blob: fda6c723e9514d7d972e5bb6b36d92e3b221627d [file] [log] [blame]
<!doctype html>
<html lang="en" dir="ltr" class="docs-wrapper docs-doc-page docs-version-1.10.0 plugin-docs plugin-id-default docs-doc-id-modules/sort/dirty_data_archive">
<head>
<meta charset="UTF-8">
<meta name="generator" content="Docusaurus v2.3.1">
<title data-rh="true">Dirty Data Archive | Apache InLong</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://inlong.apache.org/docs/1.10.0/modules/sort/dirty_data_archive"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="1.10.0"><meta data-rh="true" name="docusaurus_tag" content="docs-default-1.10.0"><meta data-rh="true" name="docsearch:version" content="1.10.0"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-1.10.0"><meta data-rh="true" property="og:title" content="Dirty Data Archive | Apache InLong"><meta data-rh="true" name="description" content="Overview"><meta data-rh="true" property="og:description" content="Overview"><link data-rh="true" rel="icon" href="/img/logo.svg"><link data-rh="true" rel="canonical" href="https://inlong.apache.org/docs/1.10.0/modules/sort/dirty_data_archive"><link data-rh="true" rel="alternate" href="https://inlong.apache.org/docs/1.10.0/modules/sort/dirty_data_archive" hreflang="en"><link data-rh="true" rel="alternate" href="https://inlong.apache.org/zh-CN/docs/1.10.0/modules/sort/dirty_data_archive" hreflang="zh-CN"><link data-rh="true" rel="alternate" href="https://inlong.apache.org/docs/1.10.0/modules/sort/dirty_data_archive" hreflang="x-default"><link data-rh="true" rel="preconnect" href="https://YUW9QEL53E-dsn.algolia.net" crossorigin="anonymous"><link rel="alternate" type="application/rss+xml" href="/blog/rss.xml" title="Apache InLong RSS Feed">
<link rel="alternate" type="application/atom+xml" href="/blog/atom.xml" title="Apache InLong Atom Feed">
<link rel="search" type="application/opensearchdescription+xml" title="Apache InLong" href="/opensearch.xml">
<script src="https://www.apachecon.com/event-images/snippet.js" async></script><link rel="stylesheet" href="/assets/css/styles.c64edd51.css">
<link rel="preload" href="/assets/js/runtime~main.63c98e82.js" as="script">
<link rel="preload" href="/assets/js/main.070aef2a.js" as="script">
</head>
<body class="navigation-with-keyboard">
<script>!function(){function e(e){document.documentElement.setAttribute("data-theme",e)}var t=function(){var e=null;try{e=localStorage.getItem("theme")}catch(e){}return e}();null!==t?e(t):window.matchMedia("(prefers-color-scheme: dark)").matches?e("dark"):(window.matchMedia("(prefers-color-scheme: light)").matches,e("light"))}()</script><div id="__docusaurus">
<div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="navbar navbar--fixed-top"><div class="navbar__inner"><div class="navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><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"><img src="/img/logo.svg" alt="Apache" class="themedImage_ToTc themedImage--light_HNdA"><img src="/img/logo.svg" alt="Apache" class="themedImage_ToTc themedImage--dark_i4oU"></div><b class="navbar__title text--truncate">Apache InLong</b></a></div><div class="navbar__items navbar__items--right"><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a class="navbar__link" aria-haspopup="true" aria-expanded="false" role="button" href="/docs/introduction">Docs</a><ul class="dropdown__menu"><li><a class="dropdown__link" href="/docs/next/introduction">Next</a></li><li><a class="dropdown__link" href="/docs/introduction">1.11.0</a></li><li><a class="dropdown__link" href="/docs/1.10.0/introduction">1.10.0</a></li><li><a class="dropdown__link" href="/docs/1.9.0/introduction">1.9.0</a></li><li><a class="dropdown__link" href="/docs/1.8.0/introduction">1.8.0</a></li><li><a class="dropdown__link" href="/versions/">All versions</a></li></ul></div><a class="navbar__item navbar__link" href="/downloads">Download</a><a class="navbar__item navbar__link" href="/community/how-to-contribute">Community</a><a class="navbar__item navbar__link" href="/blog">Blog</a><a class="navbar__item navbar__link" href="/team">Team</a><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link">ASF</a><ul class="dropdown__menu"><li><a href="https://www.apache.org/" target="_blank" rel="noopener noreferrer" class="dropdown__link">Apache Software Foundation</a></li><li><a href="https://www.apache.org/licenses/" target="_blank" rel="noopener noreferrer" class="dropdown__link">License</a></li><li><a href="https://www.apache.org/events/current-event" target="_blank" rel="noopener noreferrer" class="dropdown__link">Events</a></li><li><a href="https://www.apache.org/security/" target="_blank" rel="noopener noreferrer" class="dropdown__link">Security</a></li><li><a href="https://www.apache.org/foundation/sponsorship.html" target="_blank" rel="noopener noreferrer" class="dropdown__link">Sponsorship</a></li><li><a href="https://www.apache.org/foundation/policies/privacy.html" target="_blank" rel="noopener noreferrer" class="dropdown__link">Privacy</a></li><li><a href="https://www.apache.org/foundation/thanks.html" target="_blank" rel="noopener noreferrer" class="dropdown__link">Thanks</a></li></ul></div><div class="navbar__item dropdown dropdown--hoverable dropdown--right"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link"><svg viewBox="0 0 24 24" width="20" height="20" aria-hidden="true" class="iconLanguage_nlXk"><path fill="currentColor" d="M12.87 15.07l-2.54-2.51.03-.03c1.74-1.94 2.98-4.17 3.71-6.53H17V4h-7V2H8v2H1v1.99h11.17C11.5 7.92 10.44 9.75 9 11.35 8.07 10.32 7.3 9.19 6.69 8h-2c.73 1.63 1.73 3.17 2.98 4.56l-5.09 5.02L4 19l5-5 3.11 3.11.76-2.04zM18.5 10h-2L12 22h2l1.12-3h4.75L21 22h2l-4.5-12zm-2.62 7l1.62-4.33L19.12 17h-3.24z"></path></svg>English</a><ul class="dropdown__menu"><li><a href="/docs/1.10.0/modules/sort/dirty_data_archive" target="_self" rel="noopener noreferrer" class="dropdown__link dropdown__link--active" lang="en">English</a></li><li><a href="/zh-CN/docs/1.10.0/modules/sort/dirty_data_archive" target="_self" rel="noopener noreferrer" class="dropdown__link" lang="zh-CN">简体中文</a></li></ul></div><a href="https://github.com/apache/inlong" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><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></a><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type="button" disabled="" title="Switch between dark and light mode (currently light mode)" aria-label="Switch between dark and light mode (currently light mode)" aria-live="polite"><svg viewBox="0 0 24 24" width="24" height="24" class="lightToggleIcon_pyhR"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" class="darkToggleIcon_wfgR"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg></button></div><div class="searchBox_ZlJk"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><svg width="20" height="20" class="DocSearch-Search-Icon" viewBox="0 0 20 20"><path d="M14.386 14.386l4.0877 4.0877-4.0877-4.0877c-2.9418 2.9419-7.7115 2.9419-10.6533 0-2.9419-2.9418-2.9419-7.7115 0-10.6533 2.9418-2.9419 7.7115-2.9419 10.6533 0 2.9419 2.9418 2.9419 7.7115 0 10.6533z" stroke="currentColor" fill="none" fill-rule="evenodd" stroke-linecap="round" stroke-linejoin="round"></path></svg><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"></span></button></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div id="docusaurus_skipToContent_fallback" class="main-wrapper mainWrapper_z2l0 docsWrapper_BCFX"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_sjWU" type="button"></button><div class="docPage__5DB"><aside class="theme-doc-sidebar-container docSidebarContainer_b6E3"><div class="sidebarViewport_Xe31"><div class="sidebar_njMd"><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_SIkG"><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/1.10.0/introduction">Introduction</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/design_and_concept/basic_concept">Design and Concept</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/quick_start/how_to_build">Quick Start</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/deployment/standalone">Deployment</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" aria-expanded="true" href="/docs/1.10.0/modules/agent/overview">Components</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/agent/overview">Agent</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/dataproxy/overview">DataProxy</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/tubemq/overview">TubeMQ</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" aria-expanded="true" tabindex="0" href="/docs/1.10.0/modules/sort/overview">Sort</a></div><ul style="display:block;overflow:visible;height:auto" class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/1.10.0/modules/sort/overview">Overview</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/1.10.0/modules/sort/quick_start">Deployment</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/1.10.0/modules/sort/example">Example</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link" tabindex="0" href="/docs/1.10.0/modules/sort/metrics">Monitor Metrics</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" tabindex="0" href="/docs/1.10.0/modules/sort/dirty_data_archive">Dirty Data Archive</a></li></ul></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/manager/overview">Manager</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/dashboard/overview">Dashboard</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/sort-standalone/overview">Sort Standalone</a></div></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--sublist-caret" aria-expanded="false" tabindex="0" href="/docs/1.10.0/modules/audit/overview">Audit</a></div></li></ul></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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/data_node/extract_node/overview">Data Nodes</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/sdk/dataproxy-sdk/cpp">SDK</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/user_guide/dashboard_usage">User Guide</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/development/inlong_msg">Development</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 menu__link--sublist-caret" aria-expanded="false" href="/docs/1.10.0/administration/user_management">Administration</a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/docs/1.10.0/contact">Contact Us</a></li></ul></nav></div></div></aside><main class="docMainContainer_gTbr"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_VOVn"><div class="theme-doc-version-banner alert alert--warning margin-bottom--md" role="alert"><div>This is documentation for <!-- -->Apache InLong<!-- --> <b>1.10.0</b>, which is no longer actively maintained.</div><div class="margin-top--md">For up-to-date documentation, see the <b><a href="/docs/modules/sort/dirty_data_archive">latest version</a></b> (<!-- -->1.11.0<!-- -->).</div></div><div class="docItemContainer_Djhp"><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_Z_bl" aria-label="Breadcrumbs"><ul class="breadcrumbs" itemscope="" itemtype="https://schema.org/BreadcrumbList"><li class="breadcrumbs__item"><a aria-label="Home page" class="breadcrumbs__link" href="/"><svg viewBox="0 0 24 24" class="breadcrumbHomeIcon_YNFT"><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill="currentColor"></path></svg></a></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">Components</span><meta itemprop="position" content="1"></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">Sort</span><meta itemprop="position" content="2"></li><li itemscope="" itemprop="itemListElement" itemtype="https://schema.org/ListItem" class="breadcrumbs__item breadcrumbs__item--active"><span class="breadcrumbs__link" itemprop="name">Dirty Data Archive</span><meta itemprop="position" content="3"></li></ul></nav><span class="theme-doc-version-badge badge badge--secondary">Version: 1.10.0</span><div class="tocCollapsible_ETCw theme-doc-toc-mobile tocMobile_ITEo"><button type="button" class="clean-btn tocCollapsibleButton_TO0P">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Dirty Data Archive</h1></header><h2 class="anchor anchorWithStickyNavbar_LWe7" id="overview">Overview<a href="#overview" class="hash-link" aria-label="Direct link to Overview" title="Direct link to Overview"></a></h2><p>Dirty data refers to data that cannot be extracted, transformed, and loaded correctly due to the quality of the data itself during the process of data extraction, transform, and loading.
Common dirty data may have field types, lengths, and numbers that do not match. Data serialization, deserialization exception, target library, the table does not exist, etc.
Dirty data archives can dump the dirty data during InLong data flow operation to third-party storage, which is convenient for businesses to find problems.
Sort currently supports dirty data archiving for S3 and Log targets, as well as dirty data archiving for common data sources such as Kafka, Doris, Iceberg, HBase, Hive, Elasticsearch, and JDBC.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="supported-nodes">Supported Nodes<a href="#supported-nodes" class="hash-link" aria-label="Direct link to Supported Nodes" title="Direct link to Supported Nodes"></a></h2><table><thead><tr><th>Type</th><th>Name</th><th>Archive Target System</th></tr></thead><tbody><tr><td>Extract Node</td><td>Kafka</td><td>Log, S3</td></tr><tr><td>Load Node</td><td>Hive</td><td>Log, S3</td></tr><tr><td></td><td>Kafka</td><td>Log, S3</td></tr><tr><td></td><td>HBase</td><td>Log, S3</td></tr><tr><td></td><td>ClickHouse</td><td>Log, S3</td></tr><tr><td></td><td>Iceberg</td><td>Log, S3</td></tr><tr><td></td><td>Elasticsearch</td><td>Log, S3</td></tr><tr><td></td><td>PostgreSQL</td><td>Log, S3</td></tr><tr><td></td><td>HDFS</td><td>Log, S3</td></tr><tr><td></td><td>TDSQL Postgres</td><td>Log, S3</td></tr><tr><td></td><td>Doris</td><td>Log, S3</td></tr><tr><td></td><td>SQL Server</td><td>Log, S3</td></tr><tr><td></td><td>Greenplum</td><td>Log, S3</td></tr></tbody></table><h2 class="anchor anchorWithStickyNavbar_LWe7" id="dirty-data-format">Dirty Data Format<a href="#dirty-data-format" class="hash-link" aria-label="Direct link to Dirty Data Format" title="Direct link to Dirty Data Format"></a></h2><p>During the processing of dirty data archive, we define the following system variables for formatting dirty data:</p><ul><li>SYSTEM_TIME: System time, the format is &#x27;yyyy-MM-dd HH:mm:ss&#x27;</li><li>DIRTY_TYPE:Dirty type, common dirty types are SerializeError, DeserializeError, DataTypeMappingError, etc</li><li>DIRTY_MESSAGE: Dirty data message, that is the cause of dirty data, abnormal information, etc</li></ul><p>The format for archiving to Log:</p><ul><li>[${dirty.side-output.log-tag}]<!-- --> ${value}, Among them, ${value} is the merged value of ${dirty.side-output.labels} and ${dirty data}, and formatted by &#x27;csv&#x27; or &#x27;json&#x27;</li></ul><p>The format for archiving to S3:</p><ul><li>The filename generation format of S3: ${dirty.side-output.s3.key}/${dirty.identifier}-${randome-sequence}.${suffix}</li><li>The format of the data in the file of S3: it merge the ${dirty.side-output.labels} and ${dirty data} and formatted by &#x27;csv&#x27; or &#x27;json&#x27;</li></ul><p><strong>Notes</strong>:For ${dirty.side-output.log-tag}, ${dirty.side-output.labels}, ${dirty.identifier}, ${dirty.side-output.s3.key} see the configuration details below.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="configuration">Configuration<a href="#configuration" class="hash-link" aria-label="Direct link to Configuration" title="Direct link to Configuration"></a></h2><h3 class="anchor anchorWithStickyNavbar_LWe7" id="common-configuration">Common Configuration<a href="#common-configuration" class="hash-link" aria-label="Direct link to Common Configuration" title="Direct link to Common Configuration"></a></h3><table><thead><tr><th>Option</th><th>Required</th><th>Default</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>dirty.ignore</td><td>optional</td><td>false</td><td>Boolean</td><td>Whether to ignore dirty data, the default is &#x27;false&#x27;</td></tr><tr><td>dirty.side-output.enable</td><td>optional</td><td>false</td><td>Boolean</td><td>Whether to support dirty data archive, the default is &#x27;false&#x27;</td></tr><tr><td>dirty.side-output.connector</td><td>required</td><td>(none)</td><td>String</td><td>The connector of dirty data archive, it must be set when &#x27;dirty.side-output.enable&#x27; is &#x27;true&#x27;, currently only &#x27;log&#x27; and &#x27;s3&#x27; are supported.</td></tr><tr><td>dirty.side-output.format</td><td>optional</td><td>csv</td><td>String</td><td>The format of dirty data archive, currently only supports &#x27;csv&#x27; and &#x27;json&#x27;, defaults is &#x27;csv&#x27;.</td></tr><tr><td>dirty.side-output.log.enable</td><td>optional</td><td>true</td><td>Boolean</td><td>Whether to support log printing when dirty data is archived, the default is &#x27;true&#x27;.</td></tr><tr><td>dirty.side-output.ignore-errors</td><td>optional</td><td>true</td><td>Boolean</td><td>Whether to ignore errors in dirty data archives, defaults is &#x27;true&#x27;.</td></tr><tr><td>dirty.identifier</td><td>required</td><td>(none)</td><td>String</td><td>The identifier of dirty data, it will be used for filename generation of file dirty archive, topic generation of mq dirty archive, tablename generation of database, etc, and it supports variable replace like &#x27;${variable}&#x27;. There are several system variables(SYSTEM_TIME,DIRTY_TYPE,DIRTY_MESSAGE) are currently supported, and the support of other variables is determined by the connector.</td></tr><tr><td>dirty.side-output.log-tag</td><td>optional</td><td>(none)</td><td>String</td><td>The log tag of dirty data, it will be used for log printing, and it supports variable replace like &#x27;${variable}&#x27;. There are several system variables(SYSTEM_TIME,DIRTY_TYPE,DIRTY_MESSAGE) are currently supported, and the support of other variables is determined by the connector.</td></tr><tr><td>dirty.side-output.labels</td><td>optional</td><td>(none)</td><td>String</td><td>The labels of dirty data, it will be used for log printing and will be archived with dirty data, and it supports variable replace like &#x27;${variable}&#x27;. There are several system variables(SYSTEM_TIME,DIRTY_TYPE,DIRTY_MESSAGE) are currently supported, and the support of other variables is determined by the connector.