| <!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/snap-0.2.5/src/compress.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>compress.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="../../snap/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="../../snap/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::ops::{Deref, DerefMut}; |
| <span class="kw">use </span>std::ptr; |
| |
| <span class="kw">use </span>byteorder::{ByteOrder, LittleEndian <span class="kw">as </span>LE}; |
| |
| <span class="kw">use </span>error::{Error, <span class="prelude-ty">Result</span>}; |
| <span class="kw">use </span>varint::write_varu64; |
| <span class="kw">use </span>{MAX_INPUT_SIZE, MAX_BLOCK_SIZE}; |
| |
| <span class="doccomment">/// The total number of slots we permit for our hash table of 4 byte repeat |
| /// sequences. |
| </span><span class="kw">const </span>MAX_TABLE_SIZE: usize = <span class="number">1</span><<<span class="number">14</span>; |
| |
| <span class="doccomment">/// The size of a small hash table. This is useful for reducing overhead when |
| /// compressing very small blocks of bytes. |
| </span><span class="kw">const </span>SMALL_TABLE_SIZE: usize = <span class="number">1</span><<<span class="number">10</span>; |
| |
| <span class="doccomment">/// The total number of bytes that we always leave uncompressed at the end |
| /// of the buffer. This in particular affords us some wiggle room during |
| /// compression such that faster copy operations can be used. |
| </span><span class="kw">const </span>INPUT_MARGIN: usize = <span class="number">16 </span>- <span class="number">1</span>; |
| |
| <span class="doccomment">/// The minimum block size that we're willing to consider for compression. |
| /// Anything smaller than this gets emitted as a literal. |
| </span><span class="kw">const </span>MIN_NON_LITERAL_BLOCK_SIZE: usize = <span class="number">1 </span>+ <span class="number">1 </span>+ INPUT_MARGIN; |
| |
| <span class="doccomment">/// Nice names for the various Snappy tags. |
| </span><span class="kw">enum </span>Tag { |
| Literal = <span class="number">0b00</span>, |
| Copy1 = <span class="number">0b01</span>, |
| Copy2 = <span class="number">0b10</span>, |
| <span class="comment">// Compression never actually emits a Copy4 operation and decompression |
| // uses tricks so that we never explicitly do case analysis on the copy |
| // operation type, therefore leading to the fact that we never use Copy4. |
| </span><span class="attribute">#[allow(dead_code)] |
| </span>Copy4 = <span class="number">0b11</span>, |
| } |
| |
| <span class="doccomment">/// Returns the maximum compressed size given the uncompressed size. |
| /// |
| /// If the uncompressed size exceeds the maximum allowable size then this |
| /// returns 0. |
| </span><span class="kw">pub fn </span>max_compress_len(input_len: usize) -> usize { |
| <span class="kw">let </span>input_len = input_len <span class="kw">as </span>u64; |
| <span class="kw">if </span>input_len > MAX_INPUT_SIZE { |
| <span class="kw">return </span><span class="number">0</span>; |
| } |
| <span class="kw">let </span>max = <span class="number">32 </span>+ input_len + (input_len / <span class="number">6</span>); |
| <span class="kw">if </span>max > MAX_INPUT_SIZE { |
| <span class="number">0 |
| </span>} <span class="kw">else </span>{ |
| max <span class="kw">as </span>usize |
| } |
| } |
| |
| <span class="doccomment">/// Encoder is a raw encoder for compressing bytes in the Snappy format. |
| /// |
| /// Thie encoder does not use the Snappy frame format and simply compresses the |
| /// given bytes in one big Snappy block (that is, it has a single header). |
| /// |
| /// Unless you explicitly need the low-level control, you should use `Writer` |
| /// instead, which compresses to the Snappy frame format. |
| /// |
| /// It is beneficial to reuse an Encoder. |
| </span><span class="kw">pub struct </span>Encoder { |
| small: [u16; SMALL_TABLE_SIZE], |
| big: Vec<u16>, |
| } |
| |
| <span class="kw">impl </span>Encoder { |
| <span class="doccomment">/// Return a new encoder that can be used for compressing bytes. |
| </span><span class="kw">pub fn </span>new() -> Encoder { |
| Encoder { |
| small: [<span class="number">0</span>; SMALL_TABLE_SIZE], |
| big: <span class="macro">vec!</span>[], |
| } |
| } |
| |
| <span class="doccomment">/// Compresses all bytes in `input` into `output`. |
| /// |
| /// `input` can be any arbitrary sequence of bytes. |
| /// |
| /// `output` must be large enough to hold the maximum possible compressed |
| /// size of `input`, which can be computed using `max_compress_len`. |
| /// |
| /// On success, this returns the number of bytes written to `output`. |
| /// |
| /// # Errors |
| /// |
| /// This method returns an error in the following circumstances: |
| /// |
| /// * The total number of bytes to compress exceeds `2^32 - 1`. |
| /// * `output` has length less than `max_compress_len(input.len())`. |
| </span><span class="kw">pub fn </span>compress( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| <span class="kw-2">mut </span>input: <span class="kw-2">&</span>[u8], |
| output: <span class="kw-2">&mut </span>[u8], |
| ) -> <span class="prelude-ty">Result</span><usize> { |
| <span class="kw">match </span>max_compress_len(input.len()) { |
| <span class="number">0 </span>=> { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::TooBig { |
| given: input.len() <span class="kw">as </span>u64, |
| max: MAX_INPUT_SIZE, |
| }); |
| } |
| min <span class="kw">if </span>output.len() < min => { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::BufferTooSmall { |
| given: output.len() <span class="kw">as </span>u64, |
| min: min <span class="kw">as </span>u64, |
| }); |
| } |
| <span class="kw">_ </span>=> {} |
| } |
| <span class="comment">// Handle an edge case specially. |
| </span><span class="kw">if </span>input.is_empty() { |
| <span class="comment">// Encodes a varint of 0, denoting the total size of uncompressed |
| // bytes. |
| </span>output[<span class="number">0</span>] = <span class="number">0</span>; |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(<span class="number">1</span>); |
| } |
| <span class="comment">// Write the Snappy header, which is just the total number of |
| // uncompressed bytes. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>d = write_varu64(output, input.len() <span class="kw">as </span>u64); |
| <span class="kw">while </span>!input.is_empty() { |
| <span class="comment">// Find the next block. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>src = input; |
| <span class="kw">if </span>src.len() > MAX_BLOCK_SIZE { |
| src = <span class="kw-2">&</span>src[..MAX_BLOCK_SIZE <span class="kw">as </span>usize]; |
| } |
| input = <span class="kw-2">&</span>input[src.len()..]; |
| |
| <span class="comment">// If the block is smallish, then don't waste time on it and just |
| // emit a literal. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>block = Block::new(src, output, d); |
| <span class="kw">if </span>block.src.len() < MIN_NON_LITERAL_BLOCK_SIZE { |
| <span class="kw">let </span>lit_end = block.src.len(); |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// SAFETY: next_emit is zero (in bounds) and the end is |
| // the length of the block (in bounds). |
| </span>block.emit_literal(lit_end); |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>table = <span class="self">self</span>.block_table(block.src.len()); |
| block.compress(table); |
| } |
| d = block.d; |
| } |
| <span class="prelude-val">Ok</span>(d) |
| } |
| |
| <span class="doccomment">/// Compresses all bytes in `input` into a freshly allocated `Vec`. |
| /// |
| /// This is just like the `compress` method, except it allocates a `Vec` |
| /// with the right size for you. (This is intended to be a convenience |
| /// method.) |
| /// |
| /// This method returns an error under the same circumstances that |
| /// `compress` does. |
| </span><span class="kw">pub fn </span>compress_vec(<span class="kw-2">&mut </span><span class="self">self</span>, input: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Result</span><Vec<u8>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>buf = <span class="macro">vec!</span>[<span class="number">0</span>; max_compress_len(input.len())]; |
| <span class="kw">let </span>n = <span class="macro">try!</span>(<span class="self">self</span>.compress(input, <span class="kw-2">&mut </span>buf)); |
| buf.truncate(n); |
| <span class="prelude-val">Ok</span>(buf) |
| } |
| } |
| |
| <span class="kw">struct </span>Block<<span class="lifetime">'s</span>, <span class="lifetime">'d</span>> { |
| src: <span class="kw-2">&</span><span class="lifetime">'s </span>[u8], |
| s: usize, |
| s_limit: usize, |
| dst: <span class="kw-2">&</span><span class="lifetime">'d </span><span class="kw-2">mut </span>[u8], |
| d: usize, |
| next_emit: usize, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'s</span>, <span class="lifetime">'d</span>> Block<<span class="lifetime">'s</span>, <span class="lifetime">'d</span>> { |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>new( |
| src: <span class="kw-2">&</span><span class="lifetime">'s </span>[u8], |
| dst: <span class="kw-2">&</span><span class="lifetime">'d </span><span class="kw-2">mut </span>[u8], |
| d: usize, |
| ) -> Block<<span class="lifetime">'s</span>, <span class="lifetime">'d</span>> { |
| Block { |
| src: src, |
| s: <span class="number">0</span>, |
| s_limit: src.len(), |
| dst: dst, |
| d: d, |
| next_emit: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>compress(<span class="kw-2">&mut </span><span class="self">self</span>, <span class="kw-2">mut </span>table: BlockTable) { |
| <span class="macro">debug_assert!</span>(!table.is_empty()); |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.src.len() >= MIN_NON_LITERAL_BLOCK_SIZE); |
| |
| <span class="self">self</span>.s += <span class="number">1</span>; |
| <span class="self">self</span>.s_limit -= INPUT_MARGIN; |
| <span class="kw">let </span><span class="kw-2">mut </span>next_hash = table.hash(LE::read_u32(<span class="kw-2">&</span><span class="self">self</span>.src[<span class="self">self</span>.s..])); |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>skip = <span class="number">32</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>candidate; |
| <span class="kw">let </span><span class="kw-2">mut </span>s_next = <span class="self">self</span>.s; |
| <span class="kw">loop </span>{ |
| <span class="self">self</span>.s = s_next; |
| <span class="kw">let </span>bytes_between_hash_lookups = skip >> <span class="number">5</span>; |
| s_next = <span class="self">self</span>.s + bytes_between_hash_lookups; |
| skip += bytes_between_hash_lookups; |
| <span class="kw">if </span>s_next > <span class="self">self</span>.s_limit { |
| <span class="kw">return </span><span class="self">self</span>.done(); |
| } |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// SAFETY: next_hash is always computed by table.hash |
| // which is guaranteed to be in bounds. |
| </span>candidate = <span class="kw-2">*</span>table.get_unchecked(next_hash) <span class="kw">as </span>usize; |
| <span class="kw-2">*</span>table.get_unchecked_mut(next_hash) = <span class="self">self</span>.s <span class="kw">as </span>u16; |
| |
| <span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr(); |
| <span class="comment">// SAFETY: s_next is guaranteed to be less than s_limit by |
| // the conditional above, which implies s_next is in |
| // bounds. |
| </span><span class="kw">let </span>x = loadu32_le(srcp.offset(s_next <span class="kw">as </span>isize)); |
| next_hash = table.hash(x); |
| <span class="comment">// SAFETY: self.s is always less than s_next, so it is also |
| // in bounds by the argument above. |
| // |
| // candidate is extracted from table, which is only ever |
| // set to valid positions in the block and is therefore |
| // also in bounds. |
| // |
| // We only need to compare y/z for equality, so we don't |
| // need to both with endianness. cur corresponds to the |
| // bytes at the current position and cand corresponds to |
| // a potential match. If they're equal, we declare victory |
| // and move below to try and extend the match. |
| </span><span class="kw">let </span>cur = loadu32(srcp.offset(<span class="self">self</span>.s <span class="kw">as </span>isize)); |
| <span class="kw">let </span>cand = loadu32(srcp.offset(candidate <span class="kw">as </span>isize)); |
| <span class="kw">if </span>cur == cand { |
| <span class="kw">break</span>; |
| } |
| } |
| } |
| <span class="comment">// While the above found a candidate for compression, before we |
| // emit a copy operation for it, we need to make sure that we emit |
| // any bytes between the last copy operation and this one as a |
| // literal. |
| </span><span class="kw">let </span>lit_end = <span class="self">self</span>.s; |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// SAFETY: next_emit is set to a previous value of self.s, |
| // which is guaranteed to be less than s_limit (in bounds). |
| // lit_end is set to the current value of self.s, also |
| // guaranteed to be less than s_limit (in bounds). |
| </span><span class="self">self</span>.emit_literal(lit_end); |
| } |
| <span class="kw">loop </span>{ |
| <span class="comment">// Look for more matching bytes starting at the position of |
| // the candidate and the current src position. We increment |
| // self.s and candidate by 4 since we already know the first 4 |
| // bytes match. |
| </span><span class="kw">let </span>base = <span class="self">self</span>.s; |
| <span class="self">self</span>.s += <span class="number">4</span>; |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// SAFETY: candidate is always set to a value from our |
| // hash table, which only contains positions in self.src |
| // that have been seen for this block that occurred before |
| // self.s. |
| </span><span class="self">self</span>.extend_match(candidate + <span class="number">4</span>); |
| } |
| <span class="kw">let </span>(offset, len) = (base - candidate, <span class="self">self</span>.s - base); |
| <span class="self">self</span>.emit_copy(offset, len); |
| <span class="self">self</span>.next_emit = <span class="self">self</span>.s; |
| <span class="kw">if </span><span class="self">self</span>.s >= <span class="self">self</span>.s_limit { |
| <span class="kw">return </span><span class="self">self</span>.done(); |
| } |
| <span class="comment">// Update the hash table with the byte sequences |
| // self.src[self.s - 1..self.s + 3] and |
| // self.src[self.s..self.s + 4]. Instead of reading 4 bytes |
| // twice, we read 8 bytes once. |
| // |
| // If we happen to get a hit on self.src[self.s..self.s + 4], |
| // then continue this loop and extend the match. |
| </span><span class="kw">unsafe </span>{ |
| <span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr(); |
| <span class="comment">// SAFETY: self.s can never exceed s_limit given by the |
| // conditional above and self.s is guaranteed to be |
| // non-zero and is therefore in bounds. |
| </span><span class="kw">let </span>x = loadu64_le(srcp.offset((<span class="self">self</span>.s - <span class="number">1</span>) <span class="kw">as </span>isize)); |
| <span class="comment">// The lower 4 bytes of x correspond to |
| // self.src[self.s - 1..self.s + 3]. |
| </span><span class="kw">let </span>prev_hash = table.hash(x <span class="kw">as </span>u32); |
| <span class="comment">// SAFETY: Hash values are guaranteed to be in bounds. |
| </span><span class="kw-2">*</span>table.get_unchecked_mut(prev_hash) = (<span class="self">self</span>.s - <span class="number">1</span>) <span class="kw">as </span>u16; |
| <span class="comment">// The lower 4 bytes of x>>8 correspond to |
| // self.src[self.s..self.s + 4]. |
| </span><span class="kw">let </span>cur_hash = table.hash((x >> <span class="number">8</span>) <span class="kw">as </span>u32); |
| <span class="comment">// SAFETY: Hash values are guaranteed to be in bounds. |
| </span>candidate = <span class="kw-2">*</span>table.get_unchecked(cur_hash) <span class="kw">as </span>usize; |
| <span class="kw-2">*</span>table.get_unchecked_mut(cur_hash) = <span class="self">self</span>.s <span class="kw">as </span>u16; |
| |
| <span class="comment">// SAFETY: candidate is set from table, which always |
| // contains valid positions in the current block. |
| </span><span class="kw">let </span>y = loadu32_le(srcp.offset(candidate <span class="kw">as </span>isize)); |
| <span class="kw">if </span>(x >> <span class="number">8</span>) <span class="kw">as </span>u32 != y { |
| <span class="comment">// If we didn't get a hit, update the next hash |
| // and move on. Our initial 8 byte read continues to |
| // pay off. |
| </span>next_hash = table.hash((x >> <span class="number">16</span>) <span class="kw">as </span>u32); |
| <span class="self">self</span>.s += <span class="number">1</span>; |
| <span class="kw">break</span>; |
| } |
| } |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Emits one or more copy operations with the given offset and length. |
| /// offset must be in the range [1, 65535] and len must be in the range |
| /// [4, 65535]. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>emit_copy(<span class="kw-2">&mut </span><span class="self">self</span>, offset: usize, <span class="kw-2">mut </span>len: usize) { |
| <span class="macro">debug_assert!</span>(<span class="number">1 </span><= offset && offset <= <span class="number">65535</span>); |
| <span class="comment">// Copy operations only allow lengths up to 64, but we'll allow bigger |
| // lengths and emit as many operations as we need. |
| // |
| // N.B. Since our block size is 64KB, we never actually emit a copy 4 |
| // operation. |
| </span><span class="macro">debug_assert!</span>(<span class="number">4 </span><= len && len <= <span class="number">65535</span>); |
| |
| <span class="comment">// Emit copy 2 operations until we don't have to. |
| // We check on 68 here and emit a shorter copy than 64 below because |
| // it is cheaper to, e.g., encode a length 67 copy as a length 60 |
| // copy 2 followed by a length 7 copy 1 than to encode it as a length |
| // 64 copy 2 followed by a length 3 copy 2. They key here is that a |
| // copy 1 operation requires at least length 4 which forces a length 3 |
| // copy to use a copy 2 operation. |
| </span><span class="kw">while </span>len >= <span class="number">68 </span>{ |
| <span class="self">self</span>.emit_copy2(offset, <span class="number">64</span>); |
| len -= <span class="number">64</span>; |
| } |
| <span class="kw">if </span>len > <span class="number">64 </span>{ |
| <span class="self">self</span>.emit_copy2(offset, <span class="number">60</span>); |
| len -= <span class="number">60</span>; |
| } |
| <span class="comment">// If we can squeeze the last copy into a copy 1 operation, do it. |
| </span><span class="kw">if </span>len <= <span class="number">11 </span>&& offset <= <span class="number">2047 </span>{ |
| <span class="self">self</span>.dst[<span class="self">self</span>.d] = |
| (((offset >> <span class="number">8</span>) <span class="kw">as </span>u8) << <span class="number">5</span>) |
| | (((len - <span class="number">4</span>) <span class="kw">as </span>u8) << <span class="number">2</span>) |
| | (Tag::Copy1 <span class="kw">as </span>u8); |
| <span class="self">self</span>.dst[<span class="self">self</span>.d + <span class="number">1</span>] = offset <span class="kw">as </span>u8; |
| <span class="self">self</span>.d += <span class="number">2</span>; |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.emit_copy2(offset, len); |
| } |
| } |
| |
| <span class="doccomment">/// Emits a "copy 2" operation with the given offset and length. The |
| /// offset and length must be valid for a copy 2 operation. i.e., offset |
| /// must be in the range [1, 65535] and len must be in the range [1, 64]. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>emit_copy2(<span class="kw-2">&mut </span><span class="self">self</span>, offset: usize, len: usize) { |
| <span class="macro">debug_assert!</span>(<span class="number">1 </span><= offset && offset <= <span class="number">65535</span>); |
| <span class="macro">debug_assert!</span>(<span class="number">1 </span><= len && len <= <span class="number">64</span>); |
| <span class="self">self</span>.dst[<span class="self">self</span>.d] = (((len - <span class="number">1</span>) <span class="kw">as </span>u8) << <span class="number">2</span>) | (Tag::Copy2 <span class="kw">as </span>u8); |
| LE::write_u16(<span class="kw-2">&mut </span><span class="self">self</span>.dst[<span class="self">self</span>.d + <span class="number">1</span>..], offset <span class="kw">as </span>u16); |
| <span class="self">self</span>.d += <span class="number">3</span>; |
| } |
| |
| <span class="doccomment">/// Attempts to extend a match from the current position in self.src with |
| /// the candidate position given. |
| /// |
| /// This method uses unaligned loads and elides bounds checks, so the |
| /// caller must guarantee that cand points to a valid location in self.src |
| /// and is less than the current position in src. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">unsafe fn </span>extend_match(<span class="kw-2">&mut </span><span class="self">self</span>, <span class="kw-2">mut </span>cand: usize) { |
| <span class="macro">debug_assert!</span>(cand < <span class="self">self</span>.s); |
| <span class="kw">while </span><span class="self">self</span>.s + <span class="number">8 </span><= <span class="self">self</span>.src.len() { |
| <span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr(); |
| <span class="comment">// SAFETY: The loop invariant guarantees that there is at least |
| // 8 bytes to read at self.src + self.s. Since cand must be |
| // guaranteed by the caller to be valid and less than self.s, it |
| // also has enough room to read 8 bytes. |
| // |
| // TODO(ag): Despite my best efforts, I couldn't get this to |
| // autovectorize with 128-bit loads. The logic after the loads |
| // appears to be a little too clever... |
| </span><span class="kw">let </span>x = loadu64(srcp.offset(<span class="self">self</span>.s <span class="kw">as </span>isize)); |
| <span class="kw">let </span>y = loadu64(srcp.offset(cand <span class="kw">as </span>isize)); |
| <span class="kw">if </span>x == y { |
| <span class="comment">// If all 8 bytes are equal, move on... |
| </span><span class="self">self</span>.s += <span class="number">8</span>; |
| cand += <span class="number">8</span>; |
| } <span class="kw">else </span>{ |
| <span class="comment">// Otherwise, find the last byte that was equal. We can do |
| // this efficiently by interpreted x/y as little endian |
| // numbers, which lets us use the number of trailing zeroes |
| // as a proxy for the number of equivalent bits (after an XOR). |
| </span><span class="kw">let </span>z = x.to_le() ^ y.to_le(); |
| <span class="self">self</span>.s += z.trailing_zeros() <span class="kw">as </span>usize / <span class="number">8</span>; |
| <span class="kw">return</span>; |
| } |
| } |
| <span class="comment">// When we have fewer than 8 bytes left in the block, fall back to the |
| // slow loop. |
| </span><span class="kw">while </span><span class="self">self</span>.s < <span class="self">self</span>.src.len() && <span class="self">self</span>.src[<span class="self">self</span>.s] == <span class="self">self</span>.src[cand] { |
| <span class="self">self</span>.s += <span class="number">1</span>; |
| cand += <span class="number">1</span>; |
| } |
| } |
| |
| <span class="doccomment">/// Executes any cleanup when the current block has finished compressing. |
| /// In particular, it emits any leftover bytes as a literal. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>done(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="kw">if </span><span class="self">self</span>.next_emit < <span class="self">self</span>.src.len() { |
| <span class="kw">let </span>lit_end = <span class="self">self</span>.src.len(); |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// SAFETY: Both next_emit and lit_end are trivially in bounds |
| // given the conditional and definition above. |
| </span><span class="self">self</span>.emit_literal(lit_end); |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Emits a literal from self.src[self.next_emit..lit_end]. |
| /// |
| /// This uses unaligned loads and elides bounds checks, so the caller must |
| /// guarantee that self.src[self.next_emit..lit_end] is valid. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">unsafe fn </span>emit_literal(<span class="kw-2">&mut </span><span class="self">self</span>, lit_end: usize) { |
| <span class="kw">let </span>lit_start = <span class="self">self</span>.next_emit; |
| <span class="kw">let </span>len = lit_end - lit_start; |
| <span class="kw">let </span>n = len.checked_sub(<span class="number">1</span>).unwrap(); |
| <span class="kw">if </span>n <= <span class="number">59 </span>{ |
| <span class="self">self</span>.dst[<span class="self">self</span>.d] = ((n <span class="kw">as </span>u8) << <span class="number">2</span>) | (Tag::Literal <span class="kw">as </span>u8); |
| <span class="self">self</span>.d += <span class="number">1</span>; |
| <span class="kw">if </span>len <= <span class="number">16 </span>&& lit_start + <span class="number">16 </span><= <span class="self">self</span>.src.len() { |
| <span class="comment">// SAFETY: lit_start is equivalent to self.next_emit, which |
| // is only set to self.s immediately proceeding a copy |
| // emit. The conditional above also ensures that there is at |
| // least 16 bytes of room in both src and dst. |
| // |
| // dst is big enough because the buffer is guaranteed to |
| // be big enough to hold biggest possible compressed size plus |
| // an extra 32 bytes, which exceeds the 16 byte copy here. |
| </span><span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr().offset(lit_start <span class="kw">as </span>isize); |
| <span class="kw">let </span>dstp = <span class="self">self</span>.dst.as_mut_ptr().offset(<span class="self">self</span>.d <span class="kw">as </span>isize); |
| ptr::copy_nonoverlapping(srcp, dstp, <span class="number">16</span>); |
| <span class="self">self</span>.d += len; |
| <span class="kw">return</span>; |
| } |
| } <span class="kw">else if </span>n < <span class="number">256 </span>{ |
| <span class="self">self</span>.dst[<span class="self">self</span>.d] = (<span class="number">60 </span><< <span class="number">2</span>) | (Tag::Literal <span class="kw">as </span>u8); |
| <span class="self">self</span>.dst[<span class="self">self</span>.d + <span class="number">1</span>] = n <span class="kw">as </span>u8; |
| <span class="self">self</span>.d += <span class="number">2</span>; |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.dst[<span class="self">self</span>.d] = (<span class="number">61 </span><< <span class="number">2</span>) | (Tag::Literal <span class="kw">as </span>u8); |
| LE::write_u16(<span class="kw-2">&mut </span><span class="self">self</span>.dst[<span class="self">self</span>.d + <span class="number">1</span>..], n <span class="kw">as </span>u16); |
| <span class="self">self</span>.d += <span class="number">3</span>; |
| } |
| <span class="comment">// SAFETY: lit_start is equivalent to self.next_emit, which |
| // is only set to self.s immediately proceeding a copy, which |
| // implies that it always points to valid bytes in self.src. |
| // |
| // We can't guarantee that there are at least len bytes though, |
| // which must be guaranteed by the caller and is why this method |
| // is unsafe. |
| </span><span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr().offset(lit_start <span class="kw">as </span>isize); |
| <span class="kw">let </span>dstp = <span class="self">self</span>.dst.as_mut_ptr().offset(<span class="self">self</span>.d <span class="kw">as </span>isize); |
| ptr::copy_nonoverlapping(srcp, dstp, len); |
| <span class="self">self</span>.d += len; |
| } |
| } |
| |
| <span class="doccomment">/// `BlockTable` is a map from 4 byte sequences to positions of their most |
| /// recent occurrence in a block. In particular, this table lets us quickly |
| /// find candidates for compression. |
| /// |
| /// We expose the `hash` method so that callers can be fastidious about the |
| /// number of times a hash is computed. |
| </span><span class="kw">struct </span>BlockTable<<span class="lifetime">'a</span>> { |
| table: <span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span>[u16], |
| <span class="doccomment">/// The number of bits required to shift the hash such that the result |
| /// is less than table.len(). |
| </span>shift: u32, |
| } |
| |
| <span class="kw">impl </span>Encoder { |
| <span class="kw">fn </span>block_table(<span class="kw-2">&mut </span><span class="self">self</span>, block_size: usize) -> BlockTable { |
| <span class="kw">let </span><span class="kw-2">mut </span>shift: u32 = <span class="number">32 </span>- <span class="number">8</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>table_size = <span class="number">256</span>; |
| <span class="kw">while </span>table_size < MAX_TABLE_SIZE && table_size < block_size { |
| shift -= <span class="number">1</span>; |
| table_size <span class="kw-2">*</span>= <span class="number">2</span>; |
| } |
| <span class="comment">// If our block size is small, then use a small stack allocated table |
| // instead of putting a bigger one on the heap. This particular |
| // optimization is important if the caller is using Snappy to compress |
| // many small blocks. (The memset savings alone is considerable.) |
| </span><span class="kw">let </span>table: <span class="kw-2">&mut </span>[u16] = |
| <span class="kw">if </span>table_size <= SMALL_TABLE_SIZE { |
| <span class="kw-2">&mut </span><span class="self">self</span>.small[<span class="number">0</span>..table_size] |
| } <span class="kw">else </span>{ |
| <span class="kw">if </span><span class="self">self</span>.big.is_empty() { |
| <span class="comment">// Interestingly, using `self.big.resize` here led to some |
| // very weird code getting generated that led to a large |
| // slow down. Forcing the issue with a new vec seems to |
| // fix it. ---AG |
| </span><span class="self">self</span>.big = <span class="macro">vec!</span>[<span class="number">0</span>; MAX_TABLE_SIZE]; |
| } |
| <span class="kw-2">&mut </span><span class="self">self</span>.big[<span class="number">0</span>..table_size] |
| }; |
| <span class="kw">for </span>x <span class="kw">in </span><span class="kw-2">&mut *</span>table { |
| <span class="kw-2">*</span>x = <span class="number">0</span>; |
| } |
| BlockTable { |
| table: table, |
| shift: shift, |
| } |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> BlockTable<<span class="lifetime">'a</span>> { |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>hash(<span class="kw-2">&</span><span class="self">self</span>, x: u32) -> usize { |
| (x.wrapping_mul(<span class="number">0x1E35A7BD</span>) >> <span class="self">self</span>.shift) <span class="kw">as </span>usize |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Deref <span class="kw">for </span>BlockTable<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Target = [u16]; |
| <span class="kw">fn </span>deref(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[u16] { <span class="self">self</span>.table } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> DerefMut <span class="kw">for </span>BlockTable<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>deref_mut(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw-2">&mut </span>[u16] { <span class="self">self</span>.table } |
| } |
| |
| <span class="kw">unsafe fn </span>loadu64(data: <span class="kw-2">*const </span>u8) -> u64 { |
| <span class="kw">let </span><span class="kw-2">mut </span>n: u64 = <span class="number">0</span>; |
| ptr::copy_nonoverlapping( |
| data, |
| <span class="kw-2">&mut </span>n <span class="kw">as </span><span class="kw-2">*mut </span>u64 <span class="kw">as </span><span class="kw-2">*mut </span>u8, |
| <span class="number">8</span>); |
| n |
| } |
| |
| <span class="kw">unsafe fn </span>loadu64_le(data: <span class="kw-2">*const </span>u8) -> u64 { |
| loadu64(data).to_le() |
| } |
| |
| <span class="kw">unsafe fn </span>loadu32(data: <span class="kw-2">*const </span>u8) -> u32 { |
| <span class="kw">let </span><span class="kw-2">mut </span>n: u32 = <span class="number">0</span>; |
| ptr::copy_nonoverlapping( |
| data, |
| <span class="kw-2">&mut </span>n <span class="kw">as </span><span class="kw-2">*mut </span>u32 <span class="kw">as </span><span class="kw-2">*mut </span>u8, |
| <span class="number">4</span>); |
| n |
| } |
| |
| <span class="kw">unsafe fn </span>loadu32_le(data: <span class="kw-2">*const </span>u8) -> u32 { |
| loadu32(data).to_le() |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="snap" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
