| <!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/postings/recorder.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>recorder.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>common::read_u32_vint; |
| |
| <span class="kw">use </span><span class="kw">super</span>::stacker::{ExpUnrolledLinkedList, MemoryArena}; |
| <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::FieldSerializer; |
| <span class="kw">use </span><span class="kw">crate</span>::DocId; |
| |
| <span class="kw">const </span>POSITION_END: u32 = <span class="number">0</span>; |
| |
| <span class="attribute">#[derive(Default)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>BufferLender { |
| buffer_u8: Vec<u8>, |
| buffer_u32: Vec<u32>, |
| } |
| |
| <span class="kw">impl </span>BufferLender { |
| <span class="kw">pub fn </span>lend_u8(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw-2">&mut </span>Vec<u8> { |
| <span class="self">self</span>.buffer_u8.clear(); |
| <span class="kw-2">&mut </span><span class="self">self</span>.buffer_u8 |
| } |
| <span class="kw">pub fn </span>lend_all(<span class="kw-2">&mut </span><span class="self">self</span>) -> (<span class="kw-2">&mut </span>Vec<u8>, <span class="kw-2">&mut </span>Vec<u32>) { |
| <span class="self">self</span>.buffer_u8.clear(); |
| <span class="self">self</span>.buffer_u32.clear(); |
| (<span class="kw-2">&mut </span><span class="self">self</span>.buffer_u8, <span class="kw-2">&mut </span><span class="self">self</span>.buffer_u32) |
| } |
| } |
| |
| <span class="kw">pub struct </span>VInt32Reader<<span class="lifetime">'a</span>> { |
| data: <span class="kw-2">&</span><span class="lifetime">'a </span>[u8], |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> VInt32Reader<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>new(data: <span class="kw-2">&</span><span class="lifetime">'a </span>[u8]) -> VInt32Reader<<span class="lifetime">'a</span>> { |
| VInt32Reader { data } |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>VInt32Reader<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = u32; |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><u32> { |
| <span class="kw">if </span><span class="self">self</span>.data.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="prelude-val">Some</span>(read_u32_vint(<span class="kw-2">&mut </span><span class="self">self</span>.data)) |
| } |
| } |
| } |
| |
| <span class="doccomment">/// `Recorder` is in charge of recording relevant information about |
| /// the presence of a term in a document. |
| /// |
| /// Depending on the [`TextOptions`](crate::schema::TextOptions) associated |
| /// with the field, the recorder may record: |
| /// * the document frequency |
| /// * the document id |
| /// * the term frequency |
| /// * the term positions |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait </span>Recorder: Copy + Default + Send + Sync + <span class="lifetime">'static </span>{ |
| <span class="doccomment">/// Returns the current document |
| </span><span class="kw">fn </span>current_doc(<span class="kw-2">&</span><span class="self">self</span>) -> u32; |
| <span class="doccomment">/// Starts recording information about a new document |
| /// This method shall only be called if the term is within the document. |
| </span><span class="kw">fn </span>new_doc(<span class="kw-2">&mut </span><span class="self">self</span>, doc: DocId, arena: <span class="kw-2">&mut </span>MemoryArena); |
| <span class="doccomment">/// Record the position of a term. For each document, |
| /// this method will be called `term_freq` times. |
| </span><span class="kw">fn </span>record_position(<span class="kw-2">&mut </span><span class="self">self</span>, position: u32, arena: <span class="kw-2">&mut </span>MemoryArena); |
| <span class="doccomment">/// Close the document. It will help record the term frequency. |
| </span><span class="kw">fn </span>close_doc(<span class="kw-2">&mut </span><span class="self">self</span>, arena: <span class="kw-2">&mut </span>MemoryArena); |
| <span class="doccomment">/// Pushes the postings information to the serializer. |
| </span><span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| arena: <span class="kw-2">&</span>MemoryArena, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer<<span class="lifetime">'_</span>>, |
| buffer_lender: <span class="kw-2">&mut </span>BufferLender, |
| ); |
| <span class="doccomment">/// Returns the number of document containing this term. |
| /// |
| /// Returns `None` if not available. |
| </span><span class="kw">fn </span>term_doc_freq(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><u32>; |
| } |
| |
| <span class="doccomment">/// Only records the doc ids |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">pub struct </span>DocIdRecorder { |
| stack: ExpUnrolledLinkedList, |
| current_doc: DocId, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>DocIdRecorder { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| DocIdRecorder { |
| stack: ExpUnrolledLinkedList::new(), |
| current_doc: u32::MAX, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Recorder <span class="kw">for </span>DocIdRecorder { |
| <span class="kw">fn </span>current_doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.current_doc |
| } |
| |
| <span class="kw">fn </span>new_doc(<span class="kw-2">&mut </span><span class="self">self</span>, doc: DocId, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.current_doc = doc; |
| <span class="self">self</span>.stack.writer(arena).write_u32_vint(doc); |
| } |
| |
| <span class="kw">fn </span>record_position(<span class="kw-2">&mut </span><span class="self">self</span>, _position: u32, _arena: <span class="kw-2">&mut </span>MemoryArena) {} |
| |
| <span class="kw">fn </span>close_doc(<span class="kw-2">&mut </span><span class="self">self</span>, _arena: <span class="kw-2">&mut </span>MemoryArena) {} |
| |
| <span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| arena: <span class="kw-2">&</span>MemoryArena, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer<<span class="lifetime">'_</span>>, |
| buffer_lender: <span class="kw-2">&mut </span>BufferLender, |
| ) { |
| <span class="kw">let </span>(buffer, doc_ids) = buffer_lender.lend_all(); |
| <span class="self">self</span>.stack.read_to_end(arena, buffer); |
| <span class="comment">// TODO avoid reading twice. |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| doc_ids.extend( |
| VInt32Reader::new(<span class="kw-2">&</span>buffer[..]) |
| .map(|old_doc_id| doc_id_map.get_new_doc_id(old_doc_id)), |
| ); |
| doc_ids.sort_unstable(); |
| |
| <span class="kw">for </span>doc <span class="kw">in </span>doc_ids { |
| serializer.write_doc(<span class="kw-2">*</span>doc, <span class="number">0u32</span>, <span class="kw-2">&</span>[][..]); |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">for </span>doc <span class="kw">in </span>VInt32Reader::new(<span class="kw-2">&</span>buffer[..]) { |
| serializer.write_doc(doc, <span class="number">0u32</span>, <span class="kw-2">&</span>[][..]); |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>term_doc_freq(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><u32> { |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="doccomment">/// Recorder encoding document ids, and term frequencies |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">pub struct </span>TermFrequencyRecorder { |
| stack: ExpUnrolledLinkedList, |
| current_doc: DocId, |
| current_tf: u32, |
| term_doc_freq: u32, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>TermFrequencyRecorder { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| TermFrequencyRecorder { |
| stack: ExpUnrolledLinkedList::new(), |
| current_doc: <span class="number">0</span>, |
| current_tf: <span class="number">0u32</span>, |
| term_doc_freq: <span class="number">0u32</span>, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Recorder <span class="kw">for </span>TermFrequencyRecorder { |
| <span class="kw">fn </span>current_doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.current_doc |
| } |
| |
| <span class="kw">fn </span>new_doc(<span class="kw-2">&mut </span><span class="self">self</span>, doc: DocId, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.term_doc_freq += <span class="number">1</span>; |
| <span class="self">self</span>.current_doc = doc; |
| <span class="self">self</span>.stack.writer(arena).write_u32_vint(doc); |
| } |
| |
| <span class="kw">fn </span>record_position(<span class="kw-2">&mut </span><span class="self">self</span>, _position: u32, _arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.current_tf += <span class="number">1</span>; |
| } |
| |
| <span class="kw">fn </span>close_doc(<span class="kw-2">&mut </span><span class="self">self</span>, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.current_tf > <span class="number">0</span>); |
| <span class="self">self</span>.stack.writer(arena).write_u32_vint(<span class="self">self</span>.current_tf); |
| <span class="self">self</span>.current_tf = <span class="number">0</span>; |
| } |
| |
| <span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| arena: <span class="kw-2">&</span>MemoryArena, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer<<span class="lifetime">'_</span>>, |
| buffer_lender: <span class="kw-2">&mut </span>BufferLender, |
| ) { |
| <span class="kw">let </span>buffer = buffer_lender.lend_u8(); |
| <span class="self">self</span>.stack.read_to_end(arena, buffer); |
| <span class="kw">let </span><span class="kw-2">mut </span>u32_it = VInt32Reader::new(<span class="kw-2">&</span>buffer[..]); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| <span class="kw">let </span><span class="kw-2">mut </span>doc_id_and_tf = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(old_doc_id) = u32_it.next() { |
| <span class="kw">let </span>term_freq = u32_it.next().unwrap_or(<span class="self">self</span>.current_tf); |
| doc_id_and_tf.push((doc_id_map.get_new_doc_id(old_doc_id), term_freq)); |
| } |
| doc_id_and_tf.sort_unstable_by_key(|<span class="kw-2">&</span>(doc_id, <span class="kw">_</span>)| doc_id); |
| |
| <span class="kw">for </span>(doc_id, tf) <span class="kw">in </span>doc_id_and_tf { |
| serializer.write_doc(doc_id, tf, <span class="kw-2">&</span>[][..]); |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(doc) = u32_it.next() { |
| <span class="kw">let </span>term_freq = u32_it.next().unwrap_or(<span class="self">self</span>.current_tf); |
| serializer.write_doc(doc, term_freq, <span class="kw-2">&</span>[][..]); |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>term_doc_freq(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><u32> { |
| <span class="prelude-val">Some</span>(<span class="self">self</span>.term_doc_freq) |
| } |
| } |
| |
| <span class="doccomment">/// Recorder encoding term frequencies as well as positions. |
| </span><span class="attribute">#[derive(Clone, Copy)] |
| </span><span class="kw">pub struct </span>TfAndPositionRecorder { |
| stack: ExpUnrolledLinkedList, |
| current_doc: DocId, |
| term_doc_freq: u32, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>TfAndPositionRecorder { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| TfAndPositionRecorder { |
| stack: ExpUnrolledLinkedList::new(), |
| current_doc: u32::MAX, |
| term_doc_freq: <span class="number">0u32</span>, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>Recorder <span class="kw">for </span>TfAndPositionRecorder { |
| <span class="kw">fn </span>current_doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.current_doc |
| } |
| |
| <span class="kw">fn </span>new_doc(<span class="kw-2">&mut </span><span class="self">self</span>, doc: DocId, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.current_doc = doc; |
| <span class="self">self</span>.term_doc_freq += <span class="number">1u32</span>; |
| <span class="self">self</span>.stack.writer(arena).write_u32_vint(doc); |
| } |
| |
| <span class="kw">fn </span>record_position(<span class="kw-2">&mut </span><span class="self">self</span>, position: u32, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.stack |
| .writer(arena) |
| .write_u32_vint(position.wrapping_add(<span class="number">1u32</span>)); |
| } |
| |
| <span class="kw">fn </span>close_doc(<span class="kw-2">&mut </span><span class="self">self</span>, arena: <span class="kw-2">&mut </span>MemoryArena) { |
| <span class="self">self</span>.stack.writer(arena).write_u32_vint(POSITION_END); |
| } |
| |
| <span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| arena: <span class="kw-2">&</span>MemoryArena, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer<<span class="lifetime">'_</span>>, |
| buffer_lender: <span class="kw-2">&mut </span>BufferLender, |
| ) { |
| <span class="kw">let </span>(buffer_u8, buffer_positions) = buffer_lender.lend_all(); |
| <span class="self">self</span>.stack.read_to_end(arena, buffer_u8); |
| <span class="kw">let </span><span class="kw-2">mut </span>u32_it = VInt32Reader::new(<span class="kw-2">&</span>buffer_u8[..]); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc_id_and_positions = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(doc) = u32_it.next() { |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_position_plus_one = <span class="number">1u32</span>; |
| buffer_positions.clear(); |
| <span class="kw">loop </span>{ |
| <span class="kw">match </span>u32_it.next() { |
| <span class="prelude-val">Some</span>(POSITION_END) | <span class="prelude-val">None </span>=> { |
| <span class="kw">break</span>; |
| } |
| <span class="prelude-val">Some</span>(position_plus_one) => { |
| <span class="kw">let </span>delta_position = position_plus_one - prev_position_plus_one; |
| buffer_positions.push(delta_position); |
| prev_position_plus_one = position_plus_one; |
| } |
| } |
| } |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| <span class="comment">// this simple variant to remap may consume to much memory |
| </span>doc_id_and_positions |
| .push((doc_id_map.get_new_doc_id(doc), buffer_positions.to_vec())); |
| } <span class="kw">else </span>{ |
| serializer.write_doc(doc, buffer_positions.len() <span class="kw">as </span>u32, buffer_positions); |
| } |
| } |
| <span class="kw">if </span>doc_id_map.is_some() { |
| doc_id_and_positions.sort_unstable_by_key(|<span class="kw-2">&</span>(doc_id, <span class="kw">_</span>)| doc_id); |
| <span class="kw">for </span>(doc_id, positions) <span class="kw">in </span>doc_id_and_positions { |
| serializer.write_doc(doc_id, positions.len() <span class="kw">as </span>u32, <span class="kw-2">&</span>positions); |
| } |
| } |
| } |
| |
| <span class="kw">fn </span>term_doc_freq(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><u32> { |
| <span class="prelude-val">Some</span>(<span class="self">self</span>.term_doc_freq) |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>common::write_u32_vint; |
| |
| <span class="kw">use super</span>::{BufferLender, VInt32Reader}; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_buffer_lender() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer_lender = BufferLender::default(); |
| { |
| <span class="kw">let </span>buf = buffer_lender.lend_u8(); |
| <span class="macro">assert!</span>(buf.is_empty()); |
| buf.push(<span class="number">1u8</span>); |
| } |
| { |
| <span class="kw">let </span>buf = buffer_lender.lend_u8(); |
| <span class="macro">assert!</span>(buf.is_empty()); |
| buf.push(<span class="number">1u8</span>); |
| } |
| { |
| <span class="kw">let </span>(<span class="kw">_</span>, buf) = buffer_lender.lend_all(); |
| <span class="macro">assert!</span>(buf.is_empty()); |
| buf.push(<span class="number">1u32</span>); |
| } |
| { |
| <span class="kw">let </span>(<span class="kw">_</span>, buf) = buffer_lender.lend_all(); |
| <span class="macro">assert!</span>(buf.is_empty()); |
| buf.push(<span class="number">1u32</span>); |
| } |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_vint_u32() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span>vals = [<span class="number">0</span>, <span class="number">1</span>, <span class="number">324_234_234</span>, u32::MAX]; |
| <span class="kw">for </span><span class="kw-2">&</span>i <span class="kw">in </span><span class="kw-2">&</span>vals { |
| <span class="macro">assert!</span>(write_u32_vint(i, <span class="kw-2">&mut </span>buffer).is_ok()); |
| } |
| <span class="macro">assert_eq!</span>(buffer.len(), <span class="number">1 </span>+ <span class="number">1 </span>+ <span class="number">5 </span>+ <span class="number">5</span>); |
| <span class="kw">let </span>res: Vec<u32> = VInt32Reader::new(<span class="kw-2">&</span>buffer[..]).collect(); |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>res[..], <span class="kw-2">&</span>vals[..]); |
| } |
| } |
| </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> |