| <!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=x-ua-compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1"><title>Beam Quickstart for Java</title><meta name=description content="Apache Beam is an open source, unified model and set of language-specific SDKs for defining and executing data processing workflows, and also data ingestion and integration flows, supporting Enterprise Integration Patterns (EIPs) and Domain Specific Languages (DSLs). Dataflow pipelines simplify the mechanics of large-scale batch and streaming data processing and can run on a number of runtimes like Apache Flink, Apache Spark, and Google Cloud Dataflow (a cloud service). Beam also brings DSL in different languages, allowing users to easily implement their data integration processes."><link href="https://fonts.googleapis.com/css?family=Roboto:100,300,400,500,700" rel=stylesheet><link rel=preload href=/scss/main.min.408fddfe3e8a45f87a5a8c9a839d77db667c1c534e5e5cd0d957ffc3dd6c14cf.css as=style><link href=/scss/main.min.408fddfe3e8a45f87a5a8c9a839d77db667c1c534e5e5cd0d957ffc3dd6c14cf.css rel=stylesheet integrity><script src=https://code.jquery.com/jquery-2.2.4.min.js></script><style>.body__contained img{max-width:100%}</style><script type=text/javascript src=/js/bootstrap.min.2979f9a6e32fc42c3e7406339ee9fe76b31d1b52059776a02b4a7fa6a4fd280a.js defer></script> |
| <script type=text/javascript src=/js/language-switch-v2.min.121952b7980b920320ab229551857669209945e39b05ba2b433a565385ca44c6.js defer></script> |
| <script type=text/javascript src=/js/fix-menu.min.039174b67107465f2090a493f91e126f7aa797f29420f9edab8a54d9dd4b3d2d.js defer></script> |
| <script type=text/javascript src=/js/section-nav.min.1405fd5e70fab5f6c54037c269b1d137487d8f3d1b3009032525f6db3fbce991.js defer></script> |
| <script type=text/javascript src=/js/page-nav.min.af231204c9c52c5089d53a4c02739eacbb7f939e3be1c6ffcc212e0ac4dbf879.js defer></script> |
| <script type=text/javascript src=/js/expandable-list.min.75a4526624a3b8898fe7fb9e3428c205b581f8b38c7926922467aef17eac69f2.js defer></script> |
| <script type=text/javascript src=/js/copy-to-clipboard.min.364c06423d7e8993fc42bb4abc38c03195bc8386db26d18774ce775d08d5b18d.js defer></script> |
| <script type=text/javascript src=/js/calendar.min.336664054fa0f52b08bbd4e3c59b5cb6d63dcfb2b4d602839746516b0817446b.js defer></script> |
| <script type=text/javascript src=/js/fix-playground-nested-scroll.min.0283f1037cb1b9d5074c6eaf041292b524a8148a7cdb803d5ccd6d1fc4eb3253.js defer></script> |
| <script type=text/javascript src=/js/anchor-content-jump-fix.min.22d3240f81632e4c11179b9d2aaf37a40da9414333c43aa97344e8b21a7df0e4.js defer></script> |
| <link rel=alternate type=application/rss+xml title="Apache Beam" href=/feed.xml><link rel=canonical href=/get-started/quickstart/java/ data-proofer-ignore><link rel="shortcut icon" type=image/x-icon href=/images/favicon.ico><link rel=stylesheet href=https://use.fontawesome.com/releases/v5.4.1/css/all.css integrity=sha384-5sAR7xN1Nv6T6+dT2mhtzEpVJvfS3NScPQTrOxhwjIuvcA67KV2R5Jz6kr4abQsz crossorigin=anonymous><link rel=stylesheet href=https://unpkg.com/swiper@8/swiper-bundle.min.css><script async src=https://platform.twitter.com/widgets.js></script> |
| <script>(function(e,t,n,s,o,i,a){e.GoogleAnalyticsObject=o,e[o]=e[o]||function(){(e[o].q=e[o].q||[]).push(arguments)},e[o].l=1*new Date,i=t.createElement(n),a=t.getElementsByTagName(n)[0],i.async=1,i.src=s,a.parentNode.insertBefore(i,a)})(window,document,"script","//www.google-analytics.com/analytics.js","ga"),ga("create","UA-73650088-1","auto"),ga("send","pageview")</script><script>(function(e,t,n,s,o,i){e.hj=e.hj||function(){(e.hj.q=e.hj.q||[]).push(arguments)},e._hjSettings={hjid:2182187,hjsv:6},o=t.getElementsByTagName("head")[0],i=t.createElement("script"),i.async=1,i.src=n+e._hjSettings.hjid+s+e._hjSettings.hjsv,o.appendChild(i)})(window,document,"https://static.hotjar.com/c/hotjar-",".js?sv=")</script></head><body class=body data-spy=scroll data-target=.page-nav data-offset=0><nav class="navigation-bar-mobile header navbar navbar-fixed-top"><div class=navbar-header><a href=/ class=navbar-brand><img alt=Brand style=height:46px;width:43px src=/images/beam_logo_navbar_mobile.png></a> |
