| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/git/checkouts/tantivy-65d0bbbddbbd5d02/433372d/src/query/more_like_this/more_like_this.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>more_like_this.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::cmp::Reverse; |
| <span class="kw">use </span>std::collections::{BinaryHeap, HashMap}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::query::bm25::idf; |
| <span class="kw">use </span><span class="kw">crate</span>::query::{BooleanQuery, BoostQuery, Occur, Query, TermQuery}; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{Field, FieldType, IndexRecordOption, Term, Value}; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{BoxTokenStream, FacetTokenizer, PreTokenizedStream, Tokenizer}; |
| <span class="kw">use crate</span>::{DocAddress, <span class="prelude-ty">Result</span>, Searcher, TantivyError}; |
| |
| <span class="attribute">#[derive(Debug, PartialEq)] |
| </span><span class="kw">struct </span>ScoreTerm { |
| <span class="kw">pub </span>term: Term, |
| <span class="kw">pub </span>score: f32, |
| } |
| |
| <span class="kw">impl </span>ScoreTerm { |
| <span class="kw">fn </span>new(term: Term, score: f32) -> <span class="self">Self </span>{ |
| <span class="self">Self </span>{ term, score } |
| } |
| } |
| |
| <span class="kw">impl </span>Eq <span class="kw">for </span>ScoreTerm {} |
| |
| <span class="kw">impl </span>PartialOrd <span class="kw">for </span>ScoreTerm { |
| <span class="kw">fn </span>partial_cmp(<span class="kw-2">&</span><span class="self">self</span>, other: <span class="kw-2">&</span><span class="self">Self</span>) -> <span class="prelude-ty">Option</span><std::cmp::Ordering> { |
| <span class="self">self</span>.score.partial_cmp(<span class="kw-2">&</span>other.score) |
| } |
| } |
| |
| <span class="kw">impl </span>Ord <span class="kw">for </span>ScoreTerm { |
| <span class="kw">fn </span>cmp(<span class="kw-2">&</span><span class="self">self</span>, other: <span class="kw-2">&</span><span class="self">Self</span>) -> std::cmp::Ordering { |
| <span class="self">self</span>.partial_cmp(other).unwrap_or(std::cmp::Ordering::Equal) |
| } |
| } |
| |
| <span class="doccomment">/// A struct used as helper to build [`MoreLikeThisQuery`](crate::query::MoreLikeThisQuery) |
| /// This more-like-this implementation is inspired by the Apache Lucene |
| /// and closely follows the same implementation with adaptation to Tantivy vocabulary and API. |
| /// |
| /// [MoreLikeThis](https://github.com/apache/lucene/blob/main/lucene/queries/src/java/org/apache/lucene/queries/mlt/MoreLikeThis.java#L147) |
| /// [MoreLikeThisQuery](https://github.com/apache/lucene/blob/main/lucene/queries/src/java/org/apache/lucene/queries/mlt/MoreLikeThisQuery.java#L36) |
| </span><span class="attribute">#[derive(Debug, Clone)] |
| </span><span class="kw">pub struct </span>MoreLikeThis { |
| <span class="doccomment">/// Ignore words which do not occur in at least this many docs. |
| </span><span class="kw">pub </span>min_doc_frequency: <span class="prelude-ty">Option</span><u64>, |
| <span class="doccomment">/// Ignore words which occur in more than this many docs. |
| </span><span class="kw">pub </span>max_doc_frequency: <span class="prelude-ty">Option</span><u64>, |
| <span class="doccomment">/// Ignore words less frequent than this. |
| </span><span class="kw">pub </span>min_term_frequency: <span class="prelude-ty">Option</span><usize>, |
| <span class="doccomment">/// Don't return a query longer than this. |
| </span><span class="kw">pub </span>max_query_terms: <span class="prelude-ty">Option</span><usize>, |
| <span class="doccomment">/// Ignore words if less than this length. |
| </span><span class="kw">pub </span>min_word_length: <span class="prelude-ty">Option</span><usize>, |
| <span class="doccomment">/// Ignore words if greater than this length. |
| </span><span class="kw">pub </span>max_word_length: <span class="prelude-ty">Option</span><usize>, |
| <span class="doccomment">/// Boost factor to use when boosting the terms |
| </span><span class="kw">pub </span>boost_factor: <span class="prelude-ty">Option</span><f32>, |
| <span class="doccomment">/// Current set of stop words. |
| </span><span class="kw">pub </span>stop_words: Vec<String>, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>MoreLikeThis { |
| <span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| <span class="self">Self </span>{ |
| min_doc_frequency: <span class="prelude-val">Some</span>(<span class="number">5</span>), |
| max_doc_frequency: <span class="prelude-val">None</span>, |
| min_term_frequency: <span class="prelude-val">Some</span>(<span class="number">2</span>), |
| max_query_terms: <span class="prelude-val">Some</span>(<span class="number">25</span>), |
| min_word_length: <span class="prelude-val">None</span>, |
| max_word_length: <span class="prelude-val">None</span>, |
| boost_factor: <span class="prelude-val">Some</span>(<span class="number">1.0</span>), |
| stop_words: <span class="macro">vec!</span>[], |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>MoreLikeThis { |
| <span class="doccomment">/// Creates a [`BooleanQuery`] using a document address to collect |
| /// the top stored field values. |
| </span><span class="kw">pub fn </span>query_with_document( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| doc_address: DocAddress, |
| ) -> <span class="prelude-ty">Result</span><BooleanQuery> { |
| <span class="kw">let </span>score_terms = <span class="self">self</span>.retrieve_terms_from_doc_address(searcher, doc_address)<span class="question-mark">?</span>; |
| <span class="kw">let </span>query = <span class="self">self</span>.create_query(score_terms); |
| <span class="prelude-val">Ok</span>(query) |
| } |
| |
| <span class="doccomment">/// Creates a [`BooleanQuery`] using a set of field values. |
| </span><span class="kw">pub fn </span>query_with_document_fields( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| doc_fields: <span class="kw-2">&</span>[(Field, Vec<Value>)], |
| ) -> <span class="prelude-ty">Result</span><BooleanQuery> { |
| <span class="kw">let </span>score_terms = <span class="self">self</span>.retrieve_terms_from_doc_fields(searcher, doc_fields)<span class="question-mark">?</span>; |
| <span class="kw">let </span>query = <span class="self">self</span>.create_query(score_terms); |
| <span class="prelude-val">Ok</span>(query) |
| } |
| |
| <span class="doccomment">/// Creates a [`BooleanQuery`] from an ascendingly sorted list of ScoreTerm |
| /// This will map the list of ScoreTerm to a list of [`TermQuery`] and compose a |
| /// BooleanQuery using that list as sub queries. |
| </span><span class="kw">fn </span>create_query(<span class="kw-2">&</span><span class="self">self</span>, <span class="kw-2">mut </span>score_terms: Vec<ScoreTerm>) -> BooleanQuery { |
| score_terms.sort_by(|left_ts, right_ts| right_ts.cmp(left_ts)); |
| <span class="kw">let </span>best_score = score_terms.first().map_or(<span class="number">1f32</span>, |x| x.score); |
| <span class="kw">let </span><span class="kw-2">mut </span>queries = Vec::new(); |
| |
| <span class="kw">for </span>ScoreTerm { term, score } <span class="kw">in </span>score_terms { |
| <span class="kw">let </span><span class="kw-2">mut </span>query: Box<<span class="kw">dyn </span>Query> = |
| Box::new(TermQuery::new(term, IndexRecordOption::Basic)); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(factor) = <span class="self">self</span>.boost_factor { |
| query = Box::new(BoostQuery::new(query, score * factor / best_score)); |
| } |
| queries.push((Occur::Should, query)); |
| } |
| BooleanQuery::from(queries) |
| } |
| |
| <span class="doccomment">/// Finds terms for a more-like-this query. |
| /// doc_address is the address of document from which to find terms. |
| </span><span class="kw">fn </span>retrieve_terms_from_doc_address( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| doc_address: DocAddress, |
| ) -> <span class="prelude-ty">Result</span><Vec<ScoreTerm>> { |
| <span class="kw">let </span>doc = searcher.doc(doc_address)<span class="question-mark">?</span>; |
| <span class="kw">let </span>field_to_values = doc |
| .get_sorted_field_values() |
| .iter() |
| .map(|(field, values)| { |
| ( |
| <span class="kw-2">*</span>field, |
| values.iter().map(|v| (<span class="kw-2">**</span>v).clone()).collect::<Vec<Value>>(), |
| ) |
| }) |
| .collect::<Vec<<span class="kw">_</span>>>(); |
| <span class="self">self</span>.retrieve_terms_from_doc_fields(searcher, <span class="kw-2">&</span>field_to_values) |
| } |
| |
| <span class="doccomment">/// Finds terms for a more-like-this query. |
| /// field_to_field_values is a mapping from field to possible values of that field. |
| </span><span class="kw">fn </span>retrieve_terms_from_doc_fields( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| field_to_values: <span class="kw-2">&</span>[(Field, Vec<Value>)], |
| ) -> <span class="prelude-ty">Result</span><Vec<ScoreTerm>> { |
| <span class="kw">if </span>field_to_values.is_empty() { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(TantivyError::InvalidArgument( |
| <span class="string">"Cannot create more like this query on empty field values. The document may not \ |
| have stored fields" |
| </span>.to_string(), |
| )); |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>field_to_term_freq_map = HashMap::new(); |
| <span class="kw">for </span>(field, values) <span class="kw">in </span>field_to_values { |
| <span class="self">self</span>.add_term_frequencies(searcher, <span class="kw-2">*</span>field, values, <span class="kw-2">&mut </span>field_to_term_freq_map)<span class="question-mark">?</span>; |
| } |
| <span class="self">self</span>.create_score_term(searcher, field_to_term_freq_map) |
| } |
| |
| <span class="doccomment">/// Computes the frequency of values for a field while updating the term frequencies |
| /// Note: A FieldValue can be made up of multiple terms. |
| /// We are interested in extracting terms within FieldValue |
| </span><span class="kw">fn </span>add_term_frequencies( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| field: Field, |
| values: <span class="kw-2">&</span>[Value], |
| term_frequencies: <span class="kw-2">&mut </span>HashMap<Term, usize>, |
| ) -> <span class="prelude-ty">Result</span><()> { |
| <span class="kw">let </span>schema = searcher.schema(); |
| <span class="kw">let </span>tokenizer_manager = searcher.index().tokenizers(); |
| |
| <span class="kw">let </span>field_entry = schema.get_field_entry(field); |
| <span class="kw">if </span>!field_entry.is_indexed() { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(()); |
| } |
| |
| <span class="comment">// extract the raw value, possibly tokenizing & filtering to update the term frequency map |
| </span><span class="kw">match </span>field_entry.field_type() { |
| FieldType::Facet(<span class="kw">_</span>) => { |
| <span class="kw">let </span>facets: Vec<<span class="kw-2">&</span>str> = values |
| .iter() |
| .map(|value| <span class="kw">match </span>value { |
| Value::Facet(<span class="kw-2">ref </span>facet) => <span class="prelude-val">Ok</span>(facet.encoded_str()), |
| <span class="kw">_ </span>=> <span class="prelude-val">Err</span>(TantivyError::InvalidArgument( |
| <span class="string">"invalid field value"</span>.to_string(), |
| )), |
| }) |
| .collect::<<span class="prelude-ty">Result</span><Vec<<span class="kw">_</span>>>>()<span class="question-mark">?</span>; |
| <span class="kw">for </span>fake_str <span class="kw">in </span>facets { |
| FacetTokenizer.token_stream(fake_str).process(<span class="kw-2">&mut </span>|token| { |
| <span class="kw">if </span><span class="self">self</span>.is_noise_word(token.text.clone()) { |
| <span class="kw">let </span>term = Term::from_field_text(field, <span class="kw-2">&</span>token.text); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| }); |
