| <!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/fieldnorm/reader.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>reader.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../tantivy/index.html"><div class="logo-container"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy/index.html"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::sync::Arc; |
| |
| <span class="kw">use super</span>::{fieldnorm_to_id, id_to_fieldnorm}; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::{CompositeFile, FileSlice, OwnedBytes}; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::Field; |
| <span class="kw">use </span><span class="kw">crate</span>::space_usage::PerFieldSpaceUsage; |
| <span class="kw">use </span><span class="kw">crate</span>::DocId; |
| |
| <span class="doccomment">/// Reader for the fieldnorm (for each document, the number of tokens indexed in the |
| /// field) of all indexed fields in the index. |
| /// |
| /// Each fieldnorm is approximately compressed over one byte. We refer to this byte as |
| /// `fieldnorm_id`. |
| /// The mapping from `fieldnorm` to `fieldnorm_id` is given by monotonic. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>FieldNormReaders { |
| data: Arc<CompositeFile>, |
| } |
| |
| <span class="kw">impl </span>FieldNormReaders { |
| <span class="doccomment">/// Creates a field norm reader. |
| </span><span class="kw">pub fn </span>open(file: FileSlice) -> <span class="kw">crate</span>::Result<FieldNormReaders> { |
| <span class="kw">let </span>data = CompositeFile::open(<span class="kw-2">&</span>file)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(FieldNormReaders { |
| data: Arc::new(data), |
| }) |
| } |
| |
| <span class="doccomment">/// Returns the FieldNormReader for a specific field. |
| </span><span class="kw">pub fn </span>get_field(<span class="kw-2">&</span><span class="self">self</span>, field: Field) -> <span class="kw">crate</span>::Result<<span class="prelude-ty">Option</span><FieldNormReader>> { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(file) = <span class="self">self</span>.data.open_read(field) { |
| <span class="kw">let </span>fieldnorm_reader = FieldNormReader::open(file)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">Some</span>(fieldnorm_reader)) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Ok</span>(<span class="prelude-val">None</span>) |
| } |
| } |
| |
| <span class="doccomment">/// Return a break down of the space usage per field. |
| </span><span class="kw">pub fn </span>space_usage(<span class="kw-2">&</span><span class="self">self</span>) -> PerFieldSpaceUsage { |
| <span class="self">self</span>.data.space_usage() |
| } |
| |
| <span class="doccomment">/// Returns a handle to inner file |
| </span><span class="kw">pub fn </span>get_inner_file(<span class="kw-2">&</span><span class="self">self</span>) -> Arc<CompositeFile> { |
| <span class="self">self</span>.data.clone() |
| } |
| } |
| |
| <span class="doccomment">/// Reads the fieldnorm associated with a document. |
| /// |
| /// The [fieldnorm](FieldNormReader::fieldnorm) represents the length associated with |
| /// a given Field of a given document. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>FieldNormReader(ReaderImplEnum); |
| |
| <span class="kw">impl </span>From<ReaderImplEnum> <span class="kw">for </span>FieldNormReader { |
| <span class="kw">fn </span>from(reader_enum: ReaderImplEnum) -> FieldNormReader { |
| FieldNormReader(reader_enum) |
| } |
| } |
| |
| <span class="attribute">#[derive(Clone)] |
| </span><span class="kw">enum </span>ReaderImplEnum { |
| FromData(OwnedBytes), |
| Const { |
| num_docs: u32, |
| fieldnorm_id: u8, |
| fieldnorm: u32, |
| }, |
| } |
| |
| <span class="kw">impl </span>FieldNormReader { |
| <span class="doccomment">/// Creates a `FieldNormReader` with a constant fieldnorm. |
| /// |
| /// The fieldnorm will be subjected to compression as if it was coming |
| /// from an array-backed fieldnorm reader. |
| </span><span class="kw">pub fn </span>constant(num_docs: u32, fieldnorm: u32) -> FieldNormReader { |
| <span class="kw">let </span>fieldnorm_id = fieldnorm_to_id(fieldnorm); |
| <span class="kw">let </span>fieldnorm = id_to_fieldnorm(fieldnorm_id); |
| ReaderImplEnum::Const { |
| num_docs, |
| fieldnorm_id, |
| fieldnorm, |
| } |
| .into() |
| } |
| |
| <span class="doccomment">/// Opens a field norm reader given its file. |
| </span><span class="kw">pub fn </span>open(fieldnorm_file: FileSlice) -> <span class="kw">crate</span>::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>data = fieldnorm_file.read_bytes()<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(FieldNormReader::new(data)) |
| } |
| |
| <span class="kw">fn </span>new(data: OwnedBytes) -> <span class="self">Self </span>{ |
| ReaderImplEnum::FromData(data).into() |
| } |
| |
| <span class="doccomment">/// Returns the number of documents in this segment. |