| <a class=navbar-link href=/get-started/>Get Started</a> |
| <a class=navbar-link href=/documentation/>Documentation</a> |
| <button type=button class="navbar-toggle menu-open" aria-expanded=false aria-controls=navbar onclick=openMenu()> |
| <span class=sr-only>Toggle navigation</span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span></button></div><div class="navbar-mask closed"></div><div id=navbar class="navbar-container closed"><button type=button class=navbar-toggle aria-expanded=false aria-controls=navbar id=closeMenu> |
| <span class=sr-only>Toggle navigation</span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span></button><ul class="nav navbar-nav"><li><div class=searchBar-mobile><script>(function(){var t,n="012923275103528129024:4emlchv9wzi",e=document.createElement("script");e.type="text/javascript",e.async=!0,e.src="https://cse.google.com/cse.js?cx="+n,t=document.getElementsByTagName("script")[0],t.parentNode.insertBefore(e,t)})()</script><gcse:search></gcse:search></div></li><li><a class=navbar-link href=/about>About</a></li><li><a class=navbar-link href=/get-started/>Get Started</a></li><li><span class=navbar-link>Documentation</span><ul><li><a href=/documentation/>General</a></li><li><a href=/documentation/sdks/java/>Languages</a></li><li><a href=/documentation/runners/capability-matrix/>Runners</a></li><li><a href=/documentation/io/connectors/>I/O Connectors</a></li></ul></li><li><a class=navbar-link href=/roadmap/>Roadmap</a></li><li><a class=navbar-link href=/community/>Community</a></li><li><a class=navbar-link href=/contribute/>Contribute</a></li><li><a class=navbar-link href=/blog/>Blog</a></li><li><a class=navbar-link href=/case-studies/>Case Studies</a></li></ul><ul class="nav navbar-nav navbar-right"><li><a href=https://github.com/apache/beam/edit/master/website/www/site/content/en/get-started/quickstart/java.md data-proofer-ignore><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M4.543 20h4l10.5-10.5c.53-.53.828-1.25.828-2s-.298-1.47-.828-2-1.25-.828-2-.828-1.47.298-2 .828L4.543 16v4zm9.5-13.5 4 4"/></svg></a></li><li class=dropdown><a href=# class=dropdown-toggle id=apache-dropdown data-toggle=dropdown role=button aria-haspopup=true aria-expanded=false><img src=https://www.apache.org/foundation/press/kit/feather_small.png alt="Apache Logo" style=height:20px> |
| Apache |
| <span class=arrow-icon><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="none" viewBox="0 0 20 20"><circle cx="10" cy="10" r="10" fill="#ff6d00"/><path stroke="#fff" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M8.535 5.28l4.573 4.818-4.573 4.403"/></svg></span></a><ul class="dropdown-menu dropdown-menu-right"><li><a target=_blank href=https://www.apache.org/>ASF Homepage</a></li><li><a target=_blank href=https://www.apache.org/licenses/>License</a></li><li><a target=_blank href=https://www.apache.org/security/>Security</a></li><li><a target=_blank href=https://www.apache.org/foundation/thanks.html>Thanks</a></li><li><a target=_blank href=https://www.apache.org/foundation/sponsorship.html>Sponsorship</a></li><li><a target=_blank href=https://www.apache.org/foundation/policies/conduct>Code of Conduct</a></li></ul></li></ul></div></nav><nav class=navigation-bar-desktop><a href=/ class=navbar-logo><img src=/images/beam_logo_navbar.png alt="Beam Logo"></a><div class=navbar-bar-left><div class=navbar-links><a class=navbar-link href=/about>About</a> |
| <a class=navbar-link href=/get-started/>Get Started</a><li class="dropdown navbar-dropdown navbar-dropdown-documentation"><a href=# class="dropdown-toggle navbar-link" role=button aria-haspopup=true aria-expanded=false>Documentation |
| <span><svg xmlns="http://www.w3.org/2000/svg" width="12" height="11" fill="none" viewBox="0 0 12 11"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M10.666 4.535 5.847 9.108 1.444 4.535"/></svg></span></a><ul class=dropdown-menu><li><a class=navbar-dropdown-menu-link href=/documentation/>General</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/sdks/java/>Languages</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/runners/capability-matrix/>Runners</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/io/connectors/>I/O Connectors</a></li></ul></li><a class=navbar-link href=/roadmap/>Roadmap</a> |
| <a class=navbar-link href=/community/>Community</a> |
| <a class=navbar-link href=/contribute/>Contribute</a> |
| <a class=navbar-link href=/blog/>Blog</a> |
| <a class=navbar-link href=/case-studies/>Case Studies</a></div><div id=iconsBar><a type=button onclick=showSearch()><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M10.191 17c3.866.0 7-3.134 7-7s-3.134-7-7-7-7 3.134-7 7 3.134 7 7 7zm11 4-6-6"/></svg></a><a target=_blank href=https://github.com/apache/beam/edit/master/website/www/site/content/en/get-started/quickstart/java.md data-proofer-ignore><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M4.543 20h4l10.5-10.5c.53-.53.828-1.25.828-2s-.298-1.47-.828-2-1.25-.828-2-.828-1.47.298-2 .828L4.543 16v4zm9.5-13.5 4 4"/></svg></a><li class="dropdown navbar-dropdown navbar-dropdown-apache"><a href=# class=dropdown-toggle role=button aria-haspopup=true aria-expanded=false><img src=https://www.apache.org/foundation/press/kit/feather_small.png alt="Apache Logo" style=height:20px> |
| Apache |
| <span class=arrow-icon><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="none" viewBox="0 0 20 20"><circle cx="10" cy="10" r="10" fill="#ff6d00"/><path stroke="#fff" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M8.535 5.28l4.573 4.818-4.573 4.403"/></svg></span></a><ul class=dropdown-menu><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/>ASF Homepage</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/licenses/>License</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/security/>Security</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/thanks.html>Thanks</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/sponsorship.html>Sponsorship</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/policies/conduct>Code of Conduct</a></li></ul></li></div><div class="searchBar disappear"><script>(function(){var t,n="012923275103528129024:4emlchv9wzi",e=document.createElement("script");e.type="text/javascript",e.async=!0,e.src="https://cse.google.com/cse.js?cx="+n,t=document.getElementsByTagName("script")[0],t.parentNode.insertBefore(e,t)})()</script><gcse:search></gcse:search> |
| <a type=button onclick=endSearch()><svg xmlns="http://www.w3.org/2000/svg" width="25" height="25" fill="none" viewBox="0 0 25 25"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M21.122 20.827 4.727 4.432M21.122 4.43 4.727 20.827"/></svg></a></div></div></nav><div class=header-push></div><div class="top-banners swiper"><div class=swiper-wrapper><div class=swiper-slide><a href=https://tour.beam.apache.org><img class=banner-img-desktop src=/images/banners/tour-of-beam/tour-of-beam-desktop.png alt="Start Tour of Beam"> |
| <img class=banner-img-mobile src=/images/banners/tour-of-beam/tour-of-beam-mobile.png alt="Start Tour of Beam"></a></div><div class=swiper-slide><a href=https://beam.apache.org/documentation/ml/overview/><img class=banner-img-desktop src=/images/banners/machine-learning/machine-learning-desktop.jpg alt="Machine Learning"> |
| <img class=banner-img-mobile src=/images/banners/machine-learning/machine-learning-mobile.jpg alt="Machine Learning"></a></div></div><div class=swiper-pagination></div><div class=swiper-button-prev></div><div class=swiper-button-next></div></div><script src=/js/swiper-bundle.min.min.e0e8f81b0b15728d35ff73c07f42ddbb17a108d6f23df4953cb3e60df7ade675.js></script> |
| <script src=/js/sliders/top-banners.min.afa7d0a19acf7a3b28ca369490b3d401a619562a2a4c9612577be2f66a4b9855.js></script> |
| <script>function showSearch(){addPlaceholder();var e,t=document.querySelector(".searchBar");t.classList.remove("disappear"),e=document.querySelector("#iconsBar"),e.classList.add("disappear")}function addPlaceholder(){$("input:text").attr("placeholder","What are you looking for?")}function endSearch(){var e,t=document.querySelector(".searchBar");t.classList.add("disappear"),e=document.querySelector("#iconsBar"),e.classList.remove("disappear")}function blockScroll(){$("body").toggleClass("fixedPosition")}function openMenu(){addPlaceholder(),blockScroll()}</script><div class="clearfix container-main-content"><div class="section-nav closed" data-offset-top=90 data-offset-bottom=500><span class="section-nav-back glyphicon glyphicon-menu-left"></span><nav><ul class=section-nav-list data-section-nav><li><span class=section-nav-list-main-title>Get started</span></li><li><a href=/get-started/beam-overview/>Beam Overview</a></li><li><a href=/get-started/an-interactive-overview-of-beam/>An Interactive Overview of Beam</a></li><li><span class=section-nav-list-title>Quickstarts</span><ul class=section-nav-list><li><a href=https://tour.beam.apache.org>Tour of Beam</a></li><li><a href=/get-started/try-apache-beam/>Try Apache Beam</a></li><li><a href=/get-started/try-beam-playground/>Try Beam Playground</a></li><li><a href=/get-started/quickstart/java/>Java quickstart</a></li><li><a href=/get-started/quickstart/python/>Python quickstart</a></li><li><a href=/get-started/quickstart/go/>Go quickstart</a></li><li><a href=/get-started/quickstart/typescript/>Typescript quickstart</a></li><li><a href=/get-started/from-spark/>Apache Spark</a></li><li><a href=/get-started/quickstart-java/>WordCount (Java)</a></li><li><a href=/get-started/quickstart-py/>WordCount (Python)</a></li><li><a href=/get-started/quickstart-go/>WordCount (Go)</a></li></ul></li><li><a href=/get-started/downloads>Install the SDK</a></li><li><span class=section-nav-list-title>Tutorials</span><ul class=section-nav-list><li><a href=/get-started/wordcount-example/>WordCount</a></li><li><a href=/get-started/mobile-gaming-example/>Mobile Gaming</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Learning resources</span><ul class=section-nav-list><li><a href=/get-started/resources/learning-resources/#getting-started>Getting Started</a></li><li><a href=/get-started/resources/learning-resources/#articles>Articles</a></li><li><a href=/get-started/resources/learning-resources/#videos>Videos</a></li><li><a href=/get-started/resources/learning-resources/#courses>Courses</a></li><li><a href=/get-started/resources/learning-resources/#books>Books</a></li><li><a href=/get-started/resources/learning-resources/#certifications>Certifications</a></li><li><a href=/get-started/resources/learning-resources/#interactive-labs>Interactive Labs</a></li><li><a href=/get-started/resources/learning-resources/#beam-katas>Beam Katas</a></li><li><a href=/get-started/resources/learning-resources/#code-examples>Code Examples</a></li><li><a href=/get-started/resources/learning-resources/#api-reference>API Reference</a></li><li><a href=/get-started/resources/learning-resources/#feedback-and-suggestions>Feedback and Suggestions</a></li><li><a href=/get-started/resources/learning-resources/#how-to-contribute>How to Contribute</a></li><li><a href=/get-started/resources/videos-and-podcasts>Videos and Podcasts</a></li></ul></li><li><a href=/security>Security</a></li></ul></nav></div><nav class="page-nav clearfix" data-offset-top=90 data-offset-bottom=500><nav id=TableOfContents><ul><li><a href=#set-up-your-development-environment>Set up your development environment</a></li><li><a href=#clone-the-github-repository>Clone the GitHub repository</a></li><li><a href=#run-the-quickstart>Run the quickstart</a></li><li><a href=#explore-the-code>Explore the code</a><ul><li><a href=#create-a-pipeline>Create a pipeline</a></li><li><a href=#create-an-initial-pcollection>Create an initial PCollection</a></li><li><a href=#apply-a-transform-to-the-pcollection>Apply a transform to the PCollection</a></li><li><a href=#run-the-pipeline>Run the pipeline</a></li></ul></li><li><a href=#next-steps>Next Steps</a></li></ul></nav></nav><div class="body__contained body__section-nav"><h1 id=apache-beam-java-sdk-quickstart>Apache Beam Java SDK quickstart</h1><p>This quickstart shows you how to run an |
| <a href=https://github.com/apache/beam-starter-java>example pipeline</a> written with |
| the <a href=/documentation/sdks/java>Apache Beam Java SDK</a>, using the |
| <a href=/documentation/runners/direct/>Direct Runner</a>. The Direct Runner executes |
| pipelines locally on your machine.</p><p>If you’re interested in contributing to the Apache Beam Java codebase, see the |
| <a href=/contribute>Contribution Guide</a>.</p><p>On this page:</p><nav id=TableOfContents><ul><li><a href=#set-up-your-development-environment>Set up your development environment</a></li><li><a href=#clone-the-github-repository>Clone the GitHub repository</a></li><li><a href=#run-the-quickstart>Run the quickstart</a></li><li><a href=#explore-the-code>Explore the code</a><ul><li><a href=#create-a-pipeline>Create a pipeline</a></li><li><a href=#create-an-initial-pcollection>Create an initial PCollection</a></li><li><a href=#apply-a-transform-to-the-pcollection>Apply a transform to the PCollection</a></li><li><a href=#run-the-pipeline>Run the pipeline</a></li></ul></li><li><a href=#next-steps>Next Steps</a></li></ul></nav><h2 id=set-up-your-development-environment>Set up your development environment</h2><p>Use <a href=https://sdkman.io/><code>sdkman</code></a> to install the Java Development Kit (JDK).</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code># Install sdkman |
| curl -s "https://get.sdkman.io" | bash |
| |
| # Install Java 17 |
| sdk install java 17.0.5-tem</code></pre></div></div><p>You can use either <a href=https://gradle.org/>Gradle</a> or |
| <a href=https://maven.apache.org/>Apache Maven</a> to run this quickstart:</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code># Install Gradle |
| sdk install gradle |
| |
| # Install Maven |
| sdk install maven</code></pre></div></div><h2 id=clone-the-github-repository>Clone the GitHub repository</h2><p>Clone or download the |
| <a href=https://github.com/apache/beam-starter-java>apache/beam-starter-java</a> GitHub |
| repository and change into the <code>beam-starter-java</code> directory.</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code>git clone https://github.com/apache/beam-starter-java.git |
| cd beam-starter-java</code></pre></div></div><h2 id=run-the-quickstart>Run the quickstart</h2><p><strong>Gradle</strong>: To run the quickstart with Gradle, run the following command:</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code>gradle run --args='--inputText=Greetings'</code></pre></div></div><p><strong>Maven</strong>: To run the quickstart with Maven, run the following command:</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code>mvn compile exec:java -Dexec.args=--inputText='Greetings'</code></pre></div></div><p>The output is similar to the following:</p><div class=snippet><div class="notebook-skip code-snippet without_switcher"><a class=copy type=button data-bs-toggle=tooltip data-bs-placement=bottom title="Copy to clipboard"><img src=/images/copy-icon.svg></a><pre tabindex=0><code>Hello |
| World! |
| Greetings</code></pre></div></div><p>The lines might appear in a different order.</p><h2 id=explore-the-code>Explore the code</h2><p>The main code file for this quickstart is <strong>App.java</strong> |
| (<a href=https://github.com/apache/beam-starter-java/blob/main/src/main/java/com/example/App.java>GitHub</a>). |
| The code performs the following steps:</p><ol><li>Create a Beam pipeline.</li><li>Create an initial <code>PCollection</code>.</li><li>Apply a transform to the <code>PCollection</code>.</li><li>Run the pipeline, using the Direct Runner.</li></ol><h3 id=create-a-pipeline>Create a pipeline</h3><p>The code first creates a <code>Pipeline</code> object. The <code>Pipeline</code> object builds up the |
| graph of transformations to be executed.</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-java data-lang=java><span class=line><span class=cl><span class=n>var</span> <span class=n>options</span> <span class=o>=</span> <span class=n>PipelineOptionsFactory</span><span class=o>.</span><span class=na>fromArgs</span><span class=o>(</span><span class=n>args</span><span class=o>).</span><span class=na>withValidation</span><span class=o>().</span><span class=na>as</span><span class=o>(</span><span class=n>Options</span><span class=o>.</span><span class=na>class</span><span class=o>);</span> |
| </span></span><span class=line><span class=cl><span class=n>var</span> <span class=n>pipeline</span> <span class=o>=</span> <span class=n>Pipeline</span><span class=o>.</span><span class=na>create</span><span class=o>(</span><span class=n>options</span><span class=o>);</span> |
| </span></span></code></pre></div><p>The <code>PipelineOptions</code> object lets you set various options for the pipeline. The |
| <code>fromArgs</code> method shown in this example parses command-line arguments, which |
| lets you set pipeline options through the command line.</p><h3 id=create-an-initial-pcollection>Create an initial PCollection</h3><p>The <code>PCollection</code> abstraction represents a potentially distributed, |
| multi-element data set. A Beam pipeline needs a source of data to populate an |
| initial <code>PCollection</code>. The source can be bounded (with a known, fixed size) or |
| unbounded (with unlimited size).</p><p>This example uses the |
| <a href=https://beam.apache.org/releases/javadoc/current/org/apache/beam/sdk/transforms/Create.html><code>Create.of</code></a> |
| method to create a <code>PCollection</code> from an in-memory array of strings. The |
| resulting <code>PCollection</code> contains the strings “Hello”, “World!”, and a |
| user-provided input string.</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-java data-lang=java><span class=line><span class=cl><span class=k>return</span> <span class=n>pipeline</span> |
| </span></span><span class=line><span class=cl> <span class=o>.</span><span class=na>apply</span><span class=o>(</span><span class=s>"Create elements"</span><span class=o>,</span> <span class=n>Create</span><span class=o>.</span><span class=na>of</span><span class=o>(</span><span class=n>Arrays</span><span class=o>.</span><span class=na>asList</span><span class=o>(</span><span class=s>"Hello"</span><span class=o>,</span> <span class=s>"World!"</span><span class=o>,</span> <span class=n>inputText</span><span class=o>)))</span> |
| </span></span></code></pre></div><h3 id=apply-a-transform-to-the-pcollection>Apply a transform to the PCollection</h3><p>Transforms can change, filter, group, analyze, or otherwise process the |
| elements in a <code>PCollection</code>. This example uses the |
| <a href=https://beam.apache.org/releases/javadoc/current/org/apache/beam/sdk/transforms/MapElements.html><code>MapElements</code></a> |
| transform, which maps the elements of a collection into a new collection:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-java data-lang=java><span class=line><span class=cl><span class=o>.</span><span class=na>apply</span><span class=o>(</span><span class=s>"Print elements"</span><span class=o>,</span> |
| </span></span><span class=line><span class=cl> <span class=n>MapElements</span><span class=o>.</span><span class=na>into</span><span class=o>(</span><span class=n>TypeDescriptors</span><span class=o>.</span><span class=na>strings</span><span class=o>()).</span><span class=na>via</span><span class=o>(</span><span class=n>x</span> <span class=o>-></span> <span class=o>{</span> |
| </span></span><span class=line><span class=cl> <span class=n>System</span><span class=o>.</span><span class=na>out</span><span class=o>.</span><span class=na>println</span><span class=o>(</span><span class=n>x</span><span class=o>);</span> |
| </span></span><span class=line><span class=cl> <span class=k>return</span> <span class=n>x</span><span class=o>;</span> |
| </span></span><span class=line><span class=cl> <span class=o>}));</span> |
| </span></span></code></pre></div><p>where</p><ul><li><code>into</code> specifies the data type for the elements in the output collection.</li><li><code>via</code> defines a mapping function that is called on each element of the input |
| collection to create the output collection.</li></ul><p>In this example, the mapping function is a lambda that just returns the |
| original value. It also prints the value to <code>System.out</code> as a side effect.</p><h3 id=run-the-pipeline>Run the pipeline</h3><p>The code shown in the previous sections defines a pipeline, but does not |
| process any data yet. To process data, you run the pipeline:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-java data-lang=java><span class=line><span class=cl><span class=n>pipeline</span><span class=o>.</span><span class=na>run</span><span class=o>().</span><span class=na>waitUntilFinish</span><span class=o>();</span> |
| </span></span></code></pre></div><p>A Beam <a href=/documentation/basics/#runner>runner</a> runs a |
| Beam pipeline on a specific platform. This example uses the |
| <a href=https://beam.apache.org/releases/javadoc/2.3.0/org/apache/beam/runners/direct/DirectRunner.html>Direct Runner</a>, |
| which is the default runner if you don’t specify one. The Direct Runner runs |
| the pipeline locally on your machine. It is meant for testing and development, |
| rather than being optimized for efficiency. For more information, see |
| <a href=/documentation/runners/direct/>Using the Direct Runner</a>.</p><p>For production workloads, you typically use a distributed runner that runs the |
| pipeline on a big data processing system such as Apache Flink, Apache Spark, or |
| Google Cloud Dataflow. These systems support massively parallel processing.</p><h2 id=next-steps>Next Steps</h2><ul><li>Learn more about the <a href=/documentation/sdks/java/>Beam SDK for Java</a> |
| and look through the |
| <a href=https://beam.apache.org/releases/javadoc>Java SDK API reference</a>.</li><li>Take a self-paced tour through our |
| <a href=/documentation/resources/learning-resources>Learning Resources</a>.</li><li>Dive in to some of our favorite |
| <a href=/get-started/resources/videos-and-podcasts>Videos and Podcasts</a>.</li><li>Join the Beam <a href=/community/contact-us>users@</a> mailing list.</li></ul><p>Please don’t hesitate to <a href=/community/contact-us>reach out</a> if you encounter any |
| issues!</p><div class=feedback><p class=update>Last updated on 2024/05/03</p><h3>Have you found everything you were looking for?</h3><p class=description>Was it all useful and clear? Is there anything that you would like to change? Let us know!</p><button class=load-button><a href="https://docs.google.com/forms/d/e/1FAIpQLSfID7abne3GE6k6RdJIyZhPz2Gef7UkpggUEhTIDjjplHuxSA/viewform?usp=header_link" target=_blank>SEND FEEDBACK</a></button></div></div></div><footer class=footer><div class=footer__contained><div class=footer__cols><div class="footer__cols__col footer__cols__col__logos"><div class=footer__cols__col__logo><img src=/images/beam_logo_circle.svg class=footer__logo alt="Beam logo"></div><div class=footer__cols__col__logo><img src=/images/apache_logo_circle.svg class=footer__logo alt="Apache logo"></div></div><div class=footer-wrapper><div class=wrapper-grid><div class=footer__cols__col><div class=footer__cols__col__title>Start</div><div class=footer__cols__col__link><a href=/get-started/beam-overview/>Overview</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-java/>Quickstart (Java)</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-py/>Quickstart (Python)</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-go/>Quickstart (Go)</a></div><div class=footer__cols__col__link><a href=/get-started/downloads/>Downloads</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Docs</div><div class=footer__cols__col__link><a href=/documentation/programming-guide/>Concepts</a></div><div class=footer__cols__col__link><a href=/documentation/pipelines/design-your-pipeline/>Pipelines</a></div><div class=footer__cols__col__link><a href=/documentation/runners/capability-matrix/>Runners</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Community</div><div class=footer__cols__col__link><a href=/contribute/>Contribute</a></div><div class=footer__cols__col__link><a href=https://projects.apache.org/committee.html?beam target=_blank>Team<img src=/images/external-link-icon.png width=14 height=14 alt="External link."></a></div><div class=footer__cols__col__link><a href=/community/presentation-materials/>Media</a></div><div class=footer__cols__col__link><a href=/community/in-person/>Events/Meetups</a></div><div class=footer__cols__col__link><a href=/community/contact-us/>Contact Us</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Resources</div><div class=footer__cols__col__link><a href=/blog/>Blog</a></div><div class=footer__cols__col__link><a href=https://github.com/apache/beam>GitHub</a></div></div></div><div class=footer__bottom>© |
| <a href=https://www.apache.org>The Apache Software Foundation</a> |
| | <a href=/privacy_policy>Privacy Policy</a> |
| | <a href=/feed.xml>RSS Feed</a><br><br>Apache Beam, Apache, Beam, the Beam logo, and the Apache feather logo are either registered trademarks or trademarks of The Apache Software Foundation. All other products or name brands are trademarks of their respective holders, including The Apache Software Foundation.</div></div><div class="footer__cols__col footer__cols__col__logos"><div class=footer__cols__col--group><div class=footer__cols__col__logo><a href=https://github.com/apache/beam><img src=/images/logos/social-icons/github-logo-150.png class=footer__logo alt="Github logo"></a></div><div class=footer__cols__col__logo><a href=https://www.linkedin.com/company/apache-beam/><img src=/images/logos/social-icons/linkedin-logo-150.png class=footer__logo alt="Linkedin logo"></a></div></div><div class=footer__cols__col--group><div class=footer__cols__col__logo><a href=https://twitter.com/apachebeam><img src=/images/logos/social-icons/twitter-logo-150.png class=footer__logo alt="Twitter logo"></a></div><div class=footer__cols__col__logo><a href=https://www.youtube.com/channel/UChNnb_YO_7B0HlW6FhAXZZQ><img src=/images/logos/social-icons/youtube-logo-150.png class=footer__logo alt="Youtube logo"></a></div></div></div></div></div></footer></body></html> |
