| <!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/util/prefilter.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>prefilter.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> |
| <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> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| <span id="568">568</span> |
| <span id="569">569</span> |
| <span id="570">570</span> |
| <span id="571">571</span> |
| <span id="572">572</span> |
| <span id="573">573</span> |
| <span id="574">574</span> |
| <span id="575">575</span> |
| <span id="576">576</span> |
| <span id="577">577</span> |
| <span id="578">578</span> |
| <span id="579">579</span> |
| <span id="580">580</span> |
| <span id="581">581</span> |
| <span id="582">582</span> |
| <span id="583">583</span> |
| <span id="584">584</span> |
| <span id="585">585</span> |
| <span id="586">586</span> |
| <span id="587">587</span> |
| <span id="588">588</span> |
| <span id="589">589</span> |
| <span id="590">590</span> |
| <span id="591">591</span> |
| <span id="592">592</span> |
| <span id="593">593</span> |
| <span id="594">594</span> |
| <span id="595">595</span> |
| <span id="596">596</span> |
| <span id="597">597</span> |
| <span id="598">598</span> |
| <span id="599">599</span> |
| <span id="600">600</span> |
| <span id="601">601</span> |
| <span id="602">602</span> |
| <span id="603">603</span> |
| <span id="604">604</span> |
| <span id="605">605</span> |
| <span id="606">606</span> |
| <span id="607">607</span> |
| <span id="608">608</span> |
| <span id="609">609</span> |
| <span id="610">610</span> |
| <span id="611">611</span> |
| <span id="612">612</span> |
| <span id="613">613</span> |
| <span id="614">614</span> |
| <span id="615">615</span> |
| <span id="616">616</span> |
| <span id="617">617</span> |
| <span id="618">618</span> |
| <span id="619">619</span> |
| <span id="620">620</span> |
| <span id="621">621</span> |
| <span id="622">622</span> |
| <span id="623">623</span> |
| <span id="624">624</span> |
| <span id="625">625</span> |
| <span id="626">626</span> |
| <span id="627">627</span> |
| <span id="628">628</span> |
| <span id="629">629</span> |
| <span id="630">630</span> |
| <span id="631">631</span> |
| <span id="632">632</span> |
| <span id="633">633</span> |
| <span id="634">634</span> |
| <span id="635">635</span> |
| <span id="636">636</span> |
| <span id="637">637</span> |
| <span id="638">638</span> |
| <span id="639">639</span> |
| <span id="640">640</span> |
| <span id="641">641</span> |
| <span id="642">642</span> |
| <span id="643">643</span> |
| <span id="644">644</span> |
| <span id="645">645</span> |
| <span id="646">646</span> |
| <span id="647">647</span> |
| <span id="648">648</span> |
| <span id="649">649</span> |
| <span id="650">650</span> |
| <span id="651">651</span> |
| <span id="652">652</span> |
| <span id="653">653</span> |
| <span id="654">654</span> |
| <span id="655">655</span> |
| <span id="656">656</span> |
| <span id="657">657</span> |
| <span id="658">658</span> |
| <span id="659">659</span> |
| <span id="660">660</span> |
| <span id="661">661</span> |
| <span id="662">662</span> |
| <span id="663">663</span> |
| <span id="664">664</span> |
| <span id="665">665</span> |
| <span id="666">666</span> |
| <span id="667">667</span> |
| <span id="668">668</span> |
| <span id="669">669</span> |
| <span id="670">670</span> |
| <span id="671">671</span> |
| <span id="672">672</span> |
| <span id="673">673</span> |
| <span id="674">674</span> |
| <span id="675">675</span> |
| <span id="676">676</span> |
| <span id="677">677</span> |
| <span id="678">678</span> |
| <span id="679">679</span> |
| <span id="680">680</span> |
| <span id="681">681</span> |
| <span id="682">682</span> |
| <span id="683">683</span> |
| <span id="684">684</span> |
| <span id="685">685</span> |
| <span id="686">686</span> |
| <span id="687">687</span> |
| <span id="688">688</span> |
| <span id="689">689</span> |
| <span id="690">690</span> |
| <span id="691">691</span> |
| <span id="692">692</span> |
| <span id="693">693</span> |
| <span id="694">694</span> |
| <span id="695">695</span> |
| <span id="696">696</span> |
| <span id="697">697</span> |
| <span id="698">698</span> |
| <span id="699">699</span> |
| <span id="700">700</span> |
| <span id="701">701</span> |
| <span id="702">702</span> |
| <span id="703">703</span> |
| <span id="704">704</span> |
| <span id="705">705</span> |
| <span id="706">706</span> |
| <span id="707">707</span> |
| <span id="708">708</span> |
| <span id="709">709</span> |
| <span id="710">710</span> |
| <span id="711">711</span> |
| <span id="712">712</span> |
| <span id="713">713</span> |
| <span id="714">714</span> |
| <span id="715">715</span> |
| <span id="716">716</span> |
| <span id="717">717</span> |
| <span id="718">718</span> |
| <span id="719">719</span> |
| <span id="720">720</span> |
| <span id="721">721</span> |
| <span id="722">722</span> |
| <span id="723">723</span> |
| <span id="724">724</span> |
| <span id="725">725</span> |
| <span id="726">726</span> |
| <span id="727">727</span> |
| <span id="728">728</span> |
| <span id="729">729</span> |
| <span id="730">730</span> |
| <span id="731">731</span> |
| <span id="732">732</span> |
| <span id="733">733</span> |
| <span id="734">734</span> |
| <span id="735">735</span> |
| <span id="736">736</span> |
| <span id="737">737</span> |
| <span id="738">738</span> |
| <span id="739">739</span> |
| <span id="740">740</span> |
| <span id="741">741</span> |
| <span id="742">742</span> |
| <span id="743">743</span> |
| <span id="744">744</span> |
| <span id="745">745</span> |
| <span id="746">746</span> |
| <span id="747">747</span> |
| <span id="748">748</span> |
| <span id="749">749</span> |
| <span id="750">750</span> |
| <span id="751">751</span> |
| <span id="752">752</span> |
| <span id="753">753</span> |
| <span id="754">754</span> |
| <span id="755">755</span> |
| <span id="756">756</span> |
| <span id="757">757</span> |
| <span id="758">758</span> |
| <span id="759">759</span> |
| <span id="760">760</span> |
| <span id="761">761</span> |
| <span id="762">762</span> |
| <span id="763">763</span> |
| <span id="764">764</span> |
| <span id="765">765</span> |
| <span id="766">766</span> |
| <span id="767">767</span> |
| <span id="768">768</span> |
| <span id="769">769</span> |
| <span id="770">770</span> |
| <span id="771">771</span> |
| <span id="772">772</span> |
| <span id="773">773</span> |
| <span id="774">774</span> |
| <span id="775">775</span> |
| <span id="776">776</span> |
| <span id="777">777</span> |
| <span id="778">778</span> |
| <span id="779">779</span> |
| <span id="780">780</span> |
| <span id="781">781</span> |
| <span id="782">782</span> |
| <span id="783">783</span> |
| <span id="784">784</span> |
| <span id="785">785</span> |
| <span id="786">786</span> |
| <span id="787">787</span> |
| <span id="788">788</span> |
| <span id="789">789</span> |
| <span id="790">790</span> |
| <span id="791">791</span> |
| <span id="792">792</span> |
| <span id="793">793</span> |
| <span id="794">794</span> |
| <span id="795">795</span> |
| <span id="796">796</span> |
| <span id="797">797</span> |
| <span id="798">798</span> |
| <span id="799">799</span> |
| <span id="800">800</span> |
| <span id="801">801</span> |
| <span id="802">802</span> |
| <span id="803">803</span> |
| <span id="804">804</span> |
| <span id="805">805</span> |
| <span id="806">806</span> |
| <span id="807">807</span> |
| <span id="808">808</span> |
| <span id="809">809</span> |
| <span id="810">810</span> |
| <span id="811">811</span> |
| <span id="812">812</span> |
| <span id="813">813</span> |
| <span id="814">814</span> |
| <span id="815">815</span> |
| <span id="816">816</span> |
| <span id="817">817</span> |
| <span id="818">818</span> |
| <span id="819">819</span> |
| <span id="820">820</span> |
| <span id="821">821</span> |
| <span id="822">822</span> |
| <span id="823">823</span> |
| <span id="824">824</span> |
| <span id="825">825</span> |
| <span id="826">826</span> |
| <span id="827">827</span> |
| <span id="828">828</span> |
| <span id="829">829</span> |
| <span id="830">830</span> |
| <span id="831">831</span> |
| <span id="832">832</span> |
| <span id="833">833</span> |
| <span id="834">834</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>core::{ |
| cmp, |
| fmt::Debug, |
| panic::{RefUnwindSafe, UnwindSafe}, |
| u8, |
| }; |
| |
| <span class="kw">use </span>alloc::{sync::Arc, vec, vec::Vec}; |
| |
| <span class="kw">use crate</span>::{ |
| packed, |
| util::{ |
| alphabet::ByteSet, |
| search::{Match, MatchKind, Span}, |
| }, |
| }; |
| |
| <span class="doccomment">/// A prefilter for accelerating a search. |
| /// |
| /// This crate uses prefilters in the core search implementations to accelerate |
| /// common cases. They typically only apply to cases where there are a small |
| /// number of patterns (less than 100 or so), but when they do, thoughput can |
| /// be boosted considerably, perhaps by an order of magnitude. When a prefilter |
| /// is active, it is used whenever a search enters an automaton's start state. |
| /// |
| /// Currently, prefilters cannot be constructed by |
| /// callers. A `Prefilter` can only be accessed via the |
| /// [`Automaton::prefilter`](crate::automaton::Automaton::prefilter) |
| /// method and used to execute a search. In other words, a prefilter can be |
| /// used to optimize your own search implementation if necessary, but cannot do |
| /// much else. If you have a use case for more APIs, please submit an issue. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Prefilter { |
| finder: Arc<<span class="kw">dyn </span>PrefilterI>, |
| memory_usage: usize, |
| } |
| |
| <span class="kw">impl </span>Prefilter { |
| <span class="doccomment">/// Execute a search in the haystack within the span given. If a match or |
| /// a possible match is returned, then it is guaranteed to occur within |
| /// the bounds of the span. |
| /// |
| /// If the span provided is invalid for the given haystack, then behavior |
| /// is unspecified. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| <span class="self">self</span>.finder.find_in(haystack, span) |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>memory_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.memory_usage |
| } |
| } |
| |
| <span class="doccomment">/// A candidate is the result of running a prefilter on a haystack at a |
| /// particular position. |
| /// |
| /// The result is either no match, a confirmed match or a possible match. |
| /// |
| /// When no match is returned, the prefilter is guaranteeing that no possible |
| /// match can be found in the haystack, and the caller may trust this. That is, |
| /// all correct prefilters must never report false negatives. |
| /// |
| /// In some cases, a prefilter can confirm a match very quickly, in which case, |
| /// the caller may use this to stop what it's doing and report the match. In |
| /// this case, prefilter implementations must never report a false positive. |
| /// In other cases, the prefilter can only report a potential match, in which |
| /// case the callers must attempt to confirm the match. In this case, prefilter |
| /// implementations are permitted to return false positives. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub enum </span>Candidate { |
| <span class="doccomment">/// No match was found. Since false negatives are not possible, this means |
| /// the search can quit as it is guaranteed not to find another match. |
| </span><span class="prelude-val">None</span>, |
| <span class="doccomment">/// A confirmed match was found. Callers do not need to confirm it. |
| </span>Match(Match), |
| <span class="doccomment">/// The start of a possible match was found. Callers must confirm it before |
| /// reporting it as a match. |
| </span>PossibleStartOfMatch(usize), |
| } |
| |
| <span class="kw">impl </span>Candidate { |
| <span class="doccomment">/// Convert this candidate into an option. This is useful when callers |
| /// do not distinguish between true positives and false positives (i.e., |
| /// the caller must always confirm the match). |
| </span><span class="kw">pub fn </span>into_option(<span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">match </span><span class="self">self </span>{ |
| Candidate::None => <span class="prelude-val">None</span>, |
| Candidate::Match(<span class="kw-2">ref </span>m) => <span class="prelude-val">Some</span>(m.start()), |
| Candidate::PossibleStartOfMatch(start) => <span class="prelude-val">Some</span>(start), |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter describes the behavior of fast literal scanners for quickly |
| /// skipping past bytes in the haystack that we know cannot possibly |
| /// participate in a match. |
| </span><span class="kw">trait </span>PrefilterI: |
| Send + Sync + RefUnwindSafe + UnwindSafe + Debug + <span class="lifetime">'static |
| </span>{ |
| <span class="doccomment">/// Returns the next possible match candidate. This may yield false |
| /// positives, so callers must confirm a match starting at the position |
| /// returned. This, however, must never produce false negatives. That is, |
| /// this must, at minimum, return the starting position of the next match |
| /// in the given haystack after or at the given position. |
| </span><span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate; |
| } |
| |
| <span class="kw">impl</span><P: PrefilterI + <span class="question-mark">?</span>Sized> PrefilterI <span class="kw">for </span>Arc<P> { |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| (<span class="kw-2">**</span><span class="self">self</span>).find_in(haystack, span) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing the best possible prefilter. When constructed, |
| /// this builder will heuristically select the best prefilter it can build, |
| /// if any, and discard the rest. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Builder { |
| count: usize, |
| ascii_case_insensitive: bool, |
| start_bytes: StartBytesBuilder, |
| rare_bytes: RareBytesBuilder, |
| memmem: MemmemBuilder, |
| packed: <span class="prelude-ty">Option</span><packed::Builder>, |
| <span class="comment">// If we run across a condition that suggests we shouldn't use a prefilter |
| // at all (like an empty pattern), then disable prefilters entirely. |
| </span>enabled: bool, |
| } |
| |
| <span class="kw">impl </span>Builder { |
| <span class="doccomment">/// Create a new builder for constructing the best possible prefilter. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(kind: MatchKind) -> Builder { |
| <span class="kw">let </span>pbuilder = kind |
| .as_packed() |
| .map(|kind| packed::Config::new().match_kind(kind).builder()); |
| Builder { |
| count: <span class="number">0</span>, |
| ascii_case_insensitive: <span class="bool-val">false</span>, |
| start_bytes: StartBytesBuilder::new(), |
| rare_bytes: RareBytesBuilder::new(), |
| memmem: MemmemBuilder::default(), |
| packed: pbuilder, |
| enabled: <span class="bool-val">true</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Enable ASCII case insensitivity. When set, byte strings added to this |
| /// builder will be interpreted without respect to ASCII case. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>ascii_case_insensitive(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> Builder { |
| <span class="self">self</span>.ascii_case_insensitive = yes; |
| <span class="self">self</span>.start_bytes = <span class="self">self</span>.start_bytes.ascii_case_insensitive(yes); |
| <span class="self">self</span>.rare_bytes = <span class="self">self</span>.rare_bytes.ascii_case_insensitive(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Return a prefilter suitable for quickly finding potential matches. |
| /// |
| /// All patterns added to an Aho-Corasick automaton should be added to this |
| /// builder before attempting to construct the prefilter. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>build(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="kw">if </span>!<span class="self">self</span>.enabled { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="comment">// If we only have one pattern, then deferring to memmem is always |
| // the best choice. This is kind of a weird case, because, well, why |
| // use Aho-Corasick if you only have one pattern? But maybe you don't |
| // know exactly how many patterns you'll get up front, and you need to |
| // support the option of multiple patterns. So instead of relying on |
| // the caller to branch and use memmem explicitly, we just do it for |
| // them. |
| </span><span class="kw">if </span>!<span class="self">self</span>.ascii_case_insensitive { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(pre) = <span class="self">self</span>.memmem.build() { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(pre); |
| } |
| } |
| <span class="kw">match </span>(<span class="self">self</span>.start_bytes.build(), <span class="self">self</span>.rare_bytes.build()) { |
| <span class="comment">// If we could build both start and rare prefilters, then there are |
| // a few cases in which we'd want to use the start-byte prefilter |
| // over the rare-byte prefilter, since the former has lower |
| // overhead. |
| </span>(prestart @ <span class="prelude-val">Some</span>(<span class="kw">_</span>), prerare @ <span class="prelude-val">Some</span>(<span class="kw">_</span>)) => { |
| <span class="comment">// If the start-byte prefilter can scan for a smaller number |
| // of bytes than the rare-byte prefilter, then it's probably |
| // faster. |
| </span><span class="kw">let </span>has_fewer_bytes = |
| <span class="self">self</span>.start_bytes.count < <span class="self">self</span>.rare_bytes.count; |
| <span class="comment">// Otherwise, if the combined frequency rank of the detected |
| // bytes in the start-byte prefilter is "close" to the combined |
| // frequency rank of the rare-byte prefilter, then we pick |
| // the start-byte prefilter even if the rare-byte prefilter |
| // heuristically searches for rare bytes. This is because the |
| // rare-byte prefilter has higher constant costs, so we tend to |
| // prefer the start-byte prefilter when we can. |
| </span><span class="kw">let </span>has_rarer_bytes = |
| <span class="self">self</span>.start_bytes.rank_sum <= <span class="self">self</span>.rare_bytes.rank_sum + <span class="number">50</span>; |
| <span class="kw">if </span>has_fewer_bytes || has_rarer_bytes { |
| prestart |
| } <span class="kw">else </span>{ |
| prerare |
| } |
| } |
| (prestart @ <span class="prelude-val">Some</span>(<span class="kw">_</span>), <span class="prelude-val">None</span>) => prestart, |
| (<span class="prelude-val">None</span>, prerare @ <span class="prelude-val">Some</span>(<span class="kw">_</span>)) => prerare, |
| (<span class="prelude-val">None</span>, <span class="prelude-val">None</span>) <span class="kw">if </span><span class="self">self</span>.ascii_case_insensitive => <span class="prelude-val">None</span>, |
| (<span class="prelude-val">None</span>, <span class="prelude-val">None</span>) => { |
| <span class="self">self</span>.packed.as_ref().and_then(|b| b.build()).map(|s| { |
| <span class="kw">let </span>memory_usage = s.memory_usage(); |
| Prefilter { finder: Arc::new(Packed(s)), memory_usage } |
| }) |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Add a literal string to this prefilter builder. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) { |
| <span class="kw">if </span>bytes.is_empty() { |
| <span class="self">self</span>.enabled = <span class="bool-val">false</span>; |
| } |
| <span class="kw">if </span>!<span class="self">self</span>.enabled { |
| <span class="kw">return</span>; |
| } |
| <span class="self">self</span>.count += <span class="number">1</span>; |
| <span class="self">self</span>.start_bytes.add(bytes); |
| <span class="self">self</span>.rare_bytes.add(bytes); |
| <span class="self">self</span>.memmem.add(bytes); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">ref mut </span>pbuilder) = <span class="self">self</span>.packed { |
| pbuilder.add(bytes); |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A type that wraps a packed searcher and implements the `Prefilter` |
| /// interface. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>Packed(packed::Searcher); |
| |
| <span class="kw">impl </span>PrefilterI <span class="kw">for </span>Packed { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| <span class="self">self</span>.<span class="number">0 |
| </span>.find_in(<span class="kw-2">&</span>haystack, span) |
| .map_or(Candidate::None, Candidate::Match) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing a prefilter that uses memmem. |
| </span><span class="attribute">#[derive(Debug, Default)] |
| </span><span class="kw">struct </span>MemmemBuilder { |
| <span class="doccomment">/// The number of patterns that have been added. |
| </span>count: usize, |
| <span class="doccomment">/// The singular pattern to search for. This is only set when count==1. |
| </span>one: <span class="prelude-ty">Option</span><Vec<u8>>, |
| } |
| |
| <span class="kw">impl </span>MemmemBuilder { |
| <span class="kw">fn </span>build(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="attribute">#[cfg(all(feature = <span class="string">"std"</span>, feature = <span class="string">"perf-literal"</span>))] |
| </span><span class="kw">fn </span>imp(builder: <span class="kw-2">&</span>MemmemBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="kw">let </span>pattern = builder.one.as_ref()<span class="question-mark">?</span>; |
| <span class="macro">assert_eq!</span>(<span class="number">1</span>, builder.count); |
| <span class="kw">let </span>finder = Arc::new(Memmem( |
| memchr::memmem::Finder::new(pattern).into_owned(), |
| )); |
| <span class="kw">let </span>memory_usage = pattern.len(); |
| <span class="prelude-val">Some</span>(Prefilter { finder, memory_usage }) |
| } |
| |
| <span class="attribute">#[cfg(not(all(feature = <span class="string">"std"</span>, feature = <span class="string">"perf-literal"</span>)))] |
| </span><span class="kw">fn </span>imp(<span class="kw">_</span>: <span class="kw-2">&</span>MemmemBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="prelude-val">None |
| </span>} |
| |
| imp(<span class="self">self</span>) |
| } |
| |
| <span class="kw">fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) { |
| <span class="self">self</span>.count += <span class="number">1</span>; |
| <span class="kw">if </span><span class="self">self</span>.count == <span class="number">1 </span>{ |
| <span class="self">self</span>.one = <span class="prelude-val">Some</span>(bytes.to_vec()); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.one = <span class="prelude-val">None</span>; |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A type that wraps a SIMD accelerated single substring search from the |
| /// `memchr` crate for use as a prefilter. |
| /// |
| /// Currently, this prefilter is only active for Aho-Corasick searchers with |
| /// a single pattern. In theory, this could be extended to support searchers |
| /// that have a common prefix of more than one byte (for one byte, we would use |
| /// memchr), but it's not clear if it's worth it or not. |
| /// |
| /// Also, unfortunately, this currently also requires the 'std' feature to |
| /// be enabled. That's because memchr doesn't have a no-std-but-with-alloc |
| /// mode, and so APIs like Finder::into_owned aren't available when 'std' is |
| /// disabled. But there should be an 'alloc' feature that brings in APIs like |
| /// Finder::into_owned but doesn't use std-only features like runtime CPU |
| /// feature detection. |
| </span><span class="attribute">#[cfg(all(feature = <span class="string">"std"</span>, feature = <span class="string">"perf-literal"</span>))] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>Memmem(memchr::memmem::Finder<<span class="lifetime">'static</span>>); |
| |
| <span class="attribute">#[cfg(all(feature = <span class="string">"std"</span>, feature = <span class="string">"perf-literal"</span>))] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>Memmem { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| <span class="kw">use </span><span class="kw">crate</span>::util::primitives::PatternID; |
| |
| <span class="self">self</span>.<span class="number">0</span>.find(<span class="kw-2">&</span>haystack[span]).map_or(Candidate::None, |i| { |
| <span class="kw">let </span>start = span.start + i; |
| <span class="kw">let </span>end = start + <span class="self">self</span>.<span class="number">0</span>.needle().len(); |
| <span class="comment">// N.B. We can declare a match and use a fixed pattern ID here |
| // because a Memmem prefilter is only ever created for searchers |
| // with exactly one pattern. Thus, every match is always a match |
| // and it is always for the first and only pattern. |
| </span>Candidate::Match(Match::new(PatternID::ZERO, start..end)) |
| }) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing a rare byte prefilter. |
| /// |
| /// A rare byte prefilter attempts to pick out a small set of rare bytes that |
| /// occurr in the patterns, and then quickly scan to matches of those rare |
| /// bytes. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>RareBytesBuilder { |
| <span class="doccomment">/// Whether this prefilter should account for ASCII case insensitivity or |
| /// not. |
| </span>ascii_case_insensitive: bool, |
| <span class="doccomment">/// A set of rare bytes, indexed by byte value. |
| </span>rare_set: ByteSet, |
| <span class="doccomment">/// A set of byte offsets associated with bytes in a pattern. An entry |
| /// corresponds to a particular bytes (its index) and is only non-zero if |
| /// the byte occurred at an offset greater than 0 in at least one pattern. |
| /// |
| /// If a byte's offset is not representable in 8 bits, then the rare bytes |
| /// prefilter becomes inert. |
| </span>byte_offsets: RareByteOffsets, |
| <span class="doccomment">/// Whether this is available as a prefilter or not. This can be set to |
| /// false during construction if a condition is seen that invalidates the |
| /// use of the rare-byte prefilter. |
| </span>available: bool, |
| <span class="doccomment">/// The number of bytes set to an active value in `byte_offsets`. |
| </span>count: usize, |
| <span class="doccomment">/// The sum of frequency ranks for the rare bytes detected. This is |
| /// intended to give a heuristic notion of how rare the bytes are. |
| </span>rank_sum: u16, |
| } |
| |
| <span class="doccomment">/// A set of byte offsets, keyed by byte. |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">struct </span>RareByteOffsets { |
| <span class="doccomment">/// Each entry corresponds to the maximum offset of the corresponding |
| /// byte across all patterns seen. |
| </span>set: [RareByteOffset; <span class="number">256</span>], |
| } |
| |
| <span class="kw">impl </span>RareByteOffsets { |
| <span class="doccomment">/// Create a new empty set of rare byte offsets. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>empty() -> RareByteOffsets { |
| RareByteOffsets { set: [RareByteOffset::default(); <span class="number">256</span>] } |
| } |
| |
| <span class="doccomment">/// Add the given offset for the given byte to this set. If the offset is |
| /// greater than the existing offset, then it overwrites the previous |
| /// value and returns false. If there is no previous value set, then this |
| /// sets it and returns true. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>set(<span class="kw-2">&mut </span><span class="self">self</span>, byte: u8, off: RareByteOffset) { |
| <span class="self">self</span>.set[byte <span class="kw">as </span>usize].max = |
| cmp::max(<span class="self">self</span>.set[byte <span class="kw">as </span>usize].max, off.max); |
| } |
| } |
| |
| <span class="kw">impl </span>core::fmt::Debug <span class="kw">for </span>RareByteOffsets { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>core::fmt::Formatter<<span class="lifetime">'_</span>>) -> core::fmt::Result { |
| <span class="kw">let </span><span class="kw-2">mut </span>offsets = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>off <span class="kw">in </span><span class="self">self</span>.set.iter() { |
| <span class="kw">if </span>off.max > <span class="number">0 </span>{ |
| offsets.push(off); |
| } |
| } |
| f.debug_struct(<span class="string">"RareByteOffsets"</span>).field(<span class="string">"set"</span>, <span class="kw-2">&</span>offsets).finish() |
| } |
| } |
| |
| <span class="doccomment">/// Offsets associated with an occurrence of a "rare" byte in any of the |
| /// patterns used to construct a single Aho-Corasick automaton. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug)] |
| </span><span class="kw">struct </span>RareByteOffset { |
| <span class="doccomment">/// The maximum offset at which a particular byte occurs from the start |
| /// of any pattern. This is used as a shift amount. That is, when an |
| /// occurrence of this byte is found, the candidate position reported by |
| /// the prefilter is `position_of_byte - max`, such that the automaton |
| /// will begin its search at a position that is guaranteed to observe a |
| /// match. |
| /// |
| /// To avoid accidentally quadratic behavior, a prefilter is considered |
| /// ineffective when it is asked to start scanning from a position that it |
| /// has already scanned past. |
| /// |
| /// Using a `u8` here means that if we ever see a pattern that's longer |
| /// than 255 bytes, then the entire rare byte prefilter is disabled. |
| </span>max: u8, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>RareByteOffset { |
| <span class="kw">fn </span>default() -> RareByteOffset { |
| RareByteOffset { max: <span class="number">0 </span>} |
| } |
| } |
| |
| <span class="kw">impl </span>RareByteOffset { |
| <span class="doccomment">/// Create a new rare byte offset. If the given offset is too big, then |
| /// None is returned. In that case, callers should render the rare bytes |
| /// prefilter inert. |
| </span><span class="kw">fn </span>new(max: usize) -> <span class="prelude-ty">Option</span><RareByteOffset> { |
| <span class="kw">if </span>max > u8::MAX <span class="kw">as </span>usize { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="prelude-val">Some</span>(RareByteOffset { max: max <span class="kw">as </span>u8 }) |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>RareBytesBuilder { |
| <span class="doccomment">/// Create a new builder for constructing a rare byte prefilter. |
| </span><span class="kw">fn </span>new() -> RareBytesBuilder { |
| RareBytesBuilder { |
| ascii_case_insensitive: <span class="bool-val">false</span>, |
| rare_set: ByteSet::empty(), |
| byte_offsets: RareByteOffsets::empty(), |
| available: <span class="bool-val">true</span>, |
| count: <span class="number">0</span>, |
| rank_sum: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Enable ASCII case insensitivity. When set, byte strings added to this |
| /// builder will be interpreted without respect to ASCII case. |
| </span><span class="kw">fn </span>ascii_case_insensitive(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> RareBytesBuilder { |
| <span class="self">self</span>.ascii_case_insensitive = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Build the rare bytes prefilter. |
| /// |
| /// If there are more than 3 distinct rare bytes found, or if heuristics |
| /// otherwise determine that this prefilter should not be used, then `None` |
| /// is returned. |
| </span><span class="kw">fn </span>build(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">fn </span>imp(builder: <span class="kw-2">&</span>RareBytesBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="kw">if </span>!builder.available || builder.count > <span class="number">3 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>(<span class="kw-2">mut </span>bytes, <span class="kw-2">mut </span>len) = ([<span class="number">0</span>; <span class="number">3</span>], <span class="number">0</span>); |
| <span class="kw">for </span>b <span class="kw">in </span><span class="number">0</span>..=<span class="number">255 </span>{ |
| <span class="kw">if </span>builder.rare_set.contains(b) { |
| bytes[len] = b <span class="kw">as </span>u8; |
| len += <span class="number">1</span>; |
| } |
| } |
| <span class="kw">let </span>finder: Arc<<span class="kw">dyn </span>PrefilterI> = <span class="kw">match </span>len { |
| <span class="number">0 </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="number">1 </span>=> Arc::new(RareBytesOne { |
| byte1: bytes[<span class="number">0</span>], |
| offset: builder.byte_offsets.set[bytes[<span class="number">0</span>] <span class="kw">as </span>usize], |
| }), |
| <span class="number">2 </span>=> Arc::new(RareBytesTwo { |
| offsets: builder.byte_offsets, |
| byte1: bytes[<span class="number">0</span>], |
| byte2: bytes[<span class="number">1</span>], |
| }), |
| <span class="number">3 </span>=> Arc::new(RareBytesThree { |
| offsets: builder.byte_offsets, |
| byte1: bytes[<span class="number">0</span>], |
| byte2: bytes[<span class="number">1</span>], |
| byte3: bytes[<span class="number">2</span>], |
| }), |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>(), |
| }; |
| <span class="prelude-val">Some</span>(Prefilter { finder, memory_usage: <span class="number">0 </span>}) |
| } |
| |
| <span class="attribute">#[cfg(not(feature = <span class="string">"perf-literal"</span>))] |
| </span><span class="kw">fn </span>imp(<span class="kw">_</span>: <span class="kw-2">&</span>RareBytesBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="prelude-val">None |
| </span>} |
| |
| imp(<span class="self">self</span>) |
| } |
| |
| <span class="doccomment">/// Add a byte string to this builder. |
| /// |
| /// All patterns added to an Aho-Corasick automaton should be added to this |
| /// builder before attempting to construct the prefilter. |
| </span><span class="kw">fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) { |
| <span class="comment">// If we've already given up, then do nothing. |
| </span><span class="kw">if </span>!<span class="self">self</span>.available { |
| <span class="kw">return</span>; |
| } |
| <span class="comment">// If we've already blown our budget, then don't waste time looking |
| // for more rare bytes. |
| </span><span class="kw">if </span><span class="self">self</span>.count > <span class="number">3 </span>{ |
| <span class="self">self</span>.available = <span class="bool-val">false</span>; |
| <span class="kw">return</span>; |
| } |
| <span class="comment">// If the pattern is too long, then our offset table is bunk, so |
| // give up. |
| </span><span class="kw">if </span>bytes.len() >= <span class="number">256 </span>{ |
| <span class="self">self</span>.available = <span class="bool-val">false</span>; |
| <span class="kw">return</span>; |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>rarest = <span class="kw">match </span>bytes.get(<span class="number">0</span>) { |
| <span class="prelude-val">None </span>=> <span class="kw">return</span>, |
| <span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) => (b, freq_rank(b)), |
| }; |
| <span class="comment">// The idea here is to look for the rarest byte in each pattern, and |
| // add that to our set. As a special exception, if we see a byte that |
| // we've already added, then we immediately stop and choose that byte, |
| // even if there's another rare byte in the pattern. This helps us |
| // apply the rare byte optimization in more cases by attempting to pick |
| // bytes that are in common between patterns. So for example, if we |
| // were searching for `Sherlock` and `lockjaw`, then this would pick |
| // `k` for both patterns, resulting in the use of `memchr` instead of |
| // `memchr2` for `k` and `j`. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>found = <span class="bool-val">false</span>; |
| <span class="kw">for </span>(pos, <span class="kw-2">&</span>b) <span class="kw">in </span>bytes.iter().enumerate() { |
| <span class="self">self</span>.set_offset(pos, b); |
| <span class="kw">if </span>found { |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">if </span><span class="self">self</span>.rare_set.contains(b) { |
| found = <span class="bool-val">true</span>; |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">let </span>rank = freq_rank(b); |
| <span class="kw">if </span>rank < rarest.<span class="number">1 </span>{ |
| rarest = (b, rank); |
| } |
| } |
| <span class="kw">if </span>!found { |
| <span class="self">self</span>.add_rare_byte(rarest.<span class="number">0</span>); |
| } |
| } |
| |
| <span class="kw">fn </span>set_offset(<span class="kw-2">&mut </span><span class="self">self</span>, pos: usize, byte: u8) { |
| <span class="comment">// This unwrap is OK because pos is never bigger than our max. |
| </span><span class="kw">let </span>offset = RareByteOffset::new(pos).unwrap(); |
| <span class="self">self</span>.byte_offsets.set(byte, offset); |
| <span class="kw">if </span><span class="self">self</span>.ascii_case_insensitive { |
| <span class="self">self</span>.byte_offsets.set(opposite_ascii_case(byte), offset); |
| } |
| } |
| |
| <span class="kw">fn </span>add_rare_byte(<span class="kw-2">&mut </span><span class="self">self</span>, byte: u8) { |
| <span class="self">self</span>.add_one_rare_byte(byte); |
| <span class="kw">if </span><span class="self">self</span>.ascii_case_insensitive { |
| <span class="self">self</span>.add_one_rare_byte(opposite_ascii_case(byte)); |
| } |
| } |
| |
| <span class="kw">fn </span>add_one_rare_byte(<span class="kw-2">&mut </span><span class="self">self</span>, byte: u8) { |
| <span class="kw">if </span>!<span class="self">self</span>.rare_set.contains(byte) { |
| <span class="self">self</span>.rare_set.add(byte); |
| <span class="self">self</span>.count += <span class="number">1</span>; |
| <span class="self">self</span>.rank_sum += freq_rank(byte) <span class="kw">as </span>u16; |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for a single "rare" byte. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>RareBytesOne { |
| byte1: u8, |
| offset: RareByteOffset, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>RareBytesOne { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr(<span class="self">self</span>.byte1, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| { |
| <span class="kw">let </span>pos = span.start + i; |
| cmp::max( |
| span.start, |
| pos.saturating_sub(usize::from(<span class="self">self</span>.offset.max)), |
| ) |
| }) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for two "rare" bytes. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>RareBytesTwo { |
| offsets: RareByteOffsets, |
| byte1: u8, |
| byte2: u8, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>RareBytesTwo { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr2(<span class="self">self</span>.byte1, <span class="self">self</span>.byte2, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| { |
| <span class="kw">let </span>pos = span.start + i; |
| <span class="kw">let </span>offset = <span class="self">self</span>.offsets.set[usize::from(haystack[pos])].max; |
| cmp::max(span.start, pos.saturating_sub(usize::from(offset))) |
| }) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for three "rare" bytes. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>RareBytesThree { |
| offsets: RareByteOffsets, |
| byte1: u8, |
| byte2: u8, |
| byte3: u8, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>RareBytesThree { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr3(<span class="self">self</span>.byte1, <span class="self">self</span>.byte2, <span class="self">self</span>.byte3, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| { |
| <span class="kw">let </span>pos = span.start + i; |
| <span class="kw">let </span>offset = <span class="self">self</span>.offsets.set[usize::from(haystack[pos])].max; |
| cmp::max(span.start, pos.saturating_sub(usize::from(offset))) |
| }) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing a starting byte prefilter. |
| /// |
| /// A starting byte prefilter is a simplistic prefilter that looks for possible |
| /// matches by reporting all positions corresponding to a particular byte. This |
| /// generally only takes affect when there are at most 3 distinct possible |
| /// starting bytes. e.g., the patterns `foo`, `bar`, and `baz` have two |
| /// distinct starting bytes (`f` and `b`), and this prefilter returns all |
| /// occurrences of either `f` or `b`. |
| /// |
| /// In some cases, a heuristic frequency analysis may determine that it would |
| /// be better not to use this prefilter even when there are 3 or fewer distinct |
| /// starting bytes. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>StartBytesBuilder { |
| <span class="doccomment">/// Whether this prefilter should account for ASCII case insensitivity or |
| /// not. |
| </span>ascii_case_insensitive: bool, |
| <span class="doccomment">/// The set of starting bytes observed. |
| </span>byteset: Vec<bool>, |
| <span class="doccomment">/// The number of bytes set to true in `byteset`. |
| </span>count: usize, |
| <span class="doccomment">/// The sum of frequency ranks for the rare bytes detected. This is |
| /// intended to give a heuristic notion of how rare the bytes are. |
| </span>rank_sum: u16, |
| } |
| |
| <span class="kw">impl </span>StartBytesBuilder { |
| <span class="doccomment">/// Create a new builder for constructing a start byte prefilter. |
| </span><span class="kw">fn </span>new() -> StartBytesBuilder { |
| StartBytesBuilder { |
| ascii_case_insensitive: <span class="bool-val">false</span>, |
| byteset: <span class="macro">vec!</span>[<span class="bool-val">false</span>; <span class="number">256</span>], |
| count: <span class="number">0</span>, |
| rank_sum: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Enable ASCII case insensitivity. When set, byte strings added to this |
| /// builder will be interpreted without respect to ASCII case. |
| </span><span class="kw">fn </span>ascii_case_insensitive(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> StartBytesBuilder { |
| <span class="self">self</span>.ascii_case_insensitive = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Build the starting bytes prefilter. |
| /// |
| /// If there are more than 3 distinct starting bytes, or if heuristics |
| /// otherwise determine that this prefilter should not be used, then `None` |
| /// is returned. |
| </span><span class="kw">fn </span>build(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">fn </span>imp(builder: <span class="kw-2">&</span>StartBytesBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="kw">if </span>builder.count > <span class="number">3 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>(<span class="kw-2">mut </span>bytes, <span class="kw-2">mut </span>len) = ([<span class="number">0</span>; <span class="number">3</span>], <span class="number">0</span>); |
| <span class="kw">for </span>b <span class="kw">in </span><span class="number">0</span>..<span class="number">256 </span>{ |
| <span class="kw">if </span>!builder.byteset[b] { |
| <span class="kw">continue</span>; |
| } |
| <span class="comment">// We don't handle non-ASCII bytes for now. Getting non-ASCII |
| // bytes right is trickier, since we generally don't want to put |
| // a leading UTF-8 code unit into a prefilter that isn't ASCII, |
| // since they can frequently. Instead, it would be better to use a |
| // continuation byte, but this requires more sophisticated analysis |
| // of the automaton and a richer prefilter API. |
| </span><span class="kw">if </span>b > <span class="number">0x7F </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| bytes[len] = b <span class="kw">as </span>u8; |
| len += <span class="number">1</span>; |
| } |
| <span class="kw">let </span>finder: Arc<<span class="kw">dyn </span>PrefilterI> = <span class="kw">match </span>len { |
| <span class="number">0 </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="number">1 </span>=> Arc::new(StartBytesOne { byte1: bytes[<span class="number">0</span>] }), |
| <span class="number">2 </span>=> Arc::new(StartBytesTwo { |
| byte1: bytes[<span class="number">0</span>], |
| byte2: bytes[<span class="number">1</span>], |
| }), |
| <span class="number">3 </span>=> Arc::new(StartBytesThree { |
| byte1: bytes[<span class="number">0</span>], |
| byte2: bytes[<span class="number">1</span>], |
| byte3: bytes[<span class="number">2</span>], |
| }), |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>(), |
| }; |
| <span class="prelude-val">Some</span>(Prefilter { finder, memory_usage: <span class="number">0 </span>}) |
| } |
| |
| <span class="attribute">#[cfg(not(feature = <span class="string">"perf-literal"</span>))] |
| </span><span class="kw">fn </span>imp(<span class="kw">_</span>: <span class="kw-2">&</span>StartBytesBuilder) -> <span class="prelude-ty">Option</span><Prefilter> { |
| <span class="prelude-val">None |
| </span>} |
| |
| imp(<span class="self">self</span>) |
| } |
| |
| <span class="doccomment">/// Add a byte string to this builder. |
| /// |
| /// All patterns added to an Aho-Corasick automaton should be added to this |
| /// builder before attempting to construct the prefilter. |
| </span><span class="kw">fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) { |
| <span class="kw">if </span><span class="self">self</span>.count > <span class="number">3 </span>{ |
| <span class="kw">return</span>; |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">&</span>byte) = bytes.get(<span class="number">0</span>) { |
| <span class="self">self</span>.add_one_byte(byte); |
| <span class="kw">if </span><span class="self">self</span>.ascii_case_insensitive { |
| <span class="self">self</span>.add_one_byte(opposite_ascii_case(byte)); |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>add_one_byte(<span class="kw-2">&mut </span><span class="self">self</span>, byte: u8) { |
| <span class="kw">if </span>!<span class="self">self</span>.byteset[byte <span class="kw">as </span>usize] { |
| <span class="self">self</span>.byteset[byte <span class="kw">as </span>usize] = <span class="bool-val">true</span>; |
| <span class="self">self</span>.count += <span class="number">1</span>; |
| <span class="self">self</span>.rank_sum += freq_rank(byte) <span class="kw">as </span>u16; |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for a single starting byte. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>StartBytesOne { |
| byte1: u8, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>StartBytesOne { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr(<span class="self">self</span>.byte1, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| span.start + i) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for two starting bytes. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>StartBytesTwo { |
| byte1: u8, |
| byte2: u8, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>StartBytesTwo { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr2(<span class="self">self</span>.byte1, <span class="self">self</span>.byte2, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| span.start + i) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter for scanning for three starting bytes. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| #[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>StartBytesThree { |
| byte1: u8, |
| byte2: u8, |
| byte3: u8, |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"perf-literal"</span>)] |
| </span><span class="kw">impl </span>PrefilterI <span class="kw">for </span>StartBytesThree { |
| <span class="kw">fn </span>find_in(<span class="kw-2">&</span><span class="self">self</span>, haystack: <span class="kw-2">&</span>[u8], span: Span) -> Candidate { |
| memchr::memchr3(<span class="self">self</span>.byte1, <span class="self">self</span>.byte2, <span class="self">self</span>.byte3, <span class="kw-2">&</span>haystack[span]) |
| .map(|i| span.start + i) |
| .map_or(Candidate::None, Candidate::PossibleStartOfMatch) |
| } |
| } |
| |
| <span class="doccomment">/// If the given byte is an ASCII letter, then return it in the opposite case. |
| /// e.g., Given `b'A'`, this returns `b'a'`, and given `b'a'`, this returns |
| /// `b'A'`. If a non-ASCII letter is given, then the given byte is returned. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>opposite_ascii_case(b: u8) -> u8 { |
| <span class="kw">if </span><span class="string">b'A' </span><= b && b <= <span class="string">b'Z' </span>{ |
| b.to_ascii_lowercase() |
| } <span class="kw">else if </span><span class="string">b'a' </span><= b && b <= <span class="string">b'z' </span>{ |
| b.to_ascii_uppercase() |
| } <span class="kw">else </span>{ |
| b |
| } |
| } |
| |
| <span class="doccomment">/// Return the frequency rank of the given byte. The higher the rank, the more |
| /// common the byte (heuristically speaking). |
| </span><span class="kw">fn </span>freq_rank(b: u8) -> u8 { |
| <span class="kw">use </span><span class="kw">crate</span>::util::byte_frequencies::BYTE_FREQUENCIES; |
| BYTE_FREQUENCIES[b <span class="kw">as </span>usize] |
| } |
| </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> |