blob: 1680f625cbcb3a35018c9d40596e7be1963fe766 [file] [log] [blame]
<!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="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/tantivy-fst-0.4.0/src/regex/dfa.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>dfa.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../tantivy_fst/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy_fst/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span>
<span id="2">2</span>
<span id="3">3</span>
<span id="4">4</span>
<span id="5">5</span>
<span id="6">6</span>
<span id="7">7</span>
<span id="8">8</span>
<span id="9">9</span>
<span id="10">10</span>
<span id="11">11</span>
<span id="12">12</span>
<span id="13">13</span>
<span id="14">14</span>
<span id="15">15</span>
<span id="16">16</span>
<span id="17">17</span>
<span id="18">18</span>
<span id="19">19</span>
<span id="20">20</span>
<span id="21">21</span>
<span id="22">22</span>
<span id="23">23</span>
<span id="24">24</span>
<span id="25">25</span>
<span id="26">26</span>
<span id="27">27</span>
<span id="28">28</span>
<span id="29">29</span>
<span id="30">30</span>
<span id="31">31</span>
<span id="32">32</span>
<span id="33">33</span>
<span id="34">34</span>
<span id="35">35</span>
<span id="36">36</span>
<span id="37">37</span>
<span id="38">38</span>
<span id="39">39</span>
<span id="40">40</span>
<span id="41">41</span>
<span id="42">42</span>
<span id="43">43</span>
<span id="44">44</span>
<span id="45">45</span>
<span id="46">46</span>
<span id="47">47</span>
<span id="48">48</span>
<span id="49">49</span>
<span id="50">50</span>
<span id="51">51</span>
<span id="52">52</span>
<span id="53">53</span>
<span id="54">54</span>
<span id="55">55</span>
<span id="56">56</span>
<span id="57">57</span>
<span id="58">58</span>
<span id="59">59</span>
<span id="60">60</span>
<span id="61">61</span>
<span id="62">62</span>
<span id="63">63</span>
<span id="64">64</span>
<span id="65">65</span>
<span id="66">66</span>
<span id="67">67</span>
<span id="68">68</span>
<span id="69">69</span>
<span id="70">70</span>
<span id="71">71</span>
<span id="72">72</span>
<span id="73">73</span>
<span id="74">74</span>
<span id="75">75</span>
<span id="76">76</span>
<span id="77">77</span>
<span id="78">78</span>
<span id="79">79</span>
<span id="80">80</span>
<span id="81">81</span>
<span id="82">82</span>
<span id="83">83</span>
<span id="84">84</span>
<span id="85">85</span>
<span id="86">86</span>
<span id="87">87</span>
<span id="88">88</span>
<span id="89">89</span>
<span id="90">90</span>
<span id="91">91</span>
<span id="92">92</span>
<span id="93">93</span>
<span id="94">94</span>
<span id="95">95</span>
<span id="96">96</span>
<span id="97">97</span>
<span id="98">98</span>
<span id="99">99</span>
<span id="100">100</span>
<span id="101">101</span>
<span id="102">102</span>
<span id="103">103</span>
<span id="104">104</span>
<span id="105">105</span>
<span id="106">106</span>
<span id="107">107</span>
<span id="108">108</span>
<span id="109">109</span>
<span id="110">110</span>
<span id="111">111</span>
<span id="112">112</span>
<span id="113">113</span>
<span id="114">114</span>
<span id="115">115</span>
<span id="116">116</span>
<span id="117">117</span>
<span id="118">118</span>
<span id="119">119</span>
<span id="120">120</span>
<span id="121">121</span>
<span id="122">122</span>
<span id="123">123</span>
<span id="124">124</span>
<span id="125">125</span>
<span id="126">126</span>
<span id="127">127</span>
<span id="128">128</span>
<span id="129">129</span>
<span id="130">130</span>
<span id="131">131</span>
<span id="132">132</span>
<span id="133">133</span>
<span id="134">134</span>
<span id="135">135</span>
<span id="136">136</span>
<span id="137">137</span>
<span id="138">138</span>
<span id="139">139</span>
<span id="140">140</span>
<span id="141">141</span>
<span id="142">142</span>
<span id="143">143</span>
<span id="144">144</span>
<span id="145">145</span>
<span id="146">146</span>
<span id="147">147</span>
<span id="148">148</span>
<span id="149">149</span>
<span id="150">150</span>
<span id="151">151</span>
<span id="152">152</span>
<span id="153">153</span>
<span id="154">154</span>
<span id="155">155</span>
<span id="156">156</span>
<span id="157">157</span>
<span id="158">158</span>
<span id="159">159</span>
<span id="160">160</span>
<span id="161">161</span>
<span id="162">162</span>
<span id="163">163</span>
<span id="164">164</span>
<span id="165">165</span>
<span id="166">166</span>
<span id="167">167</span>
<span id="168">168</span>
<span id="169">169</span>
<span id="170">170</span>
<span id="171">171</span>
