| <!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/lib.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>lib.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> |
| </pre><pre class="rust"><code><span class="doccomment">/*! |
| This crate provides a robust regular expression parser. |
| |
| This crate defines two primary types: |
| |
| * [`Ast`](ast::Ast) is the abstract syntax of a regular expression. |
| An abstract syntax corresponds to a *structured representation* of the |
| concrete syntax of a regular expression, where the concrete syntax is the |
| pattern string itself (e.g., `foo(bar)+`). Given some abstract syntax, it |
| can be converted back to the original concrete syntax (modulo some details, |
| like whitespace). To a first approximation, the abstract syntax is complex |
| and difficult to analyze. |
| * [`Hir`](hir::Hir) is the high-level intermediate representation |
| ("HIR" or "high-level IR" for short) of regular expression. It corresponds to |
| an intermediate state of a regular expression that sits between the abstract |
| syntax and the low level compiled opcodes that are eventually responsible for |
| executing a regular expression search. Given some high-level IR, it is not |
| possible to produce the original concrete syntax (although it is possible to |
| produce an equivalent concrete syntax, but it will likely scarcely resemble |
| the original pattern). To a first approximation, the high-level IR is simple |
| and easy to analyze. |
| |
| These two types come with conversion routines: |
| |
| * An [`ast::parse::Parser`] converts concrete syntax (a `&str`) to an |
| [`Ast`](ast::Ast). |
| * A [`hir::translate::Translator`] converts an [`Ast`](ast::Ast) to a |
| [`Hir`](hir::Hir). |
| |
| As a convenience, the above two conversion routines are combined into one via |
| the top-level [`Parser`] type. This `Parser` will first convert your pattern to |
| an `Ast` and then convert the `Ast` to an `Hir`. It's also exposed as top-level |
| [`parse`] free function. |
| |
| |
| # Example |
| |
| This example shows how to parse a pattern string into its HIR: |
| |
| ``` |
| use regex_syntax::{hir::Hir, parse}; |
| |
| let hir = parse("a|b")?; |
| assert_eq!(hir, Hir::alternation(vec![ |
| Hir::literal("a".as_bytes()), |
| Hir::literal("b".as_bytes()), |
| ])); |
| # Ok::<(), Box<dyn std::error::Error>>(()) |
| ``` |
| |
| |
| # Concrete syntax supported |
| |
| The concrete syntax is documented as part of the public API of the |
| [`regex` crate](https://docs.rs/regex/%2A/regex/#syntax). |
| |
| |
| # Input safety |
| |
| A key feature of this library is that it is safe to use with end user facing |
| input. This plays a significant role in the internal implementation. In |
| particular: |
| |
| 1. Parsers provide a `nest_limit` option that permits callers to control how |
| deeply nested a regular expression is allowed to be. This makes it possible |
| to do case analysis over an `Ast` or an `Hir` using recursion without |
| worrying about stack overflow. |
| 2. Since relying on a particular stack size is brittle, this crate goes to |
| great lengths to ensure that all interactions with both the `Ast` and the |
| `Hir` do not use recursion. Namely, they use constant stack space and heap |
| space proportional to the size of the original pattern string (in bytes). |
| This includes the type's corresponding destructors. (One exception to this |
| is literal extraction, but this will eventually get fixed.) |
| |
| |
| # Error reporting |
| |
| The `Display` implementations on all `Error` types exposed in this library |
| provide nice human readable errors that are suitable for showing to end users |
| in a monospace font. |
| |
| |
| # Literal extraction |
| |
| This crate provides limited support for [literal extraction from `Hir` |
| values](hir::literal). Be warned that literal extraction uses recursion, and |
| therefore, stack size proportional to the size of the `Hir`. |
| |
| The purpose of literal extraction is to speed up searches. That is, if you |
| know a regular expression must match a prefix or suffix literal, then it is |
| often quicker to search for instances of that literal, and then confirm or deny |
| the match using the full regular expression engine. These optimizations are |
| done automatically in the `regex` crate. |
| |
| |
| # Crate features |
| |
| An important feature provided by this crate is its Unicode support. This |
| includes things like case folding, boolean properties, general categories, |
| scripts and Unicode-aware support for the Perl classes `\w`, `\s` and `\d`. |
| However, a downside of this support is that it requires bundling several |
| Unicode data tables that are substantial in size. |
| |
| A fair number of use cases do not require full Unicode support. For this |
| reason, this crate exposes a number of features to control which Unicode |
| data is available. |
| |
| If a regular expression attempts to use a Unicode feature that is not available |
| because the corresponding crate feature was disabled, then translating that |
| regular expression to an `Hir` will return an error. (It is still possible |
| construct an `Ast` for such a regular expression, since Unicode data is not |
| used until translation to an `Hir`.) Stated differently, enabling or disabling |
| any of the features below can only add or subtract from the total set of valid |
| regular expressions. Enabling or disabling a feature will never modify the |
| match semantics of a regular expression. |
| |
| The following features are available: |
| |
| * **std** - |
| Enables support for the standard library. This feature is enabled by default. |
| When disabled, only `core` and `alloc` are used. Otherwise, enabling `std` |
| generally just enables `std::error::Error` trait impls for the various error |
| types. |
| * **unicode** - |
| Enables all Unicode features. This feature is enabled by default, and will |
| always cover all Unicode features, even if more are added in the future. |
| * **unicode-age** - |
| Provide the data for the |
| [Unicode `Age` property](https://www.unicode.org/reports/tr44/tr44-24.html#Character_Age). |
| This makes it possible to use classes like `\p{Age:6.0}` to refer to all |
| codepoints first introduced in Unicode 6.0 |
| * **unicode-bool** - |
| Provide the data for numerous Unicode boolean properties. The full list |
| is not included here, but contains properties like `Alphabetic`, `Emoji`, |
| `Lowercase`, `Math`, `Uppercase` and `White_Space`. |
| * **unicode-case** - |
| Provide the data for case insensitive matching using |
| [Unicode's "simple loose matches" specification](https://www.unicode.org/reports/tr18/#Simple_Loose_Matches). |
| * **unicode-gencat** - |
| Provide the data for |
| [Unicode general categories](https://www.unicode.org/reports/tr44/tr44-24.html#General_Category_Values). |
| This includes, but is not limited to, `Decimal_Number`, `Letter`, |
| `Math_Symbol`, `Number` and `Punctuation`. |
| * **unicode-perl** - |
| Provide the data for supporting the Unicode-aware Perl character classes, |
| corresponding to `\w`, `\s` and `\d`. This is also necessary for using |
| Unicode-aware word boundary assertions. Note that if this feature is |
| disabled, the `\s` and `\d` character classes are still available if the |
| `unicode-bool` and `unicode-gencat` features are enabled, respectively. |
| * **unicode-script** - |
| Provide the data for |
| [Unicode scripts and script extensions](https://www.unicode.org/reports/tr24/). |
| This includes, but is not limited to, `Arabic`, `Cyrillic`, `Hebrew`, |
| `Latin` and `Thai`. |
| * **unicode-segment** - |
| Provide the data necessary to provide the properties used to implement the |
| [Unicode text segmentation algorithms](https://www.unicode.org/reports/tr29/). |
| This enables using classes like `\p{gcb=Extend}`, `\p{wb=Katakana}` and |
| `\p{sb=ATerm}`. |
| */ |
| |
| </span><span class="attribute">#![no_std] |
| #![forbid(unsafe_code)] |
| #![deny(missing_docs, rustdoc::broken_intra_doc_links)] |
| #![warn(missing_debug_implementations)] |
| #![cfg_attr(docsrs, feature(doc_auto_cfg))] |
| |
| #[cfg(any(test, feature = <span class="string">"std"</span>))] |
| </span><span class="kw">extern crate </span>std; |
| |
| <span class="kw">extern crate </span>alloc; |
| |
| <span class="kw">pub use crate</span>::{ |
| error::Error, |
