mirror of
https://github.com/datahub-project/datahub.git
synced 2025-07-26 02:50:01 +00:00
141 lines
148 KiB
HTML
141 lines
148 KiB
HTML
![]() |
<!doctype html>
|
|||
|
<html lang="en" dir="ltr" class="docs-wrapper docs-doc-page docs-version-current plugin-docs plugin-id-default docs-doc-id-docs/assertions/open-assertions-spec" data-has-hydrated="false">
|
|||
|
<head>
|
|||
|
<meta charset="UTF-8">
|
|||
|
<meta name="generator" content="Docusaurus v2.4.3">
|
|||
|
<title data-rh="true">DataHub Open Data Quality Assertions Specification | DataHub</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://docs.datahub.com/docs/assertions/open-assertions-spec"><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="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="DataHub Open Data Quality Assertions Specification | DataHub"><meta data-rh="true" name="description" content="DataHub is developing an open-source Data Quality Assertions Specification & Compiler that will allow you to declare data quality checks / expectations / assertions using a simple, universal"><meta data-rh="true" property="og:description" content="DataHub is developing an open-source Data Quality Assertions Specification & Compiler that will allow you to declare data quality checks / expectations / assertions using a simple, universal"><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.datahub.com/docs/assertions/open-assertions-spec"><link data-rh="true" rel="alternate" href="https://docs.datahub.com/docs/assertions/open-assertions-spec" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.datahub.com/docs/assertions/open-assertions-spec" hreflang="x-default"><link data-rh="true" rel="preconnect" href="https://RK0UG797F3-dsn.algolia.net" crossorigin="anonymous"><link rel="alternate" type="application/rss+xml" href="/learn/rss.xml" title="DataHub RSS Feed">
|
|||
|
<link rel="alternate" type="application/atom+xml" href="/learn/atom.xml" title="DataHub Atom Feed">
|
|||
|
|
|||
|
<link rel="preconnect" href="https://www.google-analytics.com">
|
|||
|
<link rel="preconnect" href="https://www.googletagmanager.com">
|
|||
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-PKGVLETT4C"></script>
|
|||
|
<script>function gtag(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],gtag("js",new Date),gtag("config","G-PKGVLETT4C",{})</script>
|
|||
|
<link rel="preconnect" href="https://www.googletagmanager.com">
|
|||
|
<script>window.dataLayer=window.dataLayer||[]</script>
|
|||
|
<script>!function(e,t,a,n,g){e[n]=e[n]||[],e[n].push({"gtm.start":(new Date).getTime(),event:"gtm.js"});var m=t.getElementsByTagName(a)[0],r=t.createElement(a);r.async=!0,r.src="https://www.googletagmanager.com/gtm.js?id=GTM-5M8T9HNN",m.parentNode.insertBefore(r,m)}(window,document,"script","dataLayer")</script>
|
|||
|
|
|||
|
|
|||
|
<link rel="search" type="application/opensearchdescription+xml" title="DataHub" href="/opensearch.xml">
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<meta httpequiv="Content-Security-Policy" content="frame-ancestors 'self' https://*.acryl.io https://acryldata.io http://localhost:*">
|
|||
|
<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Manrope:wght@400;500;700&display=swap">
|
|||
|
<script src="https://tools.luckyorange.com/core/lo.js?site-id=28ea8a38" async defer="defer"></script>
|
|||
|
<script src="/scripts/rb2b.js" async defer="defer"></script>
|
|||
|
<script src="https://app.revenuehero.io/scheduler.min.js"></script>
|
|||
|
<script src="https://tag.clearbitscripts.com/v1/pk_2e321cabe30432a5c44c0424781aa35f/tags.js" referrerpolicy="strict-origin-when-cross-origin"></script>
|
|||
|
<script src="/scripts/reo.js"></script>
|
|||
|
<script id="runllm-widget-script" type="module" src="https://widget.runllm.com" crossorigin="true" runllm-name="DataHub" runllm-assistant-id="81" runllm-position="BOTTOM_RIGHT" runllm-keyboard-shortcut="Mod+j" runllm-preset="docusaurus" runllm-theme-color="#1890FF" runllm-brand-logo="https://docs.datahub.com/img/datahub-logo-color-mark.svg" runllm-community-url="https://datahub.com/slack" runllm-community-type="slack" runllm-disable-ask-a-person="true" async></script><link rel="stylesheet" href="/assets/css/styles.d8fe2eb8.css">
|
|||
|
<link rel="preload" href="/assets/js/runtime~main.310f59c4.js" as="script">
|
|||
|
<link rel="preload" href="/assets/js/main.49198d73.js" as="script">
|
|||
|
</head>
|
|||
|
<body class="navigation-with-keyboard">
|
|||
|
<noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5M8T9HNN" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
|
|||
|
|
|||
|
<script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){var t=null;try{t=new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}return t}()||function(){var t=null;try{t=localStorage.getItem("theme")}catch(t){}return t}();t(null!==e?e:"light")}(),document.documentElement.setAttribute("data-announcement-bar-initially-dismissed",function(){try{return"true"===localStorage.getItem("docusaurus.announcement.dismiss")}catch(t){}return!1}())</script><div id="__docusaurus">
|
|||
|
<div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><div class="announcementBar_mb4j" style="background-color:transparent;color:#ffffff" role="banner"><div class="content_knG7 announcementBarContent_xLdY"><div class="shimmer-banner"><p>DataHub Secures $35 Million Series B</p><a href="https://datahub.com/news/series-b-announcement/" target="_blank" class="button"><div>Read the announcement<span> →</span></div></a></div></div></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 href="https://datahub.com" target="_blank" rel="noopener noreferrer" class="navbar__brand"><div class="navbar__logo"><img src="/img/datahub-logo-color-light-horizontal.svg" alt="DataHub Logo" class="themedImage_ToTc themedImage--light_HNdA"><img src="/img/datahub-logo-color-dark-horizontal.svg" alt="DataHub Logo" class="themedImage_ToTc themedImage--dark_i4oU"></div></a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link versionNavItem_cbn8">Next</a><ul class="dropdown__menu"><li><a aria-current="page" class="dropdown__link dropdown__link--active" href="/docs/assertions/open-assertions-spec">Next</a></li><li><a class="dropdown__link" href="/docs/1.1.0/assertions/open-assertions-spec">1.1.0</a></li><li><hr class="dropdown-separator" style="margin: 0.4rem;"></li><li><div class="dropdown__link"><b>Archived versions</b></div></li><li>
|
|||
|
<a class="dropdown__link" href="https://docs-website-t9sv4w3gr-acryldata.vercel.app/docs/features">1.0.0
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-t9sv4w3gr-acryldata.vercel.app/docs/0.15.0/features">0.15.0
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-8jkm4uler-acryldata.vercel.app/docs/0.14.1/features">0.14.1
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-eue2qafvn-acryldata.vercel.app/docs/features">0.14.0
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-psat3nzgi-acryldata.vercel.app/docs/features">0.13.1
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-lzxh86531-acryldata.vercel.app/docs/features">0.13.0
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-2uuxmgza2-acryldata.vercel.app/docs/features">0.12.1
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-irpoe2osc-acryldata.vercel.app/docs/features">0.11.0
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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>
|
|||
|
<a class="dropdown__link" href="https://docs-website-1gv2yzn9d-acryldata.vercel.app/docs/features">0.10.5
|
|||
|
<svg width="12" height="12" aria-hidden="true" viewBox="0 0 24 24"><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="navbar__items navbar__items--right"><a aria-current="page" class="navbar__item navbar__link navbar__link--active" href="/docs">Docs</a><a class="navbar__item navbar__link" href="/integrations">Integrations</a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link">Learn</a><ul class="dropdown__menu dropdown__menu_Z8FC"><div class="wrapper_kp81"><div><a href="https://datahub.com/weekly-demo" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-join-slack.png" alt="Weekly Demo"></div><div class="title_c7DP">Weekly Demo</div></a></div><div><a href="https://datahub.com/use-cases" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-forum.png" alt="Use Cases"></div><div class="title_c7DP">Use Cases</div></a></div><div><a href="httpps://datahub.com/adoption-stories" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-events.png" alt="Adoption Stories"></div><div class="title_c7DP">Adoption Stories</div></a></div><div><a href="https://medium.com/datahub-project" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-champions.png" alt="Blog"></div><div class="title_c7DP">Blog</div></a></div><div><a href="https://www.youtube.com/channel/UC3qFQC5IiwR5fvWEqi_tJ5w" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-share-your-journey.png" alt="Youtube"></div><div class="title_c7DP">Youtube</div></a></div></div></ul></div><div class="navbar__item dropdown dropdown--hoverable"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link">Community</a><ul class="dropdown__menu dropdown__menu_Z8FC"><div class="wrapper_kp81"><div><a href="https://datahub.com/slack/" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-join-slack.png" alt="Join Slack"></div><div class="title_c7DP">Join Slack</div></a></div><div><a href="https://datahub.com/events" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-events.png" alt="Events"></div><div class="title_c7DP">Events</div></a></div><div><a href="https://datahub.com/champions/" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-champions.png" alt="Champions"></div><div class="title_c7DP">Champions</div></a></div><div><a href="https://datahub.com/share-your-journey/" target="_blank" rel="noopener noreferrer" class="card_BUD7"><div class="icon_BgHd"><img src="/img/icon-share-your-journey.png" alt="Share Your Journey"></div><div class="title_c7DP">Share Your Journey</div></a></div></div></ul></div><a href="https://datahub.com/products/why-datahub-cloud/" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">
|
|||
|
<style>
|
|||
|
.cloud-cta {
|
|||
|
color: var(--ifm-menu-color-active);
|
|||
|
font-weight: 600;
|
|||
|
background: linear-gradient(40deg, var(--ifm-menu-color-active), var(--ifm-menu-color-active));
|
|||
|
background-size: 200% 100%;
|
|||
|
-webkit-background-clip: text;
|
|||
|
background-clip: text;
|
|||
|
transition: background-image 0.3s ease;
|
|||
|
}
|
|||
|
.cloud-cta:hover {
|
|||
|
color: transparent;
|
|||
|
background: linear-gradient(40deg, var(--ifm-menu-color-active), #ff1493);
|
|||
|
background-size: 200% 100%;
|
|||
|
-webkit-background-clip: text;
|
|||
|
background-clip: text;
|
|||
|
animation: gradientShift 3s ease infinite;
|
|||
|
}
|
|||
|
@keyframes gradientShift {
|
|||
|
0%, 100% { background-position: 0% 50%; }
|
|||
|
50% { background-position: 100% 50%; }
|
|||
|
}
|
|||
|
</style>
|
|||
|
<div class="cloud-cta">Get Cloud</div>
|
|||
|
</a><a href="https://datahub.com/slack?utm_source=docs&utm_medium=header&utm_campaign=docs_header" target="_blank" rel="noopener noreferrer" class="navbar__item navbar__link">
|
|||
|
<style>
|
|||
|
.slack-logo:hover {
|
|||
|
opacity: 0.8;
|
|||
|
}
|
|||
|
</style>
|
|||
|
<img class="slack-logo" src="https://upload.wikimedia.org/wikipedia/commons/d/d5/Slack_icon_2019.svg" , alt="slack" , height="20px" style="margin: 10px 0 0 0;">
|
|||
|
</a><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" aria-hidden="true"><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 menuWithAnnouncementBar_GW3s"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menuHtmlItem_M9Kj menu__list-item"><div>Getting Started</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" aria-expanded="false" href="/docs/features">What Is DataHub?</a><button aria-label="Toggle the collapsible sidebar category 'What Is DataHub?'" type="button" class="clean-btn menu__caret"></button></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--active" aria-expanded="true" href="/docs/category/features">Features</a><button aria-label="Toggle the collapsible sidebar category 'Features'" type="button" class="clean-btn menu__caret"></button></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"><div class="menu__list-item-collapsible"><a class="menu__link menu__link--sublist menu__link--active" aria-expanded="true" tabindex="0" href="/docs/managed-datahub/observe/assertions">Assertions (Data Quality)</a><button aria-label="Toggle the collapsible sidebar category 'Assertions (Data Quality)'" type="button" class="clean-btn menu__caret"></button></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 saasOnly"><a class="menu__link" tabindex="0" href="/docs/managed-datahub/observe/column-assertions">Column Assertions</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item saasOnly"><a class="menu__link" tabindex="0" href="/docs/managed-datahub/observe/custom-sql-assertions">Custom SQL Assertions</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item saasOnly"><a class="menu__link" tabindex="0" href="/docs/managed-datahub/observe/freshness-assertions">Freshness Assertions</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item saasOnly"><a class="menu__link" tabindex="0" href="/docs/managed-datahub/observe/schema-assertions">Schema Assertions</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item saasOnly"><a class="menu__link" tabindex="0" href="/docs/managed-datahub/observe/volume-assertions">Volume Assertions</a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item saa
|
|||
|
YAML-based format, and then compile this into artifacts that can be registered or directly executed by 3rd party Data Quality tools like <a href="https://docs.snowflake.com/en/user-guide/data-quality-intro" target="_blank" rel="noopener noreferrer">Snowflake DMFs</a>,
|
|||
|
dbt tests, Great Expectations or DataHub Cloud natively.</p><p>Ultimately, our goal is to provide an framework-agnostic, highly-portable format for defining Data Quality checks, making it seamless to swap out the underlying
|
|||
|
assertion engine without service disruption for end consumers of the results of these data quality checks in catalogging tools like DataHub.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="integrations">Integrations<a href="#integrations" class="hash-link" aria-label="Direct link to Integrations" title="Direct link to Integrations"></a></h2><p>Currently, the DataHub Open Assertions Specification supports the following integrations:</p><ul><li><a href="/docs/assertions/snowflake/snowflake_dmfs">Snowflake DMF Assertions</a></li></ul><p>And is looking for contributions to build out support for the following integrations:</p><ul><li>[Looking for Contributions]<!-- --> dbt tests</li><li>[Looking for Contributions]<!-- --> Great Expectation checks</li></ul><p>Below, we'll look at how to define assertions in YAML, and then provide an usage overview for each support integration.</p><h2 class="anchor anchorWithStickyNavbar_LWe7" id="the-specification-declaring-data-quality-assertions-in-yaml">The Specification: Declaring Data Quality Assertions in YAML<a href="#the-specification-declaring-data-quality-assertions-in-yaml" class="hash-link" aria-label="Direct link to The Specification: Declaring Data Quality Assertions in YAML" title="Direct link to The Specification: Declaring Data Quality Assertions in YAML"></a></h2><p>The following assertion types are currently supported by the DataHub YAML Assertion spec:</p><ul><li><a href="/docs/managed-datahub/observe/freshness-assertions">Freshness</a></li><li><a href="/docs/managed-datahub/observe/volume-assertions">Volume</a></li><li><a href="/docs/managed-datahub/observe/column-assertions">Column</a></li><li><a href="/docs/managed-datahub/observe/custom-sql-assertions">Custom SQL</a></li><li><a href="/docs/managed-datahub/observe/schema-assertions">Schema</a></li></ul><p>Each assertion type aims to validate a different aspect of structured table (e.g. on a data warehouse or data lake), from
|
|||
|
structure to size to column integrity to custom metrics.</p><p>In this section, we'll go over examples of defining each.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="freshness-assertions">Freshness Assertions<a href="#freshness-assertions" class="hash-link" aria-label="Direct link to Freshness Assertions" title="Direct link to Freshness Assertions"></a></h3><p>Freshness Assertions allow you to verify that your data was updated within the expected timeframe.
|
|||
|
Below you'll find examples of defining different types of freshness assertions via YAML.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="validating-that-table-is-updated-every-6-hours">Validating that Table is Updated Every 6 Hours<a href="#validating-that-table-is-updated-every-6-hours" class="hash-link" aria-label="Direct link to Validating that Table is Updated Every 6 Hours" title="Direct link to Validating that Table is Updated Every 6 Hours"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> freshness</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">lookback_interval</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"6 hours"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">last_modified_field</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> updated_at</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">schedule</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> interval</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key at
|
|||
|
by issuing a Query to the table which validates determines whether an update was made using the <code>updated_at</code> column in the past 6 hours.
|
|||
|
To use this check, we must specify the field that contains the last modified timestamp of a given row.</p><p>The <code>lookback_interval</code> field is used to specify the "lookback window" for the assertion, whereas the <code>schedule</code> field is used to specify how often the assertion should be run.
|
|||
|
This allows you to schedule the assertion to run at a different frequency than the lookback window, for example
|
|||
|
to detect stale data as soon as it becomes "stale" by inspecting it more frequently.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="supported-source-types">Supported Source Types<a href="#supported-source-types" class="hash-link" aria-label="Direct link to Supported Source Types" title="Direct link to Supported Source Types"></a></h4><p>Currently, the only supported <code>sourceType</code> for Freshness Assertions is <code>LAST_MODIFIED_FIELD</code>. In the future,
|
|||
|
we may support additional source types, such as <code>HIGH_WATERMARK</code>, along with data source-specific types such as
|
|||
|
<code>AUDIT_LOG</code> and <code>INFORMATION_SCHEMA</code>.</p><h3 class="anchor anchorWithStickyNavbar_LWe7" id="volume-assertions">Volume Assertions<a href="#volume-assertions" class="hash-link" aria-label="Direct link to Volume Assertions" title="Direct link to Volume Assertions"></a></h3><p>Volume Assertions allow you to verify that the number of records in your dataset meets your expectations.
|
|||
|
Below you'll find examples of defining different types of volume assertions via YAML.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="validating-that-tale-row-count-is-in-expected-range">Validating that Tale Row Count is in Expected Range<a href="#validating-that-tale-row-count-is-in-expected-range" class="hash-link" aria-label="Direct link to Validating that Tale Row Count is in Expected Range" title="Direct link to Validating that Tale Row Count is in Expected Range"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> volume</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">metric</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"row_count"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> between</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">min</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1000</span><span class="token plain"></span><br></span><span class="token-li
|
|||
|
Using the <code>condition</code> field, you can specify the type of comparison to be made, and the <code>min</code> and <code>max</code> fields to specify the range of values to compare against.
|
|||
|
Using the <code>filters</code> field, you can optionally specify a SQL WHERE clause to filter the records being counted.
|
|||
|
Using the <code>schedule</code> field you can specify when the assertion should be run, either on a fixed schedule or when new data is added to the table.
|
|||
|
The only metric currently supported is <code>row_count</code>.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="validating-that-table-row-count-is-less-than-value">Validating that Table Row Count is Less Than Value<a href="#validating-that-table-row-count-is-less-than-value" class="hash-link" aria-label="Direct link to Validating that Table Row Count is Less Than Value" title="Direct link to Validating that Table Row Count is Less Than Value"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> volume</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">metric</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token string" style="color:rgb(195, 232, 141)">"row_count"</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> less_than_or_equal_to</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">value</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1000</span><span class="token plain"></span><br></span><span class="token-line" style="color:
|
|||
|
Below you'll find examples of defining different types of column assertions via YAML.</p><p>The specification currently supports 2 types of Column Assertions:</p><ul><li><strong>Field Value</strong>: Asserts that the values in a column meet a specific condition.</li><li><strong>Field Metric</strong>: Asserts that a specific metric aggregated across the values in a column meet a specific condition.</li></ul><p>We'll go over examples of each below.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="field-values-assertion-validating-that-all-column-values-are-in-expected-range">Field Values Assertion: Validating that All Column Values are In Expected Range<a href="#field-values-assertion-validating-that-all-column-values-are-in-expected-range" class="hash-link" aria-label="Direct link to Field Values Assertion: Validating that All Column Values are In Expected Range" title="Direct link to Field Values Assertion: Validating that All Column Values are In Expected Range"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> field</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">field</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> amount</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> betw
|
|||
|
Using the <code>field</code> field, you can specify the column to be asserted on, and using the <code>condition</code> field, you can specify the type of comparison to be made,
|
|||
|
and the <code>min</code> and <code>max</code> fields to specify the range of values to compare against.
|
|||
|
Using the <code>schedule</code> field you can specify when the assertion should be run, either on a fixed schedule or when new data is added to the table.
|
|||
|
Using the <code>filters</code> field, you can optionally specify a SQL WHERE clause to filter the records being counted.
|
|||
|
Using the <code>exclude_nulls</code> field, you can specify whether to exclude NULL values from the assertion, meaning that
|
|||
|
NULL will simply be ignored if encountered, as opposed to failing the check.
|
|||
|
Using the <code>failure_threshold</code>, we can set a threshold for the number of rows that can fail the assertion before the assertion is considered failed.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="field-values-assertion-validating-that-all-column-values-are-in-expected-set">Field Values Assertion: Validating that All Column Values are In Expected Set<a href="#field-values-assertion-validating-that-all-column-values-are-in-expected-set" class="hash-link" aria-label="Direct link to Field Values Assertion: Validating that All Column Values are In Expected Set" title="Direct link to Field Values Assertion: Validating that All Column Values are In Expected Set"></a></h4><p>The validate a VARCHAR / STRING column that should contain one of a set of values:</p><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> field</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">field</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> product_id</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> in</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">value</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><
|
|||
|
has no duplicates, by checking that the unique percentage is 100%.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="field-metric-assertion-validating-string-column-is-never-empty-string">Field Metric Assertion: Validating String Column is Never Empty String<a href="#field-metric-assertion-validating-string-column-is-never-empty-string" class="hash-link" aria-label="Direct link to Field Metric Assertion: Validating String Column is Never Empty String" title="Direct link to Field Metric Assertion: Validating String Column is Never Empty String"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> field</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">field</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> name</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">metric</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> empty_percentage</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> equal_to</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">value</span><span class="token punctuati
|
|||
|
The only condition is that the SQL query must return a single value, which will be compared against the expected value.
|
|||
|
Below you'll find examples of defining different types of custom SQL assertions via YAML.</p><p>SQL Assertions are useful for more complex data quality checks that can't be easily expressed using the other assertion types,
|
|||
|
and can be used to assert on custom metrics, complex aggregations, cross-table integrity checks (JOINS) or any other SQL-based data quality check.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="validating-foreign-key-integrity">Validating Foreign Key Integrity<a href="#validating-foreign-key-integrity" class="hash-link" aria-label="Direct link to Validating Foreign Key Integrity" title="Direct link to Validating Foreign Key Integrity"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> sql</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">statement</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">|</span><span class="token scalar string" style="color:rgb(195, 232, 141)"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token scalar string" style="color:rgb(195, 232, 141)"> SELECT COUNT(*)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token scalar string" style="color:rgb(195, 232, 141)"> FROM test_db.public.purchase_events AS pe</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token scalar string" style="color:rgb(195, 232, 141)"> LEFT JOIN test_db.public.products AS p</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token scalar string" style="color:rgb(195, 232, 141)"> ON pe.product_id = p.id</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token scalar string" style="color:rgb(195, 232, 141)"> WHERE p.id IS NULL</span><span class="token plain"></span><br></span><span class="token-line" s
|
|||
|
by subtracting the row count of the raw table from the row count of the processed table.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="supported-conditions-1">Supported Conditions<a href="#supported-conditions-1" class="hash-link" aria-label="Direct link to Supported Conditions" title="Direct link to Supported Conditions"></a></h4><p>The full set of supported custom SQL assertion conditions include:</p><ul><li><code>equal_to</code></li><li><code>not_equal_to</code></li><li><code>greater_than</code></li><li><code>greater_than_or_equal_to</code></li><li><code>less_than</code></li><li><code>less_than_or_equal_to</code></li><li><code>between</code></li></ul><h3 class="anchor anchorWithStickyNavbar_LWe7" id="schema-assertions-coming-soon">Schema Assertions (Coming Soon)<a href="#schema-assertions-coming-soon" class="hash-link" aria-label="Direct link to Schema Assertions (Coming Soon)" title="Direct link to Schema Assertions (Coming Soon)"></a></h3><p>Schema Assertions allow you to define custom SQL queries to verify your data meets your expectations.
|
|||
|
Below you'll find examples of defining different types of custom SQL assertions via YAML.</p><p>The specification currently supports 2 types of Schema Assertions:</p><ul><li><strong>Exact Match</strong>: Asserts that the schema of a table - column names and their data types - exactly matches an expected schema</li><li><strong>Contains Match</strong> (Subset): Asserts that the schema of a table - column names and their data types - is a subset of an expected schema</li></ul><h4 class="anchor anchorWithStickyNavbar_LWe7" id="validating-actual-schema-exactly-equals-expected-schema">Validating Actual Schema Exactly Equals Expected Schema<a href="#validating-actual-schema-exactly-equals-expected-schema" class="hash-link" aria-label="Direct link to Validating Actual Schema Exactly Equals Expected Schema" title="Direct link to Validating Actual Schema Exactly Equals Expected Schema"></a></h4><div class="language-yaml codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#bfc7d5;--prism-background-color:#292d3e"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-yaml codeBlock_bY9V thin-scrollbar"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#bfc7d5"><span class="token key atrule">version</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> </span><span class="token number" style="color:rgb(247, 140, 108)">1</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"></span><span class="token key atrule">assertions</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token punctuation" style="color:rgb(199, 146, 234)">-</span><span class="token plain"> </span><span class="token key atrule">entity</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataset</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">(urn</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">li</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">dataPlatform</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain">snowflake</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">test_db.public.purchase_events</span><span class="token punctuation" style="color:rgb(199, 146, 234)">,</span><span class="token plain">PROD)</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> schema</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">condition</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">type</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"> exact_match</span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain"> </span><span class="token key atrule">columns</span><span class="token punctuation" style="color:rgb(199, 146, 234)">:</span><span class="token plain"></span><br></span><span class="token-line" style="color:#bfc7d5"><span class="token plain">
|
|||
|
The actual schema can also contain additional columns not specified in the expected schema.</p><h4 class="anchor anchorWithStickyNavbar_LWe7" id="supported-data-types">Supported Data Types<a href="#supported-data-types" class="hash-link" aria-label="Direct link to Supported Data Types" title="Direct link to Supported Data Types"></a></h4><p>The following high-level data types are currently supported by the Schema Assertion spec:</p><ul><li>string</li><li>number</li><li>boolean</li><li>date</li><li>timestamp</li><li>struct</li><li>array</li><li>map</li><li>union</li><li>bytes</li><li>enum</li></ul></div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="slackUtm_uoBr"><div class="slackUtm_uoBr"><hr>Need more help? Join the conversation in <a href="https://datahub.com/slack?utm_source=docs&utm_medium=footer&utm_campaign=docs_footer&utm_content=docs/assertions/open-assertions-spec">Slack!</a></div></div><div class="theme-doc-footer-edit-meta-row row"><div class="col"><a href="https://github.com/datahub-project/datahub/blob/master/docs/assertions/open-assertions-spec.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_VsjB"></div></div></footer><div class="feedbackWrapper_mUHF"><div class="feedbackWidget_PX4d"><div class="feedbackButtons_wn3V"><strong>Is this page helpful?</strong><div><button class="feedbackButton_UgQs"><span role="img" aria-label="like" class="anticon anticon-like"><svg viewBox="64 64 896 896" focusable="false" data-icon="like" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M885.9 533.7c16.8-22.2 26.1-49.4 26.1-77.7 0-44.9-25.1-87.4-65.5-111.1a67.67 67.67 0 00-34.3-9.3H572.4l6-122.9c1.4-29.7-9.1-57.9-29.5-79.4A106.62 106.62 0 00471 99.9c-52 0-98 35-111.8 85.1l-85.9 311H144c-17.7 0-32 14.3-32 32v364c0 17.7 14.3 32 32 32h601.3c9.2 0 18.2-1.8 26.5-5.4 47.6-20.3 78.3-66.8 78.3-118.4 0-12.6-1.8-25-5.4-37 16.8-22.2 26.1-49.4 26.1-77.7 0-12.6-1.8-25-5.4-37 16.8-22.2 26.1-49.4 26.1-77.7-.2-12.6-2-25.1-5.6-37.1zM184 852V568h81v284h-81zm636.4-353l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 16.5-7.2 32.2-19.6 43l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 16.5-7.2 32.2-19.6 43l-21.9 19 13.9 25.4a56.2 56.2 0 016.9 27.3c0 22.4-13.2 42.6-33.6 51.8H329V564.8l99.5-360.5a44.1 44.1 0 0142.2-32.3c7.6 0 15.1 2.2 21.1 6.7 9.9 7.4 15.2 18.6 14.6 30.5l-9.6 198.4h314.4C829 418.5 840 436.9 840 456c0 16.5-7.2 32.1-19.6 43z"></path></svg></span></button><button class="feedbackButton_UgQs"><span role="img" aria-label="dislike" class="anticon anticon-dislike"><svg viewBox="64 64 896 896" focusable="false" data-icon="dislike" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M885.9 490.3c3.6-12 5.4-24.4 5.4-37 0-28.3-9.3-55.5-26.1-77.7 3.6-12 5.4-24.4 5.4-37 0-28.3-9.3-55.5-26.1-77.7 3.6-12 5.4-24.4 5.4-37 0-51.6-30.7-98.1-78.3-118.4a66.1 66.1 0 00-26.5-5.4H144c-17.7 0-32 14.3-32 32v364c0 17.7 14.3 32 32 32h129.3l85.8 310.8C372.9 889 418.9 924 470.9 924c29.7 0 57.4-11.8 77.9-33.4 20.5-21.5 31-49.7 29.5-79.4l-6-122.9h239.9c12.1 0 23.9-3.2 34.3-9.3 40.4-23.5 65.5-66.1 65.5-111 0-28.3-9.3-55.5-26.1-77.7zM184 456V172h81v284h-81zm627.2 160.4H496.8l9.6 198.4c.6 11.9-4.7 23.1-14.6 30.5-6.1 4.5-13.6 6.8-21.1 6.7a44.28 44.28 0 01-42.2-32.3L329 459.2V172h415.4a56.85 56.85 0 0133.6 51.8c0 9.7-2.3 18.9-6.9 27.3l-13.9 25.4 21.9 19a56.76 56.76 0 0119.6 43c0 9.7-2.3 18.9-6.9 27.3l-13.9 25.4 21.9 19a56.76 56.76 0 0119.6 43c0 9.7-2.3 18.9-6.9 27.3l-14 25.5 21.9 19a56.76 56.76 0 0119.6 43c0 19.1-11 37.5-28.8 48.4z"></path></svg></span></button></div></div></div></div></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/docs/managed-datahub/
|
|||
|
<script src="/assets/js/runtime~main.310f59c4.js"></script>
|
|||
|
<script src="/assets/js/main.49198d73.js"></script>
|
|||
|
</body>
|
|||
|
</html>
|