| <!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/literal/imp.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>imp.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> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::mem; |
| |
| <span class="kw">use </span>aho_corasick::{<span class="self">self</span>, packed, AhoCorasick}; |
| <span class="kw">use </span>memchr::{memchr, memchr2, memchr3, memmem}; |
| <span class="kw">use </span>regex_syntax::hir::literal::{Literal, Seq}; |
| |
| <span class="doccomment">/// A prefix extracted from a compiled regular expression. |
| /// |
| /// A regex prefix is a set of literal strings that *must* be matched at the |
| /// beginning of a regex in order for the entire regex to match. Similarly |
| /// for a regex suffix. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>LiteralSearcher { |
| complete: bool, |
| lcp: Memmem, |
| lcs: Memmem, |
| matcher: Matcher, |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">enum </span>Matcher { |
| <span class="doccomment">/// No literals. (Never advances through the input.) |
| </span>Empty, |
| <span class="doccomment">/// A set of four or more single byte literals. |
| </span>Bytes(SingleByteSet), |
| <span class="doccomment">/// A single substring, using vector accelerated routines when available. |
| </span>Memmem(Memmem), |
| <span class="doccomment">/// An Aho-Corasick automaton. |
| </span>AC { ac: AhoCorasick, lits: Vec<Literal> }, |
| <span class="doccomment">/// A packed multiple substring searcher, using SIMD. |
| /// |
| /// Note that Aho-Corasick will actually use this packed searcher |
| /// internally automatically, however, there is some overhead associated |
| /// with going through the Aho-Corasick machinery. So using the packed |
| /// searcher directly results in some gains. |
| </span>Packed { s: packed::Searcher, lits: Vec<Literal> }, |
| } |
| |
| <span class="kw">impl </span>LiteralSearcher { |
| <span class="doccomment">/// Returns a matcher that never matches and never advances the input. |
| </span><span class="kw">pub fn </span>empty() -> <span class="self">Self </span>{ |
| <span class="self">Self</span>::new(Seq::infinite(), Matcher::Empty) |
| } |
| |
| <span class="doccomment">/// Returns a matcher for literal prefixes from the given set. |
| </span><span class="kw">pub fn </span>prefixes(lits: Seq) -> <span class="self">Self </span>{ |
| <span class="kw">let </span>matcher = Matcher::prefixes(<span class="kw-2">&</span>lits); |
| <span class="self">Self</span>::new(lits, matcher) |
| } |
| |
| <span class="doccomment">/// Returns a matcher for literal suffixes from the given set. |
| </span><span class="kw">pub fn </span>suffixes(lits: Seq) -> <span class="self">Self </span>{ |
| <span class="kw">let </span>matcher = Matcher::suffixes(<span class="kw-2">&</span>lits); |
| <span class="self">Self</span>::new(lits, matcher) |
| } |
| |
| <span class="kw">fn </span>new(lits: Seq, matcher: Matcher) -> <span class="self">Self </span>{ |
| LiteralSearcher { |
| complete: lits.is_exact(), |
| lcp: Memmem::new(lits.longest_common_prefix().unwrap_or(<span class="string">b""</span>)), |
| lcs: Memmem::new(lits.longest_common_suffix().unwrap_or(<span class="string">b""</span>)), |
| matcher, |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if all matches comprise the entire regular expression. |
| /// |
| /// This does not necessarily mean that a literal match implies a match |
| /// of the regular expression. For example, the regular expression `^a` |
| /// is comprised of a single complete literal `a`, but the regular |
| /// expression demands that it only match at the beginning of a string. |
| </span><span class="kw">pub fn </span>complete(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.complete && !<span class="self">self</span>.is_empty() |
| } |
| |
| <span class="doccomment">/// Find the position of a literal in `haystack` if it exists. |
| </span><span class="attribute">#[cfg_attr(feature = <span class="string">"perf-inline"</span>, inline(always))] |
| </span><span class="kw">pub fn </span>find(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><(usize, usize)> { |
| <span class="kw">use </span><span class="self">self</span>::Matcher::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="self">self</span>.matcher { |
| Empty => <span class="prelude-val">Some</span>((<span class="number">0</span>, <span class="number">0</span>)), |
| Bytes(<span class="kw-2">ref </span>sset) => sset.find(haystack).map(|i| (i, i + <span class="number">1</span>)), |
| Memmem(<span class="kw-2">ref </span>s) => s.find(haystack).map(|i| (i, i + s.len())), |
| AC { <span class="kw-2">ref </span>ac, .. } => { |
| ac.find(haystack).map(|m| (m.start(), m.end())) |
| } |
| Packed { <span class="kw-2">ref </span>s, .. } => { |
| s.find(haystack).map(|m| (m.start(), m.end())) |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Like find, except matches must start at index `0`. |
| </span><span class="kw">pub fn </span>find_start(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><(usize, usize)> { |
| <span class="kw">for </span>lit <span class="kw">in </span><span class="self">self</span>.iter() { |
| <span class="kw">if </span>lit.len() > haystack.len() { |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">if </span>lit == <span class="kw-2">&</span>haystack[<span class="number">0</span>..lit.len()] { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0</span>, lit.len())); |
| } |
| } |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="doccomment">/// Like find, except matches must end at index `haystack.len()`. |
| </span><span class="kw">pub fn </span>find_end(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><(usize, usize)> { |
| <span class="kw">for </span>lit <span class="kw">in </span><span class="self">self</span>.iter() { |
| <span class="kw">if </span>lit.len() > haystack.len() { |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">if </span>lit == <span class="kw-2">&</span>haystack[haystack.len() - lit.len()..] { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((haystack.len() - lit.len(), haystack.len())); |
| } |
| } |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="doccomment">/// Returns an iterator over all literals to be matched. |
| </span><span class="kw">pub fn </span>iter(<span class="kw-2">&</span><span class="self">self</span>) -> LiteralIter<<span class="lifetime">'_</span>> { |
| <span class="kw">match </span><span class="self">self</span>.matcher { |
| Matcher::Empty => LiteralIter::Empty, |
| Matcher::Bytes(<span class="kw-2">ref </span>sset) => LiteralIter::Bytes(<span class="kw-2">&</span>sset.dense), |
| Matcher::Memmem(<span class="kw-2">ref </span>s) => LiteralIter::Single(<span class="kw-2">&</span>s.finder.needle()), |
| Matcher::AC { <span class="kw-2">ref </span>lits, .. } => LiteralIter::AC(lits), |
| Matcher::Packed { <span class="kw-2">ref </span>lits, .. } => LiteralIter::Packed(lits), |
| } |
| } |
| |
| <span class="doccomment">/// Returns a matcher for the longest common prefix of this matcher. |
| </span><span class="kw">pub fn </span>lcp(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>Memmem { |
| <span class="kw-2">&</span><span class="self">self</span>.lcp |
| } |
| |
| <span class="doccomment">/// Returns a matcher for the longest common suffix of this matcher. |
| </span><span class="kw">pub fn </span>lcs(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>Memmem { |
| <span class="kw-2">&</span><span class="self">self</span>.lcs |
| } |
| |
| <span class="doccomment">/// Returns true iff this prefix is empty. |
| </span><span class="kw">pub fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.len() == <span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Returns the number of prefixes in this machine. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="kw">use </span><span class="self">self</span>::Matcher::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="self">self</span>.matcher { |
| Empty => <span class="number">0</span>, |
| Bytes(<span class="kw-2">ref </span>sset) => sset.dense.len(), |
| Memmem(<span class="kw">_</span>) => <span class="number">1</span>, |
| AC { <span class="kw-2">ref </span>ac, .. } => ac.patterns_len(), |
| Packed { <span class="kw-2">ref </span>lits, .. } => lits.len(), |
| } |
| } |
| |
| <span class="doccomment">/// Return the approximate heap usage of literals in bytes. |
| </span><span class="kw">pub fn </span>approximate_size(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="kw">use </span><span class="self">self</span>::Matcher::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="self">self</span>.matcher { |
| Empty => <span class="number">0</span>, |
| Bytes(<span class="kw-2">ref </span>sset) => sset.approximate_size(), |
| Memmem(<span class="kw-2">ref </span>single) => single.approximate_size(), |
| AC { <span class="kw-2">ref </span>ac, .. } => ac.memory_usage(), |
| Packed { <span class="kw-2">ref </span>s, .. } => s.memory_usage(), |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Matcher { |
| <span class="kw">fn </span>prefixes(lits: <span class="kw-2">&</span>Seq) -> <span class="self">Self </span>{ |
| <span class="kw">let </span>sset = SingleByteSet::prefixes(lits); |
| Matcher::new(lits, sset) |
| } |
| |
| <span class="kw">fn </span>suffixes(lits: <span class="kw-2">&</span>Seq) -> <span class="self">Self </span>{ |
| <span class="kw">let </span>sset = SingleByteSet::suffixes(lits); |
| Matcher::new(lits, sset) |
| } |
| |
| <span class="kw">fn </span>new(lits: <span class="kw-2">&</span>Seq, sset: SingleByteSet) -> <span class="self">Self </span>{ |
| <span class="kw">if </span>lits.is_empty() || lits.min_literal_len() == <span class="prelude-val">Some</span>(<span class="number">0</span>) { |
| <span class="kw">return </span>Matcher::Empty; |
| } |
| <span class="kw">let </span>lits = <span class="kw">match </span>lits.literals() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span>Matcher::Empty, |
| <span class="prelude-val">Some</span>(members) => members, |
| }; |
| <span class="kw">if </span>sset.dense.len() >= <span class="number">26 </span>{ |
| <span class="comment">// Avoid trying to match a large number of single bytes. |
| // This is *very* sensitive to a frequency analysis comparison |
| // between the bytes in sset and the composition of the haystack. |
| // No matter the size of sset, if its members all are rare in the |
| // haystack, then it'd be worth using it. How to tune this... IDK. |
| // ---AG |
| </span><span class="kw">return </span>Matcher::Empty; |
| } |
| <span class="kw">if </span>sset.complete { |
| <span class="kw">return </span>Matcher::Bytes(sset); |
| } |
| <span class="kw">if </span>lits.len() == <span class="number">1 </span>{ |
| <span class="kw">return </span>Matcher::Memmem(Memmem::new(lits[<span class="number">0</span>].as_bytes())); |
| } |
| |
| <span class="kw">let </span>pats: Vec<<span class="kw-2">&</span>[u8]> = lits.iter().map(|lit| lit.as_bytes()).collect(); |
| <span class="kw">let </span>is_aho_corasick_fast = sset.dense.len() <= <span class="number">1 </span>&& sset.all_ascii; |
| <span class="kw">if </span>lits.len() <= <span class="number">100 </span>&& !is_aho_corasick_fast { |
| <span class="kw">let </span><span class="kw-2">mut </span>builder = packed::Config::new() |
| .match_kind(packed::MatchKind::LeftmostFirst) |
| .builder(); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(s) = builder.extend(<span class="kw-2">&</span>pats).build() { |
| <span class="kw">return </span>Matcher::Packed { s, lits: lits.to_owned() }; |
| } |
| } |
| <span class="kw">let </span>ac = AhoCorasick::builder() |
| .match_kind(aho_corasick::MatchKind::LeftmostFirst) |
| .kind(<span class="prelude-val">Some</span>(aho_corasick::AhoCorasickKind::DFA)) |
| .build(<span class="kw-2">&</span>pats) |
| .unwrap(); |
| Matcher::AC { ac, lits: lits.to_owned() } |
| } |
| } |
| |
| <span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub enum </span>LiteralIter<<span class="lifetime">'a</span>> { |
| Empty, |
| Bytes(<span class="kw-2">&</span><span class="lifetime">'a </span>[u8]), |
| Single(<span class="kw-2">&</span><span class="lifetime">'a </span>[u8]), |
| AC(<span class="kw-2">&</span><span class="lifetime">'a </span>[Literal]), |
| Packed(<span class="kw-2">&</span><span class="lifetime">'a </span>[Literal]), |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>LiteralIter<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = <span class="kw-2">&</span><span class="lifetime">'a </span>[u8]; |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>::Item> { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| LiteralIter::Empty => <span class="prelude-val">None</span>, |
| LiteralIter::Bytes(<span class="kw-2">ref mut </span>many) => { |
| <span class="kw">if </span>many.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="kw">let </span>next = <span class="kw-2">&</span>many[<span class="number">0</span>..<span class="number">1</span>]; |
| <span class="kw-2">*</span>many = <span class="kw-2">&</span>many[<span class="number">1</span>..]; |
| <span class="prelude-val">Some</span>(next) |
| } |
| } |
| LiteralIter::Single(<span class="kw-2">ref mut </span>one) => { |
| <span class="kw">if </span>one.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="kw">let </span>next = <span class="kw-2">&</span>one[..]; |
| <span class="kw-2">*</span>one = <span class="kw-2">&</span>[]; |
| <span class="prelude-val">Some</span>(next) |
| } |
| } |
| LiteralIter::AC(<span class="kw-2">ref mut </span>lits) => { |
| <span class="kw">if </span>lits.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="kw">let </span>next = <span class="kw-2">&</span>lits[<span class="number">0</span>]; |
| <span class="kw-2">*</span>lits = <span class="kw-2">&</span>lits[<span class="number">1</span>..]; |
| <span class="prelude-val">Some</span>(next.as_bytes()) |
| } |
| } |
| LiteralIter::Packed(<span class="kw-2">ref mut </span>lits) => { |
| <span class="kw">if </span>lits.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="kw">let </span>next = <span class="kw-2">&</span>lits[<span class="number">0</span>]; |
| <span class="kw-2">*</span>lits = <span class="kw-2">&</span>lits[<span class="number">1</span>..]; |
| <span class="prelude-val">Some</span>(next.as_bytes()) |
| } |
| } |
| } |
| } |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>SingleByteSet { |
| sparse: Vec<bool>, |
| dense: Vec<u8>, |
| complete: bool, |
| all_ascii: bool, |
| } |
| |
| <span class="kw">impl </span>SingleByteSet { |
| <span class="kw">fn </span>new() -> SingleByteSet { |
| SingleByteSet { |
| sparse: <span class="macro">vec!</span>[<span class="bool-val">false</span>; <span class="number">256</span>], |
| dense: <span class="macro">vec!</span>[], |
| complete: <span class="bool-val">true</span>, |
| all_ascii: <span class="bool-val">true</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>prefixes(lits: <span class="kw-2">&</span>Seq) -> SingleByteSet { |
| <span class="kw">let </span><span class="kw-2">mut </span>sset = SingleByteSet::new(); |
| <span class="kw">let </span>lits = <span class="kw">match </span>lits.literals() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span>sset, |
| <span class="prelude-val">Some</span>(lits) => lits, |
| }; |
| <span class="kw">for </span>lit <span class="kw">in </span>lits.iter() { |
| sset.complete = sset.complete && lit.len() == <span class="number">1</span>; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) = lit.as_bytes().get(<span class="number">0</span>) { |
| <span class="kw">if </span>!sset.sparse[b <span class="kw">as </span>usize] { |
| <span class="kw">if </span>b > <span class="number">0x7F </span>{ |
| sset.all_ascii = <span class="bool-val">false</span>; |
| } |
| sset.dense.push(b); |
| sset.sparse[b <span class="kw">as </span>usize] = <span class="bool-val">true</span>; |
| } |
| } |
| } |
| sset |
| } |
| |
| <span class="kw">fn </span>suffixes(lits: <span class="kw-2">&</span>Seq) -> SingleByteSet { |
| <span class="kw">let </span><span class="kw-2">mut </span>sset = SingleByteSet::new(); |
| <span class="kw">let </span>lits = <span class="kw">match </span>lits.literals() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span>sset, |
| <span class="prelude-val">Some</span>(lits) => lits, |
| }; |
| <span class="kw">for </span>lit <span class="kw">in </span>lits.iter() { |
| sset.complete = sset.complete && lit.len() == <span class="number">1</span>; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) = lit.as_bytes().last() { |
| <span class="kw">if </span>!sset.sparse[b <span class="kw">as </span>usize] { |
| <span class="kw">if </span>b > <span class="number">0x7F </span>{ |
| sset.all_ascii = <span class="bool-val">false</span>; |
| } |
| sset.dense.push(b); |
| sset.sparse[b <span class="kw">as </span>usize] = <span class="bool-val">true</span>; |
| } |
| } |
| } |
| sset |
| } |
| |
| <span class="doccomment">/// Faster find that special cases certain sizes to use memchr. |
| </span><span class="attribute">#[cfg_attr(feature = <span class="string">"perf-inline"</span>, inline(always))] |
| </span><span class="kw">fn </span>find(<span class="kw-2">&</span><span class="self">self</span>, text: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">match </span><span class="self">self</span>.dense.len() { |
| <span class="number">0 </span>=> <span class="prelude-val">None</span>, |
| <span class="number">1 </span>=> memchr(<span class="self">self</span>.dense[<span class="number">0</span>], text), |
| <span class="number">2 </span>=> memchr2(<span class="self">self</span>.dense[<span class="number">0</span>], <span class="self">self</span>.dense[<span class="number">1</span>], text), |
| <span class="number">3 </span>=> memchr3(<span class="self">self</span>.dense[<span class="number">0</span>], <span class="self">self</span>.dense[<span class="number">1</span>], <span class="self">self</span>.dense[<span class="number">2</span>], text), |
| <span class="kw">_ </span>=> <span class="self">self</span>._find(text), |
| } |
| } |
| |
| <span class="doccomment">/// Generic find that works on any sized set. |
| </span><span class="kw">fn </span>_find(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">for </span>(i, <span class="kw-2">&</span>b) <span class="kw">in </span>haystack.iter().enumerate() { |
| <span class="kw">if </span><span class="self">self</span>.sparse[b <span class="kw">as </span>usize] { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(i); |
| } |
| } |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="kw">fn </span>approximate_size(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| (<span class="self">self</span>.dense.len() * mem::size_of::<u8>()) |
| + (<span class="self">self</span>.sparse.len() * mem::size_of::<bool>()) |
| } |
| } |
| |
| <span class="doccomment">/// A simple wrapper around the memchr crate's memmem implementation. |
| /// |
| /// The API this exposes mirrors the API of previous substring searchers that |
| /// this supplanted. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Memmem { |
| finder: memmem::Finder<<span class="lifetime">'static</span>>, |
| char_len: usize, |
| } |
| |
| <span class="kw">impl </span>Memmem { |
| <span class="kw">fn </span>new(pat: <span class="kw-2">&</span>[u8]) -> Memmem { |
| Memmem { |
| finder: memmem::Finder::new(pat).into_owned(), |
| char_len: char_len_lossy(pat), |
| } |
| } |
| |
| <span class="attribute">#[cfg_attr(feature = <span class="string">"perf-inline"</span>, inline(always))] |
| </span><span class="kw">pub fn </span>find(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="self">self</span>.finder.find(haystack) |
| } |
| |
| <span class="attribute">#[cfg_attr(feature = <span class="string">"perf-inline"</span>, inline(always))] |
| </span><span class="kw">pub fn </span>is_suffix(<span class="kw-2">&</span><span class="self">self</span>, text: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="kw">if </span>text.len() < <span class="self">self</span>.len() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="kw-2">&</span>text[text.len() - <span class="self">self</span>.len()..] == <span class="self">self</span>.finder.needle() |
| } |
| |
| <span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.finder.needle().len() |
| } |
| |
| <span class="kw">pub fn </span>char_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.char_len |
| } |
| |
| <span class="kw">fn </span>approximate_size(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.finder.needle().len() * mem::size_of::<u8>() |
| } |
| } |
| |
| <span class="kw">fn </span>char_len_lossy(bytes: <span class="kw-2">&</span>[u8]) -> usize { |
| String::from_utf8_lossy(bytes).chars().count() |
| } |
| </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> |