| } |
| } |
| FieldType::Str(text_options) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>token_streams: Vec<BoxTokenStream> = <span class="macro">vec!</span>[]; |
| |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">match </span>value { |
| Value::PreTokStr(tok_str) => { |
| token_streams.push(PreTokenizedStream::from(tok_str.clone()).into()); |
| } |
| Value::Str(<span class="kw-2">ref </span>text) => { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(tokenizer) = text_options |
| .get_indexing_options() |
| .map(|text_indexing_options| { |
| text_indexing_options.tokenizer().to_string() |
| }) |
| .and_then(|tokenizer_name| tokenizer_manager.get(<span class="kw-2">&</span>tokenizer_name)) |
| { |
| token_streams.push(tokenizer.token_stream(text)); |
| } |
| } |
| <span class="kw">_ </span>=> (), |
| } |
| } |
| |
| <span class="kw">for </span><span class="kw-2">mut </span>token_stream <span class="kw">in </span>token_streams { |
| token_stream.process(<span class="kw-2">&mut </span>|token| { |
| <span class="kw">if </span>!<span class="self">self</span>.is_noise_word(token.text.clone()) { |
| <span class="kw">let </span>term = Term::from_field_text(field, <span class="kw-2">&</span>token.text); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| }); |
| } |
| } |
| FieldType::U64(<span class="kw">_</span>) => { |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span>val = value.as_u64().ok_or_else(|| { |
| TantivyError::InvalidArgument(<span class="string">"invalid value"</span>.to_string()) |
| })<span class="question-mark">?</span>; |
| <span class="kw">if </span>!<span class="self">self</span>.is_noise_word(val.to_string()) { |
| <span class="kw">let </span>term = Term::from_field_u64(field, val); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| } |
| } |
| FieldType::Date(<span class="kw">_</span>) => { |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span>timestamp_micros = value |
| .as_date() |
| .ok_or_else(|| TantivyError::InvalidArgument(<span class="string">"invalid value"</span>.to_string()))<span class="question-mark">? |
| </span>.into_timestamp_micros(); |
| <span class="kw">if </span>!<span class="self">self</span>.is_noise_word(timestamp_micros.to_string()) { |
| <span class="kw">let </span>term = Term::from_field_i64(field, timestamp_micros); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| } |
| } |
| FieldType::I64(<span class="kw">_</span>) => { |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span>val = value.as_i64().ok_or_else(|| { |
| TantivyError::InvalidArgument(<span class="string">"invalid value"</span>.to_string()) |
| })<span class="question-mark">?</span>; |
| <span class="kw">if </span>!<span class="self">self</span>.is_noise_word(val.to_string()) { |
| <span class="kw">let </span>term = Term::from_field_i64(field, val); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| } |
| } |
| FieldType::F64(<span class="kw">_</span>) => { |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span>val = value.as_f64().ok_or_else(|| { |
| TantivyError::InvalidArgument(<span class="string">"invalid value"</span>.to_string()) |
| })<span class="question-mark">?</span>; |
| <span class="kw">if </span>!<span class="self">self</span>.is_noise_word(val.to_string()) { |
| <span class="kw">let </span>term = Term::from_field_f64(field, val); |
| <span class="kw-2">*</span>term_frequencies.entry(term).or_insert(<span class="number">0</span>) += <span class="number">1</span>; |
| } |
| } |
| } |
| <span class="kw">_ </span>=> {} |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Determines if the term is likely to be of interest based on "more-like-this" settings |
| </span><span class="kw">fn </span>is_noise_word(<span class="kw-2">&</span><span class="self">self</span>, word: String) -> bool { |
| <span class="kw">let </span>word_length = word.len(); |
| <span class="kw">if </span>word_length == <span class="number">0 </span>{ |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="kw">if </span><span class="self">self |