<span id="172">172</span>
<span id="173">173</span>
<span id="174">174</span>
<span id="175">175</span>
<span id="176">176</span>
<span id="177">177</span>
<span id="178">178</span>
<span id="179">179</span>
<span id="180">180</span>
</pre><pre class="rust"><code><span class="kw">use </span>std::collections::{HashMap, HashSet};
<span class="kw">use </span>std::fmt;
<span class="kw">use </span><span class="kw">super</span>::sparse::SparseSet;
<span class="kw">use </span><span class="kw">super</span>::Error;
<span class="kw">use </span><span class="kw">super</span>::Inst;
<span class="kw">const </span>STATE_LIMIT: usize = <span class="number">1_000</span>; <span class="comment">// currently at least 2MB &gt;_&lt;
</span><span class="kw">pub struct </span>DfaBuilder {
dfa: Dfa,
cache: HashMap&lt;Vec&lt;usize&gt;, usize&gt;,
}
<span class="kw">pub struct </span>Dfa {
insts: Vec&lt;Inst&gt;,
states: Vec&lt;State&gt;,
}
<span class="kw">struct </span>State {
insts: Vec&lt;usize&gt;,
next: [<span class="prelude-ty">Option</span>&lt;usize&gt;; <span class="number">256</span>],
is_match: bool,
}
<span class="kw">impl </span>DfaBuilder {
<span class="kw">pub fn </span>new(insts: Vec&lt;Inst&gt;) -&gt; <span class="self">Self </span>{
DfaBuilder {
dfa: Dfa {
insts,
states: Vec::with_capacity(<span class="number">16</span>),
},
cache: HashMap::with_capacity(<span class="number">1024</span>),
}
}
<span class="kw">pub fn </span>build(<span class="kw-2">mut </span><span class="self">self</span>) -&gt; <span class="prelude-ty">Result</span>&lt;Dfa, Error&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>cur = SparseSet::new(<span class="self">self</span>.dfa.insts.len());
<span class="kw">let </span><span class="kw-2">mut </span>next = SparseSet::new(<span class="self">self</span>.dfa.insts.len());
<span class="self">self</span>.dfa.add(<span class="kw-2">&amp;mut </span>cur, <span class="number">0</span>);
<span class="kw">let </span><span class="kw-2">mut </span>states = <span class="macro">vec!</span>[<span class="self">self</span>.cached_state(<span class="kw-2">&amp;</span>cur).unwrap()];
<span class="kw">let </span><span class="kw-2">mut </span>seen = HashSet::new();
<span class="kw">while let </span><span class="prelude-val">Some</span>(s) = states.pop() {
<span class="kw">for </span>b <span class="kw">in </span><span class="number">0</span>..<span class="number">256 </span>{
<span class="kw">let </span>ns = <span class="self">self</span>.run_state(<span class="kw-2">&amp;mut </span>cur, <span class="kw-2">&amp;mut </span>next, s, b <span class="kw">as </span>u8);
<span class="kw">if let </span><span class="prelude-val">Some</span>(ns) = ns {
<span class="kw">if </span>!seen.contains(<span class="kw-2">&amp;</span>ns) {
seen.insert(ns);
states.push(ns);
}
}
<span class="kw">if </span><span class="self">self</span>.dfa.states.len() &gt; STATE_LIMIT {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::TooManyStates(STATE_LIMIT));
}
}
}
<span class="prelude-val">Ok</span>(<span class="self">self</span>.dfa)
}
<span class="kw">fn </span>run_state(
<span class="kw-2">&amp;mut </span><span class="self">self</span>,
cur: <span class="kw-2">&amp;mut </span>SparseSet,
next: <span class="kw-2">&amp;mut </span>SparseSet,
state: usize,
byte: u8,
) -&gt; <span class="prelude-ty">Option</span>&lt;usize&gt; {
cur.clear();
<span class="kw">for </span><span class="kw-2">&amp;</span>ip <span class="kw">in </span><span class="kw-2">&amp;</span><span class="self">self</span>.dfa.states[state].insts {
cur.add(ip);
}
<span class="self">self</span>.dfa.run(cur, next, byte);
<span class="kw">let </span>next_state = <span class="self">self</span>.cached_state(next);
<span class="self">self</span>.dfa.states[state].next[byte <span class="kw">as </span>usize] = next_state;
next_state
}
<span class="kw">fn </span>cached_state(<span class="kw-2">&amp;mut </span><span class="self">self</span>, set: <span class="kw-2">&amp;</span>SparseSet) -&gt; <span class="prelude-ty">Option</span>&lt;usize&gt; {
<span class="kw">use </span><span class="kw">super</span>::Inst::<span class="kw-2">*</span>;
<span class="kw">use </span>std::collections::hash_map::Entry;
<span class="comment">// There are probably many ways to optimize this routine. ---AG
</span><span class="kw">let </span><span class="kw-2">mut </span>insts = <span class="macro">vec!</span>[];
<span class="kw">let </span><span class="kw-2">mut </span>is_match = <span class="bool-val">false</span>;
<span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..set.len() {
<span class="kw">let </span>ip = set.get(i);
<span class="kw">match </span><span class="self">self</span>.dfa.insts[ip] {
Jump(<span class="kw">_</span>) | Split(<span class="kw">_</span>, <span class="kw">_</span>) =&gt; {}
Range(<span class="kw">_</span>, <span class="kw">_</span>) =&gt; insts.push(ip),
Match =&gt; {
is_match = <span class="bool-val">true</span>;
insts.push(ip);
}
}
}
<span class="kw">if </span>insts.is_empty() {
<span class="kw">return </span><span class="prelude-val">None</span>;
}
<span class="prelude-val">Some</span>(<span class="kw">match </span><span class="self">self</span>.cache.entry(insts.clone()) {
Entry::Occupied(v) =&gt; <span class="kw-2">*</span>v.get(),
Entry::Vacant(v) =&gt; {
<span class="self">self</span>.dfa.states.push(State {
insts,
next: [<span class="prelude-val">None</span>; <span class="number">256</span>],
is_match,
});
<span class="kw-2">*</span>v.insert(<span class="self">self</span>.dfa.states.len() - <span class="number">1</span>)
}
})
}
}
<span class="kw">impl </span>Dfa {
<span class="kw">pub fn </span>is_match(<span class="kw-2">&amp;</span><span class="self">self</span>, si: usize) -&gt; bool {
<span class="self">self</span>.states[si].is_match
}
<span class="kw">pub fn </span>accept(<span class="kw-2">&amp;</span><span class="self">self</span>, si: usize, byte: u8) -&gt; <span class="prelude-ty">Option</span>&lt;usize&gt; {
<span class="self">self</span>.states[si].next[byte <span class="kw">as </span>usize]
}
<span class="kw">fn </span>add(<span class="kw-2">&amp;</span><span class="self">self</span>, set: <span class="kw-2">&amp;mut </span>SparseSet, ip: usize) {
<span class="kw">use </span><span class="kw">super</span>::Inst::<span class="kw-2">*</span>;
<span class="kw">if </span>set.contains(ip) {
<span class="kw">return</span>;
}
set.add(ip);
<span class="kw">match </span><span class="self">self</span>.insts[ip] {
Match | Range(<span class="kw">_</span>, <span class="kw">_</span>) =&gt; {}
Jump(ip) =&gt; <span class="self">self</span>.add(set, ip),
Split(ip1, ip2) =&gt; {
<span class="self">self</span>.add(set, ip1);
<span class="self">self</span>.add(set, ip2);
}
}
}
<span class="kw">fn </span>run(<span class="kw-2">&amp;</span><span class="self">self</span>, from: <span class="kw-2">&amp;</span>SparseSet, to: <span class="kw-2">&amp;mut </span>SparseSet, byte: u8) -&gt; bool {
<span class="kw">use </span><span class="kw">super</span>::Inst::<span class="kw-2">*</span>;
to.clear();
<span class="kw">let </span><span class="kw-2">mut </span>is_match = <span class="bool-val">false</span>;
<span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..from.len() {
<span class="kw">let </span>ip = from.get(i);
<span class="kw">match </span><span class="self">self</span>.insts[ip] {
Jump(<span class="kw">_</span>) | Split(<span class="kw">_</span>, <span class="kw">_</span>) =&gt; {}
Match =&gt; is_match = <span class="bool-val">true</span>,
Range(s, e) =&gt; {
<span class="kw">if </span>s &lt;= byte &amp;&amp; byte &lt;= e {
<span class="self">self</span>.add(to, ip + <span class="number">1</span>);
}
}
}
}
is_match
}
}
<span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Dfa {
<span class="kw">fn </span>fmt(<span class="kw-2">&amp;</span><span class="self">self</span>, f: <span class="kw-2">&amp;mut </span>fmt::Formatter) -&gt; fmt::Result {
<span class="kw">for </span>(i, inst) <span class="kw">in </span><span class="self">self</span>.insts.iter().enumerate() {
<span class="macro">writeln!</span>(f, <span class="string">&quot;{:03} {:?}&quot;</span>, i, inst)<span class="question-mark">?</span>;
}
<span class="macro">writeln!</span>(f, <span class="string">&quot;------------&quot;</span>)<span class="question-mark">?</span>;
<span class="kw">for </span>(i, state) <span class="kw">in </span><span class="self">self</span>.states.iter().enumerate() {
<span class="kw">if </span>state.is_match {
<span class="macro">writeln!</span>(f, <span class="string">&quot;{:03}* {:?}&quot;</span>, i, state.insts)<span class="question-mark">?</span>;
} <span class="kw">else </span>{
<span class="macro">writeln!</span>(f, <span class="string">&quot;{:03} {:?}&quot;</span>, i, state.insts)<span class="question-mark">?</span>;
}
<span class="kw">for </span>j <span class="kw">in </span><span class="number">0</span>..<span class="number">256 </span>{
<span class="kw">if let </span><span class="prelude-val">Some</span>(si) = state.next[j] {
<span class="macro">writeln!</span>(f, <span class="string">&quot;{:03} {:X} =&gt; {}&quot;</span>, i, j, si)<span class="question-mark">?</span>;
}
}
}
<span class="prelude-val">Ok</span>(())
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy_fst" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>