| <!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/fastfield/multivalued/writer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>writer.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::io; |
| |
| <span class="kw">use </span>fastfield_codecs::{ |
| Column, MonotonicallyMappableToU128, MonotonicallyMappableToU64, VecColumn, |
| }; |
| <span class="kw">use </span>rustc_hash::FxHashMap; |
| |
| <span class="kw">use </span><span class="kw">super</span>::get_fastfield_codecs_for_multivalue; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::writer::unexpected_value; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::{value_to_u64, CompositeFastFieldSerializer, FastFieldType}; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::doc_id_mapping::DocIdMapping; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::UnorderedTermId; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{Document, Field, Value}; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::TermOrdinal; |
| <span class="kw">use crate</span>::{DatePrecision, DocId}; |
| |
| <span class="doccomment">/// Writer for multi-valued (as in, more than one value per document) |
| /// int fast field. |
| /// |
| /// This `Writer` is only useful for advanced users. |
| /// The normal way to get your multivalued int in your index |
| /// is to |
| /// - declare your field with fast set to |
| /// [`Cardinality::MultiValues`](crate::schema::Cardinality::MultiValues) in your schema |
| /// - add your document simply by calling `.add_document(...)`. |
| /// |
| /// The `MultiValuedFastFieldWriter` can be acquired from the fastfield writer, by calling |
| /// [`FastFieldWriter::get_multivalue_writer_mut()`](crate::fastfield::FastFieldsWriter::get_multivalue_writer_mut). |
| /// |
| /// Once acquired, writing is done by calling |
| /// [`.add_document(&Document)`](MultiValuedFastFieldWriter::add_document) once per value. |
| /// |
| /// The serializer makes it possible to remap all of the values |
| /// that were pushed to the writer using a mapping. |
| /// This makes it possible to push unordered term ids, |
| /// during indexing and remap them to their respective |
| /// term ids when the segment is getting serialized. |
| </span><span class="kw">pub struct </span>MultiValuedFastFieldWriter { |
| field: Field, |
| precision_opt: <span class="prelude-ty">Option</span><DatePrecision>, |
| vals: Vec<UnorderedTermId>, |
| doc_index: Vec<u64>, |
| fast_field_type: FastFieldType, |
| } |
| |
| <span class="kw">impl </span>MultiValuedFastFieldWriter { |
| <span class="doccomment">/// Creates a new `MultiValuedFastFieldWriter` |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new( |
| field: Field, |
| fast_field_type: FastFieldType, |
| precision_opt: <span class="prelude-ty">Option</span><DatePrecision>, |
| ) -> <span class="self">Self </span>{ |
| MultiValuedFastFieldWriter { |
| field, |
| precision_opt, |
| vals: Vec::new(), |
| doc_index: Vec::new(), |
| fast_field_type, |
| } |
| } |
| |
| <span class="doccomment">/// The memory used (inclusive childs) |
| </span><span class="kw">pub fn </span>mem_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.vals.capacity() * std::mem::size_of::<UnorderedTermId>() |
| + <span class="self">self</span>.doc_index.capacity() * std::mem::size_of::<u64>() |
| } |
| |
| <span class="doccomment">/// Access the field associated with the `MultiValuedFastFieldWriter` |
| </span><span class="kw">pub fn </span>field(<span class="kw-2">&</span><span class="self">self</span>) -> Field { |
| <span class="self">self</span>.field |
| } |
| |
| <span class="doccomment">/// Finalize the current document. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>next_doc(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="self">self</span>.doc_index.push(<span class="self">self</span>.vals.len() <span class="kw">as </span>u64); |
| } |
| |
| <span class="doccomment">/// Pushes a new value to the current document. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>add_val(<span class="kw-2">&mut </span><span class="self">self</span>, val: UnorderedTermId) { |
| <span class="self">self</span>.vals.push(val); |
| } |
| |
| <span class="doccomment">/// Shift to the next document and adds |
| /// all of the matching field values present in the document. |
| </span><span class="kw">pub fn </span>add_document(<span class="kw-2">&mut </span><span class="self">self</span>, doc: <span class="kw-2">&</span>Document) -> <span class="kw">crate</span>::Result<()> { |
| <span class="self">self</span>.next_doc(); |
| <span class="comment">// facets/texts are indexed in the `SegmentWriter` as we encode their unordered id. |
| </span><span class="kw">if </span><span class="self">self</span>.fast_field_type.is_storing_term_ids() { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(()); |
| } |
| <span class="kw">for </span>field_value <span class="kw">in </span>doc.field_values() { |
| <span class="kw">if </span>field_value.field == <span class="self">self</span>.field { |
| <span class="kw">let </span>value = field_value.value(); |
| <span class="kw">let </span>value_u64 = <span class="kw">match </span>(<span class="self">self</span>.precision_opt, value) { |
| (<span class="prelude-val">Some</span>(precision), Value::Date(date_val)) => { |
| date_val.truncate(precision).to_u64() |
| } |
| <span class="kw">_ </span>=> value_to_u64(value)<span class="question-mark">?</span>, |
| }; |
| <span class="self">self</span>.add_val(value_u64); |
| } |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Returns an iterator over values per doc_id in ascending doc_id order. |
| /// |
| /// Normally the order is simply iterating self.doc_id_index. |
| /// With doc_id_map it accounts for the new mapping, returning values in the order of the |
| /// new doc_ids. |
| </span><span class="kw">fn </span>get_ordered_values<<span class="lifetime">'a</span>: <span class="lifetime">'b</span>, <span class="lifetime">'b</span>>( |
| <span class="kw-2">&</span><span class="lifetime">'a </span><span class="self">self</span>, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span><span class="lifetime">'b </span>DocIdMapping>, |
| ) -> <span class="kw">impl </span>Iterator<Item = <span class="kw-2">&</span><span class="lifetime">'b </span>[u64]> { |
| <span class="kw">let </span>doc_id_iter: Box<<span class="kw">dyn </span>Iterator<Item = u32>> = <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| Box::new(doc_id_map.iter_old_doc_ids()) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>max_doc = <span class="self">self</span>.doc_index.len() <span class="kw">as </span>DocId; |
| Box::new(<span class="number">0</span>..max_doc) |
| }; |
| doc_id_iter.map(<span class="kw">move </span>|doc_id| <span class="self">self</span>.get_values_for_doc_id(doc_id)) |
| } |
| |
| <span class="doccomment">/// returns all values for a doc_ids |
| </span><span class="kw">fn </span>get_values_for_doc_id(<span class="kw-2">&</span><span class="self">self</span>, doc_id: u32) -> <span class="kw-2">&</span>[u64] { |
| <span class="kw">let </span>start_pos = <span class="self">self</span>.doc_index[doc_id <span class="kw">as </span>usize] <span class="kw">as </span>usize; |
| <span class="kw">let </span>end_pos = <span class="self">self |
| </span>.doc_index |
| .get(doc_id <span class="kw">as </span>usize + <span class="number">1</span>) |
| .cloned() |
| .unwrap_or(<span class="self">self</span>.vals.len() <span class="kw">as </span>u64) <span class="kw">as </span>usize; <span class="comment">// special case, last doc_id has no offset information |
| </span><span class="kw-2">&</span><span class="self">self</span>.vals[start_pos..end_pos] |
| } |
| <span class="doccomment">/// Serializes fast field values by pushing them to the `FastFieldSerializer`. |
| /// |
| /// If a mapping is given, the values are remapped *and sorted* before serialization. |
| /// This is used when serializing `facets`. Specifically their terms are |
| /// first stored in the writer as their position in the `IndexWriter`'s `HashMap`. |
| /// This value is called an `UnorderedTermId`. |
| /// |
| /// During the serialization of the segment, terms gets sorted and |
| /// `tantivy` builds a mapping to convert this `UnorderedTermId` into |
| /// term ordinals. |
| </span><span class="kw">pub fn </span>serialize( |
| <span class="kw-2">mut </span><span class="self">self</span>, |
| serializer: <span class="kw-2">&mut </span>CompositeFastFieldSerializer, |
| term_mapping_opt: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>FxHashMap<UnorderedTermId, TermOrdinal>>, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ) -> io::Result<()> { |
| { |
| <span class="self">self</span>.doc_index.push(<span class="self">self</span>.vals.len() <span class="kw">as </span>u64); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span><span class="self">self</span>.doc_index[..]); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| <span class="kw">let </span>multi_value_start_index = MultivalueStartIndex::new(<span class="kw-2">&</span>col, doc_id_map); |
| serializer.create_auto_detect_u64_fast_field_with_idx( |
| <span class="self">self</span>.field, |
| multi_value_start_index, |
| <span class="number">0</span>, |
| )<span class="question-mark">?</span>; |
| } <span class="kw">else </span>{ |
| serializer.create_auto_detect_u64_fast_field_with_idx(<span class="self">self</span>.field, col, <span class="number">0</span>)<span class="question-mark">?</span>; |
| } |
| } |
| { |
| <span class="comment">// Writing the values themselves. |
| // TODO FIXME: Use less memory. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>values: Vec<u64> = Vec::new(); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(term_mapping) = term_mapping_opt { |
| <span class="kw">if </span><span class="self">self</span>.fast_field_type.is_facet() { |
| <span class="kw">let </span><span class="kw-2">mut </span>doc_vals: Vec<u64> = Vec::with_capacity(<span class="number">100</span>); |
| <span class="kw">for </span>vals <span class="kw">in </span><span class="self">self</span>.get_ordered_values(doc_id_map) { |
| <span class="comment">// In the case of facets, we want a vec of facet ord that is sorted. |
| </span>doc_vals.clear(); |
| <span class="kw">let </span>remapped_vals = vals |
| .iter() |
| .map(|val| <span class="kw-2">*</span>term_mapping.get(val).expect(<span class="string">"Missing term ordinal"</span>)); |
| doc_vals.extend(remapped_vals); |
| doc_vals.sort_unstable(); |
| <span class="kw">for </span><span class="kw-2">&</span>val <span class="kw">in </span><span class="kw-2">&</span>doc_vals { |
| values.push(val); |
| } |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">for </span>vals <span class="kw">in </span><span class="self">self</span>.get_ordered_values(doc_id_map) { |
| <span class="kw">let </span>remapped_vals = vals |
| .iter() |
| .map(|val| <span class="kw-2">*</span>term_mapping.get(val).expect(<span class="string">"Missing term ordinal"</span>)); |
| <span class="kw">for </span>val <span class="kw">in </span>remapped_vals { |
| values.push(val); |
| } |
| } |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">for </span>vals <span class="kw">in </span><span class="self">self</span>.get_ordered_values(doc_id_map) { |
| <span class="comment">// sort values in case of remapped doc_ids? |
| </span><span class="kw">for </span><span class="kw-2">&</span>val <span class="kw">in </span>vals { |
| values.push(val); |
| } |
| } |
| } |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>values[..]); |
| serializer.create_auto_detect_u64_fast_field_with_idx_and_codecs( |
| <span class="self">self</span>.field, |
| col, |
| <span class="number">1</span>, |
| <span class="kw-2">&</span>get_fastfield_codecs_for_multivalue(), |
| )<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>MultivalueStartIndex<<span class="lifetime">'a</span>, C: Column> { |
| column: <span class="kw-2">&</span><span class="lifetime">'a </span>C, |
| doc_id_map: <span class="kw-2">&</span><span class="lifetime">'a </span>DocIdMapping, |
| min: u64, |
| max: u64, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, C: Column> MultivalueStartIndex<<span class="lifetime">'a</span>, C> { |
| <span class="kw">pub fn </span>new(column: <span class="kw-2">&</span><span class="lifetime">'a </span>C, doc_id_map: <span class="kw-2">&</span><span class="lifetime">'a </span>DocIdMapping) -> <span class="self">Self </span>{ |
| <span class="macro">assert_eq!</span>(column.num_vals(), doc_id_map.num_old_doc_ids() <span class="kw">as </span>u32 + <span class="number">1</span>); |
| <span class="kw">let </span>(min, max) = |
| tantivy_bitpacker::minmax(iter_remapped_multivalue_index(doc_id_map, column)) |
| .unwrap_or((<span class="number">0u64</span>, <span class="number">0u64</span>)); |
| MultivalueStartIndex { |
| column, |
| doc_id_map, |
| min, |
| max, |
| } |
| } |
| } |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, C: Column> Column <span class="kw">for </span>MultivalueStartIndex<<span class="lifetime">'a</span>, C> { |
| <span class="kw">fn </span>get_val(<span class="kw-2">&</span><span class="self">self</span>, _idx: u32) -> u64 { |
| <span class="macro">unimplemented!</span>() |
| } |
| |
| <span class="kw">fn </span>min_value(<span class="kw-2">&</span><span class="self">self</span>) -> u64 { |
| <span class="self">self</span>.min |
| } |
| |
| <span class="kw">fn </span>max_value(<span class="kw-2">&</span><span class="self">self</span>) -> u64 { |
| <span class="self">self</span>.max |
| } |
| |
| <span class="kw">fn </span>num_vals(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| (<span class="self">self</span>.doc_id_map.num_new_doc_ids() + <span class="number">1</span>) <span class="kw">as </span>u32 |
| } |
| |
| <span class="kw">fn </span>iter(<span class="kw-2">&</span><span class="self">self</span>) -> Box<<span class="kw">dyn </span>Iterator<Item = u64> + <span class="lifetime">'_</span>> { |
| Box::new(iter_remapped_multivalue_index( |
| <span class="self">self</span>.doc_id_map, |
| <span class="kw-2">&</span><span class="self">self</span>.column, |
| )) |
| } |
| } |
| |
| <span class="kw">fn </span>iter_remapped_multivalue_index<<span class="lifetime">'a</span>, C: Column>( |
| doc_id_map: <span class="kw-2">&</span><span class="lifetime">'a </span>DocIdMapping, |
| column: <span class="kw-2">&</span><span class="lifetime">'a </span>C, |
| ) -> <span class="kw">impl </span>Iterator<Item = u64> + <span class="lifetime">'a </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>offset = <span class="number">0</span>; |
| std::iter::once(<span class="number">0</span>).chain(doc_id_map.iter_old_doc_ids().map(<span class="kw">move </span>|old_doc| { |
| <span class="kw">let </span>num_vals_for_doc = column.get_val(old_doc + <span class="number">1</span>) - column.get_val(old_doc); |
| offset += num_vals_for_doc; |
| offset <span class="kw">as </span>u64 |
| })) |
| } |
| |
| <span class="doccomment">/// Writer for multi-valued (as in, more than one value per document) |
| /// int fast field. |
| /// |
| /// This `Writer` is only useful for advanced users. |
| /// The normal way to get your multivalued int in your index |
| /// is to |
| /// - declare your field with fast set to `Cardinality::MultiValues` |
| /// in your schema |
| /// - add your document simply by calling `.add_document(...)`. |
| /// |
| /// The `MultiValuedFastFieldWriter` can be acquired from the |
| |
| </span><span class="kw">pub struct </span>MultiValueU128FastFieldWriter { |
| field: Field, |
| vals: Vec<u128>, |
| doc_index: Vec<u64>, |
| } |
| |
| <span class="kw">impl </span>MultiValueU128FastFieldWriter { |
| <span class="doccomment">/// Creates a new `U128MultiValueFastFieldWriter` |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(field: Field) -> <span class="self">Self </span>{ |
| MultiValueU128FastFieldWriter { |
| field, |
| vals: Vec::new(), |
| doc_index: Vec::new(), |
| } |
| } |
| |
| <span class="doccomment">/// The memory used (inclusive childs) |
| </span><span class="kw">pub fn </span>mem_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.vals.capacity() * std::mem::size_of::<UnorderedTermId>() |
| + <span class="self">self</span>.doc_index.capacity() * std::mem::size_of::<u64>() |
| } |
| |
| <span class="doccomment">/// Finalize the current document. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>next_doc(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="self">self</span>.doc_index.push(<span class="self">self</span>.vals.len() <span class="kw">as </span>u64); |
| } |
| |
| <span class="doccomment">/// Pushes a new value to the current document. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>add_val(<span class="kw-2">&mut </span><span class="self">self</span>, val: u128) { |
| <span class="self">self</span>.vals.push(val); |
| } |
| |
| <span class="doccomment">/// Shift to the next document and adds |
| /// all of the matching field values present in the document. |
| </span><span class="kw">pub fn </span>add_document(<span class="kw-2">&mut </span><span class="self">self</span>, doc: <span class="kw-2">&</span>Document) -> <span class="kw">crate</span>::Result<()> { |
| <span class="self">self</span>.next_doc(); |
| <span class="kw">for </span>field_value <span class="kw">in </span>doc.field_values() { |
| <span class="kw">if </span>field_value.field == <span class="self">self</span>.field { |
| <span class="kw">let </span>value = field_value.value(); |
| <span class="kw">let </span>ip_addr = value |
| .as_ip_addr() |
| .ok_or_else(|| unexpected_value(<span class="string">"ip"</span>, value))<span class="question-mark">?</span>; |
| <span class="kw">let </span>ip_addr_u128 = ip_addr.to_u128(); |
| <span class="self">self</span>.add_val(ip_addr_u128); |
| } |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Returns an iterator over values per doc_id in ascending doc_id order. |
| /// |
| /// Normally the order is simply iterating self.doc_id_index. |
| /// With doc_id_map it accounts for the new mapping, returning values in the order of the |
| /// new doc_ids. |
| </span><span class="kw">fn </span>get_ordered_values<<span class="lifetime">'a</span>: <span class="lifetime">'b</span>, <span class="lifetime">'b</span>>( |
| <span class="kw-2">&</span><span class="lifetime">'a </span><span class="self">self</span>, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span><span class="lifetime">'b </span>DocIdMapping>, |
| ) -> <span class="kw">impl </span>Iterator<Item = <span class="kw-2">&</span><span class="lifetime">'b </span>[u128]> { |
| get_ordered_values(<span class="kw-2">&</span><span class="self">self</span>.vals, <span class="kw-2">&</span><span class="self">self</span>.doc_index, doc_id_map) |
| } |
| |
| <span class="doccomment">/// Serializes fast field values. |
| </span><span class="kw">pub fn </span>serialize( |
| <span class="kw-2">mut </span><span class="self">self</span>, |
| serializer: <span class="kw-2">&mut </span>CompositeFastFieldSerializer, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ) -> io::Result<()> { |
| { |
| <span class="comment">// writing the offset index |
| // |
| </span><span class="self">self</span>.doc_index.push(<span class="self">self</span>.vals.len() <span class="kw">as </span>u64); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span><span class="self">self</span>.doc_index[..]); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| <span class="kw">let </span>multi_value_start_index = MultivalueStartIndex::new(<span class="kw-2">&</span>col, doc_id_map); |
| serializer.create_auto_detect_u64_fast_field_with_idx( |
| <span class="self">self</span>.field, |
| multi_value_start_index, |
| <span class="number">0</span>, |
| )<span class="question-mark">?</span>; |
| } <span class="kw">else </span>{ |
| serializer.create_auto_detect_u64_fast_field_with_idx(<span class="self">self</span>.field, col, <span class="number">0</span>)<span class="question-mark">?</span>; |
| } |
| } |
| { |
| <span class="kw">let </span>iter_gen = || <span class="self">self</span>.get_ordered_values(doc_id_map).flatten().cloned(); |
| |
| serializer.create_u128_fast_field_with_idx( |
| <span class="self">self</span>.field, |
| iter_gen, |
| <span class="self">self</span>.vals.len() <span class="kw">as </span>u32, |
| <span class="number">1</span>, |
| )<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="doccomment">/// Returns an iterator over values per doc_id in ascending doc_id order. |
| /// |
| /// Normally the order is simply iterating self.doc_id_index. |
| /// With doc_id_map it accounts for the new mapping, returning values in the order of the |
| /// new doc_ids. |
| </span><span class="kw">fn </span>get_ordered_values<<span class="lifetime">'a</span>: <span class="lifetime">'b</span>, <span class="lifetime">'b</span>, T>( |
| vals: <span class="kw-2">&</span><span class="lifetime">'a </span>[T], |
| doc_index: <span class="kw-2">&</span><span class="lifetime">'a </span>[u64], |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span><span class="lifetime">'b </span>DocIdMapping>, |
| ) -> <span class="kw">impl </span>Iterator<Item = <span class="kw-2">&</span><span class="lifetime">'b </span>[T]> { |
| <span class="kw">let </span>doc_id_iter: Box<<span class="kw">dyn </span>Iterator<Item = u32>> = <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| Box::new(doc_id_map.iter_old_doc_ids()) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>max_doc = doc_index.len() <span class="kw">as </span>DocId; |
| Box::new(<span class="number">0</span>..max_doc) |
| }; |
| doc_id_iter.map(<span class="kw">move </span>|doc_id| get_values_for_doc_id(doc_id, vals, doc_index)) |
| } |
| |
| <span class="doccomment">/// returns all values for a doc_id |
| </span><span class="kw">fn </span>get_values_for_doc_id<<span class="lifetime">'a</span>, T>(doc_id: u32, vals: <span class="kw-2">&</span><span class="lifetime">'a </span>[T], doc_index: <span class="kw-2">&</span><span class="lifetime">'a </span>[u64]) -> <span class="kw-2">&</span><span class="lifetime">'a </span>[T] { |
| <span class="kw">let </span>start_pos = doc_index[doc_id <span class="kw">as </span>usize] <span class="kw">as </span>usize; |
| <span class="kw">let </span>end_pos = doc_index |
| .get(doc_id <span class="kw">as </span>usize + <span class="number">1</span>) |
| .cloned() |
| .unwrap_or(vals.len() <span class="kw">as </span>u64) <span class="kw">as </span>usize; <span class="comment">// special case, last doc_id has no offset information |
| </span><span class="kw-2">&</span>vals[start_pos..end_pos] |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_multivalue_start_index() { |
| <span class="kw">let </span>doc_id_mapping = DocIdMapping::from_new_id_to_old_id(<span class="macro">vec!</span>[<span class="number">4</span>, <span class="number">1</span>, <span class="number">2</span>]); |
| <span class="macro">assert_eq!</span>(doc_id_mapping.num_old_doc_ids(), <span class="number">5</span>); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>[<span class="number">0u64</span>, <span class="number">3</span>, <span class="number">5</span>, <span class="number">10</span>, <span class="number">12</span>, <span class="number">16</span>][..]); |
| <span class="kw">let </span>multivalue_start_index = MultivalueStartIndex::new( |
| <span class="kw-2">&</span>col, <span class="comment">// 3, 2, 5, 2, 4 |
| </span><span class="kw-2">&</span>doc_id_mapping, |
| ); |
| <span class="macro">assert_eq!</span>(multivalue_start_index.num_vals(), <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>( |
| multivalue_start_index.iter().collect::<Vec<u64>>(), |
| <span class="macro">vec!</span>[<span class="number">0</span>, <span class="number">4</span>, <span class="number">6</span>, <span class="number">11</span>] |
| ); <span class="comment">// 4, 2, 5 |
| </span>} |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_multivalue_get_vals() { |
| <span class="kw">let </span>doc_id_mapping = |
| DocIdMapping::from_new_id_to_old_id(<span class="macro">vec!</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">4</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="macro">assert_eq!</span>(doc_id_mapping.num_old_doc_ids(), <span class="number">10</span>); |
| <span class="kw">let </span>col = VecColumn::from(<span class="kw-2">&</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">5</span>, <span class="number">8</span>, <span class="number">13</span>, <span class="number">21</span>, <span class="number">34</span>, <span class="number">55</span>][..]); |
| <span class="kw">let </span>multivalue_start_index = MultivalueStartIndex::new(<span class="kw-2">&</span>col, <span class="kw-2">&</span>doc_id_mapping); |
| <span class="macro">assert_eq!</span>( |
| multivalue_start_index.iter().collect::<Vec<u64>>(), |
| <span class="macro">vec!</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">5</span>, <span class="number">8</span>, <span class="number">13</span>, <span class="number">21</span>, <span class="number">34</span>, <span class="number">55</span>] |
| ); |
| <span class="macro">assert_eq!</span>(multivalue_start_index.num_vals(), <span class="number">11</span>); |
| } |
| } |
| </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> |