blob: 6f4fd05ee9141d766d084c3b9b91e3f8354b32ff [file] [log] [blame]
<!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/bm25.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>bm25.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>
</pre><pre class="rust"><code><span class="kw">use </span>serde::{Deserialize, Serialize};
<span class="kw">use </span><span class="kw">crate</span>::fieldnorm::FieldNormReader;
<span class="kw">use </span><span class="kw">crate</span>::query::Explanation;
<span class="kw">use crate</span>::{Score, Searcher, Term};
<span class="kw">const </span>K1: Score = <span class="number">1.2</span>;
<span class="kw">const </span>B: Score = <span class="number">0.75</span>;
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>idf(doc_freq: u64, doc_count: u64) -&gt; Score {
<span class="macro">assert!</span>(doc_count &gt;= doc_freq, <span class="string">&quot;{} &gt;= {}&quot;</span>, doc_count, doc_freq);
<span class="kw">let </span>x = ((doc_count - doc_freq) <span class="kw">as </span>Score + <span class="number">0.5</span>) / (doc_freq <span class="kw">as </span>Score + <span class="number">0.5</span>);
(<span class="number">1.0 </span>+ x).ln()
}
<span class="kw">fn </span>cached_tf_component(fieldnorm: u32, average_fieldnorm: Score) -&gt; Score {
K1 * (<span class="number">1.0 </span>- B + B * fieldnorm <span class="kw">as </span>Score / average_fieldnorm)
}
<span class="kw">fn </span>compute_tf_cache(average_fieldnorm: Score) -&gt; [Score; <span class="number">256</span>] {
<span class="kw">let </span><span class="kw-2">mut </span>cache: [Score; <span class="number">256</span>] = [<span class="number">0.0</span>; <span class="number">256</span>];
<span class="kw">for </span>(fieldnorm_id, cache_mut) <span class="kw">in </span>cache.iter_mut().enumerate() {
<span class="kw">let </span>fieldnorm = FieldNormReader::id_to_fieldnorm(fieldnorm_id <span class="kw">as </span>u8);
<span class="kw-2">*</span>cache_mut = cached_tf_component(fieldnorm, average_fieldnorm);
}
cache
}
<span class="attribute">#[derive(Clone, PartialEq, Debug, Serialize, Deserialize)]
</span><span class="kw">pub struct </span>Bm25Params {
<span class="kw">pub </span>idf: Score,
<span class="kw">pub </span>avg_fieldnorm: Score,
}
<span class="attribute">#[derive(Clone)]
</span><span class="kw">pub struct </span>Bm25Weight {
idf_explain: Explanation,
weight: Score,
cache: [Score; <span class="number">256</span>],
average_fieldnorm: Score,
}
<span class="kw">impl </span>Bm25Weight {
<span class="kw">pub fn </span>boost_by(<span class="kw-2">&amp;</span><span class="self">self</span>, boost: Score) -&gt; Bm25Weight {
Bm25Weight {
idf_explain: <span class="self">self</span>.idf_explain.clone(),
weight: <span class="self">self</span>.weight * boost,
cache: <span class="self">self</span>.cache,
average_fieldnorm: <span class="self">self</span>.average_fieldnorm,
}
}
<span class="kw">pub fn </span>for_terms(searcher: <span class="kw-2">&amp;</span>Searcher, terms: <span class="kw-2">&amp;</span>[Term]) -&gt; <span class="kw">crate</span>::Result&lt;Bm25Weight&gt; {
<span class="macro">assert!</span>(!terms.is_empty(), <span class="string">&quot;Bm25 requires at least one term&quot;</span>);
<span class="kw">let </span>field = terms[<span class="number">0</span>].field();
<span class="kw">for </span>term <span class="kw">in </span><span class="kw-2">&amp;</span>terms[<span class="number">1</span>..] {
<span class="macro">assert_eq!</span>(
term.field(),
field,
<span class="string">&quot;All terms must belong to the same field.&quot;
</span>);
}
<span class="kw">let </span><span class="kw-2">mut </span>total_num_tokens = <span class="number">0u64</span>;
<span class="kw">let </span><span class="kw-2">mut </span>total_num_docs = <span class="number">0u64</span>;
<span class="kw">for </span>segment_reader <span class="kw">in </span>searcher.segment_readers() {
<span class="kw">let </span>inverted_index = segment_reader.inverted_index(field)<span class="question-mark">?</span>;
total_num_tokens += inverted_index.total_num_tokens();
total_num_docs += u64::from(segment_reader.max_doc());
}
<span class="kw">let </span>average_fieldnorm = total_num_tokens <span class="kw">as </span>Score / total_num_docs <span class="kw">as </span>Score;
<span class="kw">if </span>terms.len() == <span class="number">1 </span>{
<span class="kw">let </span>term_doc_freq = searcher.doc_freq(<span class="kw-2">&amp;</span>terms[<span class="number">0</span>])<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(Bm25Weight::for_one_term(
term_doc_freq,
total_num_docs,
average_fieldnorm,
))
} <span class="kw">else </span>{
<span class="kw">let </span><span class="kw-2">mut </span>idf_sum: Score = <span class="number">0.0</span>;
<span class="kw">for </span>term <span class="kw">in </span>terms {
<span class="kw">let </span>term_doc_freq = searcher.doc_freq(term)<span class="question-mark">?</span>;
idf_sum += idf(term_doc_freq, total_num_docs);
}
<span class="kw">let </span>idf_explain = Explanation::new(<span class="string">&quot;idf&quot;</span>, idf_sum);
<span class="prelude-val">Ok</span>(Bm25Weight::new(idf_explain, average_fieldnorm))
}
}
<span class="kw">pub fn </span>for_one_term(
term_doc_freq: u64,
total_num_docs: u64,
avg_fieldnorm: Score,
) -&gt; Bm25Weight {
<span class="kw">let </span>idf = idf(term_doc_freq, total_num_docs);
<span class="kw">let </span><span class="kw-2">mut </span>idf_explain =
Explanation::new(<span class="string">&quot;idf, computed as log(1 + (N - n + 0.5) / (n + 0.5))&quot;</span>, idf);
idf_explain.add_const(
<span class="string">&quot;n, number of docs containing this term&quot;</span>,
term_doc_freq <span class="kw">as </span>Score,
);
idf_explain.add_const(<span class="string">&quot;N, total number of docs&quot;</span>, total_num_docs <span class="kw">as </span>Score);
Bm25Weight::new(idf_explain, avg_fieldnorm)
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(idf_explain: Explanation, average_fieldnorm: Score) -&gt; Bm25Weight {
<span class="kw">let </span>weight = idf_explain.value() * (<span class="number">1.0 </span>+ K1);
Bm25Weight {
idf_explain,
weight,
cache: compute_tf_cache(average_fieldnorm),
average_fieldnorm,
}
}
<span class="attribute">#[inline]
</span><span class="kw">pub fn </span>score(<span class="kw-2">&amp;</span><span class="self">self</span>, fieldnorm_id: u8, term_freq: u32) -&gt; Score {
<span class="self">self</span>.weight * <span class="self">self</span>.tf_factor(fieldnorm_id, term_freq)
}
<span class="kw">pub fn </span>max_score(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; Score {
<span class="self">self</span>.score(<span class="number">255u8</span>, <span class="number">2_013_265_944</span>)
}
<span class="attribute">#[inline]
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>tf_factor(<span class="kw-2">&amp;</span><span class="self">self</span>, fieldnorm_id: u8, term_freq: u32) -&gt; Score {
<span class="kw">let </span>term_freq = term_freq <span class="kw">as </span>Score;
<span class="kw">let </span>norm = <span class="self">self</span>.cache[fieldnorm_id <span class="kw">as </span>usize];
term_freq / (term_freq + norm)
}
<span class="kw">pub fn </span>explain(<span class="kw-2">&amp;</span><span class="self">self</span>, fieldnorm_id: u8, term_freq: u32) -&gt; Explanation {
<span class="comment">// The explain format is directly copied from Lucene&#39;s.
// (So, Kudos to Lucene)
</span><span class="kw">let </span>score = <span class="self">self</span>.score(fieldnorm_id, term_freq);
<span class="kw">let </span>norm = <span class="self">self</span>.cache[fieldnorm_id <span class="kw">as </span>usize];
<span class="kw">let </span>term_freq = term_freq <span class="kw">as </span>Score;
<span class="kw">let </span>right_factor = term_freq / (term_freq + norm);
<span class="kw">let </span><span class="kw-2">mut </span>tf_explanation = Explanation::new(
<span class="string">&quot;freq / (freq + k1 * (1 - b + b * dl / avgdl))&quot;</span>,
right_factor,
);
tf_explanation.add_const(<span class="string">&quot;freq, occurrences of term within document&quot;</span>, term_freq);
tf_explanation.add_const(<span class="string">&quot;k1, term saturation parameter&quot;</span>, K1);
tf_explanation.add_const(<span class="string">&quot;b, length normalization parameter&quot;</span>, B);
tf_explanation.add_const(
<span class="string">&quot;dl, length of field&quot;</span>,
FieldNormReader::id_to_fieldnorm(fieldnorm_id) <span class="kw">as </span>Score,
);
tf_explanation.add_const(<span class="string">&quot;avgdl, average length of field&quot;</span>, <span class="self">self</span>.average_fieldnorm);
<span class="kw">let </span><span class="kw-2">mut </span>explanation = Explanation::new(<span class="string">&quot;TermQuery, product of...&quot;</span>, score);
explanation.add_detail(Explanation::new(<span class="string">&quot;(K1+1)&quot;</span>, K1 + <span class="number">1.0</span>));
explanation.add_detail(<span class="self">self</span>.idf_explain.clone());
explanation.add_detail(tf_explanation);
explanation
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span><span class="kw">super</span>::idf;
<span class="kw">use crate</span>::{assert_nearly_equals, Score};
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_idf() {
<span class="kw">let </span>score: Score = <span class="number">2.0</span>;
<span class="macro">assert_nearly_equals!</span>(idf(<span class="number">1</span>, <span class="number">2</span>), score.ln());
}
}
</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>