| </span>.min_word_length |
| .map(|min| word_length < min) |
| .unwrap_or(<span class="bool-val">false</span>) |
| { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="kw">if </span><span class="self">self |
| </span>.max_word_length |
| .map(|max| word_length > max) |
| .unwrap_or(<span class="bool-val">false</span>) |
| { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="self">self</span>.stop_words.contains(<span class="kw-2">&</span>word) |
| } |
| |
| <span class="doccomment">/// Couputes the score for each term while ignoring not useful terms |
| </span><span class="kw">fn </span>create_score_term( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| searcher: <span class="kw-2">&</span>Searcher, |
| per_field_term_frequencies: HashMap<Term, usize>, |
| ) -> <span class="prelude-ty">Result</span><Vec<ScoreTerm>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>score_terms: BinaryHeap<Reverse<ScoreTerm>> = BinaryHeap::new(); |
| <span class="kw">let </span>num_docs = searcher |
| .segment_readers() |
| .iter() |
| .map(|segment_reader| segment_reader.num_docs() <span class="kw">as </span>u64) |
| .sum::<u64>(); |
| |
| <span class="kw">for </span>(term, term_frequency) <span class="kw">in </span>per_field_term_frequencies.iter() { |
| <span class="comment">// ignore terms with less than min_term_frequency |
| </span><span class="kw">if </span><span class="self">self |
| </span>.min_term_frequency |
| .map(|min_term_frequency| <span class="kw-2">*</span>term_frequency < min_term_frequency) |
| .unwrap_or(<span class="bool-val">false</span>) |
| { |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="kw">let </span>doc_freq = searcher.doc_freq(term)<span class="question-mark">?</span>; |
| |
| <span class="comment">// ignore terms with less than min_doc_frequency |
| </span><span class="kw">if </span><span class="self">self |
| </span>.min_doc_frequency |
| .map(|min_doc_frequency| doc_freq < min_doc_frequency) |
| .unwrap_or(<span class="bool-val">false</span>) |
| { |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="comment">// ignore terms with more than max_doc_frequency |
| </span><span class="kw">if </span><span class="self">self |
| </span>.max_doc_frequency |
| .map(|max_doc_frequency| doc_freq > max_doc_frequency) |
| .unwrap_or(<span class="bool-val">false</span>) |
| { |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="comment">// ignore terms with zero frequency |
| </span><span class="kw">if </span>doc_freq == <span class="number">0 </span>{ |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="comment">// compute similarity & score |
| </span><span class="kw">let </span>idf = idf(doc_freq, num_docs); |
| <span class="kw">let </span>score = (<span class="kw-2">*</span>term_frequency <span class="kw">as </span>f32) * idf; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(limit) = <span class="self">self</span>.max_query_terms { |
| <span class="kw">if </span>score_terms.len() > limit { |
| <span class="comment">// update the least significant term |
| </span><span class="kw">let </span>least_significant_term_score = score_terms.peek().unwrap().<span class="number">0</span>.score; |
| <span class="kw">if </span>least_significant_term_score < score { |
| score_terms.peek_mut().unwrap().<span class="number">0 </span>= ScoreTerm::new(term.clone(), score); |
| } |
| } <span class="kw">else </span>{ |
| score_terms.push(Reverse(ScoreTerm::new(term.clone(), score))); |
| } |
| } <span class="kw">else </span>{ |
| score_terms.push(Reverse(ScoreTerm::new(term.clone(), score))); |
| } |
| } |
| |
| <span class="kw">let </span>score_terms_vec: Vec<ScoreTerm> = score_terms |
| .into_iter() |
| .map(|reverse_score_term| reverse_score_term.<span class="number">0</span>) |
| .collect(); |
| |
| <span class="prelude-val">Ok</span>(score_terms_vec) |
| } |
| } |
| </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> |