| <!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-syntax-0.7.2/src/utf8.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>utf8.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_syntax/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_syntax/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> |
| </pre><pre class="rust"><code><span class="doccomment">/*! |
| Converts ranges of Unicode scalar values to equivalent ranges of UTF-8 bytes. |
| |
| This is sub-module is useful for constructing byte based automatons that need |
| to embed UTF-8 decoding. The most common use of this module is in conjunction |
| with the [`hir::ClassUnicodeRange`](crate::hir::ClassUnicodeRange) type. |
| |
| See the documentation on the `Utf8Sequences` iterator for more details and |
| an example. |
| |
| # Wait, what is this? |
| |
| This is simplest to explain with an example. Let's say you wanted to test |
| whether a particular byte sequence was a Cyrillic character. One possible |
| scalar value range is `[0400-04FF]`. The set of allowed bytes for this |
| range can be expressed as a sequence of byte ranges: |
| |
| ```text |
| [D0-D3][80-BF] |
| ``` |
| |
| This is simple enough: simply encode the boundaries, `0400` encodes to |
| `D0 80` and `04FF` encodes to `D3 BF`, and create ranges from each |
| corresponding pair of bytes: `D0` to `D3` and `80` to `BF`. |
| |
| However, what if you wanted to add the Cyrillic Supplementary characters to |
| your range? Your range might then become `[0400-052F]`. The same procedure |
| as above doesn't quite work because `052F` encodes to `D4 AF`. The byte ranges |
| you'd get from the previous transformation would be `[D0-D4][80-AF]`. However, |
| this isn't quite correct because this range doesn't capture many characters, |
| for example, `04FF` (because its last byte, `BF` isn't in the range `80-AF`). |
| |
| Instead, you need multiple sequences of byte ranges: |
| |
| ```text |
| [D0-D3][80-BF] # matches codepoints 0400-04FF |
| [D4][80-AF] # matches codepoints 0500-052F |
| ``` |
| |
| This gets even more complicated if you want bigger ranges, particularly if |
| they naively contain surrogate codepoints. For example, the sequence of byte |
| ranges for the basic multilingual plane (`[0000-FFFF]`) look like this: |
| |
| ```text |
| [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] |
| ``` |
| |
| Note that the byte ranges above will *not* match any erroneous encoding of |
| UTF-8, including encodings of surrogate codepoints. |
| |
| And, of course, for all of Unicode (`[000000-10FFFF]`): |
| |
| ```text |
| [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] |
| [F0][90-BF][80-BF][80-BF] |
| [F1-F3][80-BF][80-BF][80-BF] |
| [F4][80-8F][80-BF][80-BF] |
| ``` |
| |
| This module automates the process of creating these byte ranges from ranges of |
| Unicode scalar values. |
| |
| # Lineage |
| |
| I got the idea and general implementation strategy from Russ Cox in his |
| [article on regexps](https://web.archive.org/web/20160404141123/https://swtch.com/~rsc/regexp/regexp3.html) and RE2. |
| Russ Cox got it from Ken Thompson's `grep` (no source, folk lore?). |
| I also got the idea from |
| [Lucene](https://github.com/apache/lucene-solr/blob/ae93f4e7ac6a3908046391de35d4f50a0d3c59ca/lucene/core/src/java/org/apache/lucene/util/automaton/UTF32ToUTF8.java), |
| which uses it for executing automata on their term index. |
| */ |
| |
| </span><span class="kw">use </span>core::{char, fmt, iter::FusedIterator, slice}; |
| |
| <span class="kw">use </span>alloc::{vec, vec::Vec}; |
| |
| <span class="kw">const </span>MAX_UTF8_BYTES: usize = <span class="number">4</span>; |
| |
| <span class="doccomment">/// Utf8Sequence represents a sequence of byte ranges. |
| /// |
| /// To match a Utf8Sequence, a candidate byte sequence must match each |
| /// successive range. |
| /// |
| /// For example, if there are two ranges, `[C2-DF][80-BF]`, then the byte |
| /// sequence `\xDD\x61` would not match because `0x61 < 0x80`. |
| </span><span class="attribute">#[derive(Copy, Clone, Eq, PartialEq, PartialOrd, Ord)] |
| </span><span class="kw">pub enum </span>Utf8Sequence { |
| <span class="doccomment">/// One byte range. |
| </span>One(Utf8Range), |
| <span class="doccomment">/// Two successive byte ranges. |
| </span>Two([Utf8Range; <span class="number">2</span>]), |
| <span class="doccomment">/// Three successive byte ranges. |
| </span>Three([Utf8Range; <span class="number">3</span>]), |
| <span class="doccomment">/// Four successive byte ranges. |
| </span>Four([Utf8Range; <span class="number">4</span>]), |
| } |
| |
| <span class="kw">impl </span>Utf8Sequence { |
| <span class="doccomment">/// Creates a new UTF-8 sequence from the encoded bytes of a scalar value |
| /// range. |
| /// |
| /// This assumes that `start` and `end` have the same length. |
| </span><span class="kw">fn </span>from_encoded_range(start: <span class="kw-2">&</span>[u8], end: <span class="kw-2">&</span>[u8]) -> <span class="self">Self </span>{ |
| <span class="macro">assert_eq!</span>(start.len(), end.len()); |
| <span class="kw">match </span>start.len() { |
| <span class="number">2 </span>=> Utf8Sequence::Two([ |
| Utf8Range::new(start[<span class="number">0</span>], end[<span class="number">0</span>]), |
| Utf8Range::new(start[<span class="number">1</span>], end[<span class="number">1</span>]), |
| ]), |
| <span class="number">3 </span>=> Utf8Sequence::Three([ |
| Utf8Range::new(start[<span class="number">0</span>], end[<span class="number">0</span>]), |
| Utf8Range::new(start[<span class="number">1</span>], end[<span class="number">1</span>]), |
| Utf8Range::new(start[<span class="number">2</span>], end[<span class="number">2</span>]), |
| ]), |
| <span class="number">4 </span>=> Utf8Sequence::Four([ |
| Utf8Range::new(start[<span class="number">0</span>], end[<span class="number">0</span>]), |
| Utf8Range::new(start[<span class="number">1</span>], end[<span class="number">1</span>]), |
| Utf8Range::new(start[<span class="number">2</span>], end[<span class="number">2</span>]), |
| Utf8Range::new(start[<span class="number">3</span>], end[<span class="number">3</span>]), |
| ]), |
| n => <span class="macro">unreachable!</span>(<span class="string">"invalid encoded length: {}"</span>, n), |
| } |
| } |
| |
| <span class="doccomment">/// Returns the underlying sequence of byte ranges as a slice. |
| </span><span class="kw">pub fn </span>as_slice(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[Utf8Range] { |
| <span class="kw">use </span><span class="self">self</span>::Utf8Sequence::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| One(<span class="kw-2">ref </span>r) => slice::from_ref(r), |
| Two(<span class="kw-2">ref </span>r) => <span class="kw-2">&</span>r[..], |
| Three(<span class="kw-2">ref </span>r) => <span class="kw-2">&</span>r[..], |
| Four(<span class="kw-2">ref </span>r) => <span class="kw-2">&</span>r[..], |
| } |
| } |
| |
| <span class="doccomment">/// Returns the number of byte ranges in this sequence. |
| /// |
| /// The length is guaranteed to be in the closed interval `[1, 4]`. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.as_slice().len() |
| } |
| |
| <span class="doccomment">/// Reverses the ranges in this sequence. |
| /// |
| /// For example, if this corresponds to the following sequence: |
| /// |
| /// ```text |
| /// [D0-D3][80-BF] |
| /// ``` |
| /// |
| /// Then after reversal, it will be |
| /// |
| /// ```text |
| /// [80-BF][D0-D3] |
| /// ``` |
| /// |
| /// This is useful when one is constructing a UTF-8 automaton to match |
| /// character classes in reverse. |
| </span><span class="kw">pub fn </span>reverse(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Utf8Sequence::One(<span class="kw">_</span>) => {} |
| Utf8Sequence::Two(<span class="kw-2">ref mut </span>x) => x.reverse(), |
| Utf8Sequence::Three(<span class="kw-2">ref mut </span>x) => x.reverse(), |
| Utf8Sequence::Four(<span class="kw-2">ref mut </span>x) => x.reverse(), |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if and only if a prefix of `bytes` matches this sequence |
| /// of byte ranges. |
| </span><span class="kw">pub fn </span>matches(<span class="kw-2">&</span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="kw">if </span>bytes.len() < <span class="self">self</span>.len() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="kw">for </span>(<span class="kw-2">&</span>b, r) <span class="kw">in </span>bytes.iter().zip(<span class="self">self</span>) { |
| <span class="kw">if </span>!r.matches(b) { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| } |
| <span class="bool-val">true |
| </span>} |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> IntoIterator <span class="kw">for </span><span class="kw-2">&</span><span class="lifetime">'a </span>Utf8Sequence { |
| <span class="kw">type </span>IntoIter = slice::Iter<<span class="lifetime">'a</span>, Utf8Range>; |
| <span class="kw">type </span>Item = <span class="kw-2">&</span><span class="lifetime">'a </span>Utf8Range; |
| |
| <span class="kw">fn </span>into_iter(<span class="self">self</span>) -> <span class="self">Self</span>::IntoIter { |
| <span class="self">self</span>.as_slice().iter() |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Utf8Sequence { |
| <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 { |
| <span class="kw">use </span><span class="self">self</span>::Utf8Sequence::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| One(<span class="kw-2">ref </span>r) => <span class="macro">write!</span>(f, <span class="string">"{:?}"</span>, r), |
| Two(<span class="kw-2">ref </span>r) => <span class="macro">write!</span>(f, <span class="string">"{:?}{:?}"</span>, r[<span class="number">0</span>], r[<span class="number">1</span>]), |
| Three(<span class="kw-2">ref </span>r) => <span class="macro">write!</span>(f, <span class="string">"{:?}{:?}{:?}"</span>, r[<span class="number">0</span>], r[<span class="number">1</span>], r[<span class="number">2</span>]), |
| Four(<span class="kw-2">ref </span>r) => { |
| <span class="macro">write!</span>(f, <span class="string">"{:?}{:?}{:?}{:?}"</span>, r[<span class="number">0</span>], r[<span class="number">1</span>], r[<span class="number">2</span>], r[<span class="number">3</span>]) |
| } |
| } |
| } |
| } |
| |
| <span class="doccomment">/// A single inclusive range of UTF-8 bytes. |
| </span><span class="attribute">#[derive(Clone, Copy, Eq, PartialEq, PartialOrd, Ord)] |
| </span><span class="kw">pub struct </span>Utf8Range { |
| <span class="doccomment">/// Start of byte range (inclusive). |
| </span><span class="kw">pub </span>start: u8, |
| <span class="doccomment">/// End of byte range (inclusive). |
| </span><span class="kw">pub </span>end: u8, |
| } |
| |
| <span class="kw">impl </span>Utf8Range { |
| <span class="kw">fn </span>new(start: u8, end: u8) -> <span class="self">Self </span>{ |
| Utf8Range { start, end } |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the given byte is in this range. |
| </span><span class="kw">pub fn </span>matches(<span class="kw-2">&</span><span class="self">self</span>, b: u8) -> bool { |
| <span class="self">self</span>.start <= b && b <= <span class="self">self</span>.end |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Utf8Range { |
| <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 { |
| <span class="kw">if </span><span class="self">self</span>.start == <span class="self">self</span>.end { |
| <span class="macro">write!</span>(f, <span class="string">"[{:X}]"</span>, <span class="self">self</span>.start) |
| } <span class="kw">else </span>{ |
| <span class="macro">write!</span>(f, <span class="string">"[{:X}-{:X}]"</span>, <span class="self">self</span>.start, <span class="self">self</span>.end) |
| } |
| } |
| } |
| |
| <span class="doccomment">/// An iterator over ranges of matching UTF-8 byte sequences. |
| /// |
| /// The iteration represents an alternation of comprehensive byte sequences |
| /// that match precisely the set of UTF-8 encoded scalar values. |
| /// |
| /// A byte sequence corresponds to one of the scalar values in the range given |
| /// if and only if it completely matches exactly one of the sequences of byte |
| /// ranges produced by this iterator. |
| /// |
| /// Each sequence of byte ranges matches a unique set of bytes. That is, no two |
| /// sequences will match the same bytes. |
| /// |
| /// # Example |
| /// |
| /// This shows how to match an arbitrary byte sequence against a range of |
| /// scalar values. |
| /// |
| /// ```rust |
| /// use regex_syntax::utf8::{Utf8Sequences, Utf8Sequence}; |
