blob: aeb3b52fc4d2931e4f3a311626ff244b151403a8 [file] [log] [blame]
<!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/decompress.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>decompress.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>
</pre><pre class="rust"><code><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>tag;
<span class="kw">use </span>varint::read_varu64;
<span class="kw">use </span>MAX_INPUT_SIZE;
<span class="doccomment">/// A lookup table for quickly computing the various attributes derived from a
/// tag byte.
</span><span class="kw">const </span>TAG_LOOKUP_TABLE: TagLookupTable = TagLookupTable(tag::TAG_LOOKUP_TABLE);
<span class="doccomment">/// `WORD_MASK` is a map from the size of an integer in bytes to its
/// corresponding on a 32 bit integer. This is used when we need to read an
/// integer and we know there are at least 4 bytes to read from a buffer. In
/// this case, we can read a 32 bit little endian integer and mask out only the
/// bits we need. This in particular saves a branch.
</span><span class="kw">const </span>WORD_MASK: [usize; <span class="number">5</span>] = [<span class="number">0</span>, <span class="number">0xFF</span>, <span class="number">0xFFFF</span>, <span class="number">0xFFFFFF</span>, <span class="number">0xFFFFFFFF</span>];
<span class="doccomment">/// Returns the decompressed size (in bytes) of the compressed bytes given.
///
/// `input` must be a sequence of bytes returned by a conforming Snappy
/// compressor.
///
/// # Errors
///
/// This function returns an error in the following circumstances:
///
/// * An invalid Snappy header was seen.
/// * The total space required for decompression exceeds `2^32 - 1`.
</span><span class="kw">pub fn </span>decompress_len(input: <span class="kw-2">&amp;</span>[u8]) -&gt; <span class="prelude-ty">Result</span>&lt;usize&gt; {
<span class="kw">if </span>input.is_empty() {
<span class="kw">return </span><span class="prelude-val">Ok</span>(<span class="number">0</span>);
}
<span class="prelude-val">Ok</span>(<span class="macro">try!</span>(Header::read(input)).decompress_len)
}
<span class="doccomment">/// Decoder is a raw decoder for decompressing bytes in the Snappy format.
///
/// This decoder does not use the Snappy frame format and simply decompresses
/// the given bytes as if it were returned from `Encoder`.
///
/// Unless you explicitly need the low-level control, you should use
/// `Reader` instead, which decompresses the Snappy frame format.
</span><span class="attribute">#[derive(Clone, Debug, Default)]
</span><span class="kw">pub struct </span>Decoder {
<span class="comment">// Place holder for potential future fields.
</span>_dummy: (),
}
<span class="kw">impl </span>Decoder {
<span class="doccomment">/// Return a new decoder that can be used for decompressing bytes.
</span><span class="kw">pub fn </span>new() -&gt; Decoder {
Decoder { _dummy: () }
}
<span class="doccomment">/// Decompresses all bytes in `input` into `output`.
///
/// `input` must be a sequence of bytes returned by a conforming Snappy
/// compressor.
///
/// The size of `output` must be large enough to hold all decompressed
/// bytes from the `input`. The size required can be queried with the
/// `decompress_len` function.
///
/// On success, this returns the number of bytes written to `output`.
///
/// # Errors
///
/// This method returns an error in the following circumstances:
///
/// * Invalid compressed Snappy data was seen.
/// * The total space required for decompression exceeds `2^32 - 1`.
/// * `output` has length less than `decompress_len(input)`.
</span><span class="kw">pub fn </span>decompress(
<span class="kw-2">&amp;mut </span><span class="self">self</span>,
input: <span class="kw-2">&amp;</span>[u8],
output: <span class="kw-2">&amp;mut </span>[u8],
) -&gt; <span class="prelude-ty">Result</span>&lt;usize&gt; {
<span class="kw">if </span>input.is_empty() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::Empty);
}
<span class="kw">let </span>hdr = <span class="macro">try!</span>(Header::read(input));
<span class="kw">if </span>hdr.decompress_len &gt; output.len() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::BufferTooSmall {
given: output.len() <span class="kw">as </span>u64,
min: hdr.decompress_len <span class="kw">as </span>u64,
});
}
<span class="kw">let </span>dst = <span class="kw-2">&amp;mut </span>output[..hdr.decompress_len];
<span class="kw">let </span><span class="kw-2">mut </span>dec = Decompress {
src: <span class="kw-2">&amp;</span>input[hdr.len..],
s: <span class="number">0</span>,
dst: dst,
d: <span class="number">0</span>,
};
<span class="macro">try!</span>(dec.decompress());
<span class="prelude-val">Ok</span>(dec.dst.len())
}
<span class="doccomment">/// Decompresses all bytes in `input` into a freshly allocated `Vec`.
///
/// This is just like the `decompress` 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
/// `decompress` does.
</span><span class="kw">pub fn </span>decompress_vec(<span class="kw-2">&amp;mut </span><span class="self">self</span>, input: <span class="kw-2">&amp;</span>[u8]) -&gt; <span class="prelude-ty">Result</span>&lt;Vec&lt;u8&gt;&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>buf = <span class="macro">vec!</span>[<span class="number">0</span>; <span class="macro">try!</span>(decompress_len(input))];
<span class="kw">let </span>n = <span class="macro">try!</span>(<span class="self">self</span>.decompress(input, <span class="kw-2">&amp;mut </span>buf));
buf.truncate(n);
<span class="prelude-val">Ok</span>(buf)
}
}
<span class="doccomment">/// Decompress is the state of the Snappy compressor.
</span><span class="kw">struct </span>Decompress&lt;<span class="lifetime">&#39;s</span>, <span class="lifetime">&#39;d</span>&gt; {
<span class="doccomment">/// The original compressed bytes not including the header.
</span>src: <span class="kw-2">&amp;</span><span class="lifetime">&#39;s </span>[u8],
<span class="doccomment">/// The current position in the compressed bytes.
</span>s: usize,
<span class="doccomment">/// The output buffer to write the decompressed bytes.
</span>dst: <span class="kw-2">&amp;</span><span class="lifetime">&#39;d </span><span class="kw-2">mut </span>[u8],
<span class="doccomment">/// The current position in the decompressed buffer.
</span>d: usize,
}
<span class="kw">impl</span>&lt;<span class="lifetime">&#39;s</span>, <span class="lifetime">&#39;d</span>&gt; Decompress&lt;<span class="lifetime">&#39;s</span>, <span class="lifetime">&#39;d</span>&gt; {
<span class="doccomment">/// Decompresses snappy compressed bytes in `src` to `dst`.
///
/// This assumes that the header has already been read and that `dst` is
/// big enough to store all decompressed bytes.
</span><span class="kw">fn </span>decompress(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; <span class="prelude-ty">Result</span>&lt;()&gt; {
<span class="kw">while </span><span class="self">self</span>.s &lt; <span class="self">self</span>.src.len() {
<span class="kw">let </span>byte = <span class="self">self</span>.src[<span class="self">self</span>.s];
<span class="self">self</span>.s += <span class="number">1</span>;
<span class="kw">if </span>byte &amp; <span class="number">0b000000_11 </span>== <span class="number">0 </span>{
<span class="kw">let </span>len = (byte &gt;&gt; <span class="number">2</span>) <span class="kw">as </span>usize + <span class="number">1</span>;
<span class="macro">try!</span>(<span class="self">self</span>.read_literal(len));
} <span class="kw">else </span>{
<span class="macro">try!</span>(<span class="self">self</span>.read_copy(byte));
}
}
<span class="kw">if </span><span class="self">self</span>.d != <span class="self">self</span>.dst.len() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::HeaderMismatch {
expected_len: <span class="self">self</span>.dst.len() <span class="kw">as </span>u64,
got_len: <span class="self">self</span>.d <span class="kw">as </span>u64,
});
}
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Decompresses a literal from `src` starting at `s` to `dst` starting at
/// `d` and returns the updated values of `s` and `d`. `s` should point to
/// the byte immediately proceding the literal tag byte.
///
/// `len` is the length of the literal if it&#39;s &lt;=60. Otherwise, it&#39;s the
/// length tag, indicating the number of bytes needed to read a little
/// endian integer at `src[s..]`. i.e., `61 =&gt; 1 byte`, `62 =&gt; 2 bytes`,
/// `63 =&gt; 3 bytes` and `64 =&gt; 4 bytes`.
///
/// `len` must be &lt;=64.
</span><span class="attribute">#[inline(always)]
</span><span class="kw">fn </span>read_literal(
<span class="kw-2">&amp;mut </span><span class="self">self</span>,
len: usize,
) -&gt; <span class="prelude-ty">Result</span>&lt;()&gt; {
<span class="macro">debug_assert!</span>(len &lt;= <span class="number">64</span>);
<span class="kw">let </span><span class="kw-2">mut </span>len = len <span class="kw">as </span>u64;
<span class="comment">// As an optimization for the common case, if the literal length is
// &lt;=16 and we have enough room in both `src` and `dst`, copy the
// literal using unaligned loads and stores.
//
// We pick 16 bytes with the hope that it optimizes down to a 128 bit
// load/store.
</span><span class="kw">if </span>len &lt;= <span class="number">16
</span>&amp;&amp; <span class="self">self</span>.s + <span class="number">16 </span>&lt;= <span class="self">self</span>.src.len()
&amp;&amp; <span class="self">self</span>.d + <span class="number">16 </span>&lt;= <span class="self">self</span>.dst.len() {
<span class="kw">unsafe </span>{
<span class="comment">// SAFETY: We know both src and dst have at least 16 bytes of
// wiggle room after s/d, even if `len` is &lt;16, so the copy is
// safe.
</span><span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr().offset(<span class="self">self</span>.s <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);
<span class="comment">// Hopefully uses SIMD registers for 128 bit load/store.
</span>ptr::copy_nonoverlapping(srcp, dstp, <span class="number">16</span>);
}
<span class="self">self</span>.d += len <span class="kw">as </span>usize;
<span class="self">self</span>.s += len <span class="kw">as </span>usize;
<span class="kw">return </span><span class="prelude-val">Ok</span>(());
}
<span class="comment">// When the length is bigger than 60, it indicates that we need to read
// an additional 1-4 bytes to get the real length of the literal.
</span><span class="kw">if </span>len &gt;= <span class="number">61 </span>{
<span class="comment">// If there aren&#39;t at least 4 bytes left to read then we know this
// is corrupt because the literal must have length &gt;=61.
</span><span class="kw">if </span><span class="self">self</span>.s <span class="kw">as </span>u64 + <span class="number">4 </span>&gt; <span class="self">self</span>.src.len() <span class="kw">as </span>u64 {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::Literal {
len: <span class="number">4</span>,
src_len: (<span class="self">self</span>.src.len() - <span class="self">self</span>.s) <span class="kw">as </span>u64,
dst_len: (<span class="self">self</span>.dst.len() - <span class="self">self</span>.d) <span class="kw">as </span>u64,
});
}
<span class="comment">// Since we know there are 4 bytes left to read, read a 32 bit LE
// integer and mask away the bits we don&#39;t need.
</span><span class="kw">let </span>byte_count = len <span class="kw">as </span>usize - <span class="number">60</span>;
len = LE::read_u32(<span class="kw-2">&amp;</span><span class="self">self</span>.src[<span class="self">self</span>.s..]) <span class="kw">as </span>u64;
len = (len &amp; (WORD_MASK[byte_count] <span class="kw">as </span>u64)) + <span class="number">1</span>;
<span class="self">self</span>.s += byte_count;
}
<span class="comment">// If there&#39;s not enough buffer left to load or store this literal,
// then the input is corrupt.
// if self.s + len &gt; self.src.len() || self.d + len &gt; self.dst.len() {
</span><span class="kw">if </span>((<span class="self">self</span>.src.len() - <span class="self">self</span>.s) <span class="kw">as </span>u64) &lt; len
|| ((<span class="self">self</span>.dst.len() - <span class="self">self</span>.d) <span class="kw">as </span>u64) &lt; len {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::Literal {
len: len,
src_len: (<span class="self">self</span>.src.len() - <span class="self">self</span>.s) <span class="kw">as </span>u64,
dst_len: (<span class="self">self</span>.dst.len() - <span class="self">self</span>.d) <span class="kw">as </span>u64,
});
}
<span class="kw">unsafe </span>{
<span class="comment">// SAFETY: We&#39;ve already checked the bounds, so we know this copy
// is correct.
</span><span class="kw">let </span>srcp = <span class="self">self</span>.src.as_ptr().offset(<span class="self">self</span>.s <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="kw">as </span>usize);
}
<span class="self">self</span>.s += len <span class="kw">as </span>usize;
<span class="self">self</span>.d += len <span class="kw">as </span>usize;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Reads a copy from `src` and writes the decompressed bytes to `dst`. `s`
/// should point to the byte immediately proceding the copy tag byte.
</span><span class="attribute">#[inline(always)]
</span><span class="kw">fn </span>read_copy(
<span class="kw-2">&amp;mut </span><span class="self">self</span>,
tag_byte: u8,
) -&gt; <span class="prelude-ty">Result</span>&lt;()&gt; {
<span class="comment">// Find the copy offset and len, then advance the input past the copy.
// The rest of this function deals with reading/writing to output only.
</span><span class="kw">let </span>entry = TAG_LOOKUP_TABLE.entry(tag_byte);
<span class="kw">let </span>offset = <span class="macro">try!</span>(entry.offset(<span class="self">self</span>.src, <span class="self">self</span>.s));
<span class="kw">let </span>len = entry.len();
<span class="self">self</span>.s += entry.num_tag_bytes();
<span class="comment">// What we really care about here is whether `d == 0` or `d &lt; offset`.
// To save an extra branch, use `d &lt; offset - 1` instead. If `d` is
// `0`, then `offset.wrapping_sub(1)` will be usize::MAX which is also
// the max value of `d`.
</span><span class="kw">if </span><span class="self">self</span>.d &lt;= offset.wrapping_sub(<span class="number">1</span>) {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::Offset {
offset: offset <span class="kw">as </span>u64,
dst_pos: <span class="self">self</span>.d <span class="kw">as </span>u64,
});
}
<span class="comment">// When all is said and done, dst is advanced to end.
</span><span class="kw">let </span>end = <span class="self">self</span>.d + len;
<span class="comment">// When the copy is small and the offset is at least 8 bytes away from
// `d`, then we can decompress the copy with two 64 bit unaligned
// loads/stores.
</span><span class="kw">if </span>offset &gt;= <span class="number">8 </span>&amp;&amp; len &lt;= <span class="number">16 </span>&amp;&amp; <span class="self">self</span>.d + <span class="number">16 </span>&lt;= <span class="self">self</span>.dst.len() {
<span class="kw">unsafe </span>{
<span class="comment">// SAFETY: We know dstp points to at least 16 bytes of memory
// from the condition above, and we also know that dstp is
// preceded by at least `offset` bytes from the `d &lt;= offset`
// check above.
//
// We also know that dstp and dstp-8 do not overlap from the
// check above, justifying the use of copy_nonoverlapping.
</span><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);
<span class="kw">let </span>srcp = dstp.offset(-(offset <span class="kw">as </span>isize));
<span class="comment">// We can&#39;t do a single 16 byte load/store because src/dst may
// overlap with each other. Namely, the second copy here may
// copy bytes written in the first copy!
</span>ptr::copy_nonoverlapping(srcp, dstp, <span class="number">8</span>);
ptr::copy_nonoverlapping(srcp.offset(<span class="number">8</span>), dstp.offset(<span class="number">8</span>), <span class="number">8</span>);
}
<span class="comment">// If we have some wiggle room, try to decompress the copy 16 bytes
// at a time with 128 bit unaligned loads/stores. Remember, we can&#39;t
// just do a memcpy because decompressing copies may require copying
// overlapping memory.
//
// We need the extra wiggle room to make effective use of 128 bit
// loads/stores. Even if the store ends up copying more data than we
// need, we&#39;re careful to advance `d` by the correct amount at the end.
</span>} <span class="kw">else if </span>end + <span class="number">24 </span>&lt;= <span class="self">self</span>.dst.len() {
<span class="kw">unsafe </span>{
<span class="comment">// SAFETY: We know that dstp is preceded by at least `offset`
// bytes from the `d &lt;= offset` check above.
//
// We don&#39;t know whether dstp overlaps with srcp, so we start
// by copying from srcp to dstp until they no longer overlap.
// The worst case is when dstp-src = 3 and copy length = 1. The
// first loop will issue these copy operations before stopping:
//
// [-1, 14] -&gt; [0, 15]
// [-1, 14] -&gt; [3, 18]
// [-1, 14] -&gt; [9, 24]
//
// But the copy had length 1, so it was only supposed to write
// to [0, 0]. But the last copy wrote to [9, 24], which is 24
// extra bytes in dst *beyond* the end of the copy, which is
// guaranteed by the conditional above.
</span><span class="kw">let </span><span class="kw-2">mut </span>dstp = <span class="self">self</span>.dst.as_mut_ptr().offset(<span class="self">self</span>.d <span class="kw">as </span>isize);
<span class="kw">let </span><span class="kw-2">mut </span>srcp = dstp.offset(-(offset <span class="kw">as </span>isize));
<span class="kw">loop </span>{
<span class="kw">let </span>diff = (dstp <span class="kw">as </span>isize) - (srcp <span class="kw">as </span>isize);
<span class="kw">if </span>diff &gt;= <span class="number">16 </span>{
<span class="kw">break</span>;
}
<span class="comment">// srcp and dstp can overlap, so use ptr::copy.
</span><span class="macro">debug_assert!</span>(<span class="self">self</span>.d + <span class="number">16 </span>&lt;= <span class="self">self</span>.dst.len());
ptr::copy(srcp, dstp, <span class="number">16</span>);
<span class="self">self</span>.d += diff <span class="kw">as </span>usize;
dstp = dstp.offset(diff);
}
<span class="kw">while </span><span class="self">self</span>.d &lt; end {
ptr::copy_nonoverlapping(srcp, dstp, <span class="number">16</span>);
srcp = srcp.offset(<span class="number">16</span>);
dstp = dstp.offset(<span class="number">16</span>);
<span class="self">self</span>.d += <span class="number">16</span>;
}
<span class="comment">// At this point, `d` is likely wrong. We correct it before
// returning. It&#39;s correct value is `end`.
</span>}
} <span class="kw">else </span>{
<span class="kw">if </span>end &gt; <span class="self">self</span>.dst.len() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::CopyWrite {
len: len <span class="kw">as </span>u64,
dst_len: (<span class="self">self</span>.dst.len() - <span class="self">self</span>.d) <span class="kw">as </span>u64,
});
}
<span class="comment">// Finally, the slow byte-by-byte case, which should only be used
// for the last few bytes of decompression.
</span><span class="kw">while </span><span class="self">self</span>.d != end {
<span class="self">self</span>.dst[<span class="self">self</span>.d] = <span class="self">self</span>.dst[<span class="self">self</span>.d - offset];
<span class="self">self</span>.d += <span class="number">1</span>;
}
}
<span class="self">self</span>.d = end;
<span class="prelude-val">Ok</span>(())
}
}
<span class="doccomment">/// Header represents the single varint that starts every Snappy compressed
/// block.
</span><span class="attribute">#[derive(Debug)]
</span><span class="kw">struct </span>Header {
<span class="doccomment">/// The length of the header in bytes (i.e., the varint).
</span>len: usize,
<span class="doccomment">/// The length of the original decompressed input in bytes.
</span>decompress_len: usize,
}
<span class="kw">impl </span>Header {
<span class="doccomment">/// Reads the varint header from the given input.
///
/// If there was a problem reading the header then an error is returned.
/// If a header is returned then it is guaranteed to be valid.
</span><span class="attribute">#[inline(always)]
</span><span class="kw">fn </span>read(input: <span class="kw-2">&amp;</span>[u8]) -&gt; <span class="prelude-ty">Result</span>&lt;Header&gt; {
<span class="kw">let </span>(decompress_len, header_len) = read_varu64(input);
<span class="kw">if </span>header_len == <span class="number">0 </span>{
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::Header);
}
<span class="kw">if </span>decompress_len &gt; MAX_INPUT_SIZE {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::TooBig {
given: decompress_len <span class="kw">as </span>u64,
max: MAX_INPUT_SIZE,
});
}
<span class="prelude-val">Ok</span>(Header { len: header_len, decompress_len: decompress_len <span class="kw">as </span>usize })
}
}
<span class="doccomment">/// A lookup table for quickly computing the various attributes derived from
/// a tag byte. The attributes are most useful for the three &quot;copy&quot; tags
/// and include the length of the copy, part of the offset (for copy 1-byte
/// only) and the total number of bytes proceding the tag byte that encode
/// the other part of the offset (1 for copy 1, 2 for copy 2 and 4 for copy 4).
///
/// More specifically, the keys of the table are u8s and the values are u16s.
/// The bits of the values are laid out as follows:
///
/// xxaa abbb xxcc cccc
///
/// Where `a` is the number of bytes, `b` are the three bits of the offset
/// for copy 1 (the other 8 bits are in the byte proceding the tag byte; for
/// copy 2 and copy 4, `b = 0`), and `c` is the length of the copy (max of 64).
///
/// We could pack this in fewer bits, but the position of the three `b` bits
/// lines up with the most significant three bits in the total offset for copy
/// 1, which avoids an extra shift instruction.
///
/// In sum, this table is useful because it reduces branches and various
/// arithmetic operations.
</span><span class="kw">struct </span>TagLookupTable([u16; <span class="number">256</span>]);
<span class="kw">impl </span>TagLookupTable {
<span class="doccomment">/// Look up the tag entry given the tag `byte`.
</span><span class="attribute">#[inline(always)]
</span><span class="kw">fn </span>entry(<span class="kw-2">&amp;</span><span class="self">self</span>, byte: u8) -&gt; TagEntry {
TagEntry(<span class="self">self</span>.<span class="number">0</span>[byte <span class="kw">as </span>usize] <span class="kw">as </span>usize)
}
}
<span class="doccomment">/// Represents a single entry in the tag lookup table.
///
/// See the documentation in `TagLookupTable` for the bit layout.
///
/// The type is a `usize` for convenience.
</span><span class="kw">struct </span>TagEntry(usize);
<span class="kw">impl </span>TagEntry {
<span class="doccomment">/// Return the total number of bytes proceding this tag byte required to
/// encode the offset.
</span><span class="kw">fn </span>num_tag_bytes(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; usize {
<span class="self">self</span>.<span class="number">0 </span>&gt;&gt; <span class="number">11
</span>}
<span class="doccomment">/// Return the total copy length, capped at 64.
</span><span class="kw">fn </span>len(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; usize {
<span class="self">self</span>.<span class="number">0 </span>&amp; <span class="number">0xFF
</span>}
<span class="doccomment">/// Return the copy offset corresponding to this copy operation. `s` should
/// point to the position just after the tag byte that this entry was read
/// from.
///
/// This requires reading from the compressed input since the offset is
/// encoded in bytes proceding the tag byte.
</span><span class="kw">fn </span>offset(<span class="kw-2">&amp;</span><span class="self">self</span>, src: <span class="kw-2">&amp;</span>[u8], s: usize) -&gt; <span class="prelude-ty">Result</span>&lt;usize&gt; {
<span class="kw">let </span>num_tag_bytes = <span class="self">self</span>.num_tag_bytes();
<span class="kw">let </span>trailer =
<span class="comment">// It is critical for this case to come first, since it is the
// fast path. We really hope that this case gets branch
// predicted.
</span><span class="kw">if </span>s + <span class="number">4 </span>&lt;= src.len() {
<span class="kw">unsafe </span>{
<span class="comment">// SAFETY: The conditional above guarantees that
// src[s..s+4] is valid to read from.
</span><span class="kw">let </span>p = src.as_ptr().offset(s <span class="kw">as </span>isize);
<span class="comment">// We use WORD_MASK here to mask out the bits we don&#39;t
// need. While we&#39;re guaranteed to read 4 valid bytes,
// not all of those bytes are necessarily part of the
// offset. This is the key optimization: we don&#39;t need to
// branch on num_tag_bytes.
</span>loadu32_le(p) <span class="kw">as </span>usize &amp; WORD_MASK[num_tag_bytes]
}
} <span class="kw">else if </span>num_tag_bytes == <span class="number">1 </span>{
<span class="kw">if </span>s &gt;= src.len() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::CopyRead {
len: <span class="number">1</span>,
src_len: (src.len() - s) <span class="kw">as </span>u64,
});
}
src[s] <span class="kw">as </span>usize
} <span class="kw">else if </span>num_tag_bytes == <span class="number">2 </span>{
<span class="kw">if </span>s + <span class="number">1 </span>&gt;= src.len() {
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::CopyRead {
len: <span class="number">2</span>,
src_len: (src.len() - s) <span class="kw">as </span>u64,
});
}
LE::read_u16(<span class="kw-2">&amp;</span>src[s..]) <span class="kw">as </span>usize
} <span class="kw">else </span>{
<span class="kw">return </span><span class="prelude-val">Err</span>(Error::CopyRead {
len: num_tag_bytes <span class="kw">as </span>u64,
src_len: (src.len() - s) <span class="kw">as </span>u64,
});
};
<span class="prelude-val">Ok</span>((<span class="self">self</span>.<span class="number">0 </span>&amp; <span class="number">0b0000_0111_0000_0000</span>) | trailer)
}
}
<span class="doccomment">/// Loads a little endian encoded u32 from data.
///
/// This is unsafe because `data` must point to some memory of size at least 4.
</span><span class="attribute">#[inline(always)]
</span><span class="kw">unsafe fn </span>loadu32_le(data: <span class="kw-2">*const </span>u8) -&gt; 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">&amp;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.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>