fix: vendor per-kind sites in the hub; drop stale blog docs

- collect.py: when a kind points at the shared site root, copy only the
  per-kind subdir (site/lib -> <repo>/lib) instead of the whole site, so
  stray single-site build output never leaks into the hub
- Purge stale collected artifacts (404.html, assets/, search/, sitemaps,
  objects.inv, duplicate mcp/) from every repo dir, matching the cleaned
  source site/ roots
- Refresh collected output from source repos, incl. the khata-app app
- Remove the vendored Blog API docs (config.yml entry + blog/) and its card
This commit is contained in:
2026-10-11 23:12:19 +05:30
parent 74aaf2f53e
commit c5619bc5e8
526 changed files with 10 additions and 104714 deletions

View File

@@ -1,717 +0,0 @@
<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="icon" href="/assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
<title>omniread</title>
<link rel="stylesheet" href="/assets/stylesheets/main.84d31ad4.min.css">
<link rel="stylesheet" href="/assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Inter:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Inter";--md-code-font:"JetBrains Mono"}</style>
<link rel="stylesheet" href="/assets/_mkdocstrings.css">
<link rel="stylesheet" href="https://unpkg.com/dracula-prism/dist/css/dracula-prism.css">
<script>__md_scope=new URL("/",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="/." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
omniread
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan" aria-hidden="true" type="radio" name="__palette" id="__palette_0">
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="/." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></svg>
</a>
omniread
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="/lib/" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_2" >
<div class="md-nav__link md-nav__container">
<a href="/lib/core/" class="md-nav__link ">
<span class="md-ellipsis">
Core API
</span>
</a>
<label class="md-nav__link " for="__nav_2" id="__nav_2_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Core API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="/lib/core/content/" class="md-nav__link">
<span class="md-ellipsis">
Content
</span>
</a>
</li>
<li class="md-nav__item">
<a href="/lib/core/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="/lib/core/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<div class="md-nav__link md-nav__container">
<a href="/lib/html/" class="md-nav__link ">
<span class="md-ellipsis">
HTML Handling
</span>
</a>
<label class="md-nav__link " for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
HTML Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="/lib/html/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="/lib/html/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<div class="md-nav__link md-nav__container">
<a href="/lib/pdf/" class="md-nav__link ">
<span class="md-ellipsis">
PDF Handling
</span>
</a>
<label class="md-nav__link " for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
PDF Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="/lib/pdf/client/" class="md-nav__link">
<span class="md-ellipsis">
Client
</span>
</a>
</li>
<li class="md-nav__item">
<a href="/lib/pdf/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="/lib/pdf/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1>404 - Not found</h1>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var labels=set.querySelector(".tabbed-labels");for(var tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "/", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest"], "search": "/assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="/assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>

View File

@@ -1,119 +0,0 @@
/* Avoid breaking parameter names, etc. in table cells. */
.doc-contents td code {
word-break: normal !important;
}
/* No line break before first paragraph of descriptions. */
.doc-md-description,
.doc-md-description>p:first-child {
display: inline;
}
/* Max width for docstring sections tables. */
.doc .md-typeset__table,
.doc .md-typeset__table table {
display: table !important;
width: 100%;
}
.doc .md-typeset__table tr {
display: table-row;
}
/* Defaults in Spacy table style. */
.doc-param-default {
float: right;
}
/* Backward-compatibility: docstring section titles in bold. */
.doc-section-title {
font-weight: bold;
}
/* Symbols in Navigation and ToC. */
:root,
[data-md-color-scheme="default"] {
--doc-symbol-attribute-fg-color: #953800;
--doc-symbol-function-fg-color: #8250df;
--doc-symbol-method-fg-color: #8250df;
--doc-symbol-class-fg-color: #0550ae;
--doc-symbol-module-fg-color: #5cad0f;
--doc-symbol-attribute-bg-color: #9538001a;
--doc-symbol-function-bg-color: #8250df1a;
--doc-symbol-method-bg-color: #8250df1a;
--doc-symbol-class-bg-color: #0550ae1a;
--doc-symbol-module-bg-color: #5cad0f1a;
}
[data-md-color-scheme="slate"] {
--doc-symbol-attribute-fg-color: #ffa657;
--doc-symbol-function-fg-color: #d2a8ff;
--doc-symbol-method-fg-color: #d2a8ff;
--doc-symbol-class-fg-color: #79c0ff;
--doc-symbol-module-fg-color: #baff79;
--doc-symbol-attribute-bg-color: #ffa6571a;
--doc-symbol-function-bg-color: #d2a8ff1a;
--doc-symbol-method-bg-color: #d2a8ff1a;
--doc-symbol-class-bg-color: #79c0ff1a;
--doc-symbol-module-bg-color: #baff791a;
}
code.doc-symbol {
border-radius: .1rem;
font-size: .85em;
padding: 0 .3em;
font-weight: bold;
}
code.doc-symbol-attribute {
color: var(--doc-symbol-attribute-fg-color);
background-color: var(--doc-symbol-attribute-bg-color);
}
code.doc-symbol-attribute::after {
content: "attr";
}
code.doc-symbol-function {
color: var(--doc-symbol-function-fg-color);
background-color: var(--doc-symbol-function-bg-color);
}
code.doc-symbol-function::after {
content: "func";
}
code.doc-symbol-method {
color: var(--doc-symbol-method-fg-color);
background-color: var(--doc-symbol-method-bg-color);
}
code.doc-symbol-method::after {
content: "meth";
}
code.doc-symbol-class {
color: var(--doc-symbol-class-fg-color);
background-color: var(--doc-symbol-class-bg-color);
}
code.doc-symbol-class::after {
content: "class";
}
code.doc-symbol-module {
color: var(--doc-symbol-module-fg-color);
background-color: var(--doc-symbol-module-bg-color);
}
code.doc-symbol-module::after {
content: "mod";
}
.doc-signature .autorefs {
color: inherit;
border-bottom: 1px dotted currentcolor;
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.8 KiB

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1,18 +0,0 @@
/*!
* Lunr languages, `Danish` language
* https://github.com/MihaiValentin/lunr-languages
*
* Copyright 2014, Mihai Valentin
* http://www.mozilla.org/MPL/
*/
/*!
* based on
* Snowball JavaScript Library v0.3
* http://code.google.com/p/urim/
* http://snowball.tartarus.org/
*
* Copyright 2010, Oleg Mazko
* http://www.mozilla.org/MPL/
*/
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.da=function(){this.pipeline.reset(),this.pipeline.add(e.da.trimmer,e.da.stopWordFilter,e.da.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.da.stemmer))},e.da.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.da.trimmer=e.trimmerSupport.generateTrimmer(e.da.wordCharacters),e.Pipeline.registerFunction(e.da.trimmer,"trimmer-da"),e.da.stemmer=function(){var r=e.stemmerSupport.Among,i=e.stemmerSupport.SnowballProgram,n=new function(){function e(){var e,r=f.cursor+3;if(d=f.limit,0<=r&&r<=f.limit){for(a=r;;){if(e=f.cursor,f.in_grouping(w,97,248)){f.cursor=e;break}if(f.cursor=e,e>=f.limit)return;f.cursor++}for(;!f.out_grouping(w,97,248);){if(f.cursor>=f.limit)return;f.cursor++}d=f.cursor,d<a&&(d=a)}}function n(){var e,r;if(f.cursor>=d&&(r=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,e=f.find_among_b(c,32),f.limit_backward=r,e))switch(f.bra=f.cursor,e){case 1:f.slice_del();break;case 2:f.in_grouping_b(p,97,229)&&f.slice_del()}}function t(){var e,r=f.limit-f.cursor;f.cursor>=d&&(e=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,f.find_among_b(l,4)?(f.bra=f.cursor,f.limit_backward=e,f.cursor=f.limit-r,f.cursor>f.limit_backward&&(f.cursor--,f.bra=f.cursor,f.slice_del())):f.limit_backward=e)}function s(){var e,r,i,n=f.limit-f.cursor;if(f.ket=f.cursor,f.eq_s_b(2,"st")&&(f.bra=f.cursor,f.eq_s_b(2,"ig")&&f.slice_del()),f.cursor=f.limit-n,f.cursor>=d&&(r=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,e=f.find_among_b(m,5),f.limit_backward=r,e))switch(f.bra=f.cursor,e){case 1:f.slice_del(),i=f.limit-f.cursor,t(),f.cursor=f.limit-i;break;case 2:f.slice_from("løs")}}function o(){var e;f.cursor>=d&&(e=f.limit_backward,f.limit_backward=d,f.ket=f.cursor,f.out_grouping_b(w,97,248)?(f.bra=f.cursor,u=f.slice_to(u),f.limit_backward=e,f.eq_v_b(u)&&f.slice_del()):f.limit_backward=e)}var a,d,u,c=[new r("hed",-1,1),new r("ethed",0,1),new r("ered",-1,1),new r("e",-1,1),new r("erede",3,1),new r("ende",3,1),new r("erende",5,1),new r("ene",3,1),new r("erne",3,1),new r("ere",3,1),new r("en",-1,1),new r("heden",10,1),new r("eren",10,1),new r("er",-1,1),new r("heder",13,1),new r("erer",13,1),new r("s",-1,2),new r("heds",16,1),new r("es",16,1),new r("endes",18,1),new r("erendes",19,1),new r("enes",18,1),new r("ernes",18,1),new r("eres",18,1),new r("ens",16,1),new r("hedens",24,1),new r("erens",24,1),new r("ers",16,1),new r("ets",16,1),new r("erets",28,1),new r("et",-1,1),new r("eret",30,1)],l=[new r("gd",-1,-1),new r("dt",-1,-1),new r("gt",-1,-1),new r("kt",-1,-1)],m=[new r("ig",-1,1),new r("lig",0,1),new r("elig",1,1),new r("els",-1,1),new r("løst",-1,2)],w=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,48,0,128],p=[239,254,42,3,0,0,0,0,0,0,0,0,0,0,0,0,16],f=new i;this.setCurrent=function(e){f.setCurrent(e)},this.getCurrent=function(){return f.getCurrent()},this.stem=function(){var r=f.cursor;return e(),f.limit_backward=r,f.cursor=f.limit,n(),f.cursor=f.limit,t(),f.cursor=f.limit,s(),f.cursor=f.limit,o(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return n.setCurrent(e),n.stem(),n.getCurrent()}):(n.setCurrent(e),n.stem(),n.getCurrent())}}(),e.Pipeline.registerFunction(e.da.stemmer,"stemmer-da"),e.da.stopWordFilter=e.generateStopWordFilter("ad af alle alt anden at blev blive bliver da de dem den denne der deres det dette dig din disse dog du efter eller en end er et for fra ham han hans har havde have hende hendes her hos hun hvad hvis hvor i ikke ind jeg jer jo kunne man mange med meget men mig min mine mit mod ned noget nogle nu når og også om op os over på selv sig sin sine sit skal skulle som sådan thi til ud under var vi vil ville vor være været".split(" ")),e.Pipeline.registerFunction(e.da.stopWordFilter,"stopWordFilter-da")}});

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.hi=function(){this.pipeline.reset(),this.pipeline.add(e.hi.trimmer,e.hi.stopWordFilter,e.hi.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.hi.stemmer))},e.hi.wordCharacters="ऀ-ःऄ-एऐ-टठ-यर-िी-ॏॐ-य़ॠ-९॰-ॿa-zA-Za-zA-Z0-90-9",e.hi.trimmer=e.trimmerSupport.generateTrimmer(e.hi.wordCharacters),e.Pipeline.registerFunction(e.hi.trimmer,"trimmer-hi"),e.hi.stopWordFilter=e.generateStopWordFilter("अत अपना अपनी अपने अभी अंदर आदि आप इत्यादि इन इनका इन्हीं इन्हें इन्हों इस इसका इसकी इसके इसमें इसी इसे उन उनका उनकी उनके उनको उन्हीं उन्हें उन्हों उस उसके उसी उसे एक एवं एस ऐसे और कई कर करता करते करना करने करें कहते कहा का काफ़ी कि कितना किन्हें किन्हों किया किर किस किसी किसे की कुछ कुल के को कोई कौन कौनसा गया घर जब जहाँ जा जितना जिन जिन्हें जिन्हों जिस जिसे जीधर जैसा जैसे जो तक तब तरह तिन तिन्हें तिन्हों तिस तिसे तो था थी थे दबारा दिया दुसरा दूसरे दो द्वारा न नके नहीं ना निहायत नीचे ने पर पहले पूरा पे फिर बनी बही बहुत बाद बाला बिलकुल भी भीतर मगर मानो मे में यदि यह यहाँ यही या यिह ये रखें रहा रहे ऱ्वासा लिए लिये लेकिन व वग़ैरह वर्ग वह वहाँ वहीं वाले वुह वे वो सकता सकते सबसे सभी साथ साबुत साभ सारा से सो संग ही हुआ हुई हुए है हैं हो होता होती होते होना होने".split(" ")),e.hi.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.hi.tokenizer=function(i){if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var t=i.toString().toLowerCase().replace(/^\s+/,"");return r.cut(t).split("|")},e.Pipeline.registerFunction(e.hi.stemmer,"stemmer-hi"),e.Pipeline.registerFunction(e.hi.stopWordFilter,"stopWordFilter-hi")}});

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.hy=function(){this.pipeline.reset(),this.pipeline.add(e.hy.trimmer,e.hy.stopWordFilter)},e.hy.wordCharacters="[A-Za-z԰-֏ff-ﭏ]",e.hy.trimmer=e.trimmerSupport.generateTrimmer(e.hy.wordCharacters),e.Pipeline.registerFunction(e.hy.trimmer,"trimmer-hy"),e.hy.stopWordFilter=e.generateStopWordFilter("դու և եք էիր էիք հետո նաև նրանք որը վրա է որ պիտի են այս մեջ ն իր ու ի այդ որոնք այն կամ էր մի ես համար այլ իսկ էին ենք հետ ին թ էինք մենք նրա նա դուք եմ էի ըստ որպես ում".split(" ")),e.Pipeline.registerFunction(e.hy.stopWordFilter,"stopWordFilter-hy"),e.hy.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}(),e.Pipeline.registerFunction(e.hy.stemmer,"stemmer-hy")}});

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var r="2"==e.version[0];e.ja=function(){this.pipeline.reset(),this.pipeline.add(e.ja.trimmer,e.ja.stopWordFilter,e.ja.stemmer),r?this.tokenizer=e.ja.tokenizer:(e.tokenizer&&(e.tokenizer=e.ja.tokenizer),this.tokenizerFn&&(this.tokenizerFn=e.ja.tokenizer))};var t=new e.TinySegmenter;e.ja.tokenizer=function(i){var n,o,s,p,a,u,m,l,c,f;if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(t){return r?new e.Token(t.toLowerCase()):t.toLowerCase()});for(o=i.toString().toLowerCase().replace(/^\s+/,""),n=o.length-1;n>=0;n--)if(/\S/.test(o.charAt(n))){o=o.substring(0,n+1);break}for(a=[],s=o.length,c=0,l=0;c<=s;c++)if(u=o.charAt(c),m=c-l,u.match(/\s/)||c==s){if(m>0)for(p=t.segment(o.slice(l,c)).filter(function(e){return!!e}),f=l,n=0;n<p.length;n++)r?a.push(new e.Token(p[n],{position:[f,p[n].length],index:a.length})):a.push(p[n]),f+=p[n].length;l=c+1}return a},e.ja.stemmer=function(){return function(e){return e}}(),e.Pipeline.registerFunction(e.ja.stemmer,"stemmer-ja"),e.ja.wordCharacters="一二三四五六七八九十百千万億兆一-龠々〆ヵヶぁ-んァ-ヴーア-ン゙a-zA-Za-zA-Z0-90-9",e.ja.trimmer=e.trimmerSupport.generateTrimmer(e.ja.wordCharacters),e.Pipeline.registerFunction(e.ja.trimmer,"trimmer-ja"),e.ja.stopWordFilter=e.generateStopWordFilter("これ それ あれ この その あの ここ そこ あそこ こちら どこ だれ なに なん 何 私 貴方 貴方方 我々 私達 あの人 あのかた 彼女 彼 です あります おります います は が の に を で え から まで より も どの と し それで しかし".split(" ")),e.Pipeline.registerFunction(e.ja.stopWordFilter,"stopWordFilter-ja"),e.jp=e.ja,e.Pipeline.registerFunction(e.jp.stemmer,"stemmer-jp"),e.Pipeline.registerFunction(e.jp.trimmer,"trimmer-jp"),e.Pipeline.registerFunction(e.jp.stopWordFilter,"stopWordFilter-jp")}});

View File

@@ -1 +0,0 @@
module.exports=require("./lunr.ja");

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.kn=function(){this.pipeline.reset(),this.pipeline.add(e.kn.trimmer,e.kn.stopWordFilter,e.kn.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.kn.stemmer))},e.kn.wordCharacters="ಀ-಄ಅ-ಔಕ-ಹಾ-ೌ಼-ಽೕ-ೖೝ-ೞೠ-ೡೢ-ೣ೤೥೦-೯ೱ-ೳ",e.kn.trimmer=e.trimmerSupport.generateTrimmer(e.kn.wordCharacters),e.Pipeline.registerFunction(e.kn.trimmer,"trimmer-kn"),e.kn.stopWordFilter=e.generateStopWordFilter("ಮತ್ತು ಈ ಒಂದು ರಲ್ಲಿ ಹಾಗೂ ಎಂದು ಅಥವಾ ಇದು ರ ಅವರು ಎಂಬ ಮೇಲೆ ಅವರ ತನ್ನ ಆದರೆ ತಮ್ಮ ನಂತರ ಮೂಲಕ ಹೆಚ್ಚು ನ ಆ ಕೆಲವು ಅನೇಕ ಎರಡು ಹಾಗು ಪ್ರಮುಖ ಇದನ್ನು ಇದರ ಸುಮಾರು ಅದರ ಅದು ಮೊದಲ ಬಗ್ಗೆ ನಲ್ಲಿ ರಂದು ಇತರ ಅತ್ಯಂತ ಹೆಚ್ಚಿನ ಸಹ ಸಾಮಾನ್ಯವಾಗಿ ನೇ ಹಲವಾರು ಹೊಸ ದಿ ಕಡಿಮೆ ಯಾವುದೇ ಹೊಂದಿದೆ ದೊಡ್ಡ ಅನ್ನು ಇವರು ಪ್ರಕಾರ ಇದೆ ಮಾತ್ರ ಕೂಡ ಇಲ್ಲಿ ಎಲ್ಲಾ ವಿವಿಧ ಅದನ್ನು ಹಲವು ರಿಂದ ಕೇವಲ ದ ದಕ್ಷಿಣ ಗೆ ಅವನ ಅತಿ ನೆಯ ಬಹಳ ಕೆಲಸ ಎಲ್ಲ ಪ್ರತಿ ಇತ್ಯಾದಿ ಇವು ಬೇರೆ ಹೀಗೆ ನಡುವೆ ಇದಕ್ಕೆ ಎಸ್ ಇವರ ಮೊದಲು ಶ್ರೀ ಮಾಡುವ ಇದರಲ್ಲಿ ರೀತಿಯ ಮಾಡಿದ ಕಾಲ ಅಲ್ಲಿ ಮಾಡಲು ಅದೇ ಈಗ ಅವು ಗಳು ಎ ಎಂಬುದು ಅವನು ಅಂದರೆ ಅವರಿಗೆ ಇರುವ ವಿಶೇಷ ಮುಂದೆ ಅವುಗಳ ಮುಂತಾದ ಮೂಲ ಬಿ ಮೀ ಒಂದೇ ಇನ್ನೂ ಹೆಚ್ಚಾಗಿ ಮಾಡಿ ಅವರನ್ನು ಇದೇ ಯ ರೀತಿಯಲ್ಲಿ ಜೊತೆ ಅದರಲ್ಲಿ ಮಾಡಿದರು ನಡೆದ ಆಗ ಮತ್ತೆ ಪೂರ್ವ ಆತ ಬಂದ ಯಾವ ಒಟ್ಟು ಇತರೆ ಹಿಂದೆ ಪ್ರಮಾಣದ ಗಳನ್ನು ಕುರಿತು ಯು ಆದ್ದರಿಂದ ಅಲ್ಲದೆ ನಗರದ ಮೇಲಿನ ಏಕೆಂದರೆ ರಷ್ಟು ಎಂಬುದನ್ನು ಬಾರಿ ಎಂದರೆ ಹಿಂದಿನ ಆದರೂ ಆದ ಸಂಬಂಧಿಸಿದ ಮತ್ತೊಂದು ಸಿ ಆತನ ".split(" ")),e.kn.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.kn.tokenizer=function(t){if(!arguments.length||null==t||void 0==t)return[];if(Array.isArray(t))return t.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var n=t.toString().toLowerCase().replace(/^\s+/,"");return r.cut(n).split("|")},e.Pipeline.registerFunction(e.kn.stemmer,"stemmer-kn"),e.Pipeline.registerFunction(e.kn.stopWordFilter,"stopWordFilter-kn")}});

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){e.multiLanguage=function(){for(var t=Array.prototype.slice.call(arguments),i=t.join("-"),r="",n=[],s=[],p=0;p<t.length;++p)"en"==t[p]?(r+="\\w",n.unshift(e.stopWordFilter),n.push(e.stemmer),s.push(e.stemmer)):(r+=e[t[p]].wordCharacters,e[t[p]].stopWordFilter&&n.unshift(e[t[p]].stopWordFilter),e[t[p]].stemmer&&(n.push(e[t[p]].stemmer),s.push(e[t[p]].stemmer)));var o=e.trimmerSupport.generateTrimmer(r);return e.Pipeline.registerFunction(o,"lunr-multi-trimmer-"+i),n.unshift(o),function(){this.pipeline.reset(),this.pipeline.add.apply(this.pipeline,n),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add.apply(this.searchPipeline,s))}}}});

File diff suppressed because one or more lines are too long

View File

@@ -1,18 +0,0 @@
/*!
* Lunr languages, `Norwegian` language
* https://github.com/MihaiValentin/lunr-languages
*
* Copyright 2014, Mihai Valentin
* http://www.mozilla.org/MPL/
*/
/*!
* based on
* Snowball JavaScript Library v0.3
* http://code.google.com/p/urim/
* http://snowball.tartarus.org/
*
* Copyright 2010, Oleg Mazko
* http://www.mozilla.org/MPL/
*/
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.no=function(){this.pipeline.reset(),this.pipeline.add(e.no.trimmer,e.no.stopWordFilter,e.no.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.no.stemmer))},e.no.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.no.trimmer=e.trimmerSupport.generateTrimmer(e.no.wordCharacters),e.Pipeline.registerFunction(e.no.trimmer,"trimmer-no"),e.no.stemmer=function(){var r=e.stemmerSupport.Among,n=e.stemmerSupport.SnowballProgram,i=new function(){function e(){var e,r=w.cursor+3;if(a=w.limit,0<=r||r<=w.limit){for(s=r;;){if(e=w.cursor,w.in_grouping(d,97,248)){w.cursor=e;break}if(e>=w.limit)return;w.cursor=e+1}for(;!w.out_grouping(d,97,248);){if(w.cursor>=w.limit)return;w.cursor++}a=w.cursor,a<s&&(a=s)}}function i(){var e,r,n;if(w.cursor>=a&&(r=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,e=w.find_among_b(m,29),w.limit_backward=r,e))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:n=w.limit-w.cursor,w.in_grouping_b(c,98,122)?w.slice_del():(w.cursor=w.limit-n,w.eq_s_b(1,"k")&&w.out_grouping_b(d,97,248)&&w.slice_del());break;case 3:w.slice_from("er")}}function t(){var e,r=w.limit-w.cursor;w.cursor>=a&&(e=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,w.find_among_b(u,2)?(w.bra=w.cursor,w.limit_backward=e,w.cursor=w.limit-r,w.cursor>w.limit_backward&&(w.cursor--,w.bra=w.cursor,w.slice_del())):w.limit_backward=e)}function o(){var e,r;w.cursor>=a&&(r=w.limit_backward,w.limit_backward=a,w.ket=w.cursor,e=w.find_among_b(l,11),e?(w.bra=w.cursor,w.limit_backward=r,1==e&&w.slice_del()):w.limit_backward=r)}var s,a,m=[new r("a",-1,1),new r("e",-1,1),new r("ede",1,1),new r("ande",1,1),new r("ende",1,1),new r("ane",1,1),new r("ene",1,1),new r("hetene",6,1),new r("erte",1,3),new r("en",-1,1),new r("heten",9,1),new r("ar",-1,1),new r("er",-1,1),new r("heter",12,1),new r("s",-1,2),new r("as",14,1),new r("es",14,1),new r("edes",16,1),new r("endes",16,1),new r("enes",16,1),new r("hetenes",19,1),new r("ens",14,1),new r("hetens",21,1),new r("ers",14,1),new r("ets",14,1),new r("et",-1,1),new r("het",25,1),new r("ert",-1,3),new r("ast",-1,1)],u=[new r("dt",-1,-1),new r("vt",-1,-1)],l=[new r("leg",-1,1),new r("eleg",0,1),new r("ig",-1,1),new r("eig",2,1),new r("lig",2,1),new r("elig",4,1),new r("els",-1,1),new r("lov",-1,1),new r("elov",7,1),new r("slov",7,1),new r("hetslov",9,1)],d=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,48,0,128],c=[119,125,149,1],w=new n;this.setCurrent=function(e){w.setCurrent(e)},this.getCurrent=function(){return w.getCurrent()},this.stem=function(){var r=w.cursor;return e(),w.limit_backward=r,w.cursor=w.limit,i(),w.cursor=w.limit,t(),w.cursor=w.limit,o(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return i.setCurrent(e),i.stem(),i.getCurrent()}):(i.setCurrent(e),i.stem(),i.getCurrent())}}(),e.Pipeline.registerFunction(e.no.stemmer,"stemmer-no"),e.no.stopWordFilter=e.generateStopWordFilter("alle at av bare begge ble blei bli blir blitt både båe da de deg dei deim deira deires dem den denne der dere deres det dette di din disse ditt du dykk dykkar då eg ein eit eitt eller elles en enn er et ett etter for fordi fra før ha hadde han hans har hennar henne hennes her hjå ho hoe honom hoss hossen hun hva hvem hver hvilke hvilken hvis hvor hvordan hvorfor i ikke ikkje ikkje ingen ingi inkje inn inni ja jeg kan kom korleis korso kun kunne kva kvar kvarhelst kven kvi kvifor man mange me med medan meg meget mellom men mi min mine mitt mot mykje ned no noe noen noka noko nokon nokor nokre nå når og også om opp oss over på samme seg selv si si sia sidan siden sin sine sitt sjøl skal skulle slik so som som somme somt så sånn til um upp ut uten var vart varte ved vere verte vi vil ville vore vors vort vår være være vært å".split(" ")),e.Pipeline.registerFunction(e.no.stopWordFilter,"stopWordFilter-no")}});

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.sa=function(){this.pipeline.reset(),this.pipeline.add(e.sa.trimmer,e.sa.stopWordFilter,e.sa.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.sa.stemmer))},e.sa.wordCharacters="ऀ-ःऄ-एऐ-टठ-यर-िी-ॏॐ-य़ॠ-९॰-ॿ꣠-꣱ꣲ-ꣷ꣸-ꣻ꣼-ꣽꣾ-ꣿᆰ0-ᆰ9",e.sa.trimmer=e.trimmerSupport.generateTrimmer(e.sa.wordCharacters),e.Pipeline.registerFunction(e.sa.trimmer,"trimmer-sa"),e.sa.stopWordFilter=e.generateStopWordFilter('तथा अयम्‌ एकम्‌ इत्यस्मिन्‌ तथा तत्‌ वा अयम्‌ इत्यस्य ते आहूत उपरि तेषाम्‌ किन्तु तेषाम्‌ तदा इत्यनेन अधिकः इत्यस्य तत्‌ केचन बहवः द्वि तथा महत्वपूर्णः अयम्‌ अस्य विषये अयं अस्ति तत्‌ प्रथमः विषये इत्युपरि इत्युपरि इतर अधिकतमः अधिकः अपि सामान्यतया ठ इतरेतर नूतनम्‌ द न्यूनम्‌ कश्चित्‌ वा विशालः द सः अस्ति तदनुसारम् तत्र अस्ति केवलम्‌ अपि अत्र सर्वे विविधाः तत्‌ बहवः यतः इदानीम्‌ द दक्षिण इत्यस्मै तस्य उपरि नथ अतीव कार्यम्‌ सर्वे एकैकम्‌ इत्यादि। एते सन्ति उत इत्थम्‌ मध्ये एतदर्थं . स कस्य प्रथमः श्री. करोति अस्मिन् प्रकारः निर्मिता कालः तत्र कर्तुं समान अधुना ते सन्ति स एकः अस्ति सः अर्थात् तेषां कृते . स्थितम् विशेषः अग्रिम तेषाम्‌ समान स्रोतः ख म समान इदानीमपि अधिकतया करोतु ते समान इत्यस्य वीथी सह यस्मिन् कृतवान्‌ धृतः तदा पुनः पूर्वं सः आगतः किम्‌ कुल इतर पुरा मात्रा स विषये उ अतएव अपि नगरस्य उपरि यतः प्रतिशतं कतरः कालः साधनानि भूत तथापि जात सम्बन्धि अन्यत्‌ ग अतः अस्माकं स्वकीयाः अस्माकं इदानीं अन्तः इत्यादयः भवन्तः इत्यादयः एते एताः तस्य अस्य इदम् एते तेषां तेषां तेषां तान् तेषां तेषां तेषां समानः सः एकः च तादृशाः बहवः अन्ये च वदन्ति यत् कियत् कस्मै कस्मै यस्मै यस्मै यस्मै यस्मै न अतिनीचः किन्तु प्रथमं सम्पूर्णतया ततः चिरकालानन्तरं पुस्तकं सम्पूर्णतया अन्तः किन्तु अत्र वा इह इव श्रद्धाय अवशिष्यते परन्तु अन्ये वर्गाः सन्ति ते सन्ति शक्नुवन्ति सर्वे मिलित्वा सर्वे एकत्र"'.split(" ")),e.sa.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var r=e.wordcut;r.init(),e.sa.tokenizer=function(t){if(!arguments.length||null==t||void 0==t)return[];if(Array.isArray(t))return t.map(function(r){return isLunr2?new e.Token(r.toLowerCase()):r.toLowerCase()});var i=t.toString().toLowerCase().replace(/^\s+/,"");return r.cut(i).split("|")},e.Pipeline.registerFunction(e.sa.stemmer,"stemmer-sa"),e.Pipeline.registerFunction(e.sa.stopWordFilter,"stopWordFilter-sa")}});

View File

@@ -1 +0,0 @@
!function(r,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(r.lunr)}(this,function(){return function(r){r.stemmerSupport={Among:function(r,t,i,s){if(this.toCharArray=function(r){for(var t=r.length,i=new Array(t),s=0;s<t;s++)i[s]=r.charCodeAt(s);return i},!r&&""!=r||!t&&0!=t||!i)throw"Bad Among initialisation: s:"+r+", substring_i: "+t+", result: "+i;this.s_size=r.length,this.s=this.toCharArray(r),this.substring_i=t,this.result=i,this.method=s},SnowballProgram:function(){var r;return{bra:0,ket:0,limit:0,cursor:0,limit_backward:0,setCurrent:function(t){r=t,this.cursor=0,this.limit=t.length,this.limit_backward=0,this.bra=this.cursor,this.ket=this.limit},getCurrent:function(){var t=r;return r=null,t},in_grouping:function(t,i,s){if(this.cursor<this.limit){var e=r.charCodeAt(this.cursor);if(e<=s&&e>=i&&(e-=i,t[e>>3]&1<<(7&e)))return this.cursor++,!0}return!1},in_grouping_b:function(t,i,s){if(this.cursor>this.limit_backward){var e=r.charCodeAt(this.cursor-1);if(e<=s&&e>=i&&(e-=i,t[e>>3]&1<<(7&e)))return this.cursor--,!0}return!1},out_grouping:function(t,i,s){if(this.cursor<this.limit){var e=r.charCodeAt(this.cursor);if(e>s||e<i)return this.cursor++,!0;if(e-=i,!(t[e>>3]&1<<(7&e)))return this.cursor++,!0}return!1},out_grouping_b:function(t,i,s){if(this.cursor>this.limit_backward){var e=r.charCodeAt(this.cursor-1);if(e>s||e<i)return this.cursor--,!0;if(e-=i,!(t[e>>3]&1<<(7&e)))return this.cursor--,!0}return!1},eq_s:function(t,i){if(this.limit-this.cursor<t)return!1;for(var s=0;s<t;s++)if(r.charCodeAt(this.cursor+s)!=i.charCodeAt(s))return!1;return this.cursor+=t,!0},eq_s_b:function(t,i){if(this.cursor-this.limit_backward<t)return!1;for(var s=0;s<t;s++)if(r.charCodeAt(this.cursor-t+s)!=i.charCodeAt(s))return!1;return this.cursor-=t,!0},find_among:function(t,i){for(var s=0,e=i,n=this.cursor,u=this.limit,o=0,h=0,c=!1;;){for(var a=s+(e-s>>1),f=0,l=o<h?o:h,_=t[a],m=l;m<_.s_size;m++){if(n+l==u){f=-1;break}if(f=r.charCodeAt(n+l)-_.s[m])break;l++}if(f<0?(e=a,h=l):(s=a,o=l),e-s<=1){if(s>0||e==s||c)break;c=!0}}for(;;){var _=t[s];if(o>=_.s_size){if(this.cursor=n+_.s_size,!_.method)return _.result;var b=_.method();if(this.cursor=n+_.s_size,b)return _.result}if((s=_.substring_i)<0)return 0}},find_among_b:function(t,i){for(var s=0,e=i,n=this.cursor,u=this.limit_backward,o=0,h=0,c=!1;;){for(var a=s+(e-s>>1),f=0,l=o<h?o:h,_=t[a],m=_.s_size-1-l;m>=0;m--){if(n-l==u){f=-1;break}if(f=r.charCodeAt(n-1-l)-_.s[m])break;l++}if(f<0?(e=a,h=l):(s=a,o=l),e-s<=1){if(s>0||e==s||c)break;c=!0}}for(;;){var _=t[s];if(o>=_.s_size){if(this.cursor=n-_.s_size,!_.method)return _.result;var b=_.method();if(this.cursor=n-_.s_size,b)return _.result}if((s=_.substring_i)<0)return 0}},replace_s:function(t,i,s){var e=s.length-(i-t),n=r.substring(0,t),u=r.substring(i);return r=n+s+u,this.limit+=e,this.cursor>=i?this.cursor+=e:this.cursor>t&&(this.cursor=t),e},slice_check:function(){if(this.bra<0||this.bra>this.ket||this.ket>this.limit||this.limit>r.length)throw"faulty slice operation"},slice_from:function(r){this.slice_check(),this.replace_s(this.bra,this.ket,r)},slice_del:function(){this.slice_from("")},insert:function(r,t,i){var s=this.replace_s(r,t,i);r<=this.bra&&(this.bra+=s),r<=this.ket&&(this.ket+=s)},slice_to:function(){return this.slice_check(),r.substring(this.bra,this.ket)},eq_v_b:function(r){return this.eq_s_b(r.length,r)}}}},r.trimmerSupport={generateTrimmer:function(r){var t=new RegExp("^[^"+r+"]+"),i=new RegExp("[^"+r+"]+$");return function(r){return"function"==typeof r.update?r.update(function(r){return r.replace(t,"").replace(i,"")}):r.replace(t,"").replace(i,"")}}}}});

View File

@@ -1,18 +0,0 @@
/*!
* Lunr languages, `Swedish` language
* https://github.com/MihaiValentin/lunr-languages
*
* Copyright 2014, Mihai Valentin
* http://www.mozilla.org/MPL/
*/
/*!
* based on
* Snowball JavaScript Library v0.3
* http://code.google.com/p/urim/
* http://snowball.tartarus.org/
*
* Copyright 2010, Oleg Mazko
* http://www.mozilla.org/MPL/
*/
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.sv=function(){this.pipeline.reset(),this.pipeline.add(e.sv.trimmer,e.sv.stopWordFilter,e.sv.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.sv.stemmer))},e.sv.wordCharacters="A-Za-zªºÀ-ÖØ-öø-ʸˠ-ˤᴀ-ᴥᴬ-ᵜᵢ-ᵥᵫ-ᵷᵹ-ᶾḀ-ỿⁱⁿₐ-ₜKÅℲⅎⅠ-ↈⱠ-ⱿꜢ-ꞇꞋ-ꞭꞰ-ꞷꟷ-ꟿꬰ-ꭚꭜ-ꭤff-stA-Za-z",e.sv.trimmer=e.trimmerSupport.generateTrimmer(e.sv.wordCharacters),e.Pipeline.registerFunction(e.sv.trimmer,"trimmer-sv"),e.sv.stemmer=function(){var r=e.stemmerSupport.Among,n=e.stemmerSupport.SnowballProgram,t=new function(){function e(){var e,r=w.cursor+3;if(o=w.limit,0<=r||r<=w.limit){for(a=r;;){if(e=w.cursor,w.in_grouping(l,97,246)){w.cursor=e;break}if(w.cursor=e,w.cursor>=w.limit)return;w.cursor++}for(;!w.out_grouping(l,97,246);){if(w.cursor>=w.limit)return;w.cursor++}o=w.cursor,o<a&&(o=a)}}function t(){var e,r=w.limit_backward;if(w.cursor>=o&&(w.limit_backward=o,w.cursor=w.limit,w.ket=w.cursor,e=w.find_among_b(u,37),w.limit_backward=r,e))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:w.in_grouping_b(d,98,121)&&w.slice_del()}}function i(){var e=w.limit_backward;w.cursor>=o&&(w.limit_backward=o,w.cursor=w.limit,w.find_among_b(c,7)&&(w.cursor=w.limit,w.ket=w.cursor,w.cursor>w.limit_backward&&(w.bra=--w.cursor,w.slice_del())),w.limit_backward=e)}function s(){var e,r;if(w.cursor>=o){if(r=w.limit_backward,w.limit_backward=o,w.cursor=w.limit,w.ket=w.cursor,e=w.find_among_b(m,5))switch(w.bra=w.cursor,e){case 1:w.slice_del();break;case 2:w.slice_from("lös");break;case 3:w.slice_from("full")}w.limit_backward=r}}var a,o,u=[new r("a",-1,1),new r("arna",0,1),new r("erna",0,1),new r("heterna",2,1),new r("orna",0,1),new r("ad",-1,1),new r("e",-1,1),new r("ade",6,1),new r("ande",6,1),new r("arne",6,1),new r("are",6,1),new r("aste",6,1),new r("en",-1,1),new r("anden",12,1),new r("aren",12,1),new r("heten",12,1),new r("ern",-1,1),new r("ar",-1,1),new r("er",-1,1),new r("heter",18,1),new r("or",-1,1),new r("s",-1,2),new r("as",21,1),new r("arnas",22,1),new r("ernas",22,1),new r("ornas",22,1),new r("es",21,1),new r("ades",26,1),new r("andes",26,1),new r("ens",21,1),new r("arens",29,1),new r("hetens",29,1),new r("erns",21,1),new r("at",-1,1),new r("andet",-1,1),new r("het",-1,1),new r("ast",-1,1)],c=[new r("dd",-1,-1),new r("gd",-1,-1),new r("nn",-1,-1),new r("dt",-1,-1),new r("gt",-1,-1),new r("kt",-1,-1),new r("tt",-1,-1)],m=[new r("ig",-1,1),new r("lig",0,1),new r("els",-1,1),new r("fullt",-1,3),new r("löst",-1,2)],l=[17,65,16,1,0,0,0,0,0,0,0,0,0,0,0,0,24,0,32],d=[119,127,149],w=new n;this.setCurrent=function(e){w.setCurrent(e)},this.getCurrent=function(){return w.getCurrent()},this.stem=function(){var r=w.cursor;return e(),w.limit_backward=r,w.cursor=w.limit,t(),w.cursor=w.limit,i(),w.cursor=w.limit,s(),!0}};return function(e){return"function"==typeof e.update?e.update(function(e){return t.setCurrent(e),t.stem(),t.getCurrent()}):(t.setCurrent(e),t.stem(),t.getCurrent())}}(),e.Pipeline.registerFunction(e.sv.stemmer,"stemmer-sv"),e.sv.stopWordFilter=e.generateStopWordFilter("alla allt att av blev bli blir blivit de dem den denna deras dess dessa det detta dig din dina ditt du där då efter ej eller en er era ert ett från för ha hade han hans har henne hennes hon honom hur här i icke ingen inom inte jag ju kan kunde man med mellan men mig min mina mitt mot mycket ni nu när någon något några och om oss på samma sedan sig sin sina sitta själv skulle som så sådan sådana sådant till under upp ut utan vad var vara varför varit varje vars vart vem vi vid vilka vilkas vilken vilket vår våra vårt än är åt över".split(" ")),e.Pipeline.registerFunction(e.sv.stopWordFilter,"stopWordFilter-sv")}});

View File

@@ -1 +0,0 @@
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.ta=function(){this.pipeline.reset(),this.pipeline.add(e.ta.trimmer,e.ta.stopWordFilter,e.ta.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.ta.stemmer))},e.ta.wordCharacters="஀-உஊ-ஏஐ-ஙச-ட஠-னப-யர-ஹ஺-ிீ-௉ொ-௏ௐ-௙௚-௟௠-௩௪-௯௰-௹௺-௿a-zA-Za-zA-Z0-90-9",e.ta.trimmer=e.trimmerSupport.generateTrimmer(e.ta.wordCharacters),e.Pipeline.registerFunction(e.ta.trimmer,"trimmer-ta"),e.ta.stopWordFilter=e.generateStopWordFilter("அங்கு அங்கே அது அதை அந்த அவர் அவர்கள் அவள் அவன் அவை ஆக ஆகவே ஆகையால் ஆதலால் ஆதலினால் ஆனாலும் ஆனால் இங்கு இங்கே இது இதை இந்த இப்படி இவர் இவர்கள் இவள் இவன் இவை இவ்வளவு உனக்கு உனது உன் உன்னால் எங்கு எங்கே எது எதை எந்த எப்படி எவர் எவர்கள் எவள் எவன் எவை எவ்வளவு எனக்கு எனது எனவே என் என்ன என்னால் ஏது ஏன் தனது தன்னால் தானே தான் நாங்கள் நாம் நான் நீ நீங்கள்".split(" ")),e.ta.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var t=e.wordcut;t.init(),e.ta.tokenizer=function(r){if(!arguments.length||null==r||void 0==r)return[];if(Array.isArray(r))return r.map(function(t){return isLunr2?new e.Token(t.toLowerCase()):t.toLowerCase()});var i=r.toString().toLowerCase().replace(/^\s+/,"");return t.cut(i).split("|")},e.Pipeline.registerFunction(e.ta.stemmer,"stemmer-ta"),e.Pipeline.registerFunction(e.ta.stopWordFilter,"stopWordFilter-ta")}});

View File

@@ -1 +0,0 @@
!function(e,t){"function"==typeof define&&define.amd?define(t):"object"==typeof exports?module.exports=t():t()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.te=function(){this.pipeline.reset(),this.pipeline.add(e.te.trimmer,e.te.stopWordFilter,e.te.stemmer),this.searchPipeline&&(this.searchPipeline.reset(),this.searchPipeline.add(e.te.stemmer))},e.te.wordCharacters="ఀ-ఄఅ-ఔక-హా-ౌౕ-ౖౘ-ౚౠ-ౡౢ-ౣ౦-౯౸-౿఼ఽ్ౝ౷౤౥",e.te.trimmer=e.trimmerSupport.generateTrimmer(e.te.wordCharacters),e.Pipeline.registerFunction(e.te.trimmer,"trimmer-te"),e.te.stopWordFilter=e.generateStopWordFilter("అందరూ అందుబాటులో అడగండి అడగడం అడ్డంగా అనుగుణంగా అనుమతించు అనుమతిస్తుంది అయితే ఇప్పటికే ఉన్నారు ఎక్కడైనా ఎప్పుడు ఎవరైనా ఎవరో ఏ ఏదైనా ఏమైనప్పటికి ఒక ఒకరు కనిపిస్తాయి కాదు కూడా గా గురించి చుట్టూ చేయగలిగింది తగిన తర్వాత దాదాపు దూరంగా నిజంగా పై ప్రకారం ప్రక్కన మధ్య మరియు మరొక మళ్ళీ మాత్రమే మెచ్చుకో వద్ద వెంట వేరుగా వ్యతిరేకంగా సంబంధం".split(" ")),e.te.stemmer=function(){return function(e){return"function"==typeof e.update?e.update(function(e){return e}):e}}();var t=e.wordcut;t.init(),e.te.tokenizer=function(r){if(!arguments.length||null==r||void 0==r)return[];if(Array.isArray(r))return r.map(function(t){return isLunr2?new e.Token(t.toLowerCase()):t.toLowerCase()});var i=r.toString().toLowerCase().replace(/^\s+/,"");return t.cut(i).split("|")},e.Pipeline.registerFunction(e.te.stemmer,"stemmer-te"),e.Pipeline.registerFunction(e.te.stopWordFilter,"stopWordFilter-te")}});

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var r="2"==e.version[0];e.th=function(){this.pipeline.reset(),this.pipeline.add(e.th.trimmer),r?this.tokenizer=e.th.tokenizer:(e.tokenizer&&(e.tokenizer=e.th.tokenizer),this.tokenizerFn&&(this.tokenizerFn=e.th.tokenizer))},e.th.wordCharacters="[฀-๿]",e.th.trimmer=e.trimmerSupport.generateTrimmer(e.th.wordCharacters),e.Pipeline.registerFunction(e.th.trimmer,"trimmer-th");var t=e.wordcut;t.init(),e.th.tokenizer=function(i){if(!arguments.length||null==i||void 0==i)return[];if(Array.isArray(i))return i.map(function(t){return r?new e.Token(t):t});var n=i.toString().replace(/^\s+/,"");return t.cut(n).split("|")}}});

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r():r()(e.lunr)}(this,function(){return function(e){if(void 0===e)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===e.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");e.vi=function(){this.pipeline.reset(),this.pipeline.add(e.vi.stopWordFilter,e.vi.trimmer)},e.vi.wordCharacters="[A-Za-ẓ̀͐́͑̉̃̓ÂâÊêÔôĂ-ăĐ-đƠ-ơƯ-ư]",e.vi.trimmer=e.trimmerSupport.generateTrimmer(e.vi.wordCharacters),e.Pipeline.registerFunction(e.vi.trimmer,"trimmer-vi"),e.vi.stopWordFilter=e.generateStopWordFilter("là cái nhưng mà".split(" "))}});

View File

@@ -1 +0,0 @@
!function(e,r){"function"==typeof define&&define.amd?define(r):"object"==typeof exports?module.exports=r(require("@node-rs/jieba")):r()(e.lunr)}(this,function(e){return function(r,t){if(void 0===r)throw new Error("Lunr is not present. Please include / require Lunr before this script.");if(void 0===r.stemmerSupport)throw new Error("Lunr stemmer support is not present. Please include / require Lunr stemmer support before this script.");var i="2"==r.version[0];r.zh=function(){this.pipeline.reset(),this.pipeline.add(r.zh.trimmer,r.zh.stopWordFilter,r.zh.stemmer),i?this.tokenizer=r.zh.tokenizer:(r.tokenizer&&(r.tokenizer=r.zh.tokenizer),this.tokenizerFn&&(this.tokenizerFn=r.zh.tokenizer))},r.zh.tokenizer=function(n){if(!arguments.length||null==n||void 0==n)return[];if(Array.isArray(n))return n.map(function(e){return i?new r.Token(e.toLowerCase()):e.toLowerCase()});t&&e.load(t);var o=n.toString().trim().toLowerCase(),s=[];e.cut(o,!0).forEach(function(e){s=s.concat(e.split(" "))}),s=s.filter(function(e){return!!e});var u=0;return s.map(function(e,t){if(i){var n=o.indexOf(e,u),s={};return s.position=[n,e.length],s.index=t,u=n,new r.Token(e,s)}return e})},r.zh.wordCharacters="\\w一-龥",r.zh.trimmer=r.trimmerSupport.generateTrimmer(r.zh.wordCharacters),r.Pipeline.registerFunction(r.zh.trimmer,"trimmer-zh"),r.zh.stemmer=function(){return function(e){return e}}(),r.Pipeline.registerFunction(r.zh.stemmer,"stemmer-zh"),r.zh.stopWordFilter=r.generateStopWordFilter("的 一 不 在 人 有 是 为 為 以 于 於 上 他 而 后 後 之 来 來 及 了 因 下 可 到 由 这 這 与 與 也 此 但 并 並 个 個 其 已 无 無 小 我 们 們 起 最 再 今 去 好 只 又 或 很 亦 某 把 那 你 乃 它 吧 被 比 别 趁 当 當 从 從 得 打 凡 儿 兒 尔 爾 该 該 各 给 給 跟 和 何 还 還 即 几 幾 既 看 据 據 距 靠 啦 另 么 麽 每 嘛 拿 哪 您 凭 憑 且 却 卻 让 讓 仍 啥 如 若 使 谁 誰 虽 雖 随 隨 同 所 她 哇 嗡 往 些 向 沿 哟 喲 用 咱 则 則 怎 曾 至 致 着 著 诸 諸 自".split(" ")),r.Pipeline.registerFunction(r.zh.stopWordFilter,"stopWordFilter-zh")}});

View File

@@ -1,206 +0,0 @@
/**
* export the module via AMD, CommonJS or as a browser global
* Export code from https://github.com/umdjs/umd/blob/master/returnExports.js
*/
;(function (root, factory) {
if (typeof define === 'function' && define.amd) {
// AMD. Register as an anonymous module.
define(factory)
} else if (typeof exports === 'object') {
/**
* Node. Does not work with strict CommonJS, but
* only CommonJS-like environments that support module.exports,
* like Node.
*/
module.exports = factory()
} else {
// Browser globals (root is window)
factory()(root.lunr);
}
}(this, function () {
/**
* Just return a value to define the module export.
* This example returns an object, but the module
* can return a function as the exported value.
*/
return function(lunr) {
// TinySegmenter 0.1 -- Super compact Japanese tokenizer in Javascript
// (c) 2008 Taku Kudo <taku@chasen.org>
// TinySegmenter is freely distributable under the terms of a new BSD licence.
// For details, see http://chasen.org/~taku/software/TinySegmenter/LICENCE.txt
function TinySegmenter() {
var patterns = {
"[一二三四五六七八九十百千万億兆]":"M",
"[一-龠々〆ヵヶ]":"H",
"[ぁ-ん]":"I",
"[ァ-ヴーア-ン゙ー]":"K",
"[a-zA-Za-zA-Z]":"A",
"[0-90-9]":"N"
}
this.chartype_ = [];
for (var i in patterns) {
var regexp = new RegExp(i);
this.chartype_.push([regexp, patterns[i]]);
}
this.BIAS__ = -332
this.BC1__ = {"HH":6,"II":2461,"KH":406,"OH":-1378};
this.BC2__ = {"AA":-3267,"AI":2744,"AN":-878,"HH":-4070,"HM":-1711,"HN":4012,"HO":3761,"IA":1327,"IH":-1184,"II":-1332,"IK":1721,"IO":5492,"KI":3831,"KK":-8741,"MH":-3132,"MK":3334,"OO":-2920};
this.BC3__ = {"HH":996,"HI":626,"HK":-721,"HN":-1307,"HO":-836,"IH":-301,"KK":2762,"MK":1079,"MM":4034,"OA":-1652,"OH":266};
this.BP1__ = {"BB":295,"OB":304,"OO":-125,"UB":352};
this.BP2__ = {"BO":60,"OO":-1762};
this.BQ1__ = {"BHH":1150,"BHM":1521,"BII":-1158,"BIM":886,"BMH":1208,"BNH":449,"BOH":-91,"BOO":-2597,"OHI":451,"OIH":-296,"OKA":1851,"OKH":-1020,"OKK":904,"OOO":2965};
this.BQ2__ = {"BHH":118,"BHI":-1159,"BHM":466,"BIH":-919,"BKK":-1720,"BKO":864,"OHH":-1139,"OHM":-181,"OIH":153,"UHI":-1146};
this.BQ3__ = {"BHH":-792,"BHI":2664,"BII":-299,"BKI":419,"BMH":937,"BMM":8335,"BNN":998,"BOH":775,"OHH":2174,"OHM":439,"OII":280,"OKH":1798,"OKI":-793,"OKO":-2242,"OMH":-2402,"OOO":11699};
this.BQ4__ = {"BHH":-3895,"BIH":3761,"BII":-4654,"BIK":1348,"BKK":-1806,"BMI":-3385,"BOO":-12396,"OAH":926,"OHH":266,"OHK":-2036,"ONN":-973};
this.BW1__ = {",と":660,",同":727,"B1あ":1404,"B1同":542,"、と":660,"、同":727,"」と":1682,"あっ":1505,"いう":1743,"いっ":-2055,"いる":672,"うし":-4817,"うん":665,"から":3472,"がら":600,"こう":-790,"こと":2083,"こん":-1262,"さら":-4143,"さん":4573,"した":2641,"して":1104,"すで":-3399,"そこ":1977,"それ":-871,"たち":1122,"ため":601,"った":3463,"つい":-802,"てい":805,"てき":1249,"でき":1127,"です":3445,"では":844,"とい":-4915,"とみ":1922,"どこ":3887,"ない":5713,"なっ":3015,"など":7379,"なん":-1113,"にし":2468,"には":1498,"にも":1671,"に対":-912,"の一":-501,"の中":741,"ませ":2448,"まで":1711,"まま":2600,"まる":-2155,"やむ":-1947,"よっ":-2565,"れた":2369,"れで":-913,"をし":1860,"を見":731,"亡く":-1886,"京都":2558,"取り":-2784,"大き":-2604,"大阪":1497,"平方":-2314,"引き":-1336,"日本":-195,"本当":-2423,"毎日":-2113,"目指":-724,"B1あ":1404,"B1同":542,"」と":1682};
this.BW2__ = {"..":-11822,"11":-669,"――":-5730,"−−":-13175,"いう":-1609,"うか":2490,"かし":-1350,"かも":-602,"から":-7194,"かれ":4612,"がい":853,"がら":-3198,"きた":1941,"くな":-1597,"こと":-8392,"この":-4193,"させ":4533,"され":13168,"さん":-3977,"しい":-1819,"しか":-545,"した":5078,"して":972,"しな":939,"その":-3744,"たい":-1253,"たた":-662,"ただ":-3857,"たち":-786,"たと":1224,"たは":-939,"った":4589,"って":1647,"っと":-2094,"てい":6144,"てき":3640,"てく":2551,"ては":-3110,"ても":-3065,"でい":2666,"でき":-1528,"でし":-3828,"です":-4761,"でも":-4203,"とい":1890,"とこ":-1746,"とと":-2279,"との":720,"とみ":5168,"とも":-3941,"ない":-2488,"なが":-1313,"など":-6509,"なの":2614,"なん":3099,"にお":-1615,"にし":2748,"にな":2454,"によ":-7236,"に対":-14943,"に従":-4688,"に関":-11388,"のか":2093,"ので":-7059,"のに":-6041,"のの":-6125,"はい":1073,"はが":-1033,"はず":-2532,"ばれ":1813,"まし":-1316,"まで":-6621,"まれ":5409,"めて":-3153,"もい":2230,"もの":-10713,"らか":-944,"らし":-1611,"らに":-1897,"りし":651,"りま":1620,"れた":4270,"れて":849,"れば":4114,"ろう":6067,"われ":7901,"を通":-11877,"んだ":728,"んな":-4115,"一人":602,"一方":-1375,"一日":970,"一部":-1051,"上が":-4479,"会社":-1116,"出て":2163,"分の":-7758,"同党":970,"同日":-913,"大阪":-2471,"委員":-1250,"少な":-1050,"年度":-8669,"年間":-1626,"府県":-2363,"手権":-1982,"新聞":-4066,"日新":-722,"日本":-7068,"日米":3372,"曜日":-601,"朝鮮":-2355,"本人":-2697,"東京":-1543,"然と":-1384,"社会":-1276,"立て":-990,"第に":-1612,"米国":-4268,"11":-669};
this.BW3__ = {"あた":-2194,"あり":719,"ある":3846,"い.":-1185,"い。":-1185,"いい":5308,"いえ":2079,"いく":3029,"いた":2056,"いっ":1883,"いる":5600,"いわ":1527,"うち":1117,"うと":4798,"えと":1454,"か.":2857,"か。":2857,"かけ":-743,"かっ":-4098,"かに":-669,"から":6520,"かり":-2670,"が,":1816,"が、":1816,"がき":-4855,"がけ":-1127,"がっ":-913,"がら":-4977,"がり":-2064,"きた":1645,"けど":1374,"こと":7397,"この":1542,"ころ":-2757,"さい":-714,"さを":976,"し,":1557,"し、":1557,"しい":-3714,"した":3562,"して":1449,"しな":2608,"しま":1200,"す.":-1310,"す。":-1310,"する":6521,"ず,":3426,"ず、":3426,"ずに":841,"そう":428,"た.":8875,"た。":8875,"たい":-594,"たの":812,"たり":-1183,"たる":-853,"だ.":4098,"だ。":4098,"だっ":1004,"った":-4748,"って":300,"てい":6240,"てお":855,"ても":302,"です":1437,"でに":-1482,"では":2295,"とう":-1387,"とし":2266,"との":541,"とも":-3543,"どう":4664,"ない":1796,"なく":-903,"など":2135,"に,":-1021,"に、":-1021,"にし":1771,"にな":1906,"には":2644,"の,":-724,"の、":-724,"の子":-1000,"は,":1337,"は、":1337,"べき":2181,"まし":1113,"ます":6943,"まっ":-1549,"まで":6154,"まれ":-793,"らし":1479,"られ":6820,"るる":3818,"れ,":854,"れ、":854,"れた":1850,"れて":1375,"れば":-3246,"れる":1091,"われ":-605,"んだ":606,"んで":798,"カ月":990,"会議":860,"入り":1232,"大会":2217,"始め":1681,"市":965,"新聞":-5055,"日,":974,"日、":974,"社会":2024,"カ月":990};
this.TC1__ = {"AAA":1093,"HHH":1029,"HHM":580,"HII":998,"HOH":-390,"HOM":-331,"IHI":1169,"IOH":-142,"IOI":-1015,"IOM":467,"MMH":187,"OOI":-1832};
this.TC2__ = {"HHO":2088,"HII":-1023,"HMM":-1154,"IHI":-1965,"KKH":703,"OII":-2649};
this.TC3__ = {"AAA":-294,"HHH":346,"HHI":-341,"HII":-1088,"HIK":731,"HOH":-1486,"IHH":128,"IHI":-3041,"IHO":-1935,"IIH":-825,"IIM":-1035,"IOI":-542,"KHH":-1216,"KKA":491,"KKH":-1217,"KOK":-1009,"MHH":-2694,"MHM":-457,"MHO":123,"MMH":-471,"NNH":-1689,"NNO":662,"OHO":-3393};
this.TC4__ = {"HHH":-203,"HHI":1344,"HHK":365,"HHM":-122,"HHN":182,"HHO":669,"HIH":804,"HII":679,"HOH":446,"IHH":695,"IHO":-2324,"IIH":321,"III":1497,"IIO":656,"IOO":54,"KAK":4845,"KKA":3386,"KKK":3065,"MHH":-405,"MHI":201,"MMH":-241,"MMM":661,"MOM":841};
this.TQ1__ = {"BHHH":-227,"BHHI":316,"BHIH":-132,"BIHH":60,"BIII":1595,"BNHH":-744,"BOHH":225,"BOOO":-908,"OAKK":482,"OHHH":281,"OHIH":249,"OIHI":200,"OIIH":-68};
this.TQ2__ = {"BIHH":-1401,"BIII":-1033,"BKAK":-543,"BOOO":-5591};
this.TQ3__ = {"BHHH":478,"BHHM":-1073,"BHIH":222,"BHII":-504,"BIIH":-116,"BIII":-105,"BMHI":-863,"BMHM":-464,"BOMH":620,"OHHH":346,"OHHI":1729,"OHII":997,"OHMH":481,"OIHH":623,"OIIH":1344,"OKAK":2792,"OKHH":587,"OKKA":679,"OOHH":110,"OOII":-685};
this.TQ4__ = {"BHHH":-721,"BHHM":-3604,"BHII":-966,"BIIH":-607,"BIII":-2181,"OAAA":-2763,"OAKK":180,"OHHH":-294,"OHHI":2446,"OHHO":480,"OHIH":-1573,"OIHH":1935,"OIHI":-493,"OIIH":626,"OIII":-4007,"OKAK":-8156};
this.TW1__ = {"につい":-4681,"東京都":2026};
this.TW2__ = {"ある程":-2049,"いった":-1256,"ころが":-2434,"しょう":3873,"その後":-4430,"だって":-1049,"ていた":1833,"として":-4657,"ともに":-4517,"もので":1882,"一気に":-792,"初めて":-1512,"同時に":-8097,"大きな":-1255,"対して":-2721,"社会党":-3216};
this.TW3__ = {"いただ":-1734,"してい":1314,"として":-4314,"につい":-5483,"にとっ":-5989,"に当た":-6247,"ので,":-727,"ので、":-727,"のもの":-600,"れから":-3752,"十二月":-2287};
this.TW4__ = {"いう.":8576,"いう。":8576,"からな":-2348,"してい":2958,"たが,":1516,"たが、":1516,"ている":1538,"という":1349,"ました":5543,"ません":1097,"ようと":-4258,"よると":5865};
this.UC1__ = {"A":484,"K":93,"M":645,"O":-505};
this.UC2__ = {"A":819,"H":1059,"I":409,"M":3987,"N":5775,"O":646};
this.UC3__ = {"A":-1370,"I":2311};
this.UC4__ = {"A":-2643,"H":1809,"I":-1032,"K":-3450,"M":3565,"N":3876,"O":6646};
this.UC5__ = {"H":313,"I":-1238,"K":-799,"M":539,"O":-831};
this.UC6__ = {"H":-506,"I":-253,"K":87,"M":247,"O":-387};
this.UP1__ = {"O":-214};
this.UP2__ = {"B":69,"O":935};
this.UP3__ = {"B":189};
this.UQ1__ = {"BH":21,"BI":-12,"BK":-99,"BN":142,"BO":-56,"OH":-95,"OI":477,"OK":410,"OO":-2422};
this.UQ2__ = {"BH":216,"BI":113,"OK":1759};
this.UQ3__ = {"BA":-479,"BH":42,"BI":1913,"BK":-7198,"BM":3160,"BN":6427,"BO":14761,"OI":-827,"ON":-3212};
this.UW1__ = {",":156,"、":156,"「":-463,"あ":-941,"う":-127,"が":-553,"き":121,"こ":505,"で":-201,"と":-547,"ど":-123,"に":-789,"の":-185,"は":-847,"も":-466,"や":-470,"よ":182,"ら":-292,"り":208,"れ":169,"を":-446,"ん":-137,"・":-135,"主":-402,"京":-268,"区":-912,"午":871,"国":-460,"大":561,"委":729,"市":-411,"日":-141,"理":361,"生":-408,"県":-386,"都":-718,"「":-463,"・":-135};
this.UW2__ = {",":-829,"、":-829,"〇":892,"「":-645,"」":3145,"あ":-538,"い":505,"う":134,"お":-502,"か":1454,"が":-856,"く":-412,"こ":1141,"さ":878,"ざ":540,"し":1529,"す":-675,"せ":300,"そ":-1011,"た":188,"だ":1837,"つ":-949,"て":-291,"で":-268,"と":-981,"ど":1273,"な":1063,"に":-1764,"の":130,"は":-409,"ひ":-1273,"べ":1261,"ま":600,"も":-1263,"や":-402,"よ":1639,"り":-579,"る":-694,"れ":571,"を":-2516,"ん":2095,"ア":-587,"カ":306,"キ":568,"ッ":831,"三":-758,"不":-2150,"世":-302,"中":-968,"主":-861,"事":492,"人":-123,"会":978,"保":362,"入":548,"初":-3025,"副":-1566,"北":-3414,"区":-422,"大":-1769,"天":-865,"太":-483,"子":-1519,"学":760,"実":1023,"小":-2009,"市":-813,"年":-1060,"強":1067,"手":-1519,"揺":-1033,"政":1522,"文":-1355,"新":-1682,"日":-1815,"明":-1462,"最":-630,"朝":-1843,"本":-1650,"東":-931,"果":-665,"次":-2378,"民":-180,"気":-1740,"理":752,"発":529,"目":-1584,"相":-242,"県":-1165,"立":-763,"第":810,"米":509,"自":-1353,"行":838,"西":-744,"見":-3874,"調":1010,"議":1198,"込":3041,"開":1758,"間":-1257,"「":-645,"」":3145,"ッ":831,"ア":-587,"カ":306,"キ":568};
this.UW3__ = {",":4889,"1":-800,"−":-1723,"、":4889,"々":-2311,"〇":5827,"」":2670,"〓":-3573,"あ":-2696,"い":1006,"う":2342,"え":1983,"お":-4864,"か":-1163,"が":3271,"く":1004,"け":388,"げ":401,"こ":-3552,"ご":-3116,"さ":-1058,"し":-395,"す":584,"せ":3685,"そ":-5228,"た":842,"ち":-521,"っ":-1444,"つ":-1081,"て":6167,"で":2318,"と":1691,"ど":-899,"な":-2788,"に":2745,"の":4056,"は":4555,"ひ":-2171,"ふ":-1798,"へ":1199,"ほ":-5516,"ま":-4384,"み":-120,"め":1205,"も":2323,"や":-788,"よ":-202,"ら":727,"り":649,"る":5905,"れ":2773,"わ":-1207,"を":6620,"ん":-518,"ア":551,"グ":1319,"ス":874,"ッ":-1350,"ト":521,"ム":1109,"ル":1591,"ロ":2201,"ン":278,"・":-3794,"一":-1619,"下":-1759,"世":-2087,"両":3815,"中":653,"主":-758,"予":-1193,"二":974,"人":2742,"今":792,"他":1889,"以":-1368,"低":811,"何":4265,"作":-361,"保":-2439,"元":4858,"党":3593,"全":1574,"公":-3030,"六":755,"共":-1880,"円":5807,"再":3095,"分":457,"初":2475,"別":1129,"前":2286,"副":4437,"力":365,"動":-949,"務":-1872,"化":1327,"北":-1038,"区":4646,"千":-2309,"午":-783,"協":-1006,"口":483,"右":1233,"各":3588,"合":-241,"同":3906,"和":-837,"員":4513,"国":642,"型":1389,"場":1219,"外":-241,"妻":2016,"学":-1356,"安":-423,"実":-1008,"家":1078,"小":-513,"少":-3102,"州":1155,"市":3197,"平":-1804,"年":2416,"広":-1030,"府":1605,"度":1452,"建":-2352,"当":-3885,"得":1905,"思":-1291,"性":1822,"戸":-488,"指":-3973,"政":-2013,"教":-1479,"数":3222,"文":-1489,"新":1764,"日":2099,"旧":5792,"昨":-661,"時":-1248,"曜":-951,"最":-937,"月":4125,"期":360,"李":3094,"村":364,"東":-805,"核":5156,"森":2438,"業":484,"氏":2613,"民":-1694,"決":-1073,"法":1868,"海":-495,"無":979,"物":461,"特":-3850,"生":-273,"用":914,"町":1215,"的":7313,"直":-1835,"省":792,"県":6293,"知":-1528,"私":4231,"税":401,"立":-960,"第":1201,"米":7767,"系":3066,"約":3663,"級":1384,"統":-4229,"総":1163,"線":1255,"者":6457,"能":725,"自":-2869,"英":785,"見":1044,"調":-562,"財":-733,"費":1777,"車":1835,"軍":1375,"込":-1504,"通":-1136,"選":-681,"郎":1026,"郡":4404,"部":1200,"金":2163,"長":421,"開":-1432,"間":1302,"関":-1282,"雨":2009,"電":-1045,"非":2066,"駅":1620,"1":-800,"」":2670,"・":-3794,"ッ":-1350,"ア":551,"グ":1319,"ス":874,"ト":521,"ム":1109,"ル":1591,"ロ":2201,"ン":278};
this.UW4__ = {",":3930,".":3508,"―":-4841,"、":3930,"。":3508,"〇":4999,"「":1895,"」":3798,"〓":-5156,"あ":4752,"い":-3435,"う":-640,"え":-2514,"お":2405,"か":530,"が":6006,"き":-4482,"ぎ":-3821,"く":-3788,"け":-4376,"げ":-4734,"こ":2255,"ご":1979,"さ":2864,"し":-843,"じ":-2506,"す":-731,"ず":1251,"せ":181,"そ":4091,"た":5034,"だ":5408,"ち":-3654,"っ":-5882,"つ":-1659,"て":3994,"で":7410,"と":4547,"な":5433,"に":6499,"ぬ":1853,"ね":1413,"の":7396,"は":8578,"ば":1940,"ひ":4249,"び":-4134,"ふ":1345,"へ":6665,"べ":-744,"ほ":1464,"ま":1051,"み":-2082,"む":-882,"め":-5046,"も":4169,"ゃ":-2666,"や":2795,"ょ":-1544,"よ":3351,"ら":-2922,"り":-9726,"る":-14896,"れ":-2613,"ろ":-4570,"わ":-1783,"を":13150,"ん":-2352,"カ":2145,"コ":1789,"セ":1287,"ッ":-724,"ト":-403,"メ":-1635,"ラ":-881,"リ":-541,"ル":-856,"ン":-3637,"・":-4371,"ー":-11870,"一":-2069,"中":2210,"予":782,"事":-190,"井":-1768,"人":1036,"以":544,"会":950,"体":-1286,"作":530,"側":4292,"先":601,"党":-2006,"共":-1212,"内":584,"円":788,"初":1347,"前":1623,"副":3879,"力":-302,"動":-740,"務":-2715,"化":776,"区":4517,"協":1013,"参":1555,"合":-1834,"和":-681,"員":-910,"器":-851,"回":1500,"国":-619,"園":-1200,"地":866,"場":-1410,"塁":-2094,"士":-1413,"多":1067,"大":571,"子":-4802,"学":-1397,"定":-1057,"寺":-809,"小":1910,"屋":-1328,"山":-1500,"島":-2056,"川":-2667,"市":2771,"年":374,"庁":-4556,"後":456,"性":553,"感":916,"所":-1566,"支":856,"改":787,"政":2182,"教":704,"文":522,"方":-856,"日":1798,"時":1829,"最":845,"月":-9066,"木":-485,"来":-442,"校":-360,"業":-1043,"氏":5388,"民":-2716,"気":-910,"沢":-939,"済":-543,"物":-735,"率":672,"球":-1267,"生":-1286,"産":-1101,"田":-2900,"町":1826,"的":2586,"目":922,"省":-3485,"県":2997,"空":-867,"立":-2112,"第":788,"米":2937,"系":786,"約":2171,"経":1146,"統":-1169,"総":940,"線":-994,"署":749,"者":2145,"能":-730,"般":-852,"行":-792,"規":792,"警":-1184,"議":-244,"谷":-1000,"賞":730,"車":-1481,"軍":1158,"輪":-1433,"込":-3370,"近":929,"道":-1291,"選":2596,"郎":-4866,"都":1192,"野":-1100,"銀":-2213,"長":357,"間":-2344,"院":-2297,"際":-2604,"電":-878,"領":-1659,"題":-792,"館":-1984,"首":1749,"高":2120,"「":1895,"」":3798,"・":-4371,"ッ":-724,"ー":-11870,"カ":2145,"コ":1789,"セ":1287,"ト":-403,"メ":-1635,"ラ":-881,"リ":-541,"ル":-856,"ン":-3637};
this.UW5__ = {",":465,".":-299,"1":-514,"E2":-32768,"]":-2762,"、":465,"。":-299,"「":363,"あ":1655,"い":331,"う":-503,"え":1199,"お":527,"か":647,"が":-421,"き":1624,"ぎ":1971,"く":312,"げ":-983,"さ":-1537,"し":-1371,"す":-852,"だ":-1186,"ち":1093,"っ":52,"つ":921,"て":-18,"で":-850,"と":-127,"ど":1682,"な":-787,"に":-1224,"の":-635,"は":-578,"べ":1001,"み":502,"め":865,"ゃ":3350,"ょ":854,"り":-208,"る":429,"れ":504,"わ":419,"を":-1264,"ん":327,"イ":241,"ル":451,"ン":-343,"中":-871,"京":722,"会":-1153,"党":-654,"務":3519,"区":-901,"告":848,"員":2104,"大":-1296,"学":-548,"定":1785,"嵐":-1304,"市":-2991,"席":921,"年":1763,"思":872,"所":-814,"挙":1618,"新":-1682,"日":218,"月":-4353,"査":932,"格":1356,"機":-1508,"氏":-1347,"田":240,"町":-3912,"的":-3149,"相":1319,"省":-1052,"県":-4003,"研":-997,"社":-278,"空":-813,"統":1955,"者":-2233,"表":663,"語":-1073,"議":1219,"選":-1018,"郎":-368,"長":786,"間":1191,"題":2368,"館":-689,"1":-514,"E2":-32768,"「":363,"イ":241,"ル":451,"ン":-343};
this.UW6__ = {",":227,".":808,"1":-270,"E1":306,"、":227,"。":808,"あ":-307,"う":189,"か":241,"が":-73,"く":-121,"こ":-200,"じ":1782,"す":383,"た":-428,"っ":573,"て":-1014,"で":101,"と":-105,"な":-253,"に":-149,"の":-417,"は":-236,"も":-206,"り":187,"る":-135,"を":195,"ル":-673,"ン":-496,"一":-277,"中":201,"件":-800,"会":624,"前":302,"区":1792,"員":-1212,"委":798,"学":-960,"市":887,"広":-695,"後":535,"業":-697,"相":753,"社":-507,"福":974,"空":-822,"者":1811,"連":463,"郎":1082,"1":-270,"E1":306,"ル":-673,"ン":-496};
return this;
}
TinySegmenter.prototype.ctype_ = function(str) {
for (var i in this.chartype_) {
if (str.match(this.chartype_[i][0])) {
return this.chartype_[i][1];
}
}
return "O";
}
TinySegmenter.prototype.ts_ = function(v) {
if (v) { return v; }
return 0;
}
TinySegmenter.prototype.segment = function(input) {
if (input == null || input == undefined || input == "") {
return [];
}
var result = [];
var seg = ["B3","B2","B1"];
var ctype = ["O","O","O"];
var o = input.split("");
for (i = 0; i < o.length; ++i) {
seg.push(o[i]);
ctype.push(this.ctype_(o[i]))
}
seg.push("E1");
seg.push("E2");
seg.push("E3");
ctype.push("O");
ctype.push("O");
ctype.push("O");
var word = seg[3];
var p1 = "U";
var p2 = "U";
var p3 = "U";
for (var i = 4; i < seg.length - 3; ++i) {
var score = this.BIAS__;
var w1 = seg[i-3];
var w2 = seg[i-2];
var w3 = seg[i-1];
var w4 = seg[i];
var w5 = seg[i+1];
var w6 = seg[i+2];
var c1 = ctype[i-3];
var c2 = ctype[i-2];
var c3 = ctype[i-1];
var c4 = ctype[i];
var c5 = ctype[i+1];
var c6 = ctype[i+2];
score += this.ts_(this.UP1__[p1]);
score += this.ts_(this.UP2__[p2]);
score += this.ts_(this.UP3__[p3]);
score += this.ts_(this.BP1__[p1 + p2]);
score += this.ts_(this.BP2__[p2 + p3]);
score += this.ts_(this.UW1__[w1]);
score += this.ts_(this.UW2__[w2]);
score += this.ts_(this.UW3__[w3]);
score += this.ts_(this.UW4__[w4]);
score += this.ts_(this.UW5__[w5]);
score += this.ts_(this.UW6__[w6]);
score += this.ts_(this.BW1__[w2 + w3]);
score += this.ts_(this.BW2__[w3 + w4]);
score += this.ts_(this.BW3__[w4 + w5]);
score += this.ts_(this.TW1__[w1 + w2 + w3]);
score += this.ts_(this.TW2__[w2 + w3 + w4]);
score += this.ts_(this.TW3__[w3 + w4 + w5]);
score += this.ts_(this.TW4__[w4 + w5 + w6]);
score += this.ts_(this.UC1__[c1]);
score += this.ts_(this.UC2__[c2]);
score += this.ts_(this.UC3__[c3]);
score += this.ts_(this.UC4__[c4]);
score += this.ts_(this.UC5__[c5]);
score += this.ts_(this.UC6__[c6]);
score += this.ts_(this.BC1__[c2 + c3]);
score += this.ts_(this.BC2__[c3 + c4]);
score += this.ts_(this.BC3__[c4 + c5]);
score += this.ts_(this.TC1__[c1 + c2 + c3]);
score += this.ts_(this.TC2__[c2 + c3 + c4]);
score += this.ts_(this.TC3__[c3 + c4 + c5]);
score += this.ts_(this.TC4__[c4 + c5 + c6]);
// score += this.ts_(this.TC5__[c4 + c5 + c6]);
score += this.ts_(this.UQ1__[p1 + c1]);
score += this.ts_(this.UQ2__[p2 + c2]);
score += this.ts_(this.UQ3__[p3 + c3]);
score += this.ts_(this.BQ1__[p2 + c2 + c3]);
score += this.ts_(this.BQ2__[p2 + c3 + c4]);
score += this.ts_(this.BQ3__[p3 + c2 + c3]);
score += this.ts_(this.BQ4__[p3 + c3 + c4]);
score += this.ts_(this.TQ1__[p2 + c1 + c2 + c3]);
score += this.ts_(this.TQ2__[p2 + c2 + c3 + c4]);
score += this.ts_(this.TQ3__[p3 + c1 + c2 + c3]);
score += this.ts_(this.TQ4__[p3 + c2 + c3 + c4]);
var p = "O";
if (score > 0) {
result.push(word);
word = "";
p = "B";
}
p1 = p2;
p2 = p3;
p3 = p;
word += seg[i];
}
result.push(word);
return result;
}
lunr.TinySegmenter = TinySegmenter;
};
}));

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +0,0 @@
{"version":3,"sources":["src/templates/assets/stylesheets/palette/_scheme.scss","../../../../src/templates/assets/stylesheets/palette.scss","src/templates/assets/stylesheets/palette/_accent.scss","src/templates/assets/stylesheets/palette/_primary.scss","src/templates/assets/stylesheets/utilities/_break.scss"],"names":[],"mappings":"AA2BA,cAGE,6BAME,sDAAA,CACA,6DAAA,CACA,+DAAA,CACA,gEAAA,CACA,mDAAA,CACA,6DAAA,CACA,+DAAA,CACA,gEAAA,CAGA,mDAAA,CACA,gDAAA,CAGA,0BAAA,CACA,mCAAA,CAGA,iCAAA,CACA,kCAAA,CACA,mCAAA,CACA,mCAAA,CACA,kCAAA,CACA,iCAAA,CACA,+CAAA,CACA,6DAAA,CACA,gEAAA,CACA,4DAAA,CACA,4DAAA,CACA,6DAAA,CAGA,6CAAA,CAGA,+CAAA,CAGA,uDAAA,CACA,6DAAA,CACA,2DAAA,CAGA,iCAAA,CAGA,yDAAA,CACA,iEAAA,CAGA,mDAAA,CACA,mDAAA,CAGA,qDAAA,CACA,uDAAA,CAGA,8DAAA,CAKA,8DAAA,CAKA,0DAAA,CAvEA,iBCeF,CD6DE,kHAEE,YC3DJ,CDkFE,yDACE,4BChFJ,CD+EE,2DACE,4BC7EJ,CD4EE,gEACE,4BC1EJ,CDyEE,2DACE,4BCvEJ,CDsEE,yDACE,4BCpEJ,CDmEE,0DACE,4BCjEJ,CDgEE,gEACE,4BC9DJ,CD6DE,0DACE,4BC3DJ,CD0DE,2OACE,4BC/CJ,CDsDA,+FAGE,iCCpDF,CACF,CC/CE,2BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD2CN,CCrDE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDkDN,CC5DE,8BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDyDN,CCnEE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDgEN,CC1EE,8BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDuEN,CCjFE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD8EN,CCxFE,kCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDqFN,CC/FE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD4FN,CCtGE,4BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDmGN,CC7GE,6BACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCD0GN,CCpHE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDiHN,CC3HE,4BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCD2HN,CClIE,8BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDkIN,CCzIE,6BACE,yBAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDyIN,CChJE,8BACE,4BAAA,CACA,2CAAA,CAIE,8BAAA,CACA,qCDgJN,CCvJE,mCACE,4BAAA,CACA,2CAAA,CAOE,yBAAA,CACA,qCDoJN,CEzJE,4BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsJN,CEjKE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8JN,CEzKE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsKN,CEjLE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8KN,CEzLE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsLN,CEjME,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8LN,CEzME,mCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsMN,CEjNE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8MN,CEzNE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsNN,CEjOE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8NN,CEzOE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsON,CEjPE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFiPN,CEzPE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFyPN,CEjQE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFiQN,CEzQE,+BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAIE,+BAAA,CACA,sCFyQN,CEjRE,oCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCF8QN,CEzRE,8BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCFsRN,CEjSE,6BACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCAAA,CAKA,4BF0RN,CE1SE,kCACE,6BAAA,CACA,oCAAA,CACA,mCAAA,CAOE,0BAAA,CACA,sCAAA,CAKA,4BFmSN,CEpRE,sEACE,4BFuRJ,CExRE,+DACE,4BF2RJ,CE5RE,iEACE,4BF+RJ,CEhSE,gEACE,4BFmSJ,CEpSE,iEACE,4BFuSJ,CE9RA,8BACE,mDAAA,CACA,4DAAA,CACA,0DAAA,CACA,oDAAA,CACA,2DAAA,CAGA,4BF+RF,CE5RE,yCACE,+BF8RJ,CE3RI,kDAEE,0CAAA,CACA,sCAAA,CAFA,mCF+RN,CG3MI,mCD1EA,+CACE,8CFwRJ,CErRI,qDACE,8CFuRN,CElRE,iEACE,mCFoRJ,CACF,CGtNI,sCDvDA,uCACE,oCFgRJ,CACF,CEvQA,8BACE,kDAAA,CACA,4DAAA,CACA,wDAAA,CACA,oDAAA,CACA,6DAAA,CAGA,4BFwQF,CErQE,yCACE,+BFuQJ,CEpQI,kDAEE,0CAAA,CACA,sCAAA,CAFA,mCFwQN,CEjQE,yCACE,6CFmQJ,CG5NI,0CDhCA,8CACE,gDF+PJ,CACF,CGjOI,0CDvBA,iFACE,6CF2PJ,CACF,CGzPI,sCDKA,uCACE,6CFuPJ,CACF","file":"palette.css"}

View File

@@ -1,6 +0,0 @@
{
"project": "omniread",
"type": "docforge-model",
"modules_count": 22,
"source": "docforge"
}

View File

@@ -1,125 +0,0 @@
{
"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)."
}
}
}
}
}
}

View File

@@ -1,534 +0,0 @@
{
"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."
}
}
}
}
}
}
}
}

View File

@@ -1,169 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,90 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,69 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,576 +0,0 @@
{
"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."
}
}
}
}
}
}
}
}

View File

@@ -1,113 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,148 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,143 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,488 +0,0 @@
{
"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."
}
}
}
}
}
}
}
}

View File

@@ -1,234 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,164 +0,0 @@
{
"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."
}
}
}
}
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -1,69 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,440 +0,0 @@
{
"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."
}
}
}
}
}
}
}
}

View File

@@ -1,148 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,159 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,69 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,611 +0,0 @@
{
"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."
}
}
}
}
}
}
}
}

View File

@@ -1,134 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,148 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,143 +0,0 @@
{
"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."
}
}
}
}
}
}

View File

@@ -1,90 +0,0 @@
[
{
"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

View File

@@ -1,3 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
</urlset>

Binary file not shown.