| <!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/lib.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>lib.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> |
| <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> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| </pre><pre class="rust"><code><span class="attribute">#![warn(missing_docs)] |
| #![cfg_attr(all(feature = <span class="string">"unstable"</span>, test), feature(test))] |
| |
| </span><span class="doccomment">//! # `fastfield_codecs` |
| //! |
| //! - Columnar storage of data for tantivy [`Column`]. |
| //! - Encode data in different codecs. |
| //! - Monotonically map values to u64/u128 |
| |
| </span><span class="attribute">#[cfg(test)] |
| #[macro_use] |
| </span><span class="kw">extern crate </span>more_asserts; |
| |
| <span class="attribute">#[cfg(all(test, feature = <span class="string">"unstable"</span>))] |
| </span><span class="kw">extern crate </span>test; |
| |
| <span class="kw">use </span>std::io::Write; |
| <span class="kw">use </span>std::sync::Arc; |
| <span class="kw">use </span>std::{fmt, io}; |
| |
| <span class="kw">use </span>common::BinarySerializable; |
| <span class="kw">use </span>compact_space::CompactSpaceDecompressor; |
| <span class="kw">use </span>format_version::read_format_version; |
| <span class="kw">use </span>monotonic_mapping::{ |
| StrictlyMonotonicMappingInverter, StrictlyMonotonicMappingToInternal, |
| StrictlyMonotonicMappingToInternalBaseval, StrictlyMonotonicMappingToInternalGCDBaseval, |
| }; |
| <span class="kw">use </span>null_index_footer::read_null_index_footer; |
| <span class="kw">use </span>ownedbytes::OwnedBytes; |
| <span class="kw">use </span>serialize::{Header, U128Header}; |
| |
| <span class="kw">mod </span>bitpacked; |
| <span class="kw">mod </span>blockwise_linear; |
| <span class="kw">mod </span>compact_space; |
| <span class="kw">mod </span>format_version; |
| <span class="kw">mod </span>line; |
| <span class="kw">mod </span>linear; |
| <span class="kw">mod </span>monotonic_mapping; |
| <span class="kw">mod </span>monotonic_mapping_u128; |
| <span class="kw">mod </span>null_index_footer; |
| |
| <span class="kw">mod </span>column; |
| <span class="kw">mod </span>gcd; |
| <span class="kw">mod </span>serialize; |
| |
| <span class="kw">use </span><span class="self">self</span>::bitpacked::BitpackedCodec; |
| <span class="kw">use </span><span class="self">self</span>::blockwise_linear::BlockwiseLinearCodec; |
| <span class="kw">pub use </span><span class="self">self</span>::column::{monotonic_map_column, Column, IterColumn, VecColumn}; |
| <span class="kw">use </span><span class="self">self</span>::linear::LinearCodec; |
| <span class="kw">pub use </span><span class="self">self</span>::monotonic_mapping::{MonotonicallyMappableToU64, StrictlyMonotonicFn}; |
| <span class="kw">pub use </span><span class="self">self</span>::monotonic_mapping_u128::MonotonicallyMappableToU128; |
| <span class="kw">pub use </span><span class="self">self</span>::serialize::{ |
| estimate, serialize, serialize_and_load, serialize_u128, NormalizedHeader, |
| }; |
| |
| <span class="attribute">#[derive(PartialEq, Eq, PartialOrd, Ord, Debug, Clone, Copy)] |
| #[repr(u8)] |
| </span><span class="doccomment">/// Available codecs to use to encode the u64 (via [`MonotonicallyMappableToU64`]) converted data. |
| </span><span class="kw">pub enum </span>FastFieldCodecType { |
| <span class="doccomment">/// Bitpack all values in the value range. The number of bits is defined by the amplitude |
| /// `column.max_value() - column.min_value()` |
| </span>Bitpacked = <span class="number">1</span>, |
| <span class="doccomment">/// Linear interpolation puts a line between the first and last value and then bitpacks the |
| /// values by the offset from the line. The number of bits is defined by the max deviation from |
| /// the line. |
| </span>Linear = <span class="number">2</span>, |
| <span class="doccomment">/// Same as [`FastFieldCodecType::Linear`], but encodes in blocks of 512 elements. |
| </span>BlockwiseLinear = <span class="number">3</span>, |
| } |
| |
| <span class="kw">impl </span>BinarySerializable <span class="kw">for </span>FastFieldCodecType { |
| <span class="kw">fn </span>serialize<W: Write>(<span class="kw-2">&</span><span class="self">self</span>, wrt: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| <span class="self">self</span>.to_code().serialize(wrt) |
| } |
| |
| <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>code = u8::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="kw">let </span>codec_type: <span class="self">Self </span>= <span class="self">Self</span>::from_code(code) |
| .ok_or_else(|| io::Error::new(io::ErrorKind::InvalidData, <span class="string">"Unknown code `{code}.`"</span>))<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(codec_type) |
| } |
| } |
| |
| <span class="kw">impl </span>FastFieldCodecType { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>to_code(<span class="self">self</span>) -> u8 { |
| <span class="self">self </span><span class="kw">as </span>u8 |
| } |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>from_code(code: u8) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>> { |
| <span class="kw">match </span>code { |
| <span class="number">1 </span>=> <span class="prelude-val">Some</span>(<span class="self">Self</span>::Bitpacked), |
| <span class="number">2 </span>=> <span class="prelude-val">Some</span>(<span class="self">Self</span>::Linear), |
| <span class="number">3 </span>=> <span class="prelude-val">Some</span>(<span class="self">Self</span>::BlockwiseLinear), |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| } |
| |
| <span class="attribute">#[derive(PartialEq, Eq, PartialOrd, Ord, Debug, Clone, Copy)] |
| #[repr(u8)] |
| </span><span class="doccomment">/// Available codecs to use to encode the u128 (via [`MonotonicallyMappableToU128`]) converted data. |
| </span><span class="kw">pub enum </span>U128FastFieldCodecType { |
| <span class="doccomment">/// This codec takes a large number space (u128) and reduces it to a compact number space, by |
| /// removing the holes. |
| </span>CompactSpace = <span class="number">1</span>, |
| } |
| |
| <span class="kw">impl </span>BinarySerializable <span class="kw">for </span>U128FastFieldCodecType { |
| <span class="kw">fn </span>serialize<W: Write>(<span class="kw-2">&</span><span class="self">self</span>, wrt: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| <span class="self">self</span>.to_code().serialize(wrt) |
| } |
| |
| <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>code = u8::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="kw">let </span>codec_type: <span class="self">Self </span>= <span class="self">Self</span>::from_code(code) |
| .ok_or_else(|| io::Error::new(io::ErrorKind::InvalidData, <span class="string">"Unknown code `{code}.`"</span>))<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(codec_type) |
| } |
| } |
| |
| <span class="kw">impl </span>U128FastFieldCodecType { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>to_code(<span class="self">self</span>) -> u8 { |
| <span class="self">self </span><span class="kw">as </span>u8 |
| } |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>from_code(code: u8) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>> { |
| <span class="kw">match </span>code { |
| <span class="number">1 </span>=> <span class="prelude-val">Some</span>(<span class="self">Self</span>::CompactSpace), |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Returns the correct codec reader wrapped in the `Arc` for the data. |
| </span><span class="kw">pub fn </span>open_u128<Item: MonotonicallyMappableToU128 + fmt::Debug>( |
| bytes: OwnedBytes, |
| ) -> io::Result<Arc<<span class="kw">dyn </span>Column<Item>>> { |
| <span class="kw">let </span>(bytes, _format_version) = read_format_version(bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>(<span class="kw-2">mut </span>bytes, _null_index_footer) = read_null_index_footer(bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>header = U128Header::deserialize(<span class="kw-2">&mut </span>bytes)<span class="question-mark">?</span>; |
| <span class="macro">assert_eq!</span>(header.codec_type, U128FastFieldCodecType::CompactSpace); |
| <span class="kw">let </span>reader = CompactSpaceDecompressor::open(bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>inverted: StrictlyMonotonicMappingInverter<StrictlyMonotonicMappingToInternal<Item>> = |
| StrictlyMonotonicMappingToInternal::<Item>::new().into(); |
| <span class="prelude-val">Ok</span>(Arc::new(monotonic_map_column(reader, inverted))) |
| } |
| |
| <span class="doccomment">/// Returns the correct codec reader wrapped in the `Arc` for the data. |
| </span><span class="kw">pub fn </span>open<T: MonotonicallyMappableToU64 + fmt::Debug>( |
| bytes: OwnedBytes, |
| ) -> io::Result<Arc<<span class="kw">dyn </span>Column<T>>> { |
| <span class="kw">let </span>(bytes, _format_version) = read_format_version(bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>(<span class="kw-2">mut </span>bytes, _null_index_footer) = read_null_index_footer(bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>header = Header::deserialize(<span class="kw-2">&mut </span>bytes)<span class="question-mark">?</span>; |
| <span class="kw">match </span>header.codec_type { |
| FastFieldCodecType::Bitpacked => open_specific_codec::<BitpackedCodec, <span class="kw">_</span>>(bytes, <span class="kw-2">&</span>header), |
| FastFieldCodecType::Linear => open_specific_codec::<LinearCodec, <span class="kw">_</span>>(bytes, <span class="kw-2">&</span>header), |
| FastFieldCodecType::BlockwiseLinear => { |
| open_specific_codec::<BlockwiseLinearCodec, <span class="kw">_</span>>(bytes, <span class="kw-2">&</span>header) |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>open_specific_codec<C: FastFieldCodec, Item: MonotonicallyMappableToU64 + fmt::Debug>( |
| bytes: OwnedBytes, |
| header: <span class="kw-2">&</span>Header, |
| ) -> io::Result<Arc<<span class="kw">dyn </span>Column<Item>>> { |
| <span class="kw">let </span>normalized_header = header.normalized(); |
| <span class="kw">let </span>reader = C::open_from_bytes(bytes, normalized_header)<span class="question-mark">?</span>; |
| <span class="kw">let </span>min_value = header.min_value; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(gcd) = header.gcd { |
| <span class="kw">let </span>mapping = StrictlyMonotonicMappingInverter::from( |
| StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd.get(), min_value), |
| ); |
| <span class="prelude-val">Ok</span>(Arc::new(monotonic_map_column(reader, mapping))) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>mapping = StrictlyMonotonicMappingInverter::from( |
| StrictlyMonotonicMappingToInternalBaseval::new(min_value), |
| ); |
| <span class="prelude-val">Ok</span>(Arc::new(monotonic_map_column(reader, mapping))) |
| } |
| } |
| |
| <span class="doccomment">/// The FastFieldSerializerEstimate trait is required on all variants |
| /// of fast field compressions, to decide which one to choose. |
| </span><span class="kw">trait </span>FastFieldCodec: <span class="lifetime">'static </span>{ |
| <span class="doccomment">/// A codex needs to provide a unique name and id, which is |
| /// used for debugging and de/serialization. |
| </span><span class="kw">const </span>CODEC_TYPE: FastFieldCodecType; |
| |
| <span class="kw">type </span>Reader: Column<u64> + <span class="lifetime">'static</span>; |
| |
| <span class="doccomment">/// Reads the metadata and returns the CodecReader |
| </span><span class="kw">fn </span>open_from_bytes(bytes: OwnedBytes, header: NormalizedHeader) -> io::Result<<span class="self">Self</span>::Reader>; |
| |
| <span class="doccomment">/// Serializes the data using the serializer into write. |
| /// |
| /// The column iterator should be preferred over using column `get_val` method for |
| /// performance reasons. |
| </span><span class="kw">fn </span>serialize(column: <span class="kw-2">&</span><span class="kw">dyn </span>Column, write: <span class="kw-2">&mut </span><span class="kw">impl </span>Write) -> io::Result<()>; |
| |
| <span class="doccomment">/// Returns an estimate of the compression ratio. |
| /// If the codec is not applicable, returns `None`. |
| /// |
| /// The baseline is uncompressed 64bit data. |
| /// |
| /// It could make sense to also return a value representing |
| /// computational complexity. |
| </span><span class="kw">fn </span>estimate(column: <span class="kw-2">&</span><span class="kw">dyn </span>Column) -> <span class="prelude-ty">Option</span><f32>; |
| } |
| |
| <span class="doccomment">/// The list of all available codecs for u64 convertible data. |
| </span><span class="kw">pub const </span>ALL_CODEC_TYPES: [FastFieldCodecType; <span class="number">3</span>] = [ |
| FastFieldCodecType::Bitpacked, |
| FastFieldCodecType::BlockwiseLinear, |
| FastFieldCodecType::Linear, |
| ]; |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>proptest::prelude::<span class="kw-2">*</span>; |
| <span class="kw">use </span>proptest::strategy::Strategy; |
| <span class="kw">use </span>proptest::{prop_oneof, proptest}; |
| |
| <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>::linear::LinearCodec; |
| <span class="kw">use </span><span class="kw">crate</span>::serialize::Header; |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>create_and_validate<Codec: FastFieldCodec>( |
| data: <span class="kw-2">&</span>[u64], |
| name: <span class="kw-2">&</span>str, |
| ) -> <span class="prelude-ty">Option</span><(f32, f32)> { |
| <span class="kw">let </span>col = <span class="kw-2">&</span>VecColumn::from(data); |
| <span class="kw">let </span>header = Header::compute_header(col, <span class="kw-2">&</span>[Codec::CODEC_TYPE])<span class="question-mark">?</span>; |
| <span class="kw">let </span>normalized_col = header.normalize_column(col); |
| <span class="kw">let </span>estimation = Codec::estimate(<span class="kw-2">&</span>normalized_col)<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>out = Vec::new(); |
| <span class="kw">let </span>col = VecColumn::from(data); |
| serialize(col, <span class="kw-2">&mut </span>out, <span class="kw-2">&</span>[Codec::CODEC_TYPE]).unwrap(); |
| |
| <span class="kw">let </span>actual_compression = out.len() <span class="kw">as </span>f32 / (data.len() <span class="kw">as </span>f32 * <span class="number">8.0</span>); |
| |
| <span class="kw">let </span>reader = <span class="kw">crate</span>::open::<u64>(OwnedBytes::new(out)).unwrap(); |
| <span class="macro">assert_eq!</span>(reader.num_vals(), data.len() <span class="kw">as </span>u32); |
| <span class="kw">for </span>(doc, orig_val) <span class="kw">in </span>data.iter().copied().enumerate() { |
| <span class="kw">let </span>val = reader.get_val(doc <span class="kw">as </span>u32); |
| <span class="macro">assert_eq!</span>( |
| val, orig_val, |
| <span class="string">"val `{val}` does not match orig_val {orig_val:?}, in data set {name}, data \ |
| `{data:?}`"</span>, |
| ); |
| } |
| |
| <span class="kw">if </span>!data.is_empty() { |
| <span class="kw">let </span>test_rand_idx = rand::thread_rng().gen_range(<span class="number">0</span>..=data.len() - <span class="number">1</span>); |
| <span class="kw">let </span>expected_positions: Vec<u32> = data |
| .iter() |
| .enumerate() |
| .filter(|(<span class="kw">_</span>, el)| <span class="kw-2">**</span>el == data[test_rand_idx]) |
| .map(|(pos, <span class="kw">_</span>)| pos <span class="kw">as </span>u32) |
| .collect(); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| reader.get_docids_for_value_range( |
| data[test_rand_idx]..=data[test_rand_idx], |
| <span class="number">0</span>..data.len() <span class="kw">as </span>u32, |
| <span class="kw-2">&mut </span>positions, |
| ); |
| <span class="macro">assert_eq!</span>(expected_positions, positions); |
| } |
| <span class="prelude-val">Some</span>((estimation, actual_compression)) |
| } |
| |
| <span class="macro">proptest! </span>{ |
| <span class="attribute">#![proptest_config(ProptestConfig::with_cases(<span class="number">100</span>))] |
| |
| #[test] |
| </span><span class="kw">fn </span>test_proptest_small_bitpacked(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">10</span>)) { |
| create_and_validate::<BitpackedCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest bitpacked"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_proptest_small_linear(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">10</span>)) { |
| create_and_validate::<LinearCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest linearinterpol"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_proptest_small_blockwise_linear(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">10</span>)) { |
| create_and_validate::<BlockwiseLinearCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest multilinearinterpol"</span>); |
| } |
| } |
| |
| <span class="macro">proptest! </span>{ |
| <span class="attribute">#![proptest_config(ProptestConfig::with_cases(<span class="number">10</span>))] |
| |
| #[test] |
| </span><span class="kw">fn </span>test_proptest_large_bitpacked(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">6000</span>)) { |
| create_and_validate::<BitpackedCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest bitpacked"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_proptest_large_linear(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">6000</span>)) { |
| create_and_validate::<LinearCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest linearinterpol"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_proptest_large_blockwise_linear(data <span class="kw">in </span>proptest::collection::vec(num_strategy(), <span class="number">1</span>..<span class="number">6000</span>)) { |
| create_and_validate::<BlockwiseLinearCodec>(<span class="kw-2">&</span>data, <span class="string">"proptest multilinearinterpol"</span>); |
| } |
| } |
| |
| <span class="kw">fn </span>num_strategy() -> <span class="kw">impl </span>Strategy<Value = u64> { |
| <span class="macro">prop_oneof!</span>[ |
| <span class="number">1 </span>=> prop::num::u64::ANY.prop_map(|num| u64::MAX - (num % <span class="number">10</span>) ), |
| <span class="number">1 </span>=> prop::num::u64::ANY.prop_map(|num| num % <span class="number">10 </span>), |
| <span class="number">20 </span>=> prop::num::u64::ANY, |
| ] |
| } |
| |
| <span class="kw">pub fn </span>get_codec_test_datasets() -> Vec<(Vec<u64>, <span class="kw-2">&</span><span class="lifetime">'static </span>str)> { |
| <span class="kw">let </span><span class="kw-2">mut </span>data_and_names = <span class="macro">vec!</span>[]; |
| |
| <span class="kw">let </span>data = <span class="macro">vec!</span>[<span class="number">10</span>]; |
| data_and_names.push((data, <span class="string">"minimal test"</span>)); |
| |
| <span class="kw">let </span>data = (<span class="number">10</span>..=<span class="number">10_000_u64</span>).collect::<Vec<<span class="kw">_</span>>>(); |
| data_and_names.push((data, <span class="string">"simple monotonically increasing"</span>)); |
| |
| data_and_names.push(( |
| <span class="macro">vec!</span>[<span class="number">5</span>, <span class="number">6</span>, <span class="number">7</span>, <span class="number">8</span>, <span class="number">9</span>, <span class="number">10</span>, <span class="number">99</span>, <span class="number">100</span>], |
| <span class="string">"offset in linear interpol"</span>, |
| )); |
| |
| data_and_names.push((<span class="macro">vec!</span>[<span class="number">3</span>, <span class="number">18446744073709551613</span>, <span class="number">5</span>], <span class="string">"docid range regression"</span>)); |
| |
| data_and_names.push((<span class="macro">vec!</span>[<span class="number">5</span>, <span class="number">50</span>, <span class="number">3</span>, <span class="number">13</span>, <span class="number">1</span>, <span class="number">1000</span>, <span class="number">35</span>], <span class="string">"rand small"</span>)); |
| data_and_names.push((<span class="macro">vec!</span>[<span class="number">10</span>], <span class="string">"single value"</span>)); |
| |
| data_and_names.push(( |
| <span class="macro">vec!</span>[<span class="number">1572656989877777</span>, <span class="number">1170935903116329</span>, <span class="number">720575940379279</span>, <span class="number">0</span>], |
| <span class="string">"overflow error"</span>, |
| )); |
| |
| data_and_names |
| } |
| |
| <span class="kw">fn </span>test_codec<C: FastFieldCodec>() { |
| <span class="kw">let </span>codec_name = <span class="macro">format!</span>(<span class="string">"{:?}"</span>, C::CODEC_TYPE); |
| <span class="kw">for </span>(data, dataset_name) <span class="kw">in </span>get_codec_test_datasets() { |
| <span class="kw">let </span>estimate_actual_opt: <span class="prelude-ty">Option</span><(f32, f32)> = |
| <span class="kw">crate</span>::tests::create_and_validate::<C>(<span class="kw-2">&</span>data, dataset_name); |
| <span class="kw">let </span>result = <span class="kw">if let </span><span class="prelude-val">Some</span>((estimate, actual)) = estimate_actual_opt { |
| <span class="macro">format!</span>(<span class="string">"Estimate `{estimate}` Actual `{actual}`"</span>) |
| } <span class="kw">else </span>{ |
| <span class="string">"Disabled"</span>.to_string() |
| }; |
| <span class="macro">println!</span>(<span class="string">"Codec {codec_name}, DataSet {dataset_name}, {result}"</span>); |
| } |
| } |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_codec_bitpacking() { |
| test_codec::<BitpackedCodec>(); |
| } |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_codec_interpolation() { |
| test_codec::<LinearCodec>(); |
| } |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_codec_multi_interpolation() { |
| test_codec::<BlockwiseLinearCodec>(); |
| } |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>estimation_good_interpolation_case() { |
| <span class="kw">let </span>data = (<span class="number">10</span>..=<span class="number">20000_u64</span>).collect::<Vec<<span class="kw">_</span>>>(); |
| <span class="kw">let </span>data: VecColumn = data.as_slice().into(); |
| |
| <span class="kw">let </span>linear_interpol_estimation = LinearCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_le!</span>(linear_interpol_estimation, <span class="number">0.01</span>); |
| |
| <span class="kw">let </span>multi_linear_interpol_estimation = BlockwiseLinearCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_le!</span>(multi_linear_interpol_estimation, <span class="number">0.2</span>); |
| <span class="macro">assert_lt!</span>(linear_interpol_estimation, multi_linear_interpol_estimation); |
| |
| <span class="kw">let </span>bitpacked_estimation = BitpackedCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_lt!</span>(linear_interpol_estimation, bitpacked_estimation); |
| } |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>estimation_test_bad_interpolation_case() { |
| <span class="kw">let </span>data: <span class="kw-2">&</span>[u64] = <span class="kw-2">&</span>[<span class="number">200</span>, <span class="number">10</span>, <span class="number">10</span>, <span class="number">10</span>, <span class="number">10</span>, <span class="number">1000</span>, <span class="number">20</span>]; |
| |
| <span class="kw">let </span>data: VecColumn = data.into(); |
| <span class="kw">let </span>linear_interpol_estimation = LinearCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_le!</span>(linear_interpol_estimation, <span class="number">0.34</span>); |
| |
| <span class="kw">let </span>bitpacked_estimation = BitpackedCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_lt!</span>(bitpacked_estimation, linear_interpol_estimation); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>estimation_prefer_bitpacked() { |
| <span class="kw">let </span>data = VecColumn::from(<span class="kw-2">&</span>[<span class="number">10</span>, <span class="number">10</span>, <span class="number">10</span>, <span class="number">10</span>]); |
| <span class="kw">let </span>linear_interpol_estimation = LinearCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="kw">let </span>bitpacked_estimation = BitpackedCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_lt!</span>(bitpacked_estimation, linear_interpol_estimation); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>estimation_test_bad_interpolation_case_monotonically_increasing() { |
| <span class="kw">let </span><span class="kw-2">mut </span>data: Vec<u64> = (<span class="number">201</span>..=<span class="number">20000_u64</span>).collect(); |
| data.push(<span class="number">1_000_000</span>); |
| <span class="kw">let </span>data: VecColumn = data.as_slice().into(); |
| |
| <span class="comment">// in this case the linear interpolation can't in fact not be worse than bitpacking, |
| // but the estimator adds some threshold, which leads to estimated worse behavior |
| </span><span class="kw">let </span>linear_interpol_estimation = LinearCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_le!</span>(linear_interpol_estimation, <span class="number">0.35</span>); |
| |
| <span class="kw">let </span>bitpacked_estimation = BitpackedCodec::estimate(<span class="kw-2">&</span>data).unwrap(); |
| <span class="macro">assert_le!</span>(bitpacked_estimation, <span class="number">0.32</span>); |
| <span class="macro">assert_le!</span>(bitpacked_estimation, linear_interpol_estimation); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_fast_field_codec_type_to_code() { |
| <span class="kw">let </span><span class="kw-2">mut </span>count_codec = <span class="number">0</span>; |
| <span class="kw">for </span>code <span class="kw">in </span><span class="number">0</span>..=<span class="number">255 </span>{ |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(codec_type) = FastFieldCodecType::from_code(code) { |
| <span class="macro">assert_eq!</span>(codec_type.to_code(), code); |
| count_codec += <span class="number">1</span>; |
| } |
| } |
| <span class="macro">assert_eq!</span>(count_codec, <span class="number">3</span>); |
| } |
| } |
| |
| <span class="attribute">#[cfg(all(test, feature = <span class="string">"unstable"</span>))] |
| </span><span class="kw">mod </span>bench { |
| <span class="kw">use </span>std::sync::Arc; |
| |
| <span class="kw">use </span>ownedbytes::OwnedBytes; |
| <span class="kw">use </span>rand::rngs::StdRng; |
| <span class="kw">use </span>rand::{Rng, SeedableRng}; |
| <span class="kw">use </span>test::{<span class="self">self</span>, Bencher}; |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::Column; |
| |
| <span class="kw">fn </span>get_data() -> Vec<u64> { |
| <span class="kw">let </span><span class="kw-2">mut </span>rng = StdRng::seed_from_u64(<span class="number">2u64</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>data: Vec<<span class="kw">_</span>> = (<span class="number">100</span>..<span class="number">55000_u64</span>) |
| .map(|num| num + rng.gen::<u8>() <span class="kw">as </span>u64) |
| .collect(); |
| data.push(<span class="number">99_000</span>); |
| data.insert(<span class="number">1000</span>, <span class="number">2000</span>); |
| data.insert(<span class="number">2000</span>, <span class="number">100</span>); |
| data.insert(<span class="number">3000</span>, <span class="number">4100</span>); |
| data.insert(<span class="number">4000</span>, <span class="number">100</span>); |
| data.insert(<span class="number">5000</span>, <span class="number">800</span>); |
| data |
| } |
| |
| <span class="attribute">#[inline(never)] |
| </span><span class="kw">fn </span>value_iter() -> <span class="kw">impl </span>Iterator<Item = u64> { |
| <span class="number">0</span>..<span class="number">20_000 |
| </span>} |
| <span class="kw">fn </span>get_reader_for_bench<Codec: FastFieldCodec>(data: <span class="kw-2">&</span>[u64]) -> Codec::Reader { |
| <span class="kw">let </span><span class="kw-2">mut </span>bytes = Vec::new(); |
| <span class="kw">let </span>min_value = <span class="kw-2">*</span>data.iter().min().unwrap(); |
| <span class="kw">let </span>data = data.iter().map(|el| <span class="kw-2">*</span>el - min_value).collect::<Vec<<span class="kw">_</span>>>(); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>data); |
| <span class="kw">let </span>normalized_header = <span class="kw">crate</span>::NormalizedHeader { |
| num_vals: col.num_vals(), |
| max_value: col.max_value(), |
| }; |
| Codec::serialize(<span class="kw-2">&</span>VecColumn::from(<span class="kw-2">&</span>data), <span class="kw-2">&mut </span>bytes).unwrap(); |
| Codec::open_from_bytes(OwnedBytes::new(bytes), normalized_header).unwrap() |
| } |
| <span class="kw">fn </span>bench_get<Codec: FastFieldCodec>(b: <span class="kw-2">&mut </span>Bencher, data: <span class="kw-2">&</span>[u64]) { |
| <span class="kw">let </span>col = get_reader_for_bench::<Codec>(data); |
| b.iter(|| { |
| <span class="kw">let </span><span class="kw-2">mut </span>sum = <span class="number">0u64</span>; |
| <span class="kw">for </span>pos <span class="kw">in </span>value_iter() { |
| <span class="kw">let </span>val = col.get_val(pos <span class="kw">as </span>u32); |
| sum = sum.wrapping_add(val); |
| } |
| sum |
| }); |
| } |
| |
| <span class="attribute">#[inline(never)] |
| </span><span class="kw">fn </span>bench_get_dynamic_helper(b: <span class="kw-2">&mut </span>Bencher, col: Arc<<span class="kw">dyn </span>Column>) { |
| b.iter(|| { |
| <span class="kw">let </span><span class="kw-2">mut </span>sum = <span class="number">0u64</span>; |
| <span class="kw">for </span>pos <span class="kw">in </span>value_iter() { |
| <span class="kw">let </span>val = col.get_val(pos <span class="kw">as </span>u32); |
| sum = sum.wrapping_add(val); |
| } |
| sum |
| }); |
| } |
| |
| <span class="kw">fn </span>bench_get_dynamic<Codec: FastFieldCodec>(b: <span class="kw-2">&mut </span>Bencher, data: <span class="kw-2">&</span>[u64]) { |
| <span class="kw">let </span>col = Arc::new(get_reader_for_bench::<Codec>(data)); |
| bench_get_dynamic_helper(b, col); |
| } |
| <span class="kw">fn </span>bench_create<Codec: FastFieldCodec>(b: <span class="kw-2">&mut </span>Bencher, data: <span class="kw-2">&</span>[u64]) { |
| <span class="kw">let </span>min_value = <span class="kw-2">*</span>data.iter().min().unwrap(); |
| <span class="kw">let </span>data = data.iter().map(|el| <span class="kw-2">*</span>el - min_value).collect::<Vec<<span class="kw">_</span>>>(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>bytes = Vec::new(); |
| b.iter(|| { |
| bytes.clear(); |
| Codec::serialize(<span class="kw-2">&</span>VecColumn::from(<span class="kw-2">&</span>data), <span class="kw-2">&mut </span>bytes).unwrap(); |
| }); |
| } |
| |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_bitpack_create(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_create::<BitpackedCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_linearinterpol_create(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_create::<LinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_multilinearinterpol_create(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_create::<BlockwiseLinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_bitpack_get(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get::<BitpackedCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_bitpack_get_dynamic(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get_dynamic::<BitpackedCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_linearinterpol_get(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get::<LinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_linearinterpol_get_dynamic(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get_dynamic::<LinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_multilinearinterpol_get(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get::<BlockwiseLinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_fastfield_multilinearinterpol_get_dynamic(b: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>data: Vec<<span class="kw">_</span>> = get_data(); |
| bench_get_dynamic::<BlockwiseLinearCodec>(b, <span class="kw-2">&</span>data); |
| } |
| } |
| </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> |