| </span><span class="kw">pub fn </span>num_docs(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="kw">match </span><span class="kw-2">&</span><span class="self">self</span>.<span class="number">0 </span>{ |
| ReaderImplEnum::FromData(data) => data.len() <span class="kw">as </span>u32, |
| ReaderImplEnum::Const { num_docs, .. } => <span class="kw-2">*</span>num_docs, |
| } |
| } |
| |
| <span class="doccomment">/// Returns the `fieldnorm` associated with a doc id. |
| /// The fieldnorm is a value approximating the number |
| /// of tokens in a given field of the `doc_id`. |
| /// |
| /// It is imprecise, and equal or lower than |
| /// the actual number of tokens. |
| /// |
| /// The fieldnorm is effectively decoded from the |
| /// `fieldnorm_id` by doing a simple table lookup. |
| </span><span class="kw">pub fn </span>fieldnorm(<span class="kw-2">&</span><span class="self">self</span>, doc_id: DocId) -> u32 { |
| <span class="kw">match </span><span class="kw-2">&</span><span class="self">self</span>.<span class="number">0 </span>{ |
| ReaderImplEnum::FromData(data) => { |
| <span class="kw">let </span>fieldnorm_id = data.as_slice()[doc_id <span class="kw">as </span>usize]; |
| id_to_fieldnorm(fieldnorm_id) |
| } |
| ReaderImplEnum::Const { fieldnorm, .. } => <span class="kw-2">*</span>fieldnorm, |
| } |
| } |
| |
| <span class="doccomment">/// Returns the `fieldnorm_id` associated with a document. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>fieldnorm_id(<span class="kw-2">&</span><span class="self">self</span>, doc_id: DocId) -> u8 { |
| <span class="kw">match </span><span class="kw-2">&</span><span class="self">self</span>.<span class="number">0 </span>{ |
| ReaderImplEnum::FromData(data) => { |
| <span class="kw">let </span>fieldnorm_id = data.as_slice()[doc_id <span class="kw">as </span>usize]; |
| fieldnorm_id |
| } |
| ReaderImplEnum::Const { fieldnorm_id, .. } => <span class="kw-2">*</span>fieldnorm_id, |
| } |
| } |
| |
| <span class="doccomment">/// Converts a `fieldnorm_id` into a fieldnorm. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>id_to_fieldnorm(id: u8) -> u32 { |
| id_to_fieldnorm(id) |
| } |
| |
| <span class="doccomment">/// Converts a `fieldnorm` into a `fieldnorm_id`. |
| /// (This function is not injective). |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>fieldnorm_to_id(fieldnorm: u32) -> u8 { |
| fieldnorm_to_id(fieldnorm) |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">pub fn </span>for_test(field_norms: <span class="kw-2">&</span>[u32]) -> FieldNormReader { |
| <span class="kw">let </span>field_norms_id = field_norms |
| .iter() |
| .cloned() |
| .map(FieldNormReader::fieldnorm_to_id) |
| .collect::<Vec<u8>>(); |
| <span class="kw">let </span>field_norms_data = OwnedBytes::new(field_norms_id); |
| FieldNormReader::new(field_norms_data) |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span><span class="kw">crate</span>::fieldnorm::FieldNormReader; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_from_fieldnorms_array() { |
| <span class="kw">let </span>fieldnorms = <span class="kw-2">&</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">4</span>, <span class="number">1_000_000</span>]; |
| <span class="kw">let </span>fieldnorm_reader = FieldNormReader::for_test(fieldnorms); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.num_docs(), <span class="number">5</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">0</span>), <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">1</span>), <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">2</span>), <span class="number">3</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">3</span>), <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">4</span>), <span class="number">983_064</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_const_fieldnorm_reader_small_fieldnorm_id() { |
| <span class="kw">let </span>fieldnorm_reader = FieldNormReader::constant(<span class="number">1_000_000u32</span>, <span class="number">10u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.num_docs(), <span class="number">1_000_000u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">0u32</span>), <span class="number">10u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm_id(<span class="number">0u32</span>), <span class="number">10u8</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_const_fieldnorm_reader_large_fieldnorm_id() { |
| <span class="kw">let </span>fieldnorm_reader = FieldNormReader::constant(<span class="number">1_000_000u32</span>, <span class="number">300u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.num_docs(), <span class="number">1_000_000u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">0u32</span>), <span class="number">280u32</span>); |
| <span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm_id(<span class="number">0u32</span>), <span class="number">72u8</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> |