aetos/docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
42e5ed290e5de925f857fc308e1ab75a9683ac75
docs/omniread/lib/xlsx/index.html
Vishesh 'ironeagle' Bangotra a32eeaf2b4 feat: serve docs flat at /<repo>/ with no redirects 
- collect.py copies each repo's built site contents directly to a
  top-level <repo>/ dir (was libs|apis|wiki/<repo>/site nesting)
- nginx uses `index index.html lib/index.html api/index.html` so
  /dagpipe/ -> lib/index.html, /auth-server/ -> api/index.html are
  served internally with no redirects
- _index regenerates links against the flat layout
  (/dagpipe/lib/, /auth-server/api/, /mongo-ops/, /blog/...)
- config.yml static entries point at vendored blog/ + media-manager/
- Dockerfile copies per-repo dirs flat into the nginx html root
- removed stale libs/, apis/, wiki/, tutorials/ category trees
2026-09-11 21:32:30 +05:30

2274 lines
66 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
<title>Xlsx - omniread</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.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=Inter:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Inter";--md-code-font:"JetBrains Mono"}</style>
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="https://unpkg.com/dracula-prism/dist/css/dracula-prism.css">
<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="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan">
<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">
<a href="#xlsx" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></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">
omniread
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Xlsx
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan" aria-hidden="true" type="radio" name="__palette" id="__palette_0">
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<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">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<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>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</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>
</nav>
</header>
<div class="md-container" data-md-component="container">
<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" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></svg>
</a>
omniread
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_2" >
<div class="md-nav__link md-nav__container">
<a href="../core/" class="md-nav__link ">
<span class="md-ellipsis">
Core API
</span>
</a>
<label class="md-nav__link " for="__nav_2" id="__nav_2_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<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>
Core API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../core/content/" class="md-nav__link">
<span class="md-ellipsis">
Content
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../core/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../core/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<div class="md-nav__link md-nav__container">
<a href="../html/" class="md-nav__link ">
<span class="md-ellipsis">
HTML Handling
</span>
</a>
<label class="md-nav__link " for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<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>
HTML Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../html/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../html/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<div class="md-nav__link md-nav__container">
<a href="../pdf/" class="md-nav__link ">
<span class="md-ellipsis">
PDF Handling
</span>
</a>
<label class="md-nav__link " for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<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>
PDF Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../pdf/client/" class="md-nav__link">
<span class="md-ellipsis">
Client
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pdf/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pdf/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</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">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#omniread.xlsx" class="md-nav__link">
<span class="md-ellipsis">
xlsx
</span>
</a>
<nav class="md-nav" aria-label="xlsx">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx--summary" class="md-nav__link">
<span class="md-ellipsis">
Summary
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx-classes" class="md-nav__link">
<span class="md-ellipsis">
Classes
</span>
</a>
<nav class="md-nav" aria-label="Classes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.BaseXlsxClient" class="md-nav__link">
<span class="md-ellipsis">
BaseXlsxClient
</span>
</a>
<nav class="md-nav" aria-label="BaseXlsxClient">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.BaseXlsxClient-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.BaseXlsxClient.fetch" class="md-nav__link">
<span class="md-ellipsis">
fetch
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.FileSystemXlsxClient" class="md-nav__link">
<span class="md-ellipsis">
FileSystemXlsxClient
</span>
</a>
<nav class="md-nav" aria-label="FileSystemXlsxClient">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.FileSystemXlsxClient-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.FileSystemXlsxClient.fetch" class="md-nav__link">
<span class="md-ellipsis">
fetch
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser" class="md-nav__link">
<span class="md-ellipsis">
XlsxParser
</span>
</a>
<nav class="md-nav" aria-label="XlsxParser">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser-attributes" class="md-nav__link">
<span class="md-ellipsis">
Attributes
</span>
</a>
<nav class="md-nav" aria-label="Attributes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.sheet_names" class="md-nav__link">
<span class="md-ellipsis">
sheet_names
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.supported_types" class="md-nav__link">
<span class="md-ellipsis">
supported_types
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.workbook" class="md-nav__link">
<span class="md-ellipsis">
workbook
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.parse" class="md-nav__link">
<span class="md-ellipsis">
parse
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.rows" class="md-nav__link">
<span class="md-ellipsis">
rows
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParser.supports" class="md-nav__link">
<span class="md-ellipsis">
supports
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase" class="md-nav__link">
<span class="md-ellipsis">
XlsxParserBase
</span>
</a>
<nav class="md-nav" aria-label="XlsxParserBase">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase-attributes" class="md-nav__link">
<span class="md-ellipsis">
Attributes
</span>
</a>
<nav class="md-nav" aria-label="Attributes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase.supported_types" class="md-nav__link">
<span class="md-ellipsis">
supported_types
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase.parse" class="md-nav__link">
<span class="md-ellipsis">
parse
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxParserBase.supports" class="md-nav__link">
<span class="md-ellipsis">
supports
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxScraper" class="md-nav__link">
<span class="md-ellipsis">
XlsxScraper
</span>
</a>
<nav class="md-nav" aria-label="XlsxScraper">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxScraper-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.xlsx.XlsxScraper.fetch" class="md-nav__link">
<span class="md-ellipsis">
fetch
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="xlsx">Xlsx</h1>
<div class="doc doc-object doc-module">
<h2 id="omniread.xlsx" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-module"></code> <span class="doc doc-object-name doc-module-name">omniread.xlsx</span>
</h2>
<div class="doc doc-contents first">
<h3 id="omniread.xlsx--summary">Summary</h3>
<p>XLSX subpackage for OmniRead.</p>
<p>Provides acquisition and parsing of Office Open XML spreadsheet (xlsx)
content:</p>
<ul>
<li><code>BaseXlsxClient</code>: abstract backing-store client for xlsx bytes.</li>
<li><code>FileSystemXlsxClient</code>: local filesystem implementation.</li>
<li><code>XlsxScraper</code>: wraps fetched bytes into canonical <code>Content</code>.</li>
<li><code>XlsxParserBase</code>: content-type-enforcing parser contract.</li>
<li><code>XlsxParser</code>: generic string-row parser built on openpyxl.</li>
</ul>
<div class="doc doc-children">
<h3 id="omniread.xlsx-classes">Classes</h3>
<div class="doc doc-object doc-class">
<h4 id="omniread.xlsx.BaseXlsxClient" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">BaseXlsxClient</span>
</h4>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><span title="abc.ABC">ABC</span></code></p>
<p>Abstract client responsible for retrieving spreadsheet bytes.</p>
<p>Retrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span>
<span class="normal">4</span></pre></div></td><td class="code"><div><pre><span></span><code>- Implementations must accept a source identifier appropriate to
the backing store.
- Return the full xlsx binary payload.
- Raise retrieval-specific errors on failure.
</code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<h5 id="omniread.xlsx.BaseXlsxClient-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.BaseXlsxClient.fetch" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">fetch</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-abstractmethod"><code>abstractmethod</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bytes</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Fetch raw xlsx bytes from the given source.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>source</code></td>
<td>
<code><span title="typing.Any">Any</span></code>
</td>
<td>
<div class="doc-md-description">
<p>Identifier of the spreadsheet location, such as a file path,
object storage key, or remote reference.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>bytes</code></td> <td>
<code>bytes</code>
</td>
<td>
<div class="doc-md-description">
<p>Raw xlsx bytes.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>Exception</code>
</td>
<td>
<div class="doc-md-description">
<p>Retrieval-specific errors defined by the implementation.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.xlsx.FileSystemXlsxClient" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">FileSystemXlsxClient</span>
</h4>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><a class="autorefs autorefs-internal" title="omniread.xlsx.client.BaseXlsxClient" href="client/#omniread.xlsx.client.BaseXlsxClient">BaseXlsxClient</a></code></p>
<p>XLSX client that reads from the local filesystem.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Guarantees:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- This client reads spreadsheet files directly from the disk and
returns their raw binary contents.
</code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<h5 id="omniread.xlsx.FileSystemXlsxClient-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.FileSystemXlsxClient.fetch" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">fetch</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">path</span><span class="p">:</span> <span class="n">Path</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bytes</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Read an xlsx file from the local filesystem.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>path</code></td>
<td>
<code><span title="pathlib.Path">Path</span></code>
</td>
<td>
<div class="doc-md-description">
<p>Filesystem path to the spreadsheet file.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>bytes</code></td> <td>
<code>bytes</code>
</td>
<td>
<div class="doc-md-description">
<p>Raw xlsx bytes.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>FileNotFoundError</code>
</td>
<td>
<div class="doc-md-description">
<p>If the path does not exist.</p>
</div>
</td>
</tr>
<tr class="doc-section-item">
<td>
<code>ValueError</code>
</td>
<td>
<div class="doc-md-description">
<p>If the path exists but is not a file.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.xlsx.XlsxParser" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">XlsxParser</span>
</h4>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
<span class="normal"><a href="#__codelineno-0-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">XlsxParser</span><span class="p">(</span>
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">content</span><span class="p">:</span> <span class="n">Content</span><span class="p">,</span>
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">data_only</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">read_only</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><a class="autorefs autorefs-internal" title="omniread.xlsx.parser_base.XlsxParserBase" href="parser_base/#omniread.xlsx.parser_base.XlsxParserBase">XlsxParserBase</a>[list[list[str]]]</code></p>
<p>Generic xlsx parser producing string rows from a worksheet.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span>
<span class="normal">4</span></pre></div></td><td class="code"><div><pre><span></span><code>- Lazily load the workbook owned by the parser&#39;s content.
- Normalize cells (including dates and numeric values) into
deterministic string representations.
- Expose sheet discovery and row extraction helpers.
</code></pre></div></td></tr></table></div>
<p><strong>Constraints:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span></pre></div></td><td class="code"><div><pre><span></span><code>- Cells are rendered with ``str(value)`` after trimming; date and
datetime values are rendered in ISO format. Consumers requiring
locale-specific formatting must convert on their side.
</code></pre></div></td></tr></table></div>
</details>
<p>Initialize the parser.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>content</code></td>
<td>
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
</td>
<td>
<div class="doc-md-description">
<p>XLSX content to parse; its type must be supported.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
<tr class="doc-section-item">
<td><code>data_only</code></td>
<td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>Passed to openpyxl: when True, formula cells yield their last
computed value instead of the formula string.</p>
</div>
</td>
<td>
<code>True</code>
</td>
</tr>
<tr class="doc-section-item">
<td><code>read_only</code></td>
<td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>Passed to openpyxl: streaming mode for lower memory usage.</p>
</div>
</td>
<td>
<code>True</code>
</td>
</tr>
</tbody>
</table>
<div class="doc doc-children">
<h5 id="omniread.xlsx.XlsxParser-attributes">Attributes</h5>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.xlsx.XlsxParser.sheet_names" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">sheet_names</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-property"><code>property</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">sheet_names</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Names of all worksheets contained in the workbook.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.xlsx.XlsxParser.supported_types" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">supported_types</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span> <span class="o">=</span> <span class="p">{</span><span class="n">XLSX</span><span class="p">}</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Set of content types supported by this parser (XLSX only).</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.xlsx.XlsxParser.workbook" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">workbook</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-property"><code>property</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">workbook</span><span class="p">:</span> <span class="n">Workbook</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>The lazily loaded workbook backing this parser's content.</p>
</div>
</div>
<h5 id="omniread.xlsx.XlsxParser-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxParser.parse" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">parse</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">list</span><span class="p">[</span><span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Parse the first worksheet into normalized string rows.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>list[list[str]]</code>
</td>
<td>
<div class="doc-md-description">
<p>List[List[str]]:
Rows of the default (first) worksheet.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxParser.rows" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">rows</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">rows</span><span class="p">(</span>
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">sheet</span><span class="p">:</span> <span class="nb">int</span> <span class="o">|</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">skip_empty</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">list</span><span class="p">[</span><span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Extract normalized string rows from a worksheet.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>sheet</code></td>
<td>
<code>Optional[Union[int, str]]</code>
</td>
<td>
<div class="doc-md-description">
<p>Worksheet index or title; defaults to the first worksheet.</p>
</div>
</td>
<td>
<code>None</code>
</td>
</tr>
<tr class="doc-section-item">
<td><code>skip_empty</code></td>
<td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>When True (default), rows whose cells are all blank are omitted.</p>
</div>
</td>
<td>
<code>True</code>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>list[list[str]]</code>
</td>
<td>
<div class="doc-md-description">
<p>List[List[str]]:
Normalized rows; trailing blank cells are trimmed per row.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>ValueError</code>
</td>
<td>
<div class="doc-md-description">
<p>If the requested sheet does not exist.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxParser.supports" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">supports</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">supports</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">bool</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Check whether this parser supports the content's type.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>bool</code></td> <td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>True if the content type is supported; False otherwise.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.xlsx.XlsxParserBase" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">XlsxParserBase</span>
</h4>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">XlsxParserBase</span><span class="p">(</span><span class="n">content</span><span class="p">:</span> <span class="n">Content</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><a class="autorefs autorefs-internal" title="omniread.core.parser.BaseParser" href="../core/parser/#omniread.core.parser.BaseParser">BaseParser</a>[<span title="omniread.xlsx.parser_base.T">T</span>]</code>, <code><span title="typing.Generic">Generic</span>[<span title="omniread.xlsx.parser_base.T">T</span>]</code></p>
<p>Base xlsx parser.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span></pre></div></td><td class="code"><div><pre><span></span><code>- This class enforces xlsx content-type compatibility and provides
the extension point for implementing concrete xlsx parsing
strategies.
</code></pre></div></td></tr></table></div>
<p><strong>Constraints:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- Concrete implementations must define the output type `T` and
implement the `parse()` method.
</code></pre></div></td></tr></table></div>
</details>
<p>Initialize the parser with content to be parsed.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>content</code></td>
<td>
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
</td>
<td>
<div class="doc-md-description">
<p>Content instance to be parsed.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>ValueError</code>
</td>
<td>
<div class="doc-md-description">
<p>If the content type is not supported by this parser.</p>
</div>
</td>
</tr>
</tbody>
</table>
<div class="doc doc-children">
<h5 id="omniread.xlsx.XlsxParserBase-attributes">Attributes</h5>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.xlsx.XlsxParserBase.supported_types" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">supported_types</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span> <span class="o">=</span> <span class="p">{</span><span class="n">XLSX</span><span class="p">}</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Set of content types supported by this parser (XLSX only).</p>
</div>
</div>
<h5 id="omniread.xlsx.XlsxParserBase-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxParserBase.parse" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">parse</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-abstractmethod"><code>abstractmethod</code></small>
</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n">T</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Parse xlsx content into a structured output.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>T</code></td> <td>
<code><span title="omniread.xlsx.parser_base.T">T</span></code>
</td>
<td>
<div class="doc-md-description">
<p>Parsed representation of type <code>T</code>.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>Exception</code>
</td>
<td>
<div class="doc-md-description">
<p>Parsing-specific errors as defined by the implementation.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxParserBase.supports" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">supports</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">supports</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">bool</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Check whether this parser supports the content's type.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>bool</code></td> <td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>True if the content type is supported; False otherwise.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.xlsx.XlsxScraper" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">XlsxScraper</span>
</h4>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">XlsxScraper</span><span class="p">(</span><span class="o">*</span><span class="p">,</span> <span class="n">client</span><span class="p">:</span> <span class="n">BaseXlsxClient</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Scraper for xlsx spreadsheet documents.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span></pre></div></td><td class="code"><div><pre><span></span><code>- Fetch raw xlsx bytes via the configured client.
- Wrap the payload in a canonical `Content` instance with the
XLSX content type and source identifier.
</code></pre></div></td></tr></table></div>
<p><strong>Constraints:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- The scraper does not perform parsing or interpretation.
- Does not assume a specific storage backend.
</code></pre></div></td></tr></table></div>
</details>
<p>Initialize the XLSX scraper.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>client</code></td>
<td>
<code><a class="autorefs autorefs-internal" title="omniread.xlsx.client.BaseXlsxClient" href="client/#omniread.xlsx.client.BaseXlsxClient">BaseXlsxClient</a></code>
</td>
<td>
<div class="doc-md-description">
<p>Client responsible for retrieving raw spreadsheet bytes.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<div class="doc doc-children">
<h5 id="omniread.xlsx.XlsxScraper-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.xlsx.XlsxScraper.fetch" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">fetch</span>
</h6>
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Content</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Fetch an xlsx document from the given source.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>source</code></td>
<td>
<code><span title="typing.Any">Any</span></code>
</td>
<td>
<div class="doc-md-description">
<p>Identifier of the spreadsheet source as understood by the
configured client.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
<tr class="doc-section-item">
<td><code>metadata</code></td>
<td>
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
</td>
<td>
<div class="doc-md-description">
<p>Optional metadata to attach to the returned content.</p>
</div>
</td>
<td>
<code>None</code>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>Content</code></td> <td>
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
</td>
<td>
<div class="doc-md-description">
<p>A <code>Content</code> instance containing raw xlsx bytes, source
identifier, XLSX content type, and optional metadata.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>Exception</code>
</td>
<td>
<div class="doc-md-description">
<p>Retrieval-specific errors raised by the client.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var labels=set.querySelector(".tabbed-labels");for(var tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</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.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "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"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink