mirror of
https://github.com/edg-l/edlang.git
synced 2024-11-23 16:38:24 +00:00
755 lines
93 KiB
HTML
755 lines
93 KiB
HTML
|
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="A byte oriented Thompson non-deterministic finite automaton (NFA)."><title>NFA in regex_automata::nfa::thompson - Rust</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../static.files/SourceSerif4-Regular-46f98efaafac5295.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../static.files/FiraSans-Regular-018c141bf0843ffd.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../static.files/FiraSans-Medium-8f9a781e4970d388.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../static.files/SourceCodePro-Regular-562dcc5011b6de7d.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../static.files/SourceCodePro-Semibold-d899c5a5c4aeb14a.ttf.woff2"><link rel="stylesheet" href="../../../static.files/normalize-76eba96aa4d2e634.css"><link rel="stylesheet" href="../../../static.files/rustdoc-ac92e1bbe349e143.css"><meta name="rustdoc-vars" data-root-path="../../../" data-static-root-path="../../../static.files/" data-current-crate="regex_automata" data-themes="" data-resource-suffix="" data-rustdoc-version="1.76.0 (07dca489a 2024-02-04)" data-channel="1.76.0" data-search-js="search-2b6ce74ff89ae146.js" data-settings-js="settings-4313503d2e1961c2.js" ><script src="../../../static.files/storage-f2adc0d6ca4d09fb.js"></script><script defer src="sidebar-items.js"></script><script defer src="../../../static.files/main-305769736d49e732.js"></script><noscript><link rel="stylesheet" href="../../../static.files/noscript-feafe1bb7466e4bd.css"></noscript><link rel="alternate icon" type="image/png" href="../../../static.files/favicon-16x16-8b506e7a72182f1c.png"><link rel="alternate icon" type="image/png" href="../../../static.files/favicon-32x32-422f7d1d52889060.png"><link rel="icon" type="image/svg+xml" href="../../../static.files/favicon-2c020d218678b618.svg"></head><body class="rustdoc struct"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="mobile-topbar"><button class="sidebar-menu-toggle">☰</button></nav><nav class="sidebar"><div class="sidebar-crate"><h2><a href="../../../regex_automata/index.html">regex_automata</a><span class="version">0.4.5</span></h2></div><h2 class="location"><a href="#">NFA</a></h2><div class="sidebar-elems"><section><h3><a href="#implementations">Methods</a></h3><ul class="block method"><li><a href="#method.always_match">always_match</a></li><li><a href="#method.byte_classes">byte_classes</a></li><li><a href="#method.compiler">compiler</a></li><li><a href="#method.config">config</a></li><li><a href="#method.group_info">group_info</a></li><li><a href="#method.has_capture">has_capture</a></li><li><a href="#method.has_empty">has_empty</a></li><li><a href="#method.is_always_start_anchored">is_always_start_anchored</a></li><li><a href="#method.is_reverse">is_reverse</a></li><li><a href="#method.is_utf8">is_utf8</a></li><li><a href="#method.look_matcher">look_matcher</a></li><li><a href="#method.look_set_any">look_set_any</a></li><li><a href="#method.look_set_prefix_any">look_set_prefix_any</a></li><li><a href="#method.memory_usage">memory_usage</a></li><li><a href="#method.never_match">never_match</a></li><li><a href="#method.new">new</a></li><li><a href="#method.new_many">new_many</a></li><li><a href="#method.pattern_len">pattern_len</a></li><li><a href="#method.patterns">patterns</a></li><li><a href="#method.start_anchored">start_anchored</a></li><li><a href="#method.start_pattern">start_pattern</a></li><li><a href="#method.start_unanchored">start_unanchored</a></li><li><a href="#method.state">state</a></li><li><a href="#method.states">states</a></li></ul><h3><a href="#trait-implementations">Trait Implementations</a></h3><ul class="block trait-implementation"><li><a href="#
|
|||
|
|
<main><div class="width-limiter"><nav class="sub"><form class="search-form"><span></span><div id="sidebar-button" tabindex="-1"><a href="../../../regex_automata/all.html" title="show sidebar"></a></div><input class="search-input" name="search" aria-label="Run search in the documentation" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" tabindex="-1"><a href="../../../help.html" title="help">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../static.files/wheel-7b819b6101059cd0.svg"></a></div></form></nav><section id="main-content" class="content"><div class="main-heading"><h1>Struct <a href="../../index.html">regex_automata</a>::<wbr><a href="../index.html">nfa</a>::<wbr><a href="index.html">thompson</a>::<wbr><a class="struct" href="#">NFA</a><button id="copy-path" title="Copy item path to clipboard"><img src="../../../static.files/clipboard-7571035ce49a181d.svg" width="19" height="18" alt="Copy item path"></button></h1><span class="out-of-band"><a class="src" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#190-202">source</a> · <button id="toggle-all-docs" title="collapse all docs">[<span>−</span>]</button></span></div><pre class="rust item-decl"><code>pub struct NFA(<span class="comment">/* private fields */</span>);</code></pre><details class="toggle top-doc" open><summary class="hideme"><span>Expand description</span></summary><div class="docblock"><p>A byte oriented Thompson non-deterministic finite automaton (NFA).</p>
|
|||
|
|
<p>A Thompson NFA is a finite state machine that permits unconditional epsilon
|
|||
|
|
transitions, but guarantees that there exists at most one non-epsilon
|
|||
|
|
transition for each element in the alphabet for each state.</p>
|
|||
|
|
<p>An NFA may be used directly for searching, for analysis or to build
|
|||
|
|
a deterministic finite automaton (DFA).</p>
|
|||
|
|
<h2 id="cheap-clones"><a href="#cheap-clones">Cheap clones</a></h2>
|
|||
|
|
<p>Since an NFA is a core data type in this crate that many other regex
|
|||
|
|
engines are based on top of, it is convenient to give ownership of an NFA
|
|||
|
|
to said regex engines. Because of this, an NFA uses reference counting
|
|||
|
|
internally. Therefore, it is cheap to clone and it is encouraged to do so.</p>
|
|||
|
|
<h2 id="capabilities"><a href="#capabilities">Capabilities</a></h2>
|
|||
|
|
<p>Using an NFA for searching via the
|
|||
|
|
<a href="pikevm/struct.PikeVM.html" title="struct regex_automata::nfa::thompson::pikevm::PikeVM"><code>PikeVM</code></a> provides the most amount
|
|||
|
|
of “power” of any regex engine in this crate. Namely, it supports the
|
|||
|
|
following in all cases:</p>
|
|||
|
|
<ol>
|
|||
|
|
<li>Detection of a match.</li>
|
|||
|
|
<li>Location of a match, including both the start and end offset, in a
|
|||
|
|
single pass of the haystack.</li>
|
|||
|
|
<li>Location of matching capturing groups.</li>
|
|||
|
|
<li>Handles multiple patterns, including (1)-(3) when multiple patterns are
|
|||
|
|
present.</li>
|
|||
|
|
</ol>
|
|||
|
|
<h2 id="capturing-groups"><a href="#capturing-groups">Capturing Groups</a></h2>
|
|||
|
|
<p>Groups refer to parenthesized expressions inside a regex pattern. They look
|
|||
|
|
like this, where <code>exp</code> is an arbitrary regex:</p>
|
|||
|
|
<ul>
|
|||
|
|
<li><code>(exp)</code> - An unnamed capturing group.</li>
|
|||
|
|
<li><code>(?P<name>exp)</code> or <code>(?<name>exp)</code> - A named capturing group.</li>
|
|||
|
|
<li><code>(?:exp)</code> - A non-capturing group.</li>
|
|||
|
|
<li><code>(?i:exp)</code> - A non-capturing group that sets flags.</li>
|
|||
|
|
</ul>
|
|||
|
|
<p>Only the first two forms are said to be <em>capturing</em>. Capturing
|
|||
|
|
means that the last position at which they match is reportable. The
|
|||
|
|
<a href="../../util/captures/struct.Captures.html" title="struct regex_automata::util::captures::Captures"><code>Captures</code></a> type provides convenient
|
|||
|
|
access to the match positions of capturing groups, which includes looking
|
|||
|
|
up capturing groups by their name.</p>
|
|||
|
|
<h2 id="byte-oriented"><a href="#byte-oriented">Byte oriented</a></h2>
|
|||
|
|
<p>This NFA is byte oriented, which means that all of its transitions are
|
|||
|
|
defined on bytes. In other words, the alphabet of an NFA consists of the
|
|||
|
|
256 different byte values.</p>
|
|||
|
|
<p>While DFAs nearly demand that they be byte oriented for performance
|
|||
|
|
reasons, an NFA could conceivably be <em>Unicode codepoint</em> oriented. Indeed,
|
|||
|
|
a previous version of this NFA supported both byte and codepoint oriented
|
|||
|
|
modes. A codepoint oriented mode can work because an NFA fundamentally uses
|
|||
|
|
a sparse representation of transitions, which works well with the large
|
|||
|
|
sparse space of Unicode codepoints.</p>
|
|||
|
|
<p>Nevertheless, this NFA is only byte oriented. This choice is primarily
|
|||
|
|
driven by implementation simplicity, and also in part memory usage. In
|
|||
|
|
practice, performance between the two is roughly comparable. However,
|
|||
|
|
building a DFA (including a hybrid DFA) really wants a byte oriented NFA.
|
|||
|
|
So if we do have a codepoint oriented NFA, then we also need to generate
|
|||
|
|
byte oriented NFA in order to build an hybrid NFA/DFA. Thus, by only
|
|||
|
|
generating byte oriented NFAs, we can produce one less NFA. In other words,
|
|||
|
|
if we made our NFA codepoint oriented, we’d need to <em>also</em> make it support
|
|||
|
|
a byte oriented mode, which is more complicated. But a byte oriented mode
|
|||
|
|
can support everything.</p>
|
|||
|
|
<h2 id="differences-with-dfas"><a href="#differences-with-dfas">Differences with DFAs</a></h2>
|
|||
|
|
<p>At the theoretical level, the precise difference between an NFA and a DFA
|
|||
|
|
is that, in a DFA, for every state, an input symbol unambiguously refers
|
|||
|
|
to a single transition <em>and</em> that an input symbol is required for each
|
|||
|
|
transition. At a practical level, this permits DFA implementations to be
|
|||
|
|
implemented at their core with a small constant number of CPU instructions
|
|||
|
|
for each byte of input searched. In practice, this makes them quite a bit
|
|||
|
|
faster than NFAs <em>in general</em>. Namely, in order to execute a search for any
|
|||
|
|
Thompson NFA, one needs to keep track of a <em>set</em> of states, and execute
|
|||
|
|
the possible transitions on all of those states for each input symbol.
|
|||
|
|
Overall, this results in much more overhead. To a first approximation, one
|
|||
|
|
can expect DFA searches to be about an order of magnitude faster.</p>
|
|||
|
|
<p>So why use an NFA at all? The main advantage of an NFA is that it takes
|
|||
|
|
linear time (in the size of the pattern string after repetitions have been
|
|||
|
|
expanded) to build and linear memory usage. A DFA, on the other hand, may
|
|||
|
|
take exponential time and/or space to build. Even in non-pathological
|
|||
|
|
cases, DFAs often take quite a bit more memory than their NFA counterparts,
|
|||
|
|
<em>especially</em> if large Unicode character classes are involved. Of course,
|
|||
|
|
an NFA also provides additional capabilities. For example, it can match
|
|||
|
|
Unicode word boundaries on non-ASCII text and resolve the positions of
|
|||
|
|
capturing groups.</p>
|
|||
|
|
<p>Note that a <a href="crate::hybrid::regex::Regex"><code>hybrid::regex::Regex</code></a> strikes a
|
|||
|
|
good balance between an NFA and a DFA. It avoids the exponential build time
|
|||
|
|
of a DFA while maintaining its fast search time. The downside of a hybrid
|
|||
|
|
NFA/DFA is that in some cases it can be slower at search time than the NFA.
|
|||
|
|
(It also has less functionality than a pure NFA. It cannot handle Unicode
|
|||
|
|
word boundaries on non-ASCII text and cannot resolve capturing groups.)</p>
|
|||
|
|
<h2 id="example"><a href="#example">Example</a></h2>
|
|||
|
|
<p>This shows how to build an NFA with the default configuration and execute a
|
|||
|
|
search using the Pike VM.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::pikevm::PikeVM, Match};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new(<span class="string">r"foo[0-9]+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>cache = re.create_cache();
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>caps = re.create_captures();
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>expected = <span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">0</span>..<span class="number">8</span>));
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"foo12345"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
<h2 id="example-resolving-capturing-groups"><a href="#example-resolving-capturing-groups">Example: resolving capturing groups</a></h2>
|
|||
|
|
<p>This example shows how to parse some simple dates and extract the
|
|||
|
|
components of each date via capturing groups.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{
|
|||
|
|
nfa::thompson::pikevm::PikeVM,
|
|||
|
|
util::captures::Captures,
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>vm = PikeVM::new(<span class="string">r"(?P<y>\d{4})-(?P<m>\d{2})-(?P<d>\d{2})"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>cache = vm.create_cache();
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>haystack = <span class="string">"2012-03-14, 2013-01-01 and 2014-07-05"</span>;
|
|||
|
|
<span class="kw">let </span>all: Vec<Captures> = vm.captures_iter(
|
|||
|
|
<span class="kw-2">&mut </span>cache, haystack.as_bytes()
|
|||
|
|
).collect();
|
|||
|
|
<span class="comment">// There should be a total of 3 matches.
|
|||
|
|
</span><span class="macro">assert_eq!</span>(<span class="number">3</span>, all.len());
|
|||
|
|
<span class="comment">// The year from the second match is '2013'.
|
|||
|
|
</span><span class="kw">let </span>span = all[<span class="number">1</span>].get_group_by_name(<span class="string">"y"</span>).unwrap();
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="string">"2013"</span>, <span class="kw-2">&</span>haystack[span]);
|
|||
|
|
</code></pre></div>
|
|||
|
|
<p>This example shows that only the last match of a capturing group is
|
|||
|
|
reported, even if it had to match multiple times for an overall match
|
|||
|
|
to occur.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::pikevm::PikeVM, Span};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new(<span class="string">r"([a-z]){4}"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>cache = re.create_cache();
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>caps = re.create_captures();
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>haystack = <span class="string">b"quux"</span>;
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, haystack, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert!</span>(caps.is_match());
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Span::from(<span class="number">3</span>..<span class="number">4</span>)), caps.get_group(<span class="number">1</span>));
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><h2 id="implementations" class="section-header">Implementations<a href="#implementations" class="anchor">§</a></h2><div id="implementations-list"><details class="toggle implementors-toggle" open><summary><section id="impl-NFA" class="impl"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#204-1178">source</a><a href="#impl-NFA" class="anchor">§</a><h3 class="code-header">impl <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.new" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#226-228">source</a><h4 class="code-header">pub fn <a href="#method.new" class="fn">new</a>(pattern: &<a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.str.html">str</a>) -> <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/result/enum.Result.html" title="enum core::result::Result">Result</a><<a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a>, <a class="struct" href="struct.BuildError.html" title="struct regex_automata::nfa::thompson::BuildError">BuildError</a>></h4></section></summary><div class="docblock"><p>Parse the given regular expression using a default configuration and
|
|||
|
|
build an NFA from it.</p>
|
|||
|
|
<p>If you want a non-default configuration, then use the NFA
|
|||
|
|
<a href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler"><code>Compiler</code></a> with a <a href="struct.Config.html" title="struct regex_automata::nfa::thompson::Config"><code>Config</code></a>.</p>
|
|||
|
|
<h5 id="example-1"><a href="#example-1">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::pikevm::PikeVM, Match};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new(<span class="string">r"foo[0-9]+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>expected = <span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">0</span>..<span class="number">8</span>));
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"foo12345"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.new_many" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#251-253">source</a><h4 class="code-header">pub fn <a href="#method.new_many" class="fn">new_many</a><P: <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.AsRef.html" title="trait core::convert::AsRef">AsRef</a><<a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.str.html">str</a>>>(patterns: &<a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.slice.html">[P]</a>) -> <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/result/enum.Result.html" title="enum core::result::Result">Result</a><<a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a>, <a class="struct" href="struct.BuildError.html" title="struct regex_automata::nfa::thompson::BuildError">BuildError</a>></h4></section></summary><div class="docblock"><p>Parse the given regular expressions using a default configuration and
|
|||
|
|
build a multi-NFA from them.</p>
|
|||
|
|
<p>If you want a non-default configuration, then use the NFA
|
|||
|
|
<a href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler"><code>Compiler</code></a> with a <a href="struct.Config.html" title="struct regex_automata::nfa::thompson::Config"><code>Config</code></a>.</p>
|
|||
|
|
<h5 id="example-2"><a href="#example-2">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::pikevm::PikeVM, Match};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new_many(<span class="kw-2">&</span>[<span class="string">"[0-9]+"</span>, <span class="string">"[a-z]+"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>expected = <span class="prelude-val">Some</span>(Match::must(<span class="number">1</span>, <span class="number">0</span>..<span class="number">3</span>));
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"foo12345bar"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.always_match" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#274-297">source</a><h4 class="code-header">pub fn <a href="#method.always_match" class="fn">always_match</a>() -> <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h4></section></summary><div class="docblock"><p>Returns an NFA with a single regex pattern that always matches at every
|
|||
|
|
position.</p>
|
|||
|
|
<h5 id="example-3"><a href="#example-3">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::{NFA, pikevm::PikeVM}, Match};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new_from_nfa(NFA::always_match())<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>expected = <span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">0</span>..<span class="number">0</span>));
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b""</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"foo"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.never_match" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#318-324">source</a><h4 class="code-header">pub fn <a href="#method.never_match" class="fn">never_match</a>() -> <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h4></section></summary><div class="docblock"><p>Returns an NFA that never matches at any position.</p>
|
|||
|
|
<p>This is a convenience routine for creating an NFA with zero patterns.</p>
|
|||
|
|
<h5 id="example-4"><a href="#example-4">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::{NFA, pikevm::PikeVM};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new_from_nfa(NFA::never_match())<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b""</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert!</span>(!caps.is_match());
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"foo"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert!</span>(!caps.is_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.config" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#347-349">source</a><h4 class="code-header">pub fn <a href="#method.config" class="fn">config</a>() -> <a class="struct" href="struct.Config.html" title="struct regex_automata::nfa::thompson::Config">Config</a></h4></section></summary><div class="docblock"><p>Return a default configuration for an <code>NFA</code>.</p>
|
|||
|
|
<p>This is a convenience routine to avoid needing to import the <code>Config</code>
|
|||
|
|
type when customizing the construction of an NFA.</p>
|
|||
|
|
<h5 id="example-5"><a href="#example-5">Example</a></h5>
|
|||
|
|
<p>This example shows how to build an NFA with a small size limit that
|
|||
|
|
results in a compilation error for any regex that tries to use more
|
|||
|
|
heap memory than the configured limit.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::{NFA, pikevm::PikeVM};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>result = PikeVM::builder()
|
|||
|
|
.thompson(NFA::config().nfa_size_limit(<span class="prelude-val">Some</span>(<span class="number">1_000</span>)))
|
|||
|
|
<span class="comment">// Remember, \w is Unicode-aware by default and thus huge.
|
|||
|
|
</span>.build(<span class="string">r"\w+"</span>);
|
|||
|
|
<span class="macro">assert!</span>(result.is_err());</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.compiler" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#381-383">source</a><h4 class="code-header">pub fn <a href="#method.compiler" class="fn">compiler</a>() -> <a class="struct" href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler">Compiler</a></h4></section></summary><div class="docblock"><p>Return a compiler for configuring the construction of an <code>NFA</code>.</p>
|
|||
|
|
<p>This is a convenience routine to avoid needing to import the
|
|||
|
|
<a href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler"><code>Compiler</code></a> type in common cases.</p>
|
|||
|
|
<h5 id="example-6"><a href="#example-6">Example</a></h5>
|
|||
|
|
<p>This example shows how to build an NFA that is permitted match invalid
|
|||
|
|
UTF-8. Without the additional syntax configuration here, compilation of
|
|||
|
|
<code>(?-u:.)</code> would fail because it is permitted to match invalid UTF-8.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{
|
|||
|
|
nfa::thompson::pikevm::PikeVM,
|
|||
|
|
util::syntax,
|
|||
|
|
Match,
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::builder()
|
|||
|
|
.syntax(syntax::Config::new().utf8(<span class="bool-val">false</span>))
|
|||
|
|
.build(<span class="string">r"[a-z]+(?-u:.)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>expected = <span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">1</span>..<span class="number">5</span>));
|
|||
|
|
re.captures(<span class="kw-2">&mut </span>cache, <span class="string">b"\xFFabc\xFF"</span>, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.patterns" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#406-411">source</a><h4 class="code-header">pub fn <a href="#method.patterns" class="fn">patterns</a>(&self) -> <a class="struct" href="struct.PatternIter.html" title="struct regex_automata::nfa::thompson::PatternIter">PatternIter</a><'_> <a href="#" class="tooltip" data-notable-ty="PatternIter<'_>">ⓘ</a></h4></section></summary><div class="docblock"><p>Returns an iterator over all pattern identifiers in this NFA.</p>
|
|||
|
|
<p>Pattern IDs are allocated in sequential order starting from zero,
|
|||
|
|
where the order corresponds to the order of patterns provided to the
|
|||
|
|
<a href="struct.NFA.html#method.new_many" title="associated function regex_automata::nfa::thompson::NFA::new_many"><code>NFA::new_many</code></a> constructor.</p>
|
|||
|
|
<h5 id="example-7"><a href="#example-7">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, PatternID};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"[0-9]+"</span>, <span class="string">"[a-z]+"</span>, <span class="string">"[A-Z]+"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>pids: Vec<PatternID> = nfa.patterns().collect();
|
|||
|
|
<span class="macro">assert_eq!</span>(pids, <span class="macro">vec!</span>[
|
|||
|
|
PatternID::must(<span class="number">0</span>),
|
|||
|
|
PatternID::must(<span class="number">1</span>),
|
|||
|
|
PatternID::must(<span class="number">2</span>),
|
|||
|
|
]);
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.pattern_len" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#440-442">source</a><h4 class="code-header">pub fn <a href="#method.pattern_len" class="fn">pattern_len</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.usize.html">usize</a></h4></section></summary><div class="docblock"><p>Returns the total number of regex patterns in this NFA.</p>
|
|||
|
|
<p>This may return zero if the NFA was constructed with no patterns. In
|
|||
|
|
this case, the NFA can never produce a match for any input.</p>
|
|||
|
|
<p>This is guaranteed to be no bigger than <a href="../../struct.PatternID.html#associatedconstant.LIMIT" title="associated constant regex_automata::PatternID::LIMIT"><code>PatternID::LIMIT</code></a> because
|
|||
|
|
NFA construction will fail if too many patterns are added.</p>
|
|||
|
|
<p>It is always true that <code>nfa.patterns().count() == nfa.pattern_len()</code>.</p>
|
|||
|
|
<h5 id="example-8"><a href="#example-8">Example</a></h5>
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"[0-9]+"</span>, <span class="string">"[a-z]+"</span>, <span class="string">"[A-Z]+"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="number">3</span>, nfa.pattern_len());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::never_match();
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="number">0</span>, nfa.pattern_len());
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::always_match();
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="number">1</span>, nfa.pattern_len());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.start_anchored" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#473-475">source</a><h4 class="code-header">pub fn <a href="#method.start_anchored" class="fn">start_anchored</a>(&self) -> <a class="struct" href="../../util/primitives/struct.StateID.html" title="struct regex_automata::util::primitives::StateID">StateID</a></h4></section></summary><div class="docblock"><p>Return the state identifier of the initial anchored state of this NFA.</p>
|
|||
|
|
<p>The returned identifier is guaranteed to be a valid index into the
|
|||
|
|
slice returned by <a href="struct.NFA.html#method.states" title="method regex_automata::nfa::thompson::NFA::states"><code>NFA::states</code></a>, and is also a valid argument to
|
|||
|
|
<a href="struct.NFA.html#method.state" title="method regex_automata::nfa::thompson::NFA::state"><code>NFA::state</code></a>.</p>
|
|||
|
|
<h5 id="example-9"><a href="#example-9">Example</a></h5>
|
|||
|
|
<p>This example shows a somewhat contrived example where we can easily
|
|||
|
|
predict the anchored starting state.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::{NFA, State, WhichCaptures};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::compiler()
|
|||
|
|
.configure(NFA::config().which_captures(WhichCaptures::None))
|
|||
|
|
.build(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>state = nfa.state(nfa.start_anchored());
|
|||
|
|
<span class="kw">match </span><span class="kw-2">*</span>state {
|
|||
|
|
State::ByteRange { trans } => {
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="string">b'a'</span>, trans.start);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="string">b'a'</span>, trans.end);
|
|||
|
|
}
|
|||
|
|
<span class="kw">_ </span>=> <span class="macro">unreachable!</span>(<span class="string">"unexpected state"</span>),
|
|||
|
|
}
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.start_unanchored" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#501-503">source</a><h4 class="code-header">pub fn <a href="#method.start_unanchored" class="fn">start_unanchored</a>(&self) -> <a class="struct" href="../../util/primitives/struct.StateID.html" title="struct regex_automata::util::primitives::StateID">StateID</a></h4></section></summary><div class="docblock"><p>Return the state identifier of the initial unanchored state of this
|
|||
|
|
NFA.</p>
|
|||
|
|
<p>This is equivalent to the identifier returned by
|
|||
|
|
<a href="struct.NFA.html#method.start_anchored" title="method regex_automata::nfa::thompson::NFA::start_anchored"><code>NFA::start_anchored</code></a> when the NFA has no unanchored starting state.</p>
|
|||
|
|
<p>The returned identifier is guaranteed to be a valid index into the
|
|||
|
|
slice returned by <a href="struct.NFA.html#method.states" title="method regex_automata::nfa::thompson::NFA::states"><code>NFA::states</code></a>, and is also a valid argument to
|
|||
|
|
<a href="struct.NFA.html#method.state" title="method regex_automata::nfa::thompson::NFA::state"><code>NFA::state</code></a>.</p>
|
|||
|
|
<h5 id="example-10"><a href="#example-10">Example</a></h5>
|
|||
|
|
<p>This example shows that the anchored and unanchored starting states
|
|||
|
|
are equivalent when an anchored NFA is built.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new(<span class="string">"^a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert_eq!</span>(nfa.start_anchored(), nfa.start_unanchored());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.start_pattern" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#545-547">source</a><h4 class="code-header">pub fn <a href="#method.start_pattern" class="fn">start_pattern</a>(&self, pid: <a class="struct" href="../../struct.PatternID.html" title="struct regex_automata::PatternID">PatternID</a>) -> <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/option/enum.Option.html" title="enum core::option::Option">Option</a><<a class="struct" href="../../util/primitives/struct.StateID.html" title="struct regex_automata::util::primitives::StateID">StateID</a>></h4></section></summary><div class="docblock"><p>Return the state identifier of the initial anchored state for the given
|
|||
|
|
pattern, or <code>None</code> if there is no pattern corresponding to the given
|
|||
|
|
identifier.</p>
|
|||
|
|
<p>If one uses the starting state for a particular pattern, then the only
|
|||
|
|
match that can be returned is for the corresponding pattern.</p>
|
|||
|
|
<p>The returned identifier is guaranteed to be a valid index into the
|
|||
|
|
slice returned by <a href="struct.NFA.html#method.states" title="method regex_automata::nfa::thompson::NFA::states"><code>NFA::states</code></a>, and is also a valid argument to
|
|||
|
|
<a href="struct.NFA.html#method.state" title="method regex_automata::nfa::thompson::NFA::state"><code>NFA::state</code></a>.</p>
|
|||
|
|
<h5 id="errors"><a href="#errors">Errors</a></h5>
|
|||
|
|
<p>If the pattern doesn’t exist in this NFA, then this returns an error.
|
|||
|
|
This occurs when <code>pid.as_usize() >= nfa.pattern_len()</code>.</p>
|
|||
|
|
<h5 id="example-11"><a href="#example-11">Example</a></h5>
|
|||
|
|
<p>This example shows that the anchored and unanchored starting states
|
|||
|
|
are equivalent when an anchored NFA is built.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, PatternID};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"^a"</span>, <span class="string">"^b"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="comment">// The anchored and unanchored states for the entire NFA are the same,
|
|||
|
|
// since all of the patterns are anchored.
|
|||
|
|
</span><span class="macro">assert_eq!</span>(nfa.start_anchored(), nfa.start_unanchored());
|
|||
|
|
<span class="comment">// But the anchored starting states for each pattern are distinct,
|
|||
|
|
// because these starting states can only lead to matches for the
|
|||
|
|
// corresponding pattern.
|
|||
|
|
</span><span class="kw">let </span>anchored = <span class="prelude-val">Some</span>(nfa.start_anchored());
|
|||
|
|
<span class="macro">assert_ne!</span>(anchored, nfa.start_pattern(PatternID::must(<span class="number">0</span>)));
|
|||
|
|
<span class="macro">assert_ne!</span>(anchored, nfa.start_pattern(PatternID::must(<span class="number">1</span>)));
|
|||
|
|
<span class="comment">// Requesting a pattern not in the NFA will result in None:
|
|||
|
|
</span><span class="macro">assert_eq!</span>(<span class="prelude-val">None</span>, nfa.start_pattern(PatternID::must(<span class="number">2</span>)));
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.byte_classes" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#598-600">source</a><h4 class="code-header">pub fn <a href="#method.byte_classes" class="fn">byte_classes</a>(&self) -> &<a class="struct" href="../../util/alphabet/struct.ByteClasses.html" title="struct regex_automata::util::alphabet::ByteClasses">ByteClasses</a></h4></section></summary><div class="docblock"><p>Get the byte classes for this NFA.</p>
|
|||
|
|
<p>Byte classes represent a partitioning of this NFA’s alphabet into
|
|||
|
|
equivalence classes. Any two bytes in the same equivalence class are
|
|||
|
|
guaranteed to never discriminate between a match or a non-match. (The
|
|||
|
|
partitioning may not be minimal.)</p>
|
|||
|
|
<p>Byte classes are used internally by this crate when building DFAs.
|
|||
|
|
Namely, among other optimizations, they enable a space optimization
|
|||
|
|
where the DFA’s internal alphabet is defined over the equivalence
|
|||
|
|
classes of bytes instead of all possible byte values. The former is
|
|||
|
|
often quite a bit smaller than the latter, which permits the DFA to use
|
|||
|
|
less space for its transition table.</p>
|
|||
|
|
<h5 id="example-12"><a href="#example-12">Example</a></h5>
|
|||
|
|
<p>This example shows how to query the class of various bytes.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new(<span class="string">"[a-z]+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>classes = nfa.byte_classes();
|
|||
|
|
<span class="comment">// 'a' and 'z' are in the same class for this regex.
|
|||
|
|
</span><span class="macro">assert_eq!</span>(classes.get(<span class="string">b'a'</span>), classes.get(<span class="string">b'z'</span>));
|
|||
|
|
<span class="comment">// But 'a' and 'A' are not.
|
|||
|
|
</span><span class="macro">assert_ne!</span>(classes.get(<span class="string">b'a'</span>), classes.get(<span class="string">b'A'</span>));
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.state" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#632-634">source</a><h4 class="code-header">pub fn <a href="#method.state" class="fn">state</a>(&self, id: <a class="struct" href="../../util/primitives/struct.StateID.html" title="struct regex_automata::util::primitives::StateID">StateID</a>) -> &<a class="enum" href="enum.State.html" title="enum regex_automata::nfa::thompson::State">State</a></h4></section></summary><div class="docblock"><p>Return a reference to the NFA state corresponding to the given ID.</p>
|
|||
|
|
<p>This is a convenience routine for <code>nfa.states()[id]</code>.</p>
|
|||
|
|
<h5 id="panics"><a href="#panics">Panics</a></h5>
|
|||
|
|
<p>This panics when the given identifier does not reference a valid state.
|
|||
|
|
That is, when <code>id.as_usize() >= nfa.states().len()</code>.</p>
|
|||
|
|
<h5 id="example-13"><a href="#example-13">Example</a></h5>
|
|||
|
|
<p>The anchored state for a pattern will typically correspond to a
|
|||
|
|
capturing state for that pattern. (Although, this is not an API
|
|||
|
|
guarantee!)</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::{NFA, State}, PatternID};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>state = nfa.state(nfa.start_pattern(PatternID::ZERO).unwrap());
|
|||
|
|
<span class="kw">match </span><span class="kw-2">*</span>state {
|
|||
|
|
State::Capture { slot, .. } => {
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="number">0</span>, slot.as_usize());
|
|||
|
|
}
|
|||
|
|
<span class="kw">_ </span>=> <span class="macro">unreachable!</span>(<span class="string">"unexpected state"</span>),
|
|||
|
|
}
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.states" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#659-661">source</a><h4 class="code-header">pub fn <a href="#method.states" class="fn">states</a>(&self) -> &[<a class="enum" href="enum.State.html" title="enum regex_automata::nfa::thompson::State">State</a>]</h4></section></summary><div class="docblock"><p>Returns a slice of all states in this NFA.</p>
|
|||
|
|
<p>The slice returned is indexed by <code>StateID</code>. This provides a convenient
|
|||
|
|
way to access states while following transitions among those states.</p>
|
|||
|
|
<h5 id="example-14"><a href="#example-14">Example</a></h5>
|
|||
|
|
<p>This demonstrates that disabling UTF-8 mode can shrink the size of the
|
|||
|
|
NFA considerably in some cases, especially when using Unicode character
|
|||
|
|
classes.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa_unicode = NFA::new(<span class="string">r"\w"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>nfa_ascii = NFA::new(<span class="string">r"(?-u)\w"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="comment">// Yes, a factor of 45 difference. No lie.
|
|||
|
|
</span><span class="macro">assert!</span>(<span class="number">40 </span>* nfa_ascii.states().len() < nfa_unicode.states().len());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.group_info" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#696-698">source</a><h4 class="code-header">pub fn <a href="#method.group_info" class="fn">group_info</a>(&self) -> &<a class="struct" href="../../util/captures/struct.GroupInfo.html" title="struct regex_automata::util::captures::GroupInfo">GroupInfo</a></h4></section></summary><div class="docblock"><p>Returns the capturing group info for this NFA.</p>
|
|||
|
|
<p>The <a href="../../util/captures/struct.GroupInfo.html" title="struct regex_automata::util::captures::GroupInfo"><code>GroupInfo</code></a> provides a way to map to and from capture index
|
|||
|
|
and capture name for each pattern. It also provides a mapping from
|
|||
|
|
each of the capturing groups in every pattern to their corresponding
|
|||
|
|
slot offsets encoded in <a href="enum.State.html#variant.Capture" title="variant regex_automata::nfa::thompson::State::Capture"><code>State::Capture</code></a> states.</p>
|
|||
|
|
<p>Note that <code>GroupInfo</code> uses reference counting internally, such that
|
|||
|
|
cloning a <code>GroupInfo</code> is very cheap.</p>
|
|||
|
|
<h5 id="example-15"><a href="#example-15">Example</a></h5>
|
|||
|
|
<p>This example shows how to get a list of all capture group names for
|
|||
|
|
a particular pattern.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, PatternID};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa = NFA::new(<span class="string">r"(a)(?P<foo>b)(c)(d)(?P<bar>e)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="comment">// The first is the implicit group that is always unnammed. The next
|
|||
|
|
// 5 groups are the explicit groups found in the concrete syntax above.
|
|||
|
|
</span><span class="kw">let </span>expected = <span class="macro">vec!</span>[<span class="prelude-val">None</span>, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(<span class="string">"foo"</span>), <span class="prelude-val">None</span>, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(<span class="string">"bar"</span>)];
|
|||
|
|
<span class="kw">let </span>got: Vec<<span class="prelude-ty">Option</span><<span class="kw-2">&</span>str>> =
|
|||
|
|
nfa.group_info().pattern_names(PatternID::ZERO).collect();
|
|||
|
|
<span class="macro">assert_eq!</span>(expected, got);
|
|||
|
|
|
|||
|
|
<span class="comment">// Using an invalid pattern ID will result in nothing yielded.
|
|||
|
|
</span><span class="kw">let </span>got = nfa.group_info().pattern_names(PatternID::must(<span class="number">999</span>)).count();
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="number">0</span>, got);
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.has_capture" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#743-745">source</a><h4 class="code-header">pub fn <a href="#method.has_capture" class="fn">has_capture</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.bool.html">bool</a></h4></section></summary><div class="docblock"><p>Returns true if and only if this NFA has at least one
|
|||
|
|
<a href="enum.State.html#variant.Capture" title="variant regex_automata::nfa::thompson::State::Capture"><code>Capture</code></a> in its sequence of states.</p>
|
|||
|
|
<p>This is useful as a way to perform a quick test before attempting
|
|||
|
|
something that does or does not require capture states. For example,
|
|||
|
|
some regex engines (like the PikeVM) require capture states in order to
|
|||
|
|
work at all.</p>
|
|||
|
|
<h5 id="example-16"><a href="#example-16">Example</a></h5>
|
|||
|
|
<p>This example shows a few different NFAs and whether they have captures
|
|||
|
|
or not.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::{NFA, WhichCaptures};
|
|||
|
|
|
|||
|
|
<span class="comment">// Obviously has capture states.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"(a)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_capture());
|
|||
|
|
|
|||
|
|
<span class="comment">// Less obviously has capture states, because every pattern has at
|
|||
|
|
// least one anonymous capture group corresponding to the match for the
|
|||
|
|
// entire pattern.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_capture());
|
|||
|
|
|
|||
|
|
<span class="comment">// Other than hand building your own NFA, this is the only way to build
|
|||
|
|
// an NFA without capturing groups. In general, you should only do this
|
|||
|
|
// if you don't intend to use any of the NFA-oriented regex engines.
|
|||
|
|
// Overall, capturing groups don't have many downsides. Although they
|
|||
|
|
// can add a bit of noise to simple NFAs, so it can be nice to disable
|
|||
|
|
// them for debugging purposes.
|
|||
|
|
//
|
|||
|
|
// Notice that 'has_capture' is false here even when we have an
|
|||
|
|
// explicit capture group in the pattern.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::compiler()
|
|||
|
|
.configure(NFA::config().which_captures(WhichCaptures::None))
|
|||
|
|
.build(<span class="string">"(a)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.has_capture());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.has_empty" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#818-820">source</a><h4 class="code-header">pub fn <a href="#method.has_empty" class="fn">has_empty</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.bool.html">bool</a></h4></section></summary><div class="docblock"><p>Returns true if and only if this NFA can match the empty string.
|
|||
|
|
When it returns false, all possible matches are guaranteed to have a
|
|||
|
|
non-zero length.</p>
|
|||
|
|
<p>This is useful as cheap way to know whether code needs to handle the
|
|||
|
|
case of a zero length match. This is particularly important when UTF-8
|
|||
|
|
modes are enabled, as when UTF-8 mode is enabled, empty matches that
|
|||
|
|
split a codepoint must never be reported. This extra handling can
|
|||
|
|
sometimes be costly, and since regexes matching an empty string are
|
|||
|
|
somewhat rare, it can be beneficial to treat such regexes specially.</p>
|
|||
|
|
<h5 id="example-17"><a href="#example-17">Example</a></h5>
|
|||
|
|
<p>This example shows a few different NFAs and whether they match the
|
|||
|
|
empty string or not. Notice the empty string isn’t merely a matter
|
|||
|
|
of a string of length literally <code>0</code>, but rather, whether a match can
|
|||
|
|
occur between specific pairs of bytes.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, util::syntax};
|
|||
|
|
|
|||
|
|
<span class="comment">// The empty regex matches the empty string.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">""</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"empty matches empty"</span>);
|
|||
|
|
<span class="comment">// The '+' repetition operator requires at least one match, and so
|
|||
|
|
// does not match the empty string.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.has_empty(), <span class="string">"+ does not match empty"</span>);
|
|||
|
|
<span class="comment">// But the '*' repetition operator does.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a*"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"* does match empty"</span>);
|
|||
|
|
<span class="comment">// And wrapping '+' in an operator that can match an empty string also
|
|||
|
|
// causes it to match the empty string too.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"(a+)*"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"+ inside of * matches empty"</span>);
|
|||
|
|
|
|||
|
|
<span class="comment">// If a regex is just made of a look-around assertion, even if the
|
|||
|
|
// assertion requires some kind of non-empty string around it (such as
|
|||
|
|
// \b), then it is still treated as if it matches the empty string.
|
|||
|
|
// Namely, if a match occurs of just a look-around assertion, then the
|
|||
|
|
// match returned is empty.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::compiler()
|
|||
|
|
.syntax(syntax::Config::new().utf8(<span class="bool-val">false</span>))
|
|||
|
|
.build(<span class="string">r"^$\A\z\b\B(?-u:\b\B)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"assertions match empty"</span>);
|
|||
|
|
<span class="comment">// Even when an assertion is wrapped in a '+', it still matches the
|
|||
|
|
// empty string.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">r"\b+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"+ of an assertion matches empty"</span>);
|
|||
|
|
|
|||
|
|
<span class="comment">// An alternation with even one branch that can match the empty string
|
|||
|
|
// is also said to match the empty string overall.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"foo|(bar)?|quux"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"alternations can match empty"</span>);
|
|||
|
|
|
|||
|
|
<span class="comment">// An NFA that matches nothing does not match the empty string.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"[a&&b]"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.has_empty(), <span class="string">"never matching means not matching empty"</span>);
|
|||
|
|
<span class="comment">// But if it's wrapped in something that doesn't require a match at
|
|||
|
|
// all, then it can match the empty string!
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"[a&&b]*"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.has_empty(), <span class="string">"* on never-match still matches empty"</span>);
|
|||
|
|
<span class="comment">// Since a '+' requires a match, using it on something that can never
|
|||
|
|
// match will itself produce a regex that can never match anything,
|
|||
|
|
// and thus does not match the empty string.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"[a&&b]+"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.has_empty(), <span class="string">"+ on never-match still matches nothing"</span>);
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.is_utf8" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#882-884">source</a><h4 class="code-header">pub fn <a href="#method.is_utf8" class="fn">is_utf8</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.bool.html">bool</a></h4></section></summary><div class="docblock"><p>Whether UTF-8 mode is enabled for this NFA or not.</p>
|
|||
|
|
<p>When UTF-8 mode is enabled, all matches reported by a regex engine
|
|||
|
|
derived from this NFA are guaranteed to correspond to spans of valid
|
|||
|
|
UTF-8. This includes zero-width matches. For example, the regex engine
|
|||
|
|
must guarantee that the empty regex will not match at the positions
|
|||
|
|
between code units in the UTF-8 encoding of a single codepoint.</p>
|
|||
|
|
<p>See <a href="struct.Config.html#method.utf8" title="method regex_automata::nfa::thompson::Config::utf8"><code>Config::utf8</code></a> for more information.</p>
|
|||
|
|
<p>This is enabled by default.</p>
|
|||
|
|
<h5 id="example-18"><a href="#example-18">Example</a></h5>
|
|||
|
|
<p>This example shows how UTF-8 mode can impact the match spans that may
|
|||
|
|
be reported in certain cases.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{
|
|||
|
|
nfa::thompson::{<span class="self">self</span>, pikevm::PikeVM},
|
|||
|
|
Match, Input,
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::new(<span class="string">""</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>(<span class="kw-2">mut </span>cache, <span class="kw-2">mut </span>caps) = (re.create_cache(), re.create_captures());
|
|||
|
|
|
|||
|
|
<span class="comment">// UTF-8 mode is enabled by default.
|
|||
|
|
</span><span class="kw">let </span><span class="kw-2">mut </span>input = Input::new(<span class="string">"☃"</span>);
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">0</span>..<span class="number">0</span>)), caps.get_match());
|
|||
|
|
|
|||
|
|
<span class="comment">// Even though an empty regex matches at 1..1, our next match is
|
|||
|
|
// 3..3 because 1..1 and 2..2 split the snowman codepoint (which is
|
|||
|
|
// three bytes long).
|
|||
|
|
</span>input.set_start(<span class="number">1</span>);
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">3</span>..<span class="number">3</span>)), caps.get_match());
|
|||
|
|
|
|||
|
|
<span class="comment">// But if we disable UTF-8, then we'll get matches at 1..1 and 2..2:
|
|||
|
|
</span><span class="kw">let </span>re = PikeVM::builder()
|
|||
|
|
.thompson(thompson::Config::new().utf8(<span class="bool-val">false</span>))
|
|||
|
|
.build(<span class="string">""</span>)<span class="question-mark">?</span>;
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">1</span>..<span class="number">1</span>)), caps.get_match());
|
|||
|
|
|
|||
|
|
input.set_start(<span class="number">2</span>);
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">2</span>..<span class="number">2</span>)), caps.get_match());
|
|||
|
|
|
|||
|
|
input.set_start(<span class="number">3</span>);
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">3</span>..<span class="number">3</span>)), caps.get_match());
|
|||
|
|
|
|||
|
|
input.set_start(<span class="number">4</span>);
|
|||
|
|
re.search(<span class="kw-2">&mut </span>cache, <span class="kw-2">&</span>input, <span class="kw-2">&mut </span>caps);
|
|||
|
|
<span class="macro">assert_eq!</span>(<span class="prelude-val">None</span>, caps.get_match());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.is_reverse" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#908-910">source</a><h4 class="code-header">pub fn <a href="#method.is_reverse" class="fn">is_reverse</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.bool.html">bool</a></h4></section></summary><div class="docblock"><p>Returns true when this NFA is meant to be matched in reverse.</p>
|
|||
|
|
<p>Generally speaking, when this is true, it means the NFA is supposed to
|
|||
|
|
be used in conjunction with moving backwards through the haystack. That
|
|||
|
|
is, from a higher memory address to a lower memory address.</p>
|
|||
|
|
<p>It is often the case that lower level routines dealing with an NFA
|
|||
|
|
don’t need to care about whether it is “meant” to be matched in reverse
|
|||
|
|
or not. However, there are some specific cases where it matters. For
|
|||
|
|
example, the implementation of CRLF-aware <code>^</code> and <code>$</code> line anchors
|
|||
|
|
needs to know whether the search is in the forward or reverse
|
|||
|
|
direction. In the forward direction, neither <code>^</code> nor <code>$</code> should match
|
|||
|
|
when a <code>\r</code> has been seen previously and a <code>\n</code> is next. However, in
|
|||
|
|
the reverse direction, neither <code>^</code> nor <code>$</code> should match when a <code>\n</code>
|
|||
|
|
has been seen previously and a <code>\r</code> is next. This fundamentally changes
|
|||
|
|
how the state machine is constructed, and thus needs to be altered
|
|||
|
|
based on the direction of the search.</p>
|
|||
|
|
<p>This is automatically set when using a <a href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler"><code>Compiler</code></a> with a configuration
|
|||
|
|
where <a href="struct.Config.html#method.reverse" title="method regex_automata::nfa::thompson::Config::reverse"><code>Config::reverse</code></a> is enabled. If you’re building your own NFA
|
|||
|
|
by hand via a <a href="struct.Builder.html" title="struct regex_automata::nfa::thompson::Builder"><code>Builder</code></a></p>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.is_always_start_anchored" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#964-966">source</a><h4 class="code-header">pub fn <a href="#method.is_always_start_anchored" class="fn">is_always_start_anchored</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.bool.html">bool</a></h4></section></summary><div class="docblock"><p>Returns true if and only if all starting states for this NFA correspond
|
|||
|
|
to the beginning of an anchored search.</p>
|
|||
|
|
<p>Typically, an NFA will have both an anchored and an unanchored starting
|
|||
|
|
state. Namely, because it tends to be useful to have both and the cost
|
|||
|
|
of having an unanchored starting state is almost zero (for an NFA).
|
|||
|
|
However, if all patterns in the NFA are themselves anchored, then even
|
|||
|
|
the unanchored starting state will correspond to an anchored search
|
|||
|
|
since the pattern doesn’t permit anything else.</p>
|
|||
|
|
<h5 id="example-19"><a href="#example-19">Example</a></h5>
|
|||
|
|
<p>This example shows a few different scenarios where this method’s
|
|||
|
|
return value varies.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="comment">// The unanchored starting state permits matching this pattern anywhere
|
|||
|
|
// in a haystack, instead of just at the beginning.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.is_always_start_anchored());
|
|||
|
|
|
|||
|
|
<span class="comment">// In this case, the pattern is itself anchored, so there is no way
|
|||
|
|
// to run an unanchored search.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"^a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.is_always_start_anchored());
|
|||
|
|
|
|||
|
|
<span class="comment">// When multiline mode is enabled, '^' can match at the start of a line
|
|||
|
|
// in addition to the start of a haystack, so an unanchored search is
|
|||
|
|
// actually possible.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"(?m)^a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.is_always_start_anchored());
|
|||
|
|
|
|||
|
|
<span class="comment">// Weird cases also work. A pattern is only considered anchored if all
|
|||
|
|
// matches may only occur at the start of a haystack.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"(^a)|a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.is_always_start_anchored());
|
|||
|
|
|
|||
|
|
<span class="comment">// When multiple patterns are present, if they are all anchored, then
|
|||
|
|
// the NFA is always anchored too.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"^a"</span>, <span class="string">"^b"</span>, <span class="string">"^c"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.is_always_start_anchored());
|
|||
|
|
|
|||
|
|
<span class="comment">// But if one pattern is unanchored, then the NFA must permit an
|
|||
|
|
// unanchored search.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"^a"</span>, <span class="string">"b"</span>, <span class="string">"^c"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(!nfa.is_always_start_anchored());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.look_matcher" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1013-1015">source</a><h4 class="code-header">pub fn <a href="#method.look_matcher" class="fn">look_matcher</a>(&self) -> &<a class="struct" href="../../util/look/struct.LookMatcher.html" title="struct regex_automata::util::look::LookMatcher">LookMatcher</a></h4></section></summary><div class="docblock"><p>Returns the look-around matcher associated with this NFA.</p>
|
|||
|
|
<p>A look-around matcher determines how to match look-around assertions.
|
|||
|
|
In particular, some assertions are configurable. For example, the
|
|||
|
|
<code>(?m:^)</code> and <code>(?m:$)</code> assertions can have their line terminator changed
|
|||
|
|
from the default of <code>\n</code> to any other byte.</p>
|
|||
|
|
<p>If the NFA was built using a <a href="struct.Compiler.html" title="struct regex_automata::nfa::thompson::Compiler"><code>Compiler</code></a>, then this matcher
|
|||
|
|
can be set via the <a href="struct.Config.html#method.look_matcher" title="method regex_automata::nfa::thompson::Config::look_matcher"><code>Config::look_matcher</code></a> configuration
|
|||
|
|
knob. Otherwise, if you’ve built an NFA by hand, it is set via
|
|||
|
|
<a href="struct.Builder.html#method.set_look_matcher" title="method regex_automata::nfa::thompson::Builder::set_look_matcher"><code>Builder::set_look_matcher</code></a>.</p>
|
|||
|
|
<h5 id="example-20"><a href="#example-20">Example</a></h5>
|
|||
|
|
<p>This shows how to change the line terminator for multi-line assertions.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{
|
|||
|
|
nfa::thompson::{<span class="self">self</span>, pikevm::PikeVM},
|
|||
|
|
util::look::LookMatcher,
|
|||
|
|
Match, Input,
|
|||
|
|
};
|
|||
|
|
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>lookm = LookMatcher::new();
|
|||
|
|
lookm.set_line_terminator(<span class="string">b'\x00'</span>);
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>re = PikeVM::builder()
|
|||
|
|
.thompson(thompson::Config::new().look_matcher(lookm))
|
|||
|
|
.build(<span class="string">r"(?m)^[a-z]+$"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span><span class="kw-2">mut </span>cache = re.create_cache();
|
|||
|
|
|
|||
|
|
<span class="comment">// Multi-line assertions now use NUL as a terminator.
|
|||
|
|
</span><span class="macro">assert_eq!</span>(
|
|||
|
|
<span class="prelude-val">Some</span>(Match::must(<span class="number">0</span>, <span class="number">1</span>..<span class="number">4</span>)),
|
|||
|
|
re.find(<span class="kw-2">&mut </span>cache, <span class="string">b"\x00abc\x00"</span>),
|
|||
|
|
);
|
|||
|
|
<span class="comment">// ... and \n is no longer recognized as a terminator.
|
|||
|
|
</span><span class="macro">assert_eq!</span>(
|
|||
|
|
<span class="prelude-val">None</span>,
|
|||
|
|
re.find(<span class="kw-2">&mut </span>cache, <span class="string">b"\nabc\n"</span>),
|
|||
|
|
);
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.look_set_any" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1059-1061">source</a><h4 class="code-header">pub fn <a href="#method.look_set_any" class="fn">look_set_any</a>(&self) -> <a class="struct" href="../../util/look/struct.LookSet.html" title="struct regex_automata::util::look::LookSet">LookSet</a></h4></section></summary><div class="docblock"><p>Returns the union of all look-around assertions used throughout this
|
|||
|
|
NFA. When the returned set is empty, it implies that the NFA has no
|
|||
|
|
look-around assertions and thus zero conditional epsilon transitions.</p>
|
|||
|
|
<p>This is useful in some cases enabling optimizations. It is not
|
|||
|
|
unusual, for example, for optimizations to be of the form, “for any
|
|||
|
|
regex with zero conditional epsilon transitions, do …” where “…”
|
|||
|
|
is some kind of optimization.</p>
|
|||
|
|
<p>This isn’t only helpful for optimizations either. Sometimes look-around
|
|||
|
|
assertions are difficult to support. For example, many of the DFAs in
|
|||
|
|
this crate don’t support Unicode word boundaries or handle them using
|
|||
|
|
heuristics. Handling that correctly typically requires some kind of
|
|||
|
|
cheap check of whether the NFA has a Unicode word boundary in the first
|
|||
|
|
place.</p>
|
|||
|
|
<h5 id="example-21"><a href="#example-21">Example</a></h5>
|
|||
|
|
<p>This example shows how this routine varies based on the regex pattern:</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, util::look::Look};
|
|||
|
|
|
|||
|
|
<span class="comment">// No look-around at all.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_any().is_empty());
|
|||
|
|
|
|||
|
|
<span class="comment">// When multiple patterns are present, since this returns the union,
|
|||
|
|
// it will include look-around assertions that only appear in one
|
|||
|
|
// pattern.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"a"</span>, <span class="string">"b"</span>, <span class="string">"a^b"</span>, <span class="string">"c"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_any().contains(Look::Start));
|
|||
|
|
|
|||
|
|
<span class="comment">// Some groups of assertions have various shortcuts. For example:
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">r"(?-u:\b)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_any().contains_word());
|
|||
|
|
<span class="macro">assert!</span>(!nfa.look_set_any().contains_word_unicode());
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_any().contains_word_ascii());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.look_set_prefix_any" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1099-1101">source</a><h4 class="code-header">pub fn <a href="#method.look_set_prefix_any" class="fn">look_set_prefix_any</a>(&self) -> <a class="struct" href="../../util/look/struct.LookSet.html" title="struct regex_automata::util::look::LookSet">LookSet</a></h4></section></summary><div class="docblock"><p>Returns the union of all prefix look-around assertions for every
|
|||
|
|
pattern in this NFA. When the returned set is empty, it implies none of
|
|||
|
|
the patterns require moving through a conditional epsilon transition
|
|||
|
|
before inspecting the first byte in the haystack.</p>
|
|||
|
|
<p>This can be useful for determining what kinds of assertions need to be
|
|||
|
|
satisfied at the beginning of a search. For example, typically DFAs
|
|||
|
|
in this crate will build a distinct starting state for each possible
|
|||
|
|
starting configuration that might result in look-around assertions
|
|||
|
|
being satisfied differently. However, if the set returned here is
|
|||
|
|
empty, then you know that the start state is invariant because there
|
|||
|
|
are no conditional epsilon transitions to consider.</p>
|
|||
|
|
<h5 id="example-22"><a href="#example-22">Example</a></h5>
|
|||
|
|
<p>This example shows how this routine varies based on the regex pattern:</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::{nfa::thompson::NFA, util::look::Look};
|
|||
|
|
|
|||
|
|
<span class="comment">// No look-around at all.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new(<span class="string">"a"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_prefix_any().is_empty());
|
|||
|
|
|
|||
|
|
<span class="comment">// When multiple patterns are present, since this returns the union,
|
|||
|
|
// it will include look-around assertions that only appear in one
|
|||
|
|
// pattern. But it will only include assertions that are in the prefix
|
|||
|
|
// of a pattern. For example, this includes '^' but not '$' even though
|
|||
|
|
// '$' does appear.
|
|||
|
|
</span><span class="kw">let </span>nfa = NFA::new_many(<span class="kw-2">&</span>[<span class="string">"a"</span>, <span class="string">"b"</span>, <span class="string">"^ab$"</span>, <span class="string">"c"</span>])<span class="question-mark">?</span>;
|
|||
|
|
<span class="macro">assert!</span>(nfa.look_set_prefix_any().contains(Look::Start));
|
|||
|
|
<span class="macro">assert!</span>(!nfa.look_set_prefix_any().contains(Look::End));
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details><details class="toggle method-toggle" open><summary><section id="method.memory_usage" class="method"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1169-1177">source</a><h4 class="code-header">pub fn <a href="#method.memory_usage" class="fn">memory_usage</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.usize.html">usize</a></h4></section></summary><div class="docblock"><p>Returns the memory usage, in bytes, of this NFA.</p>
|
|||
|
|
<p>This does <strong>not</strong> include the stack size used up by this NFA. To
|
|||
|
|
compute that, use <code>std::mem::size_of::<NFA>()</code>.</p>
|
|||
|
|
<h5 id="example-23"><a href="#example-23">Example</a></h5>
|
|||
|
|
<p>This example shows that large Unicode character classes can use quite
|
|||
|
|
a bit of memory.</p>
|
|||
|
|
|
|||
|
|
<div class="example-wrap"><pre class="rust rust-example-rendered"><code><span class="kw">use </span>regex_automata::nfa::thompson::NFA;
|
|||
|
|
|
|||
|
|
<span class="kw">let </span>nfa_unicode = NFA::new(<span class="string">r"\w"</span>)<span class="question-mark">?</span>;
|
|||
|
|
<span class="kw">let </span>nfa_ascii = NFA::new(<span class="string">r"(?-u:\w)"</span>)<span class="question-mark">?</span>;
|
|||
|
|
|
|||
|
|
<span class="macro">assert!</span>(<span class="number">10 </span>* nfa_ascii.memory_usage() < nfa_unicode.memory_usage());
|
|||
|
|
</code></pre></div>
|
|||
|
|
</div></details></div></details></div><h2 id="trait-implementations" class="section-header">Trait Implementations<a href="#trait-implementations" class="anchor">§</a></h2><div id="trait-implementations-list"><details class="toggle implementors-toggle" open><summary><section id="impl-Clone-for-NFA" class="impl"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#189">source</a><a href="#impl-Clone-for-NFA" class="anchor">§</a><h3 class="code-header">impl <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html" title="trait core::clone::Clone">Clone</a> for <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.clone" class="method trait-impl"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#189">source</a><a href="#method.clone" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html#tymethod.clone" class="fn">clone</a>(&self) -> <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h4></section></summary><div class='docblock'>Returns a copy of the value. <a href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html#tymethod.clone">Read more</a></div></details><details class="toggle method-toggle" open><summary><section id="method.clone_from" class="method trait-impl"><span class="rightside"><span class="since" title="Stable since Rust version 1.0.0">1.0.0</span> · <a class="src" href="https://doc.rust-lang.org/1.76.0/src/core/clone.rs.html#169">source</a></span><a href="#method.clone_from" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html#method.clone_from" class="fn">clone_from</a>(&mut self, source: <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.reference.html">&Self</a>)</h4></section></summary><div class='docblock'>Performs copy-assignment from <code>source</code>. <a href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html#method.clone_from">Read more</a></div></details></div></details><details class="toggle implementors-toggle" open><summary><section id="impl-Debug-for-NFA" class="impl"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1180-1184">source</a><a href="#impl-Debug-for-NFA" class="anchor">§</a><h3 class="code-header">impl <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/fmt/trait.Debug.html" title="trait core::fmt::Debug">Debug</a> for <a class="struct" href="struct.NFA.html" title="struct regex_automata::nfa::thompson::NFA">NFA</a></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.fmt" class="method trait-impl"><a class="src rightside" href="../../../src/regex_automata/nfa/thompson/nfa.rs.html#1181-1183">source</a><a href="#method.fmt" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/fmt/trait.Debug.html#tymethod.fmt" class="fn">fmt</a>(&self, f: &mut <a class="struct" href="https://doc.rust-lang.org/1.76.0/core/fmt/struct.Formatter.html" title="struct core::fmt::Formatter">Formatter</a><'_>) -> <a class="type" href="https://doc.rust-lang.org/1.76.0/core/fmt/type.Result.html" title="type core::fmt::Result">Result</a></h4></section></summary><div class='docblock'>Formats the value using the given formatter. <a href="https://doc.rust-lang.org/1.76.0/core/fmt/trait.Debug.html#tymethod.fmt">Read more</a></div></details></div></details></div><h2 id="synthetic-implementations" class="section-header">Auto Trait Implementations<a href="#synthetic-implementations" class="anchor">§</a></h2><div id="synthetic-implementations-list"><section id="impl-RefUnwindSafe-for-NFA" class="impl"><a href="#impl-RefUnwindSafe-for-NFA" class="anchor">§</a><h3
|
|||
|
|
T: 'static + ?<a class="trait" href="https://doc.rust-lang.org/1.76.0/core/marker/trait.Sized.html" title="trait core::marker::Sized">Sized</a>,</div></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.type_id" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/any.rs.html#141">source</a><a href="#method.type_id" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/any/trait.Any.html#tymethod.type_id" class="fn">type_id</a>(&self) -> <a class="struct" href="https://doc.rust-lang.org/1.76.0/core/any/struct.TypeId.html" title="struct core::any::TypeId">TypeId</a></h4></section></summary><div class='docblock'>Gets the <code>TypeId</code> of <code>self</code>. <a href="https://doc.rust-lang.org/1.76.0/core/any/trait.Any.html#tymethod.type_id">Read more</a></div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-Borrow%3CT%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/borrow.rs.html#208">source</a><a href="#impl-Borrow%3CT%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.Borrow.html" title="trait core::borrow::Borrow">Borrow</a><T> for T<div class="where">where
|
|||
|
|
T: ?<a class="trait" href="https://doc.rust-lang.org/1.76.0/core/marker/trait.Sized.html" title="trait core::marker::Sized">Sized</a>,</div></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.borrow" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/borrow.rs.html#210">source</a><a href="#method.borrow" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.Borrow.html#tymethod.borrow" class="fn">borrow</a>(&self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.reference.html">&T</a></h4></section></summary><div class='docblock'>Immutably borrows from an owned value. <a href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.Borrow.html#tymethod.borrow">Read more</a></div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-BorrowMut%3CT%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/borrow.rs.html#216">source</a><a href="#impl-BorrowMut%3CT%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.BorrowMut.html" title="trait core::borrow::BorrowMut">BorrowMut</a><T> for T<div class="where">where
|
|||
|
|
T: ?<a class="trait" href="https://doc.rust-lang.org/1.76.0/core/marker/trait.Sized.html" title="trait core::marker::Sized">Sized</a>,</div></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.borrow_mut" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/borrow.rs.html#217">source</a><a href="#method.borrow_mut" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.BorrowMut.html#tymethod.borrow_mut" class="fn">borrow_mut</a>(&mut self) -> <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.reference.html">&mut T</a></h4></section></summary><div class='docblock'>Mutably borrows from an owned value. <a href="https://doc.rust-lang.org/1.76.0/core/borrow/trait.BorrowMut.html#tymethod.borrow_mut">Read more</a></div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-From%3CT%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#763">source</a><a href="#impl-From%3CT%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.From.html" title="trait core::convert::From">From</a><T> for T</h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.from" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#766">source</a><a href="#method.from" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.From.html#tymethod.from" class="fn">from</a>(t: T) -> T</h4></section></summary><div class="docblock"><p>Returns the argument unchanged.</p>
|
|||
|
|
</div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-Into%3CU%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#747-749">source</a><a href="#impl-Into%3CU%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T, U> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.Into.html" title="trait core::convert::Into">Into</a><U> for T<div class="where">where
|
|||
|
|
U: <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.From.html" title="trait core::convert::From">From</a><T>,</div></h3></section></summary><div class="impl-items"><details class="toggle method-toggle" open><summary><section id="method.into" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#756">source</a><a href="#method.into" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.Into.html#tymethod.into" class="fn">into</a>(self) -> U</h4></section></summary><div class="docblock"><p>Calls <code>U::from(self)</code>.</p>
|
|||
|
|
<p>That is, this conversion is whatever the implementation of
|
|||
|
|
<code><a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.From.html" title="trait core::convert::From">From</a><T> for U</code> chooses to do.</p>
|
|||
|
|
</div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-ToOwned-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/alloc/borrow.rs.html#83-85">source</a><a href="#impl-ToOwned-for-T" class="anchor">§</a><h3 class="code-header">impl<T> <a class="trait" href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html" title="trait alloc::borrow::ToOwned">ToOwned</a> for T<div class="where">where
|
|||
|
|
T: <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/clone/trait.Clone.html" title="trait core::clone::Clone">Clone</a>,</div></h3></section></summary><div class="impl-items"><details class="toggle" open><summary><section id="associatedtype.Owned" class="associatedtype trait-impl"><a href="#associatedtype.Owned" class="anchor">§</a><h4 class="code-header">type <a href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html#associatedtype.Owned" class="associatedtype">Owned</a> = T</h4></section></summary><div class='docblock'>The resulting type after obtaining ownership.</div></details><details class="toggle method-toggle" open><summary><section id="method.to_owned" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/alloc/borrow.rs.html#88">source</a><a href="#method.to_owned" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html#tymethod.to_owned" class="fn">to_owned</a>(&self) -> T</h4></section></summary><div class='docblock'>Creates owned data from borrowed data, usually by cloning. <a href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html#tymethod.to_owned">Read more</a></div></details><details class="toggle method-toggle" open><summary><section id="method.clone_into" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/alloc/borrow.rs.html#92">source</a><a href="#method.clone_into" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html#method.clone_into" class="fn">clone_into</a>(&self, target: <a class="primitive" href="https://doc.rust-lang.org/1.76.0/std/primitive.reference.html">&mut T</a>)</h4></section></summary><div class='docblock'>Uses borrowed data to replace owned data, usually by cloning. <a href="https://doc.rust-lang.org/1.76.0/alloc/borrow/trait.ToOwned.html#method.clone_into">Read more</a></div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-TryFrom%3CU%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#803-805">source</a><a href="#impl-TryFrom%3CU%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T, U> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html" title="trait core::convert::TryFrom">TryFrom</a><U> for T<div class="where">where
|
|||
|
|
U: <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.Into.html" title="trait core::convert::Into">Into</a><T>,</div></h3></section></summary><div class="impl-items"><details class="toggle" open><summary><section id="associatedtype.Error" class="associatedtype trait-impl"><a href="#associatedtype.Error" class="anchor">§</a><h4 class="code-header">type <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html#associatedtype.Error" class="associatedtype">Error</a> = <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/convert/enum.Infallible.html" title="enum core::convert::Infallible">Infallible</a></h4></section></summary><div class='docblock'>The type returned in the event of a conversion error.</div></details><details class="toggle method-toggle" open><summary><section id="method.try_from" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#810">source</a><a href="#method.try_from" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html#tymethod.try_from" class="fn">try_from</a>(value: U) -> <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/result/enum.Result.html" title="enum core::result::Result">Result</a><T, <T as <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html" title="trait core::convert::TryFrom">TryFrom</a><U>>::<a class="associatedtype" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html#associatedtype.Error" title="type core::convert::TryFrom::Error">Error</a>></h4></section></summary><div class='docblock'>Performs the conversion.</div></details></div></details><details class="toggle implementors-toggle"><summary><section id="impl-TryInto%3CU%3E-for-T" class="impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#788-790">source</a><a href="#impl-TryInto%3CU%3E-for-T" class="anchor">§</a><h3 class="code-header">impl<T, U> <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryInto.html" title="trait core::convert::TryInto">TryInto</a><U> for T<div class="where">where
|
|||
|
|
U: <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html" title="trait core::convert::TryFrom">TryFrom</a><T>,</div></h3></section></summary><div class="impl-items"><details class="toggle" open><summary><section id="associatedtype.Error-1" class="associatedtype trait-impl"><a href="#associatedtype.Error-1" class="anchor">§</a><h4 class="code-header">type <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryInto.html#associatedtype.Error" class="associatedtype">Error</a> = <U as <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html" title="trait core::convert::TryFrom">TryFrom</a><T>>::<a class="associatedtype" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html#associatedtype.Error" title="type core::convert::TryFrom::Error">Error</a></h4></section></summary><div class='docblock'>The type returned in the event of a conversion error.</div></details><details class="toggle method-toggle" open><summary><section id="method.try_into" class="method trait-impl"><a class="src rightside" href="https://doc.rust-lang.org/1.76.0/src/core/convert/mod.rs.html#795">source</a><a href="#method.try_into" class="anchor">§</a><h4 class="code-header">fn <a href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryInto.html#tymethod.try_into" class="fn">try_into</a>(self) -> <a class="enum" href="https://doc.rust-lang.org/1.76.0/core/result/enum.Result.html" title="enum core::result::Result">Result</a><U, <U as <a class="trait" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html" title="trait core::convert::TryFrom">TryFrom</a><T>>::<a class="associatedtype" href="https://doc.rust-lang.org/1.76.0/core/convert/trait.TryFrom.html#associatedtype.Error" title="type core::convert::TryFrom::Error">Error</a>></h4></section></summary><div class='docblock'>Performs the conversion.</div></details></div></details></div><script type="text/json" id="notable-traits-data">{"PatternIter<'_>":"<h3>Notable traits for <code><a class=\"struct\" href=\"struct.PatternIter.html\" title=\"struct regex_automata::nfa::thompson::PatternIter\">PatternIter</a><'a></code></h3><pre><code><div class=\"where\">impl<'a> <a class=\"trait\" href=\"https://doc.rust-lang.org/1.76.0/core/iter/traits/iterator/trait.Iterator.html\" title=\"trait core::iter::traits::iterator::Iterator\">Iterator</a> for <a class=\"struct\" href=\"struct.PatternIter.html\" title=\"struct regex_automata::nfa::thompson::PatternIter\">PatternIter</a><'a></div><div class=\"where\"> type <a href=\"https://doc.rust-lang.org/1.76.0/core/iter/traits/iterator/trait.Iterator.html#associatedtype.Item\" class=\"associatedtype\">Item</a> = <a class=\"struct\" href=\"../../struct.PatternID.html\" title=\"struct regex_automata::PatternID\">PatternID</a>;</div>"}</script></section></div></main></body></html>
|