| <!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/core/segment_reader.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>segment_reader.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::sync::{Arc, RwLock}; |
| <span class="kw">use </span>std::{fmt, io}; |
| |
| <span class="kw">use </span>fail::fail_point; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::core::{InvertedIndexReader, Segment, SegmentComponent, SegmentId}; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::{CompositeFile, FileSlice}; |
| <span class="kw">use </span><span class="kw">crate</span>::error::DataCorruption; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::{intersect_alive_bitsets, AliveBitSet, FacetReader, FastFieldReaders}; |
| <span class="kw">use </span><span class="kw">crate</span>::fieldnorm::{FieldNormReader, FieldNormReaders}; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{Field, FieldType, IndexRecordOption, Schema}; |
| <span class="kw">use </span><span class="kw">crate</span>::space_usage::SegmentSpaceUsage; |
| <span class="kw">use </span><span class="kw">crate</span>::store::StoreReader; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::TermDictionary; |
| <span class="kw">use crate</span>::{DocId, Opstamp}; |
| |
| <span class="doccomment">/// Entry point to access all of the datastructures of the `Segment` |
| /// |
| /// - term dictionary |
| /// - postings |
| /// - store |
| /// - fast field readers |
| /// - field norm reader |
| /// |
| /// The segment reader has a very low memory footprint, |
| /// as close to all of the memory data is mmapped. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>SegmentReader { |
| inv_idx_reader_cache: Arc<RwLock<HashMap<Field, Arc<InvertedIndexReader>>>>, |
| |
| segment_id: SegmentId, |
| delete_opstamp: <span class="prelude-ty">Option</span><Opstamp>, |
| |
| max_doc: DocId, |
| num_docs: DocId, |
| |
| termdict_composite: CompositeFile, |
| postings_composite: CompositeFile, |
| positions_composite: CompositeFile, |
| fast_fields_readers: Arc<FastFieldReaders>, |
| fieldnorm_readers: FieldNormReaders, |
| |
| store_file: FileSlice, |
| alive_bitset_opt: <span class="prelude-ty">Option</span><AliveBitSet>, |
| schema: Schema, |
| } |
| |
| <span class="kw">impl </span>SegmentReader { |
| <span class="doccomment">/// Returns the highest document id ever attributed in |
| /// this segment + 1. |
| </span><span class="kw">pub fn </span>max_doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.max_doc |
| } |
| |
| <span class="doccomment">/// Returns the number of alive documents. |
| /// Deleted documents are not counted. |
| </span><span class="kw">pub fn </span>num_docs(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.num_docs |
| } |
| |
| <span class="doccomment">/// Returns the schema of the index this segment belongs to. |
| </span><span class="kw">pub fn </span>schema(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>Schema { |
| <span class="kw-2">&</span><span class="self">self</span>.schema |
| } |
| |
| <span class="doccomment">/// Return the number of documents that have been |
| /// deleted in the segment. |
| </span><span class="kw">pub fn </span>num_deleted_docs(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.max_doc - <span class="self">self</span>.num_docs |
| } |
| |
| <span class="doccomment">/// Returns true if some of the documents of the segment have been deleted. |
| </span><span class="kw">pub fn </span>has_deletes(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.num_deleted_docs() > <span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Accessor to a segment's fast field reader given a field. |
| /// |
| /// Returns the u64 fast value reader if the field |
| /// is a u64 field indexed as "fast". |
| /// |
| /// Return a FastFieldNotAvailableError if the field is not |
| /// declared as a fast field in the schema. |
| /// |
| /// # Panics |
| /// May panic if the index is corrupted. |
| </span><span class="kw">pub fn </span>fast_fields(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>FastFieldReaders { |
| <span class="kw-2">&</span><span class="self">self</span>.fast_fields_readers |
| } |
| |
| <span class="doccomment">/// Accessor to the `FacetReader` associated with a given `Field`. |
| </span><span class="kw">pub fn </span>facet_reader(<span class="kw-2">&</span><span class="self">self</span>, field: Field) -> <span class="kw">crate</span>::Result<FacetReader> { |
| <span class="kw">let </span>field_entry = <span class="self">self</span>.schema.get_field_entry(field); |
| |
| <span class="kw">match </span>field_entry.field_type() { |
| FieldType::Facet(<span class="kw">_</span>) => { |
| <span class="kw">let </span>term_ords_reader = <span class="self">self</span>.fast_fields().u64s(field)<span class="question-mark">?</span>; |
| <span class="kw">let </span>termdict = <span class="self">self |
| </span>.termdict_composite |
| .open_read(field) |
| .map(TermDictionary::open) |
| .unwrap_or_else(|| <span class="prelude-val">Ok</span>(TermDictionary::empty()))<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(FacetReader::new(term_ords_reader, termdict)) |
| } |
| <span class="kw">_ </span>=> <span class="prelude-val">Err</span>(<span class="kw">crate</span>::TantivyError::InvalidArgument(<span class="macro">format!</span>( |
| <span class="string">"Field {:?} is not a facet field."</span>, |
| field_entry.name() |
| ))), |
| } |
| } |
| |
| <span class="doccomment">/// Accessor to the segment's `Field norms`'s reader. |
| /// |
| /// Field norms are the length (in tokens) of the fields. |
| /// It is used in the computation of the [TfIdf](https://fulmicoton.gitbooks.io/tantivy-doc/content/tfidf.html). |
| /// |
| /// They are simply stored as a fast field, serialized in |
| /// the `.fieldnorm` file of the segment. |
| </span><span class="kw">pub fn </span>get_fieldnorms_reader(<span class="kw-2">&</span><span class="self">self</span>, field: Field) -> <span class="kw">crate</span>::Result<FieldNormReader> { |
| <span class="self">self</span>.fieldnorm_readers.get_field(field)<span class="question-mark">?</span>.ok_or_else(|| { |
| <span class="kw">let </span>field_name = <span class="self">self</span>.schema.get_field_name(field); |
| <span class="kw">let </span>err_msg = <span class="macro">format!</span>( |
| <span class="string">"Field norm not found for field {field_name:?}. Was the field set to record norm \ |
| during indexing?" |
| </span>); |
| <span class="kw">crate</span>::TantivyError::SchemaError(err_msg) |
| }) |
| } |
| |
| <span class="attribute">#[doc(hidden)] |
| </span><span class="kw">pub fn </span>fieldnorms_readers(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>FieldNormReaders { |
| <span class="kw-2">&</span><span class="self">self</span>.fieldnorm_readers |
| } |
| |
| <span class="doccomment">/// Accessor to the segment's `StoreReader`. |
| </span><span class="kw">pub fn </span>get_store_reader(<span class="kw-2">&</span><span class="self">self</span>, cache_size: usize) -> io::Result<StoreReader> { |
| StoreReader::open(<span class="self">self</span>.store_file.clone(), cache_size) |
| } |
| |
| <span class="doccomment">/// Open a new segment for reading. |
| </span><span class="kw">pub fn </span>open(segment: <span class="kw-2">&</span>Segment) -> <span class="kw">crate</span>::Result<SegmentReader> { |
| <span class="self">Self</span>::open_with_custom_alive_set(segment, <span class="prelude-val">None</span>) |
| } |
| |
| <span class="doccomment">/// Open a new segment for reading. |
| </span><span class="kw">pub fn </span>open_with_custom_alive_set( |
| segment: <span class="kw-2">&</span>Segment, |
| custom_bitset: <span class="prelude-ty">Option</span><AliveBitSet>, |
| ) -> <span class="kw">crate</span>::Result<SegmentReader> { |
| <span class="kw">let </span>termdict_file = segment.open_read(SegmentComponent::Terms)<span class="question-mark">?</span>; |
| <span class="kw">let </span>termdict_composite = CompositeFile::open(<span class="kw-2">&</span>termdict_file)<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>store_file = segment.open_read(SegmentComponent::Store)<span class="question-mark">?</span>; |
| |
| <span class="macro">fail_point!</span>(<span class="string">"SegmentReader::open#middle"</span>); |
| |
| <span class="kw">let </span>postings_file = segment.open_read(SegmentComponent::Postings)<span class="question-mark">?</span>; |
| <span class="kw">let </span>postings_composite = CompositeFile::open(<span class="kw-2">&</span>postings_file)<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>positions_composite = { |
| <span class="kw">if let </span><span class="prelude-val">Ok</span>(positions_file) = segment.open_read(SegmentComponent::Positions) { |
| CompositeFile::open(<span class="kw-2">&</span>positions_file)<span class="question-mark">? |
| </span>} <span class="kw">else </span>{ |
| CompositeFile::empty() |
| } |
| }; |
| |
| <span class="kw">let </span>schema = segment.schema(); |
| |
| <span class="kw">let </span>fast_fields_data = segment.open_read(SegmentComponent::FastFields)<span class="question-mark">?</span>; |
| <span class="kw">let </span>fast_fields_composite = CompositeFile::open(<span class="kw-2">&</span>fast_fields_data)<span class="question-mark">?</span>; |
| <span class="kw">let </span>fast_fields_readers = |
| Arc::new(FastFieldReaders::new(schema.clone(), fast_fields_composite)); |
| <span class="kw">let </span>fieldnorm_data = segment.open_read(SegmentComponent::FieldNorms)<span class="question-mark">?</span>; |
| <span class="kw">let </span>fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>original_bitset = <span class="kw">if </span>segment.meta().has_deletes() { |
| <span class="kw">let </span>alive_doc_file_slice = segment.open_read(SegmentComponent::Delete)<span class="question-mark">?</span>; |
| <span class="kw">let </span>alive_doc_data = alive_doc_file_slice.read_bytes()<span class="question-mark">?</span>; |
| <span class="prelude-val">Some</span>(AliveBitSet::open(alive_doc_data)) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>}; |
| |
| <span class="kw">let </span>alive_bitset_opt = intersect_alive_bitset(original_bitset, custom_bitset); |
| |
| <span class="kw">let </span>max_doc = segment.meta().max_doc(); |
| <span class="kw">let </span>num_docs = alive_bitset_opt |
| .as_ref() |
| .map(|alive_bitset| alive_bitset.num_alive_docs() <span class="kw">as </span>u32) |
| .unwrap_or(max_doc); |
| |
| <span class="prelude-val">Ok</span>(SegmentReader { |
| inv_idx_reader_cache: Default::default(), |
| num_docs, |
| max_doc, |
| termdict_composite, |
| postings_composite, |
| fast_fields_readers, |
| fieldnorm_readers, |
| segment_id: segment.id(), |
| delete_opstamp: segment.meta().delete_opstamp(), |
| store_file, |
| alive_bitset_opt, |
| positions_composite, |
| schema, |
| }) |
| } |
| |
| <span class="doccomment">/// Returns a field reader associated with the field given in argument. |
| /// If the field was not present in the index during indexing time, |
| /// the InvertedIndexReader is empty. |
| /// |
| /// The field reader is in charge of iterating through the |
| /// term dictionary associated with a specific field, |
| /// and opening the posting list associated with any term. |
| /// |
| /// If the field is not marked as index, a warning is logged and an empty `InvertedIndexReader` |
| /// is returned. |
| /// Similarly, if the field is marked as indexed but no term has been indexed for the given |
| /// index, an empty `InvertedIndexReader` is returned (but no warning is logged). |
| </span><span class="kw">pub fn </span>inverted_index(<span class="kw-2">&</span><span class="self">self</span>, field: Field) -> <span class="kw">crate</span>::Result<Arc<InvertedIndexReader>> { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(inv_idx_reader) = <span class="self">self |
| </span>.inv_idx_reader_cache |
| .read() |
| .expect(<span class="string">"Lock poisoned. This should never happen"</span>) |
| .get(<span class="kw-2">&</span>field) |
| { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(Arc::clone(inv_idx_reader)); |
| } |
| <span class="kw">let </span>field_entry = <span class="self">self</span>.schema.get_field_entry(field); |
| <span class="kw">let </span>field_type = field_entry.field_type(); |
| <span class="kw">let </span>record_option_opt = field_type.get_index_record_option(); |
| |
| <span class="kw">if </span>record_option_opt.is_none() { |
| <span class="macro">warn!</span>(<span class="string">"Field {:?} does not seem indexed."</span>, field_entry.name()); |
| } |
| |
| <span class="kw">let </span>postings_file_opt = <span class="self">self</span>.postings_composite.open_read(field); |
| |
| <span class="kw">if </span>postings_file_opt.is_none() || record_option_opt.is_none() { |
| <span class="comment">// no documents in the segment contained this field. |
| // As a result, no data is associated with the inverted index. |
| // |
| // Returns an empty inverted index. |
| </span><span class="kw">let </span>record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic); |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(Arc::new(InvertedIndexReader::empty(record_option))); |
| } |
| |
| <span class="kw">let </span>record_option = record_option_opt.unwrap(); |
| <span class="kw">let </span>postings_file = postings_file_opt.unwrap(); |
| |
| <span class="kw">let </span>termdict_file: FileSlice = |
| <span class="self">self</span>.termdict_composite.open_read(field).ok_or_else(|| { |
| DataCorruption::comment_only(<span class="macro">format!</span>( |
| <span class="string">"Failed to open field {:?}'s term dictionary in the composite file. Has the \ |
| schema been modified?"</span>, |
| field_entry.name() |
| )) |
| })<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>positions_file = <span class="self">self</span>.positions_composite.open_read(field).ok_or_else(|| { |
| <span class="kw">let </span>error_msg = <span class="macro">format!</span>( |
| <span class="string">"Failed to open field {:?}'s positions in the composite file. Has the schema been \ |
| modified?"</span>, |
| field_entry.name() |
| ); |
| DataCorruption::comment_only(error_msg) |
| })<span class="question-mark">?</span>; |
| |
| <span class="kw">let </span>inv_idx_reader = Arc::new(InvertedIndexReader::new( |
| TermDictionary::open(termdict_file)<span class="question-mark">?</span>, |
| postings_file, |
| positions_file, |
| record_option, |
| )<span class="question-mark">?</span>); |
| |
| <span class="comment">// by releasing the lock in between, we may end up opening the inverting index |
| // twice, but this is fine. |
| </span><span class="self">self</span>.inv_idx_reader_cache |
| .write() |
| .expect(<span class="string">"Field reader cache lock poisoned. This should never happen."</span>) |
| .insert(field, Arc::clone(<span class="kw-2">&</span>inv_idx_reader)); |
| |
| <span class="prelude-val">Ok</span>(inv_idx_reader) |
| } |
| |
| <span class="doccomment">/// Returns the segment id |
| </span><span class="kw">pub fn </span>segment_id(<span class="kw-2">&</span><span class="self">self</span>) -> SegmentId { |
| <span class="self">self</span>.segment_id |
| } |
| |
| <span class="doccomment">/// Returns the delete opstamp |
| </span><span class="kw">pub fn </span>delete_opstamp(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><Opstamp> { |
| <span class="self">self</span>.delete_opstamp |
| } |
| |
| <span class="doccomment">/// Returns the bitset representing the alive `DocId`s. |
| </span><span class="kw">pub fn </span>alive_bitset(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="kw-2">&</span>AliveBitSet> { |
| <span class="self">self</span>.alive_bitset_opt.as_ref() |
| } |
| |
| <span class="doccomment">/// Returns true if the `doc` is marked |
| /// as deleted. |
| </span><span class="kw">pub fn </span>is_deleted(<span class="kw-2">&</span><span class="self">self</span>, doc: DocId) -> bool { |
| <span class="self">self</span>.alive_bitset() |
| .map(|alive_bitset| alive_bitset.is_deleted(doc)) |
| .unwrap_or(<span class="bool-val">false</span>) |
| } |
| |
| <span class="doccomment">/// Returns an iterator that will iterate over the alive document ids |
| </span><span class="kw">pub fn </span>doc_ids_alive(<span class="kw-2">&</span><span class="self">self</span>) -> Box<<span class="kw">dyn </span>Iterator<Item = DocId> + <span class="lifetime">'_</span>> { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(alive_bitset) = <span class="kw-2">&</span><span class="self">self</span>.alive_bitset_opt { |
| Box::new(alive_bitset.iter_alive()) |
| } <span class="kw">else </span>{ |
| Box::new(<span class="number">0u32</span>..<span class="self">self</span>.max_doc) |
| } |
| } |
| |
| <span class="doccomment">/// Summarize total space usage of this segment. |
| </span><span class="kw">pub fn </span>space_usage(<span class="kw-2">&</span><span class="self">self</span>) -> io::Result<SegmentSpaceUsage> { |
| <span class="prelude-val">Ok</span>(SegmentSpaceUsage::new( |
| <span class="self">self</span>.num_docs(), |
| <span class="self">self</span>.termdict_composite.space_usage(), |
| <span class="self">self</span>.postings_composite.space_usage(), |
| <span class="self">self</span>.positions_composite.space_usage(), |
| <span class="self">self</span>.fast_fields_readers.space_usage(), |
| <span class="self">self</span>.fieldnorm_readers.space_usage(), |
| <span class="self">self</span>.get_store_reader(<span class="number">0</span>)<span class="question-mark">?</span>.space_usage(), |
| <span class="self">self</span>.alive_bitset_opt |
| .as_ref() |
| .map(AliveBitSet::space_usage) |
| .unwrap_or(<span class="number">0</span>), |
| )) |
| } |
| } |
| |
| <span class="kw">fn </span>intersect_alive_bitset( |
| left_opt: <span class="prelude-ty">Option</span><AliveBitSet>, |
| right_opt: <span class="prelude-ty">Option</span><AliveBitSet>, |
| ) -> <span class="prelude-ty">Option</span><AliveBitSet> { |
| <span class="kw">match </span>(left_opt, right_opt) { |
| (<span class="prelude-val">Some</span>(left), <span class="prelude-val">Some</span>(right)) => { |
| <span class="macro">assert_eq!</span>(left.bitset().max_value(), right.bitset().max_value()); |
| <span class="prelude-val">Some</span>(intersect_alive_bitsets(left, right)) |
| } |
| (<span class="prelude-val">Some</span>(left), <span class="prelude-val">None</span>) => <span class="prelude-val">Some</span>(left), |
| (<span class="prelude-val">None</span>, <span class="prelude-val">Some</span>(right)) => <span class="prelude-val">Some</span>(right), |
| (<span class="prelude-val">None</span>, <span class="prelude-val">None</span>) => <span class="prelude-val">None</span>, |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>SegmentReader { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter<<span class="lifetime">'_</span>>) -> fmt::Result { |
| <span class="macro">write!</span>(f, <span class="string">"SegmentReader({:?})"</span>, <span class="self">self</span>.segment_id) |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>test { |
| <span class="kw">use </span><span class="kw">crate</span>::core::Index; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{Schema, Term, STORED, TEXT}; |
| <span class="kw">use </span><span class="kw">crate</span>::DocId; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_num_alive() -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| schema_builder.add_text_field(<span class="string">"name"</span>, TEXT | STORED); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>index = Index::create_in_ram(schema.clone()); |
| <span class="kw">let </span>name = schema.get_field(<span class="string">"name"</span>).unwrap(); |
| |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests()<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"tantivy"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"horse"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"jockey"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"cap"</span>))<span class="question-mark">?</span>; |
| <span class="comment">// we should now have one segment with two docs |
| </span>index_writer.delete_term(Term::from_field_text(name, <span class="string">"horse"</span>)); |
| index_writer.delete_term(Term::from_field_text(name, <span class="string">"cap"</span>)); |
| |
| <span class="comment">// ok, now we should have a deleted doc |
| </span>index_writer.commit()<span class="question-mark">?</span>; |
| } |
| <span class="kw">let </span>searcher = index.reader()<span class="question-mark">?</span>.searcher(); |
| <span class="macro">assert_eq!</span>(<span class="number">2</span>, searcher.segment_reader(<span class="number">0</span>).num_docs()); |
| <span class="macro">assert_eq!</span>(<span class="number">4</span>, searcher.segment_reader(<span class="number">0</span>).max_doc()); |
| <span class="prelude-val">Ok</span>(()) |
| } |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_alive_docs_iterator() -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| schema_builder.add_text_field(<span class="string">"name"</span>, TEXT | STORED); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>index = Index::create_in_ram(schema.clone()); |
| <span class="kw">let </span>name = schema.get_field(<span class="string">"name"</span>).unwrap(); |
| |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests()<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"tantivy"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"horse"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"jockey"</span>))<span class="question-mark">?</span>; |
| index_writer.add_document(<span class="macro">doc!</span>(name => <span class="string">"cap"</span>))<span class="question-mark">?</span>; |
| <span class="comment">// we should now have one segment with two docs |
| </span>index_writer.commit()<span class="question-mark">?</span>; |
| } |
| |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer2 = index.writer(<span class="number">50_000_000</span>)<span class="question-mark">?</span>; |
| index_writer2.delete_term(Term::from_field_text(name, <span class="string">"horse"</span>)); |
| index_writer2.delete_term(Term::from_field_text(name, <span class="string">"cap"</span>)); |
| |
| <span class="comment">// ok, now we should have a deleted doc |
| </span>index_writer2.commit()<span class="question-mark">?</span>; |
| } |
| <span class="kw">let </span>searcher = index.reader()<span class="question-mark">?</span>.searcher(); |
| <span class="kw">let </span>docs: Vec<DocId> = searcher.segment_reader(<span class="number">0</span>).doc_ids_alive().collect(); |
| <span class="macro">assert_eq!</span>(<span class="macro">vec!</span>[<span class="number">0u32</span>, <span class="number">2u32</span>], docs); |
| <span class="prelude-val">Ok</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> |