| <!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/aho-corasick-1.0.2/src/packed/pattern.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>pattern.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="../../../aho_corasick/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="../../../aho_corasick/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> |
| </pre><pre class="rust"><code><span class="kw">use </span>core::{cmp, fmt, mem, u16, usize}; |
| |
| <span class="kw">use </span>alloc::{string::String, vec, vec::Vec}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::packed::api::MatchKind; |
| |
| <span class="doccomment">/// The type used for representing a pattern identifier. |
| /// |
| /// We don't use `usize` here because our packed searchers don't scale to |
| /// huge numbers of patterns, so we keep things a bit smaller. |
| </span><span class="kw">pub type </span>PatternID = u16; |
| |
| <span class="doccomment">/// A non-empty collection of non-empty patterns to search for. |
| /// |
| /// This collection of patterns is what is passed around to both execute |
| /// searches and to construct the searchers themselves. Namely, this permits |
| /// searches to avoid copying all of the patterns, and allows us to keep only |
| /// one copy throughout all packed searchers. |
| /// |
| /// Note that this collection is not a set. The same pattern can appear more |
| /// than once. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Patterns { |
| <span class="doccomment">/// The match semantics supported by this collection of patterns. |
| /// |
| /// The match semantics determines the order of the iterator over patterns. |
| /// For leftmost-first, patterns are provided in the same order as were |
| /// provided by the caller. For leftmost-longest, patterns are provided in |
| /// descending order of length, with ties broken by the order in which they |
| /// were provided by the caller. |
| </span>kind: MatchKind, |
| <span class="doccomment">/// The collection of patterns, indexed by their identifier. |
| </span>by_id: Vec<Vec<u8>>, |
| <span class="doccomment">/// The order of patterns defined for iteration, given by pattern |
| /// identifiers. The order of `by_id` and `order` is always the same for |
| /// leftmost-first semantics, but may be different for leftmost-longest |
| /// semantics. |
| </span>order: Vec<PatternID>, |
| <span class="doccomment">/// The length of the smallest pattern, in bytes. |
| </span>minimum_len: usize, |
| <span class="doccomment">/// The largest pattern identifier. This should always be equivalent to |
| /// the number of patterns minus one in this collection. |
| </span>max_pattern_id: PatternID, |
| <span class="doccomment">/// The total number of pattern bytes across the entire collection. This |
| /// is used for reporting total heap usage in constant time. |
| </span>total_pattern_bytes: usize, |
| } |
| |
| <span class="kw">impl </span>Patterns { |
| <span class="doccomment">/// Create a new collection of patterns for the given match semantics. The |
| /// ID of each pattern is the index of the pattern at which it occurs in |
| /// the `by_id` slice. |
| /// |
| /// If any of the patterns in the slice given are empty, then this panics. |
| /// Similarly, if the number of patterns given is zero, then this also |
| /// panics. |
| </span><span class="kw">pub fn </span>new() -> Patterns { |
| Patterns { |
| kind: MatchKind::default(), |
| by_id: <span class="macro">vec!</span>[], |
| order: <span class="macro">vec!</span>[], |
| minimum_len: usize::MAX, |
| max_pattern_id: <span class="number">0</span>, |
| total_pattern_bytes: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Add a pattern to this collection. |
| /// |
| /// This panics if the pattern given is empty. |
| </span><span class="kw">pub fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) { |
| <span class="macro">assert!</span>(!bytes.is_empty()); |
| <span class="macro">assert!</span>(<span class="self">self</span>.by_id.len() <= u16::MAX <span class="kw">as </span>usize); |
| |
| <span class="kw">let </span>id = <span class="self">self</span>.by_id.len() <span class="kw">as </span>u16; |
| <span class="self">self</span>.max_pattern_id = id; |
| <span class="self">self</span>.order.push(id); |
| <span class="self">self</span>.by_id.push(bytes.to_vec()); |
| <span class="self">self</span>.minimum_len = cmp::min(<span class="self">self</span>.minimum_len, bytes.len()); |
| <span class="self">self</span>.total_pattern_bytes += bytes.len(); |
| } |
| |
| <span class="doccomment">/// Set the match kind semantics for this collection of patterns. |
| /// |
| /// If the kind is not set, then the default is leftmost-first. |
| </span><span class="kw">pub fn </span>set_match_kind(<span class="kw-2">&mut </span><span class="self">self</span>, kind: MatchKind) { |
| <span class="self">self</span>.kind = kind; |
| <span class="kw">match </span><span class="self">self</span>.kind { |
| MatchKind::LeftmostFirst => { |
| <span class="self">self</span>.order.sort(); |
| } |
| MatchKind::LeftmostLongest => { |
| <span class="kw">let </span>(order, by_id) = (<span class="kw-2">&mut </span><span class="self">self</span>.order, <span class="kw-2">&mut </span><span class="self">self</span>.by_id); |
| order.sort_by(|<span class="kw-2">&</span>id1, <span class="kw-2">&</span>id2| { |
| by_id[id1 <span class="kw">as </span>usize] |
| .len() |
| .cmp(<span class="kw-2">&</span>by_id[id2 <span class="kw">as </span>usize].len()) |
| .reverse() |
| }); |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Return the number of patterns in this collection. |
| /// |
| /// This is guaranteed to be greater than zero. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.by_id.len() |
| } |
| |
| <span class="doccomment">/// Returns true if and only if this collection of patterns 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 approximate total amount of heap used by these patterns, in |
| /// units of bytes. |
| </span><span class="kw">pub fn </span>memory_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.order.len() * mem::size_of::<PatternID>() |
| + <span class="self">self</span>.by_id.len() * mem::size_of::<Vec<u8>>() |
| + <span class="self">self</span>.total_pattern_bytes |
| } |
| |
| <span class="doccomment">/// Clears all heap memory associated with this collection of patterns and |
| /// resets all state such that it is a valid empty collection. |
| </span><span class="kw">pub fn </span>reset(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="self">self</span>.kind = MatchKind::default(); |
| <span class="self">self</span>.by_id.clear(); |
| <span class="self">self</span>.order.clear(); |
| <span class="self">self</span>.minimum_len = usize::MAX; |
| <span class="self">self</span>.max_pattern_id = <span class="number">0</span>; |
| } |
| |
| <span class="doccomment">/// Return the maximum pattern identifier in this collection. This can be |
| /// useful in searchers for ensuring that the collection of patterns they |
| /// are provided at search time and at build time have the same size. |
| </span><span class="kw">pub fn </span>max_pattern_id(<span class="kw-2">&</span><span class="self">self</span>) -> PatternID { |
| <span class="macro">assert_eq!</span>((<span class="self">self</span>.max_pattern_id + <span class="number">1</span>) <span class="kw">as </span>usize, <span class="self">self</span>.len()); |
| <span class="self">self</span>.max_pattern_id |
| } |
| |
| <span class="doccomment">/// Returns the length, in bytes, of the smallest pattern. |
| /// |
| /// This is guaranteed to be at least one. |
| </span><span class="kw">pub fn </span>minimum_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.minimum_len |
| } |
| |
| <span class="doccomment">/// Returns the match semantics used by these patterns. |
| </span><span class="kw">pub fn </span>match_kind(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>MatchKind { |
| <span class="kw-2">&</span><span class="self">self</span>.kind |
| } |
| |
| <span class="doccomment">/// Return the pattern with the given identifier. If such a pattern does |
| /// not exist, then this panics. |
| </span><span class="kw">pub fn </span>get(<span class="kw-2">&</span><span class="self">self</span>, id: PatternID) -> Pattern<<span class="lifetime">'_</span>> { |
| Pattern(<span class="kw-2">&</span><span class="self">self</span>.by_id[id <span class="kw">as </span>usize]) |
| } |
| |
| <span class="doccomment">/// Return the pattern with the given identifier without performing bounds |
| /// checks. |
| /// |
| /// # Safety |
| /// |
| /// Callers must ensure that a pattern with the given identifier exists |
| /// before using this method. |
| </span><span class="attribute">#[cfg(all(feature = <span class="string">"std"</span>, target_arch = <span class="string">"x86_64"</span>))] |
| </span><span class="kw">pub unsafe fn </span>get_unchecked(<span class="kw-2">&</span><span class="self">self</span>, id: PatternID) -> Pattern<<span class="lifetime">'_</span>> { |
| Pattern(<span class="self">self</span>.by_id.get_unchecked(id <span class="kw">as </span>usize)) |
| } |
| |
| <span class="doccomment">/// Return an iterator over all the patterns in this collection, in the |
| /// order in which they should be matched. |
| /// |
| /// Specifically, in a naive multi-pattern matcher, the following is |
| /// guaranteed to satisfy the match semantics of this collection of |
| /// patterns: |
| /// |
| /// ```ignore |
| /// for i in 0..haystack.len(): |
| /// for p in patterns.iter(): |
| /// if haystack[i..].starts_with(p.bytes()): |
| /// return Match(p.id(), i, i + p.bytes().len()) |
| /// ``` |
| /// |
| /// Namely, among the patterns in a collection, if they are matched in |
| /// the order provided by this iterator, then the result is guaranteed |
| /// to satisfy the correct match semantics. (Either leftmost-first or |
| /// leftmost-longest.) |
| </span><span class="kw">pub fn </span>iter(<span class="kw-2">&</span><span class="self">self</span>) -> PatternIter<<span class="lifetime">'_</span>> { |
| PatternIter { patterns: <span class="self">self</span>, i: <span class="number">0 </span>} |
| } |
| } |
| |
| <span class="doccomment">/// An iterator over the patterns in the `Patterns` collection. |
| /// |
| /// The order of the patterns provided by this iterator is consistent with the |
| /// match semantics of the originating collection of patterns. |
| /// |
| /// The lifetime `'p` corresponds to the lifetime of the collection of patterns |
| /// this is iterating over. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>PatternIter<<span class="lifetime">'p</span>> { |
| patterns: <span class="kw-2">&</span><span class="lifetime">'p </span>Patterns, |
| i: usize, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'p</span>> Iterator <span class="kw">for </span>PatternIter<<span class="lifetime">'p</span>> { |
| <span class="kw">type </span>Item = (PatternID, Pattern<<span class="lifetime">'p</span>>); |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><(PatternID, Pattern<<span class="lifetime">'p</span>>)> { |
| <span class="kw">if </span><span class="self">self</span>.i >= <span class="self">self</span>.patterns.len() { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>id = <span class="self">self</span>.patterns.order[<span class="self">self</span>.i]; |
| <span class="kw">let </span>p = <span class="self">self</span>.patterns.get(id); |
| <span class="self">self</span>.i += <span class="number">1</span>; |
| <span class="prelude-val">Some</span>((id, p)) |
| } |
| } |
| |
| <span class="doccomment">/// A pattern that is used in packed searching. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>Pattern<<span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="lifetime">'a </span>[u8]); |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> fmt::Debug <span class="kw">for </span>Pattern<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter<<span class="lifetime">'_</span>>) -> fmt::Result { |
| f.debug_struct(<span class="string">"Pattern"</span>) |
| .field(<span class="string">"lit"</span>, <span class="kw-2">&</span>String::from_utf8_lossy(<span class="kw-2">&</span><span class="self">self</span>.<span class="number">0</span>)) |
| .finish() |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'p</span>> Pattern<<span class="lifetime">'p</span>> { |
| <span class="doccomment">/// Returns the length of this pattern, in bytes. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.<span class="number">0</span>.len() |
| } |
| |
| <span class="doccomment">/// Returns the bytes of this pattern. |
| </span><span class="kw">pub fn </span>bytes(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[u8] { |
| <span class="kw-2">&</span><span class="self">self</span>.<span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Returns the first `len` low nybbles from this pattern. If this pattern |
| /// is shorter than `len`, then this panics. |
| </span><span class="attribute">#[cfg(all(feature = <span class="string">"std"</span>, target_arch = <span class="string">"x86_64"</span>))] |
| </span><span class="kw">pub fn </span>low_nybbles(<span class="kw-2">&</span><span class="self">self</span>, len: usize) -> Vec<u8> { |
| <span class="kw">let </span><span class="kw-2">mut </span>nybs = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span><span class="kw-2">&</span>b <span class="kw">in </span><span class="self">self</span>.bytes().iter().take(len) { |
| nybs.push(b & <span class="number">0xF</span>); |
| } |
| nybs |
| } |
| |
| <span class="doccomment">/// Returns true if this pattern is a prefix of the given bytes. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub fn </span>is_prefix(<span class="kw-2">&</span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="self">self</span>.len() <= bytes.len() && <span class="self">self</span>.equals(<span class="kw-2">&</span>bytes[..<span class="self">self</span>.len()]) |
| } |
| |
| <span class="doccomment">/// Returns true if and only if this pattern equals the given bytes. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub fn </span>equals(<span class="kw-2">&</span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="comment">// Why not just use memcmp for this? Well, memcmp requires calling out |
| // to libc, and this routine is called in fairly hot code paths. Other |
| // than just calling out to libc, it also seems to result in worse |
| // codegen. By rolling our own memcpy in pure Rust, it seems to appear |
| // more friendly to the optimizer. |
| // |
| // This results in an improvement in just about every benchmark. Some |
| // smaller than others, but in some cases, up to 30% faster. |
| |
| </span><span class="kw">let </span>(x, y) = (<span class="self">self</span>.bytes(), bytes); |
| <span class="kw">if </span>x.len() != y.len() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="comment">// If we don't have enough bytes to do 4-byte at a time loads, then |
| // fall back to the naive slow version. |
| </span><span class="kw">if </span>x.len() < <span class="number">4 </span>{ |
| <span class="kw">for </span>(<span class="kw-2">&</span>b1, <span class="kw-2">&</span>b2) <span class="kw">in </span>x.iter().zip(y) { |
| <span class="kw">if </span>b1 != b2 { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| } |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="comment">// When we have 4 or more bytes to compare, then proceed in chunks of 4 |
| // at a time using unaligned loads. |
| // |
| // Also, why do 4 byte loads instead of, say, 8 byte loads? The reason |
| // is that this particular version of memcmp is likely to be called |
| // with tiny needles. That means that if we do 8 byte loads, then a |
| // higher proportion of memcmp calls will use the slower variant above. |
| // With that said, this is a hypothesis and is only loosely supported |
| // by benchmarks. There's likely some improvement that could be made |
| // here. The main thing here though is to optimize for latency, not |
| // throughput. |
| |
| // SAFETY: Via the conditional above, we know that both `px` and `py` |
| // have the same length, so `px < pxend` implies that `py < pyend`. |
| // Thus, derefencing both `px` and `py` in the loop below is safe. |
| // |
| // Moreover, we set `pxend` and `pyend` to be 4 bytes before the actual |
| // end of of `px` and `py`. Thus, the final dereference outside of the |
| // loop is guaranteed to be valid. (The final comparison will overlap |
| // with the last comparison done in the loop for lengths that aren't |
| // multiples of four.) |
| // |
| // Finally, we needn't worry about alignment here, since we do |
| // unaligned loads. |
| </span><span class="kw">unsafe </span>{ |
| <span class="kw">let </span>(<span class="kw-2">mut </span>px, <span class="kw-2">mut </span>py) = (x.as_ptr(), y.as_ptr()); |
| <span class="kw">let </span>(pxend, pyend) = (px.add(x.len() - <span class="number">4</span>), py.add(y.len() - <span class="number">4</span>)); |
| <span class="kw">while </span>px < pxend { |
| <span class="kw">let </span>vx = (px <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">let </span>vy = (py <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">if </span>vx != vy { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| px = px.add(<span class="number">4</span>); |
| py = py.add(<span class="number">4</span>); |
| } |
| <span class="kw">let </span>vx = (pxend <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">let </span>vy = (pyend <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| vx == vy |
| } |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="aho_corasick" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |