| <!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/src/query/union.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>union.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="../../../tantivy/index.html"><div class="logo-container"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy/index.html"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" 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> |
| </pre><pre class="rust"><code><span class="kw">use </span>common::TinySet; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::docset::{DocSet, TERMINATED}; |
| <span class="kw">use </span><span class="kw">crate</span>::query::score_combiner::{DoNothingCombiner, ScoreCombiner}; |
| <span class="kw">use </span><span class="kw">crate</span>::query::Scorer; |
| <span class="kw">use crate</span>::{DocId, Score}; |
| |
| <span class="kw">const </span>HORIZON_NUM_TINYBITSETS: usize = <span class="number">64</span>; |
| <span class="kw">const </span>HORIZON: u32 = <span class="number">64u32 </span>* HORIZON_NUM_TINYBITSETS <span class="kw">as </span>u32; |
| |
| <span class="comment">// `drain_filter` is not stable yet. |
| // This function is similar except that it does is not unstable, and |
| // it does not keep the original vector ordering. |
| // |
| // Also, it does not "yield" any elements. |
| </span><span class="kw">fn </span>unordered_drain_filter<T, P>(v: <span class="kw-2">&mut </span>Vec<T>, <span class="kw-2">mut </span>predicate: P) |
| <span class="kw">where </span>P: FnMut(<span class="kw-2">&mut </span>T) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>i = <span class="number">0</span>; |
| <span class="kw">while </span>i < v.len() { |
| <span class="kw">if </span>predicate(<span class="kw-2">&mut </span>v[i]) { |
| v.swap_remove(i); |
| } <span class="kw">else </span>{ |
| i += <span class="number">1</span>; |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Creates a `DocSet` that iterate through the union of two or more `DocSet`s. |
| </span><span class="kw">pub struct </span>Union<TScorer, TScoreCombiner = DoNothingCombiner> { |
| docsets: Vec<TScorer>, |
| bitsets: Box<[TinySet; HORIZON_NUM_TINYBITSETS]>, |
| scores: Box<[TScoreCombiner; HORIZON <span class="kw">as </span>usize]>, |
| cursor: usize, |
| offset: DocId, |
| doc: DocId, |
| score: Score, |
| } |
| |
| <span class="kw">fn </span>refill<TScorer: Scorer, TScoreCombiner: ScoreCombiner>( |
| scorers: <span class="kw-2">&mut </span>Vec<TScorer>, |
| bitsets: <span class="kw-2">&mut </span>[TinySet; HORIZON_NUM_TINYBITSETS], |
| score_combiner: <span class="kw-2">&mut </span>[TScoreCombiner; HORIZON <span class="kw">as </span>usize], |
| min_doc: DocId, |
| ) { |
| unordered_drain_filter(scorers, |scorer| { |
| <span class="kw">let </span>horizon = min_doc + HORIZON <span class="kw">as </span>u32; |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>doc = scorer.doc(); |
| <span class="kw">if </span>doc >= horizon { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="comment">// add this document |
| </span><span class="kw">let </span>delta = doc - min_doc; |
| bitsets[(delta / <span class="number">64</span>) <span class="kw">as </span>usize].insert_mut(delta % <span class="number">64u32</span>); |
| score_combiner[delta <span class="kw">as </span>usize].update(scorer); |
| <span class="kw">if </span>scorer.advance() == TERMINATED { |
| <span class="comment">// remove the docset, it has been entirely consumed. |
| </span><span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| } |
| }); |
| } |
| |
| <span class="kw">impl</span><TScorer: Scorer, TScoreCombiner: ScoreCombiner> Union<TScorer, TScoreCombiner> { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>build( |
| docsets: Vec<TScorer>, |
| score_combiner_fn: <span class="kw">impl </span>FnOnce() -> TScoreCombiner, |
| ) -> Union<TScorer, TScoreCombiner> { |
| <span class="kw">let </span>non_empty_docsets: Vec<TScorer> = docsets |
| .into_iter() |
| .filter(|docset| docset.doc() != TERMINATED) |
| .collect(); |
| <span class="kw">let </span><span class="kw-2">mut </span>union = Union { |
| docsets: non_empty_docsets, |
| bitsets: Box::new([TinySet::empty(); HORIZON_NUM_TINYBITSETS]), |
| scores: Box::new([score_combiner_fn(); HORIZON <span class="kw">as </span>usize]), |
| cursor: HORIZON_NUM_TINYBITSETS, |
| offset: <span class="number">0</span>, |
| doc: <span class="number">0</span>, |
| score: <span class="number">0.0</span>, |
| }; |
| <span class="kw">if </span>union.refill() { |
| union.advance(); |
| } <span class="kw">else </span>{ |
| union.doc = TERMINATED; |
| } |
| union |
| } |
| |
| <span class="kw">fn </span>refill(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(min_doc) = <span class="self">self</span>.docsets.iter().map(DocSet::doc).min() { |
| <span class="self">self</span>.offset = min_doc; |
| <span class="self">self</span>.cursor = <span class="number">0</span>; |
| <span class="self">self</span>.doc = min_doc; |
| refill( |
| <span class="kw-2">&mut </span><span class="self">self</span>.docsets, |
| <span class="kw-2">&mut </span><span class="self">self</span>.bitsets, |
| <span class="kw-2">&mut </span><span class="self">self</span>.scores, |
| min_doc, |
| ); |
| <span class="bool-val">true |
| </span>} <span class="kw">else </span>{ |
| <span class="bool-val">false |
| </span>} |
| } |
| |
| <span class="kw">fn </span>advance_buffered(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="kw">while </span><span class="self">self</span>.cursor < HORIZON_NUM_TINYBITSETS { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(val) = <span class="self">self</span>.bitsets[<span class="self">self</span>.cursor].pop_lowest() { |
| <span class="kw">let </span>delta = val + (<span class="self">self</span>.cursor <span class="kw">as </span>u32) * <span class="number">64</span>; |
| <span class="self">self</span>.doc = <span class="self">self</span>.offset + delta; |
| <span class="kw">let </span>score_combiner = <span class="kw-2">&mut </span><span class="self">self</span>.scores[delta <span class="kw">as </span>usize]; |
| <span class="self">self</span>.score = score_combiner.score(); |
| score_combiner.clear(); |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.cursor += <span class="number">1</span>; |
| } |
| } |
| <span class="bool-val">false |
| </span>} |
| } |
| |
| <span class="kw">impl</span><TScorer, TScoreCombiner> DocSet <span class="kw">for </span>Union<TScorer, TScoreCombiner> |
| <span class="kw">where |
| </span>TScorer: Scorer, |
| TScoreCombiner: ScoreCombiner, |
| { |
| <span class="kw">fn </span>advance(<span class="kw-2">&mut </span><span class="self">self</span>) -> DocId { |
| <span class="kw">if </span><span class="self">self</span>.advance_buffered() { |
| <span class="kw">return </span><span class="self">self</span>.doc; |
| } |
| <span class="kw">if </span>!<span class="self">self</span>.refill() { |
| <span class="self">self</span>.doc = TERMINATED; |
| <span class="kw">return </span>TERMINATED; |
| } |
| <span class="kw">if </span>!<span class="self">self</span>.advance_buffered() { |
| <span class="kw">return </span>TERMINATED; |
| } |
| <span class="self">self</span>.doc |
| } |
| |
| <span class="kw">fn </span>seek(<span class="kw-2">&mut </span><span class="self">self</span>, target: DocId) -> DocId { |
| <span class="kw">if </span><span class="self">self</span>.doc >= target { |
| <span class="kw">return </span><span class="self">self</span>.doc; |
| } |
| <span class="kw">let </span>gap = target - <span class="self">self</span>.offset; |
| <span class="kw">if </span>gap < HORIZON { |
| <span class="comment">// Our value is within the buffered horizon. |
| |
| // Skipping to corresponding bucket. |
| </span><span class="kw">let </span>new_cursor = gap <span class="kw">as </span>usize / <span class="number">64</span>; |
| <span class="kw">for </span>obsolete_tinyset <span class="kw">in </span><span class="kw-2">&mut </span><span class="self">self</span>.bitsets[<span class="self">self</span>.cursor..new_cursor] { |
| obsolete_tinyset.clear(); |
| } |
| <span class="kw">for </span>score_combiner <span class="kw">in </span><span class="kw-2">&mut </span><span class="self">self</span>.scores[<span class="self">self</span>.cursor * <span class="number">64</span>..new_cursor * <span class="number">64</span>] { |
| score_combiner.clear(); |
| } |
| <span class="self">self</span>.cursor = new_cursor; |
| |
| <span class="comment">// Advancing until we reach the end of the bucket |
| // or we reach a doc greater or equal to the target. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>doc = <span class="self">self</span>.doc(); |
| <span class="kw">while </span>doc < target { |
| doc = <span class="self">self</span>.advance(); |
| } |
| doc |
| } <span class="kw">else </span>{ |
| <span class="comment">// clear the buffered info. |
| </span><span class="kw">for </span>obsolete_tinyset <span class="kw">in </span><span class="self">self</span>.bitsets.iter_mut() { |
| <span class="kw-2">*</span>obsolete_tinyset = TinySet::empty(); |
| } |
| <span class="kw">for </span>score_combiner <span class="kw">in </span><span class="self">self</span>.scores.iter_mut() { |
| score_combiner.clear(); |
| } |
| |
| <span class="comment">// The target is outside of the buffered horizon. |
| // advance all docsets to a doc >= to the target. |
| </span>unordered_drain_filter(<span class="kw-2">&mut </span><span class="self">self</span>.docsets, |docset| { |
| <span class="kw">if </span>docset.doc() < target { |
| docset.seek(target); |
| } |
| docset.doc() == TERMINATED |
| }); |
| |
| <span class="comment">// at this point all of the docsets |
| // are positioned on a doc >= to the target. |
| </span><span class="kw">if </span>!<span class="self">self</span>.refill() { |
| <span class="self">self</span>.doc = TERMINATED; |
| <span class="kw">return </span>TERMINATED; |
| } |
| <span class="self">self</span>.advance() |
| } |
| } |
| |
| <span class="comment">// TODO Also implement `count` with deletes efficiently. |
| |
| </span><span class="kw">fn </span>doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.doc |
| } |
| |
| <span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.docsets |
| .iter() |
| .map(|docset| docset.size_hint()) |
| .max() |
| .unwrap_or(<span class="number">0u32</span>) |
| } |
| |
| <span class="kw">fn </span>count_including_deleted(<span class="kw-2">&mut </span><span class="self">self</span>) -> u32 { |
| <span class="kw">if </span><span class="self">self</span>.doc == TERMINATED { |
| <span class="kw">return </span><span class="number">0</span>; |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>count = <span class="self">self</span>.bitsets[<span class="self">self</span>.cursor..HORIZON_NUM_TINYBITSETS] |
| .iter() |
| .map(|bitset| bitset.len()) |
| .sum::<u32>() |
| + <span class="number">1</span>; |
| <span class="kw">for </span>bitset <span class="kw">in </span><span class="self">self</span>.bitsets.iter_mut() { |
| bitset.clear(); |
| } |
| <span class="kw">while </span><span class="self">self</span>.refill() { |
| count += <span class="self">self</span>.bitsets.iter().map(|bitset| bitset.len()).sum::<u32>(); |
| <span class="kw">for </span>bitset <span class="kw">in </span><span class="self">self</span>.bitsets.iter_mut() { |
| bitset.clear(); |
| } |
| } |
| <span class="self">self</span>.cursor = HORIZON_NUM_TINYBITSETS; |
| count |
| } |
| } |
| |
| <span class="kw">impl</span><TScorer, TScoreCombiner> Scorer <span class="kw">for </span>Union<TScorer, TScoreCombiner> |
| <span class="kw">where |
| </span>TScoreCombiner: ScoreCombiner, |
| TScorer: Scorer, |
| { |
| <span class="kw">fn </span>score(<span class="kw-2">&mut </span><span class="self">self</span>) -> Score { |
| <span class="self">self</span>.score |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>std::collections::BTreeSet; |
| |
| <span class="kw">use super</span>::{Union, HORIZON}; |
| <span class="kw">use </span><span class="kw">crate</span>::docset::{DocSet, TERMINATED}; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::tests::test_skip_against_unoptimized; |
| <span class="kw">use </span><span class="kw">crate</span>::query::score_combiner::DoNothingCombiner; |
| <span class="kw">use </span><span class="kw">crate</span>::query::{ConstScorer, VecDocSet}; |
| <span class="kw">use crate</span>::{tests, DocId}; |
| |
| <span class="kw">fn </span>aux_test_union(vals: Vec<Vec<u32>>) { |
| <span class="kw">let </span><span class="kw-2">mut </span>val_set: BTreeSet<u32> = BTreeSet::new(); |
| <span class="kw">for </span>vs <span class="kw">in </span><span class="kw-2">&</span>vals { |
| <span class="kw">for </span><span class="kw-2">&</span>v <span class="kw">in </span>vs { |
| val_set.insert(v); |
| } |
| } |
| <span class="kw">let </span>union_vals: Vec<u32> = val_set.into_iter().collect(); |
| <span class="kw">let </span><span class="kw-2">mut </span>union_expected = VecDocSet::from(union_vals); |
| <span class="kw">let </span>make_union = || { |
| Union::build( |
| vals.iter() |
| .cloned() |
| .map(VecDocSet::from) |
| .map(|docset| ConstScorer::new(docset, <span class="number">1.0</span>)) |
| .collect::<Vec<ConstScorer<VecDocSet>>>(), |
| DoNothingCombiner::default, |
| ) |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span><span class="kw">union</span>: Union<<span class="kw">_</span>, DoNothingCombiner> = make_union(); |
| <span class="kw">let </span><span class="kw-2">mut </span>count = <span class="number">0</span>; |
| <span class="kw">while </span>union.doc() != TERMINATED { |
| <span class="macro">assert_eq!</span>(union_expected.doc(), union.doc()); |
| <span class="macro">assert_eq!</span>(union_expected.advance(), union.advance()); |
| count += <span class="number">1</span>; |
| } |
| <span class="macro">assert_eq!</span>(union_expected.advance(), TERMINATED); |
| <span class="macro">assert_eq!</span>(count, make_union().count_including_deleted()); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union() { |
| aux_test_union(<span class="macro">vec!</span>[ |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3333</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[], |
| ]); |
| aux_test_union(<span class="macro">vec!</span>[ |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3333</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">100000000u32</span>], |
| <span class="macro">vec!</span>[], |
| ]); |
| aux_test_union(<span class="macro">vec!</span>[ |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.01</span>, <span class="number">1</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.05</span>, <span class="number">2</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.001</span>, <span class="number">3</span>), |
| ]); |
| } |
| |
| <span class="kw">fn </span>test_aux_union_skip(docs_list: <span class="kw-2">&</span>[Vec<DocId>], skip_targets: Vec<DocId>) { |
| <span class="kw">let </span><span class="kw-2">mut </span>btree_set = BTreeSet::new(); |
| <span class="kw">for </span>docs <span class="kw">in </span>docs_list { |
| btree_set.extend(docs.iter().cloned()); |
| } |
| <span class="kw">let </span>docset_factory = || { |
| <span class="kw">let </span>res: Box<<span class="kw">dyn </span>DocSet> = Box::new(Union::build( |
| docs_list |
| .iter() |
| .cloned() |
| .map(VecDocSet::from) |
| .map(|docset| ConstScorer::new(docset, <span class="number">1.0</span>)) |
| .collect::<Vec<<span class="kw">_</span>>>(), |
| DoNothingCombiner::default, |
| )); |
| res |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>docset = docset_factory(); |
| <span class="kw">for </span>el <span class="kw">in </span>btree_set { |
| <span class="macro">assert_eq!</span>(el, docset.doc()); |
| docset.advance(); |
| } |
| <span class="macro">assert_eq!</span>(docset.doc(), TERMINATED); |
| test_skip_against_unoptimized(docset_factory, skip_targets); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union_skip_corner_case() { |
| test_aux_union_skip(<span class="kw-2">&</span>[<span class="macro">vec!</span>[<span class="number">165132</span>, <span class="number">167382</span>], <span class="macro">vec!</span>[<span class="number">25029</span>, <span class="number">25091</span>]], <span class="macro">vec!</span>[<span class="number">25029</span>]); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union_skip_corner_case2() { |
| test_aux_union_skip( |
| <span class="kw-2">&</span>[<span class="macro">vec!</span>[<span class="number">1u32</span>, <span class="number">1u32 </span>+ HORIZON], <span class="macro">vec!</span>[<span class="number">2u32</span>, <span class="number">1000u32</span>, <span class="number">10_000u32</span>]], |
| <span class="macro">vec!</span>[<span class="number">0u32</span>, <span class="number">1u32</span>, <span class="number">2u32</span>, <span class="number">3u32</span>, <span class="number">1u32 </span>+ HORIZON, <span class="number">2u32 </span>+ HORIZON], |
| ); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union_skip_corner_case3() { |
| <span class="kw">let </span><span class="kw-2">mut </span>docset = Union::build( |
| <span class="macro">vec!</span>[ |
| ConstScorer::from(VecDocSet::from(<span class="macro">vec!</span>[<span class="number">0u32</span>, <span class="number">5u32</span>])), |
| ConstScorer::from(VecDocSet::from(<span class="macro">vec!</span>[<span class="number">1u32</span>, <span class="number">4u32</span>])), |
| ], |
| DoNothingCombiner::default, |
| ); |
| <span class="macro">assert_eq!</span>(docset.doc(), <span class="number">0u32</span>); |
| <span class="macro">assert_eq!</span>(docset.seek(<span class="number">0u32</span>), <span class="number">0u32</span>); |
| <span class="macro">assert_eq!</span>(docset.seek(<span class="number">0u32</span>), <span class="number">0u32</span>); |
| <span class="macro">assert_eq!</span>(docset.doc(), <span class="number">0u32</span>) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union_skip_random() { |
| test_aux_union_skip( |
| <span class="kw-2">&</span>[ |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">7</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">9</span>, <span class="number">10000</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">8</span>, <span class="number">9</span>, <span class="number">100</span>], |
| ], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">5</span>, <span class="number">6</span>, <span class="number">7</span>, <span class="number">8</span>, <span class="number">100</span>], |
| ); |
| test_aux_union_skip( |
| <span class="kw-2">&</span>[ |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.001</span>, <span class="number">1</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.002</span>, <span class="number">2</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.005</span>, <span class="number">3</span>), |
| ], |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.01</span>, <span class="number">4</span>), |
| ); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_union_skip_specific() { |
| test_aux_union_skip( |
| <span class="kw-2">&</span>[ |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">7</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">9</span>, <span class="number">10000</span>], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">3</span>, <span class="number">8</span>, <span class="number">9</span>, <span class="number">100</span>], |
| ], |
| <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">7</span>, <span class="number">8</span>, <span class="number">9</span>, <span class="number">99</span>, <span class="number">100</span>, <span class="number">101</span>, <span class="number">500</span>, <span class="number">20000</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>test::Bencher; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::query::score_combiner::DoNothingCombiner; |
| <span class="kw">use </span><span class="kw">crate</span>::query::{ConstScorer, Union, VecDocSet}; |
| <span class="kw">use crate</span>::{tests, DocId, DocSet, TERMINATED}; |
| |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_union_3_high(bench: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>union_docset: Vec<Vec<DocId>> = <span class="macro">vec!</span>[ |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.1</span>, <span class="number">0</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.2</span>, <span class="number">1</span>), |
| ]; |
| bench.iter(|| { |
| <span class="kw">let </span><span class="kw-2">mut </span>v = Union::build( |
| union_docset |
| .iter() |
| .map(|doc_ids| VecDocSet::from(doc_ids.clone())) |
| .map(|docset| ConstScorer::new(docset, <span class="number">1.0</span>)) |
| .collect::<Vec<<span class="kw">_</span>>>(), |
| DoNothingCombiner::default, |
| ); |
| <span class="kw">while </span>v.doc() != TERMINATED { |
| v.advance(); |
| } |
| }); |
| } |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_union_3_low(bench: <span class="kw-2">&mut </span>Bencher) { |
| <span class="kw">let </span>union_docset: Vec<Vec<DocId>> = <span class="macro">vec!</span>[ |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.01</span>, <span class="number">0</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.05</span>, <span class="number">1</span>), |
| tests::sample_with_seed(<span class="number">100_000</span>, <span class="number">0.001</span>, <span class="number">2</span>), |
| ]; |
| bench.iter(|| { |
| <span class="kw">let </span><span class="kw-2">mut </span>v = Union::build( |
| union_docset |
| .iter() |
| .map(|doc_ids| VecDocSet::from(doc_ids.clone())) |
| .map(|docset| ConstScorer::new(docset, <span class="number">1.0</span>)) |
| .collect::<Vec<<span class="kw">_</span>>>(), |
| DoNothingCombiner::default, |
| ); |
| <span class="kw">while </span>v.doc() != TERMINATED { |
| v.advance(); |
| } |
| }); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |