| <!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/regex-1.8.3/src/pikevm.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>pikevm.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="../../regex/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="../../regex/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> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| </pre><pre class="rust"><code><span class="comment">// This module implements the Pike VM. That is, it guarantees linear time |
| // search of a regex on any text with memory use proportional to the size of |
| // the regex. |
| // |
| // It is equal in power to the backtracking engine in this crate, except the |
| // backtracking engine is typically faster on small regexes/texts at the |
| // expense of a bigger memory footprint. |
| // |
| // It can do more than the DFA can (specifically, record capture locations |
| // and execute Unicode word boundary assertions), but at a slower speed. |
| // Specifically, the Pike VM executes a DFA implicitly by repeatedly expanding |
| // epsilon transitions. That is, the Pike VM engine can be in multiple states |
| // at once where as the DFA is only ever in one state at a time. |
| // |
| // Therefore, the Pike VM is generally treated as the fallback when the other |
| // matching engines either aren't feasible to run or are insufficient. |
| |
| </span><span class="kw">use </span>std::mem; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::exec::ProgramCache; |
| <span class="kw">use </span><span class="kw">crate</span>::input::{Input, InputAt}; |
| <span class="kw">use </span><span class="kw">crate</span>::prog::{InstPtr, Program}; |
| <span class="kw">use </span><span class="kw">crate</span>::re_trait::Slot; |
| <span class="kw">use </span><span class="kw">crate</span>::sparse::SparseSet; |
| |
| <span class="doccomment">/// An NFA simulation matching engine. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>Fsm<<span class="lifetime">'r</span>, I> { |
| <span class="doccomment">/// The sequence of opcodes (among other things) that is actually executed. |
| /// |
| /// The program may be byte oriented or Unicode codepoint oriented. |
| </span>prog: <span class="kw-2">&</span><span class="lifetime">'r </span>Program, |
| <span class="doccomment">/// An explicit stack used for following epsilon transitions. (This is |
| /// borrowed from the cache.) |
| </span>stack: <span class="kw-2">&</span><span class="lifetime">'r </span><span class="kw-2">mut </span>Vec<FollowEpsilon>, |
| <span class="doccomment">/// The input to search. |
| </span>input: I, |
| } |
| |
| <span class="doccomment">/// A cached allocation that can be reused on each execution. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Cache { |
| <span class="doccomment">/// A pair of ordered sets for tracking NFA states. |
| </span>clist: Threads, |
| nlist: Threads, |
| <span class="doccomment">/// An explicit stack used for following epsilon transitions. |
| </span>stack: Vec<FollowEpsilon>, |
| } |
| |
| <span class="doccomment">/// An ordered set of NFA states and their captures. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>Threads { |
| <span class="doccomment">/// An ordered set of opcodes (each opcode is an NFA state). |
| </span>set: SparseSet, |
| <span class="doccomment">/// Captures for every NFA state. |
| /// |
| /// It is stored in row-major order, where the columns are the capture |
| /// slots and the rows are the states. |
| </span>caps: Vec<Slot>, |
| <span class="doccomment">/// The number of capture slots stored per thread. (Every capture has |
| /// two slots.) |
| </span>slots_per_thread: usize, |
| } |
| |
| <span class="doccomment">/// A representation of an explicit stack frame when following epsilon |
| /// transitions. This is used to avoid recursion. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">enum </span>FollowEpsilon { |
| <span class="doccomment">/// Follow transitions at the given instruction pointer. |
| </span>IP(InstPtr), |
| <span class="doccomment">/// Restore the capture slot with the given position in the input. |
| </span>Capture { slot: usize, pos: Slot }, |
| } |
| |
| <span class="kw">impl </span>Cache { |
