Files
obikmer/DevDoc/implementation/obitaxonomy/index.html
T

1744 lines
35 KiB
HTML
Raw Normal View History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
2026-08-15 20:56:29 +02:00
<link rel="prev" href="../select/">
<link rel="next" href="../../architecture/sequences/invariant/">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.7.6">
2026-08-15 20:56:29 +02:00
<title>obitaxonomy crate - obikmer</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.484c7ddc.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<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">
<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">
2026-08-15 20:56:29 +02:00
<a href="#obitaxonomy-taxonomy-concept-paths" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="obikmer" class="md-header__button md-logo" aria-label="obikmer" 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">
obikmer
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
obitaxonomy crate
</span>
</div>
</div>
</div>
<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>
</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="obikmer" class="md-nav__button md-logo" aria-label="obikmer" 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>
obikmer
</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>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="../../installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
2026-08-15 20:56:29 +02:00
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
2026-08-15 20:56:29 +02:00
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Theory
</span>
<span class="md-nav__icon md-icon"></span>
</label>
2026-08-15 20:56:29 +02:00
<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>
Theory
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../kmers/" class="md-nav__link">
<span class="md-ellipsis">
Kmers and super-kmers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/encoding/" class="md-nav__link">
<span class="md-ellipsis">
DNA encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/entropy/" class="md-nav__link">
<span class="md-ellipsis">
Entropy filter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/minimizer/" class="md-nav__link">
<span class="md-ellipsis">
Minimizer selection
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../theory/indexing/" class="md-nav__link">
<span class="md-ellipsis">
Partitioning architecture
</span>
</a>
</li>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="../../theory/evolutionary_distances/" class="md-nav__link">
<span class="md-ellipsis">
Central-position SNP distance (discussion)
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
2026-08-15 20:56:29 +02:00
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" checked>
2026-08-15 20:56:29 +02:00
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Implementation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
2026-08-15 20:56:29 +02:00
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Implementation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../superkmer/" class="md-nav__link">
<span class="md-ellipsis">
SuperKmer
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../kmer/" class="md-nav__link">
<span class="md-ellipsis">
Kmer
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../chunkreader/" class="md-nav__link">
<span class="md-ellipsis">
Chunk reader
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pipeline/" class="md-nav__link">
<span class="md-ellipsis">
Construction pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../obipipeline/" class="md-nav__link">
<span class="md-ellipsis">
obipipeline library
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../storage/" class="md-nav__link">
<span class="md-ellipsis">
On-disk storage
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../mphf/" class="md-nav__link">
<span class="md-ellipsis">
MPHF selection
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../unitig_evidence/" class="md-nav__link">
<span class="md-ellipsis">
Unitig evidence encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../evidence_elimination/" class="md-nav__link">
<span class="md-ellipsis">
Evidence elimination (discussion)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../obilayeredmap/" class="md-nav__link">
<span class="md-ellipsis">
obilayeredmap crate
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../persistent_compact_int_vec/" class="md-nav__link">
<span class="md-ellipsis">
PersistentCompactIntVec
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../persistent_bit_vec/" class="md-nav__link">
<span class="md-ellipsis">
PersistentBitVec
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../merge/" class="md-nav__link">
<span class="md-ellipsis">
Merge command
</span>
</a>
</li>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="../merge_parallelism/" class="md-nav__link">
<span class="md-ellipsis">
Merge parallelism & memory
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../filtering/" class="md-nav__link">
<span class="md-ellipsis">
Kmer filtering
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../select/" class="md-nav__link">
<span class="md-ellipsis">
Select command
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
obitaxonomy crate
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
obitaxonomy crate
</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">
2026-08-15 20:56:29 +02:00
<a href="#concept-path-syntax" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Concept path syntax
</span>
</a>
2026-08-15 20:56:29 +02:00
<nav class="md-nav" aria-label="Concept path syntax">
<ul class="md-nav__list">
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#reserved-character" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Reserved character
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#parse-errors" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Parse errors
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#public-api" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Public API
</span>
</a>
2026-08-15 20:56:29 +02:00
<nav class="md-nav" aria-label="Public API">
<ul class="md-nav__list">
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#taxsegment" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
TaxSegment
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#taxpath" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
TaxPath
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#integration-with-genomeinfo" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Integration with GenomeInfo
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#predicate-operators-in-filter-select" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Predicate operators (in filter / select)
</span>
</a>
<nav class="md-nav" aria-label="Predicate operators (in filter / select)">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#path-pattern-syntax" class="md-nav__link">
<span class="md-ellipsis">
Path pattern syntax
</span>
</a>
</li>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="#rank-aware-queries" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Rank-aware queries
</span>
</a>
2026-08-15 20:56:29 +02:00
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
2026-08-15 20:56:29 +02:00
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
2026-08-15 20:56:29 +02:00
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Architecture
</span>
<span class="md-nav__icon md-icon"></span>
</label>
2026-08-15 20:56:29 +02:00
<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>
Architecture
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../architecture/sequences/invariant/" class="md-nav__link">
<span class="md-ellipsis">
Sequences
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../architecture/index_architecture/" class="md-nav__link">
<span class="md-ellipsis">
Kmer index
</span>
</a>
</li>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="../../architecture/siblings/" class="md-nav__link">
<span class="md-ellipsis">
Sibling annex (discussion)
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../architecture/numa_worker_pools/" class="md-nav__link">
<span class="md-ellipsis">
NUMA-aware worker pools
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../architecture/numa_partition_runner/" class="md-nav__link">
<span class="md-ellipsis">
NUMA-aware partition runner
</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">
2026-08-15 20:56:29 +02:00
<a href="#concept-path-syntax" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Concept path syntax
</span>
</a>
2026-08-15 20:56:29 +02:00
<nav class="md-nav" aria-label="Concept path syntax">
<ul class="md-nav__list">
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#reserved-character" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Reserved character
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#parse-errors" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Parse errors
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#public-api" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Public API
</span>
</a>
2026-08-15 20:56:29 +02:00
<nav class="md-nav" aria-label="Public API">
<ul class="md-nav__list">
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#taxsegment" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
TaxSegment
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#taxpath" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
TaxPath
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#integration-with-genomeinfo" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Integration with GenomeInfo
</span>
</a>
</li>
<li class="md-nav__item">
2026-08-15 20:56:29 +02:00
<a href="#predicate-operators-in-filter-select" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Predicate operators (in filter / select)
</span>
</a>
<nav class="md-nav" aria-label="Predicate operators (in filter / select)">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#path-pattern-syntax" class="md-nav__link">
<span class="md-ellipsis">
Path pattern syntax
</span>
</a>
</li>
2026-08-15 20:56:29 +02:00
<li class="md-nav__item">
<a href="#rank-aware-queries" class="md-nav__link">
<span class="md-ellipsis">
2026-08-15 20:56:29 +02:00
Rank-aware queries
</span>
</a>
2026-08-15 20:56:29 +02:00
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
2026-08-15 20:56:29 +02:00
<h1 id="obitaxonomy-taxonomy-concept-paths"><code>obitaxonomy</code> — taxonomy concept paths</h1>
<p><code>obitaxonomy</code> is a dependency-free crate that defines a typed representation
of hierarchical concept paths (taxonomic or otherwise) stored in genome metadata.</p>
<hr />
<h2 id="concept-path-syntax">Concept path syntax</h2>
<p>A concept path is stored as a metadata value with the prefix <code>taxonomy:/</code>:</p>
<div class="highlight"><pre><span></span><code>taxonomy:/enterobacteriaceae@family/Escherichia@genus/Escherichia coli@species
</code></pre></div>
2026-08-15 20:56:29 +02:00
<p>Structure:</p>
<ul>
2026-08-15 20:56:29 +02:00
<li>The <code>taxonomy:/</code> prefix is the type discriminator. Any metadata value starting
with it is parsed as a <code>TaxPath</code>; all others remain plain strings.</li>
<li>The remainder is one or more <code>/</code>-separated segments.</li>
<li>Each segment is <code>name</code> or <code>name@rank</code>, where <code>rank</code> is a label for the
taxonomic level (e.g. <code>family</code>, <code>genus</code>, <code>species</code>).</li>
<li>Rank annotations are <strong>optional per segment</strong> and can be mixed freely.</li>
<li>Spaces are allowed in both names and ranks.</li>
</ul>
2026-08-15 20:56:29 +02:00
<h3 id="reserved-character">Reserved character</h3>
<p><code>@</code> is reserved throughout the taxonomy system and may <strong>not</strong> appear in:</p>
<table>
<thead>
<tr>
2026-08-15 20:56:29 +02:00
<th>Context</th>
<th>Constraint</th>
</tr>
</thead>
<tbody>
<tr>
2026-08-15 20:56:29 +02:00
<td>Segment name</td>
<td>forbidden</td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td>Rank/class label</td>
<td>forbidden</td>
</tr>
<tr>
<td>Metadata key names</td>
<td>forbidden (used as <code>key@rank</code> in predicate syntax)</td>
</tr>
</tbody>
</table>
2026-08-15 20:56:29 +02:00
<p><code>@</code> is freely allowed in plain-text metadata values (non-taxonomy).</p>
<h3 id="parse-errors">Parse errors</h3>
<table>
<thead>
<tr>
<th>Condition</th>
<th>Error</th>
</tr>
</thead>
<tbody>
<tr>
<td>Value does not start with <code>taxonomy:/</code></td>
<td><code>MissingPrefix</code></td>
</tr>
<tr>
<td>No segments after the prefix</td>
<td><code>EmptyPath</code></td>
</tr>
<tr>
<td>Segment with empty name (consecutive <code>/</code>)</td>
<td><code>EmptySegmentName</code></td>
</tr>
<tr>
<td>Segment with trailing <code>@</code> and no rank (<code>name@</code>)</td>
<td><code>EmptyRankName</code></td>
</tr>
<tr>
<td>Segment with more than one <code>@</code></td>
<td><code>AmbiguousRank</code></td>
</tr>
</tbody>
</table>
<hr />
<h2 id="public-api">Public API</h2>
<h3 id="taxsegment"><code>TaxSegment</code></h3>
<p>A single node: a name and an optional rank.</p>
<div class="highlight"><pre><span></span><code><span class="n">seg</span><span class="p">.</span><span class="n">name</span><span class="p">()</span><span class="w"> </span><span class="c1">// &amp;str</span>
<span class="n">seg</span><span class="p">.</span><span class="n">rank</span><span class="p">()</span><span class="w"> </span><span class="c1">// Option&lt;&amp;str&gt;</span>
<span class="n">seg</span><span class="p">.</span><span class="n">to_string</span><span class="p">()</span><span class="w"> </span><span class="c1">// &quot;name&quot; or &quot;name@rank&quot;</span>
<span class="n">TaxSegment</span><span class="p">::</span><span class="n">parse</span><span class="p">(</span><span class="n">s</span><span class="p">)</span><span class="w"> </span><span class="c1">// Result&lt;TaxSegment, TaxError&gt;</span>
</code></pre></div>
<h3 id="taxpath"><code>TaxPath</code></h3>
<div class="highlight"><pre><span></span><code><span class="n">TaxPath</span><span class="p">::</span><span class="n">parse</span><span class="p">(</span><span class="n">s</span><span class="p">)</span><span class="w"> </span><span class="c1">// Result&lt;TaxPath, TaxError&gt;</span>
<span class="n">path</span><span class="p">.</span><span class="n">segments</span><span class="p">()</span><span class="w"> </span><span class="c1">// &amp;[TaxSegment]</span>
<span class="n">path</span><span class="p">.</span><span class="n">depth</span><span class="p">()</span><span class="w"> </span><span class="c1">// usize — number of segments</span>
<span class="n">path</span><span class="p">.</span><span class="n">is_ancestor_of</span><span class="p">(</span><span class="o">&amp;</span><span class="n">other</span><span class="p">)</span><span class="w"> </span><span class="c1">// bool — prefix match by name, ranks ignored</span>
<span class="n">path</span><span class="p">.</span><span class="n">name_at_rank</span><span class="p">(</span><span class="s">&quot;genus&quot;</span><span class="p">)</span><span class="w"> </span><span class="c1">// Option&lt;&amp;str&gt;</span>
<span class="n">path</span><span class="p">.</span><span class="n">to_string</span><span class="p">()</span><span class="w"> </span><span class="c1">// reconstructs &quot;taxonomy:/…&quot;</span>
</code></pre></div>
<p><code>is_ancestor_of</code> compares segment <strong>names</strong> only — rank annotations are
informational and do not affect the ancestry relation.</p>
<div class="highlight"><pre><span></span><code><span class="kd">let</span><span class="w"> </span><span class="n">a</span><span class="p">:</span><span class="w"> </span><span class="nc">TaxPath</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;taxonomy:/Enterobacteriaceae@family/Escherichia@genus&quot;</span><span class="p">.</span><span class="n">parse</span><span class="p">()</span><span class="o">?</span><span class="p">;</span>
<span class="kd">let</span><span class="w"> </span><span class="n">b</span><span class="p">:</span><span class="w"> </span><span class="nc">TaxPath</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;taxonomy:/Enterobacteriaceae@family/Escherichia@genus/Escherichia coli@species&quot;</span><span class="p">.</span><span class="n">parse</span><span class="p">()</span><span class="o">?</span><span class="p">;</span>
<span class="fm">assert!</span><span class="p">(</span><span class="n">a</span><span class="p">.</span><span class="n">is_ancestor_of</span><span class="p">(</span><span class="o">&amp;</span><span class="n">b</span><span class="p">));</span><span class="w"> </span><span class="c1">// true</span>
<span class="fm">assert!</span><span class="p">(</span><span class="n">b</span><span class="p">.</span><span class="n">is_ancestor_of</span><span class="p">(</span><span class="o">&amp;</span><span class="n">a</span><span class="p">));</span><span class="w"> </span><span class="c1">// false</span>
<span class="fm">assert!</span><span class="p">(</span><span class="n">a</span><span class="p">.</span><span class="n">is_ancestor_of</span><span class="p">(</span><span class="o">&amp;</span><span class="n">a</span><span class="p">));</span><span class="w"> </span><span class="c1">// true (equal ⇒ ancestor)</span>
<span class="fm">assert_eq!</span><span class="p">(</span><span class="n">b</span><span class="p">.</span><span class="n">name_at_rank</span><span class="p">(</span><span class="s">&quot;species&quot;</span><span class="p">),</span><span class="w"> </span><span class="nb">Some</span><span class="p">(</span><span class="s">&quot;Escherichia coli&quot;</span><span class="p">));</span>
<span class="fm">assert_eq!</span><span class="p">(</span><span class="n">b</span><span class="p">.</span><span class="n">name_at_rank</span><span class="p">(</span><span class="s">&quot;genus&quot;</span><span class="p">),</span><span class="w"> </span><span class="nb">Some</span><span class="p">(</span><span class="s">&quot;Escherichia&quot;</span><span class="p">));</span>