| parser::{parse, Parser, ParserBuilder}, |
| unicode::UnicodeWordError, |
| }; |
| |
| <span class="kw">use </span>alloc::string::String; |
| |
| <span class="kw">pub mod </span>ast; |
| <span class="kw">mod </span>debug; |
| <span class="kw">mod </span>either; |
| <span class="kw">mod </span>error; |
| <span class="kw">pub mod </span>hir; |
| <span class="kw">mod </span>parser; |
| <span class="kw">mod </span>rank; |
| <span class="kw">mod </span>unicode; |
| <span class="kw">mod </span>unicode_tables; |
| <span class="kw">pub mod </span>utf8; |
| |
| <span class="doccomment">/// Escapes all regular expression meta characters in `text`. |
| /// |
| /// The string returned may be safely used as a literal in a regular |
| /// expression. |
| </span><span class="kw">pub fn </span>escape(text: <span class="kw-2">&</span>str) -> String { |
| <span class="kw">let </span><span class="kw-2">mut </span>quoted = String::new(); |
| escape_into(text, <span class="kw-2">&mut </span>quoted); |
| quoted |
| } |
| |
| <span class="doccomment">/// Escapes all meta characters in `text` and writes the result into `buf`. |
| /// |
| /// This will append escape characters into the given buffer. The characters |
| /// that are appended are safe to use as a literal in a regular expression. |
| </span><span class="kw">pub fn </span>escape_into(text: <span class="kw-2">&</span>str, buf: <span class="kw-2">&mut </span>String) { |
| buf.reserve(text.len()); |
| <span class="kw">for </span>c <span class="kw">in </span>text.chars() { |
| <span class="kw">if </span>is_meta_character(c) { |
| buf.push(<span class="string">'\\'</span>); |
| } |
| buf.push(c); |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if the given character has significance in a regex. |
| /// |
| /// Generally speaking, these are the only characters which _must_ be escaped |
| /// in order to match their literal meaning. For example, to match a literal |
| /// `|`, one could write `\|`. Sometimes escaping isn't always necessary. For |
| /// example, `-` is treated as a meta character because of its significance |
| /// for writing ranges inside of character classes, but the regex `-` will |
| /// match a literal `-` because `-` has no special meaning outside of character |
| /// classes. |
| /// |
| /// In order to determine whether a character may be escaped at all, the |
| /// [`is_escapeable_character`] routine should be used. The difference between |
| /// `is_meta_character` and `is_escapeable_character` is that the latter will |
| /// return true for some characters that are _not_ meta characters. For |
| /// example, `%` and `\%` both match a literal `%` in all contexts. In other |
| /// words, `is_escapeable_character` includes "superfluous" escapes. |
| /// |
| /// Note that the set of characters for which this function returns `true` or |
| /// `false` is fixed and won't change in a semver compatible release. (In this |
| /// case, "semver compatible release" actually refers to the `regex` crate |
| /// itself, since reducing or expanding the set of meta characters would be a |
| /// breaking change for not just `regex-syntax` but also `regex` itself.) |
| /// |
| /// # Example |
| /// |
| /// ``` |
| /// use regex_syntax::is_meta_character; |
| /// |
| /// assert!(is_meta_character('?')); |
| /// assert!(is_meta_character('-')); |
| /// assert!(is_meta_character('&')); |
| /// assert!(is_meta_character('#')); |
| /// |
| /// assert!(!is_meta_character('%')); |
| /// assert!(!is_meta_character('/')); |
| /// assert!(!is_meta_character('!')); |
| /// assert!(!is_meta_character('"')); |
| /// assert!(!is_meta_character('e')); |
| /// ``` |
| </span><span class="kw">pub fn </span>is_meta_character(c: char) -> bool { |
| <span class="kw">match </span>c { |
| <span class="string">'\\' </span>| <span class="string">'.' </span>| <span class="string">'+' </span>| <span class="string">'*' </span>| <span class="string">'?' </span>| <span class="string">'(' </span>| <span class="string">')' </span>| <span class="string">'|' </span>| <span class="string">'[' </span>| <span class="string">']' </span>| <span class="string">'{' |
| </span>| <span class="string">'}' </span>| <span class="string">'^' </span>| <span class="string">'$' </span>| <span class="string">'#' </span>| <span class="string">'&' </span>| <span class="string">'-' </span>| <span class="string">'~' </span>=> <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if the given character can be escaped in a regex. |
| /// |
| /// This returns true in all cases that `is_meta_character` returns true, but |
| /// also returns true in some cases where `is_meta_character` returns false. |
| /// For example, `%` is not a meta character, but it is escapeable. That is, |
| /// `%` and `\%` both match a literal `%` in all contexts. |
| /// |
| /// The purpose of this routine is to provide knowledge about what characters |
| /// may be escaped. Namely, most regex engines permit "superfluous" escapes |
| /// where characters without any special significance may be escaped even |
| /// though there is no actual _need_ to do so. |
| /// |
| /// This will return false for some characters. For example, `e` is not |
| /// escapeable. Therefore, `\e` will either result in a parse error (which is |
| /// true today), or it could backwards compatibly evolve into a new construct |
| /// with its own meaning. Indeed, that is the purpose of banning _some_ |
| /// superfluous escapes: it provides a way to evolve the syntax in a compatible |
| /// manner. |
| /// |
| /// # Example |
| /// |
| /// ``` |
| /// use regex_syntax::is_escapeable_character; |
| /// |
| /// assert!(is_escapeable_character('?')); |
| /// assert!(is_escapeable_character('-')); |
| /// assert!(is_escapeable_character('&')); |
| /// assert!(is_escapeable_character('#')); |
| /// assert!(is_escapeable_character('%')); |
| /// assert!(is_escapeable_character('/')); |
| /// assert!(is_escapeable_character('!')); |
| /// assert!(is_escapeable_character('"')); |
| /// |
| /// assert!(!is_escapeable_character('e')); |
| /// ``` |
| </span><span class="kw">pub fn </span>is_escapeable_character(c: char) -> bool { |
| <span class="comment">// Certainly escapeable if it's a meta character. |
| </span><span class="kw">if </span>is_meta_character(c) { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="comment">// Any character that isn't ASCII is definitely not escapeable. There's |
| // no real need to allow things like \☃ right? |
| </span><span class="kw">if </span>!c.is_ascii() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="comment">// Otherwise, we basically say that everything is escapeable unless it's a |
| // letter or digit. Things like \3 are either octal (when enabled) or an |
| // error, and we should keep it that way. Otherwise, letters are reserved |
| // for adding new syntax in a backwards compatible way. |
| </span><span class="kw">match </span>c { |
| <span class="string">'0'</span>..=<span class="string">'9' </span>| <span class="string">'A'</span>..=<span class="string">'Z' </span>| <span class="string">'a'</span>..=<span class="string">'z' </span>=> <span class="bool-val">false</span>, |
| <span class="comment">// While not currently supported, we keep these as not escapeable to |
| // give us some flexibility with respect to supporting the \< and |
| // \> word boundary assertions in the future. By rejecting them as |
| // escapeable, \< and \> will result in a parse error. Thus, we can |
| // turn them into something else in the future without it being a |
| // backwards incompatible change. |
| </span><span class="string">'<' </span>| <span class="string">'>' </span>=> <span class="bool-val">false</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">true</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the given character is a Unicode word |
| /// character. |
| /// |
| /// A Unicode word character is defined by |
| /// [UTS#18 Annex C](https://unicode.org/reports/tr18/#Compatibility_Properties). |
| /// In particular, a character |
| /// is considered a word character if it is in either of the `Alphabetic` or |
| /// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark` |
| /// or `Connector_Punctuation` general categories. |
| /// |
| /// # Panics |
| /// |
| /// If the `unicode-perl` feature is not enabled, then this function |
| /// panics. For this reason, it is recommended that callers use |
| /// [`try_is_word_character`] instead. |
| </span><span class="kw">pub fn </span>is_word_character(c: char) -> bool { |
| try_is_word_character(c).expect(<span class="string">"unicode-perl feature must be enabled"</span>) |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the given character is a Unicode word |
| /// character. |
| /// |
| /// A Unicode word character is defined by |
| /// [UTS#18 Annex C](https://unicode.org/reports/tr18/#Compatibility_Properties). |
| /// In particular, a character |
| /// is considered a word character if it is in either of the `Alphabetic` or |
| /// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark` |
| /// or `Connector_Punctuation` general categories. |
| /// |
| /// # Errors |
| /// |
| /// If the `unicode-perl` feature is not enabled, then this function always |
| /// returns an error. |
| </span><span class="kw">pub fn </span>try_is_word_character( |
| c: char, |
| ) -> core::result::Result<bool, UnicodeWordError> { |
| unicode::is_word_character(c) |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the given character is an ASCII word character. |
| /// |
| /// An ASCII word character is defined by the following character class: |
| /// `[_0-9a-zA-Z]'. |
| </span><span class="kw">pub fn </span>is_word_byte(c: u8) -> bool { |
| <span class="kw">match </span>c { |
| <span class="string">b'_' </span>| <span class="string">b'0'</span>..=<span class="string">b'9' </span>| <span class="string">b'a'</span>..=<span class="string">b'z' </span>| <span class="string">b'A'</span>..=<span class="string">b'Z' </span>=> <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span>alloc::string::ToString; |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>escape_meta() { |
| <span class="macro">assert_eq!</span>( |
| escape(<span class="string">r"\.+*?()|[]{}^$#&-~"</span>), |
| <span class="string">r"\\\.\+\*\?\(\)\|\[\]\{\}\^\$\#\&\-\~"</span>.to_string() |
| ); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>word_byte() { |
| <span class="macro">assert!</span>(is_word_byte(<span class="string">b'a'</span>)); |
| <span class="macro">assert!</span>(!is_word_byte(<span class="string">b'-'</span>)); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg(feature = <span class="string">"unicode-perl"</span>)] |
| </span><span class="kw">fn </span>word_char() { |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'a'</span>), <span class="string">"ASCII"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'à'</span>), <span class="string">"Latin-1"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'β'</span>), <span class="string">"Greek"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{11011}'</span>), <span class="string">"Brahmi (Unicode 6.0)"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{11611}'</span>), <span class="string">"Modi (Unicode 7.0)"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{11711}'</span>), <span class="string">"Ahom (Unicode 8.0)"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{17828}'</span>), <span class="string">"Tangut (Unicode 9.0)"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{1B1B1}'</span>), <span class="string">"Nushu (Unicode 10.0)"</span>); |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'\u{16E40}'</span>), <span class="string">"Medefaidrin (Unicode 11.0)"</span>); |
| <span class="macro">assert!</span>(!is_word_character(<span class="string">'-'</span>)); |
| <span class="macro">assert!</span>(!is_word_character(<span class="string">'☃'</span>)); |
| } |
| |
| <span class="attribute">#[test] |
| #[should_panic] |
| #[cfg(not(feature = <span class="string">"unicode-perl"</span>))] |
| </span><span class="kw">fn </span>word_char_disabled_panic() { |
| <span class="macro">assert!</span>(is_word_character(<span class="string">'a'</span>)); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg(not(feature = <span class="string">"unicode-perl"</span>))] |
| </span><span class="kw">fn </span>word_char_disabled_error() { |
| <span class="macro">assert!</span>(try_is_word_character(<span class="string">'a'</span>).is_err()); |
| } |
| } |
| </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> |