| <span class="doccomment">/// Create a new allocation used by the NFA machine to record execution |
| /// and captures. |
| </span><span class="kw">pub fn </span>new(_prog: <span class="kw-2">&</span>Program) -> <span class="self">Self </span>{ |
| Cache { clist: Threads::new(), nlist: Threads::new(), stack: <span class="macro">vec!</span>[] } |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'r</span>, I: Input> Fsm<<span class="lifetime">'r</span>, I> { |
| <span class="doccomment">/// Execute the NFA matching engine. |
| /// |
| /// If there's a match, `exec` returns `true` and populates the given |
| /// captures accordingly. |
| </span><span class="kw">pub fn </span>exec( |
| prog: <span class="kw-2">&</span><span class="lifetime">'r </span>Program, |
| cache: <span class="kw-2">&</span>ProgramCache, |
| matches: <span class="kw-2">&mut </span>[bool], |
| slots: <span class="kw-2">&mut </span>[Slot], |
| quit_after_match: bool, |
| input: I, |
| start: usize, |
| end: usize, |
| ) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>cache = cache.borrow_mut(); |
| <span class="kw">let </span>cache = <span class="kw-2">&mut </span>cache.pikevm; |
| cache.clist.resize(prog.len(), prog.captures.len()); |
| cache.nlist.resize(prog.len(), prog.captures.len()); |
| <span class="kw">let </span>at = input.at(start); |
| Fsm { prog, stack: <span class="kw-2">&mut </span>cache.stack, input }.exec_( |
| <span class="kw-2">&mut </span>cache.clist, |
| <span class="kw-2">&mut </span>cache.nlist, |
| matches, |
| slots, |
| quit_after_match, |
| at, |
| end, |
| ) |
| } |
| |
| <span class="kw">fn </span>exec_( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| <span class="kw-2">mut </span>clist: <span class="kw-2">&mut </span>Threads, |
| <span class="kw-2">mut </span>nlist: <span class="kw-2">&mut </span>Threads, |
| matches: <span class="kw-2">&mut </span>[bool], |
| slots: <span class="kw-2">&mut </span>[Slot], |
| quit_after_match: bool, |
| <span class="kw-2">mut </span>at: InputAt, |
| end: usize, |
| ) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>matched = <span class="bool-val">false</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>all_matched = <span class="bool-val">false</span>; |
| clist.set.clear(); |
| nlist.set.clear(); |
| <span class="lifetime">'LOOP</span>: <span class="kw">loop </span>{ |
| <span class="kw">if </span>clist.set.is_empty() { |
| <span class="comment">// Three ways to bail out when our current set of threads is |
| // empty. |
| // |
| // 1. We have a match---so we're done exploring any possible |
| // alternatives. Time to quit. (We can't do this if we're |
| // looking for matches for multiple regexes, unless we know |
| // they all matched.) |
| // |
| // 2. If the expression starts with a '^' we can terminate as |
| // soon as the last thread dies. |
| </span><span class="kw">if </span>(matched && matches.len() <= <span class="number">1</span>) |
| || all_matched |
| || (!at.is_start() && <span class="self">self</span>.prog.is_anchored_start) |
| { |
| <span class="kw">break</span>; |
| } |
| |
| <span class="comment">// 3. If there's a literal prefix for the program, try to |
| // jump ahead quickly. If it can't be found, then we can |
| // bail out early. |
| </span><span class="kw">if </span>!<span class="self">self</span>.prog.prefixes.is_empty() { |
| at = <span class="kw">match </span><span class="self">self</span>.input.prefix_at(<span class="kw-2">&</span><span class="self">self</span>.prog.prefixes, at) { |
| <span class="prelude-val">None </span>=> <span class="kw">break</span>, |
| <span class="prelude-val">Some</span>(at) => at, |
| }; |
| } |
| } |
| |
| <span class="comment">// This simulates a preceding '.*?' for every regex by adding |
| // a state starting at the current position in the input for the |
| // beginning of the program only if we don't already have a match. |
| </span><span class="kw">if </span>clist.set.is_empty() |
| || (!<span class="self">self</span>.prog.is_anchored_start && !all_matched) |
| { |
| <span class="self">self</span>.add(<span class="kw-2">&mut </span>clist, slots, <span class="number">0</span>, at); |
| } |
| <span class="comment">// The previous call to "add" actually inspects the position just |
