| <!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/re_set.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>re_set.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> |
| </pre><pre class="rust"><code><span class="macro">macro_rules! </span>define_set { |
| (<span class="macro-nonterminal">$name</span>:ident, <span class="macro-nonterminal">$builder_mod</span>:ident, <span class="macro-nonterminal">$text_ty</span>:ty, <span class="macro-nonterminal">$as_bytes</span>:expr, |
| $(<span class="attribute">#[<span class="macro-nonterminal">$doc_regexset_example</span>:meta]</span>)* ) => { |
| <span class="kw">pub mod </span><span class="macro-nonterminal">$name </span>{ |
| <span class="kw">use </span>std::fmt; |
| <span class="kw">use </span>std::iter; |
| <span class="kw">use </span>std::slice; |
| <span class="kw">use </span>std::vec; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::error::Error; |
| <span class="kw">use </span><span class="kw">crate</span>::exec::Exec; |
| <span class="kw">use </span><span class="kw">crate</span>::re_builder::<span class="macro-nonterminal">$builder_mod::RegexSetBuilder</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::re_trait::RegularExpression; |
| |
| <span class="doccomment">/// Match multiple (possibly overlapping) regular expressions in a single scan. |
| /// |
| /// A regex set corresponds to the union of two or more regular expressions. |
| /// That is, a regex set will match text where at least one of its |
| /// constituent regular expressions matches. A regex set as its formulated here |
| /// provides a touch more power: it will also report *which* regular |
| /// expressions in the set match. Indeed, this is the key difference between |
| /// regex sets and a single `Regex` with many alternates, since only one |
| /// alternate can match at a time. |
| /// |
| /// For example, consider regular expressions to match email addresses and |
| /// domains: `[a-z]+@[a-z]+\.(com|org|net)` and `[a-z]+\.(com|org|net)`. If a |
| /// regex set is constructed from those regexes, then searching the text |
| /// `foo@example.com` will report both regexes as matching. Of course, one |
| /// could accomplish this by compiling each regex on its own and doing two |
| /// searches over the text. The key advantage of using a regex set is that it |
| /// will report the matching regexes using a *single pass through the text*. |
| /// If one has hundreds or thousands of regexes to match repeatedly (like a URL |
| /// router for a complex web application or a user agent matcher), then a regex |
| /// set can realize huge performance gains. |
| /// |
| /// # Example |
| /// |
| /// This shows how the above two regexes (for matching email addresses and |
| /// domains) might work: |
| /// |
| </span>$(<span class="attribute">#[<span class="macro-nonterminal">$doc_regexset_example</span>]</span>)* |
| <span class="doccomment">/// |
| /// Note that it would be possible to adapt the above example to using `Regex` |
| /// with an expression like: |
| /// |
| /// ```text |
| /// (?P<email>[a-z]+@(?P<email_domain>[a-z]+[.](com|org|net)))|(?P<domain>[a-z]+[.](com|org|net)) |
| /// ``` |
| /// |
| /// After a match, one could then inspect the capture groups to figure out |
| /// which alternates matched. The problem is that it is hard to make this |
| /// approach scale when there are many regexes since the overlap between each |
| /// alternate isn't always obvious to reason about. |
| /// |
| /// # Limitations |
| /// |
| /// Regex sets are limited to answering the following two questions: |
| /// |
| /// 1. Does any regex in the set match? |
| /// 2. If so, which regexes in the set match? |
| /// |
| /// As with the main [`Regex`][crate::Regex] type, it is cheaper to ask (1) |
| /// instead of (2) since the matching engines can stop after the first match |
| /// is found. |
| /// |
| /// You cannot directly extract [`Match`][crate::Match] or |
| /// [`Captures`][crate::Captures] objects from a regex set. If you need these |
| /// operations, the recommended approach is to compile each pattern in the set |
| /// independently and scan the exact same input a second time with those |
| /// independently compiled patterns: |
| /// |
| /// ```rust |
| /// use regex::{Regex, RegexSet}; |
| /// |
| /// let patterns = ["foo", "bar"]; |
| /// // Both patterns will match different ranges of this string. |
| /// let text = "barfoo"; |
| /// |
| /// // Compile a set matching any of our patterns. |
| /// let set = RegexSet::new(&patterns).unwrap(); |
| /// // Compile each pattern independently. |
| /// let regexes: Vec<_> = set.patterns().iter() |
| /// .map(|pat| Regex::new(pat).unwrap()) |
| /// .collect(); |
| /// |
| /// // Match against the whole set first and identify the individual |
| /// // matching patterns. |
| /// let matches: Vec<&str> = set.matches(text).into_iter() |
| /// // Dereference the match index to get the corresponding |
| /// // compiled pattern. |
| /// .map(|match_idx| &regexes[match_idx]) |
| /// // To get match locations or any other info, we then have to search |
| /// // the exact same text again, using our separately-compiled pattern. |
| /// .map(|pat| pat.find(text).unwrap().as_str()) |
| /// .collect(); |
| /// |
| /// // Matches arrive in the order the constituent patterns were declared, |
| /// // not the order they appear in the input. |
| /// assert_eq!(vec!["foo", "bar"], matches); |
| /// ``` |
| /// |
| /// # Performance |
| /// |
| /// A `RegexSet` has the same performance characteristics as `Regex`. Namely, |
| /// search takes `O(mn)` time, where `m` is proportional to the size of the |
| /// regex set and `n` is proportional to the length of the search text. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>RegexSet(Exec); |
| |
| <span class="kw">impl </span>RegexSet { |
| <span class="doccomment">/// Create a new regex set with the given regular expressions. |
| /// |
| /// This takes an iterator of `S`, where `S` is something that can produce |
| /// a `&str`. If any of the strings in the iterator are not valid regular |
| /// expressions, then an error is returned. |
| /// |
| /// # Example |
| /// |
| /// Create a new regex set from an iterator of strings: |
| /// |
| /// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::new(&[r"\w+", r"\d+"]).unwrap(); |
| /// assert!(set.is_match("foo")); |
| /// ``` |
| </span><span class="kw">pub fn </span>new<I, S>(exprs: I) -> <span class="prelude-ty">Result</span><RegexSet, Error> |
| <span class="kw">where </span>S: AsRef<str>, I: IntoIterator<Item=S> { |
| RegexSetBuilder::new(exprs).build() |
| } |
| |
| <span class="doccomment">/// Create a new empty regex set. |
| /// |
| /// # Example |
| /// |
| /// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::empty(); |
| /// assert!(set.is_empty()); |
| /// ``` |
| </span><span class="kw">pub fn </span>empty() -> RegexSet { |
| RegexSetBuilder::new(<span class="kw-2">&</span>[<span class="string">""</span>; <span class="number">0</span>]).build().unwrap() |
| } |
| |
| <span class="doccomment">/// Returns true if and only if one of the regexes in this set matches |
| /// the text given. |
| /// |
| /// This method should be preferred if you only need to test whether any |
| /// of the regexes in the set should match, but don't care about *which* |
| /// regexes matched. This is because the underlying matching engine will |
| /// quit immediately after seeing the first match instead of continuing to |
| /// find all matches. |
| /// |
| /// Note that as with searches using `Regex`, the expression is unanchored |
| /// by default. That is, if the regex does not start with `^` or `\A`, or |
| /// end with `$` or `\z`, then it is permitted to match anywhere in the |
| /// text. |
| /// |
| /// # Example |
| /// |
| /// Tests whether a set matches some text: |
| /// |
| /// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::new(&[r"\w+", r"\d+"]).unwrap(); |
| /// assert!(set.is_match("foo")); |
| /// assert!(!set.is_match("☃")); |
| /// ``` |
| </span><span class="kw">pub fn </span>is_match(<span class="kw-2">&</span><span class="self">self</span>, text: <span class="macro-nonterminal">$text_ty</span>) -> bool { |
| <span class="self">self</span>.is_match_at(text, <span class="number">0</span>) |
| } |
| |
| <span class="doccomment">/// Returns the same as is_match, but starts the search at the given |
| /// offset. |
| /// |
| /// The significance of the starting point is that it takes the surrounding |
| /// context into consideration. For example, the `\A` anchor can only |
| /// match when `start == 0`. |
| </span><span class="attribute">#[doc(hidden)] |
| </span><span class="kw">pub fn </span>is_match_at(<span class="kw-2">&</span><span class="self">self</span>, text: <span class="macro-nonterminal">$text_ty</span>, start: usize) -> bool { |
| <span class="self">self</span>.<span class="number">0</span>.searcher().is_match_at(<span class="macro-nonterminal">$as_bytes</span>(text), start) |
| } |
| |
| <span class="doccomment">/// Returns the set of regular expressions that match in the given text. |
| /// |
| /// The set returned contains the index of each regular expression that |
| /// matches in the given text. The index is in correspondence with the |
| /// order of regular expressions given to `RegexSet`'s constructor. |
| /// |
| /// The set can also be used to iterate over the matched indices. |
| /// |
| /// Note that as with searches using `Regex`, the expression is unanchored |
| /// by default. That is, if the regex does not start with `^` or `\A`, or |
| /// end with `$` or `\z`, then it is permitted to match anywhere in the |
| /// text. |
| /// |
| /// # Example |
| /// |
| /// Tests which regular expressions match the given text: |
| /// |
| /// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::new(&[ |
| /// r"\w+", |
| /// r"\d+", |
| /// r"\pL+", |
| /// r"foo", |
| /// r"bar", |
| /// r"barfoo", |
| /// r"foobar", |
| /// ]).unwrap(); |
| /// let matches: Vec<_> = set.matches("foobar").into_iter().collect(); |
| /// assert_eq!(matches, vec![0, 2, 3, 4, 6]); |
| /// |
| /// // You can also test whether a particular regex matched: |
| /// let matches = set.matches("foobar"); |
| /// assert!(!matches.matched(5)); |
| /// assert!(matches.matched(6)); |
| /// ``` |
| </span><span class="kw">pub fn </span>matches(<span class="kw-2">&</span><span class="self">self</span>, text: <span class="macro-nonterminal">$text_ty</span>) -> SetMatches { |
| <span class="kw">let </span><span class="kw-2">mut </span>matches = <span class="macro">vec!</span>[<span class="bool-val">false</span>; <span class="self">self</span>.<span class="number">0</span>.regex_strings().len()]; |
| <span class="kw">let </span>any = <span class="self">self</span>.read_matches_at(<span class="kw-2">&mut </span>matches, text, <span class="number">0</span>); |
| SetMatches { |
| matched_any: any, |
| matches: matches, |
| } |
| } |
| |
| <span class="doccomment">/// Returns the same as matches, but starts the search at the given |
| /// offset and stores the matches into the slice given. |
| /// |
| /// The significance of the starting point is that it takes the surrounding |
| /// context into consideration. For example, the `\A` anchor can only |
| /// match when `start == 0`. |
| /// |
| /// `matches` must have a length that is at least the number of regexes |
| /// in this set. |
| /// |
| /// This method returns true if and only if at least one member of |
| /// `matches` is true after executing the set against `text`. |
| </span><span class="attribute">#[doc(hidden)] |
| </span><span class="kw">pub fn </span>read_matches_at( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| matches: <span class="kw-2">&mut </span>[bool], |
| text: <span class="macro-nonterminal">$text_ty</span>, |
| start: usize, |
| ) -> bool { |
| <span class="self">self</span>.<span class="number">0</span>.searcher().many_matches_at(matches, <span class="macro-nonterminal">$as_bytes</span>(text), start) |
| } |
| |
| <span class="doccomment">/// Returns the total number of regular expressions in this set. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.<span class="number">0</span>.regex_strings().len() |
| } |
| |
| <span class="doccomment">/// Returns `true` if this set contains no regular expressions. |
| </span><span class="kw">pub fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.<span class="number">0</span>.regex_strings().is_empty() |
| } |
| |
| <span class="doccomment">/// Returns the patterns that this set will match on. |
| /// |
| /// This function can be used to determine the pattern for a match. The |
| /// slice returned has exactly as many patterns givens to this regex set, |
| /// and the order of the slice is the same as the order of the patterns |
| /// provided to the set. |
| /// |
| /// # Example |
| /// |
| /// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::new(&[ |
| /// r"\w+", |
| /// r"\d+", |
| /// r"\pL+", |
| /// r"foo", |
| /// r"bar", |
| /// r"barfoo", |
| /// r"foobar", |
| /// ]).unwrap(); |
| /// let matches: Vec<_> = set |
| /// .matches("foobar") |
| /// .into_iter() |
| /// .map(|match_idx| &set.patterns()[match_idx]) |
| /// .collect(); |
| /// assert_eq!(matches, vec![r"\w+", r"\pL+", r"foo", r"bar", r"foobar"]); |
| /// ``` |
| </span><span class="kw">pub fn </span>patterns(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[String] { |
| <span class="self">self</span>.<span class="number">0</span>.regex_strings() |
| } |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>RegexSet { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| RegexSet::empty() |
| } |
| } |
| |
| <span class="doccomment">/// A set of matches returned by a regex set. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>SetMatches { |
| matched_any: bool, |
| matches: Vec<bool>, |
| } |
| |
| <span class="kw">impl </span>SetMatches { |
| <span class="doccomment">/// Whether this set contains any matches. |
| </span><span class="kw">pub fn </span>matched_any(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.matched_any |
| } |
| |
| <span class="doccomment">/// Whether the regex at the given index matched. |
| /// |
| /// The index for a regex is determined by its insertion order upon the |
| /// initial construction of a `RegexSet`, starting at `0`. |
| /// |
| /// # Panics |
| /// |
| /// If `regex_index` is greater than or equal to `self.len()`. |
| </span><span class="kw">pub fn </span>matched(<span class="kw-2">&</span><span class="self">self</span>, regex_index: usize) -> bool { |
| <span class="self">self</span>.matches[regex_index] |
| } |
| |
| <span class="doccomment">/// The total number of regexes in the set that created these matches. |
| /// |
| /// **WARNING:** This always returns the same value as [`RegexSet::len`]. |
| /// In particular, it does *not* return the number of elements yielded by |
| /// [`SetMatches::iter`]. The only way to determine the total number of |
| /// matched regexes is to iterate over them. |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.matches.len() |
| } |
| |
| <span class="doccomment">/// Returns an iterator over indexes in the regex that matched. |
| /// |
| /// This will always produces matches in ascending order of index, where |
| /// the index corresponds to the index of the regex that matched with |
| /// respect to its position when initially building the set. |
| </span><span class="kw">pub fn </span>iter(<span class="kw-2">&</span><span class="self">self</span>) -> SetMatchesIter<<span class="lifetime">'_</span>> { |
| SetMatchesIter((<span class="kw-2">&*</span><span class="self">self</span>.matches).into_iter().enumerate()) |
| } |
| } |
| |
| <span class="kw">impl </span>IntoIterator <span class="kw">for </span>SetMatches { |
| <span class="kw">type </span>IntoIter = SetMatchesIntoIter; |
| <span class="kw">type </span>Item = usize; |
| |
| <span class="kw">fn </span>into_iter(<span class="self">self</span>) -> <span class="self">Self</span>::IntoIter { |
| SetMatchesIntoIter(<span class="self">self</span>.matches.into_iter().enumerate()) |
| } |
| } |
| |
| <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>SetMatches { |
| <span class="kw">type </span>IntoIter = SetMatchesIter<<span class="lifetime">'a</span>>; |
| <span class="kw">type </span>Item = usize; |
| |
| <span class="kw">fn </span>into_iter(<span class="self">self</span>) -> <span class="self">Self</span>::IntoIter { |
| <span class="self">self</span>.iter() |
| } |
| } |
| |
| <span class="doccomment">/// An owned iterator over the set of matches from a regex set. |
| /// |
| /// This will always produces matches in ascending order of index, where the |
| /// index corresponds to the index of the regex that matched with respect to |
| /// its position when initially building the set. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>SetMatchesIntoIter(iter::Enumerate<vec::IntoIter<bool>>); |
| |
| <span class="kw">impl </span>Iterator <span class="kw">for </span>SetMatchesIntoIter { |
| <span class="kw">type </span>Item = usize; |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span><span class="self">self</span>.<span class="number">0</span>.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((<span class="kw">_</span>, <span class="bool-val">false</span>)) => {} |
| <span class="prelude-val">Some</span>((i, <span class="bool-val">true</span>)) => <span class="kw">return </span><span class="prelude-val">Some</span>(i), |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, <span class="prelude-ty">Option</span><usize>) { |
| <span class="self">self</span>.<span class="number">0</span>.size_hint() |
| } |
| } |
| |
| <span class="kw">impl </span>DoubleEndedIterator <span class="kw">for </span>SetMatchesIntoIter { |
| <span class="kw">fn </span>next_back(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span><span class="self">self</span>.<span class="number">0</span>.next_back() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((<span class="kw">_</span>, <span class="bool-val">false</span>)) => {} |
| <span class="prelude-val">Some</span>((i, <span class="bool-val">true</span>)) => <span class="kw">return </span><span class="prelude-val">Some</span>(i), |
| } |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>iter::FusedIterator <span class="kw">for </span>SetMatchesIntoIter {} |
| |
| <span class="doccomment">/// A borrowed iterator over the set of matches from a regex set. |
| /// |
| /// The lifetime `'a` refers to the lifetime of a `SetMatches` value. |
| /// |
| /// This will always produces matches in ascending order of index, where the |
| /// index corresponds to the index of the regex that matched with respect to |
| /// its position when initially building the set. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>SetMatchesIter<<span class="lifetime">'a</span>>(iter::Enumerate<slice::Iter<<span class="lifetime">'a</span>, bool>>); |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>SetMatchesIter<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = usize; |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span><span class="self">self</span>.<span class="number">0</span>.next() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((<span class="kw">_</span>, <span class="kw-2">&</span><span class="bool-val">false</span>)) => {} |
| <span class="prelude-val">Some</span>((i, <span class="kw-2">&</span><span class="bool-val">true</span>)) => <span class="kw">return </span><span class="prelude-val">Some</span>(i), |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, <span class="prelude-ty">Option</span><usize>) { |
| <span class="self">self</span>.<span class="number">0</span>.size_hint() |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> DoubleEndedIterator <span class="kw">for </span>SetMatchesIter<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>next_back(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span><span class="self">self</span>.<span class="number">0</span>.next_back() { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((<span class="kw">_</span>, <span class="kw-2">&</span><span class="bool-val">false</span>)) => {} |
| <span class="prelude-val">Some</span>((i, <span class="kw-2">&</span><span class="bool-val">true</span>)) => <span class="kw">return </span><span class="prelude-val">Some</span>(i), |
| } |
| } |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> iter::FusedIterator <span class="kw">for </span>SetMatchesIter<<span class="lifetime">'a</span>> {} |
| |
| <span class="attribute">#[doc(hidden)] |
| </span><span class="kw">impl </span>From<Exec> <span class="kw">for </span>RegexSet { |
| <span class="kw">fn </span>from(exec: Exec) -> <span class="self">Self </span>{ |
| RegexSet(exec) |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>RegexSet { |
| <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">"RegexSet({:?})"</span>, <span class="self">self</span>.<span class="number">0</span>.regex_strings()) |
| } |
| } |
| |
| <span class="attribute">#[allow(dead_code)] </span><span class="kw">fn </span>as_bytes_str(text: <span class="kw-2">&</span>str) -> <span class="kw-2">&</span>[u8] { text.as_bytes() } |
| <span class="attribute">#[allow(dead_code)] </span><span class="kw">fn </span>as_bytes_bytes(text: <span class="kw-2">&</span>[u8]) -> <span class="kw-2">&</span>[u8] { text } |
| } |
| } |
| } |
| |
| <span class="macro">define_set! </span>{ |
| unicode, |
| set_unicode, |
| <span class="kw-2">&</span>str, |
| as_bytes_str, |
| <span class="doccomment">/// ```rust |
| /// # use regex::RegexSet; |
| /// let set = RegexSet::new(&[ |
| /// r"[a-z]+@[a-z]+\.(com|org|net)", |
| /// r"[a-z]+\.(com|org|net)", |
| /// ]).unwrap(); |
| /// |
| /// // Ask whether any regexes in the set match. |
| /// assert!(set.is_match("foo@example.com")); |
| /// |
| /// // Identify which regexes in the set match. |
| /// let matches: Vec<_> = set.matches("foo@example.com").into_iter().collect(); |
| /// assert_eq!(vec![0, 1], matches); |
| /// |
| /// // Try again, but with text that only matches one of the regexes. |
| /// let matches: Vec<_> = set.matches("example.com").into_iter().collect(); |
| /// assert_eq!(vec![1], matches); |
| /// |
| /// // Try again, but with text that doesn't match any regex in the set. |
| /// let matches: Vec<_> = set.matches("example").into_iter().collect(); |
| /// assert!(matches.is_empty()); |
| /// ``` |
| </span>} |
| |
| <span class="macro">define_set! </span>{ |
| bytes, |
| set_bytes, |
| <span class="kw-2">&</span>[u8], |
| as_bytes_bytes, |
| <span class="doccomment">/// ```rust |
| /// # use regex::bytes::RegexSet; |
| /// let set = RegexSet::new(&[ |
| /// r"[a-z]+@[a-z]+\.(com|org|net)", |
| /// r"[a-z]+\.(com|org|net)", |
| /// ]).unwrap(); |
| /// |
| /// // Ask whether any regexes in the set match. |
| /// assert!(set.is_match(b"foo@example.com")); |
| /// |
| /// // Identify which regexes in the set match. |
| /// let matches: Vec<_> = set.matches(b"foo@example.com").into_iter().collect(); |
| /// assert_eq!(vec![0, 1], matches); |
| /// |
| /// // Try again, but with text that only matches one of the regexes. |
| /// let matches: Vec<_> = set.matches(b"example.com").into_iter().collect(); |
| /// assert_eq!(vec![1], matches); |
| /// |
| /// // Try again, but with text that doesn't match any regex in the set. |
| /// let matches: Vec<_> = set.matches(b"example").into_iter().collect(); |
| /// assert!(matches.is_empty()); |
| /// ``` |
| </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> |