feat: collect omniread wiki; register wiki kind; refresh lib and mcp artifacts
Adds the omniread wiki to the hub alongside lib and mcp and completes the library nav with csv/xlsx groups, picking up regenerated MCP modules.
This commit is contained in:
751
omniread/wiki/01_overview/index.html
Normal file
751
omniread/wiki/01_overview/index.html
Normal file
@@ -0,0 +1,751 @@
|
||||
|
||||
<!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="prev" href="..">
|
||||
|
||||
|
||||
<link rel="next" href="../02_how_to_use/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>Overview - OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="#overview" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
Overview
|
||||
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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">
|
||||
<a href=".." class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Home
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item md-tabs__item--active">
|
||||
<a href="./" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../02_how_to_use/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../03_extending/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../04_development/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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--active">
|
||||
|
||||
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<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="#architecture" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🏗️ Architecture
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#the-content-model" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📦 The Content model
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#the-contenttype-enum" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🎭 The ContentType enum
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#format-modules-at-a-glance" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🧩 Format modules at a glance
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#read-next" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📚 Read Next
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../02_how_to_use/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../03_extending/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../04_development/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h1 id="overview">🧱 Overview</h1>
|
||||
<p>OmniRead is designed as a <strong>decoupled content engine</strong> with three distinct
|
||||
layers. Understanding them is the key to using and extending the library.</p>
|
||||
<hr />
|
||||
<h2 id="architecture">🏗️ Architecture</h2>
|
||||
<div class="language-text 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>
|
||||
<span class="normal"><a href="#__codelineno-0-7"> 7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-8"> 8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-9"> 9</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-10">10</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-11">11</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-12">12</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-13">13</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-14">14</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-15">15</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><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> │ Source (URL, file, storage) │
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> └────────────┬────────────────┘
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> │
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> ┌─────────▼──────────┐
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> │ Scraper / Client │ fetches raw bytes
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a> └─────────┬──────────┘
|
||||
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8"></a> │ returns
|
||||
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9"></a> ┌─────────▼──────────┐
|
||||
</span><span id="__span-0-10"><a id="__codelineno-0-10" name="__codelineno-0-10"></a> │ Content │ raw + source + type
|
||||
</span><span id="__span-0-11"><a id="__codelineno-0-11" name="__codelineno-0-11"></a> └─────────┬──────────┘
|
||||
</span><span id="__span-0-12"><a id="__codelineno-0-12" name="__codelineno-0-12"></a> │
|
||||
</span><span id="__span-0-13"><a id="__codelineno-0-13" name="__codelineno-0-13"></a> ┌─────────▼──────────┐
|
||||
</span><span id="__span-0-14"><a id="__codelineno-0-14" name="__codelineno-0-14"></a> │ Parser │ parse() → structured T
|
||||
</span><span id="__span-0-15"><a id="__codelineno-0-15" name="__codelineno-0-15"></a> └────────────────────┘
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<ol>
|
||||
<li><strong>Scraper</strong> (<code>BaseScraper</code>) — fetches raw bytes from a source (HTTP URL,
|
||||
filesystem path, object storage). Returns a <code>Content</code> instance.
|
||||
Scrapers never interpret content.</li>
|
||||
<li><strong>Content</strong> (<code>Content</code>) — the canonical exchange model: raw bytes,
|
||||
source identifier, and optional <code>ContentType</code> enum.</li>
|
||||
<li><strong>Parser</strong> (<code>BaseParser[T]</code>) — receives a <code>Content</code> and returns a
|
||||
structured result of type <code>T</code> via <code>parse()</code>.</li>
|
||||
</ol>
|
||||
<hr />
|
||||
<h2 id="the-content-model">📦 The <code>Content</code> model</h2>
|
||||
<p>Defined in <code>omniread.core.content</code>:</p>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-1-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-7">7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-8">8</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">dataclasses</span><span class="w"> </span><span class="kn">import</span> <span class="n">dataclass</span>
|
||||
</span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">Content</span><span class="p">,</span> <span class="n">ContentType</span>
|
||||
</span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3"></a>
|
||||
</span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4"></a><span class="nd">@dataclass</span><span class="p">(</span><span class="n">slots</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
</span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5"></a><span class="k">class</span><span class="w"> </span><span class="nc">Content</span><span class="p">:</span>
|
||||
</span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6"></a> <span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span>
|
||||
</span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span>
|
||||
</span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8"></a> <span class="n">content_type</span><span class="p">:</span> <span class="n">ContentType</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<ul>
|
||||
<li><code>raw</code> — the raw bytes exactly as retrieved.</li>
|
||||
<li><code>source</code> — URL, file path, or logical name identifying the origin.</li>
|
||||
<li><code>content_type</code> — optional <code>ContentType</code> enum value.</li>
|
||||
</ul>
|
||||
<hr />
|
||||
<h2 id="the-contenttype-enum">🎭 The <code>ContentType</code> enum</h2>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Value</th>
|
||||
<th>MIME</th>
|
||||
<th>Used by</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><code>HTML</code></td>
|
||||
<td><code>text/html</code></td>
|
||||
<td>HTMLScraper</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>PDF</code></td>
|
||||
<td><code>application/pdf</code></td>
|
||||
<td>PDFScraper</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>XLSX</code></td>
|
||||
<td><code>application/vnd.openxmlformats-...</code></td>
|
||||
<td>XlsxScraper</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>CSV</code></td>
|
||||
<td><code>text/csv</code></td>
|
||||
<td>CsvScraper</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>JSON</code></td>
|
||||
<td><code>application/json</code></td>
|
||||
<td>—</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>XML</code></td>
|
||||
<td><code>application/xml</code></td>
|
||||
<td>—</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<hr />
|
||||
<h2 id="format-modules-at-a-glance">🧩 Format modules at a glance</h2>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Module</th>
|
||||
<th>Scraper</th>
|
||||
<th>Parser</th>
|
||||
<th>Client</th>
|
||||
<th>Notes</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><code>omniread.html</code></td>
|
||||
<td><code>HTMLScraper</code></td>
|
||||
<td><code>HTMLParser</code></td>
|
||||
<td>—</td>
|
||||
<td>httpx + BeautifulSoup</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>omniread.pdf</code></td>
|
||||
<td><code>PDFScraper</code></td>
|
||||
<td><code>PDFParser</code></td>
|
||||
<td><code>FileSystemPDFClient</code></td>
|
||||
<td>explicit client layer</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>omniread.csv</code></td>
|
||||
<td><code>CsvScraper</code></td>
|
||||
<td><code>CsvParser</code></td>
|
||||
<td><code>FileSystemCsvClient</code></td>
|
||||
<td>stdlib csv module</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>omniread.xlsx</code></td>
|
||||
<td><code>XlsxScraper</code></td>
|
||||
<td><code>XlsxParser</code></td>
|
||||
<td><code>FileSystemXlsxClient</code></td>
|
||||
<td>openpyxl-backed</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<hr />
|
||||
<h2 id="read-next">📚 Read Next</h2>
|
||||
<ul>
|
||||
<li><a href="../02_how_to_use/">How to Use</a> — working examples per format.</li>
|
||||
<li><a href="../03_extending/">Extending OmniRead</a> — subclassing scrapers and parsers.</li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
724
omniread/wiki/02_how_to_use/index.html
Normal file
724
omniread/wiki/02_how_to_use/index.html
Normal file
@@ -0,0 +1,724 @@
|
||||
|
||||
<!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="prev" href="../01_overview/">
|
||||
|
||||
|
||||
<link rel="next" href="../03_extending/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>How to Use - OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="#how-to-use" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
How to Use
|
||||
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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">
|
||||
<a href=".." class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Home
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../01_overview/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item md-tabs__item--active">
|
||||
<a href="./" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../03_extending/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../04_development/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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">
|
||||
<a href="../01_overview/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item md-nav__item--active">
|
||||
|
||||
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<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="#html" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🌐 HTML
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#pdf" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📕 PDF
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#csv" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📊 CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#xlsx" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📑 XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#end-to-end-flow" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🔀 End-to-end flow
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#read-next" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📚 Read Next
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../03_extending/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../04_development/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h1 id="how-to-use">🖥️ How to Use</h1>
|
||||
<p>Every format follows the same pipeline: <strong>scrape → <code>Content</code> → parse</strong>.
|
||||
This page shows each supported format with working patterns.</p>
|
||||
<hr />
|
||||
<h2 id="html">🌐 HTML</h2>
|
||||
<div class="language-python 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>
|
||||
<span class="normal"><a href="#__codelineno-0-7"> 7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-8"> 8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-9"> 9</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-10">10</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="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">HTMLScraper</span><span class="p">,</span> <span class="n">HTMLParser</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">TitleParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_soup</span><span class="o">.</span><span class="n">title</span><span class="o">.</span><span class="n">string</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a><span class="n">scraper</span> <span class="o">=</span> <span class="n">HTMLScraper</span><span class="p">()</span> <span class="c1"># httpx under the hood</span>
|
||||
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8"></a><span class="n">content</span> <span class="o">=</span> <span class="n">scraper</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="s2">"https://example.com"</span><span class="p">)</span>
|
||||
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9"></a>
|
||||
</span><span id="__span-0-10"><a id="__codelineno-0-10" name="__codelineno-0-10"></a><span class="n">title</span> <span class="o">=</span> <span class="n">TitleParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span><span class="o">.</span><span class="n">parse</span><span class="p">()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p><code>HTMLScraper</code> accepts an optional <code>client</code> (an <code>httpx.Client</code>) for transport
|
||||
control — the test suite wires one to a mock transport.</p>
|
||||
<hr />
|
||||
<h2 id="pdf">📕 PDF</h2>
|
||||
<p>PDFs need a <strong>client</strong> to supply raw bytes before parsing:</p>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-1-1"> 1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-2"> 2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-3"> 3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-4"> 4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-5"> 5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-6"> 6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-7"> 7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-8"> 8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-9"> 9</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-10">10</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-11">11</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-12">12</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-13">13</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">pathlib</span><span class="w"> </span><span class="kn">import</span> <span class="n">Path</span>
|
||||
</span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">FileSystemPDFClient</span><span class="p">,</span> <span class="n">PDFScraper</span><span class="p">,</span> <span class="n">PDFParser</span>
|
||||
</span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3"></a>
|
||||
</span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4"></a><span class="k">class</span><span class="w"> </span><span class="nc">TextPDFParser</span><span class="p">(</span><span class="n">PDFParser</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||||
</span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||||
</span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6"></a> <span class="c1"># implement your extraction logic</span>
|
||||
</span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7"></a> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span> <span class="c1"># bytes, decode as needed</span>
|
||||
</span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8"></a>
|
||||
</span><span id="__span-1-9"><a id="__codelineno-1-9" name="__codelineno-1-9"></a><span class="n">client</span> <span class="o">=</span> <span class="n">FileSystemPDFClient</span><span class="p">()</span>
|
||||
</span><span id="__span-1-10"><a id="__codelineno-1-10" name="__codelineno-1-10"></a><span class="n">scraper</span> <span class="o">=</span> <span class="n">PDFScraper</span><span class="p">(</span><span class="n">client</span><span class="o">=</span><span class="n">client</span><span class="p">)</span>
|
||||
</span><span id="__span-1-11"><a id="__codelineno-1-11" name="__codelineno-1-11"></a><span class="n">content</span> <span class="o">=</span> <span class="n">scraper</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="n">Path</span><span class="p">(</span><span class="s2">"document.pdf"</span><span class="p">))</span>
|
||||
</span><span id="__span-1-12"><a id="__codelineno-1-12" name="__codelineno-1-12"></a>
|
||||
</span><span id="__span-1-13"><a id="__codelineno-1-13" name="__codelineno-1-13"></a><span class="n">result</span> <span class="o">=</span> <span class="n">TextPDFParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span><span class="o">.</span><span class="n">parse</span><span class="p">()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p><code>PDFParser</code> subclasses receive <code>self.content</code> and implement <code>parse()</code>.</p>
|
||||
<hr />
|
||||
<h2 id="csv">📊 CSV</h2>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-2-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-7">7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-8">8</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-2-1"><a id="__codelineno-2-1" name="__codelineno-2-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">FileSystemCsvClient</span><span class="p">,</span> <span class="n">CsvScraper</span><span class="p">,</span> <span class="n">CsvParser</span>
|
||||
</span><span id="__span-2-2"><a id="__codelineno-2-2" name="__codelineno-2-2"></a>
|
||||
</span><span id="__span-2-3"><a id="__codelineno-2-3" name="__codelineno-2-3"></a><span class="n">scraper</span> <span class="o">=</span> <span class="n">CsvScraper</span><span class="p">(</span><span class="n">client</span><span class="o">=</span><span class="n">FileSystemCsvClient</span><span class="p">())</span>
|
||||
</span><span id="__span-2-4"><a id="__codelineno-2-4" name="__codelineno-2-4"></a><span class="n">content</span> <span class="o">=</span> <span class="n">scraper</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="s2">"data.csv"</span><span class="p">)</span>
|
||||
</span><span id="__span-2-5"><a id="__codelineno-2-5" name="__codelineno-2-5"></a>
|
||||
</span><span id="__span-2-6"><a id="__codelineno-2-6" name="__codelineno-2-6"></a><span class="n">parser</span> <span class="o">=</span> <span class="n">CsvParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span>
|
||||
</span><span id="__span-2-7"><a id="__codelineno-2-7" name="__codelineno-2-7"></a><span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">parser</span><span class="o">.</span><span class="n">rows</span><span class="p">():</span>
|
||||
</span><span id="__span-2-8"><a id="__codelineno-2-8" name="__codelineno-2-8"></a> <span class="nb">print</span><span class="p">(</span><span class="n">row</span><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p><code>CsvParser.rows()</code> yields string rows trimmed of empties by default
|
||||
(<code>skip_empty=True</code>).</p>
|
||||
<hr />
|
||||
<h2 id="xlsx">📑 XLSX</h2>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-3-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-7">7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-8">8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-9">9</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-3-1"><a id="__codelineno-3-1" name="__codelineno-3-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">FileSystemXlsxClient</span><span class="p">,</span> <span class="n">XlsxScraper</span><span class="p">,</span> <span class="n">XlsxParser</span>
|
||||
</span><span id="__span-3-2"><a id="__codelineno-3-2" name="__codelineno-3-2"></a>
|
||||
</span><span id="__span-3-3"><a id="__codelineno-3-3" name="__codelineno-3-3"></a><span class="n">scraper</span> <span class="o">=</span> <span class="n">XlsxScraper</span><span class="p">(</span><span class="n">client</span><span class="o">=</span><span class="n">FileSystemXlsxClient</span><span class="p">())</span>
|
||||
</span><span id="__span-3-4"><a id="__codelineno-3-4" name="__codelineno-3-4"></a><span class="n">content</span> <span class="o">=</span> <span class="n">scraper</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="s2">"statement.xlsx"</span><span class="p">)</span>
|
||||
</span><span id="__span-3-5"><a id="__codelineno-3-5" name="__codelineno-3-5"></a>
|
||||
</span><span id="__span-3-6"><a id="__codelineno-3-6" name="__codelineno-3-6"></a><span class="n">parser</span> <span class="o">=</span> <span class="n">XlsxParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span>
|
||||
</span><span id="__span-3-7"><a id="__codelineno-3-7" name="__codelineno-3-7"></a><span class="nb">print</span><span class="p">(</span><span class="n">parser</span><span class="o">.</span><span class="n">sheet_names</span><span class="p">)</span> <span class="c1"># e.g. ["Statement"]</span>
|
||||
</span><span id="__span-3-8"><a id="__codelineno-3-8" name="__codelineno-3-8"></a><span class="n">rows</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">rows</span><span class="p">(</span><span class="n">sheet</span><span class="o">=</span><span class="s2">"Statement"</span><span class="p">)</span> <span class="c1"># by name or index</span>
|
||||
</span><span id="__span-3-9"><a id="__codelineno-3-9" name="__codelineno-3-9"></a><span class="n">all_rows</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse</span><span class="p">()</span> <span class="c1"># alias for rows()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p>Key behaviors:</p>
|
||||
<ul>
|
||||
<li><code>rows(skip_empty=False)</code> keeps blank rows (off by default).</li>
|
||||
<li>Cells render as trimmed strings; date cells convert to ISO format
|
||||
(<code>2026-06-01T00:00:00</code>).</li>
|
||||
<li><code>rows(sheet="Missing")</code> raises for an unknown sheet.</li>
|
||||
</ul>
|
||||
<hr />
|
||||
<h2 id="end-to-end-flow">🔀 End-to-end flow</h2>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-4-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-4-1"><a id="__codelineno-4-1" name="__codelineno-4-1"></a><span class="n">content</span> <span class="o">=</span> <span class="n">scraper</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">)</span> <span class="c1"># 1. acquire → Content</span>
|
||||
</span><span id="__span-4-2"><a id="__codelineno-4-2" name="__codelineno-4-2"></a><span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">)</span>
|
||||
</span><span id="__span-4-3"><a id="__codelineno-4-3" name="__codelineno-4-3"></a><span class="k">assert</span> <span class="n">content</span><span class="o">.</span><span class="n">content_type</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
|
||||
</span><span id="__span-4-4"><a id="__codelineno-4-4" name="__codelineno-4-4"></a>
|
||||
</span><span id="__span-4-5"><a id="__codelineno-4-5" name="__codelineno-4-5"></a><span class="n">parser</span> <span class="o">=</span> <span class="n">MyParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span> <span class="c1"># 2. interpret → T</span>
|
||||
</span><span id="__span-4-6"><a id="__codelineno-4-6" name="__codelineno-4-6"></a><span class="n">result</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse</span><span class="p">()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="read-next">📚 Read Next</h2>
|
||||
<ul>
|
||||
<li><a href="../01_overview/">Overview</a> — the full architecture.</li>
|
||||
<li><a href="../03_extending/">Extending OmniRead</a> — custom clients and parsers.</li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
714
omniread/wiki/03_extending/index.html
Normal file
714
omniread/wiki/03_extending/index.html
Normal file
@@ -0,0 +1,714 @@
|
||||
|
||||
<!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="prev" href="../02_how_to_use/">
|
||||
|
||||
|
||||
<link rel="next" href="../04_development/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>Extending OmniRead - OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="#extending-omniread" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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">
|
||||
<a href=".." class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Home
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../01_overview/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../02_how_to_use/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item md-tabs__item--active">
|
||||
<a href="./" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../04_development/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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">
|
||||
<a href="../01_overview/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../02_how_to_use/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item md-nav__item--active">
|
||||
|
||||
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<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="#custom-parsers" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🧬 Custom parsers
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#custom-pdf-parsers" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🧬 Custom PDF parsers
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#custom-clients" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🧬 Custom clients
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#custom-scrapers" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🚀 Custom scrapers
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#extension-checklist" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
✅ Extension checklist
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#read-next" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📚 Read Next
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../04_development/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h1 id="extending-omniread">🧩 Extending OmniRead</h1>
|
||||
<p>OmniRead is meant to be extended by subclassing. All public extension points
|
||||
are generic over their result type, so your parser returns exactly the shape
|
||||
you need.</p>
|
||||
<hr />
|
||||
<h2 id="custom-parsers">🧬 Custom parsers</h2>
|
||||
<p>Subclass <code>BaseParser[T]</code> (or a format parser) and implement <code>parse()</code>:</p>
|
||||
<div class="language-python 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>
|
||||
<span class="normal"><a href="#__codelineno-0-7"> 7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-8"> 8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-9"> 9</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-10">10</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-11">11</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-12">12</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-13">13</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-14">14</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-15">15</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="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">HTMLParser</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a><span class="k">class</span><span class="w"> </span><span class="nc">Page</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">title</span><span class="p">:</span> <span class="nb">str</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> <span class="n">content</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a>
|
||||
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8"></a><span class="k">class</span><span class="w"> </span><span class="nc">PageParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">[</span><span class="n">Page</span><span class="p">]):</span>
|
||||
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Page</span><span class="p">:</span>
|
||||
</span><span id="__span-0-10"><a id="__codelineno-0-10" name="__codelineno-0-10"></a> <span class="n">soup</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_soup</span>
|
||||
</span><span id="__span-0-11"><a id="__codelineno-0-11" name="__codelineno-0-11"></a> <span class="n">div</span> <span class="o">=</span> <span class="n">soup</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"div"</span><span class="p">,</span> <span class="nb">id</span><span class="o">=</span><span class="s2">"content"</span><span class="p">)</span>
|
||||
</span><span id="__span-0-12"><a id="__codelineno-0-12" name="__codelineno-0-12"></a> <span class="k">return</span> <span class="n">Page</span><span class="p">(</span>
|
||||
</span><span id="__span-0-13"><a id="__codelineno-0-13" name="__codelineno-0-13"></a> <span class="n">title</span><span class="o">=</span><span class="n">soup</span><span class="o">.</span><span class="n">title</span><span class="o">.</span><span class="n">string</span><span class="p">,</span>
|
||||
</span><span id="__span-0-14"><a id="__codelineno-0-14" name="__codelineno-0-14"></a> <span class="n">content</span><span class="o">=</span><span class="n">div</span><span class="o">.</span><span class="n">get_text</span><span class="p">()</span> <span class="k">if</span> <span class="n">div</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-15"><a id="__codelineno-0-15" name="__codelineno-0-15"></a> <span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p>The parsed page is validated by Pydantic on construction — no manual
|
||||
assertions required.</p>
|
||||
<hr />
|
||||
<h2 id="custom-pdf-parsers">🧬 Custom PDF parsers</h2>
|
||||
<p>PDF binary layout is format-specific, so parsers return your own model:</p>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-1-1"> 1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-2"> 2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-3"> 3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-4"> 4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-5"> 5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-6"> 6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-7"> 7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-8"> 8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-9"> 9</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-10">10</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-11">11</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-12">12</a></span>
|
||||
<span class="normal"><a href="#__codelineno-1-13">13</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Literal</span>
|
||||
</span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
|
||||
</span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">PDFParser</span>
|
||||
</span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4"></a>
|
||||
</span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5"></a><span class="k">class</span><span class="w"> </span><span class="nc">ParsedPDF</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span>
|
||||
</span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6"></a> <span class="n">size_bytes</span><span class="p">:</span> <span class="nb">int</span>
|
||||
</span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7"></a> <span class="n">magic</span><span class="p">:</span> <span class="n">Literal</span><span class="p">[</span><span class="sa">b</span><span class="s2">"%PDF"</span><span class="p">]</span>
|
||||
</span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8"></a>
|
||||
</span><span id="__span-1-9"><a id="__codelineno-1-9" name="__codelineno-1-9"></a><span class="k">class</span><span class="w"> </span><span class="nc">SimplePDFParser</span><span class="p">(</span><span class="n">PDFParser</span><span class="p">[</span><span class="n">ParsedPDF</span><span class="p">]):</span>
|
||||
</span><span id="__span-1-10"><a id="__codelineno-1-10" name="__codelineno-1-10"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">ParsedPDF</span><span class="p">:</span>
|
||||
</span><span id="__span-1-11"><a id="__codelineno-1-11" name="__codelineno-1-11"></a> <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="sa">b</span><span class="s2">"%PDF"</span><span class="p">):</span>
|
||||
</span><span id="__span-1-12"><a id="__codelineno-1-12" name="__codelineno-1-12"></a> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Not a valid PDF"</span><span class="p">)</span>
|
||||
</span><span id="__span-1-13"><a id="__codelineno-1-13" name="__codelineno-1-13"></a> <span class="k">return</span> <span class="n">ParsedPDF</span><span class="p">(</span><span class="n">size_bytes</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span><span class="p">),</span> <span class="n">magic</span><span class="o">=</span><span class="sa">b</span><span class="s2">"%PDF"</span><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="custom-clients">🧬 Custom clients</h2>
|
||||
<p>Clients supply raw bytes to a scraper. For PDFs, subclass
|
||||
<code>BasePDFClient</code> (or <code>FileSystemPDFClient</code>) and implement
|
||||
<code>fetch(source) -> bytes</code>:</p>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-2-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-2-1"><a id="__codelineno-2-1" name="__codelineno-2-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread.pdf.client</span><span class="w"> </span><span class="kn">import</span> <span class="n">BasePDFClient</span>
|
||||
</span><span id="__span-2-2"><a id="__codelineno-2-2" name="__codelineno-2-2"></a>
|
||||
</span><span id="__span-2-3"><a id="__codelineno-2-3" name="__codelineno-2-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">MockPDFClient</span><span class="p">(</span><span class="n">BasePDFClient</span><span class="p">):</span>
|
||||
</span><span id="__span-2-4"><a id="__codelineno-2-4" name="__codelineno-2-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">fetch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">):</span>
|
||||
</span><span id="__span-2-5"><a id="__codelineno-2-5" name="__codelineno-2-5"></a> <span class="k">return</span> <span class="sa">b</span><span class="s2">"%PDF ..."</span> <span class="c1"># bytes for the logical identifier</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p>The same pattern applies to <code>BaseCsvClient</code> and <code>BaseXlsxClient</code>.</p>
|
||||
<hr />
|
||||
<h2 id="custom-scrapers">🚀 Custom scrapers</h2>
|
||||
<p>Festch something that a built-in scraper does not cover by extending
|
||||
<code>BaseScraper</code>:</p>
|
||||
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-3-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-3-1"><a id="__codelineno-3-1" name="__codelineno-3-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseScraper</span><span class="p">,</span> <span class="n">Content</span><span class="p">,</span> <span class="n">ContentType</span>
|
||||
</span><span id="__span-3-2"><a id="__codelineno-3-2" name="__codelineno-3-2"></a>
|
||||
</span><span id="__span-3-3"><a id="__codelineno-3-3" name="__codelineno-3-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">StorageScraper</span><span class="p">(</span><span class="n">BaseScraper</span><span class="p">):</span>
|
||||
</span><span id="__span-3-4"><a id="__codelineno-3-4" name="__codelineno-3-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">fetch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
</span><span id="__span-3-5"><a id="__codelineno-3-5" name="__codelineno-3-5"></a> <span class="n">raw</span> <span class="o">=</span> <span class="n">my_object_storage</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">source</span><span class="p">)</span> <span class="c1"># your I/O</span>
|
||||
</span><span id="__span-3-6"><a id="__codelineno-3-6" name="__codelineno-3-6"></a> <span class="k">return</span> <span class="n">Content</span><span class="p">(</span><span class="n">raw</span><span class="o">=</span><span class="n">raw</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="n">source</span><span class="p">,</span> <span class="n">content_type</span><span class="o">=</span><span class="n">ContentType</span><span class="o">.</span><span class="n">JSON</span><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="extension-checklist">✅ Extension checklist</h2>
|
||||
<ol>
|
||||
<li>Keep <strong>scraper</strong> and <strong>parser</strong> separate — never mix I/O into <code>parse()</code>.</li>
|
||||
<li>Return <code>Content</code> from any scraper/client so downstream stays uniform.</li>
|
||||
<li>Return a <em>typed</em> result from your parser (Pydantic model, dataclass, str).</li>
|
||||
<li>Test your custom layers with a mock client, not a live network.</li>
|
||||
</ol>
|
||||
<hr />
|
||||
<h2 id="read-next">📚 Read Next</h2>
|
||||
<ul>
|
||||
<li><a href="../02_how_to_use/">How to Use</a> — built-in example flows.</li>
|
||||
<li><a href="../04_development/">Development</a> — running tests and docs.</li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
696
omniread/wiki/04_development/index.html
Normal file
696
omniread/wiki/04_development/index.html
Normal file
@@ -0,0 +1,696 @@
|
||||
|
||||
<!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="prev" href="../03_extending/">
|
||||
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>Development - OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="#development" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
Development
|
||||
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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">
|
||||
<a href=".." class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Home
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../01_overview/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../02_how_to_use/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="../03_extending/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item md-tabs__item--active">
|
||||
<a href="./" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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">
|
||||
<a href="../01_overview/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../02_how_to_use/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../03_extending/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item md-nav__item--active">
|
||||
|
||||
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<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="#repository-layout" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📂 Repository layout
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#setup" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🔧 Setup
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#tests" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🧪 Tests
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#quality-gates" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
✅ Quality gates
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#building-documentation-docforge" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📝 Building documentation (docforge)
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#read-next" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📚 Read Next
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</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="development">🛠️ Development</h1>
|
||||
<p>Working on <code>omniread</code> itself.</p>
|
||||
<hr />
|
||||
<h2 id="repository-layout">📂 Repository layout</h2>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Path</th>
|
||||
<th>Purpose</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><code>omniread/</code></td>
|
||||
<td>The library package (core + html, pdf, csv, xlsx modules)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>omniread/*.pyi</code></td>
|
||||
<td>Type stubs kept in sync with implementations</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>tests/</code></td>
|
||||
<td>End-to-end and unit tests against mock transports/clients</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>covers</code></td>
|
||||
<td>—</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>docs/lib/</code></td>
|
||||
<td>Generated library reference (docforge, flat layout)</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>docs/mcp/</code></td>
|
||||
<td>Machine-readable bundle served by the MCP server</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>docs/wiki/</code></td>
|
||||
<td>This hand-written wiki</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<hr />
|
||||
<h2 id="setup">🔧 Setup</h2>
|
||||
<div class="language-bash 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></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>python<span class="w"> </span>-m<span class="w"> </span>venv<span class="w"> </span>.venv
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a>.venv/Scripts/pip<span class="w"> </span>install<span class="w"> </span>-e<span class="w"> </span><span class="s2">".[dev]"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="tests">🧪 Tests</h2>
|
||||
<p>Run the suite (offline; a mock httpx transport and mock PDF client are used):</p>
|
||||
<div class="language-bash highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-1-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1"></a>.venv/Scripts/pytest
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<p>Coverage spans end-to-end scrape → parse flows for HTML, PDF, and XLSX,
|
||||
plus client validation and CSV/XLSX parsing edge cases.</p>
|
||||
<hr />
|
||||
<h2 id="quality-gates">✅ Quality gates</h2>
|
||||
<p>The CI quality gate runs, matching the Drone pipeline:</p>
|
||||
<div class="language-bash highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-2-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-2-4">4</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-2-1"><a id="__codelineno-2-1" name="__codelineno-2-1"></a>.venv/Scripts/black<span class="w"> </span>--check<span class="w"> </span>.
|
||||
</span><span id="__span-2-2"><a id="__codelineno-2-2" name="__codelineno-2-2"></a>.venv/Scripts/ruff<span class="w"> </span>check<span class="w"> </span>.
|
||||
</span><span id="__span-2-3"><a id="__codelineno-2-3" name="__codelineno-2-3"></a>.venv/Scripts/mypy
|
||||
</span><span id="__span-2-4"><a id="__codelineno-2-4" name="__codelineno-2-4"></a>.venv/Scripts/pytest
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="building-documentation-docforge">📝 Building documentation (docforge)</h2>
|
||||
<p>The site is generated by <a href="https://git.aetoskia.com/aetos/doc-forge"><code>docforge</code></a>
|
||||
and served per kind under <code>site/{kind}</code>:</p>
|
||||
<div class="language-bash highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-3-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-3-4">4</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-3-1"><a id="__codelineno-3-1" name="__codelineno-3-1"></a>doc-forge<span class="w"> </span>build<span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="__span-3-2"><a id="__codelineno-3-2" name="__codelineno-3-2"></a><span class="w"> </span>--mkdocs<span class="w"> </span>--mcp<span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="__span-3-3"><a id="__codelineno-3-3" name="__codelineno-3-3"></a><span class="w"> </span>--module-is-source<span class="w"> </span>--module<span class="w"> </span>omniread<span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="__span-3-4"><a id="__codelineno-3-4" name="__codelineno-3-4"></a><span class="w"> </span>--site-name<span class="w"> </span><span class="s2">"OmniRead"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<ul>
|
||||
<li><code>--module-is-source</code> renders the flat <code>docs/lib/</code> layout (no nesting under
|
||||
<code>omniread/</code>), matching <code>docforge.nav.yml</code> and <code>docs/mkdocs.lib.yml</code>.</li>
|
||||
<li><code>--mcp</code> regenerates the structured bundle in <code>docs/mcp/</code>.</li>
|
||||
<li><code>--wiki</code> builds this wiki.</li>
|
||||
<li><code>gen_api.py</code> (if present) regenerates the API docs.</li>
|
||||
</ul>
|
||||
<p>Preview locally:</p>
|
||||
<div class="language-bash highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-4-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-4-3">3</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-4-1"><a id="__codelineno-4-1" name="__codelineno-4-1"></a>doc-forge<span class="w"> </span>serve<span class="w"> </span>--lib
|
||||
</span><span id="__span-4-2"><a id="__codelineno-4-2" name="__codelineno-4-2"></a>doc-forge<span class="w"> </span>serve<span class="w"> </span>--wiki
|
||||
</span><span id="__span-4-3"><a id="__codelineno-4-3" name="__codelineno-4-3"></a>doc-forge<span class="w"> </span>serve<span class="w"> </span>--mcp
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="read-next">📚 Read Next</h2>
|
||||
<ul>
|
||||
<li><a href="../03_extending/">Extending OmniRead</a> — custom parsers, scrapers, clients.</li>
|
||||
<li><a href="../01_overview/">Overview</a> — the core architecture.</li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
478
omniread/wiki/404.html
Normal file
478
omniread/wiki/404.html
Normal file
@@ -0,0 +1,478 @@
|
||||
|
||||
<!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>OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</span>
|
||||
</div>
|
||||
<div class="md-header__topic" data-md-component="header-topic">
|
||||
<span class="md-ellipsis">
|
||||
|
||||
|
||||
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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">
|
||||
<a href="/." class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Home
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="/01_overview/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="/02_how_to_use/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="/03_extending/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="/04_development/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="/." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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">
|
||||
<a href="/01_overview/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/02_how_to_use/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/03_extending/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/04_development/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
<h1>404 - Not found</h1>
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
BIN
omniread/wiki/assets/images/favicon.png
Normal file
BIN
omniread/wiki/assets/images/favicon.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.8 KiB |
16
omniread/wiki/assets/javascripts/bundle.f55a23d4.min.js
vendored
Normal file
16
omniread/wiki/assets/javascripts/bundle.f55a23d4.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ar.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ar.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.da.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.da.min.js
vendored
Normal file
@@ -0,0 +1,18 @@
|
||||
/*!
|
||||
* Lunr languages, `Danish` language
|
||||
* https://github.com/MihaiValentin/lunr-languages
|
||||
*
|
||||
* Copyright 2014, Mihai Valentin
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
/*!
|
||||
* based on
|
||||
* Snowball JavaScript Library v0.3
|
||||
* http://code.google.com/p/urim/
|
||||
* http://snowball.tartarus.org/
|
||||
*
|
||||
* Copyright 2010, Oleg Mazko
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.da=function(){this.pipeline.reset(),this.pipeline.add(e.da.trimmer,e.da.stopWordFilter,e.da.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.da.stemmer))},e.da.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.da.trimmer=e.trimmerSupport.generateTrimmer(e.da.wordCharacters),e.Pipeline.registerFunction(e.da.trimmer,"trimmer-da"),e.da.stemmer=function(){var r=e.stemmerSupport.Among,i=e.stemmerSupport.SnowballProgram,n=new function(){function e(){var e,r=f.cursor+3;if(d=f.limit,0<=r&&r<=f.limit){for(a=r;;){if(e=f.cursor,f.in_grouping(w,97,248)){f.cursor=e;break}if(f.cursor=e,e>=f.limit)return;f.cursor++}for(;!f.out_grouping(w,97,248);){if(f.cursor>=f.limit)return;f.cursor++}d=f.cursor,d<a&&(d=a)}}function n(){var e,r;if(f.cursor>=d&&(r=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,e=f.find_among_b(c,32),f.limit_backward=r,e))switch(f.bra=f.cursor,e){case 1:f.slice_del();break;case 2:f.in_grouping_b(p,97,229)&&f.slice_del()}}function t(){var e,r=f.limit-f.cursor;f.cursor>=d&&(e=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,f.find_among_b(l,4)?(f.bra=f.cursor,f.limit_backward=e,f.cursor=f.limit-r,f.cursor>f.limit_backward&&(f.cursor--,f.bra=f.cursor,f.slice_del())):f.limit_backward=e)}function s(){var e,r,i,n=f.limit-f.cursor;if(f.ket=f.cursor,f.eq_s_b(2,"st")&&(f.bra=f.cursor,f.eq_s_b(2,"ig")&&f.slice_del()),f.cursor=f.limit-n,f.cursor>=d&&(r=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,e=f.find_among_b(m,5),f.limit_backward=r,e))switch(f.bra=f.cursor,e){case 1:f.slice_del(),i=f.limit-f.cursor,t(),f.cursor=f.limit-i;break;case 2:f.slice_from("løs")}}function o(){var e;f.cursor>=d&&(e=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,f.out_grouping_b(w,97,248)?(f.bra=f.cursor,u=f.slice_to(u),f.limit_backward=e,f.eq_v_b(u)&&f.slice_del()):f.limit_backward=e)}var a,d,u,c=[new r("hed",-1,1),new r("ethed",0,1),new r("ered",-1,1),new r("e",-1,1),new r("erede",3,1),new r("ende",3,1),new r("erende",5,1),new r("ene",3,1),new r("erne",3,1),new r("ere",3,1),new r("en",-1,1),new r("heden",10,1),new r("eren",10,1),new r("er",-1,1),new r("heder",13,1),new r("erer",13,1),new r("s",-1,2),new r("heds",16,1),new r("es",16,1),new r("endes",18,1),new r("erendes",19,1),new r("enes",18,1),new r("ernes",18,1),new r("eres",18,1),new r("ens",16,1),new r("hedens",24,1),new r("erens",24,1),new r("ers",16,1),new r("ets",16,1),new r("erets",28,1),new r("et",-1,1),new r("eret",30,1)],l=[new r("gd",-1,-1),new r("dt",-1,-1),new r("gt",-1,-1),new r("kt",-1,-1)],m=[new r("ig",-1,1),new r("lig",0,1),new r("elig",1,1),new r("els",-1,1),new r("løst",-1,2)],w=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,48,0,128],p=[239,254,42,3,0,0,0,0,0,0,0,0,0,0,0,0,16],f=new i;this.setCurrent=function(e){f.setCurrent(e)},this.getCurrent=function(){return f.getCurrent()},this.stem=function(){var r=f.cursor;return e(),f.limit_backward=r,f.cursor=f.limit,n(),f.cursor=f.limit,t(),f.cursor=f.limit,s(),f.cursor=f.limit,o(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return n.setCurrent(e),n.stem(),n.getCurrent()}):(n.setCurrent(e),n.stem(),n.getCurrent())}}(),e.Pipeline.registerFunction(e.da.stemmer,"stemmer-da"),e.da.stopWordFilter=e.generateStopWordFilter("ad af alle alt anden at blev blive bliver da de dem den denne der deres det dette dig din disse dog du efter eller en end er et for fra ham han hans har havde have hende hendes her hos hun hvad hvis hvor i ikke ind jeg jer jo kunne man mange med meget men mig min mine mit mod ned noget nogle nu når og også om op os over på selv sig sin sine sit skal skulle som sådan thi til ud under var vi vil ville vor være været".split(" ")),e.Pipeline.registerFunction(e.da.stopWordFilter,"stopWordFilter-da")}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.de.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.de.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.du.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.du.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.el.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.el.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.es.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.es.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.fi.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.fi.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.fr.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.fr.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.he.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.he.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.hi.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.hi.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.hi=function(){this.pipeline.reset(),this.pipeline.add(e.hi.trimmer,e.hi.stopWordFilter,e.hi.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.hi.stemmer))},e.hi.wordCharacters="ऀ-ःऄ-एऐ-टठ-यर-िी-ॏॐ-य़ॠ-९॰-ॿa-zA-Za-zA-Z0-90-9",e.hi.trimmer=e.trimmerSupport.generateTrimmer(e.hi.wordCharacters),e.Pipeline.registerFunction(e.hi.trimmer,"trimmer-hi"),e.hi.stopWordFilter=e.generateStopWordFilter("अत अपना अपनी अपने अभी अंदर आदि आप इत्यादि इन इनका इन्हीं इन्हें इन्हों इस इसका इसकी इसके इसमें इसी इसे उन उनका उनकी उनके उनको उन्हीं उन्हें उन्हों उस उसके उसी उसे एक एवं एस ऐसे और कई कर करता करते करना करने करें कहते कहा का काफ़ी कि कितना किन्हें किन्हों किया किर किस किसी किसे की कुछ कुल के को कोई कौन कौनसा गया घर जब जहाँ जा जितना जिन जिन्हें जिन्हों जिस जिसे जीधर जैसा जैसे जो तक तब तरह तिन तिन्हें तिन्हों तिस तिसे तो था थी थे दबारा दिया दुसरा दूसरे दो द्वारा न नके नहीं ना निहायत नीचे ने पर पहले पूरा पे फिर बनी बही बहुत बाद बाला बिलकुल भी भीतर मगर मानो मे में यदि यह यहाँ यही या यिह ये रखें रहा रहे ऱ्वासा लिए लिये लेकिन व वग़ैरह वर्ग वह वहाँ वहीं वाले वुह वे वो सकता सकते सबसे सभी साथ साबुत साभ सारा से सो संग ही हुआ हुई हुए है हैं हो होता होती होते होना होने".split(" ")),e.hi.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.hi.tokenizer=function(i){if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var t=i.toString().toLowerCase().replace(/^\s+/,"");return r.cut(t).split("|")},e.Pipeline.registerFunction(e.hi.stemmer,"stemmer-hi"),e.Pipeline.registerFunction(e.hi.stopWordFilter,"stopWordFilter-hi")}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.hu.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.hu.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.hy.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.hy.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.hy=function(){this.pipeline.reset(),this.pipeline.add(e.hy.trimmer,e.hy.stopWordFilter)},e.hy.wordCharacters="[A-Za-z-֏ff-ﭏ]",e.hy.trimmer=e.trimmerSupport.generateTrimmer(e.hy.wordCharacters),e.Pipeline.registerFunction(e.hy.trimmer,"trimmer-hy"),e.hy.stopWordFilter=e.generateStopWordFilter("դու և եք էիր էիք հետո նաև նրանք որը վրա է որ պիտի են այս մեջ ն իր ու ի այդ որոնք այն կամ էր մի ես համար այլ իսկ էին ենք հետ ին թ էինք մենք նրա նա դուք եմ էի ըստ որպես ում".split(" ")),e.Pipeline.registerFunction(e.hy.stopWordFilter,"stopWordFilter-hy"),e.hy.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}(),e.Pipeline.registerFunction(e.hy.stemmer,"stemmer-hy")}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.it.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.it.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ja.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ja.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var r="2"==e.version[0];e.ja=function(){this.pipeline.reset(),this.pipeline.add(e.ja.trimmer,e.ja.stopWordFilter,e.ja.stemmer),r?this.tokenizer=e.ja.tokenizer:(e.tokenizer&&(e.tokenizer=e.ja.tokenizer),this.tokenizerFn&&(this.tokenizerFn=e.ja.tokenizer))};var t=new e.TinySegmenter;e.ja.tokenizer=function(i){var n,o,s,p,a,u,m,l,c,f;if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(t){return r?new e.Token(t.toLowerCase()):t.toLowerCase()});for(o=i.toString().toLowerCase().replace(/^\s+/,""),n=o.length-1;n>=0;n--)if(/\S/.test(o.charAt(n))){o=o.substring(0,n+1);break}for(a=[],s=o.length,c=0,l=0;c<=s;c++)if(u=o.charAt(c),m=c-l,u.match(/\s/)||c==s){if(m>0)for(p=t.segment(o.slice(l,c)).filter(function(e){return!!e}),f=l,n=0;n<p.length;n++)r?a.push(new e.Token(p[n],{position:[f,p[n].length],index:a.length})):a.push(p[n]),f+=p[n].length;l=c+1}return a},e.ja.stemmer=function(){return function(e){return e}}(),e.Pipeline.registerFunction(e.ja.stemmer,"stemmer-ja"),e.ja.wordCharacters="一二三四五六七八九十百千万億兆一-龠々〆ヵヶぁ-んァ-ヴーア-ン゙a-zA-Za-zA-Z0-90-9",e.ja.trimmer=e.trimmerSupport.generateTrimmer(e.ja.wordCharacters),e.Pipeline.registerFunction(e.ja.trimmer,"trimmer-ja"),e.ja.stopWordFilter=e.generateStopWordFilter("これ それ あれ この その あの ここ そこ あそこ こちら どこ だれ なに なん 何 私 貴方 貴方方 我々 私達 あの人 あのかた 彼女 彼 です あります おります います は が の に を で え から まで より も どの と し それで しかし".split(" ")),e.Pipeline.registerFunction(e.ja.stopWordFilter,"stopWordFilter-ja"),e.jp=e.ja,e.Pipeline.registerFunction(e.jp.stemmer,"stemmer-jp"),e.Pipeline.registerFunction(e.jp.trimmer,"trimmer-jp"),e.Pipeline.registerFunction(e.jp.stopWordFilter,"stopWordFilter-jp")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.jp.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.jp.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
module.exports=require("./lunr.ja");
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.kn.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.kn.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.kn=function(){this.pipeline.reset(),this.pipeline.add(e.kn.trimmer,e.kn.stopWordFilter,e.kn.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.kn.stemmer))},e.kn.wordCharacters="ಀ-಄ಅ-ಔಕ-ಹಾ-ೌ಼-ಽೕ-ೖೝ-ೞೠ-ೡೢ-ೣ೦-೯ೱ-ೳ",e.kn.trimmer=e.trimmerSupport.generateTrimmer(e.kn.wordCharacters),e.Pipeline.registerFunction(e.kn.trimmer,"trimmer-kn"),e.kn.stopWordFilter=e.generateStopWordFilter("ಮತ್ತು ಈ ಒಂದು ರಲ್ಲಿ ಹಾಗೂ ಎಂದು ಅಥವಾ ಇದು ರ ಅವರು ಎಂಬ ಮೇಲೆ ಅವರ ತನ್ನ ಆದರೆ ತಮ್ಮ ನಂತರ ಮೂಲಕ ಹೆಚ್ಚು ನ ಆ ಕೆಲವು ಅನೇಕ ಎರಡು ಹಾಗು ಪ್ರಮುಖ ಇದನ್ನು ಇದರ ಸುಮಾರು ಅದರ ಅದು ಮೊದಲ ಬಗ್ಗೆ ನಲ್ಲಿ ರಂದು ಇತರ ಅತ್ಯಂತ ಹೆಚ್ಚಿನ ಸಹ ಸಾಮಾನ್ಯವಾಗಿ ನೇ ಹಲವಾರು ಹೊಸ ದಿ ಕಡಿಮೆ ಯಾವುದೇ ಹೊಂದಿದೆ ದೊಡ್ಡ ಅನ್ನು ಇವರು ಪ್ರಕಾರ ಇದೆ ಮಾತ್ರ ಕೂಡ ಇಲ್ಲಿ ಎಲ್ಲಾ ವಿವಿಧ ಅದನ್ನು ಹಲವು ರಿಂದ ಕೇವಲ ದ ದಕ್ಷಿಣ ಗೆ ಅವನ ಅತಿ ನೆಯ ಬಹಳ ಕೆಲಸ ಎಲ್ಲ ಪ್ರತಿ ಇತ್ಯಾದಿ ಇವು ಬೇರೆ ಹೀಗೆ ನಡುವೆ ಇದಕ್ಕೆ ಎಸ್ ಇವರ ಮೊದಲು ಶ್ರೀ ಮಾಡುವ ಇದರಲ್ಲಿ ರೀತಿಯ ಮಾಡಿದ ಕಾಲ ಅಲ್ಲಿ ಮಾಡಲು ಅದೇ ಈಗ ಅವು ಗಳು ಎ ಎಂಬುದು ಅವನು ಅಂದರೆ ಅವರಿಗೆ ಇರುವ ವಿಶೇಷ ಮುಂದೆ ಅವುಗಳ ಮುಂತಾದ ಮೂಲ ಬಿ ಮೀ ಒಂದೇ ಇನ್ನೂ ಹೆಚ್ಚಾಗಿ ಮಾಡಿ ಅವರನ್ನು ಇದೇ ಯ ರೀತಿಯಲ್ಲಿ ಜೊತೆ ಅದರಲ್ಲಿ ಮಾಡಿದರು ನಡೆದ ಆಗ ಮತ್ತೆ ಪೂರ್ವ ಆತ ಬಂದ ಯಾವ ಒಟ್ಟು ಇತರೆ ಹಿಂದೆ ಪ್ರಮಾಣದ ಗಳನ್ನು ಕುರಿತು ಯು ಆದ್ದರಿಂದ ಅಲ್ಲದೆ ನಗರದ ಮೇಲಿನ ಏಕೆಂದರೆ ರಷ್ಟು ಎಂಬುದನ್ನು ಬಾರಿ ಎಂದರೆ ಹಿಂದಿನ ಆದರೂ ಆದ ಸಂಬಂಧಿಸಿದ ಮತ್ತೊಂದು ಸಿ ಆತನ ".split(" ")),e.kn.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.kn.tokenizer=function(t){if(!arguments.length||null==t||void 0==t)return[];if(Array.isArray(t))return t.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var n=t.toString().toLowerCase().replace(/^\s+/,"");return r.cut(n).split("|")},e.Pipeline.registerFunction(e.kn.stemmer,"stemmer-kn"),e.Pipeline.registerFunction(e.kn.stopWordFilter,"stopWordFilter-kn")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ko.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ko.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.multi.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.multi.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){e.multiLanguage=function(){for(var t=Array.prototype.slice.call(arguments),i=t.join("-"),r="",n=[],s=[],p=0;p<t.length;++p)"en"==t[p]?(r+="\\w",n.unshift(e.stopWordFilter),n.push(e.stemmer),s.push(e.stemmer)):(r+=e[t[p]].wordCharacters,e[t[p]].stopWordFilter&&n.unshift(e[t[p]].stopWordFilter),e[t[p]].stemmer&&(n.push(e[t[p]].stemmer),s.push(e[t[p]].stemmer)));var o=e.trimmerSupport.generateTrimmer(r);return e.Pipeline.registerFunction(o,"lunr-multi-trimmer-"+i),n.unshift(o),function(){this.pipeline.reset(),this.pipeline.add.apply(this.pipeline,n),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add.apply(this.searchPipeline,s))}}}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.nl.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.nl.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.no.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.no.min.js
vendored
Normal file
@@ -0,0 +1,18 @@
|
||||
/*!
|
||||
* Lunr languages, `Norwegian` language
|
||||
* https://github.com/MihaiValentin/lunr-languages
|
||||
*
|
||||
* Copyright 2014, Mihai Valentin
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
/*!
|
||||
* based on
|
||||
* Snowball JavaScript Library v0.3
|
||||
* http://code.google.com/p/urim/
|
||||
* http://snowball.tartarus.org/
|
||||
*
|
||||
* Copyright 2010, Oleg Mazko
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.no=function(){this.pipeline.reset(),this.pipeline.add(e.no.trimmer,e.no.stopWordFilter,e.no.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.no.stemmer))},e.no.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.no.trimmer=e.trimmerSupport.generateTrimmer(e.no.wordCharacters),e.Pipeline.registerFunction(e.no.trimmer,"trimmer-no"),e.no.stemmer=function(){var r=e.stemmerSupport.Among,n=e.stemmerSupport.SnowballProgram,i=new function(){function e(){var e,r=w.cursor+3;if(a=w.limit,0<=r||r<=w.limit){for(s=r;;){if(e=w.cursor,w.in_grouping(d,97,248)){w.cursor=e;break}if(e>=w.limit)return;w.cursor=e+1}for(;!w.out_grouping(d,97,248);){if(w.cursor>=w.limit)return;w.cursor++}a=w.cursor,a<s&&(a=s)}}function i(){var e,r,n;if(w.cursor>=a&&(r=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,e=w.find_among_b(m,29),w.limit_backward=r,e))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:n=w.limit-w.cursor,w.in_grouping_b(c,98,122)?w.slice_del():(w.cursor=w.limit-n,w.eq_s_b(1,"k")&&w.out_grouping_b(d,97,248)&&w.slice_del());break;case 3:w.slice_from("er")}}function t(){var e,r=w.limit-w.cursor;w.cursor>=a&&(e=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,w.find_among_b(u,2)?(w.bra=w.cursor,w.limit_backward=e,w.cursor=w.limit-r,w.cursor>w.limit_backward&&(w.cursor--,w.bra=w.cursor,w.slice_del())):w.limit_backward=e)}function o(){var e,r;w.cursor>=a&&(r=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,e=w.find_among_b(l,11),e?(w.bra=w.cursor,w.limit_backward=r,1==e&&w.slice_del()):w.limit_backward=r)}var s,a,m=[new r("a",-1,1),new r("e",-1,1),new r("ede",1,1),new r("ande",1,1),new r("ende",1,1),new r("ane",1,1),new r("ene",1,1),new r("hetene",6,1),new r("erte",1,3),new r("en",-1,1),new r("heten",9,1),new r("ar",-1,1),new r("er",-1,1),new r("heter",12,1),new r("s",-1,2),new r("as",14,1),new r("es",14,1),new r("edes",16,1),new r("endes",16,1),new r("enes",16,1),new r("hetenes",19,1),new r("ens",14,1),new r("hetens",21,1),new r("ers",14,1),new r("ets",14,1),new r("et",-1,1),new r("het",25,1),new r("ert",-1,3),new r("ast",-1,1)],u=[new r("dt",-1,-1),new r("vt",-1,-1)],l=[new r("leg",-1,1),new r("eleg",0,1),new r("ig",-1,1),new r("eig",2,1),new r("lig",2,1),new r("elig",4,1),new r("els",-1,1),new r("lov",-1,1),new r("elov",7,1),new r("slov",7,1),new r("hetslov",9,1)],d=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,48,0,128],c=[119,125,149,1],w=new n;this.setCurrent=function(e){w.setCurrent(e)},this.getCurrent=function(){return w.getCurrent()},this.stem=function(){var r=w.cursor;return e(),w.limit_backward=r,w.cursor=w.limit,i(),w.cursor=w.limit,t(),w.cursor=w.limit,o(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return i.setCurrent(e),i.stem(),i.getCurrent()}):(i.setCurrent(e),i.stem(),i.getCurrent())}}(),e.Pipeline.registerFunction(e.no.stemmer,"stemmer-no"),e.no.stopWordFilter=e.generateStopWordFilter("alle at av bare begge ble blei bli blir blitt både båe da de deg dei deim deira deires dem den denne der dere deres det dette di din disse ditt du dykk dykkar då eg ein eit eitt eller elles en enn er et ett etter for fordi fra før ha hadde han hans har hennar henne hennes her hjå ho hoe honom hoss hossen hun hva hvem hver hvilke hvilken hvis hvor hvordan hvorfor i ikke ikkje ikkje ingen ingi inkje inn inni ja jeg kan kom korleis korso kun kunne kva kvar kvarhelst kven kvi kvifor man mange me med medan meg meget mellom men mi min mine mitt mot mykje ned no noe noen noka noko nokon nokor nokre nå når og også om opp oss over på samme seg selv si si sia sidan siden sin sine sitt sjøl skal skulle slik so som som somme somt så sånn til um upp ut uten var vart varte ved vere verte vi vil ville vore vors vort vår være være vært å".split(" ")),e.Pipeline.registerFunction(e.no.stopWordFilter,"stopWordFilter-no")}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.pt.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.pt.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.ro.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.ro.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
18
omniread/wiki/assets/javascripts/lunr/min/lunr.ru.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.ru.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.sa.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.sa.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.sa=function(){this.pipeline.reset(),this.pipeline.add(e.sa.trimmer,e.sa.stopWordFilter,e.sa.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.sa.stemmer))},e.sa.wordCharacters="ऀ-ःऄ-एऐ-टठ-यर-िी-ॏॐ-य़ॠ-९॰-ॿ꣠-꣱ꣲ-ꣷ꣸-ꣻ꣼-ꣽꣾ-ꣿᆰ0-ᆰ9",e.sa.trimmer=e.trimmerSupport.generateTrimmer(e.sa.wordCharacters),e.Pipeline.registerFunction(e.sa.trimmer,"trimmer-sa"),e.sa.stopWordFilter=e.generateStopWordFilter('तथा अयम् एकम् इत्यस्मिन् तथा तत् वा अयम् इत्यस्य ते आहूत उपरि तेषाम् किन्तु तेषाम् तदा इत्यनेन अधिकः इत्यस्य तत् केचन बहवः द्वि तथा महत्वपूर्णः अयम् अस्य विषये अयं अस्ति तत् प्रथमः विषये इत्युपरि इत्युपरि इतर अधिकतमः अधिकः अपि सामान्यतया ठ इतरेतर नूतनम् द न्यूनम् कश्चित् वा विशालः द सः अस्ति तदनुसारम् तत्र अस्ति केवलम् अपि अत्र सर्वे विविधाः तत् बहवः यतः इदानीम् द दक्षिण इत्यस्मै तस्य उपरि नथ अतीव कार्यम् सर्वे एकैकम् इत्यादि। एते सन्ति उत इत्थम् मध्ये एतदर्थं . स कस्य प्रथमः श्री. करोति अस्मिन् प्रकारः निर्मिता कालः तत्र कर्तुं समान अधुना ते सन्ति स एकः अस्ति सः अर्थात् तेषां कृते . स्थितम् विशेषः अग्रिम तेषाम् समान स्रोतः ख म समान इदानीमपि अधिकतया करोतु ते समान इत्यस्य वीथी सह यस्मिन् कृतवान् धृतः तदा पुनः पूर्वं सः आगतः किम् कुल इतर पुरा मात्रा स विषये उ अतएव अपि नगरस्य उपरि यतः प्रतिशतं कतरः कालः साधनानि भूत तथापि जात सम्बन्धि अन्यत् ग अतः अस्माकं स्वकीयाः अस्माकं इदानीं अन्तः इत्यादयः भवन्तः इत्यादयः एते एताः तस्य अस्य इदम् एते तेषां तेषां तेषां तान् तेषां तेषां तेषां समानः सः एकः च तादृशाः बहवः अन्ये च वदन्ति यत् कियत् कस्मै कस्मै यस्मै यस्मै यस्मै यस्मै न अतिनीचः किन्तु प्रथमं सम्पूर्णतया ततः चिरकालानन्तरं पुस्तकं सम्पूर्णतया अन्तः किन्तु अत्र वा इह इव श्रद्धाय अवशिष्यते परन्तु अन्ये वर्गाः सन्ति ते सन्ति शक्नुवन्ति सर्वे मिलित्वा सर्वे एकत्र"'.split(" ")),e.sa.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.sa.tokenizer=function(t){if(!arguments.length||null==t||void 0==t)return[];if(Array.isArray(t))return t.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var i=t.toString().toLowerCase().replace(/^\s+/,"");return r.cut(i).split("|")},e.Pipeline.registerFunction(e.sa.stemmer,"stemmer-sa"),e.Pipeline.registerFunction(e.sa.stopWordFilter,"stopWordFilter-sa")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.stemmer.support.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.stemmer.support.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(r,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(r.lunr)}(this,function(){return function(r){r.stemmerSupport={Among:function(r,t,i,s){if(this.toCharArray=function(r){for(var t=r.length,i=new Array(t),s=0;s<t;s++)i[s]=r.charCodeAt(s);return i},!r&&""!=r||!t&&0!=t||!i)throw"Bad Among initialisation: s:"+r+", substring_i: "+t+", result: "+i;this.s_size=r.length,this.s=this.toCharArray(r),this.substring_i=t,this.result=i,this.method=s},SnowballProgram:function(){var r;return{bra:0,ket:0,limit:0,cursor:0,limit_backward:0,setCurrent:function(t){r=t,this.cursor=0,this.limit=t.length,this.limit_backward=0,this.bra=this.cursor,this.ket=this.limit},getCurrent:function(){var t=r;return r=null,t},in_grouping:function(t,i,s){if(this.cursor<this.limit){var e=r.charCodeAt(this.cursor);if(e<=s&&e>=i&&(e-=i,t[e>>3]&1<<(7&e)))return this.cursor++,!0}return!1},in_grouping_b:function(t,i,s){if(this.cursor>this.limit_backward){var e=r.charCodeAt(this.cursor-1);if(e<=s&&e>=i&&(e-=i,t[e>>3]&1<<(7&e)))return this.cursor--,!0}return!1},out_grouping:function(t,i,s){if(this.cursor<this.limit){var e=r.charCodeAt(this.cursor);if(e>s||e<i)return this.cursor++,!0;if(e-=i,!(t[e>>3]&1<<(7&e)))return this.cursor++,!0}return!1},out_grouping_b:function(t,i,s){if(this.cursor>this.limit_backward){var e=r.charCodeAt(this.cursor-1);if(e>s||e<i)return this.cursor--,!0;if(e-=i,!(t[e>>3]&1<<(7&e)))return this.cursor--,!0}return!1},eq_s:function(t,i){if(this.limit-this.cursor<t)return!1;for(var s=0;s<t;s++)if(r.charCodeAt(this.cursor+s)!=i.charCodeAt(s))return!1;return this.cursor+=t,!0},eq_s_b:function(t,i){if(this.cursor-this.limit_backward<t)return!1;for(var s=0;s<t;s++)if(r.charCodeAt(this.cursor-t+s)!=i.charCodeAt(s))return!1;return this.cursor-=t,!0},find_among:function(t,i){for(var s=0,e=i,n=this.cursor,u=this.limit,o=0,h=0,c=!1;;){for(var a=s+(e-s>>1),f=0,l=o<h?o:h,_=t[a],m=l;m<_.s_size;m++){if(n+l==u){f=-1;break}if(f=r.charCodeAt(n+l)-_.s[m])break;l++}if(f<0?(e=a,h=l):(s=a,o=l),e-s<=1){if(s>0||e==s||c)break;c=!0}}for(;;){var _=t[s];if(o>=_.s_size){if(this.cursor=n+_.s_size,!_.method)return _.result;var b=_.method();if(this.cursor=n+_.s_size,b)return _.result}if((s=_.substring_i)<0)return 0}},find_among_b:function(t,i){for(var s=0,e=i,n=this.cursor,u=this.limit_backward,o=0,h=0,c=!1;;){for(var a=s+(e-s>>1),f=0,l=o<h?o:h,_=t[a],m=_.s_size-1-l;m>=0;m--){if(n-l==u){f=-1;break}if(f=r.charCodeAt(n-1-l)-_.s[m])break;l++}if(f<0?(e=a,h=l):(s=a,o=l),e-s<=1){if(s>0||e==s||c)break;c=!0}}for(;;){var _=t[s];if(o>=_.s_size){if(this.cursor=n-_.s_size,!_.method)return _.result;var b=_.method();if(this.cursor=n-_.s_size,b)return _.result}if((s=_.substring_i)<0)return 0}},replace_s:function(t,i,s){var e=s.length-(i-t),n=r.substring(0,t),u=r.substring(i);return r=n+s+u,this.limit+=e,this.cursor>=i?this.cursor+=e:this.cursor>t&&(this.cursor=t),e},slice_check:function(){if(this.bra<0||this.bra>this.ket||this.ket>this.limit||this.limit>r.length)throw"faulty slice operation"},slice_from:function(r){this.slice_check(),this.replace_s(this.bra,this.ket,r)},slice_del:function(){this.slice_from("")},insert:function(r,t,i){var s=this.replace_s(r,t,i);r<=this.bra&&(this.bra+=s),r<=this.ket&&(this.ket+=s)},slice_to:function(){return this.slice_check(),r.substring(this.bra,this.ket)},eq_v_b:function(r){return this.eq_s_b(r.length,r)}}}},r.trimmerSupport={generateTrimmer:function(r){var t=new RegExp("^[^"+r+"]+"),i=new RegExp("[^"+r+"]+$");return function(r){return"function"==typeof r.update?r.update(function(r){return r.replace(t,"").replace(i,"")}):r.replace(t,"").replace(i,"")}}}}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.sv.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.sv.min.js
vendored
Normal file
@@ -0,0 +1,18 @@
|
||||
/*!
