feat: unify docs portal and MCP servers into one config-driven service
- add config.yml as single source of truth for collected repos/categories - add collect.py CLI to pull lib/api/wiki site builds and mcp bundles from source repos and regenerate nginx.conf + _index/index.html - port mcp runtime (main.py/core.py/config.py): nginx + health + FastMCP servers started from config.yml - docker: python:3.13-slim + nginx, expose 8000-8006 + 9000 (html portal) - drone: publish html (6007:9000) and MCP ports 8000-8006 - move mongo-ops docs to wiki/, add auth-server (api) and hexa (lib) - refresh lib site builds (lib/ prefix) and collect mcp bundles
This commit is contained in:
@@ -44,6 +44,8 @@
|
||||
|
||||
<link rel="stylesheet" href="/assets/_mkdocstrings.css">
|
||||
|
||||
<link rel="stylesheet" href="https://unpkg.com/dracula-prism/dist/css/dracula-prism.css">
|
||||
|
||||
<script>__md_scope=new URL("/",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
|
||||
|
||||
|
||||
@@ -84,7 +86,7 @@
|
||||
<a href="/." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -201,7 +203,7 @@
|
||||
<a href="/." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -216,7 +218,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/." class="md-nav__link">
|
||||
<a href="/lib/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -269,7 +271,7 @@
|
||||
|
||||
|
||||
<div class="md-nav__link md-nav__container">
|
||||
<a href="/core/" class="md-nav__link ">
|
||||
<a href="/lib/core/" class="md-nav__link ">
|
||||
|
||||
|
||||
|
||||
@@ -304,7 +306,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/core/content/" class="md-nav__link">
|
||||
<a href="/lib/core/content/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -327,7 +329,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/core/parser/" class="md-nav__link">
|
||||
<a href="/lib/core/parser/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -350,7 +352,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/core/scraper/" class="md-nav__link">
|
||||
<a href="/lib/core/scraper/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -409,7 +411,7 @@
|
||||
|
||||
|
||||
<div class="md-nav__link md-nav__container">
|
||||
<a href="/html/" class="md-nav__link ">
|
||||
<a href="/lib/html/" class="md-nav__link ">
|
||||
|
||||
|
||||
|
||||
@@ -444,7 +446,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/html/parser/" class="md-nav__link">
|
||||
<a href="/lib/html/parser/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -467,7 +469,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/html/scraper/" class="md-nav__link">
|
||||
<a href="/lib/html/scraper/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -528,7 +530,7 @@
|
||||
|
||||
|
||||
<div class="md-nav__link md-nav__container">
|
||||
<a href="/pdf/" class="md-nav__link ">
|
||||
<a href="/lib/pdf/" class="md-nav__link ">
|
||||
|
||||
|
||||
|
||||
@@ -563,7 +565,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/pdf/client/" class="md-nav__link">
|
||||
<a href="/lib/pdf/client/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -586,7 +588,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/pdf/parser/" class="md-nav__link">
|
||||
<a href="/lib/pdf/parser/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -609,7 +611,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="/pdf/scraper/" class="md-nav__link">
|
||||
<a href="/lib/pdf/scraper/" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../parser/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -477,6 +479,15 @@
|
||||
<nav class="md-nav" aria-label="Attributes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.CSV" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.HTML" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -502,6 +513,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.XLSX" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -995,6 +1015,15 @@
|
||||
<nav class="md-nav" aria-label="Attributes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.CSV" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.HTML" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -1020,6 +1049,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.content.ContentType.XLSX" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1114,7 +1152,17 @@ the semantic meaning of these models.</p>
|
||||
</span>
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span><span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="o">...</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">source</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="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="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1160,7 +1208,7 @@ the semantic meaning of these models.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">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>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1184,7 +1232,7 @@ the semantic meaning of these models.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1296,6 +1344,30 @@ the semantic meaning of these models.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.content.ContentType.CSV" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">CSV</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">CSV</span> <span class="o">=</span> <span class="s1">'text/csv'</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Comma-separated-value document content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.content.ContentType.HTML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">HTML</span>
|
||||
|
||||
@@ -1368,6 +1440,30 @@ the semantic meaning of these models.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.content.ContentType.XLSX" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XLSX</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">XLSX</span> <span class="o">=</span> <span class="s2">"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Office Open XML spreadsheet (xlsx/xlsm) content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.content.ContentType.XML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XML</span>
|
||||
|
||||
@@ -1462,10 +1558,10 @@ the semantic meaning of these models.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -9,13 +9,13 @@
|
||||
|
||||
|
||||
|
||||
<link rel="prev" href="..">
|
||||
<link rel="prev" href="../">
|
||||
|
||||
|
||||
<link rel="next" href="content/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href=".." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href=".." class="md-nav__link">
|
||||
<a href="../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -902,6 +904,15 @@
|
||||
<nav class="md-nav" aria-label="Attributes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.ContentType.CSV" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.ContentType.HTML" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -927,6 +938,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.core.ContentType.XLSX" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1140,7 +1160,7 @@ are safe for downstream consumers to depend on.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span><span class="p">:</span> <span class="n">Set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span><span class="p">:</span> <span class="nb">set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1347,7 +1367,15 @@ are safe for downstream consumers to depend on.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1383,7 +1411,7 @@ are safe for downstream consumers to depend on.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1477,7 +1505,17 @@ are safe for downstream consumers to depend on.</p>
|
||||
</span>
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span><span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="o">...</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">source</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="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="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1523,7 +1561,7 @@ are safe for downstream consumers to depend on.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">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>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1547,7 +1585,7 @@ are safe for downstream consumers to depend on.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1659,6 +1697,30 @@ are safe for downstream consumers to depend on.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.ContentType.CSV" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">CSV</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">CSV</span> <span class="o">=</span> <span class="s1">'text/csv'</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Comma-separated-value document content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.ContentType.HTML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">HTML</span>
|
||||
|
||||
@@ -1731,6 +1793,30 @@ are safe for downstream consumers to depend on.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.ContentType.XLSX" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XLSX</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">XLSX</span> <span class="o">=</span> <span class="s2">"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Office Open XML spreadsheet (xlsx/xlsm) content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.core.ContentType.XML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XML</span>
|
||||
|
||||
@@ -1825,10 +1911,10 @@ are safe for downstream consumers to depend on.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../scraper/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1108,7 +1110,7 @@ raw content into structured, typed representations.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span><span class="p">:</span> <span class="n">Set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">supported_types</span><span class="p">:</span> <span class="nb">set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1312,10 +1314,10 @@ raw content into structured, typed representations.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../../html/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -992,7 +994,15 @@ acquiring raw content from external sources.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1028,7 +1038,7 @@ acquiring raw content from external sources.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1173,10 +1183,10 @@ acquiring raw content from external sources.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
1216
libs/omniread/site/lib/csv/client/index.html
Normal file
1216
libs/omniread/site/lib/csv/client/index.html
Normal file
File diff suppressed because it is too large
Load Diff
2130
libs/omniread/site/lib/csv/index.html
Normal file
2130
libs/omniread/site/lib/csv/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1188
libs/omniread/site/lib/csv/parser/index.html
Normal file
1188
libs/omniread/site/lib/csv/parser/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1143
libs/omniread/site/lib/csv/parser_base/index.html
Normal file
1143
libs/omniread/site/lib/csv/parser_base/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1070
libs/omniread/site/lib/csv/scraper/index.html
Normal file
1070
libs/omniread/site/lib/csv/scraper/index.html
Normal file
File diff suppressed because it is too large
Load Diff
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="parser/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href=".." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href=".." class="md-nav__link">
|
||||
<a href="../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1243,7 +1245,7 @@ use this package only when HTML-specific behavior is required.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1291,7 +1293,7 @@ use this package only when HTML-specific behavior is required.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[str]</code>
|
||||
<code>str | None</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1334,7 +1336,7 @@ The value of the <code>href</code> attribute, or None if absent.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.dict">dict</span>[str, <span title="typing.Any">Any</span>]</code>
|
||||
<code>dict[str, <span title="typing.Any">Any</span>]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1421,7 +1423,7 @@ Dictionary containing extracted metadata.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.list">list</span>[<span title="typing.list">list</span>[str]]</code>
|
||||
<code>list[list[str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1496,7 +1498,19 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span><span class="o">*</span><span class="p">,</span> <span class="n">client</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">httpx</span><span class="o">.</span><span class="n">Client</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span> <span class="n">headers</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-7">7</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">client</span><span class="p">:</span> <span class="n">httpx</span><span class="o">.</span><span class="n">Client</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">headers</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1571,7 +1585,7 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>headers</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, str]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1620,7 +1634,15 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1656,7 +1678,7 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1873,10 +1895,10 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../scraper/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1363,7 +1365,7 @@ to return a structured representation appropriate for their use case.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1411,7 +1413,7 @@ to return a structured representation appropriate for their use case.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[str]</code>
|
||||
<code>str | None</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1454,7 +1456,7 @@ The value of the <code>href</code> attribute, or None if absent.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.dict">dict</span>[str, <span title="typing.Any">Any</span>]</code>
|
||||
<code>dict[str, <span title="typing.Any">Any</span>]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1541,7 +1543,7 @@ Dictionary containing extracted metadata.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.list">list</span>[<span title="typing.list">list</span>[str]]</code>
|
||||
<code>list[list[str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1671,10 +1673,10 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../../pdf/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -952,7 +954,19 @@ layer.</p>
|
||||
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span><span class="o">*</span><span class="p">,</span> <span class="n">client</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">httpx</span><span class="o">.</span><span class="n">Client</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span> <span class="n">headers</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-7">7</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">client</span><span class="p">:</span> <span class="n">httpx</span><span class="o">.</span><span class="n">Client</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">headers</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1027,7 +1041,7 @@ layer.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>headers</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, str]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1076,7 +1090,15 @@ layer.</p>
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1112,7 +1134,7 @@ layer.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1329,10 +1351,10 @@ layer.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -13,19 +13,19 @@
|
||||
<link rel="next" href="core/">
|
||||
|
||||
|
||||
<link rel="icon" href="assets/images/favicon.png">
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
|
||||
<title>omniread</title>
|
||||
<title>Home - omniread</title>
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -44,9 +44,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -88,10 +90,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href=".." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -205,10 +207,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href=".." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -245,7 +247,7 @@
|
||||
<span class="md-nav__icon md-icon"></span>
|
||||
</label>
|
||||
|
||||
<a href="." class="md-nav__link md-nav__link--active">
|
||||
<a href="./" class="md-nav__link md-nav__link--active">
|
||||
|
||||
|
||||
|
||||
@@ -429,6 +431,15 @@
|
||||
<nav class="md-nav" aria-label="Attributes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.CSV" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.HTML" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -454,6 +465,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.XLSX" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1383,6 +1403,15 @@
|
||||
<nav class="md-nav" aria-label="Attributes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.CSV" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
CSV
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.HTML" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -1408,6 +1437,15 @@
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#omniread.ContentType.XLSX" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
XLSX
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -1876,6 +1914,9 @@ required.</p>
|
||||
<li><code>FileSystemPDFClient</code>: Local filesystem PDF access.</li>
|
||||
<li><code>PDFScraper</code>: PDF-specific content acquisition.</li>
|
||||
<li><code>PDFParser</code>: Base parser for PDF binary interpretation.</li>
|
||||
<li><code>FileSystemXlsxClient</code>: Local filesystem spreadsheet access.</li>
|
||||
<li><code>XlsxScraper</code>: XLSX-specific content acquisition.</li>
|
||||
<li><code>XlsxParser</code>: Generic string-row parser for xlsx workbooks.</li>
|
||||
</ul>
|
||||
<hr />
|
||||
<h3 id="omniread--core-philosophy">Core Philosophy</h3>
|
||||
@@ -1914,7 +1955,17 @@ required.</p>
|
||||
</span>
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span><span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="o">...</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">Content</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">source</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="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="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1960,7 +2011,7 @@ required.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">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>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1984,7 +2035,7 @@ required.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -2096,6 +2147,30 @@ required.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.ContentType.CSV" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">CSV</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">CSV</span> <span class="o">=</span> <span class="s1">'text/csv'</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Comma-separated-value document content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.ContentType.HTML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">HTML</span>
|
||||
|
||||
@@ -2168,6 +2243,30 @@ required.</p>
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.ContentType.XLSX" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XLSX</span>
|
||||
|
||||
|
||||
<span class="doc doc-labels">
|
||||
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
|
||||
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="n">XLSX</span> <span class="o">=</span> <span class="s2">"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
|
||||
<p>Office Open XML spreadsheet (xlsx/xlsm) content.</p>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="doc doc-object doc-attribute">
|
||||
|
||||
|
||||
|
||||
<h6 id="omniread.ContentType.XML" class="doc doc-heading">
|
||||
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XML</span>
|
||||
|
||||
@@ -2655,7 +2754,7 @@ required.</p>
|
||||
</span>
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -2703,7 +2802,7 @@ required.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[str]</code>
|
||||
<code>str | None</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -2746,7 +2845,7 @@ The value of the <code>href</code> attribute, or None if absent.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.dict">dict</span>[str, <span title="typing.Any">Any</span>]</code>
|
||||
<code>dict[str, <span title="typing.Any">Any</span>]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -2833,7 +2932,7 @@ Dictionary containing extracted metadata.</p>
|
||||
<tbody>
|
||||
<tr class="doc-section-item">
|
||||
<td>
|
||||
<code><span title="typing.list">list</span>[<span title="typing.list">list</span>[str]]</code>
|
||||
<code>list[list[str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -2908,7 +3007,19 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
</h4>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span><span class="o">*</span><span class="p">,</span> <span class="n">client</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">httpx</span><span class="o">.</span><span class="n">Client</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span> <span class="n">headers</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-6">6</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-7">7</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">HTMLScraper</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="n">client</span><span class="p">:</span> <span class="n">httpx</span><span class="o">.</span><span class="n">Client</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">headers</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
||||
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a><span class="p">)</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -2983,7 +3094,7 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>headers</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, str]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, str]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -3032,7 +3143,15 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -3068,7 +3187,7 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -3560,7 +3679,15 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -3596,7 +3723,7 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -3732,10 +3859,10 @@ A list of rows, where each row is a list of cell text values.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": ".", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../parser/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1366,10 +1368,10 @@ interpretation, or content extraction.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="client/">
|
||||
|
||||
|
||||
<link rel="icon" href="../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href=".." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href=".." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href=".." class="md-nav__link">
|
||||
<a href="../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1420,7 +1422,15 @@ and are safe for consumers to import directly when working with PDFs.</p>
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1456,7 +1466,7 @@ and are safe for consumers to import directly when working with PDFs.</p>
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1592,10 +1602,10 @@ and are safe for consumers to import directly when working with PDFs.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -15,7 +15,7 @@
|
||||
<link rel="next" href="../scraper/">
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -24,10 +24,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -46,9 +46,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -90,10 +92,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -207,10 +209,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -225,7 +227,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -1296,10 +1298,10 @@ structured representations suitable for downstream consumption.</p>
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
@@ -13,7 +13,7 @@
|
||||
|
||||
|
||||
|
||||
<link rel="icon" href="../../assets/images/favicon.png">
|
||||
<link rel="icon" href="../../../assets/images/favicon.png">
|
||||
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
||||
|
||||
|
||||
@@ -22,10 +22,10 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/main.84d31ad4.min.css">
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
|
||||
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
|
||||
|
||||
|
||||
|
||||
@@ -44,9 +44,11 @@
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
|
||||
<link rel="stylesheet" href="../../../assets/_mkdocstrings.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>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
@@ -88,10 +90,10 @@
|
||||
|
||||
<header class="md-header md-header--shadow" data-md-component="header">
|
||||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||||
<a href="../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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">
|
||||
@@ -205,10 +207,10 @@
|
||||
|
||||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||||
<label class="md-nav__title" for="__drawer">
|
||||
<a href="../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
<a href="../../.." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
|
||||
|
||||
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
|
||||
<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
|
||||
@@ -223,7 +225,7 @@
|
||||
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="../.." class="md-nav__link">
|
||||
<a href="../../" class="md-nav__link">
|
||||
|
||||
|
||||
|
||||
@@ -999,7 +1001,15 @@ all storage and access concerns to a <code>BasePDFClient</code> implementation.<
|
||||
|
||||
|
||||
</h6>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
<div class="language-python doc-signature highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1">1</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-2">2</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-3">3</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-4">4</a></span>
|
||||
<span class="normal"><a href="#__codelineno-0-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="nf">fetch</span><span class="p">(</span>
|
||||
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a> <span class="n">source</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span>
|
||||
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a> <span class="o">*</span><span class="p">,</span>
|
||||
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a> <span class="n">metadata</span><span class="p">:</span> <span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a><span class="p">)</span> <span class="o">-></span> <span class="n">Content</span>
|
||||
</span></code></pre></div></td></tr></table></div>
|
||||
|
||||
<div class="doc doc-contents ">
|
||||
@@ -1035,7 +1045,7 @@ all storage and access concerns to a <code>BasePDFClient</code> implementation.<
|
||||
<tr class="doc-section-item">
|
||||
<td><code>metadata</code></td>
|
||||
<td>
|
||||
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
<code>Optional[<span title="collections.abc.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
|
||||
</td>
|
||||
<td>
|
||||
<div class="doc-md-description">
|
||||
@@ -1171,10 +1181,10 @@ all storage and access concerns to a <code>BasePDFClient</code> implementation.<
|
||||
|
||||
|
||||
|
||||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
<script id="__config" type="application/json">{"base": "../../..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "../../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
|
||||
|
||||
|
||||
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
<script src="../../../assets/javascripts/bundle.f55a23d4.min.js"></script>
|
||||
|
||||
|
||||
</body>
|
||||
1216
libs/omniread/site/lib/xlsx/client/index.html
Normal file
1216
libs/omniread/site/lib/xlsx/client/index.html
Normal file
File diff suppressed because it is too large
Load Diff
2274
libs/omniread/site/lib/xlsx/index.html
Normal file
2274
libs/omniread/site/lib/xlsx/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1330
libs/omniread/site/lib/xlsx/parser/index.html
Normal file
1330
libs/omniread/site/lib/xlsx/parser/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1143
libs/omniread/site/lib/xlsx/parser_base/index.html
Normal file
1143
libs/omniread/site/lib/xlsx/parser_base/index.html
Normal file
File diff suppressed because it is too large
Load Diff
1069
libs/omniread/site/lib/xlsx/scraper/index.html
Normal file
1069
libs/omniread/site/lib/xlsx/scraper/index.html
Normal file
File diff suppressed because it is too large
Load Diff
6
libs/omniread/site/mcp/index.json
Normal file
6
libs/omniread/site/mcp/index.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"project": "omniread",
|
||||
"type": "docforge-model",
|
||||
"modules_count": 22,
|
||||
"source": "docforge"
|
||||
}
|
||||
125
libs/omniread/site/mcp/modules/omniread.core.content.json
Normal file
125
libs/omniread/site/mcp/modules/omniread.core.content.json
Normal file
@@ -0,0 +1,125 @@
|
||||
{
|
||||
"module": "omniread.core.content",
|
||||
"content": {
|
||||
"path": "omniread.core.content",
|
||||
"docstring": "# Summary\n\nCanonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"dataclass": {
|
||||
"name": "dataclass",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.dataclass",
|
||||
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Enum": {
|
||||
"name": "Enum",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Enum",
|
||||
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.ContentType",
|
||||
"signature": "<bound method Class.signature of Class('ContentType', 20, 49)>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.HTML",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.PDF",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.XLSX",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.CSV",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.JSON",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.XML",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.Content",
|
||||
"signature": "<bound method Class.signature of Class('Content', 52, 84)>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.raw",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.source",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.content_type",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.metadata",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
534
libs/omniread/site/mcp/modules/omniread.core.json
Normal file
534
libs/omniread/site/mcp/modules/omniread.core.json
Normal file
@@ -0,0 +1,534 @@
|
||||
{
|
||||
"module": "omniread.core",
|
||||
"content": {
|
||||
"path": "omniread.core",
|
||||
"docstring": "# Summary\n\nCore domain contracts for OmniRead.\n\nThis package defines the **format-agnostic domain layer** of OmniRead.\nIt exposes canonical content models and abstract interfaces that are\nimplemented by format-specific modules (HTML, PDF, etc.).\n\nPublic exports from this package are considered **stable contracts** and\nare safe for downstream consumers to depend on.\n\nSubmodules:\n\n- `content`: Canonical content models and enums.\n- `parser`: Abstract parsing contracts.\n- `scraper`: Abstract scraping contracts.\n\nFormat-specific behavior must not be introduced at this layer.\n\n---\n\n# Public API\n\n- `Content`\n- `ContentType`\n\n---",
|
||||
"objects": {
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "module",
|
||||
"path": "omniread.core.content",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCanonical content models for OmniRead.\n\nThis module defines the **format-agnostic content representation** used across\nall parsers and scrapers in OmniRead.\n\nThe models defined here represent *what* was extracted, not *how* it was\nretrieved or parsed. Format-specific behavior and metadata must not alter\nthe semantic meaning of these models.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"dataclass": {
|
||||
"name": "dataclass",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.dataclass",
|
||||
"signature": "<bound method Alias.signature of Alias('dataclass', 'dataclasses.dataclass')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Enum": {
|
||||
"name": "Enum",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Enum",
|
||||
"signature": "<bound method Alias.signature of Alias('Enum', 'enum.Enum')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.content.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.ContentType",
|
||||
"signature": "<bound method Class.signature of Class('ContentType', 20, 49)>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.HTML",
|
||||
"signature": null,
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.PDF",
|
||||
"signature": null,
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.XLSX",
|
||||
"signature": null,
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.CSV",
|
||||
"signature": null,
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.JSON",
|
||||
"signature": null,
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.ContentType.XML",
|
||||
"signature": null,
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.content.Content",
|
||||
"signature": "<bound method Class.signature of Class('Content', 52, 84)>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.raw",
|
||||
"signature": null,
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.source",
|
||||
"signature": null,
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.content_type",
|
||||
"signature": null,
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.content.Content.metadata",
|
||||
"signature": null,
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser": {
|
||||
"name": "parser",
|
||||
"kind": "module",
|
||||
"path": "omniread.core.parser",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nAbstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.BaseParser",
|
||||
"signature": "<bound method Class.signature of Class('BaseParser', 30, 111)>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.BaseParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.BaseParser.content",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 75, 94)>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.supports",
|
||||
"signature": "<bound method Function.signature of Function('supports', 96, 111)>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"scraper": {
|
||||
"name": "scraper",
|
||||
"kind": "module",
|
||||
"path": "omniread.core.scraper",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.BaseScraper",
|
||||
"signature": "<bound method Class.signature of Class('BaseScraper', 31, 83)>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
169
libs/omniread/site/mcp/modules/omniread.core.parser.json
Normal file
169
libs/omniread/site/mcp/modules/omniread.core.parser.json
Normal file
@@ -0,0 +1,169 @@
|
||||
{
|
||||
"module": "omniread.core.parser",
|
||||
"content": {
|
||||
"path": "omniread.core.parser",
|
||||
"docstring": "# Summary\n\nAbstract parsing contracts for OmniRead.\n\nThis module defines the **format-agnostic parser interface** used to transform\nraw content into structured, typed representations.\n\nParsers are responsible for:\n\n- Interpreting a single `Content` instance\n- Validating compatibility with the content type\n- Producing a structured output suitable for downstream consumers\n\nParsers are not responsible for:\n\n- Fetching or acquiring content\n- Performing retries or error recovery\n- Managing multiple content sources",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.parser.BaseParser",
|
||||
"signature": "<bound method Class.signature of Class('BaseParser', 30, 111)>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.BaseParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.parser.BaseParser.content",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 75, 94)>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.parser.BaseParser.supports",
|
||||
"signature": "<bound method Function.signature of Function('supports', 96, 111)>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
90
libs/omniread/site/mcp/modules/omniread.core.scraper.json
Normal file
90
libs/omniread/site/mcp/modules/omniread.core.scraper.json
Normal file
@@ -0,0 +1,90 @@
|
||||
{
|
||||
"module": "omniread.core.scraper",
|
||||
"content": {
|
||||
"path": "omniread.core.scraper",
|
||||
"docstring": "# Summary\n\nAbstract scraping contracts for OmniRead.\n\nThis module defines the **format-agnostic scraper interface** responsible for\nacquiring raw content from external sources.\n\nScrapers are responsible for:\n\n- Locating and retrieving raw content bytes\n- Attaching minimal contextual metadata\n- Returning normalized `Content` objects\n\nScrapers are explicitly NOT responsible for:\n\n- Parsing or interpreting content\n- Inferring structure or semantics\n- Performing content-type specific processing\n\nAll interpretation must be delegated to parsers.",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.core.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.core.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.core.scraper.BaseScraper",
|
||||
"signature": "<bound method Class.signature of Class('BaseScraper', 31, 83)>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.core.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 52, 83)>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
69
libs/omniread/site/mcp/modules/omniread.csv.client.json
Normal file
69
libs/omniread/site/mcp/modules/omniread.csv.client.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"module": "omniread.csv.client",
|
||||
"content": {
|
||||
"path": "omniread.csv.client",
|
||||
"docstring": "# Summary\n\nCSV client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\ncomma-separated-value document bytes from a concrete backing store.\n\nClients provide low-level access to csv binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BaseCsvClient": {
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.BaseCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('BaseCsvClient', 25, 58)>",
|
||||
"docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.client.BaseCsvClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
||||
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemCsvClient": {
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemCsvClient', 61, 97)>",
|
||||
"docstring": "CSV client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads csv files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
||||
"docstring": "Read a csv file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the csv file.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
576
libs/omniread/site/mcp/modules/omniread.csv.json
Normal file
576
libs/omniread/site/mcp/modules/omniread.csv.json
Normal file
@@ -0,0 +1,576 @@
|
||||
{
|
||||
"module": "omniread.csv",
|
||||
"content": {
|
||||
"path": "omniread.csv",
|
||||
"docstring": "# Summary\n\nCSV subpackage for OmniRead.\n\nProvides acquisition and parsing of comma-separated-value content:\n\n- `BaseCsvClient`: abstract backing-store client for csv bytes.\n- `FileSystemCsvClient`: local filesystem implementation.\n- `CsvScraper`: wraps fetched bytes into canonical `Content`.\n- `CsvParserBase`: content-type-enforcing parser contract.\n- `CsvParser`: generic string-row parser built on the standard csv module.",
|
||||
"objects": {
|
||||
"BaseCsvClient": {
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.BaseCsvClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
|
||||
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemCsvClient": {
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.FileSystemCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemCsvClient', 'omniread.csv.client.FileSystemCsvClient')>",
|
||||
"docstring": "CSV client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads csv files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.FileSystemCsvClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.FileSystemCsvClient.fetch')>",
|
||||
"docstring": "Read a csv file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the csv file.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParser": {
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvParser",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParser', 'omniread.csv.parser.CsvParser')>",
|
||||
"docstring": "Generic csv parser producing string rows from the document.\n\nNotes:\n **Responsibilities:**\n\n - Decode the payload (UTF-8 with BOM support, Latin-1 fallback).\n - Detect the delimiter from a leading sample (`,` `;` tab `|`),\n defaulting to `,`.\n - Normalize cells into deterministic stripped string values.\n - Expose row extraction helpers mirroring `XlsxParser.rows`.\n\n **Constraints:**\n\n - All values are strings; consumers requiring typed values must\n convert on their side.\n - Quoted fields containing delimiters/newlines are handled by\n the standard ``csv`` module.",
|
||||
"members": {
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.CsvParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser.CsvParser.parse')>",
|
||||
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.CsvParser.rows",
|
||||
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.csv.parser.CsvParser.rows')>",
|
||||
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParserBase": {
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.CsvParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.csv.parser_base.CsvParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (CSV only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.CsvParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser_base.CsvParserBase.parse')>",
|
||||
"docstring": "Parse csv content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvScraper": {
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.CsvScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvScraper', 'omniread.csv.scraper.CsvScraper')>",
|
||||
"docstring": "Scraper for csv documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw csv bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n CSV content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.CsvScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.scraper.CsvScraper.fetch')>",
|
||||
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
},
|
||||
"client": {
|
||||
"name": "client",
|
||||
"kind": "module",
|
||||
"path": "omniread.csv.client",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCSV client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\ncomma-separated-value document bytes from a concrete backing store.\n\nClients provide low-level access to csv binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BaseCsvClient": {
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.BaseCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('BaseCsvClient', 25, 58)>",
|
||||
"docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.client.BaseCsvClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
||||
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemCsvClient": {
|
||||
"name": "FileSystemCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemCsvClient', 61, 97)>",
|
||||
"docstring": "CSV client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads csv files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.client.FileSystemCsvClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
||||
"docstring": "Read a csv file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the csv file.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser": {
|
||||
"name": "parser",
|
||||
"kind": "module",
|
||||
"path": "omniread.csv.parser",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCSV parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for comma-separated-value\ndocuments. It exposes records as lists of string cells so downstream\nconsumers can interpret tabular content without depending on the ``csv``\nmodule directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization and\ndelimiter detection.",
|
||||
"members": {
|
||||
"Sniffer": {
|
||||
"name": "Sniffer",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.Sniffer",
|
||||
"signature": "<bound method Alias.signature of Alias('Sniffer', 'csv.Sniffer')>",
|
||||
"docstring": null
|
||||
},
|
||||
"reader": {
|
||||
"name": "reader",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.reader",
|
||||
"signature": "<bound method Alias.signature of Alias('reader', 'csv.reader')>",
|
||||
"docstring": null
|
||||
},
|
||||
"StringIO": {
|
||||
"name": "StringIO",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.StringIO",
|
||||
"signature": "<bound method Alias.signature of Alias('StringIO', 'io.StringIO')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParserBase": {
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.CsvParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.csv.parser_base.CsvParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (CSV only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser_base.CsvParserBase.parse')>",
|
||||
"docstring": "Parse csv content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParser": {
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParser",
|
||||
"signature": "<bound method Class.signature of Class('CsvParser', 24, 102)>",
|
||||
"docstring": "Generic csv parser producing string rows from the document.\n\nNotes:\n **Responsibilities:**\n\n - Decode the payload (UTF-8 with BOM support, Latin-1 fallback).\n - Detect the delimiter from a leading sample (`,` `;` tab `|`),\n defaulting to `,`.\n - Normalize cells into deterministic stripped string values.\n - Expose row extraction helpers mirroring `XlsxParser.rows`.\n\n **Constraints:**\n\n - All values are strings; consumers requiring typed values must\n convert on their side.\n - Quoted fields containing delimiters/newlines are handled by\n the standard ``csv`` module.",
|
||||
"members": {
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 57, 65)>",
|
||||
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParser.rows",
|
||||
"signature": "<bound method Function.signature of Function('rows', 67, 95)>",
|
||||
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser_base": {
|
||||
"name": "parser_base",
|
||||
"kind": "module",
|
||||
"path": "omniread.csv.parser_base",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCSV parser base implementation for OmniRead.\n\nThis module defines the **CSV-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for\ncomma-separated-value documents.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"CsvParserBase": {
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase",
|
||||
"signature": "<bound method Class.signature of Class('CsvParserBase', 20, 55)>",
|
||||
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (CSV only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"docstring": "Parse csv content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"scraper": {
|
||||
"name": "scraper",
|
||||
"kind": "module",
|
||||
"path": "omniread.csv.scraper",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nCSV scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw\ncomma-separated-value document content from a backing store via a\nconfigured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseCsvClient": {
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
|
||||
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvScraper": {
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.CsvScraper",
|
||||
"signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
|
||||
"docstring": "Scraper for csv documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw csv bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n CSV content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.scraper.CsvScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
|
||||
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
113
libs/omniread/site/mcp/modules/omniread.csv.parser.json
Normal file
113
libs/omniread/site/mcp/modules/omniread.csv.parser.json
Normal file
@@ -0,0 +1,113 @@
|
||||
{
|
||||
"module": "omniread.csv.parser",
|
||||
"content": {
|
||||
"path": "omniread.csv.parser",
|
||||
"docstring": "# Summary\n\nCSV parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for comma-separated-value\ndocuments. It exposes records as lists of string cells so downstream\nconsumers can interpret tabular content without depending on the ``csv``\nmodule directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization and\ndelimiter detection.",
|
||||
"objects": {
|
||||
"Sniffer": {
|
||||
"name": "Sniffer",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.Sniffer",
|
||||
"signature": "<bound method Alias.signature of Alias('Sniffer', 'csv.Sniffer')>",
|
||||
"docstring": null
|
||||
},
|
||||
"reader": {
|
||||
"name": "reader",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.reader",
|
||||
"signature": "<bound method Alias.signature of Alias('reader', 'csv.reader')>",
|
||||
"docstring": null
|
||||
},
|
||||
"StringIO": {
|
||||
"name": "StringIO",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser.StringIO",
|
||||
"signature": "<bound method Alias.signature of Alias('StringIO', 'io.StringIO')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParserBase": {
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('CsvParserBase', 'omniread.csv.parser_base.CsvParserBase')>",
|
||||
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser.CsvParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.csv.parser_base.CsvParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (CSV only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.csv.parser_base.CsvParserBase.parse')>",
|
||||
"docstring": "Parse csv content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvParser": {
|
||||
"name": "CsvParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser.CsvParser",
|
||||
"signature": "<bound method Class.signature of Class('CsvParser', 24, 102)>",
|
||||
"docstring": "Generic csv parser producing string rows from the document.\n\nNotes:\n **Responsibilities:**\n\n - Decode the payload (UTF-8 with BOM support, Latin-1 fallback).\n - Detect the delimiter from a leading sample (`,` `;` tab `|`),\n defaulting to `,`.\n - Normalize cells into deterministic stripped string values.\n - Expose row extraction helpers mirroring `XlsxParser.rows`.\n\n **Constraints:**\n\n - All values are strings; consumers requiring typed values must\n convert on their side.\n - Quoted fields containing delimiters/newlines are handled by\n the standard ``csv`` module.",
|
||||
"members": {
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 57, 65)>",
|
||||
"docstring": "Parse the document into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the document."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser.CsvParser.rows",
|
||||
"signature": "<bound method Function.signature of Function('rows', 67, 95)>",
|
||||
"docstring": "Extract normalized string rows from the document.\n\nArgs:\n skip_empty (bool):\n When True (default), rows whose cells are all blank are\n omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
148
libs/omniread/site/mcp/modules/omniread.csv.parser_base.json
Normal file
148
libs/omniread/site/mcp/modules/omniread.csv.parser_base.json
Normal file
@@ -0,0 +1,148 @@
|
||||
{
|
||||
"module": "omniread.csv.parser_base",
|
||||
"content": {
|
||||
"path": "omniread.csv.parser_base",
|
||||
"docstring": "# Summary\n\nCSV parser base implementation for OmniRead.\n\nThis module defines the **CSV-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for\ncomma-separated-value documents.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.parser_base.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"CsvParserBase": {
|
||||
"name": "CsvParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase",
|
||||
"signature": "<bound method Class.signature of Class('CsvParserBase', 20, 55)>",
|
||||
"docstring": "Base csv parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces csv content-type compatibility and provides\n the extension point for implementing concrete csv parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (CSV only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.parser_base.CsvParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"docstring": "Parse csv content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
143
libs/omniread/site/mcp/modules/omniread.csv.scraper.json
Normal file
143
libs/omniread/site/mcp/modules/omniread.csv.scraper.json
Normal file
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"module": "omniread.csv.scraper",
|
||||
"content": {
|
||||
"path": "omniread.csv.scraper",
|
||||
"docstring": "# Summary\n\nCSV scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw\ncomma-separated-value document content from a backing store via a\nconfigured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.csv.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.csv.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseCsvClient": {
|
||||
"name": "BaseCsvClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseCsvClient', 'omniread.csv.client.BaseCsvClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving csv bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full csv binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.scraper.BaseCsvClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.csv.client.BaseCsvClient.fetch')>",
|
||||
"docstring": "Fetch raw csv bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw csv bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"CsvScraper": {
|
||||
"name": "CsvScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.csv.scraper.CsvScraper",
|
||||
"signature": "<bound method Class.signature of Class('CsvScraper', 22, 81)>",
|
||||
"docstring": "Scraper for csv documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw csv bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n CSV content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.csv.scraper.CsvScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 49, 81)>",
|
||||
"docstring": "Fetch a csv document from the given source.\n\nArgs:\n source (Any):\n Identifier of the csv source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw csv bytes, source\n identifier, CSV content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
488
libs/omniread/site/mcp/modules/omniread.html.json
Normal file
488
libs/omniread/site/mcp/modules/omniread.html.json
Normal file
@@ -0,0 +1,488 @@
|
||||
{
|
||||
"module": "omniread.html",
|
||||
"content": {
|
||||
"path": "omniread.html",
|
||||
"docstring": "# Summary\n\nHTML format implementation for OmniRead.\n\nThis package provides **HTML-specific implementations** of the core OmniRead\ncontracts defined in `omniread.core`.\n\nIt includes:\n\n- HTML parsers that interpret HTML content.\n- HTML scrapers that retrieve HTML documents.\n\nKey characteristics:\n\n- Implements, but does not redefine, core contracts.\n- May contain HTML-specific behavior and edge-case handling.\n- Produces canonical content models defined in `omniread.core.content`.\n\nConsumers should depend on `omniread.core` interfaces wherever possible and\nuse this package only when HTML-specific behavior is required.\n\n---\n\n# Public API\n\n- `HTMLScraper`\n- `HTMLParser`\n\n---",
|
||||
"objects": {
|
||||
"HTMLScraper": {
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.HTMLScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('HTMLScraper', 'omniread.html.scraper.HTMLScraper')>",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.HTMLScraper.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.html.scraper.HTMLScraper.content_type')>",
|
||||
"docstring": null
|
||||
},
|
||||
"validate_content_type": {
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('validate_content_type', 'omniread.html.scraper.HTMLScraper.validate_content_type')>",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.html.scraper.HTMLScraper.fetch')>",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
},
|
||||
"HTMLParser": {
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.HTMLParser",
|
||||
"signature": "<bound method Alias.signature of Alias('HTMLParser', 'omniread.html.parser.HTMLParser')>",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.HTMLParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.html.parser.HTMLParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.html.parser.HTMLParser.parse')>",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_div",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_div', 'omniread.html.parser.HTMLParser.parse_div')>",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_link",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_link', 'omniread.html.parser.HTMLParser.parse_link')>",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_table",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_table', 'omniread.html.parser.HTMLParser.parse_table')>",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Alias.signature of Alias('parse_meta', 'omniread.html.parser.HTMLParser.parse_meta')>",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser": {
|
||||
"name": "parser",
|
||||
"kind": "module",
|
||||
"path": "omniread.html.parser",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nHTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BeautifulSoup": {
|
||||
"name": "BeautifulSoup",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.BeautifulSoup",
|
||||
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Tag": {
|
||||
"name": "Tag",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Tag",
|
||||
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"HTMLParser": {
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.HTMLParser",
|
||||
"signature": "<bound method Class.signature of Class('HTMLParser', 30, 202)>",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.HTMLParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 81, 96)>",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||
"signature": "<bound method Function.signature of Function('parse_div', 102, 117)>",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||
"signature": "<bound method Function.signature of Function('parse_table', 134, 152)>",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Function.signature of Function('parse_meta', 174, 202)>",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"scraper": {
|
||||
"name": "scraper",
|
||||
"kind": "module",
|
||||
"path": "omniread.html.scraper",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nHTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"httpx": {
|
||||
"name": "httpx",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.httpx",
|
||||
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
},
|
||||
"HTMLScraper": {
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.HTMLScraper",
|
||||
"signature": "<bound method Class.signature of Class('HTMLScraper', 32, 143)>",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.HTMLScraper.content_type",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"validate_content_type": {
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Function.signature of Function('validate_content_type', 80, 102)>",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
234
libs/omniread/site/mcp/modules/omniread.html.parser.json
Normal file
234
libs/omniread/site/mcp/modules/omniread.html.parser.json
Normal file
@@ -0,0 +1,234 @@
|
||||
{
|
||||
"module": "omniread.html.parser",
|
||||
"content": {
|
||||
"path": "omniread.html.parser",
|
||||
"docstring": "# Summary\n\nHTML parser base implementations for OmniRead.\n\nThis module provides reusable HTML parsing utilities built on top of\nthe abstract parser contracts defined in `omniread.core.parser`.\n\nIt supplies:\n\n- Content-type enforcement for HTML inputs\n- BeautifulSoup initialization and lifecycle management\n- Common helper methods for extracting structured data from HTML elements\n\nConcrete parsers must subclass `HTMLParser` and implement the `parse()` method\nto return a structured representation appropriate for their use case.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BeautifulSoup": {
|
||||
"name": "BeautifulSoup",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.BeautifulSoup",
|
||||
"signature": "<bound method Alias.signature of Alias('BeautifulSoup', 'bs4.BeautifulSoup')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Tag": {
|
||||
"name": "Tag",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.parser.Tag",
|
||||
"signature": "<bound method Alias.signature of Alias('Tag', 'bs4.Tag')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"HTMLParser": {
|
||||
"name": "HTMLParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.parser.HTMLParser",
|
||||
"signature": "<bound method Class.signature of Class('HTMLParser', 30, 202)>",
|
||||
"docstring": "Base HTML parser.\n\nNotes:\n **Responsibilities:**\n\n - This class extends the core `BaseParser` with HTML-specific behavior,\n including DOM parsing via BeautifulSoup and reusable extraction helpers.\n - Provides reusable helpers for HTML extraction. Concrete parsers must\n explicitly define the return type.\n\n **Guarantees:**\n\n - Accepts only HTML content.\n - Owns a parsed BeautifulSoup DOM tree.\n - Provides pure helper utilities for common HTML structures.\n\n **Constraints:**\n\n - Concrete subclasses must define the output type `T` and implement\n the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.parser.HTMLParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (HTML only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 81, 96)>",
|
||||
"docstring": "Fully parse the HTML content into structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the HTML DOM and return a\n deterministic, structured output."
