<!doctype html>
<html class="docs-version-0.6.0" lang="cn" 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="/cn/blog/rss.xml" title="Apache Hudi: User-Facing Analytics RSS Feed">
<link rel="alternate" type="application/atom+xml" href="/cn/blog/atom.xml" title="Apache Hudi: User-Facing Analytics Atom Feed">
<link rel="alternate" type="application/json" href="/cn/blog/feed.json" title="Apache Hudi: User-Facing Analytics JSON Feed">
<link rel="search" type="application/opensearchdescription+xml" title="Apache Hudi" href="/cn/opensearch.xml">
<link rel="alternate" type="application/rss+xml" href="/cn/videos/rss.xml" title="Apache Hudi RSS Feed">
<link rel="alternate" type="application/atom+xml" href="/cn/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">查询 Hudi 数据集 | 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/cn/docs/0.6.0/querying_data"><meta data-react-helmet="true" name="docsearch:language" content="cn"><meta data-react-helmet="true" name="docsearch:version" content="0.6.0"><meta data-react-helmet="true" name="docsearch:docusaurus_tag" content="docs-default-0.6.0"><meta data-react-helmet="true" property="og:title" content="查询 Hudi 数据集 | Apache Hudi"><meta data-react-helmet="true" name="description" content="从概念上讲，Hudi物理存储一次数据到DFS上，同时在其上提供三个逻辑视图，如之前所述。"><meta data-react-helmet="true" property="og:description" content="从概念上讲，Hudi物理存储一次数据到DFS上，同时在其上提供三个逻辑视图，如之前所述。"><meta data-react-helmet="true" name="keywords" content="hudi,hive,spark,sql,presto"><link data-react-helmet="true" rel="icon" href="/cn/assets/images/favicon.ico"><link data-react-helmet="true" rel="canonical" href="https://hudi.apache.org/cn/docs/0.6.0/querying_data"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/docs/0.6.0/querying_data" hreflang="en"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/cn/docs/0.6.0/querying_data" hreflang="cn"><link data-react-helmet="true" rel="alternate" href="https://hudi.apache.org/docs/0.6.0/querying_data" hreflang="x-default"><link data-react-helmet="true" rel="preconnect" href="https://BH4D9OD16A-dsn.algolia.net" crossorigin="anonymous"><link rel="stylesheet" href="/cn/assets/css/styles.ea681a30.css">
<link rel="preload" href="/cn/assets/js/runtime~main.0acdb754.js" as="script">
<link rel="preload" href="/cn/assets/js/main.6d6aa24f.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&amp;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="/cn/"><div class="navbar__logo navbarLogo_Bz6n"><img src="/cn/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/cn/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--dark_uzRr"></div></a><a class="navbar__item navbar__link" href="/cn/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="/cn/talks"><div class="labelWrapperDropdown_Mqbj">Talks</div></a></li><li><a class="dropdown__link" href="/cn/videos"><div class="labelWrapperDropdown_Mqbj">Video Guides</div></a></li><li><a class="dropdown__link" href="/cn/docs/faq"><div class="labelWrapperDropdown_Mqbj">FAQ</div></a></li><li><a class="dropdown__link" href="/cn/tech-specs"><div class="labelWrapperDropdown_Mqbj">Tech Specs</div></a></li><li><a class="dropdown__link" href="/cn/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="/cn/contribute/how-to-contribute"><div class="labelWrapperDropdown_Mqbj">How to Contribute</div></a></li><li><a class="dropdown__link" href="/cn/contribute/developer-setup"><div class="labelWrapperDropdown_Mqbj">Developer Setup</div></a></li><li><a class="dropdown__link" href="/cn/contribute/rfc-process"><div class="labelWrapperDropdown_Mqbj">RFC Process</div></a></li><li><a class="dropdown__link" href="/cn/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="/cn/community/get-involved"><div class="labelWrapperDropdown_Mqbj">Get Involved</div></a></li><li><a class="dropdown__link" href="/cn/community/syncs"><div class="labelWrapperDropdown_Mqbj">Community Syncs</div></a></li><li><a class="dropdown__link" href="/cn/community/office_hours"><div class="labelWrapperDropdown_Mqbj">Office Hours</div></a></li><li><a class="dropdown__link" href="/cn/community/team"><div class="labelWrapperDropdown_Mqbj">Team</div></a></li></ul></div><a class="navbar__item navbar__link" href="/cn/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a><a class="navbar__item navbar__link" href="/cn/powered-by"><div class="labelWrapperDropdown_Mqbj">Who&#x27;s Using</div></a><a class="navbar__item navbar__link" href="/cn/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a><a class="navbar__item navbar__link" href="/cn/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="/cn/docs/0.6.0/quick-start-guide"><div class="labelWrapperDropdown_Mqbj">0.6.0<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="/cn/docs/next/querying_data"><div class="labelWrapperDropdown_Mqbj">Next</div></a></li><li><a class="dropdown__link" href="/cn/docs/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.1</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.14.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.14.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.13.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.1</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.13.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.13.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.12.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.3</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.12.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.2</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.12.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.1</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.12.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.12.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.11.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.1</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.11.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.11.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.10.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.1</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.10.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.10.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.9.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.9.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.8.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.8.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.7.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.7.0</div></a></li><li><a aria-current="page" class="dropdown__link dropdown__link--active" href="/cn/docs/0.6.0/querying_data"><div class="labelWrapperDropdown_Mqbj">0.6.0</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.5.3/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.3</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.5.2/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.2</div></a></li><li><a class="dropdown__link" href="/cn/docs/0.5.1/querying_data"><div class="labelWrapperDropdown_Mqbj">0.5.1</div></a></li><li><a class="dropdown__link" href="/cn/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>Chinese</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/0.6.0/querying_data" target="_self" rel="noopener noreferrer" class="dropdown__link"><div class="labelWrapperDropdown_Mqbj">English</div></a></li><li><a href="/cn/docs/0.6.0/querying_data" target="_self" rel="noopener noreferrer" class="dropdown__link dropdown__link--active"><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="/cn/"><div class="navbar__logo"><img src="/cn/assets/images/hudi.png" alt="Apache Hudi" class="themedImage_TMUO themedImage--light_4Vu1"><img src="/cn/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="/cn/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="/cn/blog"><div class="labelWrapperDropdown_Mqbj">Blog</div></a></li><li class="menu__list-item"><a class="menu__link" href="/cn/powered-by"><div class="labelWrapperDropdown_Mqbj">Who&#x27;s Using</div></a></li><li class="menu__list-item"><a class="menu__link" href="/cn/roadmap"><div class="labelWrapperDropdown_Mqbj">Roadmap</div></a></li><li class="menu__list-item"><a class="menu__link" href="/cn/releases/download"><div class="labelWrapperDropdown_Mqbj">Download</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">Versions</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"><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="/cn/docs/0.6.0/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="/cn/docs/0.6.0/use_cases">使用案例</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/cn/docs/0.6.0/writing_data">写入 Hudi 数据集</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="/cn/docs/0.6.0/querying_data">查询 Hudi 数据集</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/cn/docs/0.6.0/configurations">配置</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/cn/docs/0.6.0/performance">性能</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/cn/docs/0.6.0/deployment">管理 Hudi Pipelines</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="/cn/docs/0.6.0/cloud">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="/cn/docs/0.6.0/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>0.6.0</b>, which is no longer actively maintained.</div><div class="margin-top--md">For up-to-date documentation, see the <b><a href="/cn/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: <!-- -->0.6.0</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>查询 Hudi 数据集</h1></header><p>从概念上讲，Hudi物理存储一次数据到DFS上，同时在其上提供三个逻辑视图，如<a href="/cn/docs/concepts#views">之前</a>所述。
数据集同步到Hive Metastore后，它将提供由Hudi的自定义输入格式支持的Hive外部表。一旦提供了适当的Hudi捆绑包，
就可以通过Hive、Spark和Presto之类的常用查询引擎来查询数据集。</p><p>具体来说，在写入过程中传递了两个由<a href="/cn/docs/configurations#TABLE_NAME_OPT_KEY">table name</a>命名的Hive表。
例如，如果<code>table name = hudi_tbl</code>，我们得到</p><ul><li><code>hudi_tbl</code> 实现了由 <code>HoodieParquetInputFormat</code> 支持的数据集的读优化视图，从而提供了纯列式数据。</li><li><code>hudi_tbl_rt</code> 实现了由 <code>HoodieParquetRealtimeInputFormat</code> 支持的数据集的实时视图，从而提供了基础数据和日志数据的合并视图。</li></ul><p>如概念部分所述，<a href="https://www.oreilly.com/ideas/ubers-case-for-incremental-processing-on-hadoop" target="_blank" rel="noopener noreferrer">增量处理</a>所需要的
一个关键原语是<code>增量拉取</code>（以从数据集中获取更改流/日志）。您可以增量提取Hudi数据集，这意味着自指定的即时时间起，
您可以只获得全部更新和新行。 这与插入更新一起使用，对于构建某些数据管道尤其有用，包括将1个或多个源Hudi表（数据流/事实）以增量方式拉出（流/事实）
并与其他表（数据集/维度）结合以<a href="/cn/docs/writing_data">写出增量</a>到目标Hudi数据集。增量视图是通过查询上表之一实现的，并具有特殊配置，
该特殊配置指示查询计划仅需要从数据集中获取增量数据。</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="查询引擎支持列表">查询引擎支持列表<a class="hash-link" href="#查询引擎支持列表" title="Direct link to heading">​</a></h2><p>下面的表格展示了各查询引擎是否支持Hudi格式</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="读优化表">读优化表<a class="hash-link" href="#读优化表" title="Direct link to heading">​</a></h3><table><thead><tr><th>查询引擎</th><th>实时视图</th><th>增量拉取</th></tr></thead><tbody><tr><td><strong>Hive</strong></td><td>Y</td><td>Y</td></tr><tr><td><strong>Spark SQL</strong></td><td>Y</td><td>Y</td></tr><tr><td><strong>Spark Datasource</strong></td><td>Y</td><td>Y</td></tr><tr><td><strong>PrestoDB</strong></td><td>Y</td><td>N</td></tr><tr><td><strong>Impala</strong></td><td>Y</td><td>N</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_y2LR" id="实时表">实时表<a class="hash-link" href="#实时表" title="Direct link to heading">​</a></h3><table><thead><tr><th>查询引擎</th><th>实时视图</th><th>增量拉取</th><th>读优化表</th></tr></thead><tbody><tr><td><strong>Hive</strong></td><td>Y</td><td>Y</td><td>Y</td></tr><tr><td><strong>Spark SQL</strong></td><td>Y</td><td>Y</td><td>Y</td></tr><tr><td><strong>Spark Datasource</strong></td><td>Y</td><td>N</td><td>Y</td></tr><tr><td><strong>PrestoDB</strong></td><td>Y</td><td>N</td><td>Y</td></tr><tr><td><strong>Impala</strong></td><td>N</td><td>N</td><td>Y</td></tr></tbody></table><p>接下来，我们将详细讨论在每个查询引擎上如何访问所有三个视图。</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="hive">Hive<a class="hash-link" href="#hive" title="Direct link to heading">​</a></h2><p>为了使Hive能够识别Hudi数据集并正确查询，
HiveServer2需要在其<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">辅助jars路径</a>中提供<code>hudi-hadoop-mr-bundle-x.y.z-SNAPSHOT.jar</code>。
这将确保输入格式类及其依赖项可用于查询计划和执行。</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="hive-ro-view">读优化表<a class="hash-link" href="#hive-ro-view" title="Direct link to heading">​</a></h3><p>除了上述设置之外，对于beeline cli访问，还需要将<code>hive.input.format</code>变量设置为<code>org.apache.hudi.hadoop.HoodieParquetInputFormat</code>输入格式的完全限定路径名。
对于Tez，还需要将<code>hive.tez.input.format</code>设置为<code>org.apache.hadoop.hive.ql.io.HiveInputFormat</code>。</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="hive-rt-view">实时表<a class="hash-link" href="#hive-rt-view" title="Direct link to heading">​</a></h3><p>除了在HiveServer2上安装Hive捆绑jars之外，还需要将其放在整个集群的hadoop/hive安装中，这样查询也可以使用自定义RecordReader。</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="hive-incr-pull">增量拉取<a class="hash-link" href="#hive-incr-pull" title="Direct link to heading">​</a></h3><p><code>HiveIncrementalPuller</code>允许通过HiveQL从大型事实/维表中增量提取更改，
结合了Hive（可靠地处理复杂的SQL查询）和增量原语的好处（通过增量拉取而不是完全扫描来加快查询速度）。
该工具使用Hive JDBC运行hive查询并将其结果保存在临时表中，这个表可以被插入更新。
Upsert实用程序（<code>HoodieDeltaStreamer</code>）具有目录结构所需的所有状态，以了解目标表上的提交时间应为多少。
例如：<code>/app/incremental-hql/intermediate/{source_table_name}_temp/{last_commit_included}</code>。
已注册的Delta Hive表的格式为<code>{tmpdb}.{source_table}_{last_commit_included}</code>。</p><p>以下是HiveIncrementalPuller的配置选项</p><table><thead><tr><th><strong>配置</strong></th><th><strong>描述</strong></th><th><strong>默认值</strong></th></tr></thead><tbody><tr><td>hiveUrl</td><td>要连接的Hive Server 2的URL</td><td></td></tr><tr><td>hiveUser</td><td>Hive Server 2 用户名</td><td></td></tr><tr><td>hivePass</td><td>Hive Server 2 密码</td><td></td></tr><tr><td>queue</td><td>YARN 队列名称</td><td></td></tr><tr><td>tmp</td><td>DFS中存储临时增量数据的目录。目录结构将遵循约定。请参阅以下部分。</td><td></td></tr><tr><td>extractSQLFile</td><td>在源表上要执行的提取数据的SQL。提取的数据将是自特定时间点以来已更改的所有行。</td><td></td></tr><tr><td>sourceTable</td><td>源表名称。在Hive环境属性中需要设置。</td><td></td></tr><tr><td>targetTable</td><td>目标表名称。中间存储目录结构需要。</td><td></td></tr><tr><td>sourceDataPath</td><td>源DFS基本路径。这是读取Hudi元数据的地方。</td><td></td></tr><tr><td>targetDataPath</td><td>目标DFS基本路径。 这是计算fromCommitTime所必需的。 如果显式指定了fromCommitTime，则不需要设置这个参数。</td><td></td></tr><tr><td>tmpdb</td><td>用来创建中间临时增量表的数据库</td><td>hoodie_temp</td></tr><tr><td>fromCommitTime</td><td>这是最重要的参数。 这是从中提取更改的记录的时间点。</td><td></td></tr><tr><td>maxCommits</td><td>要包含在拉取中的提交数。将此设置为-1将包括从fromCommitTime开始的所有提交。将此设置为大于0的值，将包括在fromCommitTime之后仅更改指定提交次数的记录。如果您需要一次赶上两次提交，则可能需要这样做。</td><td>3</td></tr><tr><td>help</td><td>实用程序帮助</td><td></td></tr></tbody></table><p>设置fromCommitTime=0和maxCommits=-1将提取整个源数据集，可用于启动Backfill。
如果目标数据集是Hudi数据集，则该实用程序可以确定目标数据集是否没有提交或延迟超过24小时（这是可配置的），
它将自动使用Backfill配置，因为增量应用最近24小时的更改会比Backfill花费更多的时间。
该工具当前的局限性在于缺乏在混合模式（正常模式和增量模式）下自联接同一表的支持。</p><p><strong>关于使用Fetch任务执行的Hive查询的说明：</strong>
由于Fetch任务为每个分区调用InputFormat.listStatus()，每个listStatus()调用都会列出Hoodie元数据。
为了避免这种情况，如下操作可能是有用的，即使用Hive session属性对增量查询禁用Fetch任务：
<code>set hive.fetch.task.conversion = none;</code>。这将确保Hive查询使用Map Reduce执行，
合并分区（用逗号分隔），并且对所有这些分区仅调用一次InputFormat.listStatus()。</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="spark">Spark<a class="hash-link" href="#spark" title="Direct link to heading">​</a></h2><p>Spark可将Hudi jars和捆绑包轻松部署和管理到作业/笔记本中。简而言之，通过Spark有两种方法可以访问Hudi数据集。</p><ul><li><strong>Hudi DataSource</strong>：支持实时视图，读取优化和增量拉取，类似于标准数据源（例如：<code>spark.read.parquet</code>）的工作方式。</li><li><strong>以Hive表读取</strong>：支持所有三个视图，包括实时视图，依赖于自定义的Hudi输入格式（再次类似Hive）。</li></ul><p>通常，您的spark作业需要依赖<code>hudi-spark</code>或<code>hudi-spark-bundle-x.y.z.jar</code>，
它们必须位于驱动程序和执行程序的类路径上（提示：使用<code>--jars</code>参数）。</p><h3 class="anchor anchorWithStickyNavbar_y2LR" id="spark-ro-view">读优化表<a class="hash-link" href="#spark-ro-view" title="Direct link to heading">​</a></h3><p>要使用SparkSQL将RO表读取为Hive表，只需按如下所示将路径过滤器推入sparkContext。
对于Hudi表，该方法保留了Spark内置的读取Parquet文件的优化功能，例如进行矢量化读取。</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(&quot;mapreduce.input.pathFilter.class&quot;, 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>如果您希望通过数据源在DFS上使用全局路径，则只需执行以下类似操作即可得到Spark DataFrame。</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">Dataset&lt;Row&gt; hoodieROViewDF = spark.read().format(&quot;org.apache.hudi&quot;)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">// pass any path glob, can include hudi &amp; non-hudi datasets</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">.load(&quot;/glob/path/pattern&quot;);</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">实时表<a class="hash-link" href="#spark-rt-view" title="Direct link to heading">​</a></h3><p>将实时表在Spark中作为Hive表进行查询，设置<code>spark.sql.hive.convertMetastoreParquet = false</code>，
迫使Spark回退到使用Hive Serde读取数据（计划/执行仍然是Spark）。</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-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&gt; sqlContext.sql(&quot;select count(*) from hudi_rt where datestr = &#x27;2016-10-02&#x27;&quot;).show()</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>如果您希望通过数据源在DFS上使用全局路径，则只需执行以下类似操作即可得到Spark DataFrame。</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">Dataset&lt;Row&gt; hoodieRealtimeViewDF = spark.read().format(&quot;org.apache.hudi&quot;)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">// pass any path glob, can include hudi &amp; non-hudi datasets</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">.load(&quot;/glob/path/pattern&quot;);</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>如果您希望只查询实时表的读优化视图</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">Dataset&lt;Row&gt; hoodieRealtimeViewDF = spark.read().format(&quot;org.apache.hudi&quot;)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">.option(DataSourceReadOptions.QUERY_TYPE_OPT_KEY, DataSourceReadOptions.QUERY_TYPE_READ_OPTIMIZED_OPT_VAL)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">// pass any path glob, can include hudi &amp; non-hudi datasets</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">.load(&quot;/glob/path/pattern&quot;);</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">增量拉取<a class="hash-link" href="#spark-incr-pull" title="Direct link to heading">​</a></h3><p><code>hudi-spark</code>模块提供了DataSource API，这是一种从Hudi数据集中提取数据并通过Spark处理数据的更优雅的方法。
如下所示是一个示例增量拉取，它将获取自<code>beginInstantTime</code>以来写入的所有记录。</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&lt;Row&gt; hoodieIncViewDF = spark.read()</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">     .format(&quot;org.apache.hudi&quot;)</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">            &lt;beginInstantTime&gt;)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">     .option(DataSourceReadOptions.INCR_PATH_GLOB_OPT_KEY(),</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">            &quot;/year=2020/month=*/day=*&quot;) // 可选，从指定的分区增量拉取</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">     .load(tablePath); // 用数据集的最底层路径</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>请参阅<a href="/cn/docs/configurations#spark-datasource">设置</a>部分，以查看所有数据源选项。</p><p>另外，<code>HoodieReadClient</code>通过Hudi的隐式索引提供了以下功能。</p><table><thead><tr><th><strong>API</strong></th><th><strong>描述</strong></th></tr></thead><tbody><tr><td>read(keys)</td><td>使用Hudi自己的索通过快速查找将与键对应的数据作为DataFrame读出</td></tr><tr><td>filterExists()</td><td>从提供的RDD<!-- -->[HoodieRecord]<!-- -->中过滤出已经存在的记录。对删除重复数据有用</td></tr><tr><td>checkExists(keys)</td><td>检查提供的键是否存在于Hudi数据集中</td></tr></tbody></table><h2 class="anchor anchorWithStickyNavbar_y2LR" id="prestodb">PrestoDB<a class="hash-link" href="#prestodb" title="Direct link to heading">​</a></h2><p>PrestoDB是一种常用的查询引擎，可提供交互式查询性能。 Hudi RO表可以在Presto中无缝查询。
这需要在整个安装过程中将<code>hudi-presto-bundle</code> jar放入<code>&lt;presto_install&gt;/plugin/hive-hadoop2/</code>中。</p><h2 class="anchor anchorWithStickyNavbar_y2LR" id="impala-34-or-later">Impala (3.4 or later)<a class="hash-link" href="#impala-34-or-later" title="Direct link to heading">​</a></h2><h3 class="anchor anchorWithStickyNavbar_y2LR" id="读优化表-1">读优化表<a class="hash-link" href="#读优化表-1" title="Direct link to heading">​</a></h3><p>Impala可以在HDFS上查询Hudi读优化表，作为一种 <a href="https://docs.cloudera.com/documentation/enterprise/6/6.3/topics/impala_tables#external_tables" target="_blank" rel="noopener noreferrer">EXTERNAL TABLE</a> 的形式。<br>
<!-- -->可以通过以下方式在Impala上建立Hudi读优化表:</p><div class="codeBlockContainer_J+bg theme-code-block"><div class="codeBlockContent_csEI"><pre tabindex="0" class="prism-code language-undefined 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">CREATE EXTERNAL TABLE database.table_name</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">LIKE PARQUET &#x27;/path/to/load/xxx.parquet&#x27;</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">STORED AS HUDIPARQUET</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">LOCATION &#x27;/path/to/load&#x27;;</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>Impala可以利用合理的文件分区来提高查询的效率。
如果想要建立分区的表，文件夹命名需要根据此种方式<code>year=2020/month=1</code>.
Impala使用<code>=</code>来区分分区名和分区值.<br>
<!-- -->可以通过以下方式在Impala上建立分区Hudi读优化表:</p><div class="codeBlockContainer_J+bg theme-code-block"><div class="codeBlockContent_csEI"><pre tabindex="0" class="prism-code language-undefined 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">CREATE EXTERNAL TABLE database.table_name</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">LIKE PARQUET &#x27;/path/to/load/xxx.parquet&#x27;</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">PARTITION BY (year int, month int, day int)</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">STORED AS HUDIPARQUET</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">LOCATION &#x27;/path/to/load&#x27;;</span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain">ALTER TABLE database.table_name RECOVER PARTITIONS;</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div><p>在Hudi成功写入一个新的提交后, 刷新Impala表来得到最新的结果.</p><div class="codeBlockContainer_J+bg theme-code-block"><div class="codeBlockContent_csEI"><pre tabindex="0" class="prism-code language-undefined 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">REFRESH database.table_name</span><br></span></code></pre><button type="button" aria-label="Copy code to clipboard" class="copyButton_M3SB clean-btn">Copy</button></div></div></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-0.6.0/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="/cn/docs/0.6.0/writing_data"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">写入 Hudi 数据集</div></a></div><div class="pagination-nav__item pagination-nav__item--next"><a class="pagination-nav__link" href="/cn/docs/0.6.0/configurations"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">配置</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="#查询引擎支持列表" class="table-of-contents__link toc-highlight">查询引擎支持列表</a><ul><li><a href="#读优化表" class="table-of-contents__link toc-highlight">读优化表</a></li><li><a href="#实时表" class="table-of-contents__link toc-highlight">实时表</a></li></ul></li><li><a href="#hive" class="table-of-contents__link toc-highlight">Hive</a><ul><li><a href="#hive-ro-view" class="table-of-contents__link toc-highlight">读优化表</a></li><li><a href="#hive-rt-view" class="table-of-contents__link toc-highlight">实时表</a></li><li><a href="#hive-incr-pull" class="table-of-contents__link toc-highlight">增量拉取</a></li></ul></li><li><a href="#spark" class="table-of-contents__link toc-highlight">Spark</a><ul><li><a href="#spark-ro-view" class="table-of-contents__link toc-highlight">读优化表</a></li><li><a href="#spark-rt-view" class="table-of-contents__link toc-highlight">实时表</a></li><li><a href="#spark-incr-pull" class="table-of-contents__link toc-highlight">增量拉取</a></li></ul></li><li><a href="#prestodb" class="table-of-contents__link toc-highlight">PrestoDB</a></li><li><a href="#impala-34-or-later" class="table-of-contents__link toc-highlight">Impala (3.4 or later)</a><ul><li><a href="#读优化表-1" class="table-of-contents__link toc-highlight">读优化表</a></li></ul></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="/cn/blog/2021/07/21/streaming-data-lake-platform">Our Vision</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/concepts">Concepts</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/community/team">Team</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/releases/release-0.14.1">Releases</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/releases/download">Download</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/powered-by">Who&#x27;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="/cn/docs/quick-start-guide">Quick Start</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/docker_demo">Docker Demo</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/blog">Blog</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/talks">Talks</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/videos">Video Guides</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/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="/cn/docs/s3_hoodie">AWS</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/gcs_hoodie">Google Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/oss_hoodie">Alibaba Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/azure_hoodie">Microsoft Azure</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/docs/cos_hoodie">Tencent Cloud</a></li><li class="footer__item"><a class="footer__link-item" href="/cn/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="/cn/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="/cn/assets/images/logo-big.png" alt="Apache Hudi™" class="themedImage_TMUO themedImage--light_4Vu1 footer__logo"><img src="/cn/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>.
      Hudi, Apache and the Apache feather logo are trademarks of The Apache Software Foundation. <a href="/docs/privacy">Privacy Policy</a></div></div></div></footer></div>
<script src="/cn/assets/js/runtime~main.0acdb754.js"></script>
<script src="/cn/assets/js/main.6d6aa24f.js"></script>
</body>
</html>