| <!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/segment_postings.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>segment_postings.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>common::HasLen; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::docset::DocSet; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::AliveBitSet; |
| <span class="kw">use </span><span class="kw">crate</span>::positions::PositionReader; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::compression::COMPRESSION_BLOCK_SIZE; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::{branchless_binary_search, BlockSegmentPostings, Postings}; |
| <span class="kw">use crate</span>::{DocId, TERMINATED}; |
| |
| <span class="doccomment">/// `SegmentPostings` represents the inverted list or postings associated with |
| /// a term in a `Segment`. |
| /// |
| /// As we iterate through the `SegmentPostings`, the frequencies are optionally decoded. |
| /// Positions on the other hand, are optionally entirely decoded upfront. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>SegmentPostings { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) block_cursor: BlockSegmentPostings, |
| cur: usize, |
| position_reader: <span class="prelude-ty">Option</span><PositionReader>, |
| } |
| |
| <span class="kw">impl </span>SegmentPostings { |
| <span class="doccomment">/// Returns an empty segment postings object |
| </span><span class="kw">pub fn </span>empty() -> <span class="self">Self </span>{ |
| SegmentPostings { |
| block_cursor: BlockSegmentPostings::empty(), |
| cur: <span class="number">0</span>, |
| position_reader: <span class="prelude-val">None</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Compute the number of non-deleted documents. |
| /// |
| /// This method will clone and scan through the posting lists. |
| /// (this is a rather expensive operation). |
| </span><span class="kw">pub fn </span>doc_freq_given_deletes(<span class="kw-2">&</span><span class="self">self</span>, alive_bitset: <span class="kw-2">&</span>AliveBitSet) -> u32 { |
| <span class="kw">let </span><span class="kw-2">mut </span>docset = <span class="self">self</span>.clone(); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc_freq = <span class="number">0</span>; |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>doc = docset.doc(); |
| <span class="kw">if </span>doc == TERMINATED { |
| <span class="kw">return </span>doc_freq; |
| } |
| <span class="kw">if </span>alive_bitset.is_alive(doc) { |
| doc_freq += <span class="number">1u32</span>; |
| } |
| docset.advance(); |
| } |
| } |
| |
| <span class="doccomment">/// Returns the overall number of documents in the block postings. |
| /// It does not take in account whether documents are deleted or not. |
| </span><span class="kw">pub fn </span>doc_freq(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.block_cursor.doc_freq() |
| } |
| |
| <span class="doccomment">/// Creates a segment postings object with the given documents |
| /// and no frequency encoded. |
| /// |
| /// This method is mostly useful for unit tests. |
| /// |
| /// It serializes the doc ids using tantivy's codec |
| /// and returns a `SegmentPostings` object that embeds a |
| /// buffer with the serialized data. |
| </span><span class="attribute">#[cfg(test)] |
| </span><span class="kw">pub fn </span>create_from_docs(docs: <span class="kw-2">&</span>[u32]) -> SegmentPostings { |
| <span class="kw">use </span><span class="kw">crate</span>::directory::FileSlice; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::serializer::PostingsSerializer; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::IndexRecordOption; |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>postings_serializer = |
| PostingsSerializer::new(<span class="kw-2">&mut </span>buffer, <span class="number">0.0</span>, IndexRecordOption::Basic, <span class="prelude-val">None</span>); |
| postings_serializer.new_term(docs.len() <span class="kw">as </span>u32); |
| <span class="kw">for </span><span class="kw-2">&</span>doc <span class="kw">in </span>docs { |
| postings_serializer.write_doc(doc, <span class="number">1u32</span>); |
| } |
| postings_serializer |
| .close_term(docs.len() <span class="kw">as </span>u32) |
| .expect(<span class="string">"In memory Serialization should never fail."</span>); |
| } |
| <span class="kw">let </span>block_segment_postings = BlockSegmentPostings::open( |
| docs.len() <span class="kw">as </span>u32, |
| FileSlice::from(buffer), |
| IndexRecordOption::Basic, |
| IndexRecordOption::Basic, |
| ) |
| .unwrap(); |
| SegmentPostings::from_block_postings(block_segment_postings, <span class="prelude-val">None</span>) |
| } |
| |
| <span class="doccomment">/// Helper functions to create `SegmentPostings` for tests. |
| </span><span class="attribute">#[cfg(test)] |
| </span><span class="kw">pub fn </span>create_from_docs_and_tfs( |
| doc_and_tfs: <span class="kw-2">&</span>[(u32, u32)], |
| fieldnorms: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>[u32]>, |
| ) -> SegmentPostings { |
| <span class="kw">use </span><span class="kw">crate</span>::directory::FileSlice; |
| <span class="kw">use </span><span class="kw">crate</span>::fieldnorm::FieldNormReader; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::serializer::PostingsSerializer; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::IndexRecordOption; |
| <span class="kw">use </span><span class="kw">crate</span>::Score; |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer: Vec<u8> = Vec::new(); |
| <span class="kw">let </span>fieldnorm_reader = fieldnorms.map(FieldNormReader::for_test); |
| <span class="kw">let </span>average_field_norm = fieldnorms |
| .map(|fieldnorms| { |
| <span class="kw">if </span>fieldnorms.is_empty() { |
| <span class="kw">return </span><span class="number">0.0</span>; |
| } |
| <span class="kw">let </span>total_num_tokens: u64 = fieldnorms |
| .iter() |
| .map(|<span class="kw-2">&</span>fieldnorm| fieldnorm <span class="kw">as </span>u64) |
| .sum::<u64>(); |
| total_num_tokens <span class="kw">as </span>Score / fieldnorms.len() <span class="kw">as </span>Score |
| }) |
| .unwrap_or(<span class="number">0.0</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings_serializer = PostingsSerializer::new( |
| <span class="kw-2">&mut </span>buffer, |
| average_field_norm, |
| IndexRecordOption::WithFreqs, |
| fieldnorm_reader, |
| ); |
| postings_serializer.new_term(doc_and_tfs.len() <span class="kw">as </span>u32); |
| <span class="kw">for </span><span class="kw-2">&</span>(doc, tf) <span class="kw">in </span>doc_and_tfs { |
| postings_serializer.write_doc(doc, tf); |
| } |
| postings_serializer |
| .close_term(doc_and_tfs.len() <span class="kw">as </span>u32) |
| .unwrap(); |
| <span class="kw">let </span>block_segment_postings = BlockSegmentPostings::open( |
| doc_and_tfs.len() <span class="kw">as </span>u32, |
| FileSlice::from(buffer), |
| IndexRecordOption::WithFreqs, |
| IndexRecordOption::WithFreqs, |
| ) |
| .unwrap(); |
| SegmentPostings::from_block_postings(block_segment_postings, <span class="prelude-val">None</span>) |
| } |
| |
| <span class="doccomment">/// Reads a Segment postings from an &[u8] |
| /// |
| /// * `len` - number of document in the posting lists. |
| /// * `data` - data array. The complete data is not necessarily used. |
| /// * `freq_handler` - the freq handler is in charge of decoding frequencies and/or positions |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>from_block_postings( |
| segment_block_postings: BlockSegmentPostings, |
| position_reader: <span class="prelude-ty">Option</span><PositionReader>, |
| ) -> SegmentPostings { |
| SegmentPostings { |
| block_cursor: segment_block_postings, |
| cur: <span class="number">0</span>, <span class="comment">// cursor within the block |
| </span>position_reader, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>DocSet <span class="kw">for </span>SegmentPostings { |
| <span class="comment">// goes to the next element. |
| // next needs to be called a first time to point to the correct element. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>advance(<span class="kw-2">&mut </span><span class="self">self</span>) -> DocId { |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.block_cursor.block_is_loaded()); |
| <span class="kw">if </span><span class="self">self</span>.cur == COMPRESSION_BLOCK_SIZE - <span class="number">1 </span>{ |
| <span class="self">self</span>.cur = <span class="number">0</span>; |
| <span class="self">self</span>.block_cursor.advance(); |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.cur += <span class="number">1</span>; |
| } |
| <span class="self">self</span>.doc() |
| } |
| |
| <span class="kw">fn </span>seek(<span class="kw-2">&mut </span><span class="self">self</span>, target: DocId) -> DocId { |
| <span class="macro">debug_assert!</span>(<span class="self">self</span>.doc() <= target); |
| <span class="kw">if </span><span class="self">self</span>.doc() >= target { |
| <span class="kw">return </span><span class="self">self</span>.doc(); |
| } |
| |
| <span class="self">self</span>.block_cursor.seek(target); |
| |
| <span class="comment">// At this point we are on the block, that might contain our document. |
| </span><span class="kw">let </span>output = <span class="self">self</span>.block_cursor.full_block(); |
| <span class="self">self</span>.cur = branchless_binary_search(output, target); |
| |
| <span class="comment">// The last block is not full and padded with the value TERMINATED, |
| // so that we are guaranteed to have at least doc in the block (a real one or the padding) |
| // that is greater or equal to the target. |
| </span><span class="macro">debug_assert!</span>(<span class="self">self</span>.cur < COMPRESSION_BLOCK_SIZE); |
| |
| <span class="comment">// `doc` is now the first element >= `target` |
| |
| // If all docs are smaller than target the current block should be incomplemented and padded |
| // with the value `TERMINATED`. |
| // |
| // After the search, the cursor should point to the first value of TERMINATED. |
| </span><span class="kw">let </span>doc = output[<span class="self">self</span>.cur]; |
| <span class="macro">debug_assert!</span>(doc >= target); |
| <span class="macro">debug_assert_eq!</span>(doc, <span class="self">self</span>.doc()); |
| doc |
| } |
| |
| <span class="doccomment">/// Return the current document's `DocId`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>doc(<span class="kw-2">&</span><span class="self">self</span>) -> DocId { |
| <span class="self">self</span>.block_cursor.doc(<span class="self">self</span>.cur) |
| } |
| |
| <span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.len() <span class="kw">as </span>u32 |
| } |
| } |
| |
| <span class="kw">impl </span>HasLen <span class="kw">for </span>SegmentPostings { |
| <span class="kw">fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.block_cursor.doc_freq() <span class="kw">as </span>usize |
| } |
| } |
| |
| <span class="kw">impl </span>Postings <span class="kw">for </span>SegmentPostings { |
| <span class="doccomment">/// Returns the frequency associated with the current document. |
| /// If the schema is set up so that no frequency have been encoded, |
| /// this method should always return 1. |
| /// |
| /// # Panics |
| /// |
| /// Will panics if called without having called advance before. |
| </span><span class="kw">fn </span>term_freq(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="macro">debug_assert!</span>( |
| <span class="comment">// Here we do not use the len of `freqs()` |
| // because it is actually ok to request for the freq of doc |
| // even if no frequency were encoded for the field. |
| // |
| // In that case we hit the block just as if the frequency had been |
| // decoded. The block is simply prefilled by the value 1. |
| </span><span class="self">self</span>.cur < COMPRESSION_BLOCK_SIZE, |
| <span class="string">"Have you forgotten to call `.advance()` at least once before calling `.term_freq()`." |
| </span>); |
| <span class="self">self</span>.block_cursor.freq(<span class="self">self</span>.cur) |
| } |
| |
| <span class="kw">fn </span>positions_with_offset(<span class="kw-2">&mut </span><span class="self">self</span>, offset: u32, output: <span class="kw-2">&mut </span>Vec<u32>) { |
| <span class="kw">let </span>term_freq = <span class="self">self</span>.term_freq() <span class="kw">as </span>usize; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(position_reader) = <span class="self">self</span>.position_reader.as_mut() { |
| <span class="kw">let </span>read_offset = <span class="self">self</span>.block_cursor.position_offset() |
| + (<span class="self">self</span>.block_cursor.freqs()[..<span class="self">self</span>.cur] |
| .iter() |
| .cloned() |
| .sum::<u32>() <span class="kw">as </span>u64); |
| output.resize(term_freq, <span class="number">0u32</span>); |
| position_reader.read(read_offset, <span class="kw-2">&mut </span>output[..]); |
| <span class="kw">let </span><span class="kw-2">mut </span>cum = offset; |
| <span class="kw">for </span>output_mut <span class="kw">in </span>output.iter_mut() { |
| cum += <span class="kw-2">*</span>output_mut; |
| <span class="kw-2">*</span>output_mut = cum; |
| } |
| } <span class="kw">else </span>{ |
| output.clear(); |
| } |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>common::HasLen; |
| |
| <span class="kw">use </span><span class="kw">super</span>::SegmentPostings; |
| <span class="kw">use </span><span class="kw">crate</span>::docset::{DocSet, TERMINATED}; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::AliveBitSet; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::postings::Postings; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_empty_segment_postings() { |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = SegmentPostings::empty(); |
| <span class="macro">assert_eq!</span>(postings.advance(), TERMINATED); |
| <span class="macro">assert_eq!</span>(postings.advance(), TERMINATED); |
| <span class="macro">assert_eq!</span>(postings.len(), <span class="number">0</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_empty_postings_doc_returns_terminated() { |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = SegmentPostings::empty(); |
| <span class="macro">assert_eq!</span>(postings.doc(), TERMINATED); |
| <span class="macro">assert_eq!</span>(postings.advance(), TERMINATED); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_empty_postings_doc_term_freq_returns_0() { |
| <span class="kw">let </span>postings = SegmentPostings::empty(); |
| <span class="macro">assert_eq!</span>(postings.term_freq(), <span class="number">1</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_doc_freq() { |
| <span class="kw">let </span>docs = SegmentPostings::create_from_docs(<span class="kw-2">&</span>[<span class="number">0</span>, <span class="number">2</span>, <span class="number">10</span>]); |
| <span class="macro">assert_eq!</span>(docs.doc_freq(), <span class="number">3</span>); |
| <span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&</span>[<span class="number">2</span>], <span class="number">12</span>); |
| <span class="macro">assert_eq!</span>(docs.doc_freq_given_deletes(<span class="kw-2">&</span>alive_bitset), <span class="number">2</span>); |
| <span class="kw">let </span>all_deleted = |
| AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&</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="number">10</span>, <span class="number">11</span>], <span class="number">12</span>); |
| <span class="macro">assert_eq!</span>(docs.doc_freq_given_deletes(<span class="kw-2">&</span>all_deleted), <span class="number">0</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> |