</td></tr><tr><td>dirty.side-output.field-delimiter</td><td>optional</td><td>,</td><td>String</td><td>The column separator of dirty data archive, it is used for &#x27;csv&#x27; format, the default is &#x27;,&#x27;.</td></tr><tr><td>dirty.side-output.line-delimiter</td><td>optional</td><td>\n</td><td>String</td><td>The row separator of dirty data archive, it is used for &#x27;csv&#x27; and &#x27;json&#x27; format, the default is &#x27;\n&#x27;.</td></tr><tr><td>dirty.side-output.batch.size</td><td>optional</td><td>100</td><td>Integer</td><td>The cache batch size of dirty data archive, the default is &#x27;100&#x27;.</td></tr><tr><td>dirty.side-output.batch.bytes</td><td>optional</td><td>10240</td><td>Integer</td><td>The cache batch byte of dirty data archive, the unit is byte and the default is &#x27;10240&#x27;(10KB).</td></tr><tr><td>dirty.side-output.retries</td><td>optional</td><td>3</td><td>Integer</td><td>The retris of dirty data archive,the default is &#x27;3&#x27;.</td></tr><tr><td>dirty.side-output.batch.interval</td><td>optional</td><td>60000</td><td>Integer</td><td>The interval time of irty data archive, the unit is millisecond, the default is &#x27;60000&#x27;(60s).</td></tr></tbody></table><h3 class="anchor anchorWithStickyNavbar_LWe7" id="s3-archive-configuration">S3 Archive Configuration<a href="#s3-archive-configuration" class="hash-link" aria-label="Direct link to S3 Archive Configuration" title="Direct link to S3 Archive Configuration"></a></h3><table><thead><tr><th>Option</th><th>Required</th><th>Default</th><th>Type</th><th>Description</th></tr></thead><tbody><tr><td>dirty.side-output.s3.endpoint</td><td>required</td><td>(none)</td><td>String</td><td>The endpoint of s3 archive</td></tr><tr><td>dirty.side-output.s3.region</td><td>required</td><td>(none)</td><td>String</td><td>The region of s3 archive</td></tr><tr><td>dirty.side-output.s3.bucket</td><td>required</td><td>(none)</td><td>String</td><td>The bucket of s3 archive</td></tr><tr><td>dirty.side-output.s3.key</td><td>required</td><td>(none)</td><td>String</td><td>The key of s3 archive</td></tr><tr><td>dirty.side-output.s3.access-key-id</td><td>optional</td><td>(none)</td><td>String</td><td>The access key id of s3 archive, it needs to be configured in the environment if this item is not configured.</td></tr><tr><td>dirty.side-output.s3.secret-key-id</td><td>optional</td><td>(none)</td><td>String</td><td>The secret key id of s3 archive, it needs to be configured in the environment if this item is not configured.</td></tr></tbody></table><h2 class="anchor anchorWithStickyNavbar_LWe7" id="usage">Usage<a href="#usage" class="hash-link" aria-label="Direct link to Usage" title="Direct link to Usage"></a></h2><p>One example about sync Kafka data to Kafka data and we will introduce usage of dirty data archive(it is similar to other nodes).</p><ul><li>The useage for archive to log</li></ul><div class="language-sql codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#F8F8F2;--prism-background-color:#282A36"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-sql codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#F8F8F2"><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">create</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">table</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_input</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> STRING</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">WITH</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;log&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.ignore&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.enable&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;csv&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SYSTEM_TIME=${SYSTEM_TIME}&amp;DIRTY_TYPE=${DIRTY_TYPE}&amp;database=inlong&amp;table=user&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;inlong.metric.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;groupId=1&amp;streamId=1&amp;nodeId=1&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;topic&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;user_input&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.bootstrap.servers&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;localhost:9092&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;kafka-inlong&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;scan.startup.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;earliest-offset&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.timestamp-format.standard&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SQL&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.encode.decimal-as-plain-number&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.literal&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;null&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.ignore-parse-errors&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;false&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;DROP&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.fail-on-missing-field&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;false&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.group.id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;test_group&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></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"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">CREATE</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">TABLE</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_output</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> STRING</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">WITH</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;topic&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;user_output&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.bootstrap.servers&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;localhost:9092&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;kafka-inlong&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;sink.ignore.changelog&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.timestamp-format.standard&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SQL&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.encode.decimal-as-plain-number&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.literal&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;null&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.ignore-parse-errors&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;DROP&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.fail-on-missing-field&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.ignore&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;log&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.enable&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;csv&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.log.enable&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.log-tag&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;DirtyData&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SYSTEM_TIME=${SYSTEM_TIME}&amp;DIRTY_TYPE=${DIRTY_TYPE}&amp;database=inlong&amp;table=user&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></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"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INSERT</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INTO</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_output</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">SELECT</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">FROM</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_input</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token comment" style="color:rgb(98, 114, 164)">-- In this example, we deliberately input a piece of data in non-json format, such as: 1,zhangsan,18, then the following dirty data will be printed in the log according to the configuration:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token punctuation" style="color:rgb(248, 248, 242)">[</span><span class="token plain">DirtyData</span><span class="token punctuation" style="color:rgb(248, 248, 242)">]</span><span class="token plain"> </span><span class="token number">2023</span><span class="token operator">-</span><span class="token number">01</span><span class="token operator">-</span><span class="token number">30</span><span class="token plain"> </span><span class="token number">13</span><span class="token plain">:</span><span class="token number">01</span><span class="token plain">:</span><span class="token number">01</span><span class="token plain"> ValueDeserializeError</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain">inlong</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">user</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token number">1</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain">zhangsan</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token number">18</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg class="copyButtonIcon_y97N" viewBox="0 0 24 24"><path d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg class="copyButtonSuccessIcon_LjdS" viewBox="0 0 24 24"><path d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div><ul><li>The useage for archive to s3</li></ul><div class="language-sql codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#F8F8F2;--prism-background-color:#282A36"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-sql codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#F8F8F2"><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">create</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">table</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_input</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> STRING</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">WITH</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.ignore&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.enable&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;csv&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SYSTEM_TIME=${SYSTEM_TIME}&amp;DIRTY_TYPE=${DIRTY_TYPE}&amp;database=inlong&amp;table=user&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.bucket&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3-test-bucket&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.endpoint&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3.test.endpoint&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.key&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty/test&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.region&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;region&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.access-key-id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;access_key_id&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.secret-key-id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;secret_key_id&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.identifier&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;inlong-user-${SYSTEM_TIME}&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;inlong.metric.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;groupId=1&amp;streamId=1&amp;nodeId=1&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;topic&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;user_input&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.bootstrap.servers&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;localhost:9092&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;kafka-inlong&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;scan.startup.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;earliest-offset&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.timestamp-format.standard&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SQL&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.encode.decimal-as-plain-number&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.literal&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;null&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.ignore-parse-errors&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;false&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;DROP&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.fail-on-missing-field&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;false&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.group.id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;test_group&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></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"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">CREATE</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">TABLE</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_output</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> STRING</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INT</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">WITH</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(248, 248, 242)">(</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;topic&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;user_output&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;properties.bootstrap.servers&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;localhost:9092&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;kafka-inlong&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;sink.ignore.changelog&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.timestamp-format.standard&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SQL&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.encode.decimal-as-plain-number&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.literal&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;null&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.ignore-parse-errors&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.map-null-key.mode&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;DROP&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;json.fail-on-missing-field&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.connector&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.ignore&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.enable&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;true&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.format&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;csv&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.labels&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;SYSTEM_TIME=${SYSTEM_TIME}&amp;DIRTY_TYPE=${DIRTY_TYPE}&amp;database=inlong&amp;table=user&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.bucket&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3-test-bucket&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.endpoint&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;s3.test.endpoint&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.key&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty/test&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.region&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;region&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.access-key-id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;access_key_id&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.side-output.s3.secret-key-id&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;secret_key_id&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;dirty.identifier&#x27;</span><span class="token plain"> </span><span class="token operator">=</span><span class="token plain"> </span><span class="token string" style="color:rgb(255, 121, 198)">&#x27;inlong-user-${SYSTEM_TIME}&#x27;</span><span class="token punctuation" style="color:rgb(248, 248, 242)">)</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></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"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INSERT</span><span class="token plain"> </span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">INTO</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_output</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">SELECT</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">id</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">name</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">age</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">FROM</span><span class="token plain"> </span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token identifier">table_user_input</span><span class="token identifier punctuation" style="color:rgb(248, 248, 242)">`</span><span class="token punctuation" style="color:rgb(248, 248, 242)">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token comment" style="color:rgb(98, 114, 164)">-- In this example, we deliberately input a piece of data in non-json format, such as: 1,zhangsan,18, then the following dirty data will be written to s3 according to the configuration(the file path is: dirty/test/inlong-user-2023-01-01130101xxxx.txt, where xxxx is a 4-digit random sequence):</span><span class="token plain"></span><br></span><span class="token-line" style="color:#F8F8F2"><span class="token plain"></span><span class="token punctuation" style="color:rgb(248, 248, 242)">[</span><span class="token plain">DirtyData</span><span class="token punctuation" style="color:rgb(248, 248, 242)">]</span><span class="token plain"> </span><span class="token number">2023</span><span class="token operator">-</span><span class="token number">01</span><span class="token operator">-</span><span class="token number">30</span><span class="token plain"> </span><span class="token number">13</span><span class="token plain">:</span><span class="token number">01</span><span class="token plain">:</span><span class="token number">01</span><span class="token plain"> ValueDeserializeError</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain">inlong</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token keyword" style="color:rgb(189, 147, 249);font-style:italic">user</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token number">1</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token plain">zhangsan</span><span class="token punctuation" style="color:rgb(248, 248, 242)">,</span><span class="token number">18</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg class="copyButtonIcon_y97N" viewBox="0 0 24 24"><path d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg class="copyButtonSuccessIcon_LjdS" viewBox="0 0 24 24"><path d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></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/inlong-website/edit/master/versioned_docs/version-1.10.0/modules/sort/dirty_data_archive.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_Z9Sw" 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_vwxv"></div></div></footer></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages navigation"><a class="pagination-nav__link pagination-nav__link--prev" href="/docs/1.10.0/modules/sort/metrics"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Monitor Metrics</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/docs/1.10.0/modules/manager/overview"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Overview</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#overview" class="table-of-contents__link toc-highlight">Overview</a></li><li><a href="#supported-nodes" class="table-of-contents__link toc-highlight">Supported Nodes</a></li><li><a href="#dirty-data-format" class="table-of-contents__link toc-highlight">Dirty Data Format</a></li><li><a href="#configuration" class="table-of-contents__link toc-highlight">Configuration</a><ul><li><a href="#common-configuration" class="table-of-contents__link toc-highlight">Common Configuration</a></li><li><a href="#s3-archive-configuration" class="table-of-contents__link toc-highlight">S3 Archive Configuration</a></li></ul></li><li><a href="#usage" class="table-of-contents__link toc-highlight">Usage</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">Events</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://www.apachecon.com/" target="_blank" rel="noopener noreferrer" class="footer__link-item">ApacheCon<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><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></a></li><li class="footer__item"><a class="acevent" data-format="square" data-mode="dark" data-event="random"></a></li></ul></div><div class="col footer__col"><div class="footer__title">Community</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://twitter.com/ApacheInlong" target="_blank" rel="noopener noreferrer" class="footer__link-item">Twitter<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><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></a></li><li class="footer__item"><a href="https://inlong.apache.org/img/apache-inlong-wechat.jpg" target="_blank" rel="noopener noreferrer" class="footer__link-item">WeChat<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><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></a></li><li class="footer__item"><a href="mailto:dev@inlong.apache.org" target="_blank" rel="noopener noreferrer" class="footer__link-item">Email</a></li></ul></div><div class="col footer__col"><div class="footer__title">More</div><ul class="footer__items clean-list"><li class="footer__item"><a class="footer__link-item" href="/blog">Blog</a></li><li class="footer__item"><a href="https://github.com/apache/inlong" target="_blank" rel="noopener noreferrer" class="footer__link-item">GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><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></a></li></ul></div></div><div class="footer__bottom text--center"><div class="margin-bottom--sm"><img src="/img/asf_logo.svg" alt="Apache InLong" class="themedImage_ToTc themedImage--light_HNdA footer__logo"><img src="/img/asf_logo.svg" alt="Apache InLong" class="themedImage_ToTc themedImage--dark_i4oU footer__logo"></div><div class="footer__copyright"><div style="font-family: Avenir-Medium;font-size: 14px;color: #999;">
<div>Copyright © 2020-2024 The Apache Software Foundation. Licensed under the Apache License, Version 2.0.</div>
<div style="margin-top: 20px; padding-top: 20px; border-top: 1px solid #666;line-height: 20px;">The Apache Software Foundation Apache InLong, InLong, Apache, the Apache feather, and the Apache InLong project logo are either registered trademarks or trademarks of the Apache Software Foundation.</div>
</div></div></div></div></footer></div>
<script src="/assets/js/runtime~main.63c98e82.js"></script>
<script src="/assets/js/main.070aef2a.js"></script>
</body>
</html>