aetos/docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
docs/libs/mail-intake/site/mail_intake/parsers/index.html
Vishesh 'ironeagle' Bangotra 24ecde4222
All checks were successful
continuous-integration/drone/push Build is passing
Details
added more libs
2026-01-22 17:20:17 +05:30

1814 lines
38 KiB
HTML
Raw Permalink Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../credentials/redis/">
<link rel="next" href="body/">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
<title>Parsers - mail_intake</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">
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#parsers" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="mail_intake" class="md-header__button md-logo" aria-label="mail_intake" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
mail_intake
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Parsers
</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">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href="../" class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../ingestion/" class="md-tabs__link">
Core API
</a>
</li>
<li class="md-tabs__item">
<a href="../models/" class="md-tabs__link">
Domain Models
</a>
</li>
<li class="md-tabs__item">
<a href="../adapters/" class="md-tabs__link">
Provider Adapters
</a>
</li>
<li class="md-tabs__item">
<a href="../auth/" class="md-tabs__link">
Authentication & Storage
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="./" class="md-tabs__link">
Normalization & Parsing
</a>
</li>
<li class="md-tabs__item">
<a href="../config/" class="md-tabs__link">
Configuration & Errors
</a>
</li>
</ul>
</div>
</nav>
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="mail_intake" class="md-nav__button md-logo" aria-label="mail_intake" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
mail_intake
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../" class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Core API
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Core API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../ingestion/" class="md-nav__link">
<span class="md-ellipsis">
Ingestion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../ingestion/reader/" class="md-nav__link">
<span class="md-ellipsis">
Reader
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Domain Models
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Domain Models
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../models/" class="md-nav__link">
<span class="md-ellipsis">
Models
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../models/message/" class="md-nav__link">
<span class="md-ellipsis">
Message
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../models/thread/" class="md-nav__link">
<span class="md-ellipsis">
Thread
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Provider Adapters
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Provider Adapters
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../adapters/" class="md-nav__link">
<span class="md-ellipsis">
Adapters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../adapters/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../adapters/gmail/" class="md-nav__link">
<span class="md-ellipsis">
Gmail
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Authentication & Storage
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Authentication & Storage
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../auth/" class="md-nav__link">
<span class="md-ellipsis">
Auth
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../auth/base/" class="md-nav__link">
<span class="md-ellipsis">
Base
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../auth/google/" class="md-nav__link">
<span class="md-ellipsis">
Google
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../credentials/" class="md-nav__link">
<span class="md-ellipsis">
Credentials
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../credentials/store/" class="md-nav__link">
<span class="md-ellipsis">
Store
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../credentials/pickle/" class="md-nav__link">
<span class="md-ellipsis">
Pickle
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../credentials/redis/" class="md-nav__link">
<span class="md-ellipsis">
Redis
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" checked>
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="">
<span class="md-ellipsis">
Normalization & Parsing
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Normalization & Parsing
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Parsers
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Parsers
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#mail_intake.parsers" class="md-nav__link">
<span class="md-ellipsis">
parsers
</span>
</a>
<nav class="md-nav" aria-label="parsers">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#mail_intake.parsers.extract_body" class="md-nav__link">
<span class="md-ellipsis">
extract_body
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.extract_sender" class="md-nav__link">
<span class="md-ellipsis">
extract_sender
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.normalize_subject" class="md-nav__link">
<span class="md-ellipsis">
normalize_subject
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.parse_headers" class="md-nav__link">
<span class="md-ellipsis">
parse_headers
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="body/" class="md-nav__link">
<span class="md-ellipsis">
Body
</span>
</a>
</li>
<li class="md-nav__item">
<a href="headers/" class="md-nav__link">
<span class="md-ellipsis">
Headers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="subject/" class="md-nav__link">
<span class="md-ellipsis">
Subject
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
Configuration & Errors
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Configuration & Errors
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../config/" class="md-nav__link">
<span class="md-ellipsis">
Config
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../exceptions/" class="md-nav__link">
<span class="md-ellipsis">
Exceptions
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#mail_intake.parsers" class="md-nav__link">
<span class="md-ellipsis">
parsers
</span>
</a>
<nav class="md-nav" aria-label="parsers">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#mail_intake.parsers.extract_body" class="md-nav__link">
<span class="md-ellipsis">
extract_body
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.extract_sender" class="md-nav__link">
<span class="md-ellipsis">
extract_sender
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.normalize_subject" class="md-nav__link">
<span class="md-ellipsis">
normalize_subject
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#mail_intake.parsers.parse_headers" class="md-nav__link">
<span class="md-ellipsis">
parse_headers
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="parsers">Parsers</h1>
<div class="doc doc-object doc-module">
<h2 id="mail_intake.parsers" class="doc doc-heading">
<span class="doc doc-object-name doc-module-name">mail_intake.parsers</span>
</h2>
<div class="doc doc-contents first">
<p>Message parsing utilities for Mail Intake.</p>
<p>This package contains <strong>provider-aware but adapter-agnostic parsing helpers</strong>
used to extract and normalize structured information from raw mail payloads.</p>
<p>Parsers in this package are responsible for:
- Interpreting provider-native message structures
- Extracting meaningful fields such as headers, body text, and subjects
- Normalizing data into consistent internal representations</p>
<p>This package does not:
- Perform network or IO operations
- Contain provider API logic
- Construct domain models directly</p>
<p>Parsing functions are designed to be composable and are orchestrated by the
ingestion layer.</p>
<div class="doc doc-children">
<div class="doc doc-object doc-function">
<h3 id="mail_intake.parsers.extract_body" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">extract_body</span>
</h3>
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">extract_body</span><span class="p">(</span><span class="n">payload</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="nb">str</span>
</code></pre></div>
<div class="doc doc-contents ">
<p>Extract the best-effort message body from a Gmail payload.</p>
<p>Priority:
1. text/plain
2. text/html (stripped to text)
3. Single-part body
4. empty string (if nothing usable found)</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>payload</code></td>
<td>
<code><span title="typing.Dict">Dict</span>[str, <span title="typing.Any">Any</span>]</code>
</td>
<td>
<div class="doc-md-description">
<p>Provider-native message payload dictionary.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>str</code>
</td>
<td>
<div class="doc-md-description">
<p>Extracted plain-text message body.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="doc doc-object doc-function">
<h3 id="mail_intake.parsers.extract_sender" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">extract_sender</span>
</h3>
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">extract_sender</span><span class="p">(</span><span class="n">headers</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span>
</code></pre></div>
<div class="doc doc-contents ">
<p>Extract sender email and optional display name from headers.</p>
<p>This function parses the <code>From</code> header and attempts to extract:
- Sender email address
- Optional human-readable display name</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>headers</code></td>
<td>
<code><span title="typing.Dict">Dict</span>[str, str]</code>
</td>
<td>
<div class="doc-md-description">
<p>Normalized header dictionary as returned by
:func:<code>parse_headers</code>.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>str</code>
</td>
<td>
<div class="doc-md-description">
<p>A tuple <code>(email, name)</code> where:</p>
</div>
</td>
</tr>
<tr class="doc-section-item">
<td>
<code><span title="typing.Optional">Optional</span>[str]</code>
</td>
<td>
<div class="doc-md-description">
<ul>
<li><code>email</code> is the sender email address</li>
</ul>
</div>
</td>
</tr>
<tr class="doc-section-item">
<td>
<code><span title="typing.Tuple">Tuple</span>[str, <span title="typing.Optional">Optional</span>[str]]</code>
</td>
<td>
<div class="doc-md-description">
<ul>
<li><code>name</code> is the display name, or <code>None</code> if unavailable</li>
</ul>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Examples:</span></p>
<p><code>"John Doe &lt;john@example.com&gt;"</code> → <code>("john@example.com", "John Doe")</code>
<code>"john@example.com"</code> → <code>("john@example.com", None)</code></p>
</div>
</div>
<div class="doc doc-object doc-function">
<h3 id="mail_intake.parsers.normalize_subject" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">normalize_subject</span>
</h3>
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">normalize_subject</span><span class="p">(</span><span class="n">subject</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span>
</code></pre></div>
<div class="doc doc-contents ">
<p>Normalize an email subject for thread-level comparison.</p>
<p>Operations:
- Strips common prefixes such as <code>Re:</code>, <code>Fwd:</code>, and <code>FW:</code>
- Repeats prefix stripping to handle stacked prefixes
- Collapses excessive whitespace
- Preserves original casing (no lowercasing)</p>
<p>This function is intentionally conservative and avoids aggressive
transformations that could alter the semantic meaning of the subject.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>subject</code></td>
<td>
<code>str</code>
</td>
<td>
<div class="doc-md-description">
<p>Raw subject line from a message header.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>str</code>
</td>
<td>
<div class="doc-md-description">
<p>Normalized subject string suitable for thread grouping.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="doc doc-object doc-function">
<h3 id="mail_intake.parsers.parse_headers" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">parse_headers</span>
</h3>
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse_headers</span><span class="p">(</span><span class="n">raw_headers</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]])</span> <span class="o">-&gt;</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span>
</code></pre></div>
<div class="doc doc-contents ">
<p>Convert a list of Gmail-style headers into a normalized dict.</p>
<p>Provider payloads (such as Gmail) typically represent headers as a list
of name/value mappings. This function normalizes them into a
case-insensitive dictionary keyed by lowercase header names.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>raw_headers</code></td>
<td>
<code><span title="typing.List">List</span>[<span title="typing.Dict">Dict</span>[str, str]]</code>
</td>
<td>
<div class="doc-md-description">
<p>List of header dictionaries, each containing
<code>name</code> and <code>value</code> keys.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code><span title="typing.Dict">Dict</span>[str, str]</code>
</td>
<td>
<div class="doc-md-description">
<p>Dictionary mapping lowercase header names to stripped values.</p>
</div>
</td>
</tr>
</tbody>
</table>
<details class="example" open>
<summary>Example</summary>
<p>Input:
[
{"name": "From", "value": "John Doe <a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#106;&#111;&#104;&#110;&#64;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#99;&#111;&#109;">&#106;&#111;&#104;&#110;&#64;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#99;&#111;&#109;</a>"},
{"name": "Subject", "value": "Re: Interview Update"},
]</p>
<p>Output:
{
"from": "John Doe <a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#106;&#111;&#104;&#110;&#64;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#99;&#111;&#109;">&#106;&#111;&#104;&#110;&#64;&#101;&#120;&#97;&#109;&#112;&#108;&#101;&#46;&#99;&#111;&#109;</a>",
"subject": "Re: Interview Update",
}</p>
</details>
</div>
</div>
</div>
</div>
</div>
</article>
</div>
<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.tabs", "navigation.expand", "navigation.top", "navigation.instant", "content.code.copy", "content.code.annotate"], "search": "../../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink