| <!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/prog.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>prog.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::cmp::Ordering; |
| <span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::fmt; |
| <span class="kw">use </span>std::mem; |
| <span class="kw">use </span>std::ops::Deref; |
| <span class="kw">use </span>std::slice; |
| <span class="kw">use </span>std::sync::Arc; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::input::Char; |
| <span class="kw">use </span><span class="kw">crate</span>::literal::LiteralSearcher; |
| |
| <span class="doccomment">/// `InstPtr` represents the index of an instruction in a regex program. |
| </span><span class="kw">pub type </span>InstPtr = usize; |
| |
| <span class="doccomment">/// Program is a sequence of instructions and various facts about thos |
| /// instructions. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>Program { |
| <span class="doccomment">/// A sequence of instructions that represents an NFA. |
| </span><span class="kw">pub </span>insts: Vec<Inst>, |
| <span class="doccomment">/// Pointers to each Match instruction in the sequence. |
| /// |
| /// This is always length 1 unless this program represents a regex set. |
| </span><span class="kw">pub </span>matches: Vec<InstPtr>, |
| <span class="doccomment">/// The ordered sequence of all capture groups extracted from the AST. |
| /// Unnamed groups are `None`. |
| </span><span class="kw">pub </span>captures: Vec<<span class="prelude-ty">Option</span><String>>, |
| <span class="doccomment">/// Pointers to all named capture groups into `captures`. |
| </span><span class="kw">pub </span>capture_name_idx: Arc<HashMap<String, usize>>, |
| <span class="doccomment">/// If the number of capture groups is the same for all possible matches, |
| /// then this is that number. |
| </span><span class="kw">pub </span>static_captures_len: <span class="prelude-ty">Option</span><usize>, |
| <span class="doccomment">/// A pointer to the start instruction. This can vary depending on how |
| /// the program was compiled. For example, programs for use with the DFA |
| /// engine have a `.*?` inserted at the beginning of unanchored regular |
| /// expressions. The actual starting point of the program is after the |
| /// `.*?`. |
| </span><span class="kw">pub </span>start: InstPtr, |
| <span class="doccomment">/// A set of equivalence classes for discriminating bytes in the compiled |
| /// program. |
| </span><span class="kw">pub </span>byte_classes: Vec<u8>, |
| <span class="doccomment">/// When true, this program can only match valid UTF-8. |
| </span><span class="kw">pub </span>only_utf8: bool, |
| <span class="doccomment">/// When true, this program uses byte range instructions instead of Unicode |
| /// range instructions. |
| </span><span class="kw">pub </span>is_bytes: bool, |
| <span class="doccomment">/// When true, the program is compiled for DFA matching. For example, this |
| /// implies `is_bytes` and also inserts a preceding `.*?` for unanchored |
| /// regexes. |
| </span><span class="kw">pub </span>is_dfa: bool, |
| <span class="doccomment">/// When true, the program matches text in reverse (for use only in the |
| /// DFA). |
| </span><span class="kw">pub </span>is_reverse: bool, |
| <span class="doccomment">/// Whether the regex must match from the start of the input. |
| </span><span class="kw">pub </span>is_anchored_start: bool, |
| <span class="doccomment">/// Whether the regex must match at the end of the input. |
| </span><span class="kw">pub </span>is_anchored_end: bool, |
| <span class="doccomment">/// Whether this program contains a Unicode word boundary instruction. |
| </span><span class="kw">pub </span>has_unicode_word_boundary: bool, |
| <span class="doccomment">/// A possibly empty machine for very quickly matching prefix literals. |
| </span><span class="kw">pub </span>prefixes: LiteralSearcher, |
| <span class="doccomment">/// A limit on the size of the cache that the DFA is allowed to use while |
| /// matching. |
| /// |
| /// The cache limit specifies approximately how much space we're willing to |
| /// give to the state cache. Once the state cache exceeds the size, it is |
| /// wiped and all states must be re-computed. |
| /// |
| /// Note that this value does not impact correctness. It can be set to 0 |
| /// and the DFA will run just fine. (It will only ever store exactly one |
| /// state in the cache, and will likely run very slowly, but it will work.) |
| /// |
| /// Also note that this limit is *per thread of execution*. That is, |
| /// if the same regex is used to search text across multiple threads |
| /// simultaneously, then the DFA cache is not shared. Instead, copies are |
| /// made. |
| </span><span class="kw">pub </span>dfa_size_limit: usize, |
| } |
| |
| <span class="kw">impl </span>Program { |
| <span class="doccomment">/// Creates an empty instruction sequence. Fields are given default |
| /// values. |
| </span><span class="kw">pub fn </span>new() -> <span class="self">Self </span>{ |
| Program { |
| insts: <span class="macro">vec!</span>[], |
| matches: <span class="macro">vec!</span>[], |
| captures: <span class="macro">vec!</span>[], |
| capture_name_idx: Arc::new(HashMap::new()), |
| static_captures_len: <span class="prelude-val">None</span>, |
| start: <span class="number">0</span>, |
| byte_classes: <span class="macro">vec!</span>[<span class="number">0</span>; <span class="number">256</span>], |
| only_utf8: <span class="bool-val">true</span>, |
| is_bytes: <span class="bool-val">false</span>, |
| is_dfa: <span class="bool-val">false</span>, |
| is_reverse: <span class="bool-val">false</span>, |
| is_anchored_start: <span class="bool-val">false</span>, |
| is_anchored_end: <span class="bool-val">false</span>, |
| has_unicode_word_boundary: <span class="bool-val">false</span>, |
| prefixes: LiteralSearcher::empty(), |
| dfa_size_limit: <span class="number">2 </span>* (<span class="number">1 </span><< <span class="number">20</span>), |
| } |
| } |
| |
| <span class="doccomment">/// If pc is an index to a no-op instruction (like Save), then return the |
| /// next pc that is not a no-op instruction. |
| </span><span class="kw">pub fn </span>skip(<span class="kw-2">&</span><span class="self">self</span>, <span class="kw-2">mut </span>pc: usize) -> usize { |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span><span class="self">self</span>[pc] { |
| Inst::Save(<span class="kw-2">ref </span>i) => pc = i.goto, |
| <span class="kw">_ </span>=> <span class="kw">return </span>pc, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Return true if and only if an execution engine at instruction `pc` will |
| /// always lead to a match. |
| </span><span class="kw">pub fn </span>leads_to_match(<span class="kw-2">&</span><span class="self">self</span>, pc: usize) -> bool { |
| <span class="kw">if </span><span class="self">self</span>.matches.len() > <span class="number">1 </span>{ |
| <span class="comment">// If we have a regex set, then we have more than one ending |
| // state, so leading to one of those states is generally |
| // meaningless. |
| </span><span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="kw">match </span><span class="self">self</span>[<span class="self">self</span>.skip(pc)] { |
| Inst::Match(<span class="kw">_</span>) => <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if the current configuration demands that an implicit |
| /// `.*?` be prepended to the instruction sequence. |
| </span><span class="kw">pub fn </span>needs_dotstar(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.is_dfa && !<span class="self">self</span>.is_reverse && !<span class="self">self</span>.is_anchored_start |
| } |
| |
| <span class="doccomment">/// Returns true if this program uses Byte instructions instead of |
| /// Char/Range instructions. |
| </span><span class="kw">pub fn </span>uses_bytes(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.is_bytes || <span class="self">self</span>.is_dfa |
| } |
| |
| <span class="doccomment">/// Returns true if this program exclusively matches valid UTF-8 bytes. |
| /// |
| /// That is, if an invalid UTF-8 byte is seen, then no match is possible. |
| </span><span class="kw">pub fn </span>only_utf8(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.only_utf8 |
| } |
| |
| <span class="doccomment">/// Return the approximate heap usage of this instruction sequence in |
| /// bytes. |
| </span><span class="kw">pub fn </span>approximate_size(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="comment">// The only instruction that uses heap space is Ranges (for |
| // Unicode codepoint programs) to store non-overlapping codepoint |
| // ranges. To keep this operation constant time, we ignore them. |
| </span>(<span class="self">self</span>.len() * mem::size_of::<Inst>()) |
| + (<span class="self">self</span>.matches.len() * mem::size_of::<InstPtr>()) |
| + (<span class="self">self</span>.captures.len() * mem::size_of::<<span class="prelude-ty">Option</span><String>>()) |
| + (<span class="self">self</span>.capture_name_idx.len() |
| * (mem::size_of::<String>() + mem::size_of::<usize>())) |
| + (<span class="self">self</span>.byte_classes.len() * mem::size_of::<u8>()) |
| + <span class="self">self</span>.prefixes.approximate_size() |
| } |
| } |
| |
| <span class="kw">impl </span>Deref <span class="kw">for </span>Program { |
| <span class="kw">type </span>Target = [Inst]; |
| |
| <span class="attribute">#[cfg_attr(feature = <span class="string">"perf-inline"</span>, inline(always))] |
| </span><span class="kw">fn </span>deref(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span><span class="self">Self</span>::Target { |
| <span class="kw-2">&*</span><span class="self">self</span>.insts |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Program { |
| <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>::Inst::<span class="kw-2">*</span>; |
| |
| <span class="kw">fn </span>with_goto(cur: usize, goto: usize, fmtd: String) -> String { |
| <span class="kw">if </span>goto == cur + <span class="number">1 </span>{ |
| fmtd |
| } <span class="kw">else </span>{ |
| <span class="macro">format!</span>(<span class="string">"{} (goto: {})"</span>, fmtd, goto) |
| } |
| } |
| |
| <span class="kw">fn </span>visible_byte(b: u8) -> String { |
| <span class="kw">use </span>std::ascii::escape_default; |
| <span class="kw">let </span>escaped = escape_default(b).collect::<Vec<u8>>(); |
| String::from_utf8_lossy(<span class="kw-2">&</span>escaped).into_owned() |
| } |
| |
| <span class="kw">for </span>(pc, inst) <span class="kw">in </span><span class="self">self</span>.iter().enumerate() { |
| <span class="kw">match </span><span class="kw-2">*</span>inst { |
| Match(slot) => <span class="macro">write!</span>(f, <span class="string">"{:04} Match({:?})"</span>, pc, slot)<span class="question-mark">?</span>, |
| Save(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">let </span>s = <span class="macro">format!</span>(<span class="string">"{:04} Save({})"</span>, pc, inst.slot); |
| <span class="macro">write!</span>(f, <span class="string">"{}"</span>, with_goto(pc, inst.goto, s))<span class="question-mark">?</span>; |
| } |
| Split(<span class="kw-2">ref </span>inst) => { |
| <span class="macro">write!</span>( |
| f, |
| <span class="string">"{:04} Split({}, {})"</span>, |
| pc, inst.goto1, inst.goto2 |
| )<span class="question-mark">?</span>; |
| } |
| EmptyLook(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">let </span>s = <span class="macro">format!</span>(<span class="string">"{:?}"</span>, inst.look); |
| <span class="macro">write!</span>(f, <span class="string">"{:04} {}"</span>, pc, with_goto(pc, inst.goto, s))<span class="question-mark">?</span>; |
| } |
| Char(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">let </span>s = <span class="macro">format!</span>(<span class="string">"{:?}"</span>, inst.c); |
| <span class="macro">write!</span>(f, <span class="string">"{:04} {}"</span>, pc, with_goto(pc, inst.goto, s))<span class="question-mark">?</span>; |
| } |
| Ranges(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">let </span>ranges = inst |
| .ranges |
| .iter() |
| .map(|r| <span class="macro">format!</span>(<span class="string">"{:?}-{:?}"</span>, r.<span class="number">0</span>, r.<span class="number">1</span>)) |
| .collect::<Vec<String>>() |
| .join(<span class="string">", "</span>); |
| <span class="macro">write!</span>( |
| f, |
| <span class="string">"{:04} {}"</span>, |
| pc, |
| with_goto(pc, inst.goto, ranges) |
| )<span class="question-mark">?</span>; |
| } |
| Bytes(<span class="kw-2">ref </span>inst) => { |
| <span class="kw">let </span>s = <span class="macro">format!</span>( |
| <span class="string">"Bytes({}, {})"</span>, |
| visible_byte(inst.start), |
| visible_byte(inst.end) |
| ); |
| <span class="macro">write!</span>(f, <span class="string">"{:04} {}"</span>, pc, with_goto(pc, inst.goto, s))<span class="question-mark">?</span>; |
| } |
| } |
| <span class="kw">if </span>pc == <span class="self">self</span>.start { |
| <span class="macro">write!</span>(f, <span class="string">" (start)"</span>)<span class="question-mark">?</span>; |
| } |
| <span class="macro">writeln!</span>(f)<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</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>Program { |
| <span class="kw">type </span>Item = <span class="kw-2">&</span><span class="lifetime">'a </span>Inst; |
| <span class="kw">type </span>IntoIter = slice::Iter<<span class="lifetime">'a</span>, Inst>; |
| <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">/// Inst is an instruction code in a Regex program. |
| /// |
| /// Regrettably, a regex program either contains Unicode codepoint |
| /// instructions (Char and Ranges) or it contains byte instructions (Bytes). |
| /// A regex program can never contain both. |
| /// |
| /// It would be worth investigating splitting this into two distinct types and |
| /// then figuring out how to make the matching engines polymorphic over those |
| /// types without sacrificing performance. |
| /// |
| /// Other than the benefit of moving invariants into the type system, another |
| /// benefit is the decreased size. If we remove the `Char` and `Ranges` |
| /// instructions from the `Inst` enum, then its size shrinks from 32 bytes to |
| /// 24 bytes. (This is because of the removal of a `Box<[]>` in the `Ranges` |
| /// variant.) Given that byte based machines are typically much bigger than |
| /// their Unicode analogues (because they can decode UTF-8 directly), this ends |
| /// up being a pretty significant savings. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub enum </span>Inst { |
| <span class="doccomment">/// Match indicates that the program has reached a match state. |
| /// |
| /// The number in the match corresponds to the Nth logical regular |
| /// expression in this program. This index is always 0 for normal regex |
| /// programs. Values greater than 0 appear when compiling regex sets, and |
| /// each match instruction gets its own unique value. The value corresponds |
| /// to the Nth regex in the set. |
| </span>Match(usize), |
| <span class="doccomment">/// Save causes the program to save the current location of the input in |
| /// the slot indicated by InstSave. |
| </span>Save(InstSave), |
| <span class="doccomment">/// Split causes the program to diverge to one of two paths in the |
| /// program, preferring goto1 in InstSplit. |
| </span>Split(InstSplit), |
| <span class="doccomment">/// EmptyLook represents a zero-width assertion in a regex program. A |
| /// zero-width assertion does not consume any of the input text. |
| </span>EmptyLook(InstEmptyLook), |
| <span class="doccomment">/// Char requires the regex program to match the character in InstChar at |
| /// the current position in the input. |
| </span>Char(InstChar), |
| <span class="doccomment">/// Ranges requires the regex program to match the character at the current |
| /// position in the input with one of the ranges specified in InstRanges. |
| </span>Ranges(InstRanges), |
| <span class="doccomment">/// Bytes is like Ranges, except it expresses a single byte range. It is |
| /// used in conjunction with Split instructions to implement multi-byte |
| /// character classes. |
| </span>Bytes(InstBytes), |
| } |
| |
| <span class="kw">impl </span>Inst { |
| <span class="doccomment">/// Returns true if and only if this is a match instruction. |
| </span><span class="kw">pub fn </span>is_match(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Inst::Match(<span class="kw">_</span>) => <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Representation of the Save instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstSave { |
| <span class="doccomment">/// The next location to execute in the program. |
| </span><span class="kw">pub </span>goto: InstPtr, |
| <span class="doccomment">/// The capture slot (there are two slots for every capture in a regex, |
| /// including the zeroth capture for the entire match). |
| </span><span class="kw">pub </span>slot: usize, |
| } |
| |
| <span class="doccomment">/// Representation of the Split instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstSplit { |
| <span class="doccomment">/// The first instruction to try. A match resulting from following goto1 |
| /// has precedence over a match resulting from following goto2. |
| </span><span class="kw">pub </span>goto1: InstPtr, |
| <span class="doccomment">/// The second instruction to try. A match resulting from following goto1 |
| /// has precedence over a match resulting from following goto2. |
| </span><span class="kw">pub </span>goto2: InstPtr, |
| } |
| |
| <span class="doccomment">/// Representation of the `EmptyLook` instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstEmptyLook { |
| <span class="doccomment">/// The next location to execute in the program if this instruction |
| /// succeeds. |
| </span><span class="kw">pub </span>goto: InstPtr, |
| <span class="doccomment">/// The type of zero-width assertion to check. |
| </span><span class="kw">pub </span>look: EmptyLook, |
| } |
| |
| <span class="doccomment">/// The set of zero-width match instructions. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug, PartialEq, Eq)] |
| </span><span class="kw">pub enum </span>EmptyLook { |
| <span class="doccomment">/// Start of line or input. |
| </span>StartLine, |
| <span class="doccomment">/// End of line or input. |
| </span>EndLine, |
| <span class="doccomment">/// Start of input. |
| </span>StartText, |
| <span class="doccomment">/// End of input. |
| </span>EndText, |
| <span class="doccomment">/// Word character on one side and non-word character on other. |
| </span>WordBoundary, |
| <span class="doccomment">/// Word character on both sides or non-word character on both sides. |
| </span>NotWordBoundary, |
| <span class="doccomment">/// ASCII word boundary. |
| </span>WordBoundaryAscii, |
| <span class="doccomment">/// Not ASCII word boundary. |
| </span>NotWordBoundaryAscii, |
| } |
| |
| <span class="doccomment">/// Representation of the Char instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstChar { |
| <span class="doccomment">/// The next location to execute in the program if this instruction |
| /// succeeds. |
| </span><span class="kw">pub </span>goto: InstPtr, |
| <span class="doccomment">/// The character to test. |
| </span><span class="kw">pub </span>c: char, |
| } |
| |
| <span class="doccomment">/// Representation of the Ranges instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstRanges { |
| <span class="doccomment">/// The next location to execute in the program if this instruction |
| /// succeeds. |
| </span><span class="kw">pub </span>goto: InstPtr, |
| <span class="doccomment">/// The set of Unicode scalar value ranges to test. |
| </span><span class="kw">pub </span>ranges: Box<[(char, char)]>, |
| } |
| |
| <span class="kw">impl </span>InstRanges { |
| <span class="doccomment">/// Tests whether the given input character matches this instruction. |
| </span><span class="kw">pub fn </span>matches(<span class="kw-2">&</span><span class="self">self</span>, c: Char) -> bool { |
| <span class="comment">// This speeds up the `match_class_unicode` benchmark by checking |
| // some common cases quickly without binary search. e.g., Matching |
| // a Unicode class on predominantly ASCII text. |
| </span><span class="kw">for </span>r <span class="kw">in </span><span class="self">self</span>.ranges.iter().take(<span class="number">4</span>) { |
| <span class="kw">if </span>c < r.<span class="number">0 </span>{ |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="kw">if </span>c <= r.<span class="number">1 </span>{ |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| } |
| <span class="self">self</span>.ranges |
| .binary_search_by(|r| { |
| <span class="kw">if </span>r.<span class="number">1 </span>< c { |
| Ordering::Less |
| } <span class="kw">else if </span>r.<span class="number">0 </span>> c { |
| Ordering::Greater |
| } <span class="kw">else </span>{ |
| Ordering::Equal |
| } |
| }) |
| .is_ok() |
| } |
| |
| <span class="doccomment">/// Return the number of distinct characters represented by all of the |
| /// ranges. |
| </span><span class="kw">pub fn </span>num_chars(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.ranges |
| .iter() |
| .map(|<span class="kw-2">&</span>(s, e)| <span class="number">1 </span>+ (e <span class="kw">as </span>u32) - (s <span class="kw">as </span>u32)) |
| .sum::<u32>() <span class="kw">as </span>usize |
| } |
| } |
| |
| <span class="doccomment">/// Representation of the Bytes instruction. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>InstBytes { |
| <span class="doccomment">/// The next location to execute in the program if this instruction |
| /// succeeds. |
| </span><span class="kw">pub </span>goto: InstPtr, |
| <span class="doccomment">/// The start (inclusive) of this byte range. |
| </span><span class="kw">pub </span>start: u8, |
| <span class="doccomment">/// The end (inclusive) of this byte range. |
| </span><span class="kw">pub </span>end: u8, |
| } |
| |
| <span class="kw">impl </span>InstBytes { |
| <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>, byte: u8) -> bool { |
| <span class="self">self</span>.start <= byte && byte <= <span class="self">self</span>.end |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>test { |
| <span class="attribute">#[test] |
| #[cfg(target_pointer_width = <span class="string">"64"</span>)] |
| </span><span class="kw">fn </span>test_size_of_inst() { |
| <span class="kw">use </span>std::mem::size_of; |
| |
| <span class="kw">use </span><span class="kw">super</span>::Inst; |
| |
| <span class="macro">assert_eq!</span>(<span class="number">32</span>, size_of::<Inst>()); |
| } |
| } |
| </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> |