aboutsummaryrefslogtreecommitdiff
path: root/src/regex/program.rs.html
diff options
context:
space:
mode:
author2015-06-29 20:16:15 +0000
committer2015-06-29 20:16:15 +0000
commit64106c4d3d4ddba8c7bc2af75376e6d3d3d75601 (patch)
tree8c64d6e8be006486d975a651505fbbde61365cd6 /src/regex/program.rs.html
downloadirsc-64106c4d3d4ddba8c7bc2af75376e6d3d3d75601.tar.gz
irsc-64106c4d3d4ddba8c7bc2af75376e6d3d3d75601.tar.xz
irsc-64106c4d3d4ddba8c7bc2af75376e6d3d3d75601.zip
Update documentationgh-pages
Diffstat (limited to 'src/regex/program.rs.html')
-rw-r--r--src/regex/program.rs.html1057
1 files changed, 1057 insertions, 0 deletions
diff --git a/src/regex/program.rs.html b/src/regex/program.rs.html
new file mode 100644
index 0000000..8f6ed02
--- /dev/null
+++ b/src/regex/program.rs.html
@@ -0,0 +1,1057 @@
+<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/program.rs`.">
+ <meta name="keywords" content="rust, rustlang, rust-lang">
+
+ <title>program.rs.html -- source</title>
+
+ <link rel="stylesheet" type="text/css" href="../../main.css">
+
+ <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico">
+
+</head>
+<body class="rustdoc">
+ <!--[if lte IE 8]>
+ <div class="warning">
+ This old browser is unsupported and will most likely display funky
+ things.
+ </div>
+ <![endif]-->
+
+
+
+ <section class="sidebar">
+ <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a>
+
+ </section>
+
+ <nav class="sub">
+ <form class="search-form js-only">
+ <div class="search-container">
+ <input class="search-input" name="search"
+ autocomplete="off"
+ placeholder="Click or press 'S' to search, '?' for more options..."
+ type="search">
+ </div>
+ </form>
+ </nav>
+
+ <section id='main' class="content source"><pre class="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>
+</pre><pre class='rust '>
+<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span>
+<span class='comment'>// file at the top-level directory of this distribution and at</span>
+<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span>
+<span class='comment'>//</span>
+<span class='comment'>// Licensed under the Apache License, Version 2.0 &lt;LICENSE-APACHE or</span>
+<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0&gt; or the MIT license</span>
+<span class='comment'>// &lt;LICENSE-MIT or http://opensource.org/licenses/MIT&gt;, at your</span>
+<span class='comment'>// option. This file may not be copied, modified, or distributed</span>
+<span class='comment'>// except according to those terms.</span>
+
+<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>cmp</span>::{<span class='self'>self</span>, <span class='ident'>Ordering</span>};
+
+<span class='kw'>use</span> <span class='ident'>syntax</span>;
+
+<span class='kw'>use</span> <span class='ident'>Error</span>;
+<span class='kw'>use</span> <span class='ident'>backtrack</span>::{<span class='ident'>Backtrack</span>, <span class='ident'>BackMachine</span>};
+<span class='kw'>use</span> <span class='ident'>char</span>::<span class='ident'>Char</span>;
+<span class='kw'>use</span> <span class='ident'>compile</span>::<span class='ident'>Compiler</span>;
+<span class='kw'>use</span> <span class='ident'>nfa</span>::{<span class='ident'>Nfa</span>, <span class='ident'>NfaThreads</span>};
+<span class='kw'>use</span> <span class='ident'>pool</span>::<span class='ident'>Pool</span>;
+<span class='kw'>use</span> <span class='ident'>prefix</span>::<span class='ident'>Prefix</span>;
+<span class='kw'>use</span> <span class='ident'>re</span>::<span class='ident'>CaptureIdxs</span>;
+
+<span class='kw'>const</span> <span class='ident'>NUM_PREFIX_LIMIT</span>: <span class='ident'>usize</span> <span class='op'>=</span> <span class='number'>30</span>;
+<span class='kw'>const</span> <span class='ident'>PREFIX_LENGTH_LIMIT</span>: <span class='ident'>usize</span> <span class='op'>=</span> <span class='number'>15</span>;
+
+<span class='kw'>pub</span> <span class='kw'>type</span> <span class='ident'>InstIdx</span> <span class='op'>=</span> <span class='ident'>usize</span>;
+
+<span class='doccomment'>/// An instruction, the underlying unit of a compiled regular expression</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>Inst</span> {
+ <span class='doccomment'>/// A match has occurred.</span>
+ <span class='doccomment'>/// This is always the last instruction and only occurs in a single spot.</span>
+ <span class='doccomment'>/// We could special case this in the code, but it is much clearer to</span>
+ <span class='doccomment'>/// handle it as a proper instruction.</span>
+ <span class='ident'>Match</span>,
+ <span class='doccomment'>/// Save the current location in the input into the given capture location.</span>
+ <span class='ident'>Save</span>(<span class='ident'>usize</span>),
+ <span class='doccomment'>/// Jump to the instruction given.</span>
+ <span class='ident'>Jump</span>(<span class='ident'>InstIdx</span>),
+ <span class='doccomment'>/// Match either instruction, preferring the first.</span>
+ <span class='ident'>Split</span>(<span class='ident'>InstIdx</span>, <span class='ident'>InstIdx</span>),
+ <span class='doccomment'>/// A zero-width instruction. When this instruction matches, the input</span>
+ <span class='doccomment'>/// is not advanced.</span>
+ <span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>),
+ <span class='doccomment'>/// Match a single possibly case insensitive character.</span>
+ <span class='ident'>Char</span>(<span class='ident'>OneChar</span>),
+ <span class='doccomment'>/// Match one or more possibly case insensitive character ranges.</span>
+ <span class='ident'>Ranges</span>(<span class='ident'>CharRanges</span>),
+}
+
+<span class='doccomment'>/// A single character instruction.</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>OneChar</span> {
+ <span class='doccomment'>/// The character.</span>
+ <span class='kw'>pub</span> <span class='ident'>c</span>: <span class='ident'>char</span>,
+ <span class='doccomment'>/// True if the character should be matched case insensitively.</span>
+ <span class='doccomment'>/// (i.e., The input character will need to be case folded.)</span>
+ <span class='kw'>pub</span> <span class='ident'>casei</span>: <span class='ident'>bool</span>,
+}
+
+<span class='doccomment'>/// A multi-range character class instruction.</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>CharRanges</span> {
+ <span class='doccomment'>/// Sorted sequence of non-overlapping ranges.</span>
+ <span class='kw'>pub</span> <span class='ident'>ranges</span>: <span class='ident'>Vec</span><span class='op'>&lt;</span>(<span class='ident'>char</span>, <span class='ident'>char</span>)<span class='op'>&gt;</span>,
+ <span class='doccomment'>/// Whether to match case insensitively.</span>
+ <span class='kw'>pub</span> <span class='ident'>casei</span>: <span class='ident'>bool</span>,
+}
+
+<span class='doccomment'>/// The set of zero-width match instructions.</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>, <span class='ident'>PartialEq</span>, <span class='ident'>Eq</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>LookInst</span> {
+ <span class='doccomment'>/// Start of line or input.</span>
+ <span class='ident'>StartLine</span>,
+ <span class='doccomment'>/// End of line or input.</span>
+ <span class='ident'>EndLine</span>,
+ <span class='doccomment'>/// Start of input.</span>
+ <span class='ident'>StartText</span>,
+ <span class='doccomment'>/// End of input.</span>
+ <span class='ident'>EndText</span>,
+ <span class='doccomment'>/// Word character on one side and non-word character on other.</span>
+ <span class='ident'>WordBoundary</span>,
+ <span class='doccomment'>/// Word character on both sides or non-word character on both sides.</span>
+ <span class='ident'>NotWordBoundary</span>,
+}
+
+<span class='kw'>impl</span> <span class='ident'>OneChar</span> {
+ <span class='doccomment'>/// Tests whether the given input character matches this instruction.</span>
+ <span class='attribute'>#[<span class='ident'>inline</span>(<span class='ident'>always</span>)]</span> <span class='comment'>// About ~5-15% more throughput then `#[inline]`</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='ident'>c</span>: <span class='ident'>Char</span>) <span class='op'>-&gt;</span> <span class='ident'>bool</span> {
+ <span class='self'>self</span>.<span class='ident'>c</span> <span class='op'>==</span> <span class='ident'>c</span> <span class='op'>||</span> (<span class='self'>self</span>.<span class='ident'>casei</span> <span class='op'>&amp;&amp;</span> <span class='self'>self</span>.<span class='ident'>c</span> <span class='op'>==</span> <span class='ident'>c</span>.<span class='ident'>case_fold</span>())
+ }
+}
+
+<span class='kw'>impl</span> <span class='ident'>CharRanges</span> {
+ <span class='doccomment'>/// Emits a range specifically for the `.` expression.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>any</span>() <span class='op'>-&gt;</span> <span class='ident'>CharRanges</span> {
+ <span class='ident'>CharRanges</span> {
+ <span class='ident'>ranges</span>: <span class='macro'>vec</span><span class='macro'>!</span>[(<span class='string'>&#39;\x00&#39;</span>, <span class='string'>&#39;\u{10ffff}&#39;</span>)],
+ <span class='ident'>casei</span>: <span class='boolval'>false</span>,
+ }
+ }
+
+ <span class='doccomment'>/// Emits a range specifically for the `(?s).` expression.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>any_nonl</span>() <span class='op'>-&gt;</span> <span class='ident'>CharRanges</span> {
+ <span class='ident'>CharRanges</span> {
+ <span class='ident'>ranges</span>: <span class='macro'>vec</span><span class='macro'>!</span>[(<span class='string'>&#39;\x00&#39;</span>, <span class='string'>&#39;\x09&#39;</span>), (<span class='string'>&#39;\x0B&#39;</span>, <span class='string'>&#39;\u{10ffff}&#39;</span>)],
+ <span class='ident'>casei</span>: <span class='boolval'>false</span>,
+ }
+ }
+
+ <span class='doccomment'>/// Emits a range from the AST character class.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>from_class</span>(<span class='ident'>cls</span>: <span class='ident'>syntax</span>::<span class='ident'>CharClass</span>) <span class='op'>-&gt;</span> <span class='ident'>CharRanges</span> {
+ <span class='kw'>let</span> <span class='ident'>casei</span> <span class='op'>=</span> <span class='ident'>cls</span>.<span class='ident'>is_case_insensitive</span>();
+ <span class='ident'>CharRanges</span> {
+ <span class='ident'>ranges</span>: <span class='ident'>cls</span>.<span class='ident'>into_iter</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>r</span><span class='op'>|</span> (<span class='ident'>r</span>.<span class='ident'>start</span>, <span class='ident'>r</span>.<span class='ident'>end</span>)).<span class='ident'>collect</span>(),
+ <span class='ident'>casei</span>: <span class='ident'>casei</span>,
+ }
+ }
+
+ <span class='doccomment'>/// Tests whether the given input character matches this instruction.</span>
+ <span class='attribute'>#[<span class='ident'>inline</span>(<span class='ident'>always</span>)]</span> <span class='comment'>// About ~5-15% more throughput then `#[inline]`</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>c</span>: <span class='ident'>Char</span>) <span class='op'>-&gt;</span> <span class='prelude-ty'>Option</span><span class='op'>&lt;</span><span class='ident'>usize</span><span class='op'>&gt;</span> {
+ <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>casei</span> {
+ <span class='ident'>c</span> <span class='op'>=</span> <span class='ident'>c</span>.<span class='ident'>case_fold</span>();
+ }
+ <span class='comment'>// This speeds up the `match_class_unicode` benchmark by checking</span>
+ <span class='comment'>// some common cases quickly without binary search. e.g., Matching</span>
+ <span class='comment'>// a Unicode class on predominantly ASCII text.</span>
+ <span class='kw'>for</span> <span class='ident'>i</span> <span class='kw'>in</span> <span class='number'>0</span>..<span class='ident'>cmp</span>::<span class='ident'>min</span>(<span class='self'>self</span>.<span class='ident'>ranges</span>.<span class='ident'>len</span>(), <span class='number'>4</span>) {
+ <span class='kw'>let</span> <span class='ident'>r</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>ranges</span>[<span class='ident'>i</span>];
+ <span class='kw'>if</span> <span class='ident'>c</span> <span class='op'>&lt;</span> <span class='ident'>r</span>.<span class='number'>0</span> {
+ <span class='kw'>return</span> <span class='prelude-val'>None</span>;
+ }
+ <span class='kw'>if</span> <span class='ident'>c</span> <span class='op'>&lt;=</span> <span class='ident'>r</span>.<span class='number'>1</span> {
+ <span class='kw'>return</span> <span class='prelude-val'>Some</span>(<span class='ident'>i</span>);
+ }
+ }
+ <span class='self'>self</span>.<span class='ident'>ranges</span>.<span class='ident'>binary_search_by</span>(<span class='op'>|</span><span class='ident'>r</span><span class='op'>|</span> {
+ <span class='kw'>if</span> <span class='ident'>r</span>.<span class='number'>1</span> <span class='op'>&lt;</span> <span class='ident'>c</span> {
+ <span class='ident'>Ordering</span>::<span class='ident'>Less</span>
+ } <span class='kw'>else</span> <span class='kw'>if</span> <span class='ident'>r</span>.<span class='number'>0</span> <span class='op'>&gt;</span> <span class='ident'>c</span> {
+ <span class='ident'>Ordering</span>::<span class='ident'>Greater</span>
+ } <span class='kw'>else</span> {
+ <span class='ident'>Ordering</span>::<span class='ident'>Equal</span>
+ }
+ }).<span class='ident'>ok</span>()
+ }
+}
+
+<span class='kw'>impl</span> <span class='ident'>LookInst</span> {
+ <span class='doccomment'>/// Tests whether the pair of characters matches this zero-width</span>
+ <span class='doccomment'>/// instruction.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='ident'>c1</span>: <span class='ident'>Char</span>, <span class='ident'>c2</span>: <span class='ident'>Char</span>) <span class='op'>-&gt;</span> <span class='ident'>bool</span> {
+ <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>LookInst</span>::<span class='op'>*</span>;
+ <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> {
+ <span class='ident'>StartLine</span> <span class='op'>=&gt;</span> <span class='ident'>c1</span>.<span class='ident'>is_none</span>() <span class='op'>||</span> <span class='ident'>c1</span> <span class='op'>==</span> <span class='string'>&#39;\n&#39;</span>,
+ <span class='ident'>EndLine</span> <span class='op'>=&gt;</span> <span class='ident'>c2</span>.<span class='ident'>is_none</span>() <span class='op'>||</span> <span class='ident'>c2</span> <span class='op'>==</span> <span class='string'>&#39;\n&#39;</span>,
+ <span class='ident'>StartText</span> <span class='op'>=&gt;</span> <span class='ident'>c1</span>.<span class='ident'>is_none</span>(),
+ <span class='ident'>EndText</span> <span class='op'>=&gt;</span> <span class='ident'>c2</span>.<span class='ident'>is_none</span>(),
+ <span class='kw-2'>ref</span> <span class='ident'>wbty</span> <span class='op'>=&gt;</span> {
+ <span class='kw'>let</span> (<span class='ident'>w1</span>, <span class='ident'>w2</span>) <span class='op'>=</span> (<span class='ident'>c1</span>.<span class='ident'>is_word_char</span>(), <span class='ident'>c2</span>.<span class='ident'>is_word_char</span>());
+ (<span class='op'>*</span><span class='ident'>wbty</span> <span class='op'>==</span> <span class='ident'>WordBoundary</span> <span class='op'>&amp;&amp;</span> <span class='ident'>w1</span> <span class='op'>^</span> <span class='ident'>w2</span>)
+ <span class='op'>||</span> (<span class='op'>*</span><span class='ident'>wbty</span> <span class='op'>==</span> <span class='ident'>NotWordBoundary</span> <span class='op'>&amp;&amp;</span> <span class='op'>!</span>(<span class='ident'>w1</span> <span class='op'>^</span> <span class='ident'>w2</span>))
+ }
+ }
+ }
+}
+
+<span class='doccomment'>/// The matching engines offered by this regex implementation.</span>
+<span class='doccomment'>///</span>
+<span class='doccomment'>/// N.B. This is exported for use in testing.</span>
+<span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Copy</span>, <span class='ident'>Debug</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>MatchEngine</span> {
+ <span class='doccomment'>/// A bounded backtracking implementation. About twice as fast as the</span>
+ <span class='doccomment'>/// NFA, but can only work on small regexes and small input.</span>
+ <span class='ident'>Backtrack</span>,
+ <span class='doccomment'>/// A full NFA simulation. Can always be employed but almost always the</span>
+ <span class='doccomment'>/// slowest choice.</span>
+ <span class='ident'>Nfa</span>,
+ <span class='doccomment'>/// If the entire regex is a literal and no capture groups have been</span>
+ <span class='doccomment'>/// requested, then we can degrade to a simple substring match.</span>
+ <span class='ident'>Literals</span>,
+}
+
+<span class='doccomment'>/// Program represents a compiled regular expression. Once an expression is</span>
+<span class='doccomment'>/// compiled, its representation is immutable and will never change.</span>
+<span class='doccomment'>/// (Well, almost. In fact, the matching engines cache state that can be</span>
+<span class='doccomment'>/// reused on subsequent searches. But this is interior mutability that</span>
+<span class='doccomment'>/// shouldn&#39;t be observable by the caller.)</span>
+<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Debug</span>)]</span>
+<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>Program</span> {
+ <span class='doccomment'>/// The original regular expression string.</span>
+ <span class='kw'>pub</span> <span class='ident'>original</span>: <span class='ident'>String</span>,
+ <span class='doccomment'>/// A sequence of instructions.</span>
+ <span class='kw'>pub</span> <span class='ident'>insts</span>: <span class='ident'>Vec</span><span class='op'>&lt;</span><span class='ident'>Inst</span><span class='op'>&gt;</span>,
+ <span class='doccomment'>/// The sequence of capture group names. There is an entry for each capture</span>
+ <span class='doccomment'>/// group index and a name exists only if the capture group is named.</span>
+ <span class='kw'>pub</span> <span class='ident'>cap_names</span>: <span class='ident'>Vec</span><span class='op'>&lt;</span><span class='prelude-ty'>Option</span><span class='op'>&lt;</span><span class='ident'>String</span><span class='op'>&gt;&gt;</span>,
+ <span class='doccomment'>/// If the regular expression requires a literal prefix in order to have a</span>
+ <span class='doccomment'>/// match, that prefix is stored here as a DFA.</span>
+ <span class='kw'>pub</span> <span class='ident'>prefixes</span>: <span class='ident'>Prefix</span>,
+ <span class='doccomment'>/// True iff matching any literal prefix indicates a match.</span>
+ <span class='kw'>pub</span> <span class='ident'>prefixes_complete</span>: <span class='ident'>bool</span>,
+ <span class='doccomment'>/// True iff program is anchored at the beginning.</span>
+ <span class='kw'>pub</span> <span class='ident'>anchored_begin</span>: <span class='ident'>bool</span>,
+ <span class='doccomment'>/// True iff program is anchored at the end.</span>
+ <span class='kw'>pub</span> <span class='ident'>anchored_end</span>: <span class='ident'>bool</span>,
+ <span class='doccomment'>/// The type of matching engine to use.</span>
+ <span class='doccomment'>/// When `None` (the default), pick an engine automatically.</span>
+ <span class='kw'>pub</span> <span class='ident'>engine</span>: <span class='prelude-ty'>Option</span><span class='op'>&lt;</span><span class='ident'>MatchEngine</span><span class='op'>&gt;</span>,
+ <span class='doccomment'>/// Cached NFA threads.</span>
+ <span class='kw'>pub</span> <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span><span class='op'>&lt;</span><span class='ident'>NfaThreads</span><span class='op'>&gt;</span>,
+ <span class='doccomment'>/// Cached backtracking memory.</span>
+ <span class='kw'>pub</span> <span class='ident'>backtrack</span>: <span class='ident'>Pool</span><span class='op'>&lt;</span><span class='ident'>BackMachine</span><span class='op'>&gt;</span>,
+}
+
+<span class='kw'>impl</span> <span class='ident'>Program</span> {
+ <span class='doccomment'>/// Compiles a Regex.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>new</span>(
+ <span class='ident'>engine</span>: <span class='prelude-ty'>Option</span><span class='op'>&lt;</span><span class='ident'>MatchEngine</span><span class='op'>&gt;</span>,
+ <span class='ident'>size_limit</span>: <span class='ident'>usize</span>,
+ <span class='ident'>re</span>: <span class='kw-2'>&amp;</span><span class='ident'>str</span>,
+ ) <span class='op'>-&gt;</span> <span class='prelude-ty'>Result</span><span class='op'>&lt;</span><span class='ident'>Program</span>, <span class='ident'>Error</span><span class='op'>&gt;</span> {
+ <span class='kw'>let</span> <span class='ident'>expr</span> <span class='op'>=</span> <span class='macro'>try</span><span class='macro'>!</span>(<span class='ident'>syntax</span>::<span class='ident'>Expr</span>::<span class='ident'>parse</span>(<span class='ident'>re</span>));
+ <span class='kw'>let</span> (<span class='ident'>insts</span>, <span class='ident'>cap_names</span>) <span class='op'>=</span> <span class='macro'>try</span><span class='macro'>!</span>(<span class='ident'>Compiler</span>::<span class='ident'>new</span>(<span class='ident'>size_limit</span>).<span class='ident'>compile</span>(<span class='ident'>expr</span>));
+ <span class='kw'>let</span> (<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>) <span class='op'>=</span> (<span class='ident'>insts</span>.<span class='ident'>len</span>(), <span class='ident'>num_captures</span>(<span class='kw-2'>&amp;</span><span class='ident'>insts</span>));
+ <span class='kw'>let</span> <span class='ident'>create_threads</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>NfaThreads</span>::<span class='ident'>new</span>(<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>);
+ <span class='kw'>let</span> <span class='ident'>create_backtrack</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>BackMachine</span>::<span class='ident'>new</span>();
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>prog</span> <span class='op'>=</span> <span class='ident'>Program</span> {
+ <span class='ident'>original</span>: <span class='ident'>re</span>.<span class='ident'>into</span>(),
+ <span class='ident'>insts</span>: <span class='ident'>insts</span>,
+ <span class='ident'>cap_names</span>: <span class='ident'>cap_names</span>,
+ <span class='ident'>prefixes</span>: <span class='ident'>Prefix</span>::<span class='ident'>Empty</span>,
+ <span class='ident'>prefixes_complete</span>: <span class='boolval'>false</span>,
+ <span class='ident'>anchored_begin</span>: <span class='boolval'>false</span>,
+ <span class='ident'>anchored_end</span>: <span class='boolval'>false</span>,
+ <span class='ident'>engine</span>: <span class='ident'>engine</span>,
+ <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_threads</span>)),
+ <span class='ident'>backtrack</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_backtrack</span>)),
+ };
+
+ <span class='ident'>prog</span>.<span class='ident'>find_prefixes</span>();
+ <span class='ident'>prog</span>.<span class='ident'>anchored_begin</span> <span class='op'>=</span> <span class='kw'>match</span> <span class='ident'>prog</span>.<span class='ident'>insts</span>[<span class='number'>1</span>] {
+ <span class='ident'>Inst</span>::<span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>::<span class='ident'>StartText</span>) <span class='op'>=&gt;</span> <span class='boolval'>true</span>,
+ _ <span class='op'>=&gt;</span> <span class='boolval'>false</span>,
+ };
+ <span class='ident'>prog</span>.<span class='ident'>anchored_end</span> <span class='op'>=</span> <span class='kw'>match</span> <span class='ident'>prog</span>.<span class='ident'>insts</span>[<span class='ident'>prog</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>() <span class='op'>-</span> <span class='number'>3</span>] {
+ <span class='ident'>Inst</span>::<span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>::<span class='ident'>EndText</span>) <span class='op'>=&gt;</span> <span class='boolval'>true</span>,
+ _ <span class='op'>=&gt;</span> <span class='boolval'>false</span>,
+ };
+ <span class='prelude-val'>Ok</span>(<span class='ident'>prog</span>)
+ }
+
+ <span class='doccomment'>/// Executes a compiled regex program.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>exec</span>(
+ <span class='kw-2'>&amp;</span><span class='self'>self</span>,
+ <span class='ident'>caps</span>: <span class='kw-2'>&amp;</span><span class='kw-2'>mut</span> <span class='ident'>CaptureIdxs</span>,
+ <span class='ident'>text</span>: <span class='kw-2'>&amp;</span><span class='ident'>str</span>,
+ <span class='ident'>start</span>: <span class='ident'>usize</span>,
+ ) <span class='op'>-&gt;</span> <span class='ident'>bool</span> {
+ <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>choose_engine</span>(<span class='ident'>caps</span>.<span class='ident'>len</span>(), <span class='ident'>text</span>) {
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Backtrack</span> <span class='op'>=&gt;</span> <span class='ident'>Backtrack</span>::<span class='ident'>exec</span>(<span class='self'>self</span>, <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>),
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Nfa</span> <span class='op'>=&gt;</span> <span class='ident'>Nfa</span>::<span class='ident'>exec</span>(<span class='self'>self</span>, <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>),
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Literals</span> <span class='op'>=&gt;</span> {
+ <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>find</span>(<span class='kw-2'>&amp;</span><span class='ident'>text</span>[<span class='ident'>start</span>..]) {
+ <span class='prelude-val'>None</span> <span class='op'>=&gt;</span> <span class='boolval'>false</span>,
+ <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=&gt;</span> {
+ <span class='kw'>if</span> <span class='ident'>caps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>2</span> {
+ <span class='ident'>caps</span>[<span class='number'>0</span>] <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='ident'>start</span> <span class='op'>+</span> <span class='ident'>s</span>);
+ <span class='ident'>caps</span>[<span class='number'>1</span>] <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='ident'>start</span> <span class='op'>+</span> <span class='ident'>e</span>);
+ }
+ <span class='boolval'>true</span>
+ }
+ }
+ }
+ }
+ }
+
+ <span class='kw'>fn</span> <span class='ident'>choose_engine</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='ident'>cap_len</span>: <span class='ident'>usize</span>, <span class='ident'>text</span>: <span class='kw-2'>&amp;</span><span class='ident'>str</span>) <span class='op'>-&gt;</span> <span class='ident'>MatchEngine</span> {
+ <span class='comment'>// If the engine is already chosen, then we use it.</span>
+ <span class='comment'>// But that might not be a good idea. e.g., What if `Literals` is</span>
+ <span class='comment'>// chosen and it can&#39;t work? I guess we should probably check whether</span>
+ <span class='comment'>// the chosen engine is appropriate or not.</span>
+ <span class='self'>self</span>.<span class='ident'>engine</span>.<span class='ident'>unwrap_or_else</span>(<span class='op'>||</span> {
+ <span class='kw'>if</span> <span class='ident'>cap_len</span> <span class='op'>&lt;=</span> <span class='number'>2</span>
+ <span class='op'>&amp;&amp;</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>preserves_priority</span>()
+ <span class='op'>&amp;&amp;</span> <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> {
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Literals</span>
+ } <span class='kw'>else</span> <span class='kw'>if</span> <span class='ident'>Backtrack</span>::<span class='ident'>should_exec</span>(<span class='self'>self</span>, <span class='ident'>text</span>) {
+ <span class='comment'>// We&#39;re only here if the input and regex combined are small.</span>
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Backtrack</span>
+ } <span class='kw'>else</span> {
+ <span class='ident'>MatchEngine</span>::<span class='ident'>Nfa</span>
+ }
+ })
+ }
+
+ <span class='doccomment'>/// Returns the total number of capture groups in the regular expression.</span>
+ <span class='doccomment'>/// This includes the zeroth capture.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>num_captures</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>) <span class='op'>-&gt;</span> <span class='ident'>usize</span> {
+ <span class='ident'>num_captures</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>.<span class='ident'>insts</span>)
+ }
+
+ <span class='doccomment'>/// Allocate new capture groups.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>alloc_captures</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>) <span class='op'>-&gt;</span> <span class='ident'>Vec</span><span class='op'>&lt;</span><span class='prelude-ty'>Option</span><span class='op'>&lt;</span><span class='ident'>usize</span><span class='op'>&gt;&gt;</span> {
+ <span class='macro'>vec</span><span class='macro'>!</span>[<span class='prelude-val'>None</span>; <span class='number'>2</span> <span class='op'>*</span> <span class='self'>self</span>.<span class='ident'>num_captures</span>()]
+ }
+
+ <span class='doccomment'>/// Find and store a prefix machine for the current program.</span>
+ <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>find_prefixes</span>(<span class='kw-2'>&amp;</span><span class='kw-2'>mut</span> <span class='self'>self</span>) {
+ <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>Inst</span>::<span class='op'>*</span>;
+
+ <span class='kw'>let</span> (<span class='ident'>ps</span>, <span class='ident'>complete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='number'>1</span>);
+ <span class='kw'>if</span> <span class='ident'>ps</span>.<span class='ident'>len</span>() <span class='op'>&gt;</span> <span class='number'>0</span> {
+ <span class='self'>self</span>.<span class='ident'>prefixes</span> <span class='op'>=</span> <span class='ident'>Prefix</span>::<span class='ident'>new</span>(<span class='ident'>ps</span>);
+ <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> <span class='op'>=</span> <span class='ident'>complete</span>;
+ <span class='kw'>return</span>;
+ }
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='number'>1</span>;
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>prefixes</span> <span class='op'>=</span> <span class='macro'>vec</span><span class='macro'>!</span>[];
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='boolval'>true</span>;
+ <span class='kw'>while</span> <span class='kw'>let</span> <span class='ident'>Split</span>(<span class='ident'>x</span>, <span class='ident'>y</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>] {
+ <span class='kw'>let</span> (<span class='ident'>xps</span>, <span class='ident'>xcomplete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='ident'>x</span>);
+ <span class='kw'>let</span> (<span class='ident'>yps</span>, <span class='ident'>ycomplete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='ident'>y</span>);
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>done</span> <span class='op'>=</span> <span class='boolval'>false</span>;
+ <span class='kw'>match</span> (<span class='kw-2'>&amp;</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>x</span>], <span class='kw-2'>&amp;</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>y</span>]) {
+ <span class='comment'>// We should be able to support this. Add explicit stack. ---AG</span>
+ (<span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _), <span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _)) <span class='op'>=&gt;</span> <span class='kw'>return</span>,
+ (_, <span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _)) <span class='kw'>if</span> <span class='ident'>xps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=&gt;</span> <span class='kw'>return</span>,
+ (_, <span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _)) <span class='op'>=&gt;</span> {
+ <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&amp;&amp;</span> <span class='ident'>xcomplete</span>;
+ <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>xps</span>);
+ <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>y</span>;
+ }
+ (<span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _), _) <span class='kw'>if</span> <span class='ident'>yps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=&gt;</span> <span class='kw'>return</span>,
+ (<span class='kw-2'>&amp;</span><span class='ident'>Split</span>(_, _), _) <span class='op'>=&gt;</span> {
+ <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&amp;&amp;</span> <span class='ident'>ycomplete</span>;
+ <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>yps</span>);
+ <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>x</span>;
+ }
+ _ <span class='kw'>if</span> <span class='ident'>xps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>||</span> <span class='ident'>yps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=&gt;</span> <span class='kw'>return</span>,
+ <span class='comment'>// This is our base case. We&#39;ve followed splits the whole</span>
+ <span class='comment'>// way, which means both instructions lead to a match.</span>
+ _ <span class='op'>=&gt;</span> {
+ <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&amp;&amp;</span> <span class='ident'>xcomplete</span> <span class='op'>&amp;&amp;</span> <span class='ident'>ycomplete</span>;
+ <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>xps</span>);
+ <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>yps</span>);
+ <span class='ident'>done</span> <span class='op'>=</span> <span class='boolval'>true</span>;
+ }
+ }
+ <span class='comment'>// Arg. We&#39;ve over-extended ourselves, quit with nothing to</span>
+ <span class='comment'>// show for it.</span>
+ <span class='kw'>if</span> <span class='ident'>prefixes</span>.<span class='ident'>len</span>() <span class='op'>&gt;</span> <span class='ident'>NUM_PREFIX_LIMIT</span> {
+ <span class='kw'>return</span>;
+ }
+ <span class='kw'>if</span> <span class='ident'>done</span> { <span class='kw'>break</span>; }
+ }
+ <span class='self'>self</span>.<span class='ident'>prefixes</span> <span class='op'>=</span> <span class='ident'>Prefix</span>::<span class='ident'>new</span>(<span class='ident'>prefixes</span>);
+ <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&amp;&amp;</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>len</span>() <span class='op'>&gt;</span> <span class='number'>0</span>;
+ }
+
+ <span class='doccomment'>/// Find a prefix starting at the given instruction.</span>
+ <span class='doccomment'>///</span>
+ <span class='doccomment'>/// Returns `true` in the tuple if the end of the prefix leads trivially</span>
+ <span class='doccomment'>/// to a match. (This may report false negatives, but being conservative</span>
+ <span class='doccomment'>/// is OK.)</span>
+ <span class='kw'>fn</span> <span class='ident'>prefixes_from_insts</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>pc</span>: <span class='ident'>usize</span>) <span class='op'>-&gt;</span> (<span class='ident'>Vec</span><span class='op'>&lt;</span><span class='ident'>String</span><span class='op'>&gt;</span>, <span class='ident'>bool</span>) {
+ <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>Inst</span>::<span class='op'>*</span>;
+
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>true</span>;
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>alts</span> <span class='op'>=</span> <span class='macro'>vec</span><span class='macro'>!</span>[<span class='ident'>String</span>::<span class='ident'>new</span>()];
+ <span class='kw'>while</span> <span class='ident'>pc</span> <span class='op'>&lt;</span> <span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>() {
+ <span class='kw'>let</span> <span class='ident'>inst</span> <span class='op'>=</span> <span class='kw-2'>&amp;</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>];
+
+ <span class='comment'>// Each iteration adds one character to every alternate prefix *or*</span>
+ <span class='comment'>// it stops. Thus, the prefix alternates grow in lock step, and it</span>
+ <span class='comment'>// suffices to check one of them to see if the prefix limit has been</span>
+ <span class='comment'>// exceeded.</span>
+ <span class='kw'>if</span> <span class='ident'>alts</span>[<span class='number'>0</span>].<span class='ident'>len</span>() <span class='op'>&gt;</span> <span class='ident'>PREFIX_LENGTH_LIMIT</span> {
+ <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>false</span>;
+ <span class='kw'>break</span>;
+ }
+ <span class='kw'>match</span> <span class='op'>*</span><span class='ident'>inst</span> {
+ <span class='ident'>Save</span>(_) <span class='op'>=&gt;</span> { <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>; <span class='kw'>continue</span> } <span class='comment'>// completely ignore it</span>
+ <span class='ident'>Char</span>(<span class='ident'>OneChar</span> { <span class='ident'>c</span>, <span class='ident'>casei</span>: <span class='boolval'>false</span> }) <span class='op'>=&gt;</span> {
+ <span class='kw'>for</span> <span class='ident'>alt</span> <span class='kw'>in</span> <span class='kw-2'>&amp;</span><span class='kw-2'>mut</span> <span class='ident'>alts</span> {
+ <span class='ident'>alt</span>.<span class='ident'>push</span>(<span class='ident'>c</span>);
+ }
+ <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>;
+ }
+ <span class='ident'>Ranges</span>(<span class='ident'>CharRanges</span> { <span class='kw-2'>ref</span> <span class='ident'>ranges</span>, <span class='ident'>casei</span>: <span class='boolval'>false</span> }) <span class='op'>=&gt;</span> {
+ <span class='kw'>let</span> <span class='ident'>nchars</span> <span class='op'>=</span> <span class='ident'>num_chars_in_ranges</span>(<span class='ident'>ranges</span>);
+ <span class='kw'>if</span> <span class='ident'>alts</span>.<span class='ident'>len</span>() <span class='op'>*</span> <span class='ident'>nchars</span> <span class='op'>&gt;</span> <span class='ident'>NUM_PREFIX_LIMIT</span> {
+ <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>false</span>;
+ <span class='kw'>break</span>;
+ }
+
+ <span class='kw'>let</span> <span class='ident'>orig</span> <span class='op'>=</span> <span class='ident'>alts</span>;
+ <span class='ident'>alts</span> <span class='op'>=</span> <span class='ident'>Vec</span>::<span class='ident'>with_capacity</span>(<span class='ident'>orig</span>.<span class='ident'>len</span>());
+ <span class='kw'>for</span> <span class='kw-2'>&amp;</span>(<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='kw'>in</span> <span class='ident'>ranges</span> {
+ <span class='kw'>for</span> <span class='ident'>c</span> <span class='kw'>in</span> (<span class='ident'>s</span> <span class='kw'>as</span> <span class='ident'>u32</span>)..(<span class='ident'>e</span> <span class='kw'>as</span> <span class='ident'>u32</span> <span class='op'>+</span> <span class='number'>1</span>){
+ <span class='kw'>for</span> <span class='ident'>alt</span> <span class='kw'>in</span> <span class='kw-2'>&amp;</span><span class='ident'>orig</span> {
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>alt</span> <span class='op'>=</span> <span class='ident'>alt</span>.<span class='ident'>clone</span>();
+ <span class='ident'>alt</span>.<span class='ident'>push</span>(::<span class='ident'>std</span>::<span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='ident'>c</span>).<span class='ident'>unwrap</span>());
+ <span class='ident'>alts</span>.<span class='ident'>push</span>(<span class='ident'>alt</span>);
+ }
+ }
+ }
+ <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>;
+ }
+ <span class='ident'>Jump</span>(<span class='ident'>pc2</span>) <span class='op'>=&gt;</span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>pc2</span>,
+ _ <span class='op'>=&gt;</span> { <span class='ident'>complete</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>leads_to_match</span>(<span class='ident'>pc</span>); <span class='kw'>break</span> }
+ }
+ }
+ <span class='kw'>if</span> <span class='ident'>alts</span>[<span class='number'>0</span>].<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> {
+ (<span class='macro'>vec</span><span class='macro'>!</span>[], <span class='boolval'>false</span>)
+ } <span class='kw'>else</span> {
+ (<span class='ident'>alts</span>, <span class='ident'>complete</span>)
+ }
+ }
+
+ <span class='kw'>fn</span> <span class='ident'>leads_to_match</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>pc</span>: <span class='ident'>usize</span>) <span class='op'>-&gt;</span> <span class='ident'>bool</span> {
+ <span class='comment'>// I&#39;m pretty sure this is conservative, so it might have some</span>
+ <span class='comment'>// false negatives.</span>
+ <span class='kw'>loop</span> {
+ <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>] {
+ <span class='ident'>Inst</span>::<span class='ident'>Match</span> <span class='op'>=&gt;</span> <span class='kw'>return</span> <span class='boolval'>true</span>,
+ <span class='ident'>Inst</span>::<span class='ident'>Save</span>(_) <span class='op'>=&gt;</span> <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>,
+ <span class='ident'>Inst</span>::<span class='ident'>Jump</span>(<span class='ident'>pc2</span>) <span class='op'>=&gt;</span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>pc2</span>,
+ _ <span class='op'>=&gt;</span> <span class='kw'>return</span> <span class='boolval'>false</span>,
+ }
+ }
+ }
+}
+
+<span class='kw'>impl</span> <span class='ident'>Clone</span> <span class='kw'>for</span> <span class='ident'>Program</span> {
+ <span class='kw'>fn</span> <span class='ident'>clone</span>(<span class='kw-2'>&amp;</span><span class='self'>self</span>) <span class='op'>-&gt;</span> <span class='ident'>Program</span> {
+ <span class='kw'>let</span> (<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>) <span class='op'>=</span> (<span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>(), <span class='self'>self</span>.<span class='ident'>num_captures</span>());
+ <span class='kw'>let</span> <span class='ident'>create_threads</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>NfaThreads</span>::<span class='ident'>new</span>(<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>);
+ <span class='kw'>let</span> <span class='ident'>create_backtrack</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>BackMachine</span>::<span class='ident'>new</span>();
+ <span class='ident'>Program</span> {
+ <span class='ident'>original</span>: <span class='self'>self</span>.<span class='ident'>original</span>.<span class='ident'>clone</span>(),
+ <span class='ident'>insts</span>: <span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>clone</span>(),
+ <span class='ident'>cap_names</span>: <span class='self'>self</span>.<span class='ident'>cap_names</span>.<span class='ident'>clone</span>(),
+ <span class='ident'>prefixes</span>: <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>clone</span>(),
+ <span class='ident'>prefixes_complete</span>: <span class='self'>self</span>.<span class='ident'>prefixes_complete</span>,
+ <span class='ident'>anchored_begin</span>: <span class='self'>self</span>.<span class='ident'>anchored_begin</span>,
+ <span class='ident'>anchored_end</span>: <span class='self'>self</span>.<span class='ident'>anchored_end</span>,
+ <span class='ident'>engine</span>: <span class='self'>self</span>.<span class='ident'>engine</span>,
+ <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_threads</span>)),
+ <span class='ident'>backtrack</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_backtrack</span>)),
+ }
+ }
+}
+
+<span class='doccomment'>/// Return the number of captures in the given sequence of instructions.</span>
+<span class='kw'>fn</span> <span class='ident'>num_captures</span>(<span class='ident'>insts</span>: <span class='kw-2'>&amp;</span>[<span class='ident'>Inst</span>]) <span class='op'>-&gt;</span> <span class='ident'>usize</span> {
+ <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>n</span> <span class='op'>=</span> <span class='number'>0</span>;
+ <span class='kw'>for</span> <span class='ident'>inst</span> <span class='kw'>in</span> <span class='ident'>insts</span> {
+ <span class='kw'>match</span> <span class='op'>*</span><span class='ident'>inst</span> {
+ <span class='ident'>Inst</span>::<span class='ident'>Save</span>(<span class='ident'>c</span>) <span class='op'>=&gt;</span> <span class='ident'>n</span> <span class='op'>=</span> <span class='ident'>cmp</span>::<span class='ident'>max</span>(<span class='ident'>n</span>, <span class='ident'>c</span><span class='op'>+</span><span class='number'>1</span>),
+ _ <span class='op'>=&gt;</span> {}
+ }
+ }
+ <span class='comment'>// There&#39;s exactly 2 Save slots for every capture.</span>
+ <span class='ident'>n</span> <span class='op'>/</span> <span class='number'>2</span>
+}
+
+<span class='doccomment'>/// Count the number of characters in the given range.</span>
+<span class='doccomment'>///</span>
+<span class='doccomment'>/// This is useful for pre-emptively limiting the number of prefix literals</span>
+<span class='doccomment'>/// we extract from a regex program.</span>
+<span class='kw'>fn</span> <span class='ident'>num_chars_in_ranges</span>(<span class='ident'>ranges</span>: <span class='kw-2'>&amp;</span>[(<span class='ident'>char</span>, <span class='ident'>char</span>)]) <span class='op'>-&gt;</span> <span class='ident'>usize</span> {
+ <span class='ident'>ranges</span>.<span class='ident'>iter</span>()
+ .<span class='ident'>map</span>(<span class='op'>|</span><span class='kw-2'>&amp;</span>(<span class='ident'>s</span>, <span class='ident'>e</span>)<span class='op'>|</span> (<span class='ident'>e</span> <span class='kw'>as</span> <span class='ident'>u32</span>) <span class='op'>-</span> (<span class='ident'>s</span> <span class='kw'>as</span> <span class='ident'>u32</span>))
+ .<span class='ident'>fold</span>(<span class='number'>0</span>, <span class='op'>|</span><span class='ident'>acc</span>, <span class='ident'>len</span><span class='op'>|</span> <span class='ident'>acc</span> <span class='op'>+</span> <span class='ident'>len</span>) <span class='kw'>as</span> <span class='ident'>usize</span>
+}
+</pre>
+</section>
+ <section id='search' class="content hidden"></section>
+
+ <section class="footer"></section>
+
+ <div id="help" class="hidden">
+ <div class="shortcuts">
+ <h1>Keyboard shortcuts</h1>
+ <dl>
+ <dt>?</dt>
+ <dd>Show this help dialog</dd>
+ <dt>S</dt>
+ <dd>Focus the search field</dd>
+ <dt>&larrb;</dt>
+ <dd>Move up in search results</dd>
+ <dt>&rarrb;</dt>
+ <dd>Move down in search results</dd>
+ <dt>&#9166;</dt>
+ <dd>Go to active search result</dd>
+ </dl>
+ </div>
+ <div class="infos">
+ <h1>Search tricks</h1>
+ <p>
+ Prefix searches with a type followed by a colon (e.g.
+ <code>fn:</code>) to restrict the search to a given type.
+ </p>
+ <p>
+ Accepted types are: <code>fn</code>, <code>mod</code>,
+ <code>struct</code>, <code>enum</code>,
+ <code>trait</code>, <code>typedef</code> (or
+ <code>tdef</code>).
+ </p>
+ <p>
+ Search functions by type signature (e.g.
+ <code>vec -> usize</code>)
+ </p>
+ </div>
+ </div>
+
+
+
+ <script>
+ window.rootPath = "../../";
+ window.currentCrate = "regex";
+ window.playgroundUrl = "";
+ </script>
+ <script src="../../jquery.js"></script>
+ <script src="../../main.js"></script>
+
+ <script async src="../../search-index.js"></script>
+</body>
+</html> \ No newline at end of file