| // before the current character. For stepping through the machine, |
| // we can to look at the current character, so we advance the |
| // input. |
| </span><span class="kw">let </span>at_next = <span class="self">self</span>.input.at(at.next_pos()); |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..clist.set.len() { |
| <span class="kw">let </span>ip = clist.set[i]; |
| <span class="kw">if </span><span class="self">self</span>.step( |
| <span class="kw-2">&mut </span>nlist, |
| matches, |
| slots, |
| clist.caps(ip), |
| ip, |
| at, |
| at_next, |
| ) { |
| matched = <span class="bool-val">true</span>; |
| all_matched = all_matched || matches.iter().all(|<span class="kw-2">&</span>b| b); |
| <span class="kw">if </span>quit_after_match { |
| <span class="comment">// If we only care if a match occurs (not its |
| // position), then we can quit right now. |
| </span><span class="kw">break </span><span class="lifetime">'LOOP</span>; |
| } |
| <span class="kw">if </span><span class="self">self</span>.prog.matches.len() == <span class="number">1 </span>{ |
| <span class="comment">// We don't need to check the rest of the threads |
| // in this set because we've matched something |
| // ("leftmost-first"). However, we still need to check |
| // threads in the next set to support things like |
| // greedy matching. |
| // |
| // This is only true on normal regexes. For regex sets, |
| // we need to mush on to observe other matches. |
| </span><span class="kw">break</span>; |
| } |
| } |
| } |
| <span class="kw">if </span>at.pos() >= end { |
| <span class="kw">break</span>; |
| } |
| at = at_next; |
| mem::swap(clist, nlist); |
| nlist.set.clear(); |
| } |
| matched |
| } |
| |
| <span class="doccomment">/// Step through the input, one token (byte or codepoint) at a time. |
| /// |
| /// nlist is the set of states that will be processed on the next token |
| /// in the input. |
| /// |
| /// caps is the set of captures passed by the caller of the NFA. They are |
| /// written to only when a match state is visited. |
| /// |
| /// thread_caps is the set of captures set for the current NFA state, ip. |
| /// |
| /// at and at_next are the current and next positions in the input. at or |
| /// at_next may be EOF. |
| </span><span class="kw">fn </span>step( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| nlist: <span class="kw-2">&mut </span>Threads, |
| matches: <span class="kw-2">&mut </span>[bool], |
| slots: <span class="kw-2">&mut </span>[Slot], |
| thread_caps: <span class="kw-2">&mut </span>[<span class="prelude-ty">Option</span><usize>], |
| ip: usize, |
| at: InputAt, |
| at_next: InputAt, |
| ) -> bool { |
| <span class="kw">use </span><span class="kw">crate</span>::prog::Inst::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="self">self</span>.prog[ip] { |
| Match(match_slot) => { |
| <span class="kw">if </span>match_slot < matches.len() { |
| matches[match_slot] = <span class="bool-val">true</span>; |
| } |
| <span class="kw">for </span>(slot, val) <span class="kw">in </span>slots.iter_mut().zip(thread_caps.iter()) { |
| <span class="kw-2">*</span>slot = <span class="kw-2">*</span>val; |
| } |
| <span class="bool-val">true |
| </span>} |
| Char(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">if </span>inst.c == at.char() { |
| <span class="self">self</span>.add(nlist, thread_caps, inst.goto, at_next); |
| } |
| <span class="bool-val">false |
| </span>} |
| Ranges(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">if </span>inst.matches(at.char()) { |
| <span class="self">self</span>.add(nlist, thread_caps, inst.goto, at_next); |
| } |
| <span class="bool-val">false |
| </span>} |
| Bytes(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(b) = at.byte() { |
| <span class="kw">if </span>inst.matches(b) { |
| <span class="self">self</span>.add(nlist, thread_caps, inst.goto, at_next); |
| } |
| } |
| <span class="bool-val">false |
| </span>} |
| EmptyLook(<span class="kw">_</span>) | Save(<span class="kw">_</span>) | Split(<span class="kw">_</span>) => <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Follows epsilon transitions and adds them for processing to nlist, |
| /// starting at and including ip. |
| </span><span class="kw">fn </span>add( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| nlist: <span class="kw-2">&mut </span>Threads, |
| thread_caps: <span class="kw-2">&mut </span>[<span class="prelude-ty">Option</span><usize>], |
| ip: usize, |
| at: InputAt, |
| ) { |
| <span class="self">self</span>.stack.push(FollowEpsilon::IP(ip)); |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(frame) = <span class="self">self</span>.stack.pop() { |
| <span class="kw">match </span>frame { |
| FollowEpsilon::IP(ip) => { |
| <span class="self">self</span>.add_step(nlist, thread_caps, ip, at); |
| } |
| FollowEpsilon::Capture { slot, pos } => { |
| thread_caps[slot] = pos; |
| } |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A helper function for add that avoids excessive pushing to the stack. |
| </span><span class="kw">fn </span>add_step( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| nlist: <span class="kw-2">&mut </span>Threads, |
| thread_caps: <span class="kw-2">&mut </span>[<span class="prelude-ty">Option</span><usize>], |
| <span class="kw-2">mut </span>ip: usize, |
| at: InputAt, |
| ) { |
| <span class="comment">// Instead of pushing and popping to the stack, we mutate ip as we |
| // traverse the set of states. We only push to the stack when we |
| // absolutely need recursion (restoring captures or following a |
| // branch). |
| </span><span class="kw">use </span><span class="kw">crate</span>::prog::Inst::<span class="kw-2">*</span>; |
| <span class="kw">loop </span>{ |
| <span class="comment">// Don't visit states we've already added. |
| </span><span class="kw">if </span>nlist.set.contains(ip) { |
| <span class="kw">return</span>; |
| } |
| nlist.set.insert(ip); |
| <span class="kw">match </span><span class="self">self</span>.prog[ip] { |
| EmptyLook(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">if </span><span class="self">self</span>.input.is_empty_match(at, inst) { |
| ip = inst.goto; |
| } |
| } |
| Save(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">if </span>inst.slot < thread_caps.len() { |
| <span class="self">self</span>.stack.push(FollowEpsilon::Capture { |
| slot: inst.slot, |
| pos: thread_caps[inst.slot], |
| }); |
| thread_caps[inst.slot] = <span class="prelude-val">Some</span>(at.pos()); |
| } |
| ip = inst.goto; |
| } |
| Split(<span class="kw-2">ref </span>inst) => { |
| <span class="self">self</span>.stack.push(FollowEpsilon::IP(inst.goto2)); |
| ip = inst.goto1; |
| } |
| Match(<span class="kw">_</span>) | Char(<span class="kw">_</span>) | Ranges(<span class="kw">_</span>) | Bytes(<span class="kw">_</span>) => { |
| <span class="kw">let </span>t = <span class="kw-2">&mut </span>nlist.caps(ip); |
| <span class="kw">for </span>(slot, val) <span class="kw">in </span>t.iter_mut().zip(thread_caps.iter()) { |
| <span class="kw-2">*</span>slot = <span class="kw-2">*</span>val; |
| } |
| <span class="kw">return</span>; |
| } |
| } |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Threads { |
| <span class="kw">fn </span>new() -> <span class="self">Self </span>{ |
| Threads { set: SparseSet::new(<span class="number">0</span>), caps: <span class="macro">vec!</span>[], slots_per_thread: <span class="number">0 </span>} |
| } |
| |
| <span class="kw">fn </span>resize(<span class="kw-2">&mut </span><span class="self">self</span>, num_insts: usize, ncaps: usize) { |
| <span class="kw">if </span>num_insts == <span class="self">self</span>.set.capacity() { |
| <span class="kw">return</span>; |
| } |
| <span class="self">self</span>.slots_per_thread = ncaps * <span class="number">2</span>; |
| <span class="self">self</span>.set = SparseSet::new(num_insts); |
| <span class="self">self</span>.caps = <span class="macro">vec!</span>[<span class="prelude-val">None</span>; <span class="self">self</span>.slots_per_thread * num_insts]; |
| } |
| |
| <span class="kw">fn </span>caps(<span class="kw-2">&mut </span><span class="self">self</span>, pc: usize) -> <span class="kw-2">&mut </span>[<span class="prelude-ty">Option</span><usize>] { |
| <span class="kw">let </span>i = pc * <span class="self">self</span>.slots_per_thread; |
| <span class="kw-2">&mut </span><span class="self">self</span>.caps[i..i + <span class="self">self</span>.slots_per_thread] |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |