| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/regex-1.8.3/src/compile.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>compile.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../normalize.css"><link rel="stylesheet" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../ayu.css" disabled><link rel="stylesheet" href="../../dark.css" disabled><link rel="stylesheet" href="../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../storage.js"></script><script defer src="../../source-script.js"></script><script defer src="../../source-files.js"></script><script defer src="../../main.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../regex/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../regex/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| <span id="568">568</span> |
| <span id="569">569</span> |
| <span id="570">570</span> |
| <span id="571">571</span> |
| <span id="572">572</span> |
| <span id="573">573</span> |
| <span id="574">574</span> |
| <span id="575">575</span> |
| <span id="576">576</span> |
| <span id="577">577</span> |
| <span id="578">578</span> |
| <span id="579">579</span> |
| <span id="580">580</span> |
| <span id="581">581</span> |
| <span id="582">582</span> |
| <span id="583">583</span> |
| <span id="584">584</span> |
| <span id="585">585</span> |
| <span id="586">586</span> |
| <span id="587">587</span> |
| <span id="588">588</span> |
| <span id="589">589</span> |
| <span id="590">590</span> |
| <span id="591">591</span> |
| <span id="592">592</span> |
| <span id="593">593</span> |
| <span id="594">594</span> |
| <span id="595">595</span> |
| <span id="596">596</span> |
| <span id="597">597</span> |
| <span id="598">598</span> |
| <span id="599">599</span> |
| <span id="600">600</span> |
| <span id="601">601</span> |
| <span id="602">602</span> |
| <span id="603">603</span> |
| <span id="604">604</span> |
| <span id="605">605</span> |
| <span id="606">606</span> |
| <span id="607">607</span> |
| <span id="608">608</span> |
| <span id="609">609</span> |
| <span id="610">610</span> |
| <span id="611">611</span> |
| <span id="612">612</span> |
| <span id="613">613</span> |
| <span id="614">614</span> |
| <span id="615">615</span> |
| <span id="616">616</span> |
| <span id="617">617</span> |
| <span id="618">618</span> |
| <span id="619">619</span> |
| <span id="620">620</span> |
| <span id="621">621</span> |
| <span id="622">622</span> |
| <span id="623">623</span> |
| <span id="624">624</span> |
| <span id="625">625</span> |
| <span id="626">626</span> |
| <span id="627">627</span> |
| <span id="628">628</span> |
| <span id="629">629</span> |
| <span id="630">630</span> |
| <span id="631">631</span> |
| <span id="632">632</span> |
| <span id="633">633</span> |
| <span id="634">634</span> |
| <span id="635">635</span> |
| <span id="636">636</span> |
| <span id="637">637</span> |
| <span id="638">638</span> |
| <span id="639">639</span> |
| <span id="640">640</span> |
| <span id="641">641</span> |
| <span id="642">642</span> |
| <span id="643">643</span> |
| <span id="644">644</span> |
| <span id="645">645</span> |
| <span id="646">646</span> |
| <span id="647">647</span> |
| <span id="648">648</span> |
| <span id="649">649</span> |
| <span id="650">650</span> |
| <span id="651">651</span> |
| <span id="652">652</span> |
| <span id="653">653</span> |
| <span id="654">654</span> |
| <span id="655">655</span> |
| <span id="656">656</span> |
| <span id="657">657</span> |
| <span id="658">658</span> |
| <span id="659">659</span> |
| <span id="660">660</span> |
| <span id="661">661</span> |
| <span id="662">662</span> |
| <span id="663">663</span> |
| <span id="664">664</span> |
| <span id="665">665</span> |
| <span id="666">666</span> |
| <span id="667">667</span> |
| <span id="668">668</span> |
| <span id="669">669</span> |
| <span id="670">670</span> |
| <span id="671">671</span> |
| <span id="672">672</span> |
| <span id="673">673</span> |
| <span id="674">674</span> |
| <span id="675">675</span> |
| <span id="676">676</span> |
| <span id="677">677</span> |
| <span id="678">678</span> |
| <span id="679">679</span> |
| <span id="680">680</span> |
| <span id="681">681</span> |
| <span id="682">682</span> |
| <span id="683">683</span> |
| <span id="684">684</span> |
| <span id="685">685</span> |
| <span id="686">686</span> |
| <span id="687">687</span> |
| <span id="688">688</span> |
| <span id="689">689</span> |
| <span id="690">690</span> |
| <span id="691">691</span> |
| <span id="692">692</span> |
| <span id="693">693</span> |
| <span id="694">694</span> |
| <span id="695">695</span> |
| <span id="696">696</span> |
| <span id="697">697</span> |
| <span id="698">698</span> |
| <span id="699">699</span> |
| <span id="700">700</span> |
| <span id="701">701</span> |
| <span id="702">702</span> |
| <span id="703">703</span> |
| <span id="704">704</span> |
| <span id="705">705</span> |
| <span id="706">706</span> |
| <span id="707">707</span> |
| <span id="708">708</span> |
| <span id="709">709</span> |
| <span id="710">710</span> |
| <span id="711">711</span> |
| <span id="712">712</span> |
| <span id="713">713</span> |
| <span id="714">714</span> |
| <span id="715">715</span> |
| <span id="716">716</span> |
| <span id="717">717</span> |
| <span id="718">718</span> |
| <span id="719">719</span> |
| <span id="720">720</span> |
| <span id="721">721</span> |
| <span id="722">722</span> |
| <span id="723">723</span> |
| <span id="724">724</span> |
| <span id="725">725</span> |
| <span id="726">726</span> |
| <span id="727">727</span> |
| <span id="728">728</span> |
| <span id="729">729</span> |
| <span id="730">730</span> |
| <span id="731">731</span> |
| <span id="732">732</span> |
| <span id="733">733</span> |
| <span id="734">734</span> |
| <span id="735">735</span> |
| <span id="736">736</span> |
| <span id="737">737</span> |
| <span id="738">738</span> |
| <span id="739">739</span> |
| <span id="740">740</span> |
| <span id="741">741</span> |
| <span id="742">742</span> |
| <span id="743">743</span> |
| <span id="744">744</span> |
| <span id="745">745</span> |
| <span id="746">746</span> |
| <span id="747">747</span> |
| <span id="748">748</span> |
| <span id="749">749</span> |
| <span id="750">750</span> |
| <span id="751">751</span> |
| <span id="752">752</span> |
| <span id="753">753</span> |
| <span id="754">754</span> |
| <span id="755">755</span> |
| <span id="756">756</span> |
| <span id="757">757</span> |
| <span id="758">758</span> |
| <span id="759">759</span> |
| <span id="760">760</span> |
| <span id="761">761</span> |
| <span id="762">762</span> |
| <span id="763">763</span> |
| <span id="764">764</span> |
| <span id="765">765</span> |
| <span id="766">766</span> |
| <span id="767">767</span> |
| <span id="768">768</span> |
| <span id="769">769</span> |
| <span id="770">770</span> |
| <span id="771">771</span> |
| <span id="772">772</span> |
| <span id="773">773</span> |
| <span id="774">774</span> |
| <span id="775">775</span> |
| <span id="776">776</span> |
| <span id="777">777</span> |
| <span id="778">778</span> |
| <span id="779">779</span> |
| <span id="780">780</span> |
| <span id="781">781</span> |
| <span id="782">782</span> |
| <span id="783">783</span> |
| <span id="784">784</span> |
| <span id="785">785</span> |
| <span id="786">786</span> |
| <span id="787">787</span> |
| <span id="788">788</span> |
| <span id="789">789</span> |
| <span id="790">790</span> |
| <span id="791">791</span> |
| <span id="792">792</span> |
| <span id="793">793</span> |
| <span id="794">794</span> |
| <span id="795">795</span> |
| <span id="796">796</span> |
| <span id="797">797</span> |
| <span id="798">798</span> |
| <span id="799">799</span> |
| <span id="800">800</span> |
| <span id="801">801</span> |
| <span id="802">802</span> |
| <span id="803">803</span> |
| <span id="804">804</span> |
| <span id="805">805</span> |
| <span id="806">806</span> |
| <span id="807">807</span> |
| <span id="808">808</span> |
| <span id="809">809</span> |
| <span id="810">810</span> |
| <span id="811">811</span> |
| <span id="812">812</span> |
| <span id="813">813</span> |
| <span id="814">814</span> |
| <span id="815">815</span> |
| <span id="816">816</span> |
| <span id="817">817</span> |
| <span id="818">818</span> |
| <span id="819">819</span> |
| <span id="820">820</span> |
| <span id="821">821</span> |
| <span id="822">822</span> |
| <span id="823">823</span> |
| <span id="824">824</span> |
| <span id="825">825</span> |
| <span id="826">826</span> |
| <span id="827">827</span> |
| <span id="828">828</span> |
| <span id="829">829</span> |
| <span id="830">830</span> |
| <span id="831">831</span> |
| <span id="832">832</span> |
| <span id="833">833</span> |
| <span id="834">834</span> |
| <span id="835">835</span> |
| <span id="836">836</span> |
| <span id="837">837</span> |
| <span id="838">838</span> |
| <span id="839">839</span> |
| <span id="840">840</span> |
| <span id="841">841</span> |
| <span id="842">842</span> |
| <span id="843">843</span> |
| <span id="844">844</span> |
| <span id="845">845</span> |
| <span id="846">846</span> |
| <span id="847">847</span> |
| <span id="848">848</span> |
| <span id="849">849</span> |
| <span id="850">850</span> |
| <span id="851">851</span> |
| <span id="852">852</span> |
| <span id="853">853</span> |
| <span id="854">854</span> |
| <span id="855">855</span> |
| <span id="856">856</span> |
| <span id="857">857</span> |
| <span id="858">858</span> |
| <span id="859">859</span> |
| <span id="860">860</span> |
| <span id="861">861</span> |
| <span id="862">862</span> |
| <span id="863">863</span> |
| <span id="864">864</span> |
| <span id="865">865</span> |
| <span id="866">866</span> |
| <span id="867">867</span> |
| <span id="868">868</span> |
| <span id="869">869</span> |
| <span id="870">870</span> |
| <span id="871">871</span> |
| <span id="872">872</span> |
| <span id="873">873</span> |
| <span id="874">874</span> |
| <span id="875">875</span> |
| <span id="876">876</span> |
| <span id="877">877</span> |
| <span id="878">878</span> |
| <span id="879">879</span> |
| <span id="880">880</span> |
| <span id="881">881</span> |
| <span id="882">882</span> |
| <span id="883">883</span> |
| <span id="884">884</span> |
| <span id="885">885</span> |
| <span id="886">886</span> |
| <span id="887">887</span> |
| <span id="888">888</span> |
| <span id="889">889</span> |
| <span id="890">890</span> |
| <span id="891">891</span> |
| <span id="892">892</span> |
| <span id="893">893</span> |
| <span id="894">894</span> |
| <span id="895">895</span> |
| <span id="896">896</span> |
| <span id="897">897</span> |
| <span id="898">898</span> |
| <span id="899">899</span> |
| <span id="900">900</span> |
| <span id="901">901</span> |
| <span id="902">902</span> |
| <span id="903">903</span> |
| <span id="904">904</span> |
| <span id="905">905</span> |
| <span id="906">906</span> |
| <span id="907">907</span> |
| <span id="908">908</span> |
| <span id="909">909</span> |
| <span id="910">910</span> |
| <span id="911">911</span> |
| <span id="912">912</span> |
| <span id="913">913</span> |
| <span id="914">914</span> |
| <span id="915">915</span> |
| <span id="916">916</span> |
| <span id="917">917</span> |
| <span id="918">918</span> |
| <span id="919">919</span> |
| <span id="920">920</span> |
| <span id="921">921</span> |
| <span id="922">922</span> |
| <span id="923">923</span> |
| <span id="924">924</span> |
| <span id="925">925</span> |
| <span id="926">926</span> |
| <span id="927">927</span> |
| <span id="928">928</span> |
| <span id="929">929</span> |
| <span id="930">930</span> |
| <span id="931">931</span> |
| <span id="932">932</span> |
| <span id="933">933</span> |
| <span id="934">934</span> |
