bigquery-etl/index.html

1443 строки
27 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="description" content="Mozilla BigQuery ETL">
<meta name="author" content="Mozilla Data Platform Team">
<link rel="next" href="mozfun/about/">
<link rel="icon" href="favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.5.43">
<title>Home - BigQuery ETL</title>
<link rel="stylesheet" href="assets/stylesheets/main.0253249f.min.css">
<link rel="stylesheet" href="assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL(".",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="teal" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="." title="BigQuery ETL" class="md-header__button md-logo" aria-label="BigQuery ETL" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
BigQuery ETL
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Home
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/mozilla/bigquery-etl/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
mozilla/bigquery-etl
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item md-tabs__item--active">
<a href="." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="mozfun/about/" class="md-tabs__link">
UDFs
</a>
</li>
<li class="md-tabs__item">
<a href="cookbooks/common_workflows/" class="md-tabs__link">
Cookbooks
</a>
</li>
<li class="md-tabs__item">
<a href="bqetl/" class="md-tabs__link">
Reference
</a>
</li>
</ul>
</div>
</nav>
<!-- Additional styles for landing page -->
<style>
@media screen and (min-width: 900px) {
.tx-hero {
margin-top: 30px;
padding: 20px;
display: flex;
}
.tx-hero__content {
margin-top: 50px;
width: 40%;
}
}
@media screen and (max-width: 900px) {
.tx-hero__content {
margin: 10px;
padding: 10px;
text-align: center;
}
}
</style>
<!-- Hero for landing page -->
<section class="tx-container">
<div class="md-grid md-typeset">
<div class="tx-hero">
<!-- Hero image -->
<div class="tx-hero__image">
<img
src="illustration.png"
alt=""
width="800"
height="800"
draggable="false"
>
</div>
<!-- Hero content -->
<div class="tx-hero__content">
<h2>BigQuery ETL is Mozilla's framework for creating derived datasets and user-defined functions in BigQuery.</h2>
<p>At present, this site contains documentation for the Google Cloud Platform projects <code>mozdata</code> — the primary home for user analysis, and <code>mozfun</code> — the user-defined functions (UDFs) available in BigQuery.</p>
<p>It also contains <a href="cookbooks/creating_a_derived_dataset/">a tutorial on creating a <i>new</i> derived dataset</a>.</p>
<p>For information on how to set up this project for local development, refer to the <a
href="https://github.com/mozilla/bigquery-etl#quick-start"
>README</a>.</p>
</div>
</div>
</div>
</section>
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="." title="BigQuery ETL" class="md-nav__button md-logo" aria-label="BigQuery ETL" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
BigQuery ETL
</label>
<div class="md-nav__source">
<a href="https://github.com/mozilla/bigquery-etl/" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
mozilla/bigquery-etl
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<a href="." class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
UDFs
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
UDFs
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_1" >
<label class="md-nav__link" for="__nav_2_1" id="__nav_2_1_label" tabindex="0">
<span class="md-ellipsis">
Mozfun
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_2_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_1">
<span class="md-nav__icon md-icon"></span>
Mozfun
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="mozfun/about/" class="md-nav__link">
<span class="md-ellipsis">
mozfun
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/addons/" class="md-nav__link">
<span class="md-ellipsis">
Addons
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/assert/" class="md-nav__link">
<span class="md-ellipsis">
Assert
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/bits28/" class="md-nav__link">
<span class="md-ellipsis">
bits28
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/bytes/" class="md-nav__link">
<span class="md-ellipsis">
bytes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/event_analysis/" class="md-nav__link">
<span class="md-ellipsis">
event_analysis
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/ga/" class="md-nav__link">
<span class="md-ellipsis">
Ga
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/glam/" class="md-nav__link">
<span class="md-ellipsis">
Glam
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/glean/" class="md-nav__link">
<span class="md-ellipsis">
glean
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/google_ads/" class="md-nav__link">
<span class="md-ellipsis">
Google ads
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/google_search_console/" class="md-nav__link">
<span class="md-ellipsis">
google_search_console
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/hist/" class="md-nav__link">
<span class="md-ellipsis">
hist
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/iap/" class="md-nav__link">
<span class="md-ellipsis">
iap
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/json/" class="md-nav__link">
<span class="md-ellipsis">
json
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/ltv/" class="md-nav__link">
<span class="md-ellipsis">
Ltv
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/map/" class="md-nav__link">
<span class="md-ellipsis">
map
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/marketing/" class="md-nav__link">
<span class="md-ellipsis">
Marketing
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/mobile_search/" class="md-nav__link">
<span class="md-ellipsis">
Mobile search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/norm/" class="md-nav__link">
<span class="md-ellipsis">
norm
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/serp_events/" class="md-nav__link">
<span class="md-ellipsis">
serp_events
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/stats/" class="md-nav__link">
<span class="md-ellipsis">
stats
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/utils/" class="md-nav__link">
<span class="md-ellipsis">
Utils
</span>
</a>
</li>
<li class="md-nav__item">
<a href="mozfun/vpn/" class="md-nav__link">
<span class="md-ellipsis">
vpn
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2_2" >
<label class="md-nav__link" for="__nav_2_2" id="__nav_2_2_label" tabindex="0">
<span class="md-ellipsis">
Moz fx data shared prod
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_2_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2_2">
<span class="md-nav__icon md-icon"></span>
Moz fx data shared prod
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="moz-fx-data-shared-prod/udf/" class="md-nav__link">
<span class="md-ellipsis">
Udf
</span>
</a>
</li>
<li class="md-nav__item">
<a href="moz-fx-data-shared-prod/udf_js/" class="md-nav__link">
<span class="md-ellipsis">
Udf js
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Cookbooks
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Cookbooks
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="cookbooks/common_workflows/" class="md-nav__link">
<span class="md-ellipsis">
Common workflows
</span>
</a>
</li>
<li class="md-nav__item">
<a href="cookbooks/creating_a_derived_dataset/" class="md-nav__link">
<span class="md-ellipsis">
Creating a derived dataset
</span>
</a>
</li>
<li class="md-nav__item">
<a href="cookbooks/testing/" class="md-nav__link">
<span class="md-ellipsis">
Testing
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="bqetl/" class="md-nav__link">
<span class="md-ellipsis">
bqetl CLI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/configuration/" class="md-nav__link">
<span class="md-ellipsis">
Bqetl Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/recommended_practices/" class="md-nav__link">
<span class="md-ellipsis">
Recommended practices
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/incremental/" class="md-nav__link">
<span class="md-ellipsis">
Incremental queries
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/scheduling/" class="md-nav__link">
<span class="md-ellipsis">
Scheduling
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/public_data/" class="md-nav__link">
<span class="md-ellipsis">
Public data
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/airflow_tags/" class="md-nav__link">
<span class="md-ellipsis">
Airflow Tags
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/data_checks/" class="md-nav__link">
<span class="md-ellipsis">
Data Checks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="reference/stage-deploys-continuous-integration/" class="md-nav__link">
<span class="md-ellipsis">
Stage Deploy & CI
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": ".", "features": ["navigation.tabs"], "search": "assets/javascripts/workers/search.6ce7567c.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
<script src="assets/javascripts/bundle.83f73b43.min.js"></script>
</body>
</html>