| <!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/git/checkouts/tantivy-65d0bbbddbbd5d02/433372d/fastfield_codecs/src/serialize.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>serialize.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="../../fastfield_codecs/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="../../fastfield_codecs/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> |
| </pre><pre class="rust"><code><span class="comment">// Copyright (C) 2022 Quickwit, Inc. |
| // |
| // Quickwit is offered under the AGPL v3.0 and as commercial software. |
| // For commercial licensing, contact us at hello@quickwit.io. |
| // |
| // AGPL: |
| // This program is free software: you can redistribute it and/or modify |
| // it under the terms of the GNU Affero General Public License as |
| // published by the Free Software Foundation, either version 3 of the |
| // License, or (at your option) any later version. |
| // |
| // This program is distributed in the hope that it will be useful, |
| // but WITHOUT ANY WARRANTY; without even the implied warranty of |
| // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| // GNU Affero General Public License for more details. |
| // |
| // You should have received a copy of the GNU Affero General Public License |
| // along with this program. If not, see <http://www.gnu.org/licenses/>. |
| |
| </span><span class="kw">use </span>std::num::NonZeroU64; |
| <span class="kw">use </span>std::sync::Arc; |
| <span class="kw">use </span>std::{fmt, io}; |
| |
| <span class="kw">use </span>common::{BinarySerializable, VInt}; |
| <span class="kw">use </span>log::warn; |
| <span class="kw">use </span>ownedbytes::OwnedBytes; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::bitpacked::BitpackedCodec; |
| <span class="kw">use </span><span class="kw">crate</span>::blockwise_linear::BlockwiseLinearCodec; |
| <span class="kw">use </span><span class="kw">crate</span>::compact_space::CompactSpaceCompressor; |
| <span class="kw">use </span><span class="kw">crate</span>::format_version::append_format_version; |
| <span class="kw">use </span><span class="kw">crate</span>::linear::LinearCodec; |
| <span class="kw">use </span><span class="kw">crate</span>::monotonic_mapping::{ |
| StrictlyMonotonicFn, StrictlyMonotonicMappingToInternal, |
| StrictlyMonotonicMappingToInternalGCDBaseval, |
| }; |
| <span class="kw">use </span><span class="kw">crate</span>::null_index_footer::{ |
| append_null_index_footer, FastFieldCardinality, NullIndexCodec, NullIndexFooter, |
| }; |
| <span class="kw">use crate</span>::{ |
| monotonic_map_column, Column, FastFieldCodec, FastFieldCodecType, MonotonicallyMappableToU64, |
| U128FastFieldCodecType, VecColumn, ALL_CODEC_TYPES, |
| }; |
| |
| <span class="doccomment">/// The normalized header gives some parameters after applying the following |
| /// normalization of the vector: |
| /// `val -> (val - min_value) / gcd` |
| /// |
| /// By design, after normalization, `min_value = 0` and `gcd = 1`. |
| </span><span class="attribute">#[derive(Debug, Copy, Clone)] |
| </span><span class="kw">pub struct </span>NormalizedHeader { |
| <span class="doccomment">/// The number of values in the underlying column. |
| </span><span class="kw">pub </span>num_vals: u32, |
| <span class="doccomment">/// The max value of the underlying column. |
| </span><span class="kw">pub </span>max_value: u64, |
| } |
| |
| <span class="attribute">#[derive(Debug, Copy, Clone)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Header { |
| <span class="kw">pub </span>num_vals: u32, |
| <span class="kw">pub </span>min_value: u64, |
| <span class="kw">pub </span>max_value: u64, |
| <span class="kw">pub </span>gcd: <span class="prelude-ty">Option</span><NonZeroU64>, |
| <span class="kw">pub </span>codec_type: FastFieldCodecType, |
| } |
| |
| <span class="kw">impl </span>Header { |
| <span class="kw">pub fn </span>normalized(<span class="self">self</span>) -> NormalizedHeader { |
| <span class="kw">let </span>gcd = <span class="self">self</span>.gcd.map(|gcd| gcd.get()).unwrap_or(<span class="number">1</span>); |
| <span class="kw">let </span>gcd_min_val_mapping = |
| StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd, <span class="self">self</span>.min_value); |
| |
| <span class="kw">let </span>max_value = gcd_min_val_mapping.mapping(<span class="self">self</span>.max_value); |
| NormalizedHeader { |
| num_vals: <span class="self">self</span>.num_vals, |
| max_value, |
| } |
| } |
| |
| <span class="kw">pub fn </span>normalize_column<C: Column>(<span class="kw-2">&</span><span class="self">self</span>, from_column: C) -> <span class="kw">impl </span>Column { |
| normalize_column(from_column, <span class="self">self</span>.min_value, <span class="self">self</span>.gcd) |
| } |
| |
| <span class="kw">pub fn </span>compute_header( |
| column: <span class="kw">impl </span>Column<u64>, |
| codecs: <span class="kw-2">&</span>[FastFieldCodecType], |
| ) -> <span class="prelude-ty">Option</span><Header> { |
| <span class="kw">let </span>num_vals = column.num_vals(); |
| <span class="kw">let </span>min_value = column.min_value(); |
| <span class="kw">let </span>max_value = column.max_value(); |
| <span class="kw">let </span>gcd = <span class="kw">crate</span>::gcd::find_gcd(column.iter().map(|val| val - min_value)) |
| .filter(|gcd| gcd.get() > <span class="number">1u64</span>); |
| <span class="kw">let </span>normalized_column = normalize_column(column, min_value, gcd); |
| <span class="kw">let </span>codec_type = detect_codec(normalized_column, codecs)<span class="question-mark">?</span>; |
| <span class="prelude-val">Some</span>(Header { |
| num_vals, |
| min_value, |
| max_value, |
| gcd, |
| codec_type, |
| }) |
| } |
| } |
| |
| <span class="attribute">#[derive(Debug, Copy, Clone, PartialEq, Eq)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>U128Header { |
| <span class="kw">pub </span>num_vals: u32, |
| <span class="kw">pub </span>codec_type: U128FastFieldCodecType, |
| } |
| |
| <span class="kw">impl </span>BinarySerializable <span class="kw">for </span>U128Header { |
| <span class="kw">fn </span>serialize<W: io::Write>(<span class="kw-2">&</span><span class="self">self</span>, writer: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| VInt(<span class="self">self</span>.num_vals <span class="kw">as </span>u64).serialize(writer)<span class="question-mark">?</span>; |
| <span class="self">self</span>.codec_type.serialize(writer)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>deserialize<R: io::Read>(reader: <span class="kw-2">&mut </span>R) -> io::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>num_vals = VInt::deserialize(reader)<span class="question-mark">?</span>.<span class="number">0 </span><span class="kw">as </span>u32; |
| <span class="kw">let </span>codec_type = U128FastFieldCodecType::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(U128Header { |
| num_vals, |
| codec_type, |
| }) |
| } |
| } |
| |
| <span class="kw">pub fn </span>normalize_column<C: Column>( |
| from_column: C, |
| min_value: u64, |
| gcd: <span class="prelude-ty">Option</span><NonZeroU64>, |
| ) -> <span class="kw">impl </span>Column { |
| <span class="kw">let </span>gcd = gcd.map(|gcd| gcd.get()).unwrap_or(<span class="number">1</span>); |
| <span class="kw">let </span>mapping = StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd, min_value); |
| monotonic_map_column(from_column, mapping) |
| } |
| |
| <span class="kw">impl </span>BinarySerializable <span class="kw">for </span>Header { |
| <span class="kw">fn </span>serialize<W: io::Write>(<span class="kw-2">&</span><span class="self">self</span>, writer: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| VInt(<span class="self">self</span>.num_vals <span class="kw">as </span>u64).serialize(writer)<span class="question-mark">?</span>; |
| VInt(<span class="self">self</span>.min_value).serialize(writer)<span class="question-mark">?</span>; |
| VInt(<span class="self">self</span>.max_value - <span class="self">self</span>.min_value).serialize(writer)<span class="question-mark">?</span>; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(gcd) = <span class="self">self</span>.gcd { |
| VInt(gcd.get()).serialize(writer)<span class="question-mark">?</span>; |
| } <span class="kw">else </span>{ |
| VInt(<span class="number">0u64</span>).serialize(writer)<span class="question-mark">?</span>; |
| } |
| <span class="self">self</span>.codec_type.serialize(writer)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>deserialize<R: io::Read>(reader: <span class="kw-2">&mut </span>R) -> io::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>num_vals = VInt::deserialize(reader)<span class="question-mark">?</span>.<span class="number">0 </span><span class="kw">as </span>u32; |
| <span class="kw">let </span>min_value = VInt::deserialize(reader)<span class="question-mark">?</span>.<span class="number">0</span>; |
| <span class="kw">let </span>amplitude = VInt::deserialize(reader)<span class="question-mark">?</span>.<span class="number">0</span>; |
| <span class="kw">let </span>max_value = min_value + amplitude; |
| <span class="kw">let </span>gcd_u64 = VInt::deserialize(reader)<span class="question-mark">?</span>.<span class="number">0</span>; |
| <span class="kw">let </span>codec_type = FastFieldCodecType::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(Header { |
| num_vals, |
| min_value, |
| max_value, |
| gcd: NonZeroU64::new(gcd_u64), |
| codec_type, |
| }) |
| } |
| } |
| |
| <span class="doccomment">/// Return estimated compression for given codec in the value range [0.0..1.0], where 1.0 means no |
| /// compression. |
| </span><span class="kw">pub fn </span>estimate<T: MonotonicallyMappableToU64 + fmt::Debug>( |
| typed_column: <span class="kw">impl </span>Column<T>, |
| codec_type: FastFieldCodecType, |
| ) -> <span class="prelude-ty">Option</span><f32> { |
| <span class="kw">let </span>column = monotonic_map_column(typed_column, StrictlyMonotonicMappingToInternal::<T>::new()); |
| <span class="kw">let </span>min_value = column.min_value(); |
| <span class="kw">let </span>gcd = <span class="kw">crate</span>::gcd::find_gcd(column.iter().map(|val| val - min_value)) |
| .filter(|gcd| gcd.get() > <span class="number">1u64</span>); |
| <span class="kw">let </span>mapping = StrictlyMonotonicMappingToInternalGCDBaseval::new( |
| gcd.map(|gcd| gcd.get()).unwrap_or(<span class="number">1u64</span>), |
| min_value, |
| ); |
| <span class="kw">let </span>normalized_column = monotonic_map_column(<span class="kw-2">&</span>column, mapping); |
| <span class="kw">match </span>codec_type { |
| FastFieldCodecType::Bitpacked => BitpackedCodec::estimate(<span class="kw-2">&</span>normalized_column), |
| FastFieldCodecType::Linear => LinearCodec::estimate(<span class="kw-2">&</span>normalized_column), |
| FastFieldCodecType::BlockwiseLinear => BlockwiseLinearCodec::estimate(<span class="kw-2">&</span>normalized_column), |
| } |
| } |
| |
| <span class="doccomment">/// Serializes u128 values with the compact space codec. |
| </span><span class="kw">pub fn </span>serialize_u128<F: Fn() -> I, I: Iterator<Item = u128>>( |
| iter_gen: F, |
| num_vals: u32, |
| output: <span class="kw-2">&mut </span><span class="kw">impl </span>io::Write, |
| ) -> io::Result<()> { |
| <span class="kw">let </span>header = U128Header { |
| num_vals, |
| codec_type: U128FastFieldCodecType::CompactSpace, |
| }; |
| header.serialize(output)<span class="question-mark">?</span>; |
| <span class="kw">let </span>compressor = CompactSpaceCompressor::train_from(iter_gen(), num_vals); |
| compressor.compress_into(iter_gen(), output).unwrap(); |
| |
| <span class="kw">let </span>null_index_footer = NullIndexFooter { |
| cardinality: FastFieldCardinality::Single, |
| null_index_codec: NullIndexCodec::Full, |
| null_index_byte_range: <span class="number">0</span>..<span class="number">0</span>, |
| }; |
| append_null_index_footer(output, null_index_footer)<span class="question-mark">?</span>; |
| append_format_version(output)<span class="question-mark">?</span>; |
| |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Serializes the column with the codec with the best estimate on the data. |
| </span><span class="kw">pub fn </span>serialize<T: MonotonicallyMappableToU64 + fmt::Debug>( |
| typed_column: <span class="kw">impl </span>Column<T>, |
| output: <span class="kw-2">&mut </span><span class="kw">impl </span>io::Write, |
| codecs: <span class="kw-2">&</span>[FastFieldCodecType], |
| ) -> io::Result<()> { |
| <span class="kw">let </span>column = monotonic_map_column(typed_column, StrictlyMonotonicMappingToInternal::<T>::new()); |
| <span class="kw">let </span>header = Header::compute_header(<span class="kw-2">&</span>column, codecs).ok_or_else(|| { |
| io::Error::new( |
| io::ErrorKind::InvalidInput, |
| <span class="macro">format!</span>( |
| <span class="string">"Data cannot be serialized with this list of codec. {:?}"</span>, |
| codecs |
| ), |
| ) |
| })<span class="question-mark">?</span>; |
| header.serialize(output)<span class="question-mark">?</span>; |
| <span class="kw">let </span>normalized_column = header.normalize_column(column); |
| <span class="macro">assert_eq!</span>(normalized_column.min_value(), <span class="number">0u64</span>); |
| serialize_given_codec(normalized_column, header.codec_type, output)<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>null_index_footer = NullIndexFooter { |
| cardinality: FastFieldCardinality::Single, |
| null_index_codec: NullIndexCodec::Full, |
| null_index_byte_range: <span class="number">0</span>..<span class="number">0</span>, |
| }; |
| append_null_index_footer(output, null_index_footer)<span class="question-mark">?</span>; |
| append_format_version(output)<span class="question-mark">?</span>; |
| |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>detect_codec( |
| column: <span class="kw">impl </span>Column<u64>, |
| codecs: <span class="kw-2">&</span>[FastFieldCodecType], |
| ) -> <span class="prelude-ty">Option</span><FastFieldCodecType> { |
| <span class="kw">let </span><span class="kw-2">mut </span>estimations = Vec::new(); |
| <span class="kw">for </span><span class="kw-2">&</span>codec <span class="kw">in </span>codecs { |
| <span class="kw">let </span>estimation_opt = <span class="kw">match </span>codec { |
| FastFieldCodecType::Bitpacked => BitpackedCodec::estimate(<span class="kw-2">&</span>column), |
| FastFieldCodecType::Linear => LinearCodec::estimate(<span class="kw-2">&</span>column), |
| FastFieldCodecType::BlockwiseLinear => BlockwiseLinearCodec::estimate(<span class="kw-2">&</span>column), |
| }; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(estimation) = estimation_opt { |
| estimations.push((estimation, codec)); |
| } |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(broken_estimation) = estimations.iter().find(|estimation| estimation.<span class="number">0</span>.is_nan()) { |
| <span class="macro">warn!</span>( |
| <span class="string">"broken estimation for fast field codec {:?}"</span>, |
| broken_estimation.<span class="number">1 |
| </span>); |
| } |
| <span class="comment">// removing nan values for codecs with broken calculations, and max values which disables |
| // codecs |
| </span>estimations.retain(|estimation| !estimation.<span class="number">0</span>.is_nan() && estimation.<span class="number">0 </span>!= f32::MAX); |
| estimations.sort_by(|(score_left, <span class="kw">_</span>), (score_right, <span class="kw">_</span>)| score_left.total_cmp(score_right)); |
| <span class="prelude-val">Some</span>(estimations.first()<span class="question-mark">?</span>.<span class="number">1</span>) |
| } |
| |
| <span class="kw">fn </span>serialize_given_codec( |
| column: <span class="kw">impl </span>Column<u64>, |
| codec_type: FastFieldCodecType, |
| output: <span class="kw-2">&mut </span><span class="kw">impl </span>io::Write, |
| ) -> io::Result<()> { |
| <span class="kw">match </span>codec_type { |
| FastFieldCodecType::Bitpacked => { |
| BitpackedCodec::serialize(<span class="kw-2">&</span>column, output)<span class="question-mark">?</span>; |
| } |
| FastFieldCodecType::Linear => { |
| LinearCodec::serialize(<span class="kw-2">&</span>column, output)<span class="question-mark">?</span>; |
| } |
| FastFieldCodecType::BlockwiseLinear => { |
| BlockwiseLinearCodec::serialize(<span class="kw-2">&</span>column, output)<span class="question-mark">?</span>; |
| } |
| } |
| output.flush()<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Helper function to serialize a column (autodetect from all codecs) and then open it |
| </span><span class="kw">pub fn </span>serialize_and_load<T: MonotonicallyMappableToU64 + Ord + Default + fmt::Debug>( |
| column: <span class="kw-2">&</span>[T], |
| ) -> Arc<<span class="kw">dyn </span>Column<T>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| <span class="kw">super</span>::serialize(VecColumn::from(<span class="kw-2">&</span>column), <span class="kw-2">&mut </span>buffer, <span class="kw-2">&</span>ALL_CODEC_TYPES).unwrap(); |
| <span class="kw">super</span>::open(OwnedBytes::new(buffer)).unwrap() |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_serialize_deserialize_u128_header() { |
| <span class="kw">let </span>original = U128Header { |
| num_vals: <span class="number">11</span>, |
| codec_type: U128FastFieldCodecType::CompactSpace, |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>out = Vec::new(); |
| original.serialize(<span class="kw-2">&mut </span>out).unwrap(); |
| <span class="kw">let </span>restored = U128Header::deserialize(<span class="kw-2">&mut &</span>out[..]).unwrap(); |
| <span class="macro">assert_eq!</span>(restored, original); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_serialize_deserialize() { |
| <span class="kw">let </span>original = [<span class="number">1u64</span>, <span class="number">5u64</span>, <span class="number">10u64</span>]; |
| <span class="kw">let </span>restored: Vec<u64> = serialize_and_load(<span class="kw-2">&</span>original[..]).iter().collect(); |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>restored, <span class="kw-2">&</span>original[..]); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_fastfield_bool_size_bitwidth_1() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>[<span class="bool-val">false</span>, <span class="bool-val">true</span>][..]); |
| serialize(col, <span class="kw-2">&mut </span>buffer, <span class="kw-2">&</span>ALL_CODEC_TYPES).unwrap(); |
| <span class="comment">// 5 bytes of header, 1 byte of value, 7 bytes of padding. |
| </span><span class="macro">assert_eq!</span>(buffer.len(), <span class="number">3 </span>+ <span class="number">5 </span>+ <span class="number">8 </span>+ <span class="number">4 </span>+ <span class="number">2</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_fastfield_bool_bit_size_bitwidth_0() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>[<span class="bool-val">true</span>][..]); |
| serialize(col, <span class="kw-2">&mut </span>buffer, <span class="kw-2">&</span>ALL_CODEC_TYPES).unwrap(); |
| <span class="comment">// 5 bytes of header, 0 bytes of value, 7 bytes of padding. |
| </span><span class="macro">assert_eq!</span>(buffer.len(), <span class="number">3 </span>+ <span class="number">5 </span>+ <span class="number">7 </span>+ <span class="number">4 </span>+ <span class="number">2</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_fastfield_gcd() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| <span class="kw">let </span>vals: Vec<u64> = (<span class="number">0</span>..<span class="number">80</span>).map(|val| (val % <span class="number">7</span>) * <span class="number">1_000u64</span>).collect(); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>vals[..]); |
| serialize(col, <span class="kw-2">&mut </span>buffer, <span class="kw-2">&</span>[FastFieldCodecType::Bitpacked]).unwrap(); |
| <span class="comment">// Values are stored over 3 bits. |
| </span><span class="macro">assert_eq!</span>(buffer.len(), <span class="number">3 </span>+ <span class="number">7 </span>+ (<span class="number">3 </span>* <span class="number">80 </span>/ <span class="number">8</span>) + <span class="number">7 </span>+ <span class="number">4 </span>+ <span class="number">2</span>); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="fastfield_codecs" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |