OBIKmers/obikmer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 27 Wiki Activity

large refactoring

Browse Source
This commit is contained in:
Eric Coissac
2026-08-17 09:28:53 +02:00
parent 49e66f16a2
commit 7bac0f3850
236 changed files with 77584 additions and 3733 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/404.html
+549 -467
View File
File diff suppressed because it is too large Load Diff
doc/apa.csl
-2133
View File
File diff suppressed because it is too large Load Diff
doc/index.refs/index.html → doc/architecture/index.html
+694 -482
View File
File diff suppressed because it is too large Load Diff
doc/architecture/index_architecture.refs/index.html
-1068
View File
File diff suppressed because it is too large Load Diff
doc/architecture/index_architecture/index.html
-1779
View File
File diff suppressed because it is too large Load Diff
doc/architecture/query.refs/index.html
-1062
View File
File diff suppressed because it is too large Load Diff
doc/architecture/query/index.html
-1402
View File
File diff suppressed because it is too large Load Diff
doc/architecture/sequences/invariant.refs/index.html
-1058
View File
File diff suppressed because it is too large Load Diff
doc/architecture/sequences/invariant/index.html
-1047
View File
File diff suppressed because it is too large Load Diff
doc/css/extra.css
-35
View File
@@ -1,35 +0,0 @@
/* docs/css/extra.css */
/* Styles principaux pour le conteneur et le texte */
.ps-root {
font-family: "Courier New", monospace;
font-size: 0.9em;
line-height: 1.5;
}
/* Styles pour les mots-clés */
.ps-keyword {
font-weight: bold;
color: #d73a49; /* Une belle teinte de rouge */
}
/* --- CORRECTION DE L'INDENTATION --- */
/* Cible tous les niveaux d'indentation et applique une marge gauche */
[class*="ps-indent-"] {
display: inline-block;
}
.ps-indent-1 {
margin-left: 2em;
}
.ps-indent-2 {
margin-left: 4em;
}
.ps-indent-3 {
margin-left: 6em;
}
.ps-indent-4 {
margin-left: 8em;
}
.ps-indent-5 {
margin-left: 10em;
}
doc/theory/entropy/index.html → doc/formats/index_layout/index.html
+673 -650
View File
File diff suppressed because it is too large Load Diff
doc/implementation/chunkreader/index.html
-689
View File
@@ -1,689 +0,0 @@
<!DOCTYPE html>
<html class="no-js" lang="en">
<head>
<meta charset="utf-8"/>
<meta content="width=device-width,initial-scale=1" name="viewport"/>
<link href="../kmer/" rel="prev"/>
<link href="../pipeline/" rel="next"/>
<link href="../../assets/images/favicon.png" rel="icon"/>
<meta content="mkdocs-1.6.1, mkdocs-material-9.7.6" name="generator"/>
<title>Chunk reader - obikmer</title>
<link href="../../assets/stylesheets/main.484c7ddc.min.css" rel="stylesheet"/>
<link crossorigin="" href="https://fonts.gstatic.com" rel="preconnect"/>
<link href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&amp;display=fallback" rel="stylesheet"/>
<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 autocomplete="off" class="md-toggle" data-md-toggle="drawer" id="__drawer" type="checkbox"/>
<input autocomplete="off" class="md-toggle" data-md-toggle="search" id="__search" type="checkbox"/>
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a class="md-skip" href="#chunk-reader-implementation">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav aria-label="Header" class="md-header__inner md-grid">
<a aria-label="obikmer" class="md-header__button md-logo" data-md-component="logo" href="../.." title="obikmer">
<svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><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"></path></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"></path></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">
Chunk reader
</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 aria-label="Navigation" class="md-nav md-nav--primary" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a aria-label="obikmer" class="md-nav__button md-logo" data-md-component="logo" href="../.." title="obikmer">
<svg viewbox="0 0 24 24" xmlns="http://www.w3.org/2000/svg"><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"></path></svg>
</a>
obikmer
</label>
<ul class="md-nav__list" data-md-scrollfix="">
<li class="md-nav__item">
<a class="md-nav__link" href="../..">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" id="__nav_2" type="checkbox"/>
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Theory
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav aria-expanded="false" aria-labelledby="__nav_2_label" class="md-nav" data-md-level="1">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Theory
</label>
<ul class="md-nav__list" data-md-scrollfix="">
<li class="md-nav__item">
<a class="md-nav__link" href="../../kmers/">
<span class="md-ellipsis">
Kmers and super-kmers
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../../theory/encoding/">
<span class="md-ellipsis">
DNA encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../../theory/entropy/">
<span class="md-ellipsis">
Entropy filter
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../../theory/minimizer/">
<span class="md-ellipsis">
Minimizer selection
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../../theory/indexing/">
<span class="md-ellipsis">
Partitioning architecture
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input checked="" class="md-nav__toggle md-toggle" id="__nav_3" type="checkbox"/>
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Implementation
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav aria-expanded="true" aria-labelledby="__nav_3_label" class="md-nav" data-md-level="1">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Implementation
</label>
<ul class="md-nav__list" data-md-scrollfix="">
<li class="md-nav__item">
<a class="md-nav__link" href="../superkmer/">
<span class="md-ellipsis">
SuperKmer
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../kmer/">
<span class="md-ellipsis">
Kmer
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" id="__toc" type="checkbox"/>
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Chunk reader
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a class="md-nav__link md-nav__link--active" href="./">
<span class="md-ellipsis">
Chunk reader
</span>
</a>
<nav aria-label="Table of contents" class="md-nav md-nav--secondary">
<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 class="md-nav__link" href="#two-reading-paths">
<span class="md-ellipsis">
Two reading paths
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#record-path-chunk-reader">
<span class="md-ellipsis">
Record path: chunk reader
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#output-type-rope">
<span class="md-ellipsis">
Output type: Rope
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#seqchunkiter">
<span class="md-ellipsis">
SeqChunkIter
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#boundary-detection-fasta">
<span class="md-ellipsis">
Boundary detection — FASTA
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#boundary-detection-fastq">
<span class="md-ellipsis">
Boundary detection — FASTQ
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../pipeline/">
<span class="md-ellipsis">
Construction pipeline
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../obipipeline/">
<span class="md-ellipsis">
obipipeline library
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../storage/">
<span class="md-ellipsis">
On-disk storage
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../mphf/">
<span class="md-ellipsis">
MPHF selection
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../unitig_evidence/">
<span class="md-ellipsis">
Unitig evidence encoding
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../evidence_elimination/">
<span class="md-ellipsis">
Evidence elimination (discussion)
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../obilayeredmap/">
<span class="md-ellipsis">
obilayeredmap crate
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../persistent_compact_int_vec/">
<span class="md-ellipsis">
PersistentCompactIntVec
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../persistent_bit_vec/">
<span class="md-ellipsis">
PersistentBitVec
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../merge/">
<span class="md-ellipsis">
Merge command
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../rebuild_filter/">
<span class="md-ellipsis">
Kmer filtering (rebuild/dump/unitig)
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle" id="__nav_4" type="checkbox"/>
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Architecture
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav aria-expanded="false" aria-labelledby="__nav_4_label" class="md-nav" data-md-level="1">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Architecture
</label>
<ul class="md-nav__list" data-md-scrollfix="">
<li class="md-nav__item">
<a class="md-nav__link" href="../../architecture/sequences/invariant/">
<span class="md-ellipsis">
Sequences
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="../../architecture/index_architecture/">
<span class="md-ellipsis">
Kmer index
</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 aria-label="Table of contents" class="md-nav md-nav--secondary">
<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 class="md-nav__link" href="#two-reading-paths">
<span class="md-ellipsis">
Two reading paths
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#record-path-chunk-reader">
<span class="md-ellipsis">
Record path: chunk reader
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#output-type-rope">
<span class="md-ellipsis">
Output type: Rope
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#seqchunkiter">
<span class="md-ellipsis">
SeqChunkIter
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#boundary-detection-fasta">
<span class="md-ellipsis">
Boundary detection — FASTA
</span>
</a>
</li>
<li class="md-nav__item">
<a class="md-nav__link" href="#boundary-detection-fastq">
<span class="md-ellipsis">
Boundary detection — FASTQ
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="chunk-reader-implementation">Chunk reader — implementation</h1>
<p><code>obiread</code> exposes two distinct sequence reading paths, each optimised for a different use case.</p>
<h2 id="two-reading-paths">Two reading paths</h2>
<table>
<thead>
<tr>
<th>Path</th>
<th>API</th>
<th>Output unit</th>
<th>Per-record identity</th>
<th>Use case</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>Record path</strong></td>
<td><code>read_sequence_chunks</code> → <code>parse_chunk</code></td>
<td><code>SeqRecord</code> (id + raw sequence + normalised rope)</td>
<td>yes</td>
<td><code>query</code> — must read complete records</td>
</tr>
<tr>
<td><strong>Stream path</strong></td>
<td><code>open_nuc_stream</code></td>
<td><code>NucPage</code> (flat normalised byte buffer)</td>
<td>no</td>
<td><code>index</code>, <code>superkmer</code> — bulk throughput</td>
</tr>
</tbody>
</table>
<p>The record path uses <code>Rope</code>-backed chunks and is described in detail below.
The stream path (<code>NucStream</code> / <code>NucPage</code>) is described in the scatter section of <a href="../pipeline/">pipeline</a>.</p>
<hr/>
<h2 id="record-path-chunk-reader">Record path: chunk reader</h2>
<p>The chunk reader reads FASTA or FASTQ files in fixed-size blocks and yields self-contained chunks, each ending on a complete sequence record boundary. <code>parse_chunk</code> then converts each chunk into a <code>Vec&lt;SeqRecord&gt;</code>, where each record carries its identifier, raw sequence bytes, and a normalised rope ready for superkmer building.</p>
<p>This path is mandatory for <code>query</code>, where superkmers must be tracked back to their originating sequence (id, kmer offset) for output annotation.</p>
<h2 id="output-type-rope">Output type: Rope</h2>
<p>Each chunk is a <code>Rope</code> — a segmented byte sequence: a <code>Vec</code> of blocks, where each block is a <code>Vec&lt;Cell&lt;u8&gt;&gt;</code>. The consumer iterates over the blocks via a forward or backward cursor.</p>
<p><code>Rope::split_off(pos)</code> splits at an absolute byte offset in O(log n) (binary search over block-start index). If <code>pos</code> falls inside a block, that block is split in two via <code>Vec::split_off</code> — no <code>memcpy</code> in the common case.</p>
<h2 id="seqchunkiter">SeqChunkIter</h2>
<div class="highlight"><pre><span></span><code><span class="k">pub</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">SeqChunkIter</span><span class="o">&lt;</span><span class="n">R</span><span class="p">:</span><span class="w"> </span><span class="nc">Read</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span><span class="w"> </span><span class="cm">/* private */</span><span class="w"> </span><span class="p">}</span>
<span class="k">impl</span><span class="o">&lt;</span><span class="n">R</span><span class="p">:</span><span class="w"> </span><span class="nc">Read</span><span class="o">&gt;</span><span class="w"> </span><span class="nb">Iterator</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="n">SeqChunkIter</span><span class="o">&lt;</span><span class="n">R</span><span class="o">&gt;</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">type</span><span class="w"> </span><span class="nc">Item</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">io</span><span class="p">::</span><span class="nb">Result</span><span class="o">&lt;</span><span class="n">Rope</span><span class="o">&gt;</span><span class="p">;</span>
<span class="p">}</span>
<span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">fasta_chunks</span><span class="o">&lt;</span><span class="n">R</span><span class="p">:</span><span class="w"> </span><span class="nc">Read</span><span class="o">&gt;</span><span class="p">(</span><span class="n">source</span><span class="p">:</span><span class="w"> </span><span class="nc">R</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">SeqChunkIter</span><span class="o">&lt;</span><span class="n">R</span><span class="o">&gt;</span>
<span class="k">pub</span><span class="w"> </span><span class="k">fn</span><span class="w"> </span><span class="nf">fastq_chunks</span><span class="o">&lt;</span><span class="n">R</span><span class="p">:</span><span class="w"> </span><span class="nc">Read</span><span class="o">&gt;</span><span class="p">(</span><span class="n">source</span><span class="p">:</span><span class="w"> </span><span class="nc">R</span><span class="p">)</span><span class="w"> </span><span class="p">-&gt;</span><span class="w"> </span><span class="nc">SeqChunkIter</span><span class="o">&lt;</span><span class="n">R</span><span class="o">&gt;</span>
</code></pre></div>
<p><code>next()</code> loop:</p>
<div class="highlight"><pre><span></span><code>1. read one block of block_size bytes → push onto Rope
2. call splitter(rope) → Option&lt;abs_offset&gt;
if Some(pos):
tail = rope.split_off(pos) ← O(log n), may split one block
chunk = mem::replace(&amp;mut rope, tail)
return Some(Ok(chunk))
3. if EOF and rope non-empty: return Some(Ok(rope)) as final chunk
4. if EOF and rope empty: return None
</code></pre></div>
<p>The <code>Splitter</code> function signature is <code>fn(&amp;Rope) -&gt; Option&lt;usize&gt;</code>. It returns the absolute byte offset of the start of the last complete record, or <code>None</code> if no boundary was found in the accumulated rope (need more data).</p>
<h2 id="boundary-detection-fasta">Boundary detection — FASTA</h2>
<p>Backward scan with a 2-state machine. Searches (right to left) for <code>&gt;</code> followed by <code>\n</code> or <code>\r</code> (i.e., a <code>&gt;</code> that is preceded by a newline in forward order):</p>
<pre class="mermaid"><code>stateDiagram-v2
direction LR
[*] --&gt; Scanning
Scanning --&gt; FoundGt : '&gt;'
FoundGt --&gt; Scanning : other
FoundGt --&gt; [*] : '\\n' / '\\r' ✓</code></pre>
<p>Returns the byte offset of the <code>&gt;</code> that starts the last complete record. Returns <code>None</code> if only one <code>&gt;</code> is found (cannot confirm there is a prior complete record).</p>
<h2 id="boundary-detection-fastq">Boundary detection — FASTQ</h2>
<p>FASTQ records have a rigid 4-line structure (<code>@header</code>, sequence, <code>+</code>, quality). The <code>@</code> character (ASCII 64, Phred score 31) can appear legitimately in quality lines, making any forward heuristic unreliable. The backward scanner verifies the full structural context before accepting a candidate <code>@</code>.</p>
<p>7-state machine (states 0–6), scanning from <strong>right to left</strong>. Each time a <code>+</code> is found, its position is saved as <code>restart</code>; any state mismatch resets the scan to that position.</p>
<pre class="mermaid"><code>stateDiagram-v2
direction LR
[*] --&gt; Scanning
Scanning --&gt; FoundPlus : '+' (save restart)
FoundPlus --&gt; AfterNlPlus : '\\n' / '\\r'
FoundPlus --&gt; Scanning : other → backtrack
AfterNlPlus --&gt; AfterNlPlus : séparateur
AfterNlPlus --&gt; InSequence : lettre / - / . / [ / ]
AfterNlPlus --&gt; Scanning : other → backtrack
InSequence --&gt; AfterSequence : '\\n' / '\\r'
InSequence --&gt; InSequence : lettre / - / . / [ / ]
InSequence --&gt; Scanning : other → backtrack
AfterSequence --&gt; AfterSequence : '\\n' / '\\r'
AfterSequence --&gt; InHeader : other
InHeader --&gt; FoundAt : '@' (save cut)
InHeader --&gt; Scanning : '\\n' / '\\r' → backtrack
InHeader --&gt; InHeader : other
FoundAt --&gt; [*] : '\\n' / '\\r' ✓
FoundAt --&gt; InHeader : other</code></pre>
<p><code>restart</code> is updated each time a <code>+</code> is found. When any state fails its expected input, the scan jumps back to <code>restart</code> and continues from there — guaranteeing that a <code>@</code> in a quality line cannot be accepted as a record start, because the <code>\n+\n</code> structure immediately following it (going backward) will not be found.</p>
<p>Returns the byte offset of the <code>@</code> that starts the last complete record.</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/" rel="noopener" target="_blank">
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>
doc/implementation/evidence_elimination/index.html
-1461
View File
File diff suppressed because it is too large Load Diff
doc/implementation/kmer/index.html
-1348
View File
File diff suppressed because it is too large Load Diff
doc/implementation/merge/index.html
-1577
View File
File diff suppressed because it is too large Load Diff
doc/implementation/mphf/index.html
-1559
View File
File diff suppressed because it is too large Load Diff
doc/implementation/obilayeredmap.refs/index.html
-1068
View File
File diff suppressed because it is too large Load Diff
doc/implementation/obilayeredmap/index.html
-1987
View File
File diff suppressed because it is too large Load Diff
doc/implementation/obipipeline.refs/index.html
-1059
View File
File diff suppressed because it is too large Load Diff
doc/implementation/obipipeline/index.html
-1501
View File
File diff suppressed because it is too large Load Diff
doc/implementation/persistent_bit_vec.refs/index.html
-1059
View File
File diff suppressed because it is too large Load Diff
doc/implementation/persistent_bit_vec/index.html
-1764
View File
File diff suppressed because it is too large Load Diff
doc/implementation/persistent_compact_int_vec/index.html
-1792
View File
File diff suppressed because it is too large Load Diff
doc/implementation/pipeline/index.html
-1409
View File
File diff suppressed because it is too large Load Diff
doc/implementation/rebuild_filter/index.html
-1611
View File
File diff suppressed because it is too large Load Diff
doc/implementation/storage.refs/index.html
-1064
View File
File diff suppressed because it is too large Load Diff
doc/implementation/storage/index.html
-1502
View File
File diff suppressed because it is too large Load Diff
doc/implementation/superkmer.refs/index.html
-1059
View File
File diff suppressed because it is too large Load Diff
doc/implementation/superkmer/index.html
-1351
View File
File diff suppressed because it is too large Load Diff
doc/implementation/unitig_evidence.refs/index.html
-1064
View File
File diff suppressed because it is too large Load Diff
doc/implementation/unitig_evidence/index.html
-1623
View File
File diff suppressed because it is too large Load Diff
doc/index.html
+678 -571
View File
File diff suppressed because it is too large Load Diff
doc/installation/index.html
+1484
View File
File diff suppressed because it is too large Load Diff
doc/kmers.refs/index.html
-1059
View File
File diff suppressed because it is too large Load Diff
doc/references.bib
+18
View File
@@ -241,3 +241,21 @@
volume = 33,
year = 2017,
bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btw832}}
@misc{Mash-distances-doc,
author = {{Marbl Lab}},
howpublished = {Mash documentation},
title = {Mash Distance},
url = {https://mash.readthedocs.io/en/latest/distances.html},
urldate = {2026-07-09},
year = 2026}
@article{Fan2015-mash-formula,
author = {Fan, Huan and Ives, Anthony R and Surget-Groba, Yann and Cannon, Charles H},
doi = {10.1186/s12864-015-1647-5},
journal = {BMC Genomics},
number = 1,
title = {An assembly and alignment-free method of phylogeny reconstruction from next-generation sequencing data},
url = {https://doi.org/10.1186/s12864-015-1647-5},
volume = 16,
year = 2015}
doc/sitemap.xml.gz
BIN
View File
Binary file not shown.
doc/theory/encoding.refs/index.html
-1057
View File
File diff suppressed because it is too large Load Diff
doc/theory/encoding/index.html
+581 -490
View File
File diff suppressed because it is too large Load Diff
doc/theory/entropy.refs/index.html → doc/theory/entropy_filter/index.html
+717 -483
View File
File diff suppressed because it is too large Load Diff
doc/theory/indexing.refs/index.html
-1058
View File
File diff suppressed because it is too large Load Diff
doc/theory/indexing/index.html → doc/theory/indexing_architecture/index.html
+591 -485
View File
File diff suppressed because it is too large Load Diff
doc/kmers/index.html → doc/theory/kmers_and_superkmers/index.html
+568 -515
View File
File diff suppressed because it is too large Load Diff
doc/theory/minimizer.refs/index.html
-1058
View File
File diff suppressed because it is too large Load Diff
doc/theory/minimizer/index.html → doc/theory/minimizer_selection/index.html
+604 -572
View File
File diff suppressed because it is too large Load Diff
doc/implementation/kmer.refs/index.html → doc/usage/annotate/index.html
+569 -361
View File
File diff suppressed because it is too large Load Diff
doc/implementation/mphf.refs/index.html → doc/usage/dump/index.html
+555 -364
View File
File diff suppressed because it is too large Load Diff
doc/implementation/evidence_elimination.refs/index.html → doc/usage/estimate/index.html
+531 -379
View File
File diff suppressed because it is too large Load Diff
doc/usage/filter/index.html
+1363
View File
File diff suppressed because it is too large Load Diff
doc/usage/index_command/index.html
+1364
View File
File diff suppressed because it is too large Load Diff
doc/usage/merge/index.html
+1286
View File
File diff suppressed because it is too large Load Diff
doc/usage/name-tree/index.html
+1235
View File
File diff suppressed because it is too large Load Diff
doc/usage/pack/index.html
+1268
View File
File diff suppressed because it is too large Load Diff
doc/usage/phylo/index.html
+2109
View File
File diff suppressed because it is too large Load Diff
doc/implementation/chunkreader.refs/index.html → doc/usage/predicates/index.html
+635 -360
View File
File diff suppressed because it is too large Load Diff
doc/usage/query/index.html
+1311
View File
File diff suppressed because it is too large Load Diff
doc/implementation/persistent_compact_int_vec.refs/index.html → doc/usage/reindex/index.html
+564 -362
View File
File diff suppressed because it is too large Load Diff
doc/usage/select/index.html
+1307
View File
File diff suppressed because it is too large Load Diff
doc/usage/superkmer/index.html
+1272
View File
File diff suppressed because it is too large Load Diff
doc/implementation/merge.refs/index.html → doc/usage/unitig/index.html
+529 -367
View File
File diff suppressed because it is too large Load Diff
doc/implementation/pipeline.refs/index.html → doc/usage/utils/index.html
+569 -367
View File
File diff suppressed because it is too large Load Diff
doc/vancouver.csl
-377
View File
@@ -1,377 +0,0 @@
<?xml version="1.0" encoding="utf-8"?>
<style xmlns="http://purl.org/net/xbiblio/csl" class="in-text" version="1.0" demote-non-dropping-particle="sort-only" initialize-with-hyphen="false" page-range-format="minimal">
<info>
<title>Vancouver</title>
<id>http://www.zotero.org/styles/vancouver</id>
<link href="http://www.zotero.org/styles/vancouver" rel="self"/>
<link href="http://www.nlm.nih.gov/bsd/uniform_requirements.html" rel="documentation"/>
<author>
<name>Michael Berkowitz</name>
<email>mberkowi@gmu.edu</email>
</author>
<contributor>
<name>Sean Takats</name>
<email>stakats@gmu.edu</email>
</contributor>
<contributor>
<name>Sebastian Karcher</name>
</contributor>
<category citation-format="numeric"/>
<category field="generic-base"/>
<category field="medicine"/>
<summary>Vancouver style as outlined by International Committee of Medical Journal Editors Uniform Requirements for Manuscripts Submitted to Biomedical Journals: Sample References</summary>
<updated>2025-05-17T20:55:38-04:00</updated>
<rights license="http://creativecommons.org/licenses/by-sa/3.0/">This work is licensed under a Creative Commons Attribution-ShareAlike 3.0 License</rights>
</info>
<locale xml:lang="en">
<date form="text" delimiter=" ">
<date-part name="year"/>
<date-part name="month" form="short" strip-periods="true"/>
<date-part name="day"/>
</date>
<terms>
<term name="collection-editor" form="long">
<single>editor</single>
<multiple>editors</multiple>
</term>
<term name="presented at">presented at</term>
<term name="available at">available from</term>
<term name="section" form="short">sect.</term>
</terms>
</locale>
<locale xml:lang="fr">
<date form="text" delimiter=" ">
<date-part name="day"/>
<date-part name="month" form="short" strip-periods="true"/>
<date-part name="year"/>
</date>
</locale>
<macro name="author">
<names variable="author">
<name sort-separator=" " initialize-with="" name-as-sort-order="all" delimiter=", " delimiter-precedes-last="always"/>
<label form="long" prefix=", "/>
<substitute>
<text macro="webpage-title"/>
<names variable="editor"/>
</substitute>
</names>
</macro>
<macro name="editor">
<names variable="editor" suffix=".">
<name sort-separator=" " initialize-with="" name-as-sort-order="all" delimiter=", " delimiter-precedes-last="always"/>
<label form="long" prefix=", "/>
</names>
</macro>
<macro name="chapter-marker">
<choose>
<if type="chapter paper-conference entry-dictionary entry-encyclopedia" match="any">
<text term="in" text-case="capitalize-first"/>
</if>
</choose>
</macro>
<macro name="webpage-title">
<!--If a webpage has a container, we're assuming the citation is "part of a website" as per ch. 25 Citing Medicine https://www.ncbi.nlm.nih.gov/books/NBK7274/?report=reader -->
<choose>
<if type="webpage" variable="container-title" match="all">
<group delimiter=" ">
<text variable="container-title"/>
<text term="internet" prefix="[" suffix="]" text-case="capitalize-first"/>
</group>
</if>
</choose>
</macro>
<macro name="publisher">
<choose>
<!--discard publisher info for articles-->
<if type="article-journal article-magazine article-newspaper" match="none">
<group delimiter=": " suffix=";">
<choose>
<if type="thesis">
<text variable="publisher-place" prefix="[" suffix="]"/>
</if>
<else-if type="speech"/>
<else>
<text variable="publisher-place"/>
</else>
</choose>
<text variable="publisher"/>
</group>
</if>
</choose>
</macro>
<macro name="access">
<choose>
<if variable="URL">
<group delimiter=": ">
<text term="available at" text-case="capitalize-first"/>
<text variable="URL"/>
</group>
</if>
</choose>
</macro>
<macro name="accessed-date">
<choose>
<if variable="URL">
<group prefix="[" suffix="]" delimiter=" ">
<text term="cited" text-case="lowercase"/>
<date variable="accessed" form="text"/>
</group>
</if>
</choose>
</macro>
<macro name="container-title">
<choose>
<if type="article-journal article-magazine chapter paper-conference article-newspaper review review-book entry-dictionary entry-encyclopedia" match="any">
<group suffix="." delimiter=" ">
<choose>
<if type="article-journal review review-book" match="any">
<text variable="container-title" form="short" strip-periods="true"/>
</if>
<else>
<text variable="container-title" strip-periods="true"/>
</else>
</choose>
<choose>
<if variable="URL">
<text term="internet" prefix="[" suffix="]" text-case="capitalize-first"/>
</if>
</choose>
</group>
<text macro="edition" prefix=" "/>
</if>
<!--add event-name and event-place once they become available-->
<else-if type="bill legislation" match="any">
<group delimiter=", ">
<group delimiter=". ">
<text variable="container-title"/>
<group delimiter=" ">
<text term="section" form="short" text-case="capitalize-first"/>
<text variable="section"/>
</group>
</group>
<text variable="number"/>
</group>
</else-if>
<else-if type="speech">
<group delimiter=": " suffix=";">
<group delimiter=" ">
<text variable="genre" text-case="capitalize-first"/>
<text term="presented at"/>
</group>
<text variable="event"/>
</group>
</else-if>
<else>
<group delimiter=", " suffix=".">
<choose>
<if variable="collection-title" match="none">
<group delimiter=" ">
<label variable="volume" form="short" text-case="capitalize-first"/>
<text variable="volume"/>
</group>
</if>
</choose>
<text variable="container-title"/>
</group>
</else>
</choose>
</macro>
<macro name="title">
<choose>
<if type="webpage" variable="container-title" match="all"/>
<else>
<text variable="title"/>
<choose>
<if type="article-journal article-magazine chapter paper-conference article-newspaper review review-book entry-dictionary entry-encyclopedia" match="none">
<choose>
<if variable="URL">
<text term="internet" prefix=" [" suffix="]" text-case="capitalize-first"/>
</if>
</choose>
<text macro="edition" prefix=". "/>
</if>
</choose>
</else>
</choose>
<choose>
<if type="thesis">
<text variable="genre" prefix=" [" suffix="]"/>
</if>
</choose>
</macro>
<macro name="edition">
<choose>
<if is-numeric="edition">
<group delimiter=" ">
<number variable="edition" form="ordinal"/>
<text term="edition" form="short"/>
</group>
</if>
<else>
<text variable="edition" suffix="."/>
</else>
</choose>
</macro>
<macro name="date">
<choose>
<if type="article-journal article-magazine article-newspaper review review-book" match="any">
<group suffix=";" delimiter=" ">
<date variable="issued" form="text"/>
<text macro="accessed-date"/>
</group>
</if>
<else-if type="bill legislation" match="any">
<group delimiter=", ">
<date variable="issued" delimiter=" ">
<date-part name="month" form="short" strip-periods="true"/>
<date-part name="day"/>
</date>
<date variable="issued">
<date-part name="year"/>
</date>
</group>
</else-if>
<else-if type="report">
<date variable="issued" delimiter=" ">
<date-part name="year"/>
<date-part name="month" form="short" strip-periods="true"/>
</date>
<text macro="accessed-date" prefix=" "/>
</else-if>
<else-if type="patent">
<group suffix=".">
<group delimiter=", ">
<text variable="number"/>
<date variable="issued">
<date-part name="year"/>
</date>
</group>
<text macro="accessed-date" prefix=" "/>
</group>
</else-if>
<else-if type="speech">
<group delimiter="; ">
<group delimiter=" ">
<date variable="issued" delimiter=" ">
<date-part name="year"/>
<date-part name="month" form="short" strip-periods="true"/>
<date-part name="day"/>
</date>
<text macro="accessed-date"/>
</group>
<text variable="event-place"/>
</group>
</else-if>
<else>
<group suffix=".">
<date variable="issued">
<date-part name="year"/>
</date>
<text macro="accessed-date" prefix=" "/>
</group>
</else>
</choose>
</macro>
<macro name="pages">
<choose>
<if type="article-journal article-magazine article-newspaper review review-book" match="any">
<text variable="page" prefix=":"/>
</if>
<else-if type="book" match="any">
<text variable="number-of-pages" prefix=" "/>
<choose>
<if is-numeric="number-of-pages">
<label variable="number-of-pages" form="short" prefix=" " plural="never"/>
</if>
</choose>
</else-if>
<else>
<group prefix=" " delimiter=" ">
<label variable="page" form="short" plural="never"/>
<text variable="page"/>
</group>
</else>
</choose>
</macro>
<macro name="journal-location">
<choose>
<if type="article-journal article-magazine review review-book" match="any">
<text variable="volume"/>
<text variable="issue" prefix="(" suffix=")"/>
</if>
</choose>
</macro>
<macro name="webpage-part">
<choose>
<if type="webpage" variable="container-title" match="all">
<text variable="title"/>
</if>
</choose>
</macro>
<macro name="collection-details">
<choose>
<if type="article-journal article-magazine article-newspaper review review-book" match="none">
<choose>
<if variable="collection-title">
<group delimiter=" " prefix="(" suffix=")">
<names variable="collection-editor" suffix=".">
<name sort-separator=" " initialize-with="" name-as-sort-order="all" delimiter=", " delimiter-precedes-last="always"/>
<label form="long" prefix=", "/>
</names>
<group delimiter="; ">
<text variable="collection-title"/>
<group delimiter=" ">
<label variable="volume" form="short"/>
<text variable="volume"/>
</group>
</group>
</group>
</if>
</choose>
</if>
</choose>
</macro>
<macro name="report-details">
<choose>
<if type="report">
<text variable="number" prefix="Report No.: "/>
</if>
</choose>
</macro>
<citation collapse="citation-number">
<sort>
<key variable="citation-number"/>
</sort>
<layout prefix="(" suffix=")" delimiter=",">
<text variable="citation-number"/>
</layout>
</citation>
<bibliography et-al-min="7" et-al-use-first="6" second-field-align="flush">
<layout>
<text variable="citation-number" suffix="."/>
<group delimiter=". " suffix=". ">
<text macro="author"/>
<text macro="title"/>
</group>
<group delimiter=" " suffix=". ">
<group delimiter=": ">
<text macro="chapter-marker"/>
<group delimiter=" ">
<text macro="editor"/>
<text macro="container-title"/>
</group>
</group>
<text macro="publisher"/>
<group>
<text macro="date"/>
<text macro="journal-location"/>
<text macro="pages"/>
</group>
<text macro="webpage-part"/>
</group>
<text macro="collection-details" suffix=". "/>
<text macro="report-details" suffix=". "/>
<text macro="access"/>
</layout>
</bibliography>
</style>