|
||||
* Lunr languages, `Swedish` language
|
||||
* https://github.com/MihaiValentin/lunr-languages
|
||||
*
|
||||
* Copyright 2014, Mihai Valentin
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
/*!
|
||||
* based on
|
||||
* Snowball JavaScript Library v0.3
|
||||
* http://code.google.com/p/urim/
|
||||
* http://snowball.tartarus.org/
|
||||
*
|
||||
* Copyright 2010, Oleg Mazko
|
||||
* http://www.mozilla.org/MPL/
|
||||
*/
|
||||
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.sv=function(){this.pipeline.reset(),this.pipeline.add(e.sv.trimmer,e.sv.stopWordFilter,e.sv.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.sv.stemmer))},e.sv.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.sv.trimmer=e.trimmerSupport.generateTrimmer(e.sv.wordCharacters),e.Pipeline.registerFunction(e.sv.trimmer,"trimmer-sv"),e.sv.stemmer=function(){var r=e.stemmerSupport.Among,n=e.stemmerSupport.SnowballProgram,t=new function(){function e(){var e,r=w.cursor+3;if(o=w.limit,0<=r||r<=w.limit){for(a=r;;){if(e=w.cursor,w.in_grouping(l,97,246)){w.cursor=e;break}if(w.cursor=e,w.cursor>=w.limit)return;w.cursor++}for(;!w.out_grouping(l,97,246);){if(w.cursor>=w.limit)return;w.cursor++}o=w.cursor,o<a&&(o=a)}}function t(){var e,r=w.limit_backward;if(w.cursor>=o&&(w.limit_backward=o,w.cursor=w.limit,w.ket=w.cursor,e=w.find_among_b(u,37),w.limit_backward=r,e))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:w.in_grouping_b(d,98,121)&&w.slice_del()}}function i(){var e=w.limit_backward;w.cursor>=o&&(w.limit_backward=o,w.cursor=w.limit,w.find_among_b(c,7)&&(w.cursor=w.limit,w.ket=w.cursor,w.cursor>w.limit_backward&&(w.bra=--w.cursor,w.slice_del())),w.limit_backward=e)}function s(){var e,r;if(w.cursor>=o){if(r=w.limit_backward,w.limit_backward=o,w.cursor=w.limit,w.ket=w.cursor,e=w.find_among_b(m,5))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:w.slice_from("lös");break;case 3:w.slice_from("full")}w.limit_backward=r}}var a,o,u=[new r("a",-1,1),new r("arna",0,1),new r("erna",0,1),new r("heterna",2,1),new r("orna",0,1),new r("ad",-1,1),new r("e",-1,1),new r("ade",6,1),new r("ande",6,1),new r("arne",6,1),new r("are",6,1),new r("aste",6,1),new r("en",-1,1),new r("anden",12,1),new r("aren",12,1),new r("heten",12,1),new r("ern",-1,1),new r("ar",-1,1),new r("er",-1,1),new r("heter",18,1),new r("or",-1,1),new r("s",-1,2),new r("as",21,1),new r("arnas",22,1),new r("ernas",22,1),new r("ornas",22,1),new r("es",21,1),new r("ades",26,1),new r("andes",26,1),new r("ens",21,1),new r("arens",29,1),new r("hetens",29,1),new r("erns",21,1),new r("at",-1,1),new r("andet",-1,1),new r("het",-1,1),new r("ast",-1,1)],c=[new r("dd",-1,-1),new r("gd",-1,-1),new r("nn",-1,-1),new r("dt",-1,-1),new r("gt",-1,-1),new r("kt",-1,-1),new r("tt",-1,-1)],m=[new r("ig",-1,1),new r("lig",0,1),new r("els",-1,1),new r("fullt",-1,3),new r("löst",-1,2)],l=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,24,0,32],d=[119,127,149],w=new n;this.setCurrent=function(e){w.setCurrent(e)},this.getCurrent=function(){return w.getCurrent()},this.stem=function(){var r=w.cursor;return e(),w.limit_backward=r,w.cursor=w.limit,t(),w.cursor=w.limit,i(),w.cursor=w.limit,s(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return t.setCurrent(e),t.stem(),t.getCurrent()}):(t.setCurrent(e),t.stem(),t.getCurrent())}}(),e.Pipeline.registerFunction(e.sv.stemmer,"stemmer-sv"),e.sv.stopWordFilter=e.generateStopWordFilter("alla allt att av blev bli blir blivit de dem den denna deras dess dessa det detta dig din dina ditt du där då efter ej eller en er era ert ett från för ha hade han hans har henne hennes hon honom hur här i icke ingen inom inte jag ju kan kunde man med mellan men mig min mina mitt mot mycket ni nu när någon något några och om oss på samma sedan sig sin sina sitta själv skulle som så sådan sådana sådant till under upp ut utan vad var vara varför varit varje vars vart vem vi vid vilka vilkas vilken vilket vår våra vårt än är åt över".split(" ")),e.Pipeline.registerFunction(e.sv.stopWordFilter,"stopWordFilter-sv")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ta.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.ta.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.ta=function(){this.pipeline.reset(),this.pipeline.add(e.ta.trimmer,e.ta.stopWordFilter,e.ta.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.ta.stemmer))},e.ta.wordCharacters="-உஊ-ஏஐ-ஙச-ட-னப-யர-ஹ-ிீ-ொ-ௐ---௩௪-௯௰-௹௺-a-zA-Za-zA-Z0-90-9",e.ta.trimmer=e.trimmerSupport.generateTrimmer(e.ta.wordCharacters),e.Pipeline.registerFunction(e.ta.trimmer,"trimmer-ta"),e.ta.stopWordFilter=e.generateStopWordFilter("அங்கு அங்கே அது அதை அந்த அவர் அவர்கள் அவள் அவன் அவை ஆக ஆகவே ஆகையால் ஆதலால் ஆதலினால் ஆனாலும் ஆனால் இங்கு இங்கே இது இதை இந்த இப்படி இவர் இவர்கள் இவள் இவன் இவை இவ்வளவு உனக்கு உனது உன் உன்னால் எங்கு எங்கே எது எதை எந்த எப்படி எவர் எவர்கள் எவள் எவன் எவை எவ்வளவு எனக்கு எனது எனவே என் என்ன என்னால் ஏது ஏன் தனது தன்னால் தானே தான் நாங்கள் நாம் நான் நீ நீங்கள்".split(" ")),e.ta.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var t=e.wordcut;t.init(),e.ta.tokenizer=function(r){if(!arguments.length||null==r||void 0==r)return[];if(Array.isArray(r))return r.map(function(t){return isLunr2?new e.Token(t.toLowerCase()):t.toLowerCase()});var i=r.toString().toLowerCase().replace(/^\s+/,"");return t.cut(i).split("|")},e.Pipeline.registerFunction(e.ta.stemmer,"stemmer-ta"),e.Pipeline.registerFunction(e.ta.stopWordFilter,"stopWordFilter-ta")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.te.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.te.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.te=function(){this.pipeline.reset(),this.pipeline.add(e.te.trimmer,e.te.stopWordFilter,e.te.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.te.stemmer))},e.te.wordCharacters="ఀ-ఄఅ-ఔక-హా-ౌౕ-ౖౘ-ౚౠ-ౡౢ-ౣ౦-౯౸-౿఼ఽ్ౝ౷",e.te.trimmer=e.trimmerSupport.generateTrimmer(e.te.wordCharacters),e.Pipeline.registerFunction(e.te.trimmer,"trimmer-te"),e.te.stopWordFilter=e.generateStopWordFilter("అందరూ అందుబాటులో అడగండి అడగడం అడ్డంగా అనుగుణంగా అనుమతించు అనుమతిస్తుంది అయితే ఇప్పటికే ఉన్నారు ఎక్కడైనా ఎప్పుడు ఎవరైనా ఎవరో ఏ ఏదైనా ఏమైనప్పటికి ఒక ఒకరు కనిపిస్తాయి కాదు కూడా గా గురించి చుట్టూ చేయగలిగింది తగిన తర్వాత దాదాపు దూరంగా నిజంగా పై ప్రకారం ప్రక్కన మధ్య మరియు మరొక మళ్ళీ మాత్రమే మెచ్చుకో వద్ద వెంట వేరుగా వ్యతిరేకంగా సంబంధం".split(" ")),e.te.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var t=e.wordcut;t.init(),e.te.tokenizer=function(r){if(!arguments.length||null==r||void 0==r)return[];if(Array.isArray(r))return r.map(function(t){return isLunr2?new e.Token(t.toLowerCase()):t.toLowerCase()});var i=r.toString().toLowerCase().replace(/^\s+/,"");return t.cut(i).split("|")},e.Pipeline.registerFunction(e.te.stemmer,"stemmer-te"),e.Pipeline.registerFunction(e.te.stopWordFilter,"stopWordFilter-te")}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.th.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.th.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var r="2"==e.version[0];e.th=function(){this.pipeline.reset(),this.pipeline.add(e.th.trimmer),r?this.tokenizer=e.th.tokenizer:(e.tokenizer&&(e.tokenizer=e.th.tokenizer),this.tokenizerFn&&(this.tokenizerFn=e.th.tokenizer))},e.th.wordCharacters="[-]",e.th.trimmer=e.trimmerSupport.generateTrimmer(e.th.wordCharacters),e.Pipeline.registerFunction(e.th.trimmer,"trimmer-th");var t=e.wordcut;t.init(),e.th.tokenizer=function(i){if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(t){return r?new e.Token(t):t});var n=i.toString().replace(/^\s+/,"");return t.cut(n).split("|")}}});
|
||||
18
omniread/wiki/assets/javascripts/lunr/min/lunr.tr.min.js
vendored
Normal file
18
omniread/wiki/assets/javascripts/lunr/min/lunr.tr.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/javascripts/lunr/min/lunr.vi.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.vi.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.vi=function(){this.pipeline.reset(),this.pipeline.add(e.vi.stopWordFilter,e.vi.trimmer)},e.vi.wordCharacters="[A-Za-ẓ̀͐́͑̉̃̓ÂâÊêÔôĂ-ăĐ-đƠ-ơƯ-ư]",e.vi.trimmer=e.trimmerSupport.generateTrimmer(e.vi.wordCharacters),e.Pipeline.registerFunction(e.vi.trimmer,"trimmer-vi"),e.vi.stopWordFilter=e.generateStopWordFilter("là cái nhưng mà".split(" "))}});
|
||||
1
omniread/wiki/assets/javascripts/lunr/min/lunr.zh.min.js
vendored
Normal file
1
omniread/wiki/assets/javascripts/lunr/min/lunr.zh.min.js
vendored
Normal file
@@ -0,0 +1 @@
|
||||
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r(require("@node-rs/jieba")):r()(e.lunr)}(this,function(e){return function(r,t){if(void 0===r)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===r.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var i="2"==r.version[0];r.zh=function(){this.pipeline.reset(),this.pipeline.add(r.zh.trimmer,r.zh.stopWordFilter,r.zh.stemmer),i?this.tokenizer=r.zh.tokenizer:(r.tokenizer&&(r.tokenizer=r.zh.tokenizer),this.tokenizerFn&&(this.tokenizerFn=r.zh.tokenizer))},r.zh.tokenizer=function(n){if(!arguments.length||null==n||void 0==n)return[];if(Array.isArray(n))return n.map(function(e){return i?new r.Token(e.toLowerCase()):e.toLowerCase()});t&&e.load(t);var o=n.toString().trim().toLowerCase(),s=[];e.cut(o,!0).forEach(function(e){s=s.concat(e.split(" "))}),s=s.filter(function(e){return!!e});var u=0;return s.map(function(e,t){if(i){var n=o.indexOf(e,u),s={};return s.position=[n,e.length],s.index=t,u=n,new r.Token(e,s)}return e})},r.zh.wordCharacters="\\w一-龥",r.zh.trimmer=r.trimmerSupport.generateTrimmer(r.zh.wordCharacters),r.Pipeline.registerFunction(r.zh.trimmer,"trimmer-zh"),r.zh.stemmer=function(){return function(e){return e}}(),r.Pipeline.registerFunction(r.zh.stemmer,"stemmer-zh"),r.zh.stopWordFilter=r.generateStopWordFilter("的 一 不 在 人 有 是 为 為 以 于 於 上 他 而 后 後 之 来 來 及 了 因 下 可 到 由 这 這 与 與 也 此 但 并 並 个 個 其 已 无 無 小 我 们 們 起 最 再 今 去 好 只 又 或 很 亦 某 把 那 你 乃 它 吧 被 比 别 趁 当 當 从 從 得 打 凡 儿 兒 尔 爾 该 該 各 给 給 跟 和 何 还 還 即 几 幾 既 看 据 據 距 靠 啦 另 么 麽 每 嘛 拿 哪 您 凭 憑 且 却 卻 让 讓 仍 啥 如 若 使 谁 誰 虽 雖 随 隨 同 所 她 哇 嗡 往 些 向 沿 哟 喲 用 咱 则 則 怎 曾 至 致 着 著 诸 諸 自".split(" ")),r.Pipeline.registerFunction(r.zh.stopWordFilter,"stopWordFilter-zh")}});
|
||||
206
omniread/wiki/assets/javascripts/lunr/tinyseg.js
Normal file
206
omniread/wiki/assets/javascripts/lunr/tinyseg.js
Normal file
@@ -0,0 +1,206 @@
|
||||
/**
|
||||
* export the module via AMD, CommonJS or as a browser global
|
||||
* Export code from https://github.com/umdjs/umd/blob/master/returnExports.js
|
||||
*/
|
||||
;(function (root, factory) {
|
||||
if (typeof define === 'function' && define.amd) {
|
||||
// AMD. Register as an anonymous module.
|
||||
define(factory)
|
||||
} else if (typeof exports === 'object') {
|
||||
/**
|
||||
* Node. Does not work with strict CommonJS, but
|
||||
* only CommonJS-like environments that support module.exports,
|
||||
* like Node.
|
||||
*/
|
||||
module.exports = factory()
|
||||
} else {
|
||||
// Browser globals (root is window)
|
||||
factory()(root.lunr);
|
||||
}
|
||||
}(this, function () {
|
||||
/**
|
||||
* Just return a value to define the module export.
|
||||
* This example returns an object, but the module
|
||||
* can return a function as the exported value.
|
||||
*/
|
||||
|
||||
return function(lunr) {
|
||||
// TinySegmenter 0.1 -- Super compact Japanese tokenizer in Javascript
|
||||
// (c) 2008 Taku Kudo <taku@chasen.org>
|
||||
// TinySegmenter is freely distributable under the terms of a new BSD licence.
|
||||
// For details, see http://chasen.org/~taku/software/TinySegmenter/LICENCE.txt
|
||||
|
||||
function TinySegmenter() {
|
||||
var patterns = {
|
||||
"[一二三四五六七八九十百千万億兆]":"M",
|
||||
"[一-龠々〆ヵヶ]":"H",
|
||||
"[ぁ-ん]":"I",
|
||||
"[ァ-ヴーア-ン゙ー]":"K",
|
||||
"[a-zA-Za-zA-Z]":"A",
|
||||
"[0-90-9]":"N"
|
||||
}
|
||||
this.chartype_ = [];
|
||||
for (var i in patterns) {
|
||||
var regexp = new RegExp(i);
|
||||
this.chartype_.push([regexp, patterns[i]]);
|
||||
}
|
||||
|
||||
this.BIAS__ = -332
|
||||
this.BC1__ = {"HH":6,"II":2461,"KH":406,"OH":-1378};
|
||||
this.BC2__ = {"AA":-3267,"AI":2744,"AN":-878,"HH":-4070,"HM":-1711,"HN":4012,"HO":3761,"IA":1327,"IH":-1184,"II":-1332,"IK":1721,"IO":5492,"KI":3831,"KK":-8741,"MH":-3132,"MK":3334,"OO":-2920};
|
||||
this.BC3__ = {"HH":996,"HI":626,"HK":-721,"HN":-1307,"HO":-836,"IH":-301,"KK":2762,"MK":1079,"MM":4034,"OA":-1652,"OH":266};
|
||||
this.BP1__ = {"BB":295,"OB":304,"OO":-125,"UB":352};
|
||||
this.BP2__ = {"BO":60,"OO":-1762};
|
||||
this.BQ1__ = {"BHH":1150,"BHM":1521,"BII":-1158,"BIM":886,"BMH":1208,"BNH":449,"BOH":-91,"BOO":-2597,"OHI":451,"OIH":-296,"OKA":1851,"OKH":-1020,"OKK":904,"OOO":2965};
|
||||
this.BQ2__ = {"BHH":118,"BHI":-1159,"BHM":466,"BIH":-919,"BKK":-1720,"BKO":864,"OHH":-1139,"OHM":-181,"OIH":153,"UHI":-1146};
|
||||
this.BQ3__ = {"BHH":-792,"BHI":2664,"BII":-299,"BKI":419,"BMH":937,"BMM":8335,"BNN":998,"BOH":775,"OHH":2174,"OHM":439,"OII":280,"OKH":1798,"OKI":-793,"OKO":-2242,"OMH":-2402,"OOO":11699};
|
||||
this.BQ4__ = {"BHH":-3895,"BIH":3761,"BII":-4654,"BIK":1348,"BKK":-1806,"BMI":-3385,"BOO":-12396,"OAH":926,"OHH":266,"OHK":-2036,"ONN":-973};
|
||||
this.BW1__ = {",と":660,",同":727,"B1あ":1404,"B1同":542,"、と":660,"、同":727,"」と":1682,"あっ":1505,"いう":1743,"いっ":-2055,"いる":672,"うし":-4817,"うん":665,"から":3472,"がら":600,"こう":-790,"こと":2083,"こん":-1262,"さら":-4143,"さん":4573,"した":2641,"して":1104,"すで":-3399,"そこ":1977,"それ":-871,"たち":1122,"ため":601,"った":3463,"つい":-802,"てい":805,"てき":1249,"でき":1127,"です":3445,"では":844,"とい":-4915,"とみ":1922,"どこ":3887,"ない":5713,"なっ":3015,"など":7379,"なん":-1113,"にし":2468,"には":1498,"にも":1671,"に対":-912,"の一":-501,"の中":741,"ませ":2448,"まで":1711,"まま":2600,"まる":-2155,"やむ":-1947,"よっ":-2565,"れた":2369,"れで":-913,"をし":1860,"を見":731,"亡く":-1886,"京都":2558,"取り":-2784,"大き":-2604,"大阪":1497,"平方":-2314,"引き":-1336,"日本":-195,"本当":-2423,"毎日":-2113,"目指":-724,"B1あ":1404,"B1同":542,"」と":1682};
|
||||
this.BW2__ = {"..":-11822,"11":-669,"――":-5730,"−−":-13175,"いう":-1609,"うか":2490,"かし":-1350,"かも":-602,"から":-7194,"かれ":4612,"がい":853,"がら":-3198,"きた":1941,"くな":-1597,"こと":-8392,"この":-4193,"させ":4533,"され":13168,"さん":-3977,"しい":-1819,"しか":-545,"した":5078,"して":972,"しな":939,"その":-3744,"たい":-1253,"たた":-662,"ただ":-3857,"たち":-786,"たと":1224,"たは":-939,"った":4589,"って":1647,"っと":-2094,"てい":6144,"てき":3640,"てく":2551,"ては":-3110,"ても":-3065,"でい":2666,"でき":-1528,"でし":-3828,"です":-4761,"でも":-4203,"とい":1890,"とこ":-1746,"とと":-2279,"との":720,"とみ":5168,"とも":-3941,"ない":-2488,"なが":-1313,"など":-6509,"なの":2614,"なん":3099,"にお":-1615,"にし":2748,"にな":2454,"によ":-7236,"に対":-14943,"に従":-4688,"に関":-11388,"のか":2093,"ので":-7059,"のに":-6041,"のの":-6125,"はい":1073,"はが":-1033,"はず":-2532,"ばれ":1813,"まし":-1316,"まで":-6621,"まれ":5409,"めて":-3153,"もい":2230,"もの":-10713,"らか":-944,"らし":-1611,"らに":-1897,"りし":651,"りま":1620,"れた":4270,"れて":849,"れば":4114,"ろう":6067,"われ":7901,"を通":-11877,"んだ":728,"んな":-4115,"一人":602,"一方":-1375,"一日":970,"一部":-1051,"上が":-4479,"会社":-1116,"出て":2163,"分の":-7758,"同党":970,"同日":-913,"大阪":-2471,"委員":-1250,"少な":-1050,"年度":-8669,"年間":-1626,"府県":-2363,"手権":-1982,"新聞":-4066,"日新":-722,"日本":-7068,"日米":3372,"曜日":-601,"朝鮮":-2355,"本人":-2697,"東京":-1543,"然と":-1384,"社会":-1276,"立て":-990,"第に":-1612,"米国":-4268,"11":-669};
|
||||
this.BW3__ = {"あた":-2194,"あり":719,"ある":3846,"い.":-1185,"い。":-1185,"いい":5308,"いえ":2079,"いく":3029,"いた":2056,"いっ":1883,"いる":5600,"いわ":1527,"うち":1117,"うと":4798,"えと":1454,"か.":2857,"か。":2857,"かけ":-743,"かっ":-4098,"かに":-669,"から":6520,"かり":-2670,"が,":1816,"が、":1816,"がき":-4855,"がけ":-1127,"がっ":-913,"がら":-4977,"がり":-2064,"きた":1645,"けど":1374,"こと":7397,"この":1542,"ころ":-2757,"さい":-714,"さを":976,"し,":1557,"し、":1557,"しい":-3714,"した":3562,"して":1449,"しな":2608,"しま":1200,"す.":-1310,"す。":-1310,"する":6521,"ず,":3426,"ず、":3426,"ずに":841,"そう":428,"た.":8875,"た。":8875,"たい":-594,"たの":812,"たり":-1183,"たる":-853,"だ.":4098,"だ。":4098,"だっ":1004,"った":-4748,"って":300,"てい":6240,"てお":855,"ても":302,"です":1437,"でに":-1482,"では":2295,"とう":-1387,"とし":2266,"との":541,"とも":-3543,"どう":4664,"ない":1796,"なく":-903,"など":2135,"に,":-1021,"に、":-1021,"にし":1771,"にな":1906,"には":2644,"の,":-724,"の、":-724,"の子":-1000,"は,":1337,"は、":1337,"べき":2181,"まし":1113,"ます":6943,"まっ":-1549,"まで":6154,"まれ":-793,"らし":1479,"られ":6820,"るる":3818,"れ,":854,"れ、":854,"れた":1850,"れて":1375,"れば":-3246,"れる":1091,"われ":-605,"んだ":606,"んで":798,"カ月":990,"会議":860,"入り":1232,"大会":2217,"始め":1681,"市":965,"新聞":-5055,"日,":974,"日、":974,"社会":2024,"カ月":990};
|
||||
this.TC1__ = {"AAA":1093,"HHH":1029,"HHM":580,"HII":998,"HOH":-390,"HOM":-331,"IHI":1169,"IOH":-142,"IOI":-1015,"IOM":467,"MMH":187,"OOI":-1832};
|
||||
this.TC2__ = {"HHO":2088,"HII":-1023,"HMM":-1154,"IHI":-1965,"KKH":703,"OII":-2649};
|
||||
this.TC3__ = {"AAA":-294,"HHH":346,"HHI":-341,"HII":-1088,"HIK":731,"HOH":-1486,"IHH":128,"IHI":-3041,"IHO":-1935,"IIH":-825,"IIM":-1035,"IOI":-542,"KHH":-1216,"KKA":491,"KKH":-1217,"KOK":-1009,"MHH":-2694,"MHM":-457,"MHO":123,"MMH":-471,"NNH":-1689,"NNO":662,"OHO":-3393};
|
||||
this.TC4__ = {"HHH":-203,"HHI":1344,"HHK":365,"HHM":-122,"HHN":182,"HHO":669,"HIH":804,"HII":679,"HOH":446,"IHH":695,"IHO":-2324,"IIH":321,"III":1497,"IIO":656,"IOO":54,"KAK":4845,"KKA":3386,"KKK":3065,"MHH":-405,"MHI":201,"MMH":-241,"MMM":661,"MOM":841};
|
||||
this.TQ1__ = {"BHHH":-227,"BHHI":316,"BHIH":-132,"BIHH":60,"BIII":1595,"BNHH":-744,"BOHH":225,"BOOO":-908,"OAKK":482,"OHHH":281,"OHIH":249,"OIHI":200,"OIIH":-68};
|
||||
this.TQ2__ = {"BIHH":-1401,"BIII":-1033,"BKAK":-543,"BOOO":-5591};
|
||||
this.TQ3__ = {"BHHH":478,"BHHM":-1073,"BHIH":222,"BHII":-504,"BIIH":-116,"BIII":-105,"BMHI":-863,"BMHM":-464,"BOMH":620,"OHHH":346,"OHHI":1729,"OHII":997,"OHMH":481,"OIHH":623,"OIIH":1344,"OKAK":2792,"OKHH":587,"OKKA":679,"OOHH":110,"OOII":-685};
|
||||
this.TQ4__ = {"BHHH":-721,"BHHM":-3604,"BHII":-966,"BIIH":-607,"BIII":-2181,"OAAA":-2763,"OAKK":180,"OHHH":-294,"OHHI":2446,"OHHO":480,"OHIH":-1573,"OIHH":1935,"OIHI":-493,"OIIH":626,"OIII":-4007,"OKAK":-8156};
|
||||
this.TW1__ = {"につい":-4681,"東京都":2026};
|
||||
this.TW2__ = {"ある程":-2049,"いった":-1256,"ころが":-2434,"しょう":3873,"その後":-4430,"だって":-1049,"ていた":1833,"として":-4657,"ともに":-4517,"もので":1882,"一気に":-792,"初めて":-1512,"同時に":-8097,"大きな":-1255,"対して":-2721,"社会党":-3216};
|
||||
this.TW3__ = {"いただ":-1734,"してい":1314,"として":-4314,"につい":-5483,"にとっ":-5989,"に当た":-6247,"ので,":-727,"ので、":-727,"のもの":-600,"れから":-3752,"十二月":-2287};
|
||||
this.TW4__ = {"いう.":8576,"いう。":8576,"からな":-2348,"してい":2958,"たが,":1516,"たが、":1516,"ている":1538,"という":1349,"ました":5543,"ません":1097,"ようと":-4258,"よると":5865};
|
||||
this.UC1__ = {"A":484,"K":93,"M":645,"O":-505};
|
||||
this.UC2__ = {"A":819,"H":1059,"I":409,"M":3987,"N":5775,"O":646};
|
||||
this.UC3__ = {"A":-1370,"I":2311};
|
||||
this.UC4__ = {"A":-2643,"H":1809,"I":-1032,"K":-3450,"M":3565,"N":3876,"O":6646};
|
||||
this.UC5__ = {"H":313,"I":-1238,"K":-799,"M":539,"O":-831};
|
||||
this.UC6__ = {"H":-506,"I":-253,"K":87,"M":247,"O":-387};
|
||||
this.UP1__ = {"O":-214};
|
||||
this.UP2__ = {"B":69,"O":935};
|
||||
this.UP3__ = {"B":189};
|
||||
this.UQ1__ = {"BH":21,"BI":-12,"BK":-99,"BN":142,"BO":-56,"OH":-95,"OI":477,"OK":410,"OO":-2422};
|
||||
this.UQ2__ = {"BH":216,"BI":113,"OK":1759};
|
||||
this.UQ3__ = {"BA":-479,"BH":42,"BI":1913,"BK":-7198,"BM":3160,"BN":6427,"BO":14761,"OI":-827,"ON":-3212};
|
||||
this.UW1__ = {",":156,"、":156,"「":-463,"あ":-941,"う":-127,"が":-553,"き":121,"こ":505,"で":-201,"と":-547,"ど":-123,"に":-789,"の":-185,"は":-847,"も":-466,"や":-470,"よ":182,"ら":-292,"り":208,"れ":169,"を":-446,"ん":-137,"・":-135,"主":-402,"京":-268,"区":-912,"午":871,"国":-460,"大":561,"委":729,"市":-411,"日":-141,"理":361,"生":-408,"県":-386,"都":-718,"「":-463,"・":-135};
|
||||
this.UW2__ = {",":-829,"、":-829,"〇":892,"「":-645,"」":3145,"あ":-538,"い":505,"う":134,"お":-502,"か":1454,"が":-856,"く":-412,"こ":1141,"さ":878,"ざ":540,"し":1529,"す":-675,"せ":300,"そ":-1011,"た":188,"だ":1837,"つ":-949,"て":-291,"で":-268,"と":-981,"ど":1273,"な":1063,"に":-1764,"の":130,"は":-409,"ひ":-1273,"べ":1261,"ま":600,"も":-1263,"や":-402,"よ":1639,"り":-579,"る":-694,"れ":571,"を":-2516,"ん":2095,"ア":-587,"カ":306,"キ":568,"ッ":831,"三":-758,"不":-2150,"世":-302,"中":-968,"主":-861,"事":492,"人":-123,"会":978,"保":362,"入":548,"初":-3025,"副":-1566,"北":-3414,"区":-422,"大":-1769,"天":-865,"太":-483,"子":-1519,"学":760,"実":1023,"小":-2009,"市":-813,"年":-1060,"強":1067,"手":-1519,"揺":-1033,"政":1522,"文":-1355,"新":-1682,"日":-1815,"明":-1462,"最":-630,"朝":-1843,"本":-1650,"東":-931,"果":-665,"次":-2378,"民":-180,"気":-1740,"理":752,"発":529,"目":-1584,"相":-242,"県":-1165,"立":-763,"第":810,"米":509,"自":-1353,"行":838,"西":-744,"見":-3874,"調":1010,"議":1198,"込":3041,"開":1758,"間":-1257,"「":-645,"」":3145,"ッ":831,"ア":-587,"カ":306,"キ":568};
|
||||
this.UW3__ = {",":4889,"1":-800,"−":-1723,"、":4889,"々":-2311,"〇":5827,"」":2670,"〓":-3573,"あ":-2696,"い":1006,"う":2342,"え":1983,"お":-4864,"か":-1163,"が":3271,"く":1004,"け":388,"げ":401,"こ":-3552,"ご":-3116,"さ":-1058,"し":-395,"す":584,"せ":3685,"そ":-5228,"た":842,"ち":-521,"っ":-1444,"つ":-1081,"て":6167,"で":2318,"と":1691,"ど":-899,"な":-2788,"に":2745,"の":4056,"は":4555,"ひ":-2171,"ふ":-1798,"へ":1199,"ほ":-5516,"ま":-4384,"み":-120,"め":1205,"も":2323,"や":-788,"よ":-202,"ら":727,"り":649,"る":5905,"れ":2773,"わ":-1207,"を":6620,"ん":-518,"ア":551,"グ":1319,"ス":874,"ッ":-1350,"ト":521,"ム":1109,"ル":1591,"ロ":2201,"ン":278,"・":-3794,"一":-1619,"下":-1759,"世":-2087,"両":3815,"中":653,"主":-758,"予":-1193,"二":974,"人":2742,"今":792,"他":1889,"以":-1368,"低":811,"何":4265,"作":-361,"保":-2439,"元":4858,"党":3593,"全":1574,"公":-3030,"六":755,"共":-1880,"円":5807,"再":3095,"分":457,"初":2475,"別":1129,"前":2286,"副":4437,"力":365,"動":-949,"務":-1872,"化":1327,"北":-1038,"区":4646,"千":-2309,"午":-783,"協":-1006,"口":483,"右":1233,"各":3588,"合":-241,"同":3906,"和":-837,"員":4513,"国":642,"型":1389,"場":1219,"外":-241,"妻":2016,"学":-1356,"安":-423,"実":-1008,"家":1078,"小":-513,"少":-3102,"州":1155,"市":3197,"平":-1804,"年":2416,"広":-1030,"府":1605,"度":1452,"建":-2352,"当":-3885,"得":1905,"思":-1291,"性":1822,"戸":-488,"指":-3973,"政":-2013,"教":-1479,"数":3222,"文":-1489,"新":1764,"日":2099,"旧":5792,"昨":-661,"時":-1248,"曜":-951,"最":-937,"月":4125,"期":360,"李":3094,"村":364,"東":-805,"核":5156,"森":2438,"業":484,"氏":2613,"民":-1694,"決":-1073,"法":1868,"海":-495,"無":979,"物":461,"特":-3850,"生":-273,"用":914,"町":1215,"的":7313,"直":-1835,"省":792,"県":6293,"知":-1528,"私":4231,"税":401,"立":-960,"第":1201,"米":7767,"系":3066,"約":3663,"級":1384,"統":-4229,"総":1163,"線":1255,"者":6457,"能":725,"自":-2869,"英":785,"見":1044,"調":-562,"財":-733,"費":1777,"車":1835,"軍":1375,"込":-1504,"通":-1136,"選":-681,"郎":1026,"郡":4404,"部":1200,"金":2163,"長":421,"開":-1432,"間":1302,"関":-1282,"雨":2009,"電":-1045,"非":2066,"駅":1620,"1":-800,"」":2670,"・":-3794,"ッ":-1350,"ア":551,"グ":1319,"ス":874,"ト":521,"ム":1109,"ル":1591,"ロ":2201,"ン":278};
|
||||
this.UW4__ = {",":3930,".":3508,"―":-4841,"、":3930,"。":3508,"〇":4999,"「":1895,"」":3798,"〓":-5156,"あ":4752,"い":-3435,"う":-640,"え":-2514,"お":2405,"か":530,"が":6006,"き":-4482,"ぎ":-3821,"く":-3788,"け":-4376,"げ":-4734,"こ":2255,"ご":1979,"さ":2864,"し":-843,"じ":-2506,"す":-731,"ず":1251,"せ":181,"そ":4091,"た":5034,"だ":5408,"ち":-3654,"っ":-5882,"つ":-1659,"て":3994,"で":7410,"と":4547,"な":5433,"に":6499,"ぬ":1853,"ね":1413,"の":7396,"は":8578,"ば":1940,"ひ":4249,"び":-4134,"ふ":1345,"へ":6665,"べ":-744,"ほ":1464,"ま":1051,"み":-2082,"む":-882,"め":-5046,"も":4169,"ゃ":-2666,"や":2795,"ょ":-1544,"よ":3351,"ら":-2922,"り":-9726,"る":-14896,"れ":-2613,"ろ":-4570,"わ":-1783,"を":13150,"ん":-2352,"カ":2145,"コ":1789,"セ":1287,"ッ":-724,"ト":-403,"メ":-1635,"ラ":-881,"リ":-541,"ル":-856,"ン":-3637,"・":-4371,"ー":-11870,"一":-2069,"中":2210,"予":782,"事":-190,"井":-1768,"人":1036,"以":544,"会":950,"体":-1286,"作":530,"側":4292,"先":601,"党":-2006,"共":-1212,"内":584,"円":788,"初":1347,"前":1623,"副":3879,"力":-302,"動":-740,"務":-2715,"化":776,"区":4517,"協":1013,"参":1555,"合":-1834,"和":-681,"員":-910,"器":-851,"回":1500,"国":-619,"園":-1200,"地":866,"場":-1410,"塁":-2094,"士":-1413,"多":1067,"大":571,"子":-4802,"学":-1397,"定":-1057,"寺":-809,"小":1910,"屋":-1328,"山":-1500,"島":-2056,"川":-2667,"市":2771,"年":374,"庁":-4556,"後":456,"性":553,"感":916,"所":-1566,"支":856,"改":787,"政":2182,"教":704,"文":522,"方":-856,"日":1798,"時":1829,"最":845,"月":-9066,"木":-485,"来":-442,"校":-360,"業":-1043,"氏":5388,"民":-2716,"気":-910,"沢":-939,"済":-543,"物":-735,"率":672,"球":-1267,"生":-1286,"産":-1101,"田":-2900,"町":1826,"的":2586,"目":922,"省":-3485,"県":2997,"空":-867,"立":-2112,"第":788,"米":2937,"系":786,"約":2171,"経":1146,"統":-1169,"総":940,"線":-994,"署":749,"者":2145,"能":-730,"般":-852,"行":-792,"規":792,"警":-1184,"議":-244,"谷":-1000,"賞":730,"車":-1481,"軍":1158,"輪":-1433,"込":-3370,"近":929,"道":-1291,"選":2596,"郎":-4866,"都":1192,"野":-1100,"銀":-2213,"長":357,"間":-2344,"院":-2297,"際":-2604,"電":-878,"領":-1659,"題":-792,"館":-1984,"首":1749,"高":2120,"「":1895,"」":3798,"・":-4371,"ッ":-724,"ー":-11870,"カ":2145,"コ":1789,"セ":1287,"ト":-403,"メ":-1635,"ラ":-881,"リ":-541,"ル":-856,"ン":-3637};
|
||||
this.UW5__ = {",":465,".":-299,"1":-514,"E2":-32768,"]":-2762,"、":465,"。":-299,"「":363,"あ":1655,"い":331,"う":-503,"え":1199,"お":527,"か":647,"が":-421,"き":1624,"ぎ":1971,"く":312,"げ":-983,"さ":-1537,"し":-1371,"す":-852,"だ":-1186,"ち":1093,"っ":52,"つ":921,"て":-18,"で":-850,"と":-127,"ど":1682,"な":-787,"に":-1224,"の":-635,"は":-578,"べ":1001,"み":502,"め":865,"ゃ":3350,"ょ":854,"り":-208,"る":429,"れ":504,"わ":419,"を":-1264,"ん":327,"イ":241,"ル":451,"ン":-343,"中":-871,"京":722,"会":-1153,"党":-654,"務":3519,"区":-901,"告":848,"員":2104,"大":-1296,"学":-548,"定":1785,"嵐":-1304,"市":-2991,"席":921,"年":1763,"思":872,"所":-814,"挙":1618,"新":-1682,"日":218,"月":-4353,"査":932,"格":1356,"機":-1508,"氏":-1347,"田":240,"町":-3912,"的":-3149,"相":1319,"省":-1052,"県":-4003,"研":-997,"社":-278,"空":-813,"統":1955,"者":-2233,"表":663,"語":-1073,"議":1219,"選":-1018,"郎":-368,"長":786,"間":1191,"題":2368,"館":-689,"1":-514,"E2":-32768,"「":363,"イ":241,"ル":451,"ン":-343};
|
||||
this.UW6__ = {",":227,".":808,"1":-270,"E1":306,"、":227,"。":808,"あ":-307,"う":189,"か":241,"が":-73,"く":-121,"こ":-200,"じ":1782,"す":383,"た":-428,"っ":573,"て":-1014,"で":101,"と":-105,"な":-253,"に":-149,"の":-417,"は":-236,"も":-206,"り":187,"る":-135,"を":195,"ル":-673,"ン":-496,"一":-277,"中":201,"件":-800,"会":624,"前":302,"区":1792,"員":-1212,"委":798,"学":-960,"市":887,"広":-695,"後":535,"業":-697,"相":753,"社":-507,"福":974,"空":-822,"者":1811,"連":463,"郎":1082,"1":-270,"E1":306,"ル":-673,"ン":-496};
|
||||
|
||||
return this;
|
||||
}
|
||||
TinySegmenter.prototype.ctype_ = function(str) {
|
||||
for (var i in this.chartype_) {
|
||||
if (str.match(this.chartype_[i][0])) {
|
||||
return this.chartype_[i][1];
|
||||
}
|
||||
}
|
||||
return "O";
|
||||
}
|
||||
|
||||
TinySegmenter.prototype.ts_ = function(v) {
|
||||
if (v) { return v; }
|
||||
return 0;
|
||||
}
|
||||
|
||||
TinySegmenter.prototype.segment = function(input) {
|
||||
if (input == null || input == undefined || input == "") {
|
||||
return [];
|
||||
}
|
||||
var result = [];
|
||||
var seg = ["B3","B2","B1"];
|
||||
var ctype = ["O","O","O"];
|
||||
var o = input.split("");
|
||||
for (i = 0; i < o.length; ++i) {
|
||||
seg.push(o[i]);
|
||||
ctype.push(this.ctype_(o[i]))
|
||||
}
|
||||
seg.push("E1");
|
||||
seg.push("E2");
|
||||
seg.push("E3");
|
||||
ctype.push("O");
|
||||
ctype.push("O");
|
||||
ctype.push("O");
|
||||
var word = seg[3];
|
||||
var p1 = "U";
|
||||
var p2 = "U";
|
||||
var p3 = "U";
|
||||
for (var i = 4; i < seg.length - 3; ++i) {
|
||||
var score = this.BIAS__;
|
||||
var w1 = seg[i-3];
|
||||
var w2 = seg[i-2];
|
||||
var w3 = seg[i-1];
|
||||
var w4 = seg[i];
|
||||
var w5 = seg[i+1];
|
||||
var w6 = seg[i+2];
|
||||
var c1 = ctype[i-3];
|
||||
var c2 = ctype[i-2];
|
||||
var c3 = ctype[i-1];
|
||||
var c4 = ctype[i];
|
||||
var c5 = ctype[i+1];
|
||||
var c6 = ctype[i+2];
|
||||
score += this.ts_(this.UP1__[p1]);
|
||||
score += this.ts_(this.UP2__[p2]);
|
||||
score += this.ts_(this.UP3__[p3]);
|
||||
score += this.ts_(this.BP1__[p1 + p2]);
|
||||
score += this.ts_(this.BP2__[p2 + p3]);
|
||||
score += this.ts_(this.UW1__[w1]);
|
||||
score += this.ts_(this.UW2__[w2]);
|
||||
score += this.ts_(this.UW3__[w3]);
|
||||
score += this.ts_(this.UW4__[w4]);
|
||||
score += this.ts_(this.UW5__[w5]);
|
||||
score += this.ts_(this.UW6__[w6]);
|
||||
score += this.ts_(this.BW1__[w2 + w3]);
|
||||
score += this.ts_(this.BW2__[w3 + w4]);
|
||||
score += this.ts_(this.BW3__[w4 + w5]);
|
||||
score += this.ts_(this.TW1__[w1 + w2 + w3]);
|
||||
score += this.ts_(this.TW2__[w2 + w3 + w4]);
|
||||
score += this.ts_(this.TW3__[w3 + w4 + w5]);
|
||||
score += this.ts_(this.TW4__[w4 + w5 + w6]);
|
||||
score += this.ts_(this.UC1__[c1]);
|
||||
score += this.ts_(this.UC2__[c2]);
|
||||
score += this.ts_(this.UC3__[c3]);
|
||||
score += this.ts_(this.UC4__[c4]);
|
||||
score += this.ts_(this.UC5__[c5]);
|
||||
score += this.ts_(this.UC6__[c6]);
|
||||
score += this.ts_(this.BC1__[c2 + c3]);
|
||||
score += this.ts_(this.BC2__[c3 + c4]);
|
||||
score += this.ts_(this.BC3__[c4 + c5]);
|
||||
score += this.ts_(this.TC1__[c1 + c2 + c3]);
|
||||
score += this.ts_(this.TC2__[c2 + c3 + c4]);
|
||||
score += this.ts_(this.TC3__[c3 + c4 + c5]);
|
||||
score += this.ts_(this.TC4__[c4 + c5 + c6]);
|
||||
// score += this.ts_(this.TC5__[c4 + c5 + c6]);
|
||||
score += this.ts_(this.UQ1__[p1 + c1]);
|
||||
score += this.ts_(this.UQ2__[p2 + c2]);
|
||||
score += this.ts_(this.UQ3__[p3 + c3]);
|
||||
score += this.ts_(this.BQ1__[p2 + c2 + c3]);
|
||||
score += this.ts_(this.BQ2__[p2 + c3 + c4]);
|
||||
score += this.ts_(this.BQ3__[p3 + c2 + c3]);
|
||||
score += this.ts_(this.BQ4__[p3 + c3 + c4]);
|
||||
score += this.ts_(this.TQ1__[p2 + c1 + c2 + c3]);
|
||||
score += this.ts_(this.TQ2__[p2 + c2 + c3 + c4]);
|
||||
score += this.ts_(this.TQ3__[p3 + c1 + c2 + c3]);
|
||||
score += this.ts_(this.TQ4__[p3 + c2 + c3 + c4]);
|
||||
var p = "O";
|
||||
if (score > 0) {
|
||||
result.push(word);
|
||||
word = "";
|
||||
p = "B";
|
||||
}
|
||||
p1 = p2;
|
||||
p2 = p3;
|
||||
p3 = p;
|
||||
word += seg[i];
|
||||
}
|
||||
result.push(word);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
lunr.TinySegmenter = TinySegmenter;
|
||||
};
|
||||
|
||||
}));
|
||||
6708
omniread/wiki/assets/javascripts/lunr/wordcut.js
Normal file
6708
omniread/wiki/assets/javascripts/lunr/wordcut.js
Normal file
File diff suppressed because one or more lines are too long
42
omniread/wiki/assets/javascripts/workers/search.973d3a69.min.js
vendored
Normal file
42
omniread/wiki/assets/javascripts/workers/search.973d3a69.min.js
vendored
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/stylesheets/main.84d31ad4.min.css
vendored
Normal file
1
omniread/wiki/assets/stylesheets/main.84d31ad4.min.css
vendored
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1
omniread/wiki/assets/stylesheets/palette.06af60db.min.css
vendored
Normal file
1
omniread/wiki/assets/stylesheets/palette.06af60db.min.css
vendored
Normal file
File diff suppressed because one or more lines are too long
@@ -0,0 +1 @@
|
||||
{"version":3,"sources":["src/templates/assets/stylesheets/palette/_scheme.scss","../../../../src/templates/assets/stylesheets/palette.scss","src/templates/assets/stylesheets/palette/_accent.scss","src/templates/assets/stylesheets/palette/_primary.scss","src/templates/assets/stylesheets/utilities/_break.scss"],"names":[],"mappings":"AA2BA,cAGE,6BAME,sDAAA,CACA,6DAAA,CACA,+DAAA,CACA,gEAAA,CACA,mDAAA,CACA,6DAAA,CACA,+DAAA,CACA,gEAAA,CAGA,mDAAA,CACA,gDAAA,CAGA,0BAAA,CACA,mCAAA,CAGA,iCAAA,CACA,kCAAA,CACA,mCAAA,CACA,mCAAA,CACA,kCAAA,CACA,iCAAA,CACA,+CAAA,CACA,6DAAA,CACA,gEAAA,CACA,4DAAA,CACA,4DAAA,CACA,6DAAA,CAGA,6CAAA,CAGA,+CAAA,CAGA,uDAAA,CACA,6DAAA,CACA,2DAAA,CAGA,iCAAA,CAGA,yDAAA,CACA,iEAAA,CAGA,mDAAA,CACA,mDAAA,CAGA,qDAAA,CACA,uDAAA,CAGA,8DAAA,CAKA,8DAAA,CAKA,0DAAA,CAvEA,iBCeF,CD6DE,kHAEE,YC3DJ,CDkFE,yDACE,4BChFJ,CD+EE,2DACE,4BC7EJ,CD4EE,gEACE,4BC1EJ,CDyEE,2DACE,4BCvEJ,CDsEE,yDACE,4BCpEJ,CDmEE,0DACE,4BCjEJ,CDgEE,gEACE,4BC9DJ,CD6DE,0DACE,4BC3DJ,CD0DE,2OACE,4BC/CJ,CDsDA,+FAGE,iCCpDF,CACF,CC/CE,2BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD2CN,CCrDE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDkDN,CC5DE,8BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDyDN,CCnEE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDgEN,CC1EE,8BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDuEN,CCjFE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD8EN,CCxFE,kCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDqFN,CC/FE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD4FN,CCtGE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDmGN,CC7GE,6BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD0GN,CCpHE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDiHN,CC3HE,4BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCD2HN,CClIE,8BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDkIN,CCzIE,6BACE,yBAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDyIN,CChJE,8BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDgJN,CCvJE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDoJN,CEzJE,4BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsJN,CEjKE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8JN,CEzKE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsKN,CEjLE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8KN,CEzLE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsLN,CEjME,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8LN,CEzME,mCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsMN,CEjNE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8MN,CEzNE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsNN,CEjOE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8NN,CEzOE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsON,CEjPE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFiPN,CEzPE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFyPN,CEjQE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFiQN,CEzQE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFyQN,CEjRE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8QN,CEzRE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsRN,CEjSE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCAAA,CAKA,4BF0RN,CE1SE,kCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCAAA,CAKA,4BFmSN,CEpRE,sEACE,4BFuRJ,CExRE,+DACE,4BF2RJ,CE5RE,iEACE,4BF+RJ,CEhSE,gEACE,4BFmSJ,CEpSE,iEACE,4BFuSJ,CE9RA,8BACE,mDAAA,CACA,4DAAA,CACA,0DAAA,CACA,oDAAA,CACA,2DAAA,CAGA,4BF+RF,CE5RE,yCACE,+BF8RJ,CE3RI,kDAEE,0CAAA,CACA,sCAAA,CAFA,mCF+RN,CG3MI,mCD1EA,+CACE,8CFwRJ,CErRI,qDACE,8CFuRN,CElRE,iEACE,mCFoRJ,CACF,CGtNI,sCDvDA,uCACE,oCFgRJ,CACF,CEvQA,8BACE,kDAAA,CACA,4DAAA,CACA,wDAAA,CACA,oDAAA,CACA,6DAAA,CAGA,4BFwQF,CErQE,yCACE,+BFuQJ,CEpQI,kDAEE,0CAAA,CACA,sCAAA,CAFA,mCFwQN,CEjQE,yCACE,6CFmQJ,CG5NI,0CDhCA,8CACE,gDF+PJ,CACF,CGjOI,0CDvBA,iFACE,6CF2PJ,CACF,CGzPI,sCDKA,uCACE,6CFuPJ,CACF","file":"palette.css"}
|
||||
661
omniread/wiki/index.html
Normal file
661
omniread/wiki/index.html
Normal file
@@ -0,0 +1,661 @@
|
||||
|
||||
<!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="next" href="01_overview/">
|
||||
|
||||
|
||||
<link rel="icon" href="assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>OmniRead Documentation</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=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
|
||||
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
|
||||
|
||||
|
||||
|
||||
<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="blue-grey" data-md-color-accent="teal">
|
||||
|
||||
|
||||
<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="#omniread-format-agnostic-content-acquisition-and-parsing" class="md-skip">
|
||||
Skip to content
|
||||
</a>
|
||||
|
||||
</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="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</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">
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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="01_overview/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Overview
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="02_how_to_use/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
How to Use
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="03_extending/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Extending OmniRead
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-tabs__item">
|
||||
<a href="04_development/" class="md-tabs__link">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Development
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
|
||||
|
||||
<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 md-nav--integrated" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" 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 Documentation
|
||||
</label>
|
||||
|
||||
<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">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Home
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="." class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Home
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
<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="#key-features" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🚀 Key Features
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#quick-start" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
⚡ Quick Start
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#documentation-structure" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
📁 Documentation Structure
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#related-resources" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
🔗 Related Resources
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="01_overview/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Overview
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="02_how_to_use/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
How to Use
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="03_extending/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Extending OmniRead
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="04_development/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
<span class="md-ellipsis">
|
||||
Development
|
||||
|
||||
</span>
|
||||
|
||||
|
||||
</a>
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
<div class="md-content" data-md-component="content">
|
||||
<article class="md-content__inner md-typeset">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h1 id="omniread-format-agnostic-content-acquisition-and-parsing">📄 OmniRead — Format-Agnostic Content Acquisition and Parsing</h1>
|
||||
<p><code>OmniRead</code> is a composable content ingestion framework with pluggable scrapers
|
||||
and parsers for HTML, PDF, CSV, and XLSX. It cleanly separates fetching
|
||||
(I/O) from interpretation (parsing) through a canonical <code>Content</code> exchange
|
||||
model, giving each format its own scraper and parser while sharing one
|
||||
uniform pipeline.</p>
|
||||
<blockquote>
|
||||
<p><strong>Doc model:</strong> this wiki is written for humans — how‑to guides, examples,
|
||||
and extension recipes. The authoritative API contracts live in the code
|
||||
(GSDFC docstrings) and the machine‑readable bundle under <code>docs/mcp/</code>.</p>
|
||||
</blockquote>
|
||||
<hr />
|
||||
<h2 id="key-features">🚀 Key Features</h2>
|
||||
<ul>
|
||||
<li>🧱 <strong>Content/Scraper/Parser architecture</strong> — fetch and interpret in
|
||||
independent, testable layers</li>
|
||||
<li>📄 <strong>Canonical <code>Content</code> model</strong> — raw bytes + metadata passed between all
|
||||
layers via one dataclass</li>
|
||||
<li>🌐 <strong>HTML</strong> — HTTP-based scraper with httpx; DOM parsing via BeautifulSoup</li>
|
||||
<li>📕 <strong>PDF</strong> — client + scraper for raw PDF bytes; user-defined parsers</li>
|
||||
<li>📊 <strong>CSV</strong> — standard-library CSV parser over <code>rows()</code> iterator</li>
|
||||
<li>📑 <strong>XLSX</strong> — openpyxl-backed spreadsheet parser with sheet selection,
|
||||
empty-row control, and ISO date conversion</li>
|
||||
</ul>
|
||||
<hr />
|
||||
<h2 id="quick-start">⚡ Quick Start</h2>
|
||||
<div class="language-python 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>
|
||||
<span class="normal"><a href="#__codelineno-0-7">7</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-8">8</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-9">9</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="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">HTMLScraper</span><span class="p">,</span> <span class="n">HTMLParser</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">TitleParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_soup</span><span class="o">.</span><span class="n">title</span><span class="o">.</span><span class="n">string</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a><span class="n">content</span> <span class="o">=</span> <span class="n">HTMLScraper</span><span class="p">()</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span><span class="s2">"https://example.com"</span><span class="p">)</span>
|
||||
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8"></a><span class="n">title</span> <span class="o">=</span> <span class="n">TitleParser</span><span class="p">(</span><span class="n">content</span><span class="p">)</span><span class="o">.</span><span class="n">parse</span><span class="p">()</span>
|
||||
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9"></a><span class="k">assert</span> <span class="n">title</span> <span class="o">==</span> <span class="s2">"Example Domain"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
<hr />
|
||||
<h2 id="documentation-structure">📁 Documentation Structure</h2>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Section</th>
|
||||
<th>What you'll find</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><a href="01_overview/">Overview</a></td>
|
||||
<td>The three-layer architecture and the <code>Content</code> model</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href="02_how_to_use/">How to Use</a></td>
|
||||
<td>Ready-to-run examples for HTML, PDF, CSV, and XLSX</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href="03_extending/">Extending OmniRead</a></td>
|
||||
<td>Subclassing scrapers, parsers, and clients</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href="04_development/">Development</a></td>
|
||||
<td>Setup, tests, and regenerating docs</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<hr />
|
||||
<h2 id="related-resources">🔗 Related Resources</h2>
|
||||
<ul>
|
||||
<li><strong>Source Code:</strong> <a href="https://git.aetoskia.com/aetos/omniread">Gitea Repository</a></li>
|
||||
<li><strong>Internal PyPI:</strong> <a href="https://pip.aetoskia.com/simple/omniread">pip.aetoskia.com/simple/omniread</a></li>
|
||||
<li><strong>CI:</strong> Builds and publishes tagged releases, gated on black / ruff / mypy / pytest.</li>
|
||||
</ul>
|
||||
<hr />
|
||||
<p>© Aetoskia Internal — <code>omniread</code> 0.0.1</p>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</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", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "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>
|
||||
1
omniread/wiki/search/search_index.json
Normal file
1
omniread/wiki/search/search_index.json
Normal file
File diff suppressed because one or more lines are too long
3
omniread/wiki/sitemap.xml
Normal file
3
omniread/wiki/sitemap.xml
Normal file
@@ -0,0 +1,3 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
||||
</urlset>
|
||||
BIN
omniread/wiki/sitemap.xml.gz
Normal file
BIN
omniread/wiki/sitemap.xml.gz
Normal file
Binary file not shown.
Reference in New Issue
Block a user