| /// |
| /// fn matches(seqs: &[Utf8Sequence], bytes: &[u8]) -> bool { |
| /// for range in seqs { |
| /// if range.matches(bytes) { |
| /// return true; |
| /// } |
| /// } |
| /// false |
| /// } |
| /// |
| /// // Test the basic multilingual plane. |
| /// let seqs: Vec<_> = Utf8Sequences::new('\u{0}', '\u{FFFF}').collect(); |
| /// |
| /// // UTF-8 encoding of 'a'. |
| /// assert!(matches(&seqs, &[0x61])); |
| /// // UTF-8 encoding of '☃' (`\u{2603}`). |
| /// assert!(matches(&seqs, &[0xE2, 0x98, 0x83])); |
| /// // UTF-8 encoding of `\u{10348}` (outside the BMP). |
| /// assert!(!matches(&seqs, &[0xF0, 0x90, 0x8D, 0x88])); |
| /// // Tries to match against a UTF-8 encoding of a surrogate codepoint, |
| /// // which is invalid UTF-8, and therefore fails, despite the fact that |
| /// // the corresponding codepoint (0xD800) falls in the range given. |
| /// assert!(!matches(&seqs, &[0xED, 0xA0, 0x80])); |
| /// // And fails against plain old invalid UTF-8. |
| /// assert!(!matches(&seqs, &[0xFF, 0xFF])); |
| /// ``` |
| /// |
| /// If this example seems circuitous, that's because it is! It's meant to be |
| /// illustrative. In practice, you could just try to decode your byte sequence |
| /// and compare it with the scalar value range directly. However, this is not |
| /// always possible (for example, in a byte based automaton). |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>Utf8Sequences { |
| range_stack: Vec<ScalarRange>, |
| } |
| |
| <span class="kw">impl </span>Utf8Sequences { |
| <span class="doccomment">/// Create a new iterator over UTF-8 byte ranges for the scalar value range |
| /// given. |
| </span><span class="kw">pub fn </span>new(start: char, end: char) -> <span class="self">Self </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>it = Utf8Sequences { range_stack: <span class="macro">vec!</span>[] }; |
| it.push(u32::from(start), u32::from(end)); |
| it |
| } |
| |
| <span class="doccomment">/// reset resets the scalar value range. |
| /// Any existing state is cleared, but resources may be reused. |
| /// |
| /// N.B. Benchmarks say that this method is dubious. |
| </span><span class="attribute">#[doc(hidden)] |
| </span><span class="kw">pub fn </span>reset(<span class="kw-2">&mut </span><span class="self">self</span>, start: char, end: char) { |
| <span class="self">self</span>.range_stack.clear(); |
| <span class="self">self</span>.push(u32::from(start), u32::from(end)); |
| } |
| |
| <span class="kw">fn </span>push(<span class="kw-2">&mut </span><span class="self">self</span>, start: u32, end: u32) { |
| <span class="self">self</span>.range_stack.push(ScalarRange { start, end }); |
| } |
| } |
| |
| <span class="kw">struct </span>ScalarRange { |
| start: u32, |
| end: u32, |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>ScalarRange { |
| <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 { |
| <span class="macro">write!</span>(f, <span class="string">"ScalarRange({:X}, {:X})"</span>, <span class="self">self</span>.start, <span class="self">self</span>.end) |
| } |
| } |
| |
| <span class="kw">impl </span>Iterator <span class="kw">for </span>Utf8Sequences { |
| <span class="kw">type </span>Item = Utf8Sequence; |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>::Item> { |
| <span class="lifetime">'TOP</span>: <span class="kw">while let </span><span class="prelude-val">Some</span>(<span class="kw-2">mut </span>r) = <span class="self">self</span>.range_stack.pop() { |
| <span class="lifetime">'INNER</span>: <span class="kw">loop </span>{ |
| <span class="kw">if let </span><span class="prelude-val">Some</span>((r1, r2)) = r.split() { |
| <span class="self">self</span>.push(r2.start, r2.end); |
| r.start = r1.start; |
| r.end = r1.end; |
| <span class="kw">continue </span><span class="lifetime">'INNER</span>; |
| } |
| <span class="kw">if </span>!r.is_valid() { |
| <span class="kw">continue </span><span class="lifetime">'TOP</span>; |
| } |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">1</span>..MAX_UTF8_BYTES { |
| <span class="kw">let </span>max = max_scalar_value(i); |
| <span class="kw">if </span>r.start <= max && max < r.end { |
| <span class="self">self</span>.push(max + <span class="number">1</span>, r.end); |
| r.end = max; |
| <span class="kw">continue </span><span class="lifetime">'INNER</span>; |
| } |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(ascii_range) = r.as_ascii() { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(Utf8Sequence::One(ascii_range)); |
| } |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">1</span>..MAX_UTF8_BYTES { |
| <span class="kw">let </span>m = (<span class="number">1 </span><< (<span class="number">6 </span>* i)) - <span class="number">1</span>; |
| <span class="kw">if </span>(r.start & !m) != (r.end & !m) { |
| <span class="kw">if </span>(r.start & m) != <span class="number">0 </span>{ |
| <span class="self">self</span>.push((r.start | m) + <span class="number">1</span>, r.end); |
| r.end = r.start | m; |
| <span class="kw">continue </span><span class="lifetime">'INNER</span>; |
| } |
| <span class="kw">if </span>(r.end & m) != m { |
| <span class="self">self</span>.push(r.end & !m, r.end); |
| r.end = (r.end & !m) - <span class="number">1</span>; |
| <span class="kw">continue </span><span class="lifetime">'INNER</span>; |
| } |
| } |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>start = [<span class="number">0</span>; MAX_UTF8_BYTES]; |
| <span class="kw">let </span><span class="kw-2">mut </span>end = [<span class="number">0</span>; MAX_UTF8_BYTES]; |
| <span class="kw">let </span>n = r.encode(<span class="kw-2">&mut </span>start, <span class="kw-2">&mut </span>end); |
| <span class="kw">return </span><span class="prelude-val">Some</span>(Utf8Sequence::from_encoded_range( |
| <span class="kw-2">&</span>start[<span class="number">0</span>..n], |
| <span class="kw-2">&</span>end[<span class="number">0</span>..n], |
| )); |
| } |
| } |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="kw">impl </span>FusedIterator <span class="kw">for </span>Utf8Sequences {} |
| |
| <span class="kw">impl </span>ScalarRange { |
| <span class="doccomment">/// split splits this range if it overlaps with a surrogate codepoint. |
| /// |
| /// Either or both ranges may be invalid. |
| </span><span class="kw">fn </span>split(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><(ScalarRange, ScalarRange)> { |
| <span class="kw">if </span><span class="self">self</span>.start < <span class="number">0xE000 </span>&& <span class="self">self</span>.end > <span class="number">0xD7FF </span>{ |
| <span class="prelude-val">Some</span>(( |
| ScalarRange { start: <span class="self">self</span>.start, end: <span class="number">0xD7FF </span>}, |
| ScalarRange { start: <span class="number">0xE000</span>, end: <span class="self">self</span>.end }, |
| )) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="doccomment">/// is_valid returns true if and only if start <= end. |
| </span><span class="kw">fn </span>is_valid(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.start <= <span class="self">self</span>.end |
| } |
| |
| <span class="doccomment">/// as_ascii returns this range as a Utf8Range if and only if all scalar |
| /// values in this range can be encoded as a single byte. |
| </span><span class="kw">fn </span>as_ascii(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Utf8Range> { |
| <span class="kw">if </span><span class="self">self</span>.is_ascii() { |
| <span class="kw">let </span>start = u8::try_from(<span class="self">self</span>.start).unwrap(); |
| <span class="kw">let </span>end = u8::try_from(<span class="self">self</span>.end).unwrap(); |
| <span class="prelude-val">Some</span>(Utf8Range::new(start, end)) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="doccomment">/// is_ascii returns true if the range is ASCII only (i.e., takes a single |
| /// byte to encode any scalar value). |
| </span><span class="kw">fn </span>is_ascii(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.is_valid() && <span class="self">self</span>.end <= <span class="number">0x7f |
| </span>} |
| |
| <span class="doccomment">/// encode writes the UTF-8 encoding of the start and end of this range |
| /// to the corresponding destination slices, and returns the number of |
| /// bytes written. |
| /// |
| /// The slices should have room for at least `MAX_UTF8_BYTES`. |
| </span><span class="kw">fn </span>encode(<span class="kw-2">&</span><span class="self">self</span>, start: <span class="kw-2">&mut </span>[u8], end: <span class="kw-2">&mut </span>[u8]) -> usize { |
| <span class="kw">let </span>cs = char::from_u32(<span class="self">self</span>.start).unwrap(); |
| <span class="kw">let </span>ce = char::from_u32(<span class="self">self</span>.end).unwrap(); |
| <span class="kw">let </span>ss = cs.encode_utf8(start); |
| <span class="kw">let </span>se = ce.encode_utf8(end); |
| <span class="macro">assert_eq!</span>(ss.len(), se.len()); |
| ss.len() |
| } |
| } |
| |
| <span class="kw">fn </span>max_scalar_value(nbytes: usize) -> u32 { |
| <span class="kw">match </span>nbytes { |
| <span class="number">1 </span>=> <span class="number">0x007F</span>, |
| <span class="number">2 </span>=> <span class="number">0x07FF</span>, |
| <span class="number">3 </span>=> <span class="number">0xFFFF</span>, |
| <span class="number">4 </span>=> <span class="number">0x0010_FFFF</span>, |
| <span class="kw">_ </span>=> <span class="macro">unreachable!</span>(<span class="string">"invalid UTF-8 byte sequence size"</span>), |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span>core::char; |
| |
| <span class="kw">use </span>alloc::{vec, vec::Vec}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::utf8::{Utf8Range, Utf8Sequences}; |
| |
| <span class="kw">fn </span>rutf8(s: u8, e: u8) -> Utf8Range { |
| Utf8Range::new(s, e) |
| } |
| |
| <span class="kw">fn </span>never_accepts_surrogate_codepoints(start: char, end: char) { |
| <span class="kw">for </span>cp <span class="kw">in </span><span class="number">0xD800</span>..<span class="number">0xE000 </span>{ |
| <span class="kw">let </span>buf = encode_surrogate(cp); |
| <span class="kw">for </span>r <span class="kw">in </span>Utf8Sequences::new(start, end) { |
| <span class="kw">if </span>r.matches(<span class="kw-2">&</span>buf) { |
| <span class="macro">panic!</span>( |
| <span class="string">"Sequence ({:X}, {:X}) contains range {:?}, \ |
| which matches surrogate code point {:X} \ |
| with encoded bytes {:?}"</span>, |
| u32::from(start), |
| u32::from(end), |
| r, |
| cp, |
| buf, |
| ); |
| } |
| } |
| } |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>codepoints_no_surrogates() { |
| never_accepts_surrogate_codepoints(<span class="string">'\u{0}'</span>, <span class="string">'\u{FFFF}'</span>); |
| never_accepts_surrogate_codepoints(<span class="string">'\u{0}'</span>, <span class="string">'\u{10FFFF}'</span>); |
| never_accepts_surrogate_codepoints(<span class="string">'\u{0}'</span>, <span class="string">'\u{10FFFE}'</span>); |
| never_accepts_surrogate_codepoints(<span class="string">'\u{80}'</span>, <span class="string">'\u{10FFFF}'</span>); |
| never_accepts_surrogate_codepoints(<span class="string">'\u{D7FF}'</span>, <span class="string">'\u{E000}'</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>single_codepoint_one_sequence() { |
| <span class="comment">// Tests that every range of scalar values that contains a single |
| // scalar value is recognized by one sequence of byte ranges. |
| </span><span class="kw">for </span>i <span class="kw">in </span><span class="number">0x0</span>..=<span class="number">0x0010_FFFF </span>{ |
| <span class="kw">let </span>c = <span class="kw">match </span>char::from_u32(i) { |
| <span class="prelude-val">None </span>=> <span class="kw">continue</span>, |
| <span class="prelude-val">Some</span>(c) => c, |
| }; |
| <span class="kw">let </span>seqs: Vec<<span class="kw">_</span>> = Utf8Sequences::new(c, c).collect(); |
| <span class="macro">assert_eq!</span>(seqs.len(), <span class="number">1</span>); |
| } |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>bmp() { |
| <span class="kw">use </span><span class="kw">crate</span>::utf8::Utf8Sequence::<span class="kw-2">*</span>; |
| |
| <span class="kw">let </span>seqs = Utf8Sequences::new(<span class="string">'\u{0}'</span>, <span class="string">'\u{FFFF}'</span>).collect::<Vec<<span class="kw">_</span>>>(); |
| <span class="macro">assert_eq!</span>( |
| seqs, |
| <span class="macro">vec!</span>[ |
| One(rutf8(<span class="number">0x0</span>, <span class="number">0x7F</span>)), |
| Two([rutf8(<span class="number">0xC2</span>, <span class="number">0xDF</span>), rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>)]), |
| Three([ |
| rutf8(<span class="number">0xE0</span>, <span class="number">0xE0</span>), |
| rutf8(<span class="number">0xA0</span>, <span class="number">0xBF</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>) |
| ]), |
| Three([ |
| rutf8(<span class="number">0xE1</span>, <span class="number">0xEC</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>) |
| ]), |
| Three([ |
| rutf8(<span class="number">0xED</span>, <span class="number">0xED</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0x9F</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>) |
| ]), |
| Three([ |
| rutf8(<span class="number">0xEE</span>, <span class="number">0xEF</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>), |
| rutf8(<span class="number">0x80</span>, <span class="number">0xBF</span>) |
| ]), |
| ] |
| ); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>reverse() { |
| <span class="kw">use </span><span class="kw">crate</span>::utf8::Utf8Sequence::<span class="kw-2">*</span>; |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>s = One(rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>)); |
| s.reverse(); |
| <span class="macro">assert_eq!</span>(s.as_slice(), <span class="kw-2">&</span>[rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>)]); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>s = Two([rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>), rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>)]); |
| s.reverse(); |
| <span class="macro">assert_eq!</span>(s.as_slice(), <span class="kw-2">&</span>[rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>), rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>)]); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>s = Three([rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>), rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>), rutf8(<span class="number">0xC</span>, <span class="number">0xD</span>)]); |
| s.reverse(); |
| <span class="macro">assert_eq!</span>( |
| s.as_slice(), |
| <span class="kw-2">&</span>[rutf8(<span class="number">0xC</span>, <span class="number">0xD</span>), rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>), rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>)] |
| ); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>s = Four([ |
| rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>), |
| rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>), |
| rutf8(<span class="number">0xC</span>, <span class="number">0xD</span>), |
| rutf8(<span class="number">0xD</span>, <span class="number">0xE</span>), |
| ]); |
| s.reverse(); |
| <span class="macro">assert_eq!</span>( |
| s.as_slice(), |
| <span class="kw-2">&</span>[ |
| rutf8(<span class="number">0xD</span>, <span class="number">0xE</span>), |
| rutf8(<span class="number">0xC</span>, <span class="number">0xD</span>), |
| rutf8(<span class="number">0xB</span>, <span class="number">0xC</span>), |
| rutf8(<span class="number">0xA</span>, <span class="number">0xB</span>) |
| ] |
| ); |
| } |
| |
| <span class="kw">fn </span>encode_surrogate(cp: u32) -> [u8; <span class="number">3</span>] { |
| <span class="kw">const </span>TAG_CONT: u8 = <span class="number">0b1000_0000</span>; |
| <span class="kw">const </span>TAG_THREE_B: u8 = <span class="number">0b1110_0000</span>; |
| |
| <span class="macro">assert!</span>(<span class="number">0xD800 </span><= cp && cp < <span class="number">0xE000</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>dst = [<span class="number">0</span>; <span class="number">3</span>]; |
| dst[<span class="number">0</span>] = u8::try_from(cp >> <span class="number">12 </span>& <span class="number">0x0F</span>).unwrap() | TAG_THREE_B; |
| dst[<span class="number">1</span>] = u8::try_from(cp >> <span class="number">6 </span>& <span class="number">0x3F</span>).unwrap() | TAG_CONT; |
| dst[<span class="number">2</span>] = u8::try_from(cp & <span class="number">0x3F</span>).unwrap() | TAG_CONT; |
| dst |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex_syntax" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |