| <!doctype html> |
| <html class="docs-version-0.5.0" lang="en" dir="ltr"> |
| <head> |
| <meta charset="UTF-8"> |
| <meta name="viewport" content="width=device-width,initial-scale=1"> |
| <meta name="generator" content="Docusaurus v2.0.0-beta.14"> |
| <link rel="alternate" type="application/rss+xml" href="/blog/rss.xml" title="Apache Hudi: User-Facing Analytics RSS Feed"> |
| <link rel="alternate" type="application/atom+xml" href="/blog/atom.xml" title="Apache Hudi: User-Facing Analytics Atom Feed"> |
| <link rel="alternate" type="application/json" href="/blog/feed.json" title="Apache Hudi: User-Facing Analytics JSON Feed"> |
| <link rel="search" type="application/opensearchdescription+xml" title="Apache Hudi" href="/opensearch.xml"> |
| <link rel="alternate" type="application/rss+xml" href="/videos/rss.xml" title="Apache Hudi RSS Feed"> |
| <link rel="alternate" type="application/atom+xml" href="/videos/atom.xml" title="Apache Hudi Atom Feed"> |
| <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Comfortaa|Ubuntu|Roboto|Source+Code+Pro"> |
| <link rel="stylesheet" href="https://at-ui.github.io/feather-font/css/iconfont.css"><title data-react-helmet="true">Querying Hudi Datasets | Apache Hudi</title><meta data-react-helmet="true" name="twitter:card" content="summary_large_image"><meta data-react-helmet="true" property="og:url" content="https://hudi.apache.org/docs/0.5.0/querying_data"><meta data-react-helmet="true" name="docsearch:language" content="en"><meta data-react-helmet="true" name="docsearch:version" content="0.5.0"><meta data-react-helmet="true" name="docsearch:docusaurus_tag" content="docs-default-0.5.0"><meta data-react-helmet="true" property="og:title" content="Querying Hudi Datasets | Apache Hudi"><meta data-react-helmet="true" name="description" content="Conceptually, Hudi stores data physically once on DFS, while providing 3 logical views on top, as explained before."><meta data-react-helmet="true" property="og:description" content="Conceptually, Hudi stores data physically once on DFS, while providing 3 logical views on top, as explained before."><meta data-react-helmet="true" name="keywords" content="hudi,hive,spark,sql,presto"><link data-react-helmet="true" rel="icon" href="/assets/images/favicon.ico"><link data-react-helmet="true" rel="canonical" href="https://hudi.apache.org/docs/0.5.0/querying_data"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/docs/0.5.0/querying_data" hreflang="en"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/cn/docs/0.5.0/querying_data" hreflang="cn"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/docs/0.5.0/querying_data" hreflang="x-default"><link data-react-helmet="true" rel="preconnect" href="https://BH4D9OD16A-dsn.algolia.net" crossorigin="anonymous"><link rel="stylesheet" href="/assets/css/styles.ea681a30.css"> |
| <link rel="preload" href="/assets/js/runtime~main.2cab5691.js" as="script"> |
| <link rel="preload" href="/assets/js/main.bd020950.js" as="script"> |
| </head> |
| <body> |
| <script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){var t=null;try{t=localStorage.getItem("theme")}catch(t){}return t}();t(null!==e?e:"light")}(),document.documentElement.setAttribute("data-announcement-bar-initially-dismissed",function(){try{return"true"===localStorage.getItem("docusaurus.announcement.dismiss")}catch(t){}return!1}())</script><div id="__docusaurus"> |
| <div><a href="#" class="skipToContent_OuoZ">Skip to main content</a></div><div class="announcementBar_axC9" role="banner"><div class="announcementBarPlaceholder_xYHE"></div><div class="announcementBarContent_6uhP">⭐️ If you like Apache Hudi, give it a star on <a target="_blank" rel="noopener noreferrer" href="https://github.com/apache/hudi">GitHub</a>! ⭐</div><button type="button" class="clean-btn close announcementBarClose_A3A1" aria-label="Close"><svg viewBox="0 0 15 15" width="14" height="14"><g stroke="currentColor" stroke-width="3.1"><path d="M.75.75l13.5 13.5M14.25.75L.75 14.25"></path></g></svg></button></div><nav class="navbar navbar--fixed-top navbarWrapper_UIa0"><div class="navbar__inner"><img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=8f594acf-9b77-44fb-9475-3e82ead1910c" width="0" height="0" alt=""><img referrerpolicy="no-referrer-when-downgrade" src="https://analytics.apache.org/matomo.php?idsite=47&rec=1" width="0" height="0" alt=""><div class="navbar__items"><button aria-label="Navigation bar toggle" class="navbar__toggle clean-btn" type="button" tabindex="0"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo navbarLogo_Bz6n"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--dark_uzRr"></div></a><a class="navbar__item navbar__link" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">Docs</div></a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Learn<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/talks"><div class="labelWrapperDropdown_Mqbj">Talks</div></a></li><li><a class="dropdown__link" href="/videos"><div class="labelWrapperDropdown_Mqbj">Video Guides</div></a></li><li><a class="dropdown__link" href="/docs/faq"><div class="labelWrapperDropdown_Mqbj">FAQ</div></a></li><li><a class="dropdown__link" href="/tech-specs"><div class="labelWrapperDropdown_Mqbj">Tech Specs</div></a></li><li><a class="dropdown__link" href="/tech-specs-1point0"><div class="labelWrapperDropdown_Mqbj">Tech Specs 1.0</div></a></li><li><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank" rel="noopener noreferrer" class="dropdown__link"><span class="externalLink_AE3f">Technical Wiki<svg width="20" height="20" viewBox="0 0 26 26" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M16.965 8.745 9.01 16.7M10.561 8.758l6.403-.013-.013 6.403" stroke="#0DB1F9" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path><rect x="4.5" y="4.5" width="17" height="17" rx="2.5" stroke="#0DB1F9"></rect></svg></span></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Contribute<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/contribute/how-to-contribute"><div class="labelWrapperDropdown_Mqbj">How to Contribute</div></a></li><li><a class="dropdown__link" href="/contribute/developer-setup"><div class="labelWrapperDropdown_Mqbj">Developer Setup</div></a></li><li><a class="dropdown__link" href="/contribute/rfc-process"><div class="labelWrapperDropdown_Mqbj">RFC Process</div></a></li><li><a class="dropdown__link" href="/contribute/report-security-issues"><div class="labelWrapperDropdown_Mqbj">Report Security Issues</div></a></li><li><a href="https://issues.apache.org/jira/projects/HUDI/summary" target="_blank" rel="noopener noreferrer" class="dropdown__link"><span class="externalLink_AE3f">Report Issues<svg width="20" height="20" viewBox="0 0 26 26" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M16.965 8.745 9.01 16.7M10.561 8.758l6.403-.013-.013 6.403" stroke="#0DB1F9" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path><rect x="4.5" y="4.5" width="17" height="17" rx="2.5" stroke="#0DB1F9"></rect></svg></span></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj">Community<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/community/get-involved"><div class="labelWrapperDropdown_Mqbj">Get Involved</div></a></li><li><a class="dropdown__link" href="/community/syncs"><div class="labelWrapperDropdown_Mqbj">Community Syncs</div></a></li><li><a class="dropdown__link" href="/community/office_hours"><div class="labelWrapperDropdown_Mqbj">Office Hours</div></a></li><li><a class="dropdown__link" href="/community/team"><div class="labelWrapperDropdown_Mqbj">Team</div></a></li></ul></div><a class="navbar__item navbar__link" href="/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a><a class="navbar__item navbar__link" href="/powered-by"><div class="labelWrapperDropdown_Mqbj">Who's Using</div></a><a class="navbar__item navbar__link" href="/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a><a class="navbar__item navbar__link" href="/releases/download"><div class="labelWrapperDropdown_Mqbj">Download</div></a></div><div class="navbar__items navbar__items--right"><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a class="navbar__link downloadLinkDropdownHide_aDP3" href="/docs/0.5.0/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.5.0<svg width="10" height="6" viewBox="0 0 10 6" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M8.5 1.25 5 4.75l-3.5-3.5" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/docs/next/querying_data"><div class="labelWrapperDropdown_Mqbj">Current</div></a></li><li><a class="dropdown__link" href="/docs/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.1</div></a></li><li><a class="dropdown__link" href="/docs/0.14.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.0</div></a></li><li><a class="dropdown__link" href="/docs/0.13.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.1</div></a></li><li><a class="dropdown__link" href="/docs/0.13.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.0</div></a></li><li><a class="dropdown__link" href="/docs/0.12.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.3</div></a></li><li><a class="dropdown__link" href="/docs/0.12.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.2</div></a></li><li><a class="dropdown__link" href="/docs/0.12.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.1</div></a></li><li><a class="dropdown__link" href="/docs/0.12.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.0</div></a></li><li><a class="dropdown__link" href="/docs/0.11.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.1</div></a></li><li><a class="dropdown__link" href="/docs/0.11.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.0</div></a></li><li><a class="dropdown__link" href="/docs/0.10.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.1</div></a></li><li><a class="dropdown__link" href="/docs/0.10.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.0</div></a></li><li><a class="dropdown__link" href="/docs/0.9.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.9.0</div></a></li><li><a class="dropdown__link" href="/docs/0.8.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.8.0</div></a></li><li><a class="dropdown__link" href="/docs/0.7.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.7.0</div></a></li><li><a class="dropdown__link" href="/docs/0.6.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.6.0</div></a></li><li><a class="dropdown__link" href="/docs/0.5.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.3</div></a></li><li><a class="dropdown__link" href="/docs/0.5.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.2</div></a></li><li><a class="dropdown__link" href="/docs/0.5.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.1</div></a></li><li><a aria-current="page" class="dropdown__link dropdown__link--active" href="/docs/0.5.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.0</div></a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" class="navbar__link downloadLinkDropdownHide_aDP3"><div class="labelWrapperDropdown_Mqbj"><span><svg viewBox="0 0 20 20" width="20" height="20" aria-hidden="true" class="iconLanguage_zID8"><path fill="currentColor" d="M19.753 10.909c-.624-1.707-2.366-2.726-4.661-2.726-.09 0-.176.002-.262.006l-.016-2.063 3.525-.607c.115-.019.133-.119.109-.231-.023-.111-.167-.883-.188-.976-.027-.131-.102-.127-.207-.109-.104.018-3.25.461-3.25.461l-.013-2.078c-.001-.125-.069-.158-.194-.156l-1.025.016c-.105.002-.164.049-.162.148l.033 2.307s-3.061.527-3.144.543c-.084.014-.17.053-.151.143.019.09.19 1.094.208 1.172.018.08.072.129.188.107l2.924-.504.035 2.018c-1.077.281-1.801.824-2.256 1.303-.768.807-1.207 1.887-1.207 2.963 0 1.586.971 2.529 2.328 2.695 3.162.387 5.119-3.06 5.769-4.715 1.097 1.506.256 4.354-2.094 5.98-.043.029-.098.129-.033.207l.619.756c.08.096.206.059.256.023 2.51-1.73 3.661-4.515 2.869-6.683zm-7.386 3.188c-.966-.121-.944-.914-.944-1.453 0-.773.327-1.58.876-2.156a3.21 3.21 0 011.229-.799l.082 4.277a2.773 2.773 0 01-1.243.131zm2.427-.553l.046-4.109c.084-.004.166-.01.252-.01.773 0 1.494.145 1.885.361.391.217-1.023 2.713-2.183 3.758zm-8.95-7.668a.196.196 0 00-.196-.145h-1.95a.194.194 0 00-.194.144L.008 16.916c-.017.051-.011.076.062.076h1.733c.075 0 .099-.023.114-.072l1.008-3.318h3.496l1.008 3.318c.016.049.039.072.113.072h1.734c.072 0 .078-.025.062-.076-.014-.05-3.083-9.741-3.494-11.04zm-2.618 6.318l1.447-5.25 1.447 5.25H3.226z"></path></svg><span>English</span></span><svg width="14" height="14" viewBox="0 0 14 14" fill="none" xmlns="http://www.w3.org/2000/svg"><g clip-path="url(#a)"><path d="M14 6.457a6.842 6.842 0 0 0-7-6.02 6.843 6.843 0 0 0-7 6.02v1.085a6.843 6.843 0 0 0 7 6.02 6.843 6.843 0 0 0 7-6.02V6.457Zm-1.094 0h-2.625a9.92 9.92 0 0 0-.376-2.222 6.65 6.65 0 0 0 1.531-.875 5.25 5.25 0 0 1 1.444 3.097h.026Zm-8.032 0a8.479 8.479 0 0 1 .324-1.872 7.376 7.376 0 0 0 3.63 0c.175.61.284 1.239.325 1.872h-4.28Zm4.305 1.085a8.391 8.391 0 0 1-.324 1.873 7.464 7.464 0 0 0-3.658 0 8.479 8.479 0 0 1-.323-1.873h4.305Zm.35-4.375A10.342 10.342 0 0 0 8.75 1.75c.627.194 1.218.49 1.75.875a5.748 5.748 0 0 1-.998.577l.027-.035ZM7.254 1.54A8.75 8.75 0 0 1 8.46 3.552c-.48.11-.97.165-1.461.167-.492-.001-.982-.057-1.461-.167.308-.722.715-1.4 1.207-2.012h.508ZM4.498 3.202a5.748 5.748 0 0 1-.998-.577 6.029 6.029 0 0 1 1.75-.875c-.294.46-.546.947-.753 1.452Zm-1.873.15c.47.358.984.652 1.531.874A9.625 9.625 0 0 0 3.78 6.45H1.155a5.25 5.25 0 0 1 1.47-3.098ZM1.12 7.541h2.625c.038.753.164 1.5.376 2.223a6.649 6.649 0 0 0-1.531.875 5.25 5.25 0 0 1-1.47-3.098Zm3.377 3.255c.207.506.459.992.753 1.453a6.03 6.03 0 0 1-1.75-.875c.312-.226.646-.419.997-.578Zm2.25 1.663a8.594 8.594 0 0 1-1.208-2.013 6.501 6.501 0 0 1 2.922 0 8.54 8.54 0 0 1-1.207 2.013h-.508Zm2.755-1.663c.367.156.716.35 1.042.578a6.338 6.338 0 0 1-1.75.875c.275-.464.512-.95.708-1.453Zm1.873-.148a6.647 6.647 0 0 0-1.531-.875 9.45 9.45 0 0 0 .376-2.223h2.625a5.25 5.25 0 0 1-1.47 3.098Z" fill="#1C1E21"></path></g><defs><clipPath id="a"><path fill="#fff" d="M0 0h14v14H0z"></path></clipPath></defs></svg></div></a><ul class="dropdown__menu"><li><a href="/docs/0.5.0/querying_data" target="_self" rel="noopener noreferrer" class="dropdown__link dropdown__link--active"><div class="labelWrapperDropdown_Mqbj">English</div></a></li><li><a href="/cn/docs/0.5.0/querying_data" target="_self" rel="noopener noreferrer" class="dropdown__link"><div class="labelWrapperDropdown_Mqbj">Chinese</div></a></li></ul></div><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-github-link" aria-label="GitHub repository"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-twitter-link" aria-label="Hudi Twitter Handle"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-slack-link" aria-label="Hudi Slack Channel"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-youtube-link" aria-label="Hudi YouTube Channel"><div class="labelWrapperDropdown_Mqbj"></div></a><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link header-linkedin-link" aria-label="Hudi Linkedin Page"><div class="labelWrapperDropdown_Mqbj"></div></a><div class="searchBox_fBfG"><div role="button" class="searchButton_g9-U" aria-label="Search"><span class="searchText_RI6l">Search</span><svg width="14" height="14" viewBox="0 0 14 14" fill="none" xmlns="http://www.w3.org/2000/svg"><circle cx="6.864" cy="6.864" r="5.243" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></circle><path d="m10.51 10.783 2.056 2.05" stroke="#1C1E21" stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"></path></svg></div></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div><div class="navbar-sidebar"><div class="navbar-sidebar__brand"><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--dark_uzRr"></div></a><button type="button" class="clean-btn navbar-sidebar__close"><svg viewBox="0 0 15 15" width="21" height="21"><g stroke="var(--ifm-color-emphasis-600)" stroke-width="1.2"><path d="M.75.75l13.5 13.5M14.25.75L.75 14.25"></path></g></svg></button></div><div class="navbar-sidebar__items"><div class="navbar-sidebar__item menu"><ul class="menu__list"><li class="menu__list-item"><a class="menu__link" href="/docs/overview"><div class="labelWrapperDropdown_Mqbj">Docs</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Learn</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Contribute</div></a></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Community</div></a></li><li class="menu__list-item"><a class="menu__link" href="/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a></li><li class="menu__list-item"><a class="menu__link" href="/powered-by"><div class="labelWrapperDropdown_Mqbj">Who's Using</div></a></li><li class="menu__list-item"><a class="menu__link" href="/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a></li><li class="menu__list-item"><a class="menu__link" href="/releases/download"><div class="labelWrapperDropdown_Mqbj">Download</div></a></li><li class="menu__list-item"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj">Versions</div></a><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="menu__list-item"><a class="menu__link" href="/docs/next/querying_data"><div class="labelWrapperDropdown_Mqbj">Current</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.1</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.14.