|
||||
},
|
||||
"parse_div": {
|
||||
"name": "parse_div",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_div",
|
||||
"signature": "<bound method Function.signature of Function('parse_div', 102, 117)>",
|
||||
"docstring": "Extract normalized text from a `<div>` element.\n\nArgs:\n div (Tag):\n BeautifulSoup tag representing a `<div>`.\n separator (str, optional):\n String used to separate text nodes.\n\nReturns:\n str:\n Flattened, whitespace-normalized text content."
|
||||
},
|
||||
"parse_link": {
|
||||
"name": "parse_link",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_link",
|
||||
"signature": "<bound method Function.signature of Function('parse_link', 119, 132)>",
|
||||
"docstring": "Extract the hyperlink reference from an `<a>` element.\n\nArgs:\n a (Tag):\n BeautifulSoup tag representing an anchor.\n\nReturns:\n Optional[str]:\n The value of the `href` attribute, or None if absent."
|
||||
},
|
||||
"parse_table": {
|
||||
"name": "parse_table",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_table",
|
||||
"signature": "<bound method Function.signature of Function('parse_table', 134, 152)>",
|
||||
"docstring": "Parse an HTML table into a 2D list of strings.\n\nArgs:\n table (Tag):\n BeautifulSoup tag representing a `<table>`.\n\nReturns:\n list[list[str]]:\n A list of rows, where each row is a list of cell text values."
|
||||
},
|
||||
"parse_meta": {
|
||||
"name": "parse_meta",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.parser.HTMLParser.parse_meta",
|
||||
"signature": "<bound method Function.signature of Function('parse_meta', 174, 202)>",
|
||||
"docstring": "Extract high-level metadata from the HTML document.\n\nReturns:\n dict[str, Any]:\n Dictionary containing extracted metadata.\n\nNotes:\n **Responsibilities:**\n\n - Extract high-level metadata from the HTML document.\n - This includes: Document title, `<meta>` tag name/property to\n content mappings."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
164
libs/omniread/site/mcp/modules/omniread.html.scraper.json
Normal file
164
libs/omniread/site/mcp/modules/omniread.html.scraper.json
Normal file
@@ -0,0 +1,164 @@
|
||||
{
|
||||
"module": "omniread.html.scraper",
|
||||
"content": {
|
||||
"path": "omniread.html.scraper",
|
||||
"docstring": "# Summary\n\nHTML scraping implementation for OmniRead.\n\nThis module provides an HTTP-based scraper for retrieving HTML documents.\nIt implements the core `BaseScraper` contract using `httpx` as the transport\nlayer.\n\nThis scraper is responsible for:\n\n- Fetching raw HTML bytes over HTTP(S)\n- Validating response content type\n- Attaching HTTP metadata to the returned content\n\nThis scraper is not responsible for:\n\n- Parsing or interpreting HTML\n- Retrying failed requests\n- Managing crawl policies or rate limiting",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"httpx": {
|
||||
"name": "httpx",
|
||||
"kind": "alias",
|
||||
"path": "omniread.html.scraper.httpx",
|
||||
"signature": "<bound method Alias.signature of Alias('httpx', 'httpx')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
},
|
||||
"HTMLScraper": {
|
||||
"name": "HTMLScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.html.scraper.HTMLScraper",
|
||||
"signature": "<bound method Class.signature of Class('HTMLScraper', 32, 143)>",
|
||||
"docstring": "Base HTML scraper using `httpx`.\n\nNotes:\n **Responsibilities:**\n\n - This scraper retrieves HTML documents over HTTP(S) and returns\n them as raw content wrapped in a `Content` object.\n - Fetches raw bytes and metadata only.\n - The scraper uses `httpx.Client` for HTTP requests, enforces an\n HTML content type, and preserves HTTP response metadata.\n\n **Constraints:**\n\n - The scraper does not: Parse HTML, perform retries or backoff,\n handle non-HTML responses.",
|
||||
"members": {
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.html.scraper.HTMLScraper.content_type",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"validate_content_type": {
|
||||
"name": "validate_content_type",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.validate_content_type",
|
||||
"signature": "<bound method Function.signature of Function('validate_content_type', 80, 102)>",
|
||||
"docstring": "Validate that the HTTP response contains HTML content.\n\nArgs:\n response (httpx.Response):\n HTTP response returned by `httpx`.\n\nRaises:\n ValueError:\n If the `Content-Type` header is missing or does not indicate HTML content."
|
||||
},
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.html.scraper.HTMLScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 104, 143)>",
|
||||
"docstring": "Fetch an HTML document from the given source.\n\nArgs:\n source (str):\n URL of the HTML document.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to be merged into the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw HTML bytes, source URL, HTML content type, and HTTP response metadata.\n\nRaises:\n httpx.HTTPError:\n If the HTTP request fails.\n ValueError:\n If the response is not valid HTML."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
3084
libs/omniread/site/mcp/modules/omniread.json
Normal file
3084
libs/omniread/site/mcp/modules/omniread.json
Normal file
File diff suppressed because it is too large
Load Diff
69
libs/omniread/site/mcp/modules/omniread.pdf.client.json
Normal file
69
libs/omniread/site/mcp/modules/omniread.pdf.client.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"module": "omniread.pdf.client",
|
||||
"content": {
|
||||
"path": "omniread.pdf.client",
|
||||
"docstring": "# Summary\n\nPDF client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw PDF\nbytes from a concrete backing store.\n\nClients provide low-level access to PDF binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.BasePDFClient",
|
||||
"signature": "<bound method Class.signature of Class('BasePDFClient', 25, 57)>",
|
||||
"docstring": "Abstract client responsible for retrieving PDF bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.BasePDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 57)>",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemPDFClient": {
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemPDFClient', 60, 96)>",
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 71, 96)>",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
440
libs/omniread/site/mcp/modules/omniread.pdf.json
Normal file
440
libs/omniread/site/mcp/modules/omniread.pdf.json
Normal file
@@ -0,0 +1,440 @@
|
||||
{
|
||||
"module": "omniread.pdf",
|
||||
"content": {
|
||||
"path": "omniread.pdf",
|
||||
"docstring": "# Summary\n\nPDF format implementation for OmniRead.\n\nThis package provides **PDF-specific implementations** of the core OmniRead\ncontracts defined in `omniread.core`.\n\nUnlike HTML, PDF handling requires an explicit client layer for document\naccess. This package therefore includes:\n\n- PDF clients for acquiring raw PDF data.\n- PDF scrapers that coordinate client access.\n- PDF parsers that extract structured content from PDF binaries.\n\nPublic exports from this package represent the supported PDF pipeline\nand are safe for consumers to import directly when working with PDFs.\n\n---\n\n# Public API\n\n- `FileSystemPDFClient`\n- `PDFScraper`\n- `PDFParser`\n\n---",
|
||||
"objects": {
|
||||
"FileSystemPDFClient": {
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.FileSystemPDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemPDFClient', 'omniread.pdf.client.FileSystemPDFClient')>",
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.FileSystemPDFClient.fetch')>",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
},
|
||||
"PDFScraper": {
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.PDFScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('PDFScraper', 'omniread.pdf.scraper.PDFScraper')>",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.PDFScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.scraper.PDFScraper.fetch')>",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
},
|
||||
"PDFParser": {
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.PDFParser",
|
||||
"signature": "<bound method Alias.signature of Alias('PDFParser', 'omniread.pdf.parser.PDFParser')>",
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.PDFParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.pdf.parser.PDFParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (PDF only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.PDFParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.pdf.parser.PDFParser.parse')>",
|
||||
"docstring": "Parse PDF content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
},
|
||||
"client": {
|
||||
"name": "client",
|
||||
"kind": "module",
|
||||
"path": "omniread.pdf.client",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw PDF\nbytes from a concrete backing store.\n\nClients provide low-level access to PDF binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.BasePDFClient",
|
||||
"signature": "<bound method Class.signature of Class('BasePDFClient', 25, 57)>",
|
||||
"docstring": "Abstract client responsible for retrieving PDF bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.BasePDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 57)>",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemPDFClient": {
|
||||
"name": "FileSystemPDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemPDFClient', 60, 96)>",
|
||||
"docstring": "PDF client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads PDF files directly from the disk and returns\n their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.client.FileSystemPDFClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 71, 96)>",
|
||||
"docstring": "Read a PDF file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the PDF file.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser": {
|
||||
"name": "parser",
|
||||
"kind": "module",
|
||||
"path": "omniread.pdf.parser",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF parser base implementations for OmniRead.\n\nThis module defines the **PDF-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for PDF content.\n\nPDF parsers are responsible for interpreting binary PDF data and producing\nstructured representations suitable for downstream consumption.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"PDFParser": {
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.PDFParser",
|
||||
"signature": "<bound method Class.signature of Class('PDFParser', 22, 62)>",
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.PDFParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (PDF only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.PDFParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 43, 62)>",
|
||||
"docstring": "Parse PDF content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"scraper": {
|
||||
"name": "scraper",
|
||||
"kind": "module",
|
||||
"path": "omniread.pdf.scraper",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nPDF scraping implementation for OmniRead.\n\nThis module provides a PDF-specific scraper that coordinates PDF byte\nretrieval via a client and normalizes the result into a `Content` object.\n\nThe scraper implements the core `BaseScraper` contract while delegating\nall storage and access concerns to a `BasePDFClient` implementation.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving PDF bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.BasePDFClient.fetch')>",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"PDFScraper": {
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.PDFScraper",
|
||||
"signature": "<bound method Class.signature of Class('PDFScraper', 21, 78)>",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.PDFScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
148
libs/omniread/site/mcp/modules/omniread.pdf.parser.json
Normal file
148
libs/omniread/site/mcp/modules/omniread.pdf.parser.json
Normal file
@@ -0,0 +1,148 @@
|
||||
{
|
||||
"module": "omniread.pdf.parser",
|
||||
"content": {
|
||||
"path": "omniread.pdf.parser",
|
||||
"docstring": "# Summary\n\nPDF parser base implementations for OmniRead.\n\nThis module defines the **PDF-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for PDF content.\n\nPDF parsers are responsible for interpreting binary PDF data and producing\nstructured representations suitable for downstream consumption.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.parser.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"PDFParser": {
|
||||
"name": "PDFParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.parser.PDFParser",
|
||||
"signature": "<bound method Class.signature of Class('PDFParser', 22, 62)>",
|
||||
"docstring": "Base PDF parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces PDF content-type compatibility and provides\n the extension point for implementing concrete PDF parsing strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.parser.PDFParser.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (PDF only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.parser.PDFParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 43, 62)>",
|
||||
"docstring": "Parse PDF content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully interpret the PDF binary payload and\n return a deterministic, structured output."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
159
libs/omniread/site/mcp/modules/omniread.pdf.scraper.json
Normal file
159
libs/omniread/site/mcp/modules/omniread.pdf.scraper.json
Normal file
@@ -0,0 +1,159 @@
|
||||
{
|
||||
"module": "omniread.pdf.scraper",
|
||||
"content": {
|
||||
"path": "omniread.pdf.scraper",
|
||||
"docstring": "# Summary\n\nPDF scraping implementation for OmniRead.\n\nThis module provides a PDF-specific scraper that coordinates PDF byte\nretrieval via a client and normalizes the result into a `Content` object.\n\nThe scraper implements the core `BaseScraper` contract while delegating\nall storage and access concerns to a `BasePDFClient` implementation.",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.pdf.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.pdf.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseScraper": {
|
||||
"name": "BaseScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BaseScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseScraper', 'omniread.core.scraper.BaseScraper')>",
|
||||
"docstring": "Base interface for all scrapers.\n\nNotes:\n **Responsibilities:**\n\n - A scraper is responsible ONLY for fetching raw content (bytes)\n from a source. It must not interpret or parse it.\n - A scraper is a stateless acquisition component that retrieves raw\n content from a source and returns it as a `Content` object.\n - Scrapers define how content is obtained, not what the content means.\n - Implementations may vary in transport mechanism, authentication\n strategy, retry and backoff behavior.\n\n **Constraints:**\n\n - Implementations must not parse content, modify content semantics,\n or couple scraping logic to a specific parser.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BaseScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.core.scraper.BaseScraper.fetch')>",
|
||||
"docstring": "Fetch raw content from the given source.\n\nArgs:\n source (str):\n Location identifier (URL, file path, S3 URI, etc.).\n\n metadata (Optional[Mapping[str, Any]], optional):\n Optional hints for the scraper (headers, auth, etc.).\n\nReturns:\n Content:\n Content object containing raw bytes and metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must retrieve the content referenced by `source`\n and return it as raw bytes wrapped in a `Content` object."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BasePDFClient": {
|
||||
"name": "BasePDFClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BasePDFClient', 'omniread.pdf.client.BasePDFClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving PDF bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full PDF binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.BasePDFClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.pdf.client.BasePDFClient.fetch')>",
|
||||
"docstring": "Fetch raw PDF bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF location, such as a file path, object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw PDF bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"PDFScraper": {
|
||||
"name": "PDFScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.pdf.scraper.PDFScraper",
|
||||
"signature": "<bound method Class.signature of Class('PDFScraper', 21, 78)>",
|
||||
"docstring": "Scraper for PDF sources.\n\nNotes:\n **Responsibilities:**\n\n - Delegates byte retrieval to a PDF client and normalizes output\n into `Content`.\n - Preserves caller-provided metadata.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.pdf.scraper.PDFScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 78)>",
|
||||
"docstring": "Fetch a PDF document from the given source.\n\nArgs:\n source (Any):\n Identifier of the PDF source as understood by the configured PDF client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw PDF bytes, source identifier, PDF content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the PDF client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
69
libs/omniread/site/mcp/modules/omniread.xlsx.client.json
Normal file
69
libs/omniread/site/mcp/modules/omniread.xlsx.client.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"module": "omniread.xlsx.client",
|
||||
"content": {
|
||||
"path": "omniread.xlsx.client",
|
||||
"docstring": "# Summary\n\nXLSX client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\nOffice Open XML spreadsheet bytes from a concrete backing store.\n\nClients provide low-level access to xlsx binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"objects": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BaseXlsxClient": {
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.BaseXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('BaseXlsxClient', 25, 58)>",
|
||||
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.client.BaseXlsxClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
||||
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemXlsxClient": {
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemXlsxClient', 61, 97)>",
|
||||
"docstring": "XLSX client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads spreadsheet files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
||||
"docstring": "Read an xlsx file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the spreadsheet file.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
611
libs/omniread/site/mcp/modules/omniread.xlsx.json
Normal file
611
libs/omniread/site/mcp/modules/omniread.xlsx.json
Normal file
@@ -0,0 +1,611 @@
|
||||
{
|
||||
"module": "omniread.xlsx",
|
||||
"content": {
|
||||
"path": "omniread.xlsx",
|
||||
"docstring": "# Summary\n\nXLSX subpackage for OmniRead.\n\nProvides acquisition and parsing of Office Open XML spreadsheet (xlsx)\ncontent:\n\n- `BaseXlsxClient`: abstract backing-store client for xlsx bytes.\n- `FileSystemXlsxClient`: local filesystem implementation.\n- `XlsxScraper`: wraps fetched bytes into canonical `Content`.\n- `XlsxParserBase`: content-type-enforcing parser contract.\n- `XlsxParser`: generic string-row parser built on openpyxl.",
|
||||
"objects": {
|
||||
"BaseXlsxClient": {
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.BaseXlsxClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.BaseXlsxClient.fetch')>",
|
||||
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemXlsxClient": {
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.FileSystemXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('FileSystemXlsxClient', 'omniread.xlsx.client.FileSystemXlsxClient')>",
|
||||
"docstring": "XLSX client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads spreadsheet files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.FileSystemXlsxClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.FileSystemXlsxClient.fetch')>",
|
||||
"docstring": "Read an xlsx file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the spreadsheet file.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParser": {
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxParser",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParser', 'omniread.xlsx.parser.XlsxParser')>",
|
||||
"docstring": "Generic xlsx parser producing string rows from a worksheet.\n\nNotes:\n **Responsibilities:**\n\n - Lazily load the workbook owned by the parser's content.\n - Normalize cells (including dates and numeric values) into\n deterministic string representations.\n - Expose sheet discovery and row extraction helpers.\n\n **Constraints:**\n\n - Cells are rendered with ``str(value)`` after trimming; date and\n datetime values are rendered in ISO format. Consumers requiring\n locale-specific formatting must convert on their side.",
|
||||
"members": {
|
||||
"workbook": {
|
||||
"name": "workbook",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.XlsxParser.workbook",
|
||||
"signature": "<bound method Alias.signature of Alias('workbook', 'omniread.xlsx.parser.XlsxParser.workbook')>",
|
||||
"docstring": "The lazily loaded workbook backing this parser's content."
|
||||
},
|
||||
"sheet_names": {
|
||||
"name": "sheet_names",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.XlsxParser.sheet_names",
|
||||
"signature": "<bound method Alias.signature of Alias('sheet_names', 'omniread.xlsx.parser.XlsxParser.sheet_names')>",
|
||||
"docstring": "Names of all worksheets contained in the workbook."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.XlsxParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser.XlsxParser.parse')>",
|
||||
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.XlsxParser.rows",
|
||||
"signature": "<bound method Alias.signature of Alias('rows', 'omniread.xlsx.parser.XlsxParser.rows')>",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParserBase": {
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.XlsxParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.xlsx.parser_base.XlsxParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (XLSX only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.XlsxParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser_base.XlsxParserBase.parse')>",
|
||||
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxScraper": {
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.XlsxScraper",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxScraper', 'omniread.xlsx.scraper.XlsxScraper')>",
|
||||
"docstring": "Scraper for xlsx spreadsheet documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw xlsx bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n XLSX content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.XlsxScraper.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.scraper.XlsxScraper.fetch')>",
|
||||
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
},
|
||||
"client": {
|
||||
"name": "client",
|
||||
"kind": "module",
|
||||
"path": "omniread.xlsx.client",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nXLSX client abstractions for OmniRead.\n\nThis module defines the **client layer** responsible for retrieving raw\nOffice Open XML spreadsheet bytes from a concrete backing store.\n\nClients provide low-level access to xlsx binaries and are intentionally\ndecoupled from scraping and parsing logic. They do not perform validation,\ninterpretation, or content extraction.\n\nTypical backing stores include:\n\n- Local filesystems\n- Object storage (S3, GCS, etc.)\n- Network file systems",
|
||||
"members": {
|
||||
"ABC": {
|
||||
"name": "ABC",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.ABC",
|
||||
"signature": "<bound method Alias.signature of Alias('ABC', 'abc.ABC')>",
|
||||
"docstring": null
|
||||
},
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Path": {
|
||||
"name": "Path",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.Path",
|
||||
"signature": "<bound method Alias.signature of Alias('Path', 'pathlib.Path')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.client.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BaseXlsxClient": {
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.BaseXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('BaseXlsxClient', 25, 58)>",
|
||||
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.client.BaseXlsxClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 40, 58)>",
|
||||
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"FileSystemXlsxClient": {
|
||||
"name": "FileSystemXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient",
|
||||
"signature": "<bound method Class.signature of Class('FileSystemXlsxClient', 61, 97)>",
|
||||
"docstring": "XLSX client that reads from the local filesystem.\n\nNotes:\n **Guarantees:**\n\n - This client reads spreadsheet files directly from the disk and\n returns their raw binary contents.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.client.FileSystemXlsxClient.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 72, 97)>",
|
||||
"docstring": "Read an xlsx file from the local filesystem.\n\nArgs:\n path (Path):\n Filesystem path to the spreadsheet file.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n FileNotFoundError:\n If the path does not exist.\n ValueError:\n If the path exists but is not a file."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser": {
|
||||
"name": "parser",
|
||||
"kind": "module",
|
||||
"path": "omniread.xlsx.parser",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nXLSX parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for Office Open XML\nspreadsheets. It exposes workbook sheets as lists of string rows so\ndownstream consumers can interpret tabular content without depending on\nopenpyxl directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization.",
|
||||
"members": {
|
||||
"datetime": {
|
||||
"name": "datetime",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.datetime",
|
||||
"signature": "<bound method Alias.signature of Alias('datetime', 'datetime')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BytesIO": {
|
||||
"name": "BytesIO",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.BytesIO",
|
||||
"signature": "<bound method Alias.signature of Alias('BytesIO', 'io.BytesIO')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"openpyxl": {
|
||||
"name": "openpyxl",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.openpyxl",
|
||||
"signature": "<bound method Alias.signature of Alias('openpyxl', 'openpyxl')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParserBase": {
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.xlsx.parser_base.XlsxParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (XLSX only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser_base.XlsxParserBase.parse')>",
|
||||
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParser": {
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParser",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParser', 26, 149)>",
|
||||
"docstring": "Generic xlsx parser producing string rows from a worksheet.\n\nNotes:\n **Responsibilities:**\n\n - Lazily load the workbook owned by the parser's content.\n - Normalize cells (including dates and numeric values) into\n deterministic string representations.\n - Expose sheet discovery and row extraction helpers.\n\n **Constraints:**\n\n - Cells are rendered with ``str(value)`` after trimming; date and\n datetime values are rendered in ISO format. Consumers requiring\n locale-specific formatting must convert on their side.",
|
||||
"members": {
|
||||
"workbook": {
|
||||
"name": "workbook",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.workbook",
|
||||
"signature": null,
|
||||
"docstring": "The lazily loaded workbook backing this parser's content."
|
||||
},
|
||||
"sheet_names": {
|
||||
"name": "sheet_names",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.sheet_names",
|
||||
"signature": null,
|
||||
"docstring": "Names of all worksheets contained in the workbook."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 85, 93)>",
|
||||
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.rows",
|
||||
"signature": "<bound method Function.signature of Function('rows', 95, 127)>",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"parser_base": {
|
||||
"name": "parser_base",
|
||||
"kind": "module",
|
||||
"path": "omniread.xlsx.parser_base",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nXLSX parser base implementation for OmniRead.\n\nThis module defines the **XLSX-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for Office Open\nXML spreadsheet content.",
|
||||
"members": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"XlsxParserBase": {
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParserBase', 20, 55)>",
|
||||
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (XLSX only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"scraper": {
|
||||
"name": "scraper",
|
||||
"kind": "module",
|
||||
"path": "omniread.xlsx.scraper",
|
||||
"signature": null,
|
||||
"docstring": "# Summary\n\nXLSX scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw Office Open\nXML spreadsheet content from a backing store via a configured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
|
||||
"members": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseXlsxClient": {
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.BaseXlsxClient.fetch')>",
|
||||
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxScraper": {
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper",
|
||||
"signature": "<bound method Class.signature of Class('XlsxScraper', 21, 80)>",
|
||||
"docstring": "Scraper for xlsx spreadsheet documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw xlsx bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n XLSX content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
|
||||
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
134
libs/omniread/site/mcp/modules/omniread.xlsx.parser.json
Normal file
134
libs/omniread/site/mcp/modules/omniread.xlsx.parser.json
Normal file
@@ -0,0 +1,134 @@
|
||||
{
|
||||
"module": "omniread.xlsx.parser",
|
||||
"content": {
|
||||
"path": "omniread.xlsx.parser",
|
||||
"docstring": "# Summary\n\nXLSX parser implementations for OmniRead.\n\nThis module provides a concrete, generic parser for Office Open XML\nspreadsheets. It exposes workbook sheets as lists of string rows so\ndownstream consumers can interpret tabular content without depending on\nopenpyxl directly.\n\nThe parser is intentionally statement-agnostic: it performs no header\ndetection or column interpretation beyond basic cell normalization.",
|
||||
"objects": {
|
||||
"datetime": {
|
||||
"name": "datetime",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.datetime",
|
||||
"signature": "<bound method Alias.signature of Alias('datetime', 'datetime')>",
|
||||
"docstring": null
|
||||
},
|
||||
"BytesIO": {
|
||||
"name": "BytesIO",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.BytesIO",
|
||||
"signature": "<bound method Alias.signature of Alias('BytesIO', 'io.BytesIO')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"openpyxl": {
|
||||
"name": "openpyxl",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser.openpyxl",
|
||||
"signature": "<bound method Alias.signature of Alias('openpyxl', 'openpyxl')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParserBase": {
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase",
|
||||
"signature": "<bound method Alias.signature of Alias('XlsxParserBase', 'omniread.xlsx.parser_base.XlsxParserBase')>",
|
||||
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.xlsx.parser_base.XlsxParserBase.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser (XLSX only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParserBase.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.xlsx.parser_base.XlsxParserBase.parse')>",
|
||||
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxParser": {
|
||||
"name": "XlsxParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser.XlsxParser",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParser', 26, 149)>",
|
||||
"docstring": "Generic xlsx parser producing string rows from a worksheet.\n\nNotes:\n **Responsibilities:**\n\n - Lazily load the workbook owned by the parser's content.\n - Normalize cells (including dates and numeric values) into\n deterministic string representations.\n - Expose sheet discovery and row extraction helpers.\n\n **Constraints:**\n\n - Cells are rendered with ``str(value)`` after trimming; date and\n datetime values are rendered in ISO format. Consumers requiring\n locale-specific formatting must convert on their side.",
|
||||
"members": {
|
||||
"workbook": {
|
||||
"name": "workbook",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.workbook",
|
||||
"signature": null,
|
||||
"docstring": "The lazily loaded workbook backing this parser's content."
|
||||
},
|
||||
"sheet_names": {
|
||||
"name": "sheet_names",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.sheet_names",
|
||||
"signature": null,
|
||||
"docstring": "Names of all worksheets contained in the workbook."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 85, 93)>",
|
||||
"docstring": "Parse the first worksheet into normalized string rows.\n\nReturns:\n List[List[str]]:\n Rows of the default (first) worksheet."
|
||||
},
|
||||
"rows": {
|
||||
"name": "rows",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser.XlsxParser.rows",
|
||||
"signature": "<bound method Function.signature of Function('rows', 95, 127)>",
|
||||
"docstring": "Extract normalized string rows from a worksheet.\n\nArgs:\n sheet (Optional[Union[int, str]]):\n Worksheet index or title; defaults to the first worksheet.\n skip_empty (bool):\n When True (default), rows whose cells are all blank are omitted.\n\nReturns:\n List[List[str]]:\n Normalized rows; trailing blank cells are trimmed per row.\n\nRaises:\n ValueError:\n If the requested sheet does not exist."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
148
libs/omniread/site/mcp/modules/omniread.xlsx.parser_base.json
Normal file
148
libs/omniread/site/mcp/modules/omniread.xlsx.parser_base.json
Normal file
@@ -0,0 +1,148 @@
|
||||
{
|
||||
"module": "omniread.xlsx.parser_base",
|
||||
"content": {
|
||||
"path": "omniread.xlsx.parser_base",
|
||||
"docstring": "# Summary\n\nXLSX parser base implementation for OmniRead.\n\nThis module defines the **XLSX-specific parser contract**, extending the\nformat-agnostic `BaseParser` with constraints appropriate for Office Open\nXML spreadsheet content.",
|
||||
"objects": {
|
||||
"abstractmethod": {
|
||||
"name": "abstractmethod",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.abstractmethod",
|
||||
"signature": "<bound method Alias.signature of Alias('abstractmethod', 'abc.abstractmethod')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Generic": {
|
||||
"name": "Generic",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.Generic",
|
||||
"signature": "<bound method Alias.signature of Alias('Generic', 'typing.Generic')>",
|
||||
"docstring": null
|
||||
},
|
||||
"TypeVar": {
|
||||
"name": "TypeVar",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.parser_base.TypeVar",
|
||||
"signature": "<bound method Alias.signature of Alias('TypeVar', 'typing.TypeVar')>",
|
||||
"docstring": null
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseParser": {
|
||||
"name": "BaseParser",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseParser', 'omniread.core.parser.BaseParser')>",
|
||||
"docstring": "Base interface for all parsers.\n\nNotes:\n **Guarantees:**\n\n - A parser is a self-contained object that owns the `Content` it is\n responsible for interpreting.\n - Consumers may rely on early validation of content compatibility\n and type-stable return values from `parse()`.\n\n **Responsibilities:**\n\n - Implementations must declare supported content types via `supported_types`.\n - Implementations must raise parsing-specific exceptions from `parse()`.\n - Implementations must remain deterministic for a given input.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.supported_types",
|
||||
"signature": "<bound method Alias.signature of Alias('supported_types', 'omniread.core.parser.BaseParser.supported_types')>",
|
||||
"docstring": "Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic."
|
||||
},
|
||||
"content": {
|
||||
"name": "content",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.content",
|
||||
"signature": "<bound method Alias.signature of Alias('content', 'omniread.core.parser.BaseParser.content')>",
|
||||
"docstring": null
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.parse",
|
||||
"signature": "<bound method Alias.signature of Alias('parse', 'omniread.core.parser.BaseParser.parse')>",
|
||||
"docstring": "Parse the owned content into structured output.\n\nReturns:\n T:\n Parsed, structured representation.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation.\n\nNotes:\n **Responsibilities:**\n\n - Implementations must fully consume the provided content and\n return a deterministic, structured output."
|
||||
},
|
||||
"supports": {
|
||||
"name": "supports",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.BaseParser.supports",
|
||||
"signature": "<bound method Alias.signature of Alias('supports', 'omniread.core.parser.BaseParser.supports')>",
|
||||
"docstring": "Check whether this parser supports the content's type.\n\nReturns:\n bool:\n True if the content type is supported; False otherwise."
|
||||
}
|
||||
}
|
||||
},
|
||||
"T": {
|
||||
"name": "T",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.T",
|
||||
"signature": null,
|
||||
"docstring": null
|
||||
},
|
||||
"XlsxParserBase": {
|
||||
"name": "XlsxParserBase",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase",
|
||||
"signature": "<bound method Class.signature of Class('XlsxParserBase', 20, 55)>",
|
||||
"docstring": "Base xlsx parser.\n\nNotes:\n **Responsibilities:**\n\n - This class enforces xlsx content-type compatibility and provides\n the extension point for implementing concrete xlsx parsing\n strategies.\n\n **Constraints:**\n\n - Concrete implementations must define the output type `T` and\n implement the `parse()` method.",
|
||||
"members": {
|
||||
"supported_types": {
|
||||
"name": "supported_types",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.supported_types",
|
||||
"signature": null,
|
||||
"docstring": "Set of content types supported by this parser (XLSX only)."
|
||||
},
|
||||
"parse": {
|
||||
"name": "parse",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.parser_base.XlsxParserBase.parse",
|
||||
"signature": "<bound method Function.signature of Function('parse', 42, 55)>",
|
||||
"docstring": "Parse xlsx content into a structured output.\n\nReturns:\n T:\n Parsed representation of type `T`.\n\nRaises:\n Exception:\n Parsing-specific errors as defined by the implementation."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
143
libs/omniread/site/mcp/modules/omniread.xlsx.scraper.json
Normal file
143
libs/omniread/site/mcp/modules/omniread.xlsx.scraper.json
Normal file
@@ -0,0 +1,143 @@
|
||||
{
|
||||
"module": "omniread.xlsx.scraper",
|
||||
"content": {
|
||||
"path": "omniread.xlsx.scraper",
|
||||
"docstring": "# Summary\n\nXLSX scraper for OmniRead.\n\nThis module defines the scraper responsible for acquiring raw Office Open\nXML spreadsheet content from a backing store via a configured client.\n\nThe scraper does not interpret or parse the acquired bytes; it wraps them in\nthe canonical `Content` model.",
|
||||
"objects": {
|
||||
"Mapping": {
|
||||
"name": "Mapping",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.scraper.Mapping",
|
||||
"signature": "<bound method Alias.signature of Alias('Mapping', 'collections.abc.Mapping')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Any": {
|
||||
"name": "Any",
|
||||
"kind": "alias",
|
||||
"path": "omniread.xlsx.scraper.Any",
|
||||
"signature": "<bound method Alias.signature of Alias('Any', 'typing.Any')>",
|
||||
"docstring": null
|
||||
},
|
||||
"Content": {
|
||||
"name": "Content",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.Content",
|
||||
"signature": "<bound method Alias.signature of Alias('Content', 'omniread.core.content.Content')>",
|
||||
"docstring": "Normalized representation of extracted content.\n\nNotes:\n **Responsibilities:**\n\n - A `Content` instance represents a raw content payload along with\n minimal contextual metadata describing its origin and type.\n - This class is the primary exchange format between scrapers,\n parsers, and downstream consumers.",
|
||||
"members": {
|
||||
"raw": {
|
||||
"name": "raw",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.raw",
|
||||
"signature": "<bound method Alias.signature of Alias('raw', 'omniread.core.content.Content.raw')>",
|
||||
"docstring": "Raw content bytes as retrieved from the source."
|
||||
},
|
||||
"source": {
|
||||
"name": "source",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.source",
|
||||
"signature": "<bound method Alias.signature of Alias('source', 'omniread.core.content.Content.source')>",
|
||||
"docstring": "Identifier of the content origin (URL, file path, or logical name)."
|
||||
},
|
||||
"content_type": {
|
||||
"name": "content_type",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.content_type",
|
||||
"signature": "<bound method Alias.signature of Alias('content_type', 'omniread.core.content.Content.content_type')>",
|
||||
"docstring": "Optional MIME type of the content, if known."
|
||||
},
|
||||
"metadata": {
|
||||
"name": "metadata",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.Content.metadata",
|
||||
"signature": "<bound method Alias.signature of Alias('metadata', 'omniread.core.content.Content.metadata')>",
|
||||
"docstring": "Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes)."
|
||||
}
|
||||
}
|
||||
},
|
||||
"ContentType": {
|
||||
"name": "ContentType",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.ContentType",
|
||||
"signature": "<bound method Alias.signature of Alias('ContentType', 'omniread.core.content.ContentType')>",
|
||||
"docstring": "Supported MIME types for extracted content.\n\nNotes:\n **Guarantees:**\n\n - This enum represents the declared or inferred media type of the\n content source.\n - It is primarily used for routing content to the appropriate\n parser or downstream consumer.",
|
||||
"members": {
|
||||
"HTML": {
|
||||
"name": "HTML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.HTML",
|
||||
"signature": "<bound method Alias.signature of Alias('HTML', 'omniread.core.content.ContentType.HTML')>",
|
||||
"docstring": "HTML document content."
|
||||
},
|
||||
"PDF": {
|
||||
"name": "PDF",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.PDF",
|
||||
"signature": "<bound method Alias.signature of Alias('PDF', 'omniread.core.content.ContentType.PDF')>",
|
||||
"docstring": "PDF document content."
|
||||
},
|
||||
"XLSX": {
|
||||
"name": "XLSX",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.XLSX",
|
||||
"signature": "<bound method Alias.signature of Alias('XLSX', 'omniread.core.content.ContentType.XLSX')>",
|
||||
"docstring": "Office Open XML spreadsheet (xlsx/xlsm) content."
|
||||
},
|
||||
"CSV": {
|
||||
"name": "CSV",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.CSV",
|
||||
"signature": "<bound method Alias.signature of Alias('CSV', 'omniread.core.content.ContentType.CSV')>",
|
||||
"docstring": "Comma-separated-value document content."
|
||||
},
|
||||
"JSON": {
|
||||
"name": "JSON",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.JSON",
|
||||
"signature": "<bound method Alias.signature of Alias('JSON', 'omniread.core.content.ContentType.JSON')>",
|
||||
"docstring": "JSON document content."
|
||||
},
|
||||
"XML": {
|
||||
"name": "XML",
|
||||
"kind": "attribute",
|
||||
"path": "omniread.xlsx.scraper.ContentType.XML",
|
||||
"signature": "<bound method Alias.signature of Alias('XML', 'omniread.core.content.ContentType.XML')>",
|
||||
"docstring": "XML document content."
|
||||
}
|
||||
}
|
||||
},
|
||||
"BaseXlsxClient": {
|
||||
"name": "BaseXlsxClient",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient",
|
||||
"signature": "<bound method Alias.signature of Alias('BaseXlsxClient', 'omniread.xlsx.client.BaseXlsxClient')>",
|
||||
"docstring": "Abstract client responsible for retrieving spreadsheet bytes.\n\nRetrieves bytes from a specific backing store (filesystem, S3, FTP, etc.).\n\nNotes:\n **Responsibilities:**\n\n - Implementations must accept a source identifier appropriate to\n the backing store.\n - Return the full xlsx binary payload.\n - Raise retrieval-specific errors on failure.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.scraper.BaseXlsxClient.fetch",
|
||||
"signature": "<bound method Alias.signature of Alias('fetch', 'omniread.xlsx.client.BaseXlsxClient.fetch')>",
|
||||
"docstring": "Fetch raw xlsx bytes from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet location, such as a file path,\n object storage key, or remote reference.\n\nReturns:\n bytes:\n Raw xlsx bytes.\n\nRaises:\n Exception:\n Retrieval-specific errors defined by the implementation."
|
||||
}
|
||||
}
|
||||
},
|
||||
"XlsxScraper": {
|
||||
"name": "XlsxScraper",
|
||||
"kind": "class",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper",
|
||||
"signature": "<bound method Class.signature of Class('XlsxScraper', 21, 80)>",
|
||||
"docstring": "Scraper for xlsx spreadsheet documents.\n\nNotes:\n **Responsibilities:**\n\n - Fetch raw xlsx bytes via the configured client.\n - Wrap the payload in a canonical `Content` instance with the\n XLSX content type and source identifier.\n\n **Constraints:**\n\n - The scraper does not perform parsing or interpretation.\n - Does not assume a specific storage backend.",
|
||||
"members": {
|
||||
"fetch": {
|
||||
"name": "fetch",
|
||||
"kind": "function",
|
||||
"path": "omniread.xlsx.scraper.XlsxScraper.fetch",
|
||||
"signature": "<bound method Function.signature of Function('fetch', 48, 80)>",
|
||||
"docstring": "Fetch an xlsx document from the given source.\n\nArgs:\n source (Any):\n Identifier of the spreadsheet source as understood by the\n configured client.\n metadata (Optional[Mapping[str, Any]], optional):\n Optional metadata to attach to the returned content.\n\nReturns:\n Content:\n A `Content` instance containing raw xlsx bytes, source\n identifier, XLSX content type, and optional metadata.\n\nRaises:\n Exception:\n Retrieval-specific errors raised by the client."
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
90
libs/omniread/site/mcp/nav.json
Normal file
90
libs/omniread/site/mcp/nav.json
Normal file
@@ -0,0 +1,90 @@
|
||||
[
|
||||
{
|
||||
"module": "omniread",
|
||||
"resource": "doc://modules/omniread"
|
||||
},
|
||||
{
|
||||
"module": "omniread.core",
|
||||
"resource": "doc://modules/omniread.core"
|
||||
},
|
||||
{
|
||||
"module": "omniread.core.content",
|
||||
"resource": "doc://modules/omniread.core.content"
|
||||
},
|
||||
{
|
||||
"module": "omniread.core.parser",
|
||||
"resource": "doc://modules/omniread.core.parser"
|
||||
},
|
||||
{
|
||||
"module": "omniread.core.scraper",
|
||||
"resource": "doc://modules/omniread.core.scraper"
|
||||
},
|
||||
{
|
||||
"module": "omniread.csv",
|
||||
"resource": "doc://modules/omniread.csv"
|
||||
},
|
||||
{
|
||||
"module": "omniread.csv.client",
|
||||
"resource": "doc://modules/omniread.csv.client"
|
||||
},
|
||||
{
|
||||
"module": "omniread.csv.parser",
|
||||
"resource": "doc://modules/omniread.csv.parser"
|
||||
},
|
||||
{
|
||||
"module": "omniread.csv.parser_base",
|
||||
"resource": "doc://modules/omniread.csv.parser_base"
|
||||
},
|
||||
{
|
||||
"module": "omniread.csv.scraper",
|
||||
"resource": "doc://modules/omniread.csv.scraper"
|
||||
},
|
||||
{
|
||||
"module": "omniread.html",
|
||||
"resource": "doc://modules/omniread.html"
|
||||
},
|
||||
{
|
||||
"module": "omniread.html.parser",
|
||||
"resource": "doc://modules/omniread.html.parser"
|
||||
},
|
||||
{
|
||||
"module": "omniread.html.scraper",
|
||||
"resource": "doc://modules/omniread.html.scraper"
|
||||
},
|
||||
{
|
||||
"module": "omniread.pdf",
|
||||
"resource": "doc://modules/omniread.pdf"
|
||||
},
|
||||
{
|
||||
"module": "omniread.pdf.client",
|
||||
"resource": "doc://modules/omniread.pdf.client"
|
||||
},
|
||||
{
|
||||
"module": "omniread.pdf.parser",
|
||||
"resource": "doc://modules/omniread.pdf.parser"
|
||||
},
|
||||
{
|
||||
"module": "omniread.pdf.scraper",
|
||||
"resource": "doc://modules/omniread.pdf.scraper"
|
||||
},
|
||||
{
|
||||
"module": "omniread.xlsx",
|
||||
"resource": "doc://modules/omniread.xlsx"
|
||||
},
|
||||
{
|
||||
"module": "omniread.xlsx.client",
|
||||
"resource": "doc://modules/omniread.xlsx.client"
|
||||
},
|
||||
{
|
||||
"module": "omniread.xlsx.parser",
|
||||
"resource": "doc://modules/omniread.xlsx.parser"
|
||||
},
|
||||
{
|
||||
"module": "omniread.xlsx.parser_base",
|
||||
"resource": "doc://modules/omniread.xlsx.parser_base"
|
||||
},
|
||||
{
|
||||
"module": "omniread.xlsx.scraper",
|
||||
"resource": "doc://modules/omniread.xlsx.scraper"
|
||||
}
|
||||
]
|
||||
Binary file not shown.
File diff suppressed because one or more lines are too long
Binary file not shown.
Reference in New Issue
Block a user