<span class="fm">assert_eq!</span><span class="p">(</span><span class="n">b</span><span class="p">.</span><span class="n">name_at_rank</span><span class="p">(</span><span class="s">&quot;order&quot;</span><span class="p">),</span><span class="w"> </span><span class="nb">None</span><span class="p">);</span>
</code></pre></div>
<hr />
<h2 id="integration-with-genomeinfo">Integration with <code>GenomeInfo</code></h2>
<p>At index load time, every metadata value is inspected once:</p>
<ul>
2026-08-15 20:56:29 +02:00
<li>Starts with <code>taxonomy:/</code> → parsed into <code>TaxPath</code>, stored in <code>genome.taxonomy</code>.</li>
<li>Otherwise → kept as-is in <code>genome.meta</code>.</li>
</ul>
2026-08-15 20:56:29 +02:00
<div class="highlight"><pre><span></span><code><span class="k">struct</span><span class="w"> </span><span class="nc">GenomeInfo</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">label</span><span class="p">:</span><span class="w"> </span><span class="nb">String</span><span class="p">,</span>
<span class="w"> </span><span class="n">meta</span><span class="p">:</span><span class="w"> </span><span class="nc">HashMap</span><span class="o">&lt;</span><span class="nb">String</span><span class="p">,</span><span class="w"> </span><span class="nb">String</span><span class="o">&gt;</span><span class="p">,</span><span class="w"> </span><span class="c1">// plain text metadata</span>
<span class="w"> </span><span class="n">taxonomy</span><span class="p">:</span><span class="w"> </span><span class="nc">HashMap</span><span class="o">&lt;</span><span class="nb">String</span><span class="p">,</span><span class="w"> </span><span class="n">TaxPath</span><span class="o">&gt;</span><span class="p">,</span><span class="w"> </span><span class="c1">// parsed taxonomy metadata</span>
<span class="p">}</span>
</code></pre></div>
<p>The raw string is not duplicated. <code>TaxPath::to_string()</code> reconstructs the
original value losslessly for serialisation.</p>
<hr />
<h2 id="predicate-operators-in-filter-select">Predicate operators (in <code>filter</code> / <code>select</code>)</h2>
<p>Path predicates use the <code>~</code> / <code>!~</code> operators. The <strong>stored value</strong> always starts
with <code>/</code> (rooted path); the <strong>query pattern</strong> does not need to.</p>
<h3 id="path-pattern-syntax">Path pattern syntax</h3>
<table>
<thead>
<tr>
2026-08-15 20:56:29 +02:00
<th>Pattern</th>
<th>Semantics</th>
</tr>
</thead>
<tbody>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>A/B</code></td>
<td>contiguous sub-path A then B, anywhere in the value</td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>/A/B</code></td>
<td>value starts with A then B (start-anchored)</td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>A/B$</code></td>
<td>value ends with A then B (end-anchored)</td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>/A/B$</code></td>
<td>value is exactly A then B (fully anchored)</td>
</tr>
<tr>
<td><code>A@x/B</code></td>
<td>A with class <code>x</code> followed by B with any class</td>
</tr>
<tr>
<td><code>A@x/B@y</code></td>
<td>A with class <code>x</code> followed by B with class <code>y</code></td>
</tr>
</tbody>
</table>
2026-08-15 20:56:29 +02:00
<p>A segment pattern without <code>@</code> matches the segment name regardless of its stored class.</p>
<h3 id="rank-aware-queries">Rank-aware queries</h3>
<div class="highlight"><pre><span></span><code>key@rank=value
</code></pre></div>
<table>
<thead>
<tr>
2026-08-15 20:56:29 +02:00
<th>Predicate form</th>
<th>Semantics</th>
</tr>
</thead>
<tbody>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>key@rank=value</code></td>
<td>genome's <code>key</code> has <code>value</code> at rank <code>rank</code></td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>key@rank!=value</code></td>
<td>does not</td>
</tr>
<tr>
2026-08-15 20:56:29 +02:00
<td><code>key@rank=v1\|v2</code></td>
<td>value at <code>rank</code> is <code>v1</code> or <code>v2</code></td>
</tr>
</tbody>
</table>
2026-08-15 20:56:29 +02:00
<p><code>~</code> combined with <code>@rank</code> on the key (e.g. <code>key@genus~pattern</code>) is not defined
and is rejected at parse time.</p>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</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">{"annotate": null, "base": "../..", "features": [], "search": "../../assets/javascripts/workers/search.2c215733.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.79ae519e.min.js"></script>
<script src="https://unpkg.com/mathjax@3/es5/tex-mml-chtml.js"></script>
</body>
</html>