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.13.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.1</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.13.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.12.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.3</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.12.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.2</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.12.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.1</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.12.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.11.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.1</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.11.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.10.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.1</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.10.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.9.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.9.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.8.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.8.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.7.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.7.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.6.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.6.0</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.5.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.3</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.5.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.2</div></a></li><li class="menu__list-item"><a class="menu__link" href="/docs/0.5.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.1</div></a></li><li class="menu__list-item"><a aria-current="page" class="menu__link menu__link--active" href="/docs/0.5.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.0</div></a></li></ul></li><li class="menu__list-item menu__list-item--collapsed"><a role="button" class="menu__link menu__link--sublist"><div class="labelWrapperDropdown_Mqbj"><span><svg viewBox="0 0 20 20" width="20" height="20" aria-hidden="true" class="iconLanguage_zID8"><path fill="currentColor" d="M19.753 10.909c-.624-1.707-2.366-2.726-4.661-2.726-.09 0-.176.002-.262.006l-.016-2.063 3.525-.607c.115-.019.133-.119.109-.231-.023-.111-.167-.883-.188-.976-.027-.131-.102-.127-.207-.109-.104.018-3.25.461-3.25.461l-.013-2.078c-.001-.125-.069-.158-.194-.156l-1.025.016c-.105.002-.164.049-.162.148l.033 2.307s-3.061.527-3.144.543c-.084.014-.17.053-.151.143.019.09.19 1.094.208 1.172.018.08.072.129.188.107l2.924-.504.035 2.018c-1.077.281-1.801.824-2.256 1.303-.768.807-1.207 1.887-1.207 2.963 0 1.586.971 2.529 2.328 2.695 3.162.387 5.119-3.06 5.769-4.715 1.097 1.506.256 4.354-2.094 5.98-.043.029-.098.129-.033.207l.619.756c.08.096.206.059.256.023 2.51-1.73 3.661-4.515 2.869-6.683zm-7.386 3.188c-.966-.121-.944-.914-.944-1.453 0-.773.327-1.58.876-2.156a3.21 3.21 0 011.229-.799l.082 4.277a2.773 2.773 0 01-1.243.131zm2.427-.553l.046-4.109c.084-.004.166-.01.252-.01.773 0 1.494.145 1.885.361.391.217-1.023 2.713-2.183 3.758zm-8.95-7.668a.196.196 0 00-.196-.145h-1.95a.194.194 0 00-.194.144L.008 16.916c-.017.051-.011.076.062.076h1.733c.075 0 .099-.023.114-.072l1.008-3.318h3.496l1.008 3.318c.016.049.039.072.113.072h1.734c.072 0 .078-.025.062-.076-.014-.05-3.083-9.741-3.494-11.04zm-2.618 6.318l1.447-5.25 1.447 5.25H3.226z"></path></svg><span>Languages</span></span></div></a></li><li class="menu__list-item"><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="menu__link header-github-link" aria-label="GitHub repository"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="menu__link header-twitter-link" aria-label="Hudi Twitter Handle"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="menu__link header-slack-link" aria-label="Hudi Slack Channel"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="menu__link header-youtube-link" aria-label="Hudi YouTube Channel"><div class="labelWrapperDropdown_Mqbj"></div></a></li><li class="menu__list-item"><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="menu__link header-linkedin-link" aria-label="Hudi Linkedin Page"><div class="labelWrapperDropdown_Mqbj"></div></a></li></ul></div><div class="navbar-sidebar__item menu"><button type="button" class="clean-btn navbar-sidebar__back">← Back to main menu</button></div></div></div></nav><div class="main-wrapper docs-wrapper docs-doc-page"><div class="docPage_GMj9"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_i9tI" type="button"></button><aside class="docSidebarContainer_k0Pq"><div class="sidebar_a3j0"><nav class="menu thin-scrollbar menu_cyFh menuWithAnnouncementBar_+O1J"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/0.5.0/quick-start-guide">Quick-Start Guide</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/0.5.0/use_cases">Use Cases</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/0.5.0/writing_data">Writing Hudi Datasets</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" href="/docs/0.5.0/querying_data">Querying Hudi Datasets</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/0.5.0/configurations">Configurations</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/0.5.0/performance">Performance</a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist hasHref_TwRn" href="/docs/0.5.0/s3_hoodie">Storage Configurations</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist hasHref_TwRn" href="/docs/0.5.0/docker_demo">Resources</a></div></li></ul></nav></div></aside><main class="docMainContainer_Q970"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_zHA2"><div class="theme-doc-version-banner alert alert--warning margin-bottom--md" role="alert"><div>This is documentation for <!-- -->Apache Hudi<!-- --> <b>0.5.0</b>, which is no longer actively maintained.</div><div class="margin-top--md">For up-to-date documentation, see the <b><a href="/docs/querying_data">latest version</a></b> (<!-- -->0.14.1<!-- -->).</div></div><div class="docItemContainer_oiyr"><article><span class="theme-doc-version-badge badge badge--secondary">Version: <!-- -->0.5.0</span><div class="tocCollapsible_aw-L theme-doc-toc-mobile tocMobile_Tx6Y"><button type="button" class="clean-btn tocCollapsibleButton_zr6a">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Querying Hudi Datasets</h1></header><p>Conceptually, Hudi stores data physically once on DFS, while providing 3 logical views on top, as explained <a href="/docs/concepts#views">before</a>. |
| Once the dataset is synced to the Hive metastore, it provides external Hive tables backed by Hudi's custom inputformats. Once the proper hudi |
| bundle has been provided, the dataset can be queried by popular query engines like Hive, Spark and Presto.</p><p>Specifically, there are two Hive tables named off <a href="/docs/configurations#TABLE_NAME_OPT_KEY">table name</a> passed during write. |
| For e.g, if <code>table name = hudi_tbl</code>, then we get </p><ul><li><code>hudi_tbl</code> realizes the read optimized view of the dataset backed by <code>HoodieParquetInputFormat</code>, exposing purely columnar data.</li><li><code>hudi_tbl_rt</code> realizes the real time view of the dataset backed by <code>HoodieParquetRealtimeInputFormat</code>, exposing merged view of base and log data.</li></ul><p>As discussed in the concepts section, the one key primitive needed for <a href="https://www.oreilly.com/ideas/ubers-case-for-incremental-processing-on-hadoop" target="_blank" rel="noopener noreferrer">incrementally processing</a>, |
| is <code>incremental pulls</code> (to obtain a change stream/log from a dataset). Hudi datasets can be pulled incrementally, which means you can get ALL and ONLY the updated & new rows |
| since a specified instant time. This, together with upserts, are particularly useful for building data pipelines where 1 or more source Hudi tables are incrementally pulled (streams/facts), |
| joined with other tables (datasets/dimensions), to <a href="/docs/writing_data">write out deltas</a> to a target Hudi dataset. Incremental view is realized by querying one of the tables above, |
| with special configurations that indicates to query planning that only incremental data needs to be fetched out of the dataset. </p><p>In sections, below we will discuss in detail how to access all the 3 views on each query engine.</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="hive">Hive<a class="hash-link" href="#hive" title="Direct link to heading"></a></h2><p>In order for Hive to recognize Hudi datasets and query correctly, the HiveServer2 needs to be provided with the <code>hudi-hadoop-mr-bundle-x.y.z-SNAPSHOT.jar</code> |
| in its <a href="https://www.cloudera.com/documentation/enterprise/5-6-x/topics/cm_mc_hive_udf#concept_nc3_mms_lr" target="_blank" rel="noopener noreferrer">aux jars path</a>. This will ensure the input format |
| classes with its dependencies are available for query planning & execution. </p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="read-optimized-table">Read Optimized table<a class="hash-link" href="#read-optimized-table" title="Direct link to heading"></a></h3><p>In addition to setup above, for beeline cli access, the <code>hive.input.format</code> variable needs to be set to the fully qualified path name of the |
| inputformat <code>org.apache.hudi.hadoop.HoodieParquetInputFormat</code>. For Tez, additionally the <code>hive.tez.input.format</code> needs to be set |
| to <code>org.apache.hadoop.hive.ql.io.HiveInputFormat</code></p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="real-time-table">Real time table<a class="hash-link" href="#real-time-table" title="Direct link to heading"></a></h3><p>In addition to installing the hive bundle jar on the HiveServer2, it needs to be put on the hadoop/hive installation across the cluster, so that |
| queries can pick up the custom RecordReader as well.</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="incremental-pulling">Incremental Pulling<a class="hash-link" href="#incremental-pulling" title="Direct link to heading"></a></h3><p><code>HiveIncrementalPuller</code> allows incrementally extracting changes from large fact/dimension tables via HiveQL, combining the benefits of Hive (reliably process complex SQL queries) and |
| incremental primitives (speed up query by pulling tables incrementally instead of scanning fully). The tool uses Hive JDBC to run the hive query and saves its results in a temp table. |
| that can later be upserted. Upsert utility (<code>HoodieDeltaStreamer</code>) has all the state it needs from the directory structure to know what should be the commit time on the target table. |
| e.g: <code>/app/incremental-hql/intermediate/{source_table_name}_temp/{last_commit_included}</code>.The Delta Hive table registered will be of the form <code>{tmpdb}.{source_table}_{last_commit_included}</code>.</p><p>The following are the configuration options for HiveIncrementalPuller</p><table><thead><tr><th><strong>Config</strong></th><th><strong>Description</strong></th><th><strong>Default</strong></th></tr></thead><tbody><tr><td>hiveUrl</td><td>Hive Server 2 URL to connect to</td><td></td></tr><tr><td>hiveUser</td><td>Hive Server 2 Username</td><td></td></tr><tr><td>hivePass</td><td>Hive Server 2 Password</td><td></td></tr><tr><td>queue</td><td>YARN Queue name</td><td></td></tr><tr><td>tmp</td><td>Directory where the temporary delta data is stored in DFS. The directory structure will follow conventions. Please see the below section.</td><td></td></tr><tr><td>extractSQLFile</td><td>The SQL to execute on the source table to extract the data. The data extracted will be all the rows that changed since a particular point in time.</td><td></td></tr><tr><td>sourceTable</td><td>Source Table Name. Needed to set hive environment properties.</td><td></td></tr><tr><td>targetTable</td><td>Target Table Name. Needed for the intermediate storage directory structure.</td><td></td></tr><tr><td>sourceDataPath</td><td>Source DFS Base Path. This is where the Hudi metadata will be read.</td><td></td></tr><tr><td>targetDataPath</td><td>Target DFS Base path. This is needed to compute the fromCommitTime. This is not needed if fromCommitTime is specified explicitly.</td><td></td></tr><tr><td>tmpdb</td><td>The database to which the intermediate temp delta table will be created</td><td>hoodie_temp</td></tr><tr><td>fromCommitTime</td><td>This is the most important parameter. This is the point in time from which the changed records are pulled from.</td><td></td></tr><tr><td>maxCommits</td><td>Number of commits to include in the pull. Setting this to -1 will include all the commits from fromCommitTime. Setting this to a value > 0, will include records that ONLY changed in the specified number of commits after fromCommitTime. This may be needed if you need to catch up say 2 commits at a time.</td><td>3</td></tr><tr><td>help</td><td>Utility Help</td><td></td></tr></tbody></table><p>Setting fromCommitTime=0 and maxCommits=-1 will pull in the entire source dataset and can be used to initiate backfills. If the target dataset is a Hudi dataset, |
| then the utility can determine if the target dataset has no commits or is behind more than 24 hour (this is configurable), |
| it will automatically use the backfill configuration, since applying the last 24 hours incrementally could take more time than doing a backfill. The current limitation of the tool |
| is the lack of support for self-joining the same table in mixed mode (normal and incremental modes).</p><p><strong>NOTE on Hive queries that are executed using Fetch task:</strong> |
| Since Fetch tasks invoke InputFormat.listStatus() per partition, Hoodie metadata can be listed in |
| every such listStatus() call. In order to avoid this, it might be useful to disable fetch tasks |
| using the hive session property for incremental queries: <code>set hive.fetch.task.conversion=none;</code> This |
| would ensure Map Reduce execution is chosen for a Hive query, which combines partitions (comma |
| separated) and calls InputFormat.listStatus() only once with all those partitions.</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="spark">Spark<a class="hash-link" href="#spark" title="Direct link to heading"></a></h2><p>Spark provides much easier deployment & management of Hudi jars and bundles into jobs/notebooks. At a high level, there are two ways to access Hudi datasets in Spark.</p><ul><li><p><strong>Hudi DataSource</strong> : Supports Read Optimized, Incremental Pulls similar to how standard datasources (e.g: <code>spark.read.parquet</code>) work.</p></li><li><p><strong>Read as Hive tables</strong> : Supports all three views, including the real time view, relying on the custom Hudi input formats again like Hive.</p><p>In general, your spark job needs a dependency to <code>hudi-spark</code> or <code>hudi-spark-bundle-x.y.z.jar</code> needs to be on the class path of driver & executors (hint: use <code>--jars</code> argument)</p></li></ul><h3 class="anchor anchorWithStickyNavbar_y2LR" id="read-optimized-table-1">Read Optimized table<a class="hash-link" href="#read-optimized-table-1" title="Direct link to heading"></a></h3><p>To read RO table as a Hive table using SparkSQL, simply push a path filter into sparkContext as follows. |
| This method retains Spark built-in optimizations for reading Parquet files like vectorized reading on Hudi tables.</p><div class="codeBlockContainer_J+bg language-scala theme-code-block"><div class="codeBlockContent_csEI scala"><pre tabindex="0" class="prism-code language-scala codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain">spark.sparkContext.hadoopConfiguration.setClass("mapreduce.input.pathFilter.class", classOf[org.apache.hudi.hadoop.HoodieROTablePathFilter], classOf[org.apache.hadoop.fs.PathFilter]);</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>If you prefer to glob paths on DFS via the datasource, you can simply do something like below to get a Spark dataframe to work with. </p><div class="codeBlockContainer_J+bg language-java theme-code-block"><div class="codeBlockContent_csEI java"><pre tabindex="0" class="prism-code language-java codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain">Dataset<Row> hoodieROViewDF = spark.read().format("org.apache.hudi")</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">// pass any path glob, can include hudi & non-hudi datasets</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">.load("/glob/path/pattern");</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><h3 class="anchor anchorWithStickyNavbar_y2LR" id="spark-rt-view">Real time table<a class="hash-link" href="#spark-rt-view" title="Direct link to heading"></a></h3><p>Currently, real time table can only be queried as a Hive table in Spark. In order to do this, set <code>spark.sql.hive.convertMetastoreParquet=false</code>, forcing Spark to fallback |
| to using the Hive Serde to read the data (planning/executions is still Spark). </p><div class="codeBlockContainer_J+bg language-java theme-code-block"><div class="codeBlockContent_csEI java"><pre tabindex="0" class="prism-code language-java codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain">$ spark-shell --jars hudi-spark-bundle-x.y.z-SNAPSHOT.jar --driver-class-path /etc/hive/conf --packages com.databricks:spark-avro_2.11:4.0.0 --conf spark.sql.hive.convertMetastoreParquet=false --num-executors 10 --driver-memory 7g --executor-memory 2g --master yarn-client</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">scala> sqlContext.sql("select count(*) from hudi_rt where datestr = '2016-10-02'").show()</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><h3 class="anchor anchorWithStickyNavbar_y2LR" id="spark-incr-pull">Incremental Pulling<a class="hash-link" href="#spark-incr-pull" title="Direct link to heading"></a></h3><p>The <code>hudi-spark</code> module offers the DataSource API, a more elegant way to pull data from Hudi dataset and process it via Spark. |
| A sample incremental pull, that will obtain all records written since <code>beginInstantTime</code>, looks like below.</p><div class="codeBlockContainer_J+bg language-java theme-code-block"><div class="codeBlockContent_csEI java"><pre tabindex="0" class="prism-code language-java codeBlock_rtdJ thin-scrollbar" style="color:#F8F8F2;background-color:#282A36"><code class="codeBlockLines_1zSZ"><span class="token-line" style="color:#F8F8F2"><span class="token plain"> Dataset<Row> hoodieIncViewDF = spark.read()</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> .format("org.apache.hudi")</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> .option(DataSourceReadOptions.VIEW_TYPE_OPT_KEY(),</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> DataSourceReadOptions.VIEW_TYPE_INCREMENTAL_OPT_VAL())</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> .option(DataSourceReadOptions.BEGIN_INSTANTTIME_OPT_KEY(),</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> <beginInstantTime>)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> .load(tablePath); // For incremental view, pass in the root/base path of dataset</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>Please refer to <a href="/docs/configurations#spark-datasource">configurations</a> section, to view all datasource options.</p><p>Additionally, <code>HoodieReadClient</code> offers the following functionality using Hudi's implicit indexing.</p><table><thead><tr><th><strong>API</strong></th><th><strong>Description</strong></th></tr></thead><tbody><tr><td>read(keys)</td><td>Read out the data corresponding to the keys as a DataFrame, using Hudi's own index for faster lookup</td></tr><tr><td>filterExists()</td><td>Filter out already existing records from the provided RDD<!-- -->[HoodieRecord]<!-- -->. Useful for de-duplication</td></tr><tr><td>checkExists(keys)</td><td>Check if the provided keys exist in a Hudi dataset</td></tr></tbody></table><h2 class="anchor anchorWithStickyNavbar_y2LR" id="presto">Presto<a class="hash-link" href="#presto" title="Direct link to heading"></a></h2><p>Presto is a popular query engine, providing interactive query performance. Hudi RO tables can be queries seamlessly in Presto. |
| This requires the <code>hudi-presto-bundle</code> jar to be placed into <code><presto_install>/plugin/hive-hadoop2/</code>, across the installation.</p></div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="theme-doc-footer-edit-meta-row row"><div class="col"><a href="https://github.com/apache/hudi/tree/asf-site/website/versioned_docs/version-0.5.0/querying_data.md" target="_blank" rel="noreferrer noopener" class="theme-edit-this-page"><svg fill="currentColor" height="20" width="20" viewBox="0 0 40 40" class="iconEdit_mS5F" aria-hidden="true"><g><path d="m34.5 11.7l-3 3.1-6.3-6.3 3.1-3q0.5-0.5 1.2-0.5t1.1 0.5l3.9 3.9q0.5 0.4 0.5 1.1t-0.5 1.2z m-29.5 17.1l18.4-18.5 6.3 6.3-18.4 18.4h-6.3v-6.2z"></path></g></svg>Edit this page</a></div><div class="col lastUpdated_mt2f"></div></div></footer></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages navigation"><div class="pagination-nav__item"><a class="pagination-nav__link" href="/docs/0.5.0/writing_data"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Writing Hudi Datasets</div></a></div><div class="pagination-nav__item pagination-nav__item--next"><a class="pagination-nav__link" href="/docs/0.5.0/configurations"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Configurations</div></a></div></nav></div></div><div class="col col--3"><div class="tableOfContents_vrFS thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#hive" class="table-of-contents__link toc-highlight">Hive</a><ul><li><a href="#read-optimized-table" class="table-of-contents__link toc-highlight">Read Optimized table</a></li><li><a href="#real-time-table" class="table-of-contents__link toc-highlight">Real time table</a></li><li><a href="#incremental-pulling" class="table-of-contents__link toc-highlight">Incremental Pulling</a></li></ul></li><li><a href="#spark" class="table-of-contents__link toc-highlight">Spark</a><ul><li><a href="#read-optimized-table-1" class="table-of-contents__link toc-highlight">Read Optimized table</a></li><li><a href="#spark-rt-view" class="table-of-contents__link toc-highlight">Real time table</a></li><li><a href="#spark-incr-pull" class="table-of-contents__link toc-highlight">Incremental Pulling</a></li></ul></li><li><a href="#presto" class="table-of-contents__link toc-highlight">Presto</a></li></ul></div></div></div></div></main></div></div><footer class="footer"><div class="container container-fluid"><div class="row footer__links"><div class="col footer__col"><div class="footer__title">About</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/blog/2021/07/21/streaming-data-lake-platform">Our Vision</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/concepts">Concepts</a></li><li class="footer__item"><a class="footer__link-item" href="/community/team">Team</a></li><li class="footer__item"><a class="footer__link-item" href="/releases/release-0.14.1">Releases</a></li><li class="footer__item"><a class="footer__link-item" href="/releases/download">Download</a></li><li class="footer__item"><a class="footer__link-item" href="/powered-by">Who's Using</a></li></ul></div><div class="col footer__col"><div class="footer__title">Learn</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/docs/quick-start-guide">Quick Start</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/docker_demo">Docker Demo</a></li><li class="footer__item"><a class="footer__link-item" href="/blog">Blog</a></li><li class="footer__item"><a class="footer__link-item" href="/talks">Talks</a></li><li class="footer__item"><a class="footer__link-item" href="/videos">Video Guides</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/faq">FAQ</a></li><li class="footer__item"><a href="https://cwiki.apache.org/confluence/display/HUDI" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Technical Wiki<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li></ul></div><div class="col footer__col"><div class="footer__title">Hudi On Cloud</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/docs/s3_hoodie">AWS</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/gcs_hoodie">Google Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/oss_hoodie">Alibaba Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/azure_hoodie">Microsoft Azure</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/cos_hoodie">Tencent Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/docs/ibm_cos_hoodie">IBM Cloud</a></li></ul></div><div class="col footer__col"><div class="footer__title">Community</div><ul class="footer__items"><li class="footer__item"><a class="footer__link-item" href="/community/get-involved">Get Involved</a></li><li class="footer__item"><a href="https://join.slack.com/t/apache-hudi/shared_invite/zt-2ggm1fub8-_yt4Reu9djwqqVRFC7X49g" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Slack<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li><li class="footer__item"><a href="https://github.com/apache/hudi" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li><li class="footer__item"><a href="https://twitter.com/ApacheHudi" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Twitter<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li><li class="footer__item"><a href="https://www.youtube.com/channel/UCs7AhE0BWaEPZSChrBR-Muw" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>YouTube<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li><li class="footer__item"><a href="https://www.linkedin.com/company/apache-hudi/?viewAsMember=true" target="_blank" rel="noopener noreferrer" class="footer__link-item"><span>Linkedin<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_wgqa"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></span></a></li><li class="footer__item"><a href="mailto:dev-subscribe@hudi.apache.org?Subject=SubscribeToHudi" target="_blank" rel="noopener noreferrer" class="footer__link-item">Mailing List</a></li></ul></div><div class="col footer__col"><div class="footer__title">Apache</div><ul class="footer__items"><li class="footer__item"><a href="https://www.apache.org/events/current-event" target="_blank" rel="noopener noreferrer" class="footer__link-item">Events</a></li><li class="footer__item"><a href="https://www.apache.org/foundation/thanks.html" target="_blank" rel="noopener noreferrer" class="footer__link-item">Thanks</a></li><li class="footer__item"><a href="https://www.apache.org/licenses" target="_blank" rel="noopener noreferrer" class="footer__link-item">License</a></li><li class="footer__item"><a href="https://www.apache.org/security" target="_blank" rel="noopener noreferrer" class="footer__link-item">Security</a></li><li class="footer__item"><a href="https://www.apache.org/foundation/sponsorship.html" target="_blank" rel="noopener noreferrer" class="footer__link-item">Sponsorship</a></li><li class="footer__item"><a href="https://www.apache.org" target="_blank" rel="noopener noreferrer" class="footer__link-item">Foundation</a></li></ul></div></div><div class="footer__bottom text--center"><div class="margin-bottom--sm"><a href="https://hudi.apache.org/" target="_blank" rel="noopener noreferrer" class="footerLogoLink_SRtH"><img src="/assets/images/logo-big.png" alt="Apache Hudi™" class="themedImage_TMUO themedImage--light_4Vu1 footer__logo"><img src="/assets/images/logo-big.png" alt="Apache Hudi™" class="themedImage_TMUO themedImage--dark_uzRr footer__logo"></a></div><div class="footer__copyright">Copyright © 2021 <a href="https://apache.org">The Apache Software Foundation</a>, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0"> Apache License, Version 2.0</a>. <br>Hudi, Apache and the Apache feather logo are trademarks of The Apache Software Foundation.</div></div></div></footer></div> |
| <script src="/assets/js/runtime~main.2cab5691.js"></script> |
| <script src="/assets/js/main.bd020950.js"></script> |
| </body> |
| </html> |