| <span id="935">935</span> |
| <span id="936">936</span> |
| <span id="937">937</span> |
| <span id="938">938</span> |
| <span id="939">939</span> |
| <span id="940">940</span> |
| <span id="941">941</span> |
| <span id="942">942</span> |
| <span id="943">943</span> |
| <span id="944">944</span> |
| <span id="945">945</span> |
| <span id="946">946</span> |
| <span id="947">947</span> |
| <span id="948">948</span> |
| <span id="949">949</span> |
| <span id="950">950</span> |
| <span id="951">951</span> |
| <span id="952">952</span> |
| <span id="953">953</span> |
| <span id="954">954</span> |
| <span id="955">955</span> |
| <span id="956">956</span> |
| <span id="957">957</span> |
| <span id="958">958</span> |
| <span id="959">959</span> |
| <span id="960">960</span> |
| <span id="961">961</span> |
| <span id="962">962</span> |
| <span id="963">963</span> |
| <span id="964">964</span> |
| <span id="965">965</span> |
| <span id="966">966</span> |
| <span id="967">967</span> |
| <span id="968">968</span> |
| <span id="969">969</span> |
| <span id="970">970</span> |
| <span id="971">971</span> |
| <span id="972">972</span> |
| <span id="973">973</span> |
| <span id="974">974</span> |
| <span id="975">975</span> |
| <span id="976">976</span> |
| <span id="977">977</span> |
| <span id="978">978</span> |
| <span id="979">979</span> |
| <span id="980">980</span> |
| <span id="981">981</span> |
| <span id="982">982</span> |
| <span id="983">983</span> |
| <span id="984">984</span> |
| <span id="985">985</span> |
| <span id="986">986</span> |
| <span id="987">987</span> |
| <span id="988">988</span> |
| <span id="989">989</span> |
| <span id="990">990</span> |
| <span id="991">991</span> |
| <span id="992">992</span> |
| <span id="993">993</span> |
| <span id="994">994</span> |
| <span id="995">995</span> |
| <span id="996">996</span> |
| <span id="997">997</span> |
| <span id="998">998</span> |
| <span id="999">999</span> |
| <span id="1000">1000</span> |
| <span id="1001">1001</span> |
| <span id="1002">1002</span> |
| <span id="1003">1003</span> |
| <span id="1004">1004</span> |
| <span id="1005">1005</span> |
| <span id="1006">1006</span> |
| <span id="1007">1007</span> |
| <span id="1008">1008</span> |
| <span id="1009">1009</span> |
| <span id="1010">1010</span> |
| <span id="1011">1011</span> |
| <span id="1012">1012</span> |
| <span id="1013">1013</span> |
| <span id="1014">1014</span> |
| <span id="1015">1015</span> |
| <span id="1016">1016</span> |
| <span id="1017">1017</span> |
| <span id="1018">1018</span> |
| <span id="1019">1019</span> |
| <span id="1020">1020</span> |
| <span id="1021">1021</span> |
| <span id="1022">1022</span> |
| <span id="1023">1023</span> |
| <span id="1024">1024</span> |
| <span id="1025">1025</span> |
| <span id="1026">1026</span> |
| <span id="1027">1027</span> |
| <span id="1028">1028</span> |
| <span id="1029">1029</span> |
| <span id="1030">1030</span> |
| <span id="1031">1031</span> |
| <span id="1032">1032</span> |
| <span id="1033">1033</span> |
| <span id="1034">1034</span> |
| <span id="1035">1035</span> |
| <span id="1036">1036</span> |
| <span id="1037">1037</span> |
| <span id="1038">1038</span> |
| <span id="1039">1039</span> |
| <span id="1040">1040</span> |
| <span id="1041">1041</span> |
| <span id="1042">1042</span> |
| <span id="1043">1043</span> |
| <span id="1044">1044</span> |
| <span id="1045">1045</span> |
| <span id="1046">1046</span> |
| <span id="1047">1047</span> |
| <span id="1048">1048</span> |
| <span id="1049">1049</span> |
| <span id="1050">1050</span> |
| <span id="1051">1051</span> |
| <span id="1052">1052</span> |
| <span id="1053">1053</span> |
| <span id="1054">1054</span> |
| <span id="1055">1055</span> |
| <span id="1056">1056</span> |
| <span id="1057">1057</span> |
| <span id="1058">1058</span> |
| <span id="1059">1059</span> |
| <span id="1060">1060</span> |
| <span id="1061">1061</span> |
| <span id="1062">1062</span> |
| <span id="1063">1063</span> |
| <span id="1064">1064</span> |
| <span id="1065">1065</span> |
| <span id="1066">1066</span> |
| <span id="1067">1067</span> |
| <span id="1068">1068</span> |
| <span id="1069">1069</span> |
| <span id="1070">1070</span> |
| <span id="1071">1071</span> |
| <span id="1072">1072</span> |
| <span id="1073">1073</span> |
| <span id="1074">1074</span> |
| <span id="1075">1075</span> |
| <span id="1076">1076</span> |
| <span id="1077">1077</span> |
| <span id="1078">1078</span> |
| <span id="1079">1079</span> |
| <span id="1080">1080</span> |
| <span id="1081">1081</span> |
| <span id="1082">1082</span> |
| <span id="1083">1083</span> |
| <span id="1084">1084</span> |
| <span id="1085">1085</span> |
| <span id="1086">1086</span> |
| <span id="1087">1087</span> |
| <span id="1088">1088</span> |
| <span id="1089">1089</span> |
| <span id="1090">1090</span> |
| <span id="1091">1091</span> |
| <span id="1092">1092</span> |
| <span id="1093">1093</span> |
| <span id="1094">1094</span> |
| <span id="1095">1095</span> |
| <span id="1096">1096</span> |
| <span id="1097">1097</span> |
| <span id="1098">1098</span> |
| <span id="1099">1099</span> |
| <span id="1100">1100</span> |
| <span id="1101">1101</span> |
| <span id="1102">1102</span> |
| <span id="1103">1103</span> |
| <span id="1104">1104</span> |
| <span id="1105">1105</span> |
| <span id="1106">1106</span> |
| <span id="1107">1107</span> |
| <span id="1108">1108</span> |
| <span id="1109">1109</span> |
| <span id="1110">1110</span> |
| <span id="1111">1111</span> |
| <span id="1112">1112</span> |
| <span id="1113">1113</span> |
| <span id="1114">1114</span> |
| <span id="1115">1115</span> |
| <span id="1116">1116</span> |
| <span id="1117">1117</span> |
| <span id="1118">1118</span> |
| <span id="1119">1119</span> |
| <span id="1120">1120</span> |
| <span id="1121">1121</span> |
| <span id="1122">1122</span> |
| <span id="1123">1123</span> |
| <span id="1124">1124</span> |
| <span id="1125">1125</span> |
| <span id="1126">1126</span> |
| <span id="1127">1127</span> |
| <span id="1128">1128</span> |
| <span id="1129">1129</span> |
| <span id="1130">1130</span> |
| <span id="1131">1131</span> |
| <span id="1132">1132</span> |
| <span id="1133">1133</span> |
| <span id="1134">1134</span> |
| <span id="1135">1135</span> |
| <span id="1136">1136</span> |
| <span id="1137">1137</span> |
| <span id="1138">1138</span> |
| <span id="1139">1139</span> |
| <span id="1140">1140</span> |
| <span id="1141">1141</span> |
| <span id="1142">1142</span> |
| <span id="1143">1143</span> |
| <span id="1144">1144</span> |
| <span id="1145">1145</span> |
| <span id="1146">1146</span> |
| <span id="1147">1147</span> |
| <span id="1148">1148</span> |
| <span id="1149">1149</span> |
| <span id="1150">1150</span> |
| <span id="1151">1151</span> |
| <span id="1152">1152</span> |
| <span id="1153">1153</span> |
| <span id="1154">1154</span> |
| <span id="1155">1155</span> |
| <span id="1156">1156</span> |
| <span id="1157">1157</span> |
| <span id="1158">1158</span> |
| <span id="1159">1159</span> |
| <span id="1160">1160</span> |
| <span id="1161">1161</span> |
| <span id="1162">1162</span> |
| <span id="1163">1163</span> |
| <span id="1164">1164</span> |
| <span id="1165">1165</span> |
| <span id="1166">1166</span> |
| <span id="1167">1167</span> |
| <span id="1168">1168</span> |
| <span id="1169">1169</span> |
| <span id="1170">1170</span> |
| <span id="1171">1171</span> |
| <span id="1172">1172</span> |
| <span id="1173">1173</span> |
| <span id="1174">1174</span> |
| <span id="1175">1175</span> |
| <span id="1176">1176</span> |
| <span id="1177">1177</span> |
| <span id="1178">1178</span> |
| <span id="1179">1179</span> |
| <span id="1180">1180</span> |
| <span id="1181">1181</span> |
| <span id="1182">1182</span> |
| <span id="1183">1183</span> |
| <span id="1184">1184</span> |
| <span id="1185">1185</span> |
| <span id="1186">1186</span> |
| <span id="1187">1187</span> |
| <span id="1188">1188</span> |
| <span id="1189">1189</span> |
| <span id="1190">1190</span> |
| <span id="1191">1191</span> |
| <span id="1192">1192</span> |
| <span id="1193">1193</span> |
| <span id="1194">1194</span> |
| <span id="1195">1195</span> |
| <span id="1196">1196</span> |
| <span id="1197">1197</span> |
| <span id="1198">1198</span> |
| <span id="1199">1199</span> |
| <span id="1200">1200</span> |
| <span id="1201">1201</span> |
| <span id="1202">1202</span> |
| <span id="1203">1203</span> |
| <span id="1204">1204</span> |
| <span id="1205">1205</span> |
| <span id="1206">1206</span> |
| <span id="1207">1207</span> |
| <span id="1208">1208</span> |
| <span id="1209">1209</span> |
| <span id="1210">1210</span> |
| <span id="1211">1211</span> |
| <span id="1212">1212</span> |
| <span id="1213">1213</span> |
| <span id="1214">1214</span> |
| <span id="1215">1215</span> |
| <span id="1216">1216</span> |
| <span id="1217">1217</span> |
| <span id="1218">1218</span> |
| <span id="1219">1219</span> |
| <span id="1220">1220</span> |
| <span id="1221">1221</span> |
| <span id="1222">1222</span> |
| <span id="1223">1223</span> |
| <span id="1224">1224</span> |
| <span id="1225">1225</span> |
| <span id="1226">1226</span> |
| <span id="1227">1227</span> |
| <span id="1228">1228</span> |
| <span id="1229">1229</span> |
| <span id="1230">1230</span> |
| <span id="1231">1231</span> |
| <span id="1232">1232</span> |
| <span id="1233">1233</span> |
| <span id="1234">1234</span> |
| <span id="1235">1235</span> |
| <span id="1236">1236</span> |
| <span id="1237">1237</span> |
| <span id="1238">1238</span> |
| <span id="1239">1239</span> |
| <span id="1240">1240</span> |
| <span id="1241">1241</span> |
| <span id="1242">1242</span> |
| <span id="1243">1243</span> |
| <span id="1244">1244</span> |
| <span id="1245">1245</span> |
| <span id="1246">1246</span> |
| <span id="1247">1247</span> |
| <span id="1248">1248</span> |
| <span id="1249">1249</span> |
| <span id="1250">1250</span> |
| <span id="1251">1251</span> |
| <span id="1252">1252</span> |
| <span id="1253">1253</span> |
| <span id="1254">1254</span> |
| <span id="1255">1255</span> |
| <span id="1256">1256</span> |
| <span id="1257">1257</span> |
| <span id="1258">1258</span> |
| <span id="1259">1259</span> |
| <span id="1260">1260</span> |
| <span id="1261">1261</span> |
| <span id="1262">1262</span> |
| <span id="1263">1263</span> |
| <span id="1264">1264</span> |
| <span id="1265">1265</span> |
| <span id="1266">1266</span> |
| <span id="1267">1267</span> |
| <span id="1268">1268</span> |
| <span id="1269">1269</span> |
| <span id="1270">1270</span> |
| <span id="1271">1271</span> |
| <span id="1272">1272</span> |
| <span id="1273">1273</span> |
| <span id="1274">1274</span> |
| <span id="1275">1275</span> |
| <span id="1276">1276</span> |
| <span id="1277">1277</span> |
| <span id="1278">1278</span> |
| <span id="1279">1279</span> |
| <span id="1280">1280</span> |
| <span id="1281">1281</span> |
| <span id="1282">1282</span> |
| <span id="1283">1283</span> |
| <span id="1284">1284</span> |
| <span id="1285">1285</span> |
| <span id="1286">1286</span> |
| <span id="1287">1287</span> |
| <span id="1288">1288</span> |
| <span id="1289">1289</span> |
| <span id="1290">1290</span> |
| <span id="1291">1291</span> |
| <span id="1292">1292</span> |
| <span id="1293">1293</span> |
| <span id="1294">1294</span> |
| <span id="1295">1295</span> |
| <span id="1296">1296</span> |
| <span id="1297">1297</span> |
| <span id="1298">1298</span> |
| <span id="1299">1299</span> |
| <span id="1300">1300</span> |
| <span id="1301">1301</span> |
| <span id="1302">1302</span> |
| <span id="1303">1303</span> |
| <span id="1304">1304</span> |
| <span id="1305">1305</span> |
| <span id="1306">1306</span> |
| <span id="1307">1307</span> |
| <span id="1308">1308</span> |
| <span id="1309">1309</span> |
| <span id="1310">1310</span> |
| <span id="1311">1311</span> |
| <span id="1312">1312</span> |
| <span id="1313">1313</span> |
| <span id="1314">1314</span> |
| <span id="1315">1315</span> |
| <span id="1316">1316</span> |
| <span id="1317">1317</span> |
| <span id="1318">1318</span> |
| <span id="1319">1319</span> |
| <span id="1320">1320</span> |
| <span id="1321">1321</span> |
| <span id="1322">1322</span> |
| <span id="1323">1323</span> |
| <span id="1324">1324</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::fmt; |
| <span class="kw">use </span>std::iter; |
| <span class="kw">use </span>std::result; |
| <span class="kw">use </span>std::sync::Arc; |
| |
| <span class="kw">use </span>regex_syntax::hir::{<span class="self">self</span>, Hir, Look}; |
| <span class="kw">use </span>regex_syntax::is_word_byte; |
| <span class="kw">use </span>regex_syntax::utf8::{Utf8Range, Utf8Sequence, Utf8Sequences}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::prog::{ |
| EmptyLook, Inst, InstBytes, InstChar, InstEmptyLook, InstPtr, InstRanges, |
| InstSave, InstSplit, Program, |
| }; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::Error; |
| |
| <span class="kw">type </span><span class="prelude-ty">Result </span>= result::Result<Patch, Error>; |
| <span class="kw">type </span>ResultOrEmpty = result::Result<<span class="prelude-ty">Option</span><Patch>, Error>; |
| |
| <span class="attribute">#[derive(Debug)] |
| </span><span class="kw">struct </span>Patch { |
| hole: Hole, |
| entry: InstPtr, |
| } |
| |
| <span class="doccomment">/// A compiler translates a regular expression AST to a sequence of |
| /// instructions. The sequence of instructions represents an NFA. |
| </span><span class="comment">// `Compiler` is only public via the `internal` module, so avoid deriving |
| // `Debug`. |
| </span><span class="attribute">#[allow(missing_debug_implementations)] |
| </span><span class="kw">pub struct </span>Compiler { |
| insts: Vec<MaybeInst>, |
| compiled: Program, |
| capture_name_idx: HashMap<String, usize>, |
| num_exprs: usize, |
| size_limit: usize, |
| suffix_cache: SuffixCache, |
| utf8_seqs: <span class="prelude-ty">Option</span><Utf8Sequences>, |
| byte_classes: ByteClassSet, |
| <span class="comment">// This keeps track of extra bytes allocated while compiling the regex |
| // program. Currently, this corresponds to two things. First is the heap |
| // memory allocated by Unicode character classes ('InstRanges'). Second is |
| // a "fake" amount of memory used by empty sub-expressions, so that enough |
| // empty sub-expressions will ultimately trigger the compiler to bail |
| // because of a size limit restriction. (That empty sub-expressions don't |
| // add to heap memory usage is more-or-less an implementation detail.) In |
| // the second case, if we don't bail, then an excessively large repetition |
| // on an empty sub-expression can result in the compiler using a very large |
| // amount of CPU time. |
| </span>extra_inst_bytes: usize, |
| } |
| |
| <span class="kw">impl </span>Compiler { |
| <span class="doccomment">/// Create a new regular expression compiler. |
| /// |
| /// Various options can be set before calling `compile` on an expression. |
| </span><span class="kw">pub fn </span>new() -> <span class="self">Self </span>{ |
| Compiler { |
| insts: <span class="macro">vec!</span>[], |
| compiled: Program::new(), |
| capture_name_idx: HashMap::new(), |
| num_exprs: <span class="number">0</span>, |
| size_limit: <span class="number">10 </span>* (<span class="number">1 </span><< <span class="number">20</span>), |
| suffix_cache: SuffixCache::new(<span class="number">1000</span>), |
| utf8_seqs: <span class="prelude-val">Some</span>(Utf8Sequences::new(<span class="string">'\x00'</span>, <span class="string">'\x00'</span>)), |
| byte_classes: ByteClassSet::new(), |
| extra_inst_bytes: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="doccomment">/// The size of the resulting program is limited by size_limit. If |
| /// the program approximately exceeds the given size (in bytes), then |
| /// compilation will stop and return an error. |
| </span><span class="kw">pub fn </span>size_limit(<span class="kw-2">mut </span><span class="self">self</span>, size_limit: usize) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.size_limit = size_limit; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// If bytes is true, then the program is compiled as a byte based |
| /// automaton, which incorporates UTF-8 decoding into the machine. If it's |
| /// false, then the automaton is Unicode scalar value based, e.g., an |
| /// engine utilizing such an automaton is responsible for UTF-8 decoding. |
| /// |
| /// The specific invariant is that when returning a byte based machine, |
| /// the neither the `Char` nor `Ranges` instructions are produced. |
| /// Conversely, when producing a Unicode scalar value machine, the `Bytes` |
| /// instruction is never produced. |
| /// |
| /// Note that `dfa(true)` implies `bytes(true)`. |
| </span><span class="kw">pub fn </span>bytes(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.compiled.is_bytes = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// When disabled, the program compiled may match arbitrary bytes. |
| /// |
| /// When enabled (the default), all compiled programs exclusively match |
| /// valid UTF-8 bytes. |
| </span><span class="kw">pub fn </span>only_utf8(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.compiled.only_utf8 = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// When set, the machine returned is suitable for use in the DFA matching |
| /// engine. |
| /// |
| /// In particular, this ensures that if the regex is not anchored in the |
| /// beginning, then a preceding `.*?` is included in the program. (The NFA |
| /// based engines handle the preceding `.*?` explicitly, which is difficult |
| /// or impossible in the DFA engine.) |
| </span><span class="kw">pub fn </span>dfa(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.compiled.is_dfa = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// When set, the machine returned is suitable for matching text in |
| /// reverse. In particular, all concatenations are flipped. |
| </span><span class="kw">pub fn </span>reverse(<span class="kw-2">mut </span><span class="self">self</span>, yes: bool) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.compiled.is_reverse = yes; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Compile a regular expression given its AST. |
| /// |
| /// The compiler is guaranteed to succeed unless the program exceeds the |
| /// specified size limit. If the size limit is exceeded, then compilation |
| /// stops and returns an error. |
| </span><span class="kw">pub fn </span>compile(<span class="kw-2">mut </span><span class="self">self</span>, exprs: <span class="kw-2">&</span>[Hir]) -> result::Result<Program, Error> { |
| <span class="macro">debug_assert!</span>(!exprs.is_empty()); |
| <span class="self">self</span>.num_exprs = exprs.len(); |
| <span class="kw">if </span>exprs.len() == <span class="number">1 </span>{ |
| <span class="self">self</span>.compile_one(<span class="kw-2">&</span>exprs[<span class="number">0</span>]) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.compile_many(exprs) |
| } |
| } |
| |
| <span class="kw">fn </span>compile_one(<span class="kw-2">mut </span><span class="self">self</span>, expr: <span class="kw-2">&</span>Hir) -> result::Result<Program, Error> { |
| <span class="comment">// If we're compiling a forward DFA and we aren't anchored, then |
| // add a `.*?` before the first capture group. |
| // Other matching engines handle this by baking the logic into the |
| // matching engine itself. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>dotstar_patch = Patch { hole: Hole::None, entry: <span class="number">0 </span>}; |
| <span class="self">self</span>.compiled.is_anchored_start = |
| expr.properties().look_set_prefix().contains(Look::Start); |
| <span class="self">self</span>.compiled.is_anchored_end = |
| expr.properties().look_set_suffix().contains(Look::End); |
| <span class="kw">if </span><span class="self">self</span>.compiled.needs_dotstar() { |
| dotstar_patch = <span class="self">self</span>.c_dotstar()<span class="question-mark">?</span>; |
| <span class="self">self</span>.compiled.start = dotstar_patch.entry; |
| } |
| <span class="self">self</span>.compiled.captures = <span class="macro">vec!</span>[<span class="prelude-val">None</span>]; |
| <span class="kw">let </span>patch = |
| <span class="self">self</span>.c_capture(<span class="number">0</span>, expr)<span class="question-mark">?</span>.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="kw">if </span><span class="self">self</span>.compiled.needs_dotstar() { |
| <span class="self">self</span>.fill(dotstar_patch.hole, patch.entry); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.compiled.start = patch.entry; |
| } |
| <span class="self">self</span>.fill_to_next(patch.hole); |
| <span class="self">self</span>.compiled.matches = <span class="macro">vec!</span>[<span class="self">self</span>.insts.len()]; |
| <span class="self">self</span>.push_compiled(Inst::Match(<span class="number">0</span>)); |
| <span class="self">self</span>.compiled.static_captures_len = |
| expr.properties().static_explicit_captures_len(); |
| <span class="self">self</span>.compile_finish() |
| } |
| |
| <span class="kw">fn </span>compile_many( |
| <span class="kw-2">mut </span><span class="self">self</span>, |
| exprs: <span class="kw-2">&</span>[Hir], |
| ) -> result::Result<Program, Error> { |
| <span class="macro">debug_assert!</span>(exprs.len() > <span class="number">1</span>); |
| |
| <span class="self">self</span>.compiled.is_anchored_start = exprs |
| .iter() |
| .all(|e| e.properties().look_set_prefix().contains(Look::Start)); |
| <span class="self">self</span>.compiled.is_anchored_end = exprs |
| .iter() |
| .all(|e| e.properties().look_set_suffix().contains(Look::End)); |
| <span class="kw">let </span><span class="kw-2">mut </span>dotstar_patch = Patch { hole: Hole::None, entry: <span class="number">0 </span>}; |
| <span class="kw">if </span><span class="self">self</span>.compiled.needs_dotstar() { |
| dotstar_patch = <span class="self">self</span>.c_dotstar()<span class="question-mark">?</span>; |
| <span class="self">self</span>.compiled.start = dotstar_patch.entry; |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.compiled.start = <span class="number">0</span>; <span class="comment">// first instruction is always split |
| </span>} |
| <span class="self">self</span>.fill_to_next(dotstar_patch.hole); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_hole = Hole::None; |
| <span class="kw">for </span>(i, expr) <span class="kw">in </span>exprs[<span class="number">0</span>..exprs.len() - <span class="number">1</span>].iter().enumerate() { |
| <span class="self">self</span>.fill_to_next(prev_hole); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">let </span>Patch { hole, entry } = |
| <span class="self">self</span>.c_capture(<span class="number">0</span>, expr)<span class="question-mark">?</span>.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="self">self</span>.fill_to_next(hole); |
| <span class="self">self</span>.compiled.matches.push(<span class="self">self</span>.insts.len()); |
| <span class="self">self</span>.push_compiled(Inst::Match(i)); |
| prev_hole = <span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry), <span class="prelude-val">None</span>); |
| } |
| <span class="kw">let </span>i = exprs.len() - <span class="number">1</span>; |
| <span class="kw">let </span>Patch { hole, entry } = |
| <span class="self">self</span>.c_capture(<span class="number">0</span>, <span class="kw-2">&</span>exprs[i])<span class="question-mark">?</span>.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="self">self</span>.fill(prev_hole, entry); |
| <span class="self">self</span>.fill_to_next(hole); |
| <span class="self">self</span>.compiled.matches.push(<span class="self">self</span>.insts.len()); |
| <span class="self">self</span>.push_compiled(Inst::Match(i)); |
| <span class="self">self</span>.compile_finish() |
| } |
| |
| <span class="kw">fn </span>compile_finish(<span class="kw-2">mut </span><span class="self">self</span>) -> result::Result<Program, Error> { |
| <span class="self">self</span>.compiled.insts = |
| <span class="self">self</span>.insts.into_iter().map(|inst| inst.unwrap()).collect(); |
| <span class="self">self</span>.compiled.byte_classes = <span class="self">self</span>.byte_classes.byte_classes(); |
| <span class="self">self</span>.compiled.capture_name_idx = Arc::new(<span class="self">self</span>.capture_name_idx); |
| <span class="prelude-val">Ok</span>(<span class="self">self</span>.compiled) |
| } |
| |
| <span class="doccomment">/// Compile expr into self.insts, returning a patch on success, |
| /// or an error if we run out of memory. |
| /// |
| /// All of the c_* methods of the compiler share the contract outlined |
| /// here. |
| /// |
| /// The main thing that a c_* method does is mutate `self.insts` |
| /// to add a list of mostly compiled instructions required to execute |
| /// the given expression. `self.insts` contains MaybeInsts rather than |
| /// Insts because there is some backpatching required. |
| /// |
| /// The `Patch` value returned by each c_* method provides metadata |
| /// about the compiled instructions emitted to `self.insts`. The |
| /// `entry` member of the patch refers to the first instruction |
| /// (the entry point), while the `hole` member contains zero or |
| /// more offsets to partial instructions that need to be backpatched. |
| /// The c_* routine can't know where its list of instructions are going to |
| /// jump to after execution, so it is up to the caller to patch |
| /// these jumps to point to the right place. So compiling some |
| /// expression, e, we would end up with a situation that looked like: |
| /// |
| /// ```text |
| /// self.insts = [ ..., i1, i2, ..., iexit1, ..., iexitn, ...] |
| /// ^ ^ ^ |
| /// | \ / |
| /// entry \ / |
| /// hole |
| /// ``` |
| /// |
| /// To compile two expressions, e1 and e2, concatenated together we |
| /// would do: |
| /// |
| /// ```ignore |
| /// let patch1 = self.c(e1); |
| /// let patch2 = self.c(e2); |
| /// ``` |
| /// |
| /// while leaves us with a situation that looks like |
| /// |
| /// ```text |
| /// self.insts = [ ..., i1, ..., iexit1, ..., i2, ..., iexit2 ] |
| /// ^ ^ ^ ^ |
| /// | | | | |
| /// entry1 hole1 entry2 hole2 |
| /// ``` |
| /// |
| /// Then to merge the two patches together into one we would backpatch |
| /// hole1 with entry2 and return a new patch that enters at entry1 |
| /// and has hole2 for a hole. In fact, if you look at the c_concat |
| /// method you will see that it does exactly this, though it handles |
| /// a list of expressions rather than just the two that we use for |
| /// an example. |
| /// |
| /// Ok(None) is returned when an expression is compiled to no |
| /// instruction, and so no patch.entry value makes sense. |
| </span><span class="kw">fn </span>c(<span class="kw-2">&mut </span><span class="self">self</span>, expr: <span class="kw-2">&</span>Hir) -> ResultOrEmpty { |
| <span class="kw">use </span><span class="kw">crate</span>::prog; |
| <span class="kw">use </span>regex_syntax::hir::HirKind::<span class="kw-2">*</span>; |
| |
| <span class="self">self</span>.check_size()<span class="question-mark">?</span>; |
| <span class="kw">match </span><span class="kw-2">*</span>expr.kind() { |
| Empty => <span class="self">self</span>.c_empty(), |
| Literal(hir::Literal(<span class="kw-2">ref </span>bytes)) => { |
| <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse { |
| <span class="kw">let </span><span class="kw-2">mut </span>bytes = bytes.to_vec(); |
| bytes.reverse(); |
| <span class="self">self</span>.c_literal(<span class="kw-2">&</span>bytes) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.c_literal(bytes) |
| } |
| } |
| Class(hir::Class::Unicode(<span class="kw-2">ref </span>cls)) => <span class="self">self</span>.c_class(cls.ranges()), |
| Class(hir::Class::Bytes(<span class="kw-2">ref </span>cls)) => { |
| <span class="kw">if </span><span class="self">self</span>.compiled.uses_bytes() { |
| <span class="self">self</span>.c_class_bytes(cls.ranges()) |
| } <span class="kw">else </span>{ |
| <span class="macro">assert!</span>(cls.is_ascii()); |
| <span class="kw">let </span><span class="kw-2">mut </span>char_ranges = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>r <span class="kw">in </span>cls.iter() { |
| <span class="kw">let </span>(s, e) = (r.start() <span class="kw">as </span>char, r.end() <span class="kw">as </span>char); |
| char_ranges.push(hir::ClassUnicodeRange::new(s, e)); |
| } |
| <span class="self">self</span>.c_class(<span class="kw-2">&</span>char_ranges) |
| } |
| } |
| Look(<span class="kw-2">ref </span>look) => <span class="kw">match </span><span class="kw-2">*</span>look { |
| hir::Look::Start <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse => { |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::EndText) |
| } |
| hir::Look::Start => { |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::StartText) |
| } |
| hir::Look::End <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse => { |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::StartText) |
| } |
| hir::Look::End => <span class="self">self</span>.c_empty_look(prog::EmptyLook::EndText), |
| hir::Look::StartLF <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse => { |
| <span class="self">self</span>.byte_classes.set_range(<span class="string">b'\n'</span>, <span class="string">b'\n'</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::EndLine) |
| } |
| hir::Look::StartLF => { |
| <span class="self">self</span>.byte_classes.set_range(<span class="string">b'\n'</span>, <span class="string">b'\n'</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::StartLine) |
| } |
| hir::Look::EndLF <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse => { |
| <span class="self">self</span>.byte_classes.set_range(<span class="string">b'\n'</span>, <span class="string">b'\n'</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::StartLine) |
| } |
| hir::Look::EndLF => { |
| <span class="self">self</span>.byte_classes.set_range(<span class="string">b'\n'</span>, <span class="string">b'\n'</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::EndLine) |
| } |
| hir::Look::StartCRLF | hir::Look::EndCRLF => { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Syntax( |
| <span class="string">"CRLF-aware line anchors are not supported yet" |
| </span>.to_string(), |
| )); |
| } |
| hir::Look::WordAscii => { |
| <span class="self">self</span>.byte_classes.set_word_boundary(); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::WordBoundaryAscii) |
| } |
| hir::Look::WordAsciiNegate => { |
| <span class="self">self</span>.byte_classes.set_word_boundary(); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::NotWordBoundaryAscii) |
| } |
| hir::Look::WordUnicode => { |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(feature = <span class="string">"unicode-perl"</span>) { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Syntax( |
| <span class="string">"Unicode word boundaries are unavailable when \ |
| the unicode-perl feature is disabled" |
| </span>.to_string(), |
| )); |
| } |
| <span class="self">self</span>.compiled.has_unicode_word_boundary = <span class="bool-val">true</span>; |
| <span class="self">self</span>.byte_classes.set_word_boundary(); |
| <span class="comment">// We also make sure that all ASCII bytes are in a different |
| // class from non-ASCII bytes. Otherwise, it's possible for |
| // ASCII bytes to get lumped into the same class as non-ASCII |
| // bytes. This in turn may cause the lazy DFA to falsely start |
| // when it sees an ASCII byte that maps to a byte class with |
| // non-ASCII bytes. This ensures that never happens. |
| </span><span class="self">self</span>.byte_classes.set_range(<span class="number">0</span>, <span class="number">0x7F</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::WordBoundary) |
| } |
| hir::Look::WordUnicodeNegate => { |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(feature = <span class="string">"unicode-perl"</span>) { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Syntax( |
| <span class="string">"Unicode word boundaries are unavailable when \ |
| the unicode-perl feature is disabled" |
| </span>.to_string(), |
| )); |
| } |
| <span class="self">self</span>.compiled.has_unicode_word_boundary = <span class="bool-val">true</span>; |
| <span class="self">self</span>.byte_classes.set_word_boundary(); |
| <span class="comment">// See comments above for why we set the ASCII range here. |
| </span><span class="self">self</span>.byte_classes.set_range(<span class="number">0</span>, <span class="number">0x7F</span>); |
| <span class="self">self</span>.c_empty_look(prog::EmptyLook::NotWordBoundary) |
| } |
| }, |
| Capture(hir::Capture { index, <span class="kw-2">ref </span>name, <span class="kw-2">ref </span>sub }) => { |
| <span class="kw">if </span>index <span class="kw">as </span>usize >= <span class="self">self</span>.compiled.captures.len() { |
| <span class="kw">let </span>name = <span class="kw">match </span><span class="kw-2">*</span>name { |
| <span class="prelude-val">None </span>=> <span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>(<span class="kw-2">ref </span>boxed_str) => <span class="prelude-val">Some</span>(boxed_str.to_string()), |
| }; |
| <span class="self">self</span>.compiled.captures.push(name.clone()); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(name) = name { |
| <span class="self">self</span>.capture_name_idx.insert(name, index <span class="kw">as </span>usize); |
| } |
| } |
| <span class="self">self</span>.c_capture(<span class="number">2 </span>* index <span class="kw">as </span>usize, sub) |
| } |
| Concat(<span class="kw-2">ref </span>es) => { |
| <span class="kw">if </span><span class="self">self</span>.compiled.is_reverse { |
| <span class="self">self</span>.c_concat(es.iter().rev()) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.c_concat(es) |
| } |
| } |
| Alternation(<span class="kw-2">ref </span>es) => <span class="self">self</span>.c_alternate(<span class="kw-2">&**</span>es), |
| Repetition(<span class="kw-2">ref </span>rep) => <span class="self">self</span>.c_repeat(rep), |
| } |
| } |
| |
| <span class="kw">fn </span>c_empty(<span class="kw-2">&mut </span><span class="self">self</span>) -> ResultOrEmpty { |
| <span class="comment">// See: https://github.com/rust-lang/regex/security/advisories/GHSA-m5pq-gvj9-9vr8 |
| // See: CVE-2022-24713 |
| // |
| // Since 'empty' sub-expressions don't increase the size of |
| // the actual compiled object, we "fake" an increase in its |
| // size so that our 'check_size_limit' routine will eventually |
| // stop compilation if there are too many empty sub-expressions |
| // (e.g., via a large repetition). |
| </span><span class="self">self</span>.extra_inst_bytes += std::mem::size_of::<Inst>(); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">None</span>) |
| } |
| |
| <span class="kw">fn </span>c_capture(<span class="kw-2">&mut </span><span class="self">self</span>, first_slot: usize, expr: <span class="kw-2">&</span>Hir) -> ResultOrEmpty { |
| <span class="kw">if </span><span class="self">self</span>.num_exprs > <span class="number">1 </span>|| <span class="self">self</span>.compiled.is_dfa { |
| <span class="comment">// Don't ever compile Save instructions for regex sets because |
| // they are never used. They are also never used in DFA programs |
| // because DFAs can't handle captures. |
| </span><span class="self">self</span>.c(expr) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>entry = <span class="self">self</span>.insts.len(); |
| <span class="kw">let </span>hole = <span class="self">self</span>.push_hole(InstHole::Save { slot: first_slot }); |
| <span class="kw">let </span>patch = <span class="self">self</span>.c(expr)<span class="question-mark">?</span>.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="self">self</span>.fill(hole, patch.entry); |
| <span class="self">self</span>.fill_to_next(patch.hole); |
| <span class="kw">let </span>hole = <span class="self">self</span>.push_hole(InstHole::Save { slot: first_slot + <span class="number">1 </span>}); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry })) |
| } |
| } |
| |
| <span class="kw">fn </span>c_dotstar(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Result </span>{ |
| <span class="kw">let </span>hir = <span class="kw">if </span><span class="self">self</span>.compiled.only_utf8() { |
| Hir::dot(hir::Dot::AnyChar) |
| } <span class="kw">else </span>{ |
| Hir::dot(hir::Dot::AnyByte) |
| }; |
| <span class="prelude-val">Ok</span>(<span class="self">self |
| </span>.c(<span class="kw-2">&</span>Hir::repetition(hir::Repetition { |
| min: <span class="number">0</span>, |
| max: <span class="prelude-val">None</span>, |
| greedy: <span class="bool-val">false</span>, |
| sub: Box::new(hir), |
| }))<span class="question-mark">? |
| </span>.unwrap()) |
| } |
| |
| <span class="kw">fn </span>c_char(<span class="kw-2">&mut </span><span class="self">self</span>, c: char) -> ResultOrEmpty { |
| <span class="kw">if </span><span class="self">self</span>.compiled.uses_bytes() { |
| <span class="kw">if </span>c.is_ascii() { |
| <span class="kw">let </span>b = c <span class="kw">as </span>u8; |
| <span class="kw">let </span>hole = |
| <span class="self">self</span>.push_hole(InstHole::Bytes { start: b, end: b }); |
| <span class="self">self</span>.byte_classes.set_range(b, b); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry: <span class="self">self</span>.insts.len() - <span class="number">1 </span>})) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.c_class(<span class="kw-2">&</span>[hir::ClassUnicodeRange::new(c, c)]) |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>hole = <span class="self">self</span>.push_hole(InstHole::Char { c }); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry: <span class="self">self</span>.insts.len() - <span class="number">1 </span>})) |
| } |
| } |
| |
| <span class="kw">fn </span>c_class(<span class="kw-2">&mut </span><span class="self">self</span>, ranges: <span class="kw-2">&</span>[hir::ClassUnicodeRange]) -> ResultOrEmpty { |
| <span class="kw">use </span>std::mem::size_of; |
| |
| <span class="kw">if </span>ranges.is_empty() { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Syntax( |
| <span class="string">"empty character classes are not allowed"</span>.to_string(), |
| )); |
| } |
| <span class="kw">if </span><span class="self">self</span>.compiled.uses_bytes() { |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(CompileClass { c: <span class="self">self</span>, ranges }.compile()<span class="question-mark">?</span>)) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>ranges: Vec<(char, char)> = |
| ranges.iter().map(|r| (r.start(), r.end())).collect(); |
| <span class="kw">let </span>hole = <span class="kw">if </span>ranges.len() == <span class="number">1 </span>&& ranges[<span class="number">0</span>].<span class="number">0 </span>== ranges[<span class="number">0</span>].<span class="number">1 </span>{ |
| <span class="self">self</span>.push_hole(InstHole::Char { c: ranges[<span class="number">0</span>].<span class="number">0 </span>}) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.extra_inst_bytes += |
| ranges.len() * (size_of::<char>() * <span class="number">2</span>); |
| <span class="self">self</span>.push_hole(InstHole::Ranges { ranges }) |
| }; |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry: <span class="self">self</span>.insts.len() - <span class="number">1 </span>})) |
| } |
| } |
| |
| <span class="kw">fn </span>c_byte(<span class="kw-2">&mut </span><span class="self">self</span>, b: u8) -> ResultOrEmpty { |
| <span class="self">self</span>.c_class_bytes(<span class="kw-2">&</span>[hir::ClassBytesRange::new(b, b)]) |
| } |
| |
| <span class="kw">fn </span>c_class_bytes( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| ranges: <span class="kw-2">&</span>[hir::ClassBytesRange], |
| ) -> ResultOrEmpty { |
| <span class="kw">if </span>ranges.is_empty() { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Syntax( |
| <span class="string">"empty character classes are not allowed"</span>.to_string(), |
| )); |
| } |
| |
| <span class="kw">let </span>first_split_entry = <span class="self">self</span>.insts.len(); |
| <span class="kw">let </span><span class="kw-2">mut </span>holes = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_hole = Hole::None; |
| <span class="kw">for </span>r <span class="kw">in </span><span class="kw-2">&</span>ranges[<span class="number">0</span>..ranges.len() - <span class="number">1</span>] { |
| <span class="self">self</span>.fill_to_next(prev_hole); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">let </span>next = <span class="self">self</span>.insts.len(); |
| <span class="self">self</span>.byte_classes.set_range(r.start(), r.end()); |
| holes.push(<span class="self">self</span>.push_hole(InstHole::Bytes { |
| start: r.start(), |
| end: r.end(), |
| })); |
| prev_hole = <span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(next), <span class="prelude-val">None</span>); |
| } |
| <span class="kw">let </span>next = <span class="self">self</span>.insts.len(); |
| <span class="kw">let </span>r = <span class="kw-2">&</span>ranges[ranges.len() - <span class="number">1</span>]; |
| <span class="self">self</span>.byte_classes.set_range(r.start(), r.end()); |
| holes.push( |
| <span class="self">self</span>.push_hole(InstHole::Bytes { start: r.start(), end: r.end() }), |
| ); |
| <span class="self">self</span>.fill(prev_hole, next); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: Hole::Many(holes), entry: first_split_entry })) |
| } |
| |
| <span class="kw">fn </span>c_empty_look(<span class="kw-2">&mut </span><span class="self">self</span>, look: EmptyLook) -> ResultOrEmpty { |
| <span class="kw">let </span>hole = <span class="self">self</span>.push_hole(InstHole::EmptyLook { look }); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry: <span class="self">self</span>.insts.len() - <span class="number">1 </span>})) |
| } |
| |
| <span class="kw">fn </span>c_literal(<span class="kw-2">&mut </span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) -> ResultOrEmpty { |
| <span class="kw">match </span>core::str::from_utf8(bytes) { |
| <span class="prelude-val">Ok</span>(string) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>it = string.chars(); |
| <span class="kw">let </span>Patch { <span class="kw-2">mut </span>hole, entry } = <span class="kw">loop </span>{ |
| <span class="kw">match </span>it.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.c_empty(), |
| <span class="prelude-val">Some</span>(ch) => { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c_char(ch)<span class="question-mark">? </span>{ |
| <span class="kw">break </span>p; |
| } |
| } |
| } |
| }; |
| <span class="kw">for </span>ch <span class="kw">in </span>it { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c_char(ch)<span class="question-mark">? </span>{ |
| <span class="self">self</span>.fill(hole, p.entry); |
| hole = p.hole; |
| } |
| } |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry })) |
| } |
| <span class="prelude-val">Err</span>(<span class="kw">_</span>) => { |
| <span class="macro">assert!</span>(<span class="self">self</span>.compiled.uses_bytes()); |
| <span class="kw">let </span><span class="kw-2">mut </span>it = bytes.iter().copied(); |
| <span class="kw">let </span>Patch { <span class="kw-2">mut </span>hole, entry } = <span class="kw">loop </span>{ |
| <span class="kw">match </span>it.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.c_empty(), |
| <span class="prelude-val">Some</span>(byte) => { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c_byte(byte)<span class="question-mark">? </span>{ |
| <span class="kw">break </span>p; |
| } |
| } |
| } |
| }; |
| <span class="kw">for </span>byte <span class="kw">in </span>it { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c_byte(byte)<span class="question-mark">? </span>{ |
| <span class="self">self</span>.fill(hole, p.entry); |
| hole = p.hole; |
| } |
| } |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry })) |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>c_concat<<span class="lifetime">'a</span>, I>(<span class="kw-2">&mut </span><span class="self">self</span>, exprs: I) -> ResultOrEmpty |
| <span class="kw">where |
| </span>I: IntoIterator<Item = <span class="kw-2">&</span><span class="lifetime">'a </span>Hir>, |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>exprs = exprs.into_iter(); |
| <span class="kw">let </span>Patch { <span class="kw-2">mut </span>hole, entry } = <span class="kw">loop </span>{ |
| <span class="kw">match </span>exprs.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.c_empty(), |
| <span class="prelude-val">Some</span>(e) => { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c(e)<span class="question-mark">? </span>{ |
| <span class="kw">break </span>p; |
| } |
| } |
| } |
| }; |
| <span class="kw">for </span>e <span class="kw">in </span>exprs { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(p) = <span class="self">self</span>.c(e)<span class="question-mark">? </span>{ |
| <span class="self">self</span>.fill(hole, p.entry); |
| hole = p.hole; |
| } |
| } |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole, entry })) |
| } |
| |
| <span class="kw">fn </span>c_alternate(<span class="kw-2">&mut </span><span class="self">self</span>, exprs: <span class="kw-2">&</span>[Hir]) -> ResultOrEmpty { |
| <span class="macro">debug_assert!</span>( |
| exprs.len() >= <span class="number">2</span>, |
| <span class="string">"alternates must have at least 2 exprs" |
| </span>); |
| |
| <span class="comment">// Initial entry point is always the first split. |
| </span><span class="kw">let </span>first_split_entry = <span class="self">self</span>.insts.len(); |
| |
| <span class="comment">// Save up all of the holes from each alternate. They will all get |
| // patched to point to the same location. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>holes = <span class="macro">vec!</span>[]; |
| |
| <span class="comment">// true indicates that the hole is a split where we want to fill |
| // the second branch. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>prev_hole = (Hole::None, <span class="bool-val">false</span>); |
| <span class="kw">for </span>e <span class="kw">in </span><span class="kw-2">&</span>exprs[<span class="number">0</span>..exprs.len() - <span class="number">1</span>] { |
| <span class="kw">if </span>prev_hole.<span class="number">1 </span>{ |
| <span class="kw">let </span>next = <span class="self">self</span>.insts.len(); |
| <span class="self">self</span>.fill_split(prev_hole.<span class="number">0</span>, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(next)); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.fill_to_next(prev_hole.<span class="number">0</span>); |
| } |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(Patch { hole, entry }) = <span class="self">self</span>.c(e)<span class="question-mark">? </span>{ |
| holes.push(hole); |
| prev_hole = (<span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry), <span class="prelude-val">None</span>), <span class="bool-val">false</span>); |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>(split1, split2) = split.dup_one(); |
| holes.push(split1); |
| prev_hole = (split2, <span class="bool-val">true</span>); |
| } |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(Patch { hole, entry }) = <span class="self">self</span>.c(<span class="kw-2">&</span>exprs[exprs.len() - <span class="number">1</span>])<span class="question-mark">? </span>{ |
| holes.push(hole); |
| <span class="kw">if </span>prev_hole.<span class="number">1 </span>{ |
| <span class="self">self</span>.fill_split(prev_hole.<span class="number">0</span>, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(entry)); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.fill(prev_hole.<span class="number">0</span>, entry); |
| } |
| } <span class="kw">else </span>{ |
| <span class="comment">// We ignore prev_hole.1. When it's true, it means we have two |
| // empty branches both pushing prev_hole.0 into holes, so both |
| // branches will go to the same place anyway. |
| </span>holes.push(prev_hole.<span class="number">0</span>); |
| } |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: Hole::Many(holes), entry: first_split_entry })) |
| } |
| |
| <span class="kw">fn </span>c_repeat(<span class="kw-2">&mut </span><span class="self">self</span>, rep: <span class="kw-2">&</span>hir::Repetition) -> ResultOrEmpty { |
| <span class="kw">match </span>(rep.min, rep.max) { |
| (<span class="number">0</span>, <span class="prelude-val">Some</span>(<span class="number">1</span>)) => <span class="self">self</span>.c_repeat_zero_or_one(<span class="kw-2">&</span>rep.sub, rep.greedy), |
| (<span class="number">0</span>, <span class="prelude-val">None</span>) => <span class="self">self</span>.c_repeat_zero_or_more(<span class="kw-2">&</span>rep.sub, rep.greedy), |
| (<span class="number">1</span>, <span class="prelude-val">None</span>) => <span class="self">self</span>.c_repeat_one_or_more(<span class="kw-2">&</span>rep.sub, rep.greedy), |
| (min, <span class="prelude-val">None</span>) => { |
| <span class="self">self</span>.c_repeat_range_min_or_more(<span class="kw-2">&</span>rep.sub, rep.greedy, min) |
| } |
| (min, <span class="prelude-val">Some</span>(max)) => { |
| <span class="self">self</span>.c_repeat_range(<span class="kw-2">&</span>rep.sub, rep.greedy, min, max) |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>c_repeat_zero_or_one( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| expr: <span class="kw-2">&</span>Hir, |
| greedy: bool, |
| ) -> ResultOrEmpty { |
| <span class="kw">let </span>split_entry = <span class="self">self</span>.insts.len(); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">let </span>Patch { hole: hole_rep, entry: entry_rep } = <span class="kw">match </span><span class="self">self</span>.c(expr)<span class="question-mark">? </span>{ |
| <span class="prelude-val">Some</span>(p) => p, |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.pop_split_hole(), |
| }; |
| <span class="kw">let </span>split_hole = <span class="kw">if </span>greedy { |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry_rep), <span class="prelude-val">None</span>) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(entry_rep)) |
| }; |
| <span class="kw">let </span>holes = <span class="macro">vec!</span>[hole_rep, split_hole]; |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: Hole::Many(holes), entry: split_entry })) |
| } |
| |
| <span class="kw">fn </span>c_repeat_zero_or_more( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| expr: <span class="kw-2">&</span>Hir, |
| greedy: bool, |
| ) -> ResultOrEmpty { |
| <span class="kw">let </span>split_entry = <span class="self">self</span>.insts.len(); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">let </span>Patch { hole: hole_rep, entry: entry_rep } = <span class="kw">match </span><span class="self">self</span>.c(expr)<span class="question-mark">? </span>{ |
| <span class="prelude-val">Some</span>(p) => p, |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.pop_split_hole(), |
| }; |
| |
| <span class="self">self</span>.fill(hole_rep, split_entry); |
| <span class="kw">let </span>split_hole = <span class="kw">if </span>greedy { |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry_rep), <span class="prelude-val">None</span>) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(entry_rep)) |
| }; |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: split_hole, entry: split_entry })) |
| } |
| |
| <span class="kw">fn </span>c_repeat_one_or_more( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| expr: <span class="kw-2">&</span>Hir, |
| greedy: bool, |
| ) -> ResultOrEmpty { |
| <span class="kw">let </span>Patch { hole: hole_rep, entry: entry_rep } = <span class="kw">match </span><span class="self">self</span>.c(expr)<span class="question-mark">? </span>{ |
| <span class="prelude-val">Some</span>(p) => p, |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">Ok</span>(<span class="prelude-val">None</span>), |
| }; |
| <span class="self">self</span>.fill_to_next(hole_rep); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| |
| <span class="kw">let </span>split_hole = <span class="kw">if </span>greedy { |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry_rep), <span class="prelude-val">None</span>) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.fill_split(split, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(entry_rep)) |
| }; |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: split_hole, entry: entry_rep })) |
| } |
| |
| <span class="kw">fn </span>c_repeat_range_min_or_more( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| expr: <span class="kw-2">&</span>Hir, |
| greedy: bool, |
| min: u32, |
| ) -> ResultOrEmpty { |
| <span class="kw">let </span>min = u32_to_usize(min); |
| <span class="comment">// Using next_inst() is ok, because we can't return it (concat would |
| // have to return Some(_) while c_repeat_range_min_or_more returns |
| // None). |
| </span><span class="kw">let </span>patch_concat = <span class="self">self |
| </span>.c_concat(iter::repeat(expr).take(min))<span class="question-mark">? |
| </span>.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(patch_rep) = <span class="self">self</span>.c_repeat_zero_or_more(expr, greedy)<span class="question-mark">? </span>{ |
| <span class="self">self</span>.fill(patch_concat.hole, patch_rep.entry); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: patch_rep.hole, entry: patch_concat.entry })) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">None</span>) |
| } |
| } |
| |
| <span class="kw">fn </span>c_repeat_range( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| expr: <span class="kw-2">&</span>Hir, |
| greedy: bool, |
| min: u32, |
| max: u32, |
| ) -> ResultOrEmpty { |
| <span class="kw">let </span>(min, max) = (u32_to_usize(min), u32_to_usize(max)); |
| <span class="macro">debug_assert!</span>(min <= max); |
| <span class="kw">let </span>patch_concat = <span class="self">self</span>.c_concat(iter::repeat(expr).take(min))<span class="question-mark">?</span>; |
| <span class="kw">if </span>min == max { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(patch_concat); |
| } |
| <span class="comment">// Same reasoning as in c_repeat_range_min_or_more (we know that min < |
| // max at this point). |
| </span><span class="kw">let </span>patch_concat = patch_concat.unwrap_or_else(|| <span class="self">self</span>.next_inst()); |
| <span class="kw">let </span>initial_entry = patch_concat.entry; |
| <span class="comment">// It is much simpler to compile, e.g., `a{2,5}` as: |
| // |
| // aaa?a?a? |
| // |
| // But you end up with a sequence of instructions like this: |
| // |
| // 0: 'a' |
| // 1: 'a', |
| // 2: split(3, 4) |
| // 3: 'a' |
| // 4: split(5, 6) |
| // 5: 'a' |
| // 6: split(7, 8) |
| // 7: 'a' |
| // 8: MATCH |
| // |
| // This is *incredibly* inefficient because the splits end |
| // up forming a chain, which has to be resolved everything a |
| // transition is followed. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>holes = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_hole = patch_concat.hole; |
| <span class="kw">for _ in </span>min..max { |
| <span class="self">self</span>.fill_to_next(prev_hole); |
| <span class="kw">let </span>split = <span class="self">self</span>.push_split_hole(); |
| <span class="kw">let </span>Patch { hole, entry } = <span class="kw">match </span><span class="self">self</span>.c(expr)<span class="question-mark">? </span>{ |
| <span class="prelude-val">Some</span>(p) => p, |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="self">self</span>.pop_split_hole(), |
| }; |
| prev_hole = hole; |
| <span class="kw">if </span>greedy { |
| holes.push(<span class="self">self</span>.fill_split(split, <span class="prelude-val">Some</span>(entry), <span class="prelude-val">None</span>)); |
| } <span class="kw">else </span>{ |
| holes.push(<span class="self">self</span>.fill_split(split, <span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(entry))); |
| } |
| } |
| holes.push(prev_hole); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(Patch { hole: Hole::Many(holes), entry: initial_entry })) |
| } |
| |
| <span class="doccomment">/// Can be used as a default value for the c_* functions when the call to |
| /// c_function is followed by inserting at least one instruction that is |
| /// always executed after the ones written by the c* function. |
| </span><span class="kw">fn </span>next_inst(<span class="kw-2">&</span><span class="self">self</span>) -> Patch { |
| Patch { hole: Hole::None, entry: <span class="self">self</span>.insts.len() } |
| } |
| |
| <span class="kw">fn </span>fill(<span class="kw-2">&mut </span><span class="self">self</span>, hole: Hole, goto: InstPtr) { |
| <span class="kw">match </span>hole { |
| Hole::None => {} |
| Hole::One(pc) => { |
| <span class="self">self</span>.insts[pc].fill(goto); |
| } |
| Hole::Many(holes) => { |
| <span class="kw">for </span>hole <span class="kw">in </span>holes { |
| <span class="self">self</span>.fill(hole, goto); |
| } |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>fill_to_next(<span class="kw-2">&mut </span><span class="self">self</span>, hole: Hole) { |
| <span class="kw">let </span>next = <span class="self">self</span>.insts.len(); |
| <span class="self">self</span>.fill(hole, next); |
| } |
| |
| <span class="kw">fn </span>fill_split( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| hole: Hole, |
| goto1: <span class="prelude-ty">Option</span><InstPtr>, |
| goto2: <span class="prelude-ty">Option</span><InstPtr>, |
| ) -> Hole { |
| <span class="kw">match </span>hole { |
| Hole::None => Hole::None, |
| Hole::One(pc) => <span class="kw">match </span>(goto1, goto2) { |
| (<span class="prelude-val">Some</span>(goto1), <span class="prelude-val">Some</span>(goto2)) => { |
| <span class="self">self</span>.insts[pc].fill_split(goto1, goto2); |
| Hole::None |
| } |
| (<span class="prelude-val">Some</span>(goto1), <span class="prelude-val">None</span>) => { |
| <span class="self">self</span>.insts[pc].half_fill_split_goto1(goto1); |
| Hole::One(pc) |
| } |
| (<span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(goto2)) => { |
| <span class="self">self</span>.insts[pc].half_fill_split_goto2(goto2); |
| Hole::One(pc) |
| } |
| (<span class="prelude-val">None</span>, <span class="prelude-val">None</span>) => <span class="macro">unreachable!</span>( |
| <span class="string">"at least one of the split \ |
| holes must be filled" |
| </span>), |
| }, |
| Hole::Many(holes) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>new_holes = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>hole <span class="kw">in </span>holes { |
| new_holes.push(<span class="self">self</span>.fill_split(hole, goto1, goto2)); |
| } |
| <span class="kw">if </span>new_holes.is_empty() { |
| Hole::None |
| } <span class="kw">else if </span>new_holes.len() == <span class="number">1 </span>{ |
| new_holes.pop().unwrap() |
| } <span class="kw">else </span>{ |
| Hole::Many(new_holes) |
| } |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>push_compiled(<span class="kw-2">&mut </span><span class="self">self</span>, inst: Inst) { |
| <span class="self">self</span>.insts.push(MaybeInst::Compiled(inst)); |
| } |
| |
| <span class="kw">fn </span>push_hole(<span class="kw-2">&mut </span><span class="self">self</span>, inst: InstHole) -> Hole { |
| <span class="kw">let </span>hole = <span class="self">self</span>.insts.len(); |
| <span class="self">self</span>.insts.push(MaybeInst::Uncompiled(inst)); |
| Hole::One(hole) |
| } |
| |
| <span class="kw">fn </span>push_split_hole(<span class="kw-2">&mut </span><span class="self">self</span>) -> Hole { |
| <span class="kw">let </span>hole = <span class="self">self</span>.insts.len(); |
| <span class="self">self</span>.insts.push(MaybeInst::Split); |
| Hole::One(hole) |
| } |
| |
| <span class="kw">fn </span>pop_split_hole(<span class="kw-2">&mut </span><span class="self">self</span>) -> ResultOrEmpty { |
| <span class="self">self</span>.insts.pop(); |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">None</span>) |
| } |
| |
| <span class="kw">fn </span>check_size(<span class="kw-2">&</span><span class="self">self</span>) -> result::Result<(), Error> { |
| <span class="kw">use </span>std::mem::size_of; |
| |
| <span class="kw">let </span>size = |
| <span class="self">self</span>.extra_inst_bytes + (<span class="self">self</span>.insts.len() * size_of::<Inst>()); |
| <span class="kw">if </span>size > <span class="self">self</span>.size_limit { |
| <span class="prelude-val">Err</span>(Error::CompiledTooBig(<span class="self">self</span>.size_limit)) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| } |
| |
| <span class="attribute">#[derive(Debug)] |
| </span><span class="kw">enum </span>Hole { |
| <span class="prelude-val">None</span>, |
| One(InstPtr), |
| Many(Vec<Hole>), |
| } |
| |
| <span class="kw">impl </span>Hole { |
| <span class="kw">fn </span>dup_one(<span class="self">self</span>) -> (<span class="self">Self</span>, <span class="self">Self</span>) { |
| <span class="kw">match </span><span class="self">self </span>{ |
| Hole::One(pc) => (Hole::One(pc), Hole::One(pc)), |
| Hole::None | Hole::Many(<span class="kw">_</span>) => { |
| <span class="macro">unreachable!</span>(<span class="string">"must be called on single hole"</span>) |
| } |
| } |
| } |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">enum </span>MaybeInst { |
| Compiled(Inst), |
| Uncompiled(InstHole), |
| Split, |
| Split1(InstPtr), |
| Split2(InstPtr), |
| } |
| |
| <span class="kw">impl </span>MaybeInst { |
| <span class="kw">fn </span>fill(<span class="kw-2">&mut </span><span class="self">self</span>, goto: InstPtr) { |
| <span class="kw">let </span>maybeinst = <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| MaybeInst::Split => MaybeInst::Split1(goto), |
| MaybeInst::Uncompiled(<span class="kw-2">ref </span>inst) => { |
| MaybeInst::Compiled(inst.fill(goto)) |
| } |
| MaybeInst::Split1(goto1) => { |
| MaybeInst::Compiled(Inst::Split(InstSplit { |
| goto1, |
| goto2: goto, |
| })) |
| } |
| MaybeInst::Split2(goto2) => { |
| MaybeInst::Compiled(Inst::Split(InstSplit { |
| goto1: goto, |
| goto2, |
| })) |
| } |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>( |
| <span class="string">"not all instructions were compiled! \ |
| found uncompiled instruction: {:?}"</span>, |
| <span class="self">self |
| </span>), |
| }; |
| <span class="kw-2">*</span><span class="self">self </span>= maybeinst; |
| } |
| |
| <span class="kw">fn </span>fill_split(<span class="kw-2">&mut </span><span class="self">self</span>, goto1: InstPtr, goto2: InstPtr) { |
| <span class="kw">let </span>filled = <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| MaybeInst::Split => Inst::Split(InstSplit { goto1, goto2 }), |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>( |
| <span class="string">"must be called on Split instruction, \ |
| instead it was called on: {:?}"</span>, |
| <span class="self">self |
| </span>), |
| }; |
| <span class="kw-2">*</span><span class="self">self </span>= MaybeInst::Compiled(filled); |
| } |
| |
| <span class="kw">fn </span>half_fill_split_goto1(<span class="kw-2">&mut </span><span class="self">self</span>, goto1: InstPtr) { |
| <span class="kw">let </span>half_filled = <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| MaybeInst::Split => goto1, |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>( |
| <span class="string">"must be called on Split instruction, \ |
| instead it was called on: {:?}"</span>, |
| <span class="self">self |
| </span>), |
| }; |
| <span class="kw-2">*</span><span class="self">self </span>= MaybeInst::Split1(half_filled); |
| } |
| |
| <span class="kw">fn </span>half_fill_split_goto2(<span class="kw-2">&mut </span><span class="self">self</span>, goto2: InstPtr) { |
| <span class="kw">let </span>half_filled = <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| MaybeInst::Split => goto2, |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>( |
| <span class="string">"must be called on Split instruction, \ |
| instead it was called on: {:?}"</span>, |
| <span class="self">self |
| </span>), |
| }; |
| <span class="kw-2">*</span><span class="self">self </span>= MaybeInst::Split2(half_filled); |
| } |
| |
| <span class="kw">fn </span>unwrap(<span class="self">self</span>) -> Inst { |
| <span class="kw">match </span><span class="self">self </span>{ |
| MaybeInst::Compiled(inst) => inst, |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>( |
| <span class="string">"must be called on a compiled instruction, \ |
| instead it was called on: {:?}"</span>, |
| <span class="self">self |
| </span>), |
| } |
| } |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">enum </span>InstHole { |
| Save { slot: usize }, |
| EmptyLook { look: EmptyLook }, |
| Char { c: char }, |
| Ranges { ranges: Vec<(char, char)> }, |
| Bytes { start: u8, end: u8 }, |
| } |
| |
| <span class="kw">impl </span>InstHole { |
| <span class="kw">fn </span>fill(<span class="kw-2">&</span><span class="self">self</span>, goto: InstPtr) -> Inst { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| InstHole::Save { slot } => Inst::Save(InstSave { goto, slot }), |
| InstHole::EmptyLook { look } => { |
| Inst::EmptyLook(InstEmptyLook { goto, look }) |
| } |
| InstHole::Char { c } => Inst::Char(InstChar { goto, c }), |
| InstHole::Ranges { <span class="kw-2">ref </span>ranges } => Inst::Ranges(InstRanges { |
| goto, |
| ranges: ranges.clone().into_boxed_slice(), |
| }), |
| InstHole::Bytes { start, end } => { |
| Inst::Bytes(InstBytes { goto, start, end }) |
| } |
| } |
| } |
| } |
| |
| <span class="kw">struct </span>CompileClass<<span class="lifetime">'a</span>, <span class="lifetime">'b</span>> { |
| c: <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>Compiler, |
| ranges: <span class="kw-2">&</span><span class="lifetime">'b </span>[hir::ClassUnicodeRange], |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, <span class="lifetime">'b</span>> CompileClass<<span class="lifetime">'a</span>, <span class="lifetime">'b</span>> { |
| <span class="kw">fn </span>compile(<span class="kw-2">mut </span><span class="self">self</span>) -> <span class="prelude-ty">Result </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>holes = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span><span class="kw-2">mut </span>initial_entry = <span class="prelude-val">None</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>last_split = Hole::None; |
| <span class="kw">let </span><span class="kw-2">mut </span>utf8_seqs = <span class="self">self</span>.c.utf8_seqs.take().unwrap(); |
| <span class="self">self</span>.c.suffix_cache.clear(); |
| |
| <span class="kw">for </span>(i, range) <span class="kw">in </span><span class="self">self</span>.ranges.iter().enumerate() { |
| <span class="kw">let </span>is_last_range = i + <span class="number">1 </span>== <span class="self">self</span>.ranges.len(); |
| utf8_seqs.reset(range.start(), range.end()); |
| <span class="kw">let </span><span class="kw-2">mut </span>it = (<span class="kw-2">&mut </span>utf8_seqs).peekable(); |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>utf8_seq = <span class="kw">match </span>it.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">break</span>, |
| <span class="prelude-val">Some</span>(utf8_seq) => utf8_seq, |
| }; |
| <span class="kw">if </span>is_last_range && it.peek().is_none() { |
| <span class="kw">let </span>Patch { hole, entry } = <span class="self">self</span>.c_utf8_seq(<span class="kw-2">&</span>utf8_seq)<span class="question-mark">?</span>; |
| holes.push(hole); |
| <span class="self">self</span>.c.fill(last_split, entry); |
| last_split = Hole::None; |
| <span class="kw">if </span>initial_entry.is_none() { |
| initial_entry = <span class="prelude-val">Some</span>(entry); |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">if </span>initial_entry.is_none() { |
| initial_entry = <span class="prelude-val">Some</span>(<span class="self">self</span>.c.insts.len()); |
| } |
| <span class="self">self</span>.c.fill_to_next(last_split); |
| last_split = <span class="self">self</span>.c.push_split_hole(); |
| <span class="kw">let </span>Patch { hole, entry } = <span class="self">self</span>.c_utf8_seq(<span class="kw-2">&</span>utf8_seq)<span class="question-mark">?</span>; |
| holes.push(hole); |
| last_split = |
| <span class="self">self</span>.c.fill_split(last_split, <span class="prelude-val">Some</span>(entry), <span class="prelude-val">None</span>); |
| } |
| } |
| } |
| <span class="self">self</span>.c.utf8_seqs = <span class="prelude-val">Some</span>(utf8_seqs); |
| <span class="prelude-val">Ok</span>(Patch { hole: Hole::Many(holes), entry: initial_entry.unwrap() }) |
| } |
| |
| <span class="kw">fn </span>c_utf8_seq(<span class="kw-2">&mut </span><span class="self">self</span>, seq: <span class="kw-2">&</span>Utf8Sequence) -> <span class="prelude-ty">Result </span>{ |
| <span class="kw">if </span><span class="self">self</span>.c.compiled.is_reverse { |
| <span class="self">self</span>.c_utf8_seq_(seq) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.c_utf8_seq_(seq.into_iter().rev()) |
| } |
| } |
| |
| <span class="kw">fn </span>c_utf8_seq_<<span class="lifetime">'r</span>, I>(<span class="kw-2">&mut </span><span class="self">self</span>, seq: I) -> <span class="prelude-ty">Result |
| </span><span class="kw">where |
| </span>I: IntoIterator<Item = <span class="kw-2">&</span><span class="lifetime">'r </span>Utf8Range>, |
| { |
| <span class="comment">// The initial instruction for each UTF-8 sequence should be the same. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>from_inst = ::std::usize::MAX; |
| <span class="kw">let </span><span class="kw-2">mut </span>last_hole = Hole::None; |
| <span class="kw">for </span>byte_range <span class="kw">in </span>seq { |
| <span class="kw">let </span>key = SuffixCacheKey { |
| from_inst, |
| start: byte_range.start, |
| end: byte_range.end, |
| }; |
| { |
| <span class="kw">let </span>pc = <span class="self">self</span>.c.insts.len(); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(cached_pc) = <span class="self">self</span>.c.suffix_cache.get(key, pc) { |
| from_inst = cached_pc; |
| <span class="kw">continue</span>; |
| } |
| } |
| <span class="self">self</span>.c.byte_classes.set_range(byte_range.start, byte_range.end); |
| <span class="kw">if </span>from_inst == ::std::usize::MAX { |
| last_hole = <span class="self">self</span>.c.push_hole(InstHole::Bytes { |
| start: byte_range.start, |
| end: byte_range.end, |
| }); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.c.push_compiled(Inst::Bytes(InstBytes { |
| goto: from_inst, |
| start: byte_range.start, |
| end: byte_range.end, |
| })); |
| } |
| from_inst = <span class="self">self</span>.c.insts.len().checked_sub(<span class="number">1</span>).unwrap(); |
| <span class="macro">debug_assert!</span>(from_inst < ::std::usize::MAX); |
| } |
| <span class="macro">debug_assert!</span>(from_inst < ::std::usize::MAX); |
| <span class="prelude-val">Ok</span>(Patch { hole: last_hole, entry: from_inst }) |
| } |
| } |
| |
| <span class="doccomment">/// `SuffixCache` is a simple bounded hash map for caching suffix entries in |
| /// UTF-8 automata. For example, consider the Unicode range \u{0}-\u{FFFF}. |
| /// The set of byte ranges looks like this: |
| /// |
| /// [0-7F] |
| /// [C2-DF][80-BF] |
| /// [E0][A0-BF][80-BF] |
| /// [E1-EC][80-BF][80-BF] |
| /// [ED][80-9F][80-BF] |
| /// [EE-EF][80-BF][80-BF] |
| /// |
| /// Each line above translates to one alternate in the compiled regex program. |
| /// However, all but one of the alternates end in the same suffix, which is |
| /// a waste of an instruction. The suffix cache facilitates reusing them across |
| /// alternates. |
| /// |
| /// Note that a HashMap could be trivially used for this, but we don't need its |
| /// overhead. Some small bounded space (LRU style) is more than enough. |
| /// |
| /// This uses similar idea to [`SparseSet`](../sparse/struct.SparseSet.html), |
| /// except it uses hashes as original indices and then compares full keys for |
| /// validation against `dense` array. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">struct </span>SuffixCache { |
| sparse: Box<[usize]>, |
| dense: Vec<SuffixCacheEntry>, |
| } |
| |
| <span class="attribute">#[derive(Clone, Copy, Debug, Default, Eq, Hash, PartialEq)] |
| </span><span class="kw">struct </span>SuffixCacheEntry { |
| key: SuffixCacheKey, |
| pc: InstPtr, |
| } |
| |
| <span class="attribute">#[derive(Clone, Copy, Debug, Default, Eq, Hash, PartialEq)] |
| </span><span class="kw">struct </span>SuffixCacheKey { |
| from_inst: InstPtr, |
| start: u8, |
| end: u8, |
| } |
| |
| <span class="kw">impl </span>SuffixCache { |
| <span class="kw">fn </span>new(size: usize) -> <span class="self">Self </span>{ |
| SuffixCache { |
| sparse: <span class="macro">vec!</span>[<span class="number">0usize</span>; size].into(), |
| dense: Vec::with_capacity(size), |
| } |
| } |
| |
| <span class="kw">fn </span>get(<span class="kw-2">&mut </span><span class="self">self</span>, key: SuffixCacheKey, pc: InstPtr) -> <span class="prelude-ty">Option</span><InstPtr> { |
| <span class="kw">let </span>hash = <span class="self">self</span>.hash(<span class="kw-2">&</span>key); |
| <span class="kw">let </span>pos = <span class="kw-2">&mut </span><span class="self">self</span>.sparse[hash]; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(entry) = <span class="self">self</span>.dense.get(<span class="kw-2">*</span>pos) { |
| <span class="kw">if </span>entry.key == key { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(entry.pc); |
| } |
| } |
| <span class="kw-2">*</span>pos = <span class="self">self</span>.dense.len(); |
| <span class="self">self</span>.dense.push(SuffixCacheEntry { key, pc }); |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="kw">fn </span>clear(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="self">self</span>.dense.clear(); |
| } |
| |
| <span class="kw">fn </span>hash(<span class="kw-2">&</span><span class="self">self</span>, suffix: <span class="kw-2">&</span>SuffixCacheKey) -> usize { |
| <span class="comment">// Basic FNV-1a hash as described: |
| // https://en.wikipedia.org/wiki/Fowler%E2%80%93Noll%E2%80%93Vo_hash_function |
| </span><span class="kw">const </span>FNV_PRIME: u64 = <span class="number">1_099_511_628_211</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>h = <span class="number">14_695_981_039_346_656_037</span>; |
| h = (h ^ (suffix.from_inst <span class="kw">as </span>u64)).wrapping_mul(FNV_PRIME); |
| h = (h ^ (suffix.start <span class="kw">as </span>u64)).wrapping_mul(FNV_PRIME); |
| h = (h ^ (suffix.end <span class="kw">as </span>u64)).wrapping_mul(FNV_PRIME); |
| (h <span class="kw">as </span>usize) % <span class="self">self</span>.sparse.len() |
| } |
| } |
| |
| <span class="kw">struct </span>ByteClassSet([bool; <span class="number">256</span>]); |
| |
| <span class="kw">impl </span>ByteClassSet { |
| <span class="kw">fn </span>new() -> <span class="self">Self </span>{ |
| ByteClassSet([<span class="bool-val">false</span>; <span class="number">256</span>]) |
| } |
| |
| <span class="kw">fn </span>set_range(<span class="kw-2">&mut </span><span class="self">self</span>, start: u8, end: u8) { |
| <span class="macro">debug_assert!</span>(start <= end); |
| <span class="kw">if </span>start > <span class="number">0 </span>{ |
| <span class="self">self</span>.<span class="number">0</span>[start <span class="kw">as </span>usize - <span class="number">1</span>] = <span class="bool-val">true</span>; |
| } |
| <span class="self">self</span>.<span class="number">0</span>[end <span class="kw">as </span>usize] = <span class="bool-val">true</span>; |
| } |
| |
| <span class="kw">fn </span>set_word_boundary(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="comment">// We need to mark all ranges of bytes whose pairs result in |
| // evaluating \b differently. |
| </span><span class="kw">let </span>iswb = is_word_byte; |
| <span class="kw">let </span><span class="kw-2">mut </span>b1: u16 = <span class="number">0</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>b2: u16; |
| <span class="kw">while </span>b1 <= <span class="number">255 </span>{ |
| b2 = b1 + <span class="number">1</span>; |
| <span class="kw">while </span>b2 <= <span class="number">255 </span>&& iswb(b1 <span class="kw">as </span>u8) == iswb(b2 <span class="kw">as </span>u8) { |
| b2 += <span class="number">1</span>; |
| } |
| <span class="self">self</span>.set_range(b1 <span class="kw">as </span>u8, (b2 - <span class="number">1</span>) <span class="kw">as </span>u8); |
| b1 = b2; |
| } |
| } |
| |
| <span class="kw">fn </span>byte_classes(<span class="kw-2">&</span><span class="self">self</span>) -> Vec<u8> { |
| <span class="comment">// N.B. If you're debugging the DFA, it's useful to simply return |
| // `(0..256).collect()`, which effectively removes the byte classes |
| // and makes the transitions easier to read. |
| // (0usize..256).map(|x| x as u8).collect() |
| </span><span class="kw">let </span><span class="kw-2">mut </span>byte_classes = <span class="macro">vec!</span>[<span class="number">0</span>; <span class="number">256</span>]; |
| <span class="kw">let </span><span class="kw-2">mut </span>class = <span class="number">0u8</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>i = <span class="number">0</span>; |
| <span class="kw">loop </span>{ |
| byte_classes[i] = class <span class="kw">as </span>u8; |
| <span class="kw">if </span>i >= <span class="number">255 </span>{ |
| <span class="kw">break</span>; |
| } |
| <span class="kw">if </span><span class="self">self</span>.<span class="number">0</span>[i] { |
| class = class.checked_add(<span class="number">1</span>).unwrap(); |
| } |
| i += <span class="number">1</span>; |
| } |
| byte_classes |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>ByteClassSet { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter<<span class="lifetime">'_</span>>) -> fmt::Result { |
| f.debug_tuple(<span class="string">"ByteClassSet"</span>).field(&&<span class="self">self</span>.<span class="number">0</span>[..]).finish() |
| } |
| } |
| |
| <span class="kw">fn </span>u32_to_usize(n: u32) -> usize { |
| <span class="comment">// In case usize is less than 32 bits, we need to guard against overflow. |
| // On most platforms this compiles to nothing. |
| // TODO Use `std::convert::TryFrom` once it's stable. |
| </span><span class="kw">if </span>(n <span class="kw">as </span>u64) > (::std::usize::MAX <span class="kw">as </span>u64) { |
| <span class="macro">panic!</span>(<span class="string">"BUG: {} is too big to be pointer sized"</span>, n) |
| } |
| n <span class="kw">as </span>usize |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span><span class="kw">super</span>::ByteClassSet; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>byte_classes() { |
| <span class="kw">let </span><span class="kw-2">mut </span>set = ByteClassSet::new(); |
| set.set_range(<span class="string">b'a'</span>, <span class="string">b'z'</span>); |
| <span class="kw">let </span>classes = set.byte_classes(); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">0</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">1</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">2</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="string">b'a' </span><span class="kw">as </span>usize - <span class="number">1</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="string">b'a' </span><span class="kw">as </span>usize], <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="string">b'm' </span><span class="kw">as </span>usize], <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="string">b'z' </span><span class="kw">as </span>usize], <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="string">b'z' </span><span class="kw">as </span>usize + <span class="number">1</span>], <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">254</span>], <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">255</span>], <span class="number">2</span>); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>set = ByteClassSet::new(); |
| set.set_range(<span class="number">0</span>, <span class="number">2</span>); |
| set.set_range(<span class="number">4</span>, <span class="number">6</span>); |
| <span class="kw">let </span>classes = set.byte_classes(); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">0</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">1</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">2</span>], <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">3</span>], <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">4</span>], <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">5</span>], <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">6</span>], <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">7</span>], <span class="number">3</span>); |
| <span class="macro">assert_eq!</span>(classes[<span class="number">255</span>], <span class="number">3</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>full_byte_classes() { |
| <span class="kw">let </span><span class="kw-2">mut </span>set = ByteClassSet::new(); |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..<span class="number">256u16 </span>{ |
| set.set_range(i <span class="kw">as </span>u8, i <span class="kw">as </span>u8); |
| } |
| <span class="macro">assert_eq!</span>(set.byte_classes().len(), <span class="number">256</span>); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |