| <!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/memchr-2.5.0/src/memmem/prefilter/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.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="../../../../memchr/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="../../../../memchr/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> |
| </pre><pre class="rust"><code><span class="kw">use </span><span class="kw">crate</span>::memmem::{rarebytes::RareNeedleBytes, NeedleInfo}; |
| |
| <span class="kw">mod </span>fallback; |
| <span class="attribute">#[cfg(memchr_runtime_simd)] |
| </span><span class="kw">mod </span>genericsimd; |
| <span class="attribute">#[cfg(all(not(miri), target_arch = <span class="string">"wasm32"</span>, memchr_runtime_simd))] |
| </span><span class="kw">mod </span>wasm; |
| <span class="attribute">#[cfg(all(not(miri), target_arch = <span class="string">"x86_64"</span>, memchr_runtime_simd))] |
| </span><span class="kw">mod </span>x86; |
| |
| <span class="doccomment">/// The maximum frequency rank permitted for the fallback prefilter. If the |
| /// rarest byte in the needle has a frequency rank above this value, then no |
| /// prefilter is used if the fallback prefilter would otherwise be selected. |
| </span><span class="kw">const </span>MAX_FALLBACK_RANK: usize = <span class="number">250</span>; |
| |
| <span class="doccomment">/// A combination of prefilter effectiveness state, the prefilter function and |
| /// the needle info required to run a prefilter. |
| /// |
| /// For the most part, these are grouped into a single type for convenience, |
| /// instead of needing to pass around all three as distinct function |
| /// parameters. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Pre<<span class="lifetime">'a</span>> { |
| <span class="doccomment">/// State that tracks the effectiveness of a prefilter. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) state: <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>PrefilterState, |
| <span class="doccomment">/// The actual prefilter function. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) prefn: PrefilterFn, |
| <span class="doccomment">/// Information about a needle, such as its RK hash and rare byte offsets. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) ninfo: <span class="kw-2">&</span><span class="lifetime">'a </span>NeedleInfo, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Pre<<span class="lifetime">'a</span>> { |
| <span class="doccomment">/// Call this prefilter on the given haystack with the given needle. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>call( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| haystack: <span class="kw-2">&</span>[u8], |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="self">self</span>.prefn.call(<span class="self">self</span>.state, <span class="self">self</span>.ninfo, haystack, needle) |
| } |
| |
| <span class="doccomment">/// Return true if and only if this prefilter should be used. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>should_call(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.state.is_effective() |
| } |
| } |
| |
| <span class="doccomment">/// A prefilter function. |
| /// |
| /// A prefilter function describes both forward and reverse searches. |
| /// (Although, we don't currently implement prefilters for reverse searching.) |
| /// In the case of a forward search, the position returned corresponds to |
| /// the starting offset of a match (confirmed or possible). Its minimum |
| /// value is `0`, and its maximum value is `haystack.len() - 1`. In the case |
| /// of a reverse search, the position returned corresponds to the position |
| /// immediately after a match (confirmed or possible). Its minimum value is `1` |
| /// and its maximum value is `haystack.len()`. |
| /// |
| /// In both cases, the position returned is the starting (or ending) point of a |
| /// _possible_ match. That is, returning a false positive is okay. A prefilter, |
| /// however, must never return any false negatives. That is, if a match exists |
| /// at a particular position `i`, then a prefilter _must_ return that position. |
| /// It cannot skip past it. |
| /// |
| /// # Safety |
| /// |
| /// A prefilter function is not safe to create, since not all prefilters are |
| /// safe to call in all contexts. (e.g., A prefilter that uses AVX instructions |
| /// may only be called on x86_64 CPUs with the relevant AVX feature enabled.) |
| /// Thus, callers must ensure that when a prefilter function is created that it |
| /// is safe to call for the current environment. |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>PrefilterFn(PrefilterFnTy); |
| |
| <span class="doccomment">/// The type of a prefilter function. All prefilters must satisfy this |
| /// signature. |
| /// |
| /// Using a function pointer like this does inhibit inlining, but it does |
| /// eliminate branching and the extra costs associated with copying a larger |
| /// enum. Note also, that using Box<dyn SomePrefilterTrait> can't really work |
| /// here, since we want to work in contexts that don't have dynamic memory |
| /// allocation. Moreover, in the default configuration of this crate on x86_64 |
| /// CPUs released in the past ~decade, we will use an AVX2-optimized prefilter, |
| /// which generally won't be inlineable into the surrounding code anyway. |
| /// (Unless AVX2 is enabled at compile time, but this is typically rare, since |
| /// it produces a non-portable binary.) |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">type </span>PrefilterFnTy = <span class="kw">unsafe fn</span>( |
| prestate: <span class="kw-2">&mut </span>PrefilterState, |
| ninfo: <span class="kw-2">&</span>NeedleInfo, |
| haystack: <span class="kw-2">&</span>[u8], |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><usize>; |
| |
| <span class="comment">// If the haystack is too small for SSE2, then just run memchr on the |
| // rarest byte and be done with it. (It is likely that this code path is |
| // rarely exercised, since a higher level routine will probably dispatch to |
| // Rabin-Karp for such a small haystack.) |
| </span><span class="attribute">#[cfg(memchr_runtime_simd)] |
| </span><span class="kw">fn </span>simple_memchr_fallback( |
| _prestate: <span class="kw-2">&mut </span>PrefilterState, |
| ninfo: <span class="kw-2">&</span>NeedleInfo, |
| haystack: <span class="kw-2">&</span>[u8], |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">let </span>(rare, <span class="kw">_</span>) = ninfo.rarebytes.as_rare_ordered_usize(); |
| <span class="kw">crate</span>::memchr(needle[rare], haystack).map(|i| i.saturating_sub(rare)) |
| } |
| |
| <span class="kw">impl </span>PrefilterFn { |
| <span class="doccomment">/// Create a new prefilter function from the function pointer given. |
| /// |
| /// # Safety |
| /// |
| /// Callers must ensure that the given prefilter function is safe to call |
| /// for all inputs in the current environment. For example, if the given |
| /// prefilter function uses AVX instructions, then the caller must ensure |
| /// that the appropriate AVX CPU features are enabled. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">unsafe fn </span>new(prefn: PrefilterFnTy) -> PrefilterFn { |
| PrefilterFn(prefn) |
| } |
| |
| <span class="doccomment">/// Call the underlying prefilter function with the given arguments. |
| </span><span class="kw">pub fn </span>call( |
| <span class="self">self</span>, |
| prestate: <span class="kw-2">&mut </span>PrefilterState, |
| ninfo: <span class="kw-2">&</span>NeedleInfo, |
| haystack: <span class="kw-2">&</span>[u8], |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="comment">// SAFETY: Callers have the burden of ensuring that a prefilter |
| // function is safe to call for all inputs in the current environment. |
| </span><span class="kw">unsafe </span>{ (<span class="self">self</span>.<span class="number">0</span>)(prestate, ninfo, haystack, needle) } |
| } |
| } |
| |
| <span class="kw">impl </span>core::fmt::Debug <span class="kw">for </span>PrefilterFn { |
| <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) -> core::fmt::Result { |
| <span class="string">"<prefilter-fn(...)>"</span>.fmt(f) |
| } |
| } |
| |
| <span class="doccomment">/// Prefilter controls whether heuristics are used to accelerate searching. |
| /// |
| /// A prefilter refers to the idea of detecting candidate matches very quickly, |
| /// and then confirming whether those candidates are full matches. This |
| /// idea can be quite effective since it's often the case that looking for |
| /// candidates can be a lot faster than running a complete substring search |
| /// over the entire input. Namely, looking for candidates can be done with |
| /// extremely fast vectorized code. |
| /// |
| /// The downside of a prefilter is that it assumes false positives (which are |
| /// candidates generated by a prefilter that aren't matches) are somewhat rare |
| /// relative to the frequency of full matches. That is, if a lot of false |
| /// positives are generated, then it's possible for search time to be worse |
| /// than if the prefilter wasn't enabled in the first place. |
| /// |
| /// Another downside of a prefilter is that it can result in highly variable |
| /// performance, where some cases are extraordinarily fast and others aren't. |
| /// Typically, variable performance isn't a problem, but it may be for your use |
| /// case. |
| /// |
| /// The use of prefilters in this implementation does use a heuristic to detect |
| /// when a prefilter might not be carrying its weight, and will dynamically |
| /// disable its use. Nevertheless, this configuration option gives callers |
| /// the ability to disable prefilters if you have knowledge that they won't be |
| /// useful. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug)] |
| #[non_exhaustive] |
| </span><span class="kw">pub enum </span>Prefilter { |
| <span class="doccomment">/// Never used a prefilter in substring search. |
| </span><span class="prelude-val">None</span>, |
| <span class="doccomment">/// Automatically detect whether a heuristic prefilter should be used. If |
| /// it is used, then heuristics will be used to dynamically disable the |
| /// prefilter if it is believed to not be carrying its weight. |
| </span>Auto, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>Prefilter { |
| <span class="kw">fn </span>default() -> Prefilter { |
| Prefilter::Auto |
| } |
| } |
| |
| <span class="kw">impl </span>Prefilter { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>is_none(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Prefilter::None => <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// PrefilterState tracks state associated with the effectiveness of a |
| /// prefilter. It is used to track how many bytes, on average, are skipped by |
| /// the prefilter. If this average dips below a certain threshold over time, |
| /// then the state renders the prefilter inert and stops using it. |
| /// |
| /// A prefilter state should be created for each search. (Where creating an |
| /// iterator is treated as a single search.) A prefilter state should only be |
| /// created from a `Freqy`. e.g., An inert `Freqy` will produce an inert |
| /// `PrefilterState`. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>PrefilterState { |
| <span class="doccomment">/// The number of skips that has been executed. This is always 1 greater |
| /// than the actual number of skips. The special sentinel value of 0 |
| /// indicates that the prefilter is inert. This is useful to avoid |
| /// additional checks to determine whether the prefilter is still |
| /// "effective." Once a prefilter becomes inert, it should no longer be |
| /// used (according to our heuristics). |
| </span>skips: u32, |
| <span class="doccomment">/// The total number of bytes that have been skipped. |
| </span>skipped: u32, |
| } |
| |
| <span class="kw">impl </span>PrefilterState { |
| <span class="doccomment">/// The minimum number of skip attempts to try before considering whether |
| /// a prefilter is effective or not. |
| </span><span class="kw">const </span>MIN_SKIPS: u32 = <span class="number">50</span>; |
| |
| <span class="doccomment">/// The minimum amount of bytes that skipping must average. |
| /// |
| /// This value was chosen based on varying it and checking |
| /// the microbenchmarks. In particular, this can impact the |
| /// pathological/repeated-{huge,small} benchmarks quite a bit if it's set |
| /// too low. |
| </span><span class="kw">const </span>MIN_SKIP_BYTES: u32 = <span class="number">8</span>; |
| |
| <span class="doccomment">/// Create a fresh prefilter state. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new() -> PrefilterState { |
| PrefilterState { skips: <span class="number">1</span>, skipped: <span class="number">0 </span>} |
| } |
| |
| <span class="doccomment">/// Create a fresh prefilter state that is always inert. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>inert() -> PrefilterState { |
| PrefilterState { skips: <span class="number">0</span>, skipped: <span class="number">0 </span>} |
| } |
| |
| <span class="doccomment">/// Update this state with the number of bytes skipped on the last |
| /// invocation of the prefilter. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>update(<span class="kw-2">&mut </span><span class="self">self</span>, skipped: usize) { |
| <span class="self">self</span>.skips = <span class="self">self</span>.skips.saturating_add(<span class="number">1</span>); |
| <span class="comment">// We need to do this dance since it's technically possible for |
| // `skipped` to overflow a `u32`. (And we use a `u32` to reduce the |
| // size of a prefilter state.) |
| </span><span class="kw">if </span>skipped > core::u32::MAX <span class="kw">as </span>usize { |
| <span class="self">self</span>.skipped = core::u32::MAX; |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.skipped = <span class="self">self</span>.skipped.saturating_add(skipped <span class="kw">as </span>u32); |
| } |
| } |
| |
| <span class="doccomment">/// Return true if and only if this state indicates that a prefilter is |
| /// still effective. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>is_effective(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="kw">if </span><span class="self">self</span>.is_inert() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="kw">if </span><span class="self">self</span>.skips() < PrefilterState::MIN_SKIPS { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="kw">if </span><span class="self">self</span>.skipped >= PrefilterState::MIN_SKIP_BYTES * <span class="self">self</span>.skips() { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| |
| <span class="comment">// We're inert. |
| </span><span class="self">self</span>.skips = <span class="number">0</span>; |
| <span class="bool-val">false |
| </span>} |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>is_inert(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.skips == <span class="number">0 |
| </span>} |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>skips(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.skips.saturating_sub(<span class="number">1</span>) |
| } |
| } |
| |
| <span class="doccomment">/// Determine which prefilter function, if any, to use. |
| /// |
| /// This only applies to x86_64 when runtime SIMD detection is enabled (which |
| /// is the default). In general, we try to use an AVX prefilter, followed by |
| /// SSE and then followed by a generic one based on memchr. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>forward( |
| config: <span class="kw-2">&</span>Prefilter, |
| rare: <span class="kw-2">&</span>RareNeedleBytes, |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><PrefilterFn> { |
| <span class="kw">if </span>config.is_none() || needle.len() <= <span class="number">1 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| |
| <span class="attribute">#[cfg(all(not(miri), target_arch = <span class="string">"x86_64"</span>, memchr_runtime_simd))] |
| </span>{ |
| <span class="attribute">#[cfg(feature = <span class="string">"std"</span>)] |
| </span>{ |
| <span class="kw">if </span><span class="macro">cfg!</span>(memchr_runtime_avx) { |
| <span class="kw">if </span><span class="macro">is_x86_feature_detected!</span>(<span class="string">"avx2"</span>) { |
| <span class="comment">// SAFETY: x86::avx::find only requires the avx2 feature, |
| // which we've just checked above. |
| </span><span class="kw">return unsafe </span>{ <span class="prelude-val">Some</span>(PrefilterFn::new(x86::avx::find)) }; |
| } |
| } |
| } |
| <span class="kw">if </span><span class="macro">cfg!</span>(memchr_runtime_sse2) { |
| <span class="comment">// SAFETY: x86::sse::find only requires the sse2 feature, which is |
| // guaranteed to be available on x86_64. |
| </span><span class="kw">return unsafe </span>{ <span class="prelude-val">Some</span>(PrefilterFn::new(x86::sse::find)) }; |
| } |
| } |
| <span class="attribute">#[cfg(all(not(miri), target_arch = <span class="string">"wasm32"</span>, memchr_runtime_simd))] |
| </span>{ |
| <span class="comment">// SAFETY: `wasm::find` is actually a safe function |
| // |
| // Also note that the `if true` is here to prevent, on wasm with simd, |
| // rustc warning about the code below being dead code. |
| </span><span class="kw">if </span><span class="bool-val">true </span>{ |
| <span class="kw">return unsafe </span>{ <span class="prelude-val">Some</span>(PrefilterFn::new(wasm::find)) }; |
| } |
| } |
| <span class="comment">// Check that our rarest byte has a reasonably low rank. The main issue |
| // here is that the fallback prefilter can perform pretty poorly if it's |
| // given common bytes. So we try to avoid the worst cases here. |
| </span><span class="kw">let </span>(rare1_rank, <span class="kw">_</span>) = rare.as_ranks(needle); |
| <span class="kw">if </span>rare1_rank <= MAX_FALLBACK_RANK { |
| <span class="comment">// SAFETY: fallback::find is safe to call in all environments. |
| </span><span class="kw">return unsafe </span>{ <span class="prelude-val">Some</span>(PrefilterFn::new(fallback::find)) }; |
| } |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="doccomment">/// Return the minimum length of the haystack in which a prefilter should be |
| /// used. If the haystack is below this length, then it's probably not worth |
| /// the overhead of running the prefilter. |
| /// |
| /// We used to look at the length of a haystack here. That is, if it was too |
| /// small, then don't bother with the prefilter. But two things changed: |
| /// the prefilter falls back to memchr for small haystacks, and, at the |
| /// meta-searcher level, Rabin-Karp is employed for tiny haystacks anyway. |
| /// |
| /// We keep it around for now in case we want to bring it back. |
| </span><span class="attribute">#[allow(dead_code)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>minimum_len(_haystack: <span class="kw-2">&</span>[u8], needle: <span class="kw-2">&</span>[u8]) -> usize { |
| <span class="comment">// If the haystack length isn't greater than needle.len() * FACTOR, then |
| // no prefilter will be used. The presumption here is that since there |
| // are so few bytes to check, it's not worth running the prefilter since |
| // there will need to be a validation step anyway. Thus, the prefilter is |
| // largely redundant work. |
| // |
| // Increase the factor noticeably hurts the |
| // memmem/krate/prebuilt/teeny-*/never-john-watson benchmarks. |
| </span><span class="kw">const </span>PREFILTER_LENGTH_FACTOR: usize = <span class="number">2</span>; |
| <span class="kw">const </span>VECTOR_MIN_LENGTH: usize = <span class="number">16</span>; |
| <span class="kw">let </span>min = core::cmp::max( |
| VECTOR_MIN_LENGTH, |
| PREFILTER_LENGTH_FACTOR * needle.len(), |
| ); |
| <span class="comment">// For haystacks with length==min, we still want to avoid the prefilter, |
| // so add 1. |
| </span>min + <span class="number">1 |
| </span>} |
| |
| <span class="attribute">#[cfg(all(test, feature = <span class="string">"std"</span>, not(miri)))] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">mod </span>tests { |
| <span class="kw">use </span>std::convert::{TryFrom, TryInto}; |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::memmem::{ |
| prefilter::PrefilterFnTy, rabinkarp, rarebytes::RareNeedleBytes, |
| }; |
| |
| <span class="comment">// Below is a small jig that generates prefilter tests. The main purpose |
| // of this jig is to generate tests of varying needle/haystack lengths |
| // in order to try and exercise all code paths in our prefilters. And in |
| // particular, this is especially important for vectorized prefilters where |
| // certain code paths might only be exercised at certain lengths. |
| |
| </span><span class="doccomment">/// A test that represents the input and expected output to a prefilter |
| /// function. The test should be able to run with any prefilter function |
| /// and get the expected output. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>PrefilterTest { |
| <span class="comment">// These fields represent the inputs and expected output of a forwards |
| // prefilter function. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) ninfo: NeedleInfo, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) haystack: Vec<u8>, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) needle: Vec<u8>, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) output: <span class="prelude-ty">Option</span><usize>, |
| } |
| |
| <span class="kw">impl </span>PrefilterTest { |
| <span class="doccomment">/// Run all generated forward prefilter tests on the given prefn. |
| /// |
| /// # Safety |
| /// |
| /// Callers must ensure that the given prefilter function pointer is |
| /// safe to call for all inputs in the current environment. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">unsafe fn </span>run_all_tests(prefn: PrefilterFnTy) { |
| PrefilterTest::run_all_tests_filter(prefn, |<span class="kw">_</span>| <span class="bool-val">true</span>) |
| } |
| |
| <span class="doccomment">/// Run all generated forward prefilter tests that pass the given |
| /// predicate on the given prefn. |
| /// |
| /// # Safety |
| /// |
| /// Callers must ensure that the given prefilter function pointer is |
| /// safe to call for all inputs in the current environment. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">unsafe fn </span>run_all_tests_filter( |
| prefn: PrefilterFnTy, |
| <span class="kw-2">mut </span>predicate: <span class="kw">impl </span>FnMut(<span class="kw-2">&</span>PrefilterTest) -> bool, |
| ) { |
| <span class="kw">for </span>seed <span class="kw">in </span>PREFILTER_TEST_SEEDS { |
| <span class="kw">for </span>test <span class="kw">in </span>seed.generate() { |
| <span class="kw">if </span>predicate(<span class="kw-2">&</span>test) { |
| test.run(prefn); |
| } |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Create a new prefilter test from a seed and some chose offsets to |
| /// rare bytes in the seed's needle. |
| /// |
| /// If a valid test could not be constructed, then None is returned. |
| /// (Currently, we take the approach of massaging tests to be valid |
| /// instead of rejecting them outright.) |
| </span><span class="kw">fn </span>new( |
| seed: PrefilterTestSeed, |
| rare1i: usize, |
| rare2i: usize, |
| haystack_len: usize, |
| needle_len: usize, |
| output: <span class="prelude-ty">Option</span><usize>, |
| ) -> <span class="prelude-ty">Option</span><PrefilterTest> { |
| <span class="kw">let </span><span class="kw-2">mut </span>rare1i: u8 = rare1i.try_into().unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>rare2i: u8 = rare2i.try_into().unwrap(); |
| <span class="comment">// The '#' byte is never used in a haystack (unless we're expecting |
| // a match), while the '@' byte is never used in a needle. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>haystack = <span class="macro">vec!</span>[<span class="string">b'@'</span>; haystack_len]; |
| <span class="kw">let </span><span class="kw-2">mut </span>needle = <span class="macro">vec!</span>[<span class="string">b'#'</span>; needle_len]; |
| needle[<span class="number">0</span>] = seed.first; |
| needle[rare1i <span class="kw">as </span>usize] = seed.rare1; |
| needle[rare2i <span class="kw">as </span>usize] = seed.rare2; |
| <span class="comment">// If we're expecting a match, then make sure the needle occurs |
| // in the haystack at the expected position. |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(i) = output { |
| haystack[i..i + needle.len()].copy_from_slice(<span class="kw-2">&</span>needle); |
| } |
| <span class="comment">// If the operations above lead to rare offsets pointing to the |
| // non-first occurrence of a byte, then adjust it. This might lead |
| // to redundant tests, but it's simpler than trying to change the |
| // generation process I think. |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(i) = <span class="kw">crate</span>::memchr(seed.rare1, <span class="kw-2">&</span>needle) { |
| rare1i = u8::try_from(i).unwrap(); |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(i) = <span class="kw">crate</span>::memchr(seed.rare2, <span class="kw-2">&</span>needle) { |
| rare2i = u8::try_from(i).unwrap(); |
| } |
| <span class="kw">let </span>ninfo = NeedleInfo { |
| rarebytes: RareNeedleBytes::new(rare1i, rare2i), |
| nhash: rabinkarp::NeedleHash::forward(<span class="kw-2">&</span>needle), |
| }; |
| <span class="prelude-val">Some</span>(PrefilterTest { ninfo, haystack, needle, output }) |
| } |
| |
| <span class="doccomment">/// Run this specific test on the given prefilter function. If the |
| /// outputs do no match, then this routine panics with a failure |
| /// message. |
| /// |
| /// # Safety |
| /// |
| /// Callers must ensure that the given prefilter function pointer is |
| /// safe to call for all inputs in the current environment. |
| </span><span class="kw">unsafe fn </span>run(<span class="kw-2">&</span><span class="self">self</span>, prefn: PrefilterFnTy) { |
| <span class="kw">let </span><span class="kw-2">mut </span>prestate = PrefilterState::new(); |
| <span class="macro">assert_eq!</span>( |
| <span class="self">self</span>.output, |
| prefn( |
| <span class="kw-2">&mut </span>prestate, |
| <span class="kw-2">&</span><span class="self">self</span>.ninfo, |
| <span class="kw-2">&</span><span class="self">self</span>.haystack, |
| <span class="kw-2">&</span><span class="self">self</span>.needle |
| ), |
| <span class="string">"ninfo: {:?}, haystack(len={}): {:?}, needle(len={}): {:?}"</span>, |
| <span class="self">self</span>.ninfo, |
| <span class="self">self</span>.haystack.len(), |
| std::str::from_utf8(<span class="kw-2">&</span><span class="self">self</span>.haystack).unwrap(), |
| <span class="self">self</span>.needle.len(), |
| std::str::from_utf8(<span class="kw-2">&</span><span class="self">self</span>.needle).unwrap(), |
| ); |
| } |
| } |
| |
| <span class="doccomment">/// A set of prefilter test seeds. Each seed serves as the base for the |
| /// generation of many other tests. In essence, the seed captures the |
| /// "rare" and first bytes among our needle. The tests generated from each |
| /// seed essentially vary the length of the needle and haystack, while |
| /// using the rare/first byte configuration from the seed. |
| /// |
| /// The purpose of this is to test many different needle/haystack lengths. |
| /// In particular, some of the vector optimizations might only have bugs |
| /// in haystacks of a certain size. |
| </span><span class="kw">const </span>PREFILTER_TEST_SEEDS: <span class="kw-2">&</span>[PrefilterTestSeed] = <span class="kw-2">&</span>[ |
| PrefilterTestSeed { first: <span class="string">b'x'</span>, rare1: <span class="string">b'y'</span>, rare2: <span class="string">b'z' </span>}, |
| PrefilterTestSeed { first: <span class="string">b'x'</span>, rare1: <span class="string">b'x'</span>, rare2: <span class="string">b'z' </span>}, |
| PrefilterTestSeed { first: <span class="string">b'x'</span>, rare1: <span class="string">b'y'</span>, rare2: <span class="string">b'x' </span>}, |
| PrefilterTestSeed { first: <span class="string">b'x'</span>, rare1: <span class="string">b'x'</span>, rare2: <span class="string">b'x' </span>}, |
| PrefilterTestSeed { first: <span class="string">b'x'</span>, rare1: <span class="string">b'y'</span>, rare2: <span class="string">b'y' </span>}, |
| ]; |
| |
| <span class="doccomment">/// Data that describes a single prefilter test seed. |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">struct </span>PrefilterTestSeed { |
| first: u8, |
| rare1: u8, |
| rare2: u8, |
| } |
| |
| <span class="kw">impl </span>PrefilterTestSeed { |
| <span class="doccomment">/// Generate a series of prefilter tests from this seed. |
| </span><span class="kw">fn </span>generate(<span class="self">self</span>) -> <span class="kw">impl </span>Iterator<Item = PrefilterTest> { |
| <span class="kw">let </span>len_start = <span class="number">2</span>; |
| <span class="comment">// The iterator below generates *a lot* of tests. The number of |
| // tests was chosen somewhat empirically to be "bearable" when |
| // running the test suite. |
| // |
| // We use an iterator here because the collective haystacks of all |
| // these test cases add up to enough memory to OOM a conservative |
| // sandbox or a small laptop. |
| </span>(len_start..=<span class="number">40</span>).flat_map(<span class="kw">move </span>|needle_len| { |
| <span class="kw">let </span>rare_start = len_start - <span class="number">1</span>; |
| (rare_start..needle_len).flat_map(<span class="kw">move </span>|rare1i| { |
| (rare1i..needle_len).flat_map(<span class="kw">move </span>|rare2i| { |
| (needle_len..=<span class="number">66</span>).flat_map(<span class="kw">move </span>|haystack_len| { |
| PrefilterTest::new( |
| <span class="self">self</span>, |
| rare1i, |
| rare2i, |
| haystack_len, |
| needle_len, |
| <span class="prelude-val">None</span>, |
| ) |
| .into_iter() |
| .chain( |
| (<span class="number">0</span>..=(haystack_len - needle_len)).flat_map( |
| <span class="kw">move </span>|output| { |
| PrefilterTest::new( |
| <span class="self">self</span>, |
| rare1i, |
| rare2i, |
| haystack_len, |
| needle_len, |
| <span class="prelude-val">Some</span>(output), |
| ) |
| }, |
| ), |
| ) |
| }) |
| }) |
| }) |
| }) |
| } |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../../" data-current-crate="memchr" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
