time Mode</strong>: Applications that process streams with event-time semantics compute results based on timestamps of the events. Thereby, event-time processing allows for accurate and consistent results regardless whether recorded or real-time events are processed.</li>
<li><strong>Watermark Support</strong>: Flink employs watermarks to reason about time in event-time applications. Watermarks are also a flexible mechanism to trade-off the latency and completeness of results.</li>
<li><strong>Late Data Handling</strong>: When processing streams in event-time mode with watermarks, it can happen that a computation has been completed before all associated events have arrived. Such events are called late events. Flink features multiple options to handle late events, such as rerouting them via side outputs and updating previously completed results.</li>
<li><strong>Processing-time Mode</strong>: In addition to its event-time mode, Flink also supports processing-time semantics which performs computations as triggered by the wall-clock time of the processing machine. The processing-time mode can be suitable for certain applications with strict low-latency requirements that can tolerate approximate results.</li>
</ul>
<h2 id="layered-apis">Layered APIs</h2>
<p>Flink provides three layered APIs. Each API offers a different trade-off between conciseness and expressiveness and targets different use cases.</p>
<div class="row front-graphic">
<img src="/img/api-stack.png" width="500px" />
</div>
<p>We briefly present each API, discuss its applications, and show a code example.</p>
<h3 id="the-processfunctions">The ProcessFunctions</h3>
<p><a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/stream/operators/process_function.html">ProcessFunctions</a> are the most expressive function interfaces that Flink offers. Flink provides ProcessFunctions to process individual events from one or two input streams or events that were grouped in a window. ProcessFunctions provide fine-grained control over time and state. A ProcessFunction can arbitrarily modify its state and register timers that will trigger a callback function in the future. Hence, ProcessFunctions can implement complex per-event business logic as required for many <a href="/usecases.html#eventDrivenApps">stateful event-driven applications</a>.</p>
<p>The following example shows a <code>KeyedProcessFunction</code> that operates on a <code>KeyedStream</code> and matches <code>START</code> and <code>END</code> events. When a <code>START</code> event is received, the function remembers its timestamp in state and registers a timer in four hours. If an <code>END</code> event is received before the timer fires, the function computes the duration between <code>END</code> and <code>START</code> event, clears the state, and returns the value. Otherwise, the timer just fires and clears the state.</p>
<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="cm">/**</span>
<span class="cm"> * Matches keyed START and END events and computes the difference between </span>
<span class="cm"> * both elements&#39; timestamps. The first String field is the key attribute, </span>
<span class="cm"> * the second String attribute marks START and END events.</span>
<span class="cm"> */</span>
<span class="kd">public</span> <span class="kd">static</span> <span class="kd">class</span> <span class="nc">StartEndDuration</span>
<span class="kd">extends</span> <span class="n">KeyedProcessFunction</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">String</span><span class="o">&gt;,</span> <span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;&gt;</span> <span class="o">{</span>
<span class="kd">private</span> <span class="n">ValueState</span><span class="o">&lt;</span><span class="n">Long</span><span class="o">&gt;</span> <span class="n">startTime</span><span class="o">;</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="kt">void</span> <span class="nf">open</span><span class="o">(</span><span class="n">Configuration</span> <span class="n">conf</span><span class="o">)</span> <span class="o">{</span>
<span class="c1">// obtain state handle</span>
<span class="n">startTime</span> <span class="o">=</span> <span class="n">getRuntimeContext</span><span class="o">()</span>
<span class="o">.</span><span class="na">getState</span><span class="o">(</span><span class="k">new</span> <span class="n">ValueStateDescriptor</span><span class="o">&lt;</span><span class="n">Long</span><span class="o">&gt;(</span><span class="s">&quot;startTime&quot;</span><span class="o">,</span> <span class="n">Long</span><span class="o">.</span><span class="na">class</span><span class="o">));</span>
<span class="o">}</span>
<span class="cm">/** Called for each processed event. */</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="kt">void</span> <span class="nf">processElement</span><span class="o">(</span>
<span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">String</span><span class="o">&gt;</span> <span class="n">in</span><span class="o">,</span>
<span class="n">Context</span> <span class="n">ctx</span><span class="o">,</span>
<span class="n">Collector</span><span class="o">&lt;</span><span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;&gt;</span> <span class="n">out</span><span class="o">)</span> <span class="kd">throws</span> <span class="n">Exception</span> <span class="o">{</span>
<span class="k">switch</span> <span class="o">(</span><span class="n">in</span><span class="o">.</span><span class="na">f1</span><span class="o">)</span> <span class="o">{</span>
<span class="k">case</span> <span class="s">&quot;START&quot;</span><span class="o">:</span>
<span class="c1">// set the start time if we receive a start event.</span>
<span class="n">startTime</span><span class="o">.</span><span class="na">update</span><span class="o">(</span><span class="n">ctx</span><span class="o">.</span><span class="na">timestamp</span><span class="o">());</span>
<span class="c1">// register a timer in four hours from the start event.</span>
<span class="n">ctx</span><span class="o">.</span><span class="na">timerService</span><span class="o">()</span>
<span class="o">.</span><span class="na">registerEventTimeTimer</span><span class="o">(</span><span class="n">ctx</span><span class="o">.</span><span class="na">timestamp</span><span class="o">()</span> <span class="o">+</span> <span class="mi">4</span> <span class="o">*</span> <span class="mi">60</span> <span class="o">*</span> <span class="mi">60</span> <span class="o">*</span> <span class="mi">1000</span><span class="o">);</span>
<span class="k">break</span><span class="o">;</span>
<span class="k">case</span> <span class="s">&quot;END&quot;</span><span class="o">:</span>
<span class="c1">// emit the duration between start and end event</span>
<span class="n">Long</span> <span class="n">sTime</span> <span class="o">=</span> <span class="n">startTime</span><span class="o">.</span><span class="na">value</span><span class="o">();</span>
<span class="k">if</span> <span class="o">(</span><span class="n">sTime</span> <span class="o">!=</span> <span class="kc">null</span><span class="o">)</span> <span class="o">{</span>
<span class="n">out</span><span class="o">.</span><span class="na">collect</span><span class="o">(</span><span class="n">Tuple2</span><span class="o">.</span><span class="na">of</span><span class="o">(</span><span class="n">in</span><span class="o">.</span><span class="na">f0</span><span class="o">,</span> <span class="n">ctx</span><span class="o">.</span><span class="na">timestamp</span><span class="o">()</span> <span class="o">-</span> <span class="n">sTime</span><span class="o">));</span>
<span class="c1">// clear the state</span>
<span class="n">startTime</span><span class="o">.</span><span class="na">clear</span><span class="o">();</span>
<span class="o">}</span>
<span class="k">default</span><span class="o">:</span>
<span class="c1">// do nothing</span>
<span class="o">}</span>
<span class="o">}</span>
<span class="cm">/** Called when a timer fires. */</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="kt">void</span> <span class="nf">onTimer</span><span class="o">(</span>
<span class="kt">long</span> <span class="n">timestamp</span><span class="o">,</span>
<span class="n">OnTimerContext</span> <span class="n">ctx</span><span class="o">,</span>
<span class="n">Collector</span><span class="o">&lt;</span><span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;&gt;</span> <span class="n">out</span><span class="o">)</span> <span class="o">{</span>
<span class="c1">// Timeout interval exceeded. Cleaning up the state.</span>
<span class="n">startTime</span><span class="o">.</span><span class="na">clear</span><span class="o">();</span>
<span class="o">}</span>
<span class="o">}</span></code></pre></figure>
<p>The example illustrates the expressive power of the <code>KeyedProcessFunction</code> but also highlights that it is a rather verbose interface.</p>
<h3 id="the-datastream-api">The DataStream API</h3>
<p>The <a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/datastream_api.html">DataStream API</a> provides primitives for many common stream processing operations, such as windowing, record-at-a-time transformations, and enriching events by querying an external data store. The DataStream API is available for Java and Scala and is based on functions, such as <code>map()</code>, <code>reduce()</code>, and <code>aggregate()</code>. Functions can be defined by extending interfaces or as Java or Scala lambda functions.</p>
<p>The following example shows how to sessionize a clickstream and count the number of clicks per session.</p>
<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// a stream of website clicks</span>
<span class="n">DataStream</span><span class="o">&lt;</span><span class="n">Click</span><span class="o">&gt;</span> <span class="n">clicks</span> <span class="o">=</span> <span class="o">...</span>
<span class="n">DataStream</span><span class="o">&lt;</span><span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;&gt;</span> <span class="n">result</span> <span class="o">=</span> <span class="n">clicks</span>
<span class="c1">// project clicks to userId and add a 1 for counting</span>
<span class="o">.</span><span class="na">map</span><span class="o">(</span>
<span class="c1">// define function by implementing the MapFunction interface.</span>
<span class="k">new</span> <span class="n">MapFunction</span><span class="o">&lt;</span><span class="n">Click</span><span class="o">,</span> <span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;&gt;()</span> <span class="o">{</span>
<span class="nd">@Override</span>
<span class="kd">public</span> <span class="n">Tuple2</span><span class="o">&lt;</span><span class="n">String</span><span class="o">,</span> <span class="n">Long</span><span class="o">&gt;</span> <span class="nf">map</span><span class="o">(</span><span class="n">Click</span> <span class="n">click</span><span class="o">)</span> <span class="o">{</span>
<span class="k">return</span> <span class="n">Tuple2</span><span class="o">.</span><span class="na">of</span><span class="o">(</span><span class="n">click</span><span class="o">.</span><span class="na">userId</span><span class="o">,</span> <span class="mi">1L</span><span class="o">);</span>
<span class="o">}</span>
<span class="o">})</span>
<span class="c1">// key by userId (field 0)</span>
<span class="o">.</span><span class="na">keyBy</span><span class="o">(</span><span class="mi">0</span><span class="o">)</span>
<span class="c1">// define session window with 30 minute gap</span>
<span class="o">.</span><span class="na">window</span><span class="o">(</span><span class="n">EventTimeSessionWindows</span><span class="o">.</span><span class="na">withGap</span><span class="o">(</span><span class="n">Time</span><span class="o">.</span><span class="na">minutes</span><span class="o">(</span><span class="mi">30L</span><span class="o">)))</span>
<span class="c1">// count clicks per session. Define function as lambda function.</span>
<span class="o">.</span><span class="na">reduce</span><span class="o">((</span><span class="n">a</span><span class="o">,</span> <span class="n">b</span><span class="o">)</span> <span class="o">-&gt;</span> <span class="n">Tuple2</span><span class="o">.</span><span class="na">of</span><span class="o">(</span><span class="n">a</span><span class="o">.</span><span class="na">f0</span><span class="o">,</span> <span class="n">a</span><span class="o">.</span><span class="na">f1</span> <span class="o">+</span> <span class="n">b</span><span class="o">.</span><span class="na">f1</span><span class="o">));</span></code></pre></figure>
<h3 id="sql-amp-table-api">SQL &amp; Table API</h3>
<p>Flink features two relational APIs, the <a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/table/index.html">Table API and SQL</a>. Both APIs are unified APIs for batch and stream processing, i.e., queries are executed with the same semantics on unbounded, real-time streams or bounded, recorded streams and produce the same results. The Table API and SQL leverage <a href="https://calcite.apache.org">Apache Calcite</a> for parsing, validation, and query optimization. They can be seamlessly integrated with the DataStream and DataSet APIs and support user-defined scalar, aggregate, and table-valued functions.</p>
<p>Flink’s relational APIs are designed to ease the definition of <a href="/usecases.html#analytics">data analytics</a>, <a href="/usecases.html#pipelines">data pipelining, and ETL applications</a>.</p>
<p>The following example shows the SQL query to sessionize a clickstream and count the number of clicks per session. This is the same use case as in the example of the DataStream API.</p>
<div class="highlight"><pre><code class="language-sql"><span class="k">SELECT</span> <span class="n">userId</span><span class="p">,</span> <span class="k">COUNT</span><span class="p">(</span><span class="o">*</span><span class="p">)</span>
<span class="k">FROM</span> <span class="n">clicks</span>
<span class="k">GROUP</span> <span class="k">BY</span> <span class="k">SESSION</span><span class="p">(</span><span class="n">clicktime</span><span class="p">,</span> <span class="nb">INTERVAL</span> <span class="s1">&#39;30&#39;</span> <span class="k">MINUTE</span><span class="p">),</span> <span class="n">userId</span></code></pre></div>
<h2 id="libraries">Libraries</h2>
<p>Flink features several libraries for common data processing use cases. The libraries are typically embedded in an API and not fully self-contained. Hence, they can benefit from all features of the API and be integrated with other libraries.</p>
<ul>
<li>
<p><strong><a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/libs/cep.html">Complex Event Processing (CEP)</a></strong>: Pattern detection is a very common use case for event stream processing. Flink’s CEP library provides an API to specify patterns of events (think of regular expressions or state machines). The CEP library is integrated with Flink’s DataStream API, such that patterns are evaluated on DataStreams. Applications for the CEP library include network intrusion detection, business process monitoring, and fraud detection.</p>
</li>
<li>
<p><strong><a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/batch/index.html">DataSet API</a></strong>: The DataSet API is Flink’s core API for batch processing applications. The primitives of the DataSet API include <em>map</em>, <em>reduce</em>, <em>(outer) join</em>, <em>co-group</em>, and <em>iterate</em>. All operations are backed by algorithms and data structures that operate on serialized data in memory and spill to disk if the data size exceed the memory budget. The data processing algorithms of Flink’s DataSet API are inspired by traditional database operators, such as hybrid hash-join or external merge-sort.</p>
</li>
<li>
<p><strong><a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/libs/gelly/index.html">Gelly</a></strong>: Gelly is a library for scalable graph processing and analysis. Gelly is implemented on top of and integrated with the DataSet API. Hence, it benefits from its scalable and robust operators. Gelly features <a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/libs/gelly/library_methods.html">built-in algorithms</a>, such as label propagation, triangle enumeration, and page rank, but provides also a <a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/libs/gelly/graph_api.html">Graph API</a> that eases the implementation of custom graph algorithms.</p>
</li>
</ul>
<hr />
<div class="row">
<div class="col-sm-12" style="background-color: #f8f8f8;">
<h2>
<a href="/flink-architecture.html">Architecture</a> &nbsp;
<span class="glyphicon glyphicon-chevron-right"></span> &nbsp;
Applications &nbsp;
<span class="glyphicon glyphicon-chevron-right"></span> &nbsp;
<a href="/flink-operations.html">Operations</a>
</h2>
</div>
</div>
<hr />
</div>
</div>
</div>
</div>
<hr />
<div class="row">
<div class="footer text-center col-sm-12">
<p>Copyright © 2014-2019 <a href="http://apache.org">The Apache Software Foundation</a>. All Rights Reserved.</p>
<p>Apache Flink, Flink®, Apache®, the squirrel logo, and the Apache feather logo are either registered trademarks or trademarks of The Apache Software Foundation.</p>
<p><a href="/privacy-policy.html">Privacy Policy</a> &middot; <a href="/blog/feed.xml">RSS feed</a></p>
</div>
</div>
</div><!-- /.container -->
<!-- Include all compiled plugins (below), or include individual files as needed -->
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery.matchHeight/0.7.0/jquery.matchHeight-min.js"></script>
<script src="/js/codetabs.js"></script>
<script src="/js/stickysidebar.js"></script>
<!-- Google Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','//www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-52545728-1', 'auto');
ga('send', 'pageview');
</script>
</body>
</html>