| <!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/dfa.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>dfa.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> |
| </pre><pre class="rust"><code><span class="doccomment">/*! |
| Provides direct access to a DFA implementation of Aho-Corasick. |
| |
| This is a low-level API that generally only needs to be used in niche |
| circumstances. When possible, prefer using [`AhoCorasick`](crate::AhoCorasick) |
| instead of a DFA directly. Using an `DFA` directly is typically only necessary |
| when one needs access to the [`Automaton`] trait implementation. |
| */ |
| |
| </span><span class="kw">use </span>alloc::{vec, vec::Vec}; |
| |
| <span class="kw">use crate</span>::{ |
| automaton::Automaton, |
| nfa::noncontiguous, |
| util::{ |
| alphabet::ByteClasses, |
| error::{BuildError, MatchError}, |
| int::{Usize, U32}, |
| prefilter::Prefilter, |
| primitives::{IteratorIndexExt, PatternID, SmallIndex, StateID}, |
| search::{Anchored, MatchKind, StartKind}, |
| special::Special, |
| }, |
| }; |
| |
| <span class="doccomment">/// A DFA implementation of Aho-Corasick. |
| /// |
| /// When possible, prefer using [`AhoCorasick`](crate::AhoCorasick) instead of |
| /// this type directly. Using a `DFA` directly is typically only necessary when |
| /// one needs access to the [`Automaton`] trait implementation. |
| /// |
| /// This DFA can only be built by first constructing a [`noncontiguous::NFA`]. |
| /// Both [`DFA::new`] and [`Builder::build`] do this for you automatically, but |
| /// [`Builder::build_from_noncontiguous`] permits doing it explicitly. |
| /// |
| /// A DFA provides the best possible search performance (in this crate) via two |
| /// mechanisms: |
| /// |
| /// * All states use a dense representation for their transitions. |
| /// * All failure transitions are pre-computed such that they are never |
| /// explicitly handled at search time. |
| /// |
| /// These two facts combined mean that every state transition is performed |
| /// using a constant number of instructions. However, this comes at |
| /// great cost. The memory usage of a DFA can be quite exorbitant. |
| /// It is potentially multiple orders of magnitude greater than a |
| /// [`contiguous::NFA`](crate::nfa::contiguous::NFA) for example. In exchange, |
| /// a DFA will typically have better search speed than a `contiguous::NFA`, but |
| /// not by orders of magnitude. |
| /// |
| /// Unless you have a small number of patterns or memory usage is not a concern |
| /// and search performance is critical, a DFA is usually not the best choice. |
| /// |
| /// Moreover, unlike the NFAs in this crate, it is costly for a DFA to |
| /// support for anchored and unanchored search configurations. Namely, |
| /// since failure transitions are pre-computed, supporting both anchored |
| /// and unanchored searches requires a duplication of the transition table, |
| /// making the memory usage of such a DFA ever bigger. (The NFAs in this crate |
| /// unconditionally support both anchored and unanchored searches because there |
| /// is essentially no added cost for doing so.) It is for this reason that |
| /// a DFA's support for anchored and unanchored searches can be configured |
| /// via [`Builder::start_kind`]. By default, a DFA only supports unanchored |
| /// searches. |
| /// |
| /// # Example |
| /// |
| /// This example shows how to build an `DFA` directly and use it to execute |
| /// [`Automaton::try_find`]: |
| /// |
| /// ``` |
| /// use aho_corasick::{ |
| /// automaton::Automaton, |
| /// dfa::DFA, |
| /// Input, Match, |
| /// }; |
| /// |
| /// let patterns = &["b", "abc", "abcd"]; |
| /// let haystack = "abcd"; |
| /// |
| /// let nfa = DFA::new(patterns).unwrap(); |
| /// assert_eq!( |
| /// Some(Match::must(0, 1..2)), |
| /// nfa.try_find(&Input::new(haystack))?, |
| /// ); |
| /// # Ok::<(), Box<dyn std::error::Error>>(()) |
| /// ``` |
| /// |
| /// It is also possible to implement your own version of `try_find`. See the |
| /// [`Automaton`] documentation for an example. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>DFA { |
| <span class="doccomment">/// The DFA transition table. IDs in this table are pre-multiplied. So |
| /// instead of the IDs being 0, 1, 2, 3, ..., they are 0*stride, 1*stride, |
| /// 2*stride, 3*stride, ... |
| </span>trans: Vec<StateID>, |
| <span class="doccomment">/// The matches for every match state in this DFA. This is indexed by order |
| /// of match states in the DFA. Namely, as constructed, match states are |
| /// always laid out sequentially and contiguously in memory. Thus, after |
| /// converting a match state ID to a match state index, the indices are |
| /// all adjacent. |
| /// |
| /// More concretely, when a search enters a match state with id 'sid', then |
| /// the matching patterns are at 'matches[(sid >> stride2) - 2]'. The '- 2' |
| /// is to offset the first two states of a DFA: the dead and fail states. |
| </span>matches: Vec<Vec<PatternID>>, |
| <span class="doccomment">/// The amount of heap memory used, in bytes, by the inner Vecs of |
| /// 'matches'. |
| </span>matches_memory_usage: usize, |
| <span class="doccomment">/// The length of each pattern. This is used to compute the start offset |
| /// of a match. |
| </span>pattern_lens: Vec<SmallIndex>, |
| <span class="doccomment">/// A prefilter for accelerating searches, if one exists. |
| </span>prefilter: <span class="prelude-ty">Option</span><Prefilter>, |
| <span class="doccomment">/// The match semantics built into this DFA. |
| </span>match_kind: MatchKind, |
| <span class="doccomment">/// The total number of states in this DFA. |
| </span>state_len: usize, |
| <span class="doccomment">/// The alphabet size, or total number of equivalence classes, for this |
| /// DFA. Note that the actual number of transitions in each state is |
| /// stride=2^stride2, where stride is the smallest power of 2 greater than |
| /// or equal to alphabet_len. We do things this way so that we can use |
| /// bitshifting to go from a state ID to an index into 'matches'. |
| </span>alphabet_len: usize, |
| <span class="doccomment">/// The exponent with a base 2, such that stride=2^stride2. Given a state |
| /// index 'i', its state identifier is 'i << stride2'. Given a state |
| /// identifier 'sid', its state index is 'sid >> stride2'. |
| </span>stride2: usize, |
| <span class="doccomment">/// The equivalence classes for this DFA. All transitions are defined on |
| /// equivalence classes and not on the 256 distinct byte values. |
| </span>byte_classes: ByteClasses, |
| <span class="doccomment">/// The length of the shortest pattern in this automaton. |
| </span>min_pattern_len: usize, |
| <span class="doccomment">/// The length of the longest pattern in this automaton. |
| </span>max_pattern_len: usize, |
| <span class="doccomment">/// The information required to deduce which states are "special" in this |
| /// DFA. |
| </span>special: Special, |
| } |
| |
| <span class="kw">impl </span>DFA { |
| <span class="doccomment">/// Create a new Aho-Corasick DFA using the default configuration. |
| /// |
| /// Use a [`Builder`] if you want to change the configuration. |
| </span><span class="kw">pub fn </span>new<I, P>(patterns: I) -> <span class="prelude-ty">Result</span><DFA, BuildError> |
| <span class="kw">where |
| </span>I: IntoIterator<Item = P>, |
| P: AsRef<[u8]>, |
| { |
| DFA::builder().build(patterns) |
| } |
| |
| <span class="doccomment">/// A convenience method for returning a new Aho-Corasick DFA builder. |
| /// |
| /// This usually permits one to just import the `DFA` type. |
| </span><span class="kw">pub fn </span>builder() -> Builder { |
| Builder::new() |
| } |
| } |
| |
| <span class="kw">impl </span>DFA { |
| <span class="doccomment">/// A sentinel state ID indicating that a search should stop once it has |
| /// entered this state. When a search stops, it returns a match if one has |
| /// been found, otherwise no match. A DFA always has an actual dead state |
| /// at this ID. |
| /// |
| /// N.B. DFAs, unlike NFAs, do not have any notion of a FAIL state. |
| /// Namely, the whole point of a DFA is that the FAIL state is completely |
| /// compiled away. That is, DFA construction involves pre-computing the |
| /// failure transitions everywhere, such that failure transitions are no |
| /// longer used at search time. This, combined with its uniformly dense |
| /// representation, are the two most important factors in why it's faster |
| /// than the NFAs in this crate. |
| </span><span class="kw">const </span>DEAD: StateID = StateID::new_unchecked(<span class="number">0</span>); |
| |
| <span class="doccomment">/// Adds the given pattern IDs as matches to the given state and also |
| /// records the added memory usage. |
| </span><span class="kw">fn </span>set_matches(<span class="kw-2">&mut </span><span class="self">self</span>, sid: StateID, pids: <span class="kw-2">&</span>[PatternID]) { |
| <span class="kw">use </span>core::mem::size_of; |
| |
| <span class="macro">assert!</span>(!pids.is_empty(), <span class="string">"match state must have non-empty pids"</span>); |
| <span class="kw">let </span>index = (sid.as_usize() >> <span class="self">self</span>.stride2).checked_sub(<span class="number">2</span>).unwrap(); |
| <span class="self">self</span>.matches[index].extend_from_slice(pids); |
| <span class="self">self</span>.matches_memory_usage += size_of::<PatternID>() * pids.len(); |
| } |
| } |
| |
| <span class="comment">// SAFETY: 'start_state' always returns a valid state ID, 'next_state' always |
| // returns a valid state ID given a valid state ID. We otherwise claim that |
| // all other methods are correct as well. |
| </span><span class="kw">unsafe impl </span>Automaton <span class="kw">for </span>DFA { |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>start_state(<span class="kw-2">&</span><span class="self">self</span>, anchored: Anchored) -> <span class="prelude-ty">Result</span><StateID, MatchError> { |
| <span class="comment">// Either of the start state IDs can be DEAD, in which case, support |
| // for that type of search is not provided by this DFA. Which start |
| // state IDs are inactive depends on the 'StartKind' configuration at |
| // DFA construction time. |
| </span><span class="kw">match </span>anchored { |
| Anchored::No => { |
| <span class="kw">let </span>start = <span class="self">self</span>.special.start_unanchored_id; |
| <span class="kw">if </span>start == DFA::DEAD { |
| <span class="prelude-val">Err</span>(MatchError::invalid_input_unanchored()) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Ok</span>(start) |
| } |
| } |
| Anchored::Yes => { |
| <span class="kw">let </span>start = <span class="self">self</span>.special.start_anchored_id; |
| <span class="kw">if </span>start == DFA::DEAD { |
| <span class="prelude-val">Err</span>(MatchError::invalid_input_anchored()) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Ok</span>(start) |
| } |
| } |
| } |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>next_state( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| _anchored: Anchored, |
| sid: StateID, |
| byte: u8, |
| ) -> StateID { |
| <span class="kw">let </span>class = <span class="self">self</span>.byte_classes.get(byte); |
| <span class="self">self</span>.trans[(sid.as_u32() + u32::from(class)).as_usize()] |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>is_special(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID) -> bool { |
| sid <= <span class="self">self</span>.special.max_special_id |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>is_dead(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID) -> bool { |
| sid == DFA::DEAD |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>is_match(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID) -> bool { |
| !<span class="self">self</span>.is_dead(sid) && sid <= <span class="self">self</span>.special.max_match_id |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>is_start(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID) -> bool { |
| sid == <span class="self">self</span>.special.start_unanchored_id |
| || sid == <span class="self">self</span>.special.start_anchored_id |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>match_kind(<span class="kw-2">&</span><span class="self">self</span>) -> MatchKind { |
| <span class="self">self</span>.match_kind |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>patterns_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.pattern_lens.len() |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>pattern_len(<span class="kw-2">&</span><span class="self">self</span>, pid: PatternID) -> usize { |
| <span class="self">self</span>.pattern_lens[pid].as_usize() |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>min_pattern_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.min_pattern_len |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>max_pattern_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.max_pattern_len |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>match_len(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID) -> usize { |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.is_match(sid)); |
| <span class="kw">let </span>offset = (sid.as_usize() >> <span class="self">self</span>.stride2) - <span class="number">2</span>; |
| <span class="self">self</span>.matches[offset].len() |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>match_pattern(<span class="kw-2">&</span><span class="self">self</span>, sid: StateID, index: usize) -> PatternID { |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.is_match(sid)); |
| <span class="kw">let </span>offset = (sid.as_usize() >> <span class="self">self</span>.stride2) - <span class="number">2</span>; |
| <span class="self">self</span>.matches[offset][index] |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>memory_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="kw">use </span>core::mem::size_of; |
| |
| (<span class="self">self</span>.trans.len() * size_of::<u32>()) |
| + (<span class="self">self</span>.matches.len() * size_of::<Vec<PatternID>>()) |
| + <span class="self">self</span>.matches_memory_usage |
| + (<span class="self">self</span>.pattern_lens.len() * size_of::<SmallIndex>()) |
| + <span class="self">self</span>.prefilter.as_ref().map_or(<span class="number">0</span>, |p| p.memory_usage()) |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>prefilter(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="kw-2">&</span>Prefilter> { |
| <span class="self">self</span>.prefilter.as_ref() |
| } |
| } |
| |
| <span class="kw">impl </span>core::fmt::Debug <span class="kw">for </span>DFA { |
| <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="kw">use crate</span>::{ |
| automaton::{fmt_state_indicator, sparse_transitions}, |
| util::debug::DebugByte, |
| }; |
| |
| <span class="macro">writeln!</span>(f, <span class="string">"dfa::DFA("</span>)<span class="question-mark">?</span>; |
| <span class="kw">for </span>index <span class="kw">in </span><span class="number">0</span>..<span class="self">self</span>.state_len { |
| <span class="kw">let </span>sid = StateID::new_unchecked(index << <span class="self">self</span>.stride2); |
| <span class="comment">// While we do currently include the FAIL state in the transition |
| // table (to simplify construction), it is never actually used. It |
| // poses problems with the code below because it gets treated as |
| // a match state incidentally when it is, of course, not. So we |
| // special case it. The fail state is always the first state after |
| // the dead state. |
| // |
| // If the construction is changed to remove the fail state (it |
| // probably should be), then this special case should be updated. |
| </span><span class="kw">if </span>index == <span class="number">1 </span>{ |
| <span class="macro">writeln!</span>(f, <span class="string">"F {:06}:"</span>, sid.as_usize())<span class="question-mark">?</span>; |
| <span class="kw">continue</span>; |
| } |
| fmt_state_indicator(f, <span class="self">self</span>, sid)<span class="question-mark">?</span>; |
| <span class="macro">write!</span>(f, <span class="string">"{:06}: "</span>, sid.as_usize())<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>it = (<span class="number">0</span>..<span class="self">self</span>.byte_classes.alphabet_len()).map(|class| { |
| (class.as_u8(), <span class="self">self</span>.trans[sid.as_usize() + class]) |
| }); |
| <span class="kw">for </span>(i, (start, end, next)) <span class="kw">in </span>sparse_transitions(it).enumerate() { |
| <span class="kw">if </span>i > <span class="number">0 </span>{ |
| <span class="macro">write!</span>(f, <span class="string">", "</span>)<span class="question-mark">?</span>; |
| } |
| <span class="kw">if </span>start == end { |
| <span class="macro">write!</span>( |
| f, |
| <span class="string">"{:?} => {:?}"</span>, |
| DebugByte(start), |
| next.as_usize() |
| )<span class="question-mark">?</span>; |
| } <span class="kw">else </span>{ |
| <span class="macro">write!</span>( |
| f, |
| <span class="string">"{:?}-{:?} => {:?}"</span>, |
| DebugByte(start), |
| DebugByte(end), |
| next.as_usize() |
| )<span class="question-mark">?</span>; |
| } |
| } |
| <span class="macro">write!</span>(f, <span class="string">"\n"</span>)<span class="question-mark">?</span>; |
| <span class="kw">if </span><span class="self">self</span>.is_match(sid) { |
| <span class="macro">write!</span>(f, <span class="string">" matches: "</span>)<span class="question-mark">?</span>; |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..<span class="self">self</span>.match_len(sid) { |
| <span class="kw">if </span>i > <span class="number">0 </span>{ |
| <span class="macro">write!</span>(f, <span class="string">", "</span>)<span class="question-mark">?</span>; |
| } |
| <span class="kw">let </span>pid = <span class="self">self</span>.match_pattern(sid, i); |
| <span class="macro">write!</span>(f, <span class="string">"{}"</span>, pid.as_usize())<span class="question-mark">?</span>; |
| } |
| <span class="macro">write!</span>(f, <span class="string">"\n"</span>)<span class="question-mark">?</span>; |
| } |
| } |
| <span class="macro">writeln!</span>(f, <span class="string">"match kind: {:?}"</span>, <span class="self">self</span>.match_kind)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"prefilter: {:?}"</span>, <span class="self">self</span>.prefilter.is_some())<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"state length: {:?}"</span>, <span class="self">self</span>.state_len)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"pattern length: {:?}"</span>, <span class="self">self</span>.patterns_len())<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"shortest pattern length: {:?}"</span>, <span class="self">self</span>.min_pattern_len)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"longest pattern length: {:?}"</span>, <span class="self">self</span>.max_pattern_len)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"alphabet length: {:?}"</span>, <span class="self">self</span>.alphabet_len)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"stride: {:?}"</span>, <span class="number">1 </span><< <span class="self">self</span>.stride2)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"byte classes: {:?}"</span>, <span class="self">self</span>.byte_classes)<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">"memory usage: {:?}"</span>, <span class="self">self</span>.memory_usage())<span class="question-mark">?</span>; |
| <span class="macro">writeln!</span>(f, <span class="string">")"</span>)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for configuring an Aho-Corasick DFA. |
| /// |
| /// This builder has a subset of the options available to a |
| /// [`AhoCorasickBuilder`](crate::AhoCorasickBuilder). Of the shared options, |
| /// their behavior is identical. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Builder { |
| noncontiguous: noncontiguous::Builder, |
| start_kind: StartKind, |
| byte_classes: bool, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>Builder { |
| <span class="kw">fn </span>default() -> Builder { |
| Builder { |
| noncontiguous: noncontiguous::Builder::new(), |
| start_kind: StartKind::Unanchored, |
| byte_classes: <span class="bool-val">true</span>, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Builder { |
| <span class="doccomment">/// Create a new builder for configuring an Aho-Corasick DFA. |
| </span><span class="kw">pub fn </span>new() -> Builder { |
| Builder::default() |
| } |
| |
| <span class="doccomment">/// Build an Aho-Corasick DFA from the given iterator of patterns. |
| /// |
| /// A builder may be reused to create more DFAs. |
| </span><span class="kw">pub fn </span>build<I, P>(<span class="kw-2">&</span><span class="self">self</span>, patterns: I) -> <span class="prelude-ty">Result</span><DFA, BuildError> |
| <span class="kw">where |
| </span>I: IntoIterator<Item = P>, |
| P: AsRef<[u8]>, |
| { |
| <span class="kw">let </span>nnfa = <span class="self">self</span>.noncontiguous.build(patterns)<span class="question-mark">?</span>; |
| <span class="self">self</span>.build_from_noncontiguous(<span class="kw-2">&</span>nnfa) |
| } |
| |
| <span class="doccomment">/// Build an Aho-Corasick DFA from the given noncontiguous NFA. |
| /// |
| /// Note that when this method is used, only the `start_kind` and |
| /// `byte_classes` settings on this builder are respected. The other |
| /// settings only apply to the initial construction of the Aho-Corasick |
| /// automaton. Since using this method requires that initial construction |
| /// has already completed, all settings impacting only initial construction |
| /// are no longer relevant. |
| </span><span class="kw">pub fn </span>build_from_noncontiguous( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| nnfa: <span class="kw-2">&</span>noncontiguous::NFA, |
| ) -> <span class="prelude-ty">Result</span><DFA, BuildError> { |
| <span class="macro">debug!</span>(<span class="string">"building DFA"</span>); |
| <span class="kw">let </span>byte_classes = <span class="kw">if </span><span class="self">self</span>.byte_classes { |
| nnfa.byte_classes().clone() |
| } <span class="kw">else </span>{ |
| ByteClasses::singletons() |
| }; |
| <span class="kw">let </span>state_len = <span class="kw">match </span><span class="self">self</span>.start_kind { |
| StartKind::Unanchored | StartKind::Anchored => nnfa.states().len(), |
| StartKind::Both => { |
| <span class="comment">// These unwraps are OK because we know that the number of |
| // NFA states is < StateID::LIMIT which is in turn less than |
| // i32::MAX. Thus, there is always room to multiply by 2. |
| // Finally, the number of states is always at least 4 in the |
| // NFA (DEAD, FAIL, START-UNANCHORED, START-ANCHORED), so the |
| // subtraction of 4 is okay. |
| // |
| // Note that we subtract 4 because the "anchored" part of |
| // the DFA duplicates the unanchored part (without failure |
| // transitions), but reuses the DEAD, FAIL and START states. |
| </span>nnfa.states() |
| .len() |
| .checked_mul(<span class="number">2</span>) |
| .unwrap() |
| .checked_sub(<span class="number">4</span>) |
| .unwrap() |
| } |
| }; |
| <span class="kw">let </span>trans_len = |
| <span class="kw">match </span>state_len.checked_shl(byte_classes.stride2().as_u32()) { |
| <span class="prelude-val">Some</span>(trans_len) => trans_len, |
| <span class="prelude-val">None </span>=> { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(BuildError::state_id_overflow( |
| StateID::MAX.as_u64(), |
| usize::MAX.as_u64(), |
| )) |
| } |
| }; |
| StateID::new(trans_len.checked_sub(byte_classes.stride()).unwrap()) |
| .map_err(|e| { |
| BuildError::state_id_overflow( |
| StateID::MAX.as_u64(), |
| e.attempted(), |
| ) |
| })<span class="question-mark">?</span>; |
| <span class="kw">let </span>num_match_states = <span class="kw">match </span><span class="self">self</span>.start_kind { |
| StartKind::Unanchored | StartKind::Anchored => { |
| nnfa.special().max_match_id.as_usize().checked_sub(<span class="number">1</span>).unwrap() |
| } |
| StartKind::Both => nnfa |
| .special() |
| .max_match_id |
| .as_usize() |
| .checked_sub(<span class="number">1</span>) |
| .unwrap() |
| .checked_mul(<span class="number">2</span>) |
| .unwrap(), |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>dfa = DFA { |
| trans: <span class="macro">vec!</span>[DFA::DEAD; trans_len], |
| matches: <span class="macro">vec!</span>[<span class="macro">vec!</span>[]; num_match_states], |
| matches_memory_usage: <span class="number">0</span>, |
| pattern_lens: nnfa.pattern_lens_raw().to_vec(), |
| prefilter: nnfa.prefilter().map(|p| p.clone()), |
| match_kind: nnfa.match_kind(), |
| state_len, |
| alphabet_len: byte_classes.alphabet_len(), |
| stride2: byte_classes.stride2(), |
| byte_classes, |
| min_pattern_len: nnfa.min_pattern_len(), |
| max_pattern_len: nnfa.max_pattern_len(), |
| <span class="comment">// The special state IDs are set later. |
| </span>special: Special::zero(), |
| }; |
| <span class="kw">match </span><span class="self">self</span>.start_kind { |
| StartKind::Both => { |
| <span class="self">self</span>.finish_build_both_starts(nnfa, <span class="kw-2">&mut </span>dfa); |
| } |
| StartKind::Unanchored => { |
| <span class="self">self</span>.finish_build_one_start(Anchored::No, nnfa, <span class="kw-2">&mut </span>dfa); |
| } |
| StartKind::Anchored => { |
| <span class="self">self</span>.finish_build_one_start(Anchored::Yes, nnfa, <span class="kw-2">&mut </span>dfa) |
| } |
| } |
| <span class="macro">debug!</span>( |
| <span class="string">"DFA built, <states: {:?}, size: {:?}, \ |
| alphabet len: {:?}, stride: {:?}>"</span>, |
| dfa.state_len, |
| dfa.memory_usage(), |
| dfa.byte_classes.alphabet_len(), |
| dfa.byte_classes.stride(), |
| ); |
| <span class="prelude-val">Ok</span>(dfa) |
| } |
| |
| <span class="doccomment">/// Finishes building a DFA for either unanchored or anchored searches, |
| /// but NOT both. |
| </span><span class="kw">fn </span>finish_build_one_start( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| anchored: Anchored, |
| nnfa: <span class="kw-2">&</span>noncontiguous::NFA, |
| dfa: <span class="kw-2">&mut </span>DFA, |
| ) { |
| <span class="comment">// This function always succeeds because we check above that all of the |
| // states in the NFA can be mapped to DFA state IDs. |
| </span><span class="kw">let </span>stride2 = dfa.stride2; |
| <span class="kw">let </span>old2new = |oldsid: StateID| { |
| StateID::new_unchecked(oldsid.as_usize() << stride2) |
| }; |
| <span class="kw">for </span>(oldsid, state) <span class="kw">in </span>nnfa.states().iter().with_state_ids() { |
| <span class="kw">let </span>newsid = old2new(oldsid); |
| <span class="kw">if </span>!state.matches.is_empty() { |
| dfa.set_matches(newsid, <span class="kw-2">&</span>state.matches); |
| } |
| sparse_iter( |
| state, |
| <span class="kw-2">&</span>dfa.byte_classes, |
| |byte, class, <span class="kw-2">mut </span>oldnextsid| { |
| <span class="kw">if </span>oldnextsid == noncontiguous::NFA::FAIL { |
| <span class="kw">if </span>anchored.is_anchored() { |
| oldnextsid = noncontiguous::NFA::DEAD; |
| } <span class="kw">else </span>{ |
| oldnextsid = nnfa.next_state( |
| Anchored::No, |
| state.fail, |
| byte, |
| ); |
| } |
| } |
| dfa.trans[newsid.as_usize() + usize::from(class)] = |
| old2new(oldnextsid); |
| }, |
| ); |
| } |
| <span class="comment">// Now that we've remapped all the IDs in our states, all that's left |
| // is remapping the special state IDs. |
| </span><span class="kw">let </span>old = nnfa.special(); |
| <span class="kw">let </span>new = <span class="kw-2">&mut </span>dfa.special; |
| new.max_special_id = old2new(old.max_special_id); |
| new.max_match_id = old2new(old.max_match_id); |
| <span class="kw">if </span>anchored.is_anchored() { |
| new.start_unanchored_id = DFA::DEAD; |
| new.start_anchored_id = old2new(old.start_anchored_id); |
| } <span class="kw">else </span>{ |
| new.start_unanchored_id = old2new(old.start_unanchored_id); |
| new.start_anchored_id = DFA::DEAD; |
| } |
| } |
| |
| <span class="doccomment">/// Finishes building a DFA that supports BOTH unanchored and anchored |
| /// searches. It works by inter-leaving unanchored states with anchored |
| /// states in the same transition table. This way, we avoid needing to |
| /// re-shuffle states afterward to ensure that our states still look like |
| /// DEAD, MATCH, ..., START-UNANCHORED, START-ANCHORED, NON-MATCH, ... |
| /// |
| /// Honestly this is pretty inscrutable... Simplifications are most |
| /// welcome. |
| </span><span class="kw">fn </span>finish_build_both_starts( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| nnfa: <span class="kw-2">&</span>noncontiguous::NFA, |
| dfa: <span class="kw-2">&mut </span>DFA, |
| ) { |
| <span class="kw">let </span>stride2 = dfa.stride2; |
| <span class="kw">let </span>stride = <span class="number">1 </span><< stride2; |
| <span class="kw">let </span><span class="kw-2">mut </span>remap_unanchored = <span class="macro">vec!</span>[DFA::DEAD; nnfa.states().len()]; |
| <span class="kw">let </span><span class="kw-2">mut </span>remap_anchored = <span class="macro">vec!</span>[DFA::DEAD; nnfa.states().len()]; |
| <span class="kw">let </span><span class="kw-2">mut </span>is_anchored = <span class="macro">vec!</span>[<span class="bool-val">false</span>; dfa.state_len]; |
| <span class="kw">let </span><span class="kw-2">mut </span>newsid = DFA::DEAD; |
| <span class="kw">let </span>next_dfa_id = |
| |sid: StateID| StateID::new_unchecked(sid.as_usize() + stride); |
| <span class="kw">for </span>(oldsid, state) <span class="kw">in </span>nnfa.states().iter().with_state_ids() { |
| <span class="kw">if </span>oldsid == noncontiguous::NFA::DEAD |
| || oldsid == noncontiguous::NFA::FAIL |
| { |
| remap_unanchored[oldsid] = newsid; |
| remap_anchored[oldsid] = newsid; |
| newsid = next_dfa_id(newsid); |
| } <span class="kw">else if </span>oldsid == nnfa.special().start_unanchored_id |
| || oldsid == nnfa.special().start_anchored_id |
| { |
| <span class="kw">if </span>oldsid == nnfa.special().start_unanchored_id { |
| remap_unanchored[oldsid] = newsid; |
| remap_anchored[oldsid] = DFA::DEAD; |
| } <span class="kw">else </span>{ |
| remap_unanchored[oldsid] = DFA::DEAD; |
| remap_anchored[oldsid] = newsid; |
| is_anchored[newsid.as_usize() >> stride2] = <span class="bool-val">true</span>; |
| } |
| <span class="kw">if </span>!state.matches.is_empty() { |
| dfa.set_matches(newsid, <span class="kw-2">&</span>state.matches); |
| } |
| sparse_iter( |
| state, |
| <span class="kw-2">&</span>dfa.byte_classes, |
| |<span class="kw">_</span>, class, oldnextsid| { |
| <span class="kw">let </span>class = usize::from(class); |
| <span class="kw">if </span>oldnextsid == noncontiguous::NFA::FAIL { |
| dfa.trans[newsid.as_usize() + class] = DFA::DEAD; |
| } <span class="kw">else </span>{ |
| dfa.trans[newsid.as_usize() + class] = oldnextsid; |
| } |
| }, |
| ); |
| newsid = next_dfa_id(newsid); |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>unewsid = newsid; |
| newsid = next_dfa_id(newsid); |
| <span class="kw">let </span>anewsid = newsid; |
| newsid = next_dfa_id(newsid); |
| |
| remap_unanchored[oldsid] = unewsid; |
| remap_anchored[oldsid] = anewsid; |
| is_anchored[anewsid.as_usize() >> stride2] = <span class="bool-val">true</span>; |
| <span class="kw">if </span>!state.matches.is_empty() { |
| dfa.set_matches(unewsid, <span class="kw-2">&</span>state.matches); |
| dfa.set_matches(anewsid, <span class="kw-2">&</span>state.matches); |
| } |
| sparse_iter( |
| state, |
| <span class="kw-2">&</span>dfa.byte_classes, |
| |byte, class, oldnextsid| { |
| <span class="kw">let </span>class = usize::from(class); |
| <span class="kw">if </span>oldnextsid == noncontiguous::NFA::FAIL { |
| dfa.trans[unewsid.as_usize() + class] = nnfa |
| .next_state(Anchored::No, state.fail, byte); |
| } <span class="kw">else </span>{ |
| dfa.trans[unewsid.as_usize() + class] = oldnextsid; |
| dfa.trans[anewsid.as_usize() + class] = oldnextsid; |
| } |
| }, |
| ); |
| } |
| } |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..dfa.state_len { |
| <span class="kw">let </span>sid = i << stride2; |
| <span class="kw">if </span>is_anchored[i] { |
| <span class="kw">for </span>next <span class="kw">in </span>dfa.trans[sid..][..stride].iter_mut() { |
| <span class="kw-2">*</span>next = remap_anchored[<span class="kw-2">*</span>next]; |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">for </span>next <span class="kw">in </span>dfa.trans[sid..][..stride].iter_mut() { |
| <span class="kw-2">*</span>next = remap_unanchored[<span class="kw-2">*</span>next]; |
| } |
| } |
| } |
| <span class="comment">// Now that we've remapped all the IDs in our states, all that's left |
| // is remapping the special state IDs. |
| </span><span class="kw">let </span>old = nnfa.special(); |
| <span class="kw">let </span>new = <span class="kw-2">&mut </span>dfa.special; |
| new.max_special_id = remap_anchored[old.max_special_id]; |
| new.max_match_id = remap_anchored[old.max_match_id]; |
| new.start_unanchored_id = remap_unanchored[old.start_unanchored_id]; |
| new.start_anchored_id = remap_anchored[old.start_anchored_id]; |
| } |
| |
| <span class="doccomment">/// Set the desired match semantics. |
| /// |
| /// This only applies when using [`Builder::build`] and not |
| /// [`Builder::build_from_noncontiguous`]. |
| /// |
| /// See |
| /// [`AhoCorasickBuilder::match_kind`](crate::AhoCorasickBuilder::match_kind) |
| /// for more documentation and examples. |
| </span><span class="kw">pub fn </span>match_kind(<span class="kw-2">&mut </span><span class="self">self</span>, kind: MatchKind) -> <span class="kw-2">&mut </span>Builder { |
| <span class="self">self</span>.noncontiguous.match_kind(kind); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable ASCII-aware case insensitive matching. |
| /// |
| /// This only applies when using [`Builder::build`] and not |
| /// [`Builder::build_from_noncontiguous`]. |
| /// |
| /// See |
| /// [`AhoCorasickBuilder::ascii_case_insensitive`](crate::AhoCorasickBuilder::ascii_case_insensitive) |
| /// for more documentation and examples. |
| </span><span class="kw">pub fn </span>ascii_case_insensitive(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>Builder { |
| <span class="self">self</span>.noncontiguous.ascii_case_insensitive(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable heuristic prefilter optimizations. |
| /// |
| /// This only applies when using [`Builder::build`] and not |
| /// [`Builder::build_from_noncontiguous`]. |
| /// |
| /// See |
| /// [`AhoCorasickBuilder::prefilter`](crate::AhoCorasickBuilder::prefilter) |
| /// for more documentation and examples. |
| </span><span class="kw">pub fn </span>prefilter(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>Builder { |
| <span class="self">self</span>.noncontiguous.prefilter(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Sets the starting state configuration for the automaton. |
| /// |
| /// See |
| /// [`AhoCorasickBuilder::start_kind`](crate::AhoCorasickBuilder::start_kind) |
| /// for more documentation and examples. |
| </span><span class="kw">pub fn </span>start_kind(<span class="kw-2">&mut </span><span class="self">self</span>, kind: StartKind) -> <span class="kw-2">&mut </span>Builder { |
| <span class="self">self</span>.start_kind = kind; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// A debug setting for whether to attempt to shrink the size of the |
| /// automaton's alphabet or not. |
| /// |
| /// This should never be enabled unless you're debugging an automaton. |
| /// Namely, disabling byte classes makes transitions easier to reason |
| /// about, since they use the actual bytes instead of equivalence classes. |
| /// Disabling this confers no performance benefit at search time. |
| /// |
| /// See |
| /// [`AhoCorasickBuilder::byte_classes`](crate::AhoCorasickBuilder::byte_classes) |
| /// for more documentation and examples. |
| </span><span class="kw">pub fn </span>byte_classes(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>Builder { |
| <span class="self">self</span>.byte_classes = yes; |
| <span class="self">self |
| </span>} |
| } |
| |
| <span class="doccomment">/// Iterate over all possible equivalence class transitions in this state. |
| /// The closure is called for all transitions with a distinct equivalence |
| /// class, even those not explicitly represented in this sparse state. For |
| /// any implicitly defined transitions, the given closure is called with |
| /// the fail state ID. |
| /// |
| /// The closure is guaranteed to be called precisely |
| /// `byte_classes.alphabet_len()` times, once for every possible class in |
| /// ascending order. |
| </span><span class="kw">fn </span>sparse_iter<F: FnMut(u8, u8, StateID)>( |
| state: <span class="kw-2">&</span>noncontiguous::State, |
| classes: <span class="kw-2">&</span>ByteClasses, |
| <span class="kw-2">mut </span>f: F, |
| ) { |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_class = <span class="prelude-val">None</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>byte = <span class="number">0usize</span>; |
| <span class="kw">for </span><span class="kw-2">&</span>(b, id) <span class="kw">in </span>state.trans.iter() { |
| <span class="kw">while </span>byte < usize::from(b) { |
| <span class="kw">let </span>rep = byte.as_u8(); |
| <span class="kw">let </span>class = classes.get(rep); |
| byte += <span class="number">1</span>; |
| <span class="kw">if </span>prev_class != <span class="prelude-val">Some</span>(class) { |
| f(rep, class, noncontiguous::NFA::FAIL); |
| prev_class = <span class="prelude-val">Some</span>(class); |
| } |
| } |
| <span class="kw">let </span>rep = b; |
| <span class="kw">let </span>class = classes.get(rep); |
| byte += <span class="number">1</span>; |
| <span class="kw">if </span>prev_class != <span class="prelude-val">Some</span>(class) { |
| f(rep, class, id); |
| prev_class = <span class="prelude-val">Some</span>(class); |
| } |
| } |
| <span class="kw">for </span>b <span class="kw">in </span>byte..=<span class="number">255 </span>{ |
| <span class="kw">let </span>rep = b.as_u8(); |
| <span class="kw">let </span>class = classes.get(rep); |
| <span class="kw">if </span>prev_class != <span class="prelude-val">Some</span>(class) { |
| f(rep, class, noncontiguous::NFA::FAIL); |
| prev_class = <span class="prelude-val">Some</span>(class); |
| } |
| } |
| } |
| </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> |