blob: 613d49a5cd01aede4de03160234f50e0ad706fa1 [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/fieldnorm/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.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>
</pre><pre class="rust"><code><span class="doccomment">//! The fieldnorm represents the length associated with
//! a given Field of a given document.
//!
//! This metric is important to compute the score of a
//! document: a document having a query word in one of its short fields
//! (e.g. title) is likely to be more relevant than in one of its longer field
//! (e.g. body).
//!
//! It encodes `fieldnorm` on one byte with some precision loss,
//! using the exact same scheme as Lucene. Each value is placed on a log-scale
//! that takes values from `0` to `255`.
//!
//! A value on this scale is identified by a `fieldnorm_id`.
//! Apart from compression, this scale also makes it possible to
//! precompute computationally expensive functions of the fieldnorm
//! in a very short array.
//!
//! This trick is used by the Bm25 similarity.
</span><span class="kw">mod </span>code;
<span class="kw">mod </span>reader;
<span class="kw">mod </span>serializer;
<span class="kw">mod </span>writer;
<span class="kw">use </span><span class="self">self</span>::code::{fieldnorm_to_id, id_to_fieldnorm};
<span class="kw">pub use </span><span class="self">self</span>::reader::{FieldNormReader, FieldNormReaders};
<span class="kw">pub use </span><span class="self">self</span>::serializer::FieldNormsSerializer;
<span class="kw">pub use </span><span class="self">self</span>::writer::FieldNormsWriter;
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span>std::path::Path;
<span class="kw">use </span>once_cell::sync::Lazy;
<span class="kw">use </span><span class="kw">crate</span>::directory::{CompositeFile, Directory, RamDirectory, WritePtr};
<span class="kw">use </span><span class="kw">crate</span>::fieldnorm::{FieldNormReader, FieldNormsSerializer, FieldNormsWriter};
<span class="kw">use </span><span class="kw">crate</span>::query::{EnableScoring, Query, TermQuery};
<span class="kw">use </span><span class="kw">crate</span>::schema::{
Field, IndexRecordOption, Schema, TextFieldIndexing, TextOptions, STORED, TEXT,
};
<span class="kw">use crate</span>::{Index, Term, TERMINATED};
<span class="kw">pub static </span>SCHEMA: Lazy&lt;Schema&gt; = Lazy::new(|| {
<span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder();
schema_builder.add_text_field(<span class="string">&quot;field&quot;</span>, STORED);
schema_builder.add_text_field(<span class="string">&quot;txt_field&quot;</span>, TEXT);
schema_builder.add_text_field(
<span class="string">&quot;str_field&quot;</span>,
TextOptions::default().set_indexing_options(
TextFieldIndexing::default()
.set_index_option(IndexRecordOption::Basic)
.set_fieldnorms(<span class="bool-val">false</span>),
),
);
schema_builder.build()
});
<span class="kw">pub static </span>FIELD: Lazy&lt;Field&gt; = Lazy::new(|| SCHEMA.get_field(<span class="string">&quot;field&quot;</span>).unwrap());
<span class="kw">pub static </span>TXT_FIELD: Lazy&lt;Field&gt; = Lazy::new(|| SCHEMA.get_field(<span class="string">&quot;txt_field&quot;</span>).unwrap());
<span class="kw">pub static </span>STR_FIELD: Lazy&lt;Field&gt; = Lazy::new(|| SCHEMA.get_field(<span class="string">&quot;str_field&quot;</span>).unwrap());
<span class="attribute">#[test]
#[should_panic(expected = <span class="string">&quot;Cannot register a given fieldnorm twice&quot;</span>)]
</span><span class="kw">pub fn </span>test_should_panic_when_recording_fieldnorm_twice_for_same_doc() {
<span class="kw">let </span><span class="kw-2">mut </span>fieldnorm_writers = FieldNormsWriter::for_schema(<span class="kw-2">&amp;</span>SCHEMA);
fieldnorm_writers.record(<span class="number">0u32</span>, <span class="kw-2">*</span>TXT_FIELD, <span class="number">5</span>);
fieldnorm_writers.record(<span class="number">0u32</span>, <span class="kw-2">*</span>TXT_FIELD, <span class="number">3</span>);
}
<span class="attribute">#[test]
</span><span class="kw">pub fn </span>test_fieldnorm() -&gt; <span class="kw">crate</span>::Result&lt;()&gt; {
<span class="kw">let </span>path = Path::new(<span class="string">&quot;test&quot;</span>);
<span class="kw">let </span>directory: RamDirectory = RamDirectory::create();
{
<span class="kw">let </span>write: WritePtr = directory.open_write(Path::new(<span class="string">&quot;test&quot;</span>))<span class="question-mark">?</span>;
<span class="kw">let </span>serializer = FieldNormsSerializer::from_write(write)<span class="question-mark">?</span>;
<span class="kw">let </span><span class="kw-2">mut </span>fieldnorm_writers = FieldNormsWriter::for_schema(<span class="kw-2">&amp;</span>SCHEMA);
fieldnorm_writers.record(<span class="number">2u32</span>, <span class="kw-2">*</span>TXT_FIELD, <span class="number">5</span>);
fieldnorm_writers.record(<span class="number">3u32</span>, <span class="kw-2">*</span>TXT_FIELD, <span class="number">3</span>);
fieldnorm_writers.serialize(serializer, <span class="prelude-val">None</span>)<span class="question-mark">?</span>;
}
<span class="kw">let </span>file = directory.open_read(path)<span class="question-mark">?</span>;
{
<span class="kw">let </span>fields_composite = CompositeFile::open(<span class="kw-2">&amp;</span>file)<span class="question-mark">?</span>;
<span class="macro">assert!</span>(fields_composite.open_read(<span class="kw-2">*</span>FIELD).is_none());
<span class="macro">assert!</span>(fields_composite.open_read(<span class="kw-2">*</span>STR_FIELD).is_none());
<span class="kw">let </span>data = fields_composite.open_read(<span class="kw-2">*</span>TXT_FIELD).unwrap();
<span class="kw">let </span>fieldnorm_reader = FieldNormReader::open(data)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">0u32</span>), <span class="number">0u32</span>);
<span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">1u32</span>), <span class="number">0u32</span>);
<span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">2u32</span>), <span class="number">5u32</span>);
<span class="macro">assert_eq!</span>(fieldnorm_reader.fieldnorm(<span class="number">3u32</span>), <span class="number">3u32</span>);
}
<span class="prelude-val">Ok</span>(())
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_fieldnorm_disabled() -&gt; <span class="kw">crate</span>::Result&lt;()&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder();
<span class="kw">let </span>text_options = TextOptions::default()
.set_indexing_options(TextFieldIndexing::default().set_fieldnorms(<span class="bool-val">false</span>));
<span class="kw">let </span>text = schema_builder.add_text_field(<span class="string">&quot;text&quot;</span>, text_options);
<span class="kw">let </span>schema = schema_builder.build();
<span class="kw">let </span>index = Index::create_in_ram(schema);
<span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests()<span class="question-mark">?</span>;
writer.add_document(<span class="macro">doc!</span>(text=&gt;<span class="string">&quot;hello&quot;</span>))<span class="question-mark">?</span>;
writer.add_document(<span class="macro">doc!</span>(text=&gt;<span class="string">&quot;hello hello hello&quot;</span>))<span class="question-mark">?</span>;
writer.commit()<span class="question-mark">?</span>;
<span class="kw">let </span>reader = index.reader()<span class="question-mark">?</span>;
<span class="kw">let </span>searcher = reader.searcher();
<span class="kw">let </span>query = TermQuery::new(
Term::from_field_text(text, <span class="string">&quot;hello&quot;</span>),
IndexRecordOption::WithFreqs,
);
<span class="kw">let </span>weight = query.weight(EnableScoring::Enabled(<span class="kw-2">&amp;</span>searcher))<span class="question-mark">?</span>;
<span class="kw">let </span><span class="kw-2">mut </span>scorer = weight.scorer(searcher.segment_reader(<span class="number">0</span>), <span class="number">1.0f32</span>)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(scorer.doc(), <span class="number">0</span>);
<span class="macro">assert!</span>((scorer.score() - <span class="number">0.22920431</span>).abs() &lt; <span class="number">0.001f32</span>);
<span class="macro">assert_eq!</span>(scorer.advance(), <span class="number">1</span>);
<span class="macro">assert_eq!</span>(scorer.doc(), <span class="number">1</span>);
<span class="macro">assert!</span>((scorer.score() - <span class="number">0.22920431</span>).abs() &lt; <span class="number">0.001f32</span>);
<span class="macro">assert_eq!</span>(scorer.advance(), TERMINATED);
<span class="prelude-val">Ok</span>(())
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_fieldnorm_enabled() -&gt; <span class="kw">crate</span>::Result&lt;()&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder();
<span class="kw">let </span>text_options = TextOptions::default()
.set_indexing_options(TextFieldIndexing::default().set_fieldnorms(<span class="bool-val">true</span>));
<span class="kw">let </span>text = schema_builder.add_text_field(<span class="string">&quot;text&quot;</span>, text_options);
<span class="kw">let </span>schema = schema_builder.build();
<span class="kw">let </span>index = Index::create_in_ram(schema);
<span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests()<span class="question-mark">?</span>;
writer.add_document(<span class="macro">doc!</span>(text=&gt;<span class="string">&quot;hello&quot;</span>))<span class="question-mark">?</span>;
writer.add_document(<span class="macro">doc!</span>(text=&gt;<span class="string">&quot;hello hello hello&quot;</span>))<span class="question-mark">?</span>;
writer.commit()<span class="question-mark">?</span>;
<span class="kw">let </span>reader = index.reader()<span class="question-mark">?</span>;
<span class="kw">let </span>searcher = reader.searcher();
<span class="kw">let </span>query = TermQuery::new(
Term::from_field_text(text, <span class="string">&quot;hello&quot;</span>),
IndexRecordOption::WithFreqs,
);
<span class="kw">let </span>weight = query.weight(EnableScoring::Enabled(<span class="kw-2">&amp;</span>searcher))<span class="question-mark">?</span>;
<span class="kw">let </span><span class="kw-2">mut </span>scorer = weight.scorer(searcher.segment_reader(<span class="number">0</span>), <span class="number">1.0f32</span>)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(scorer.doc(), <span class="number">0</span>);
<span class="macro">assert!</span>((scorer.score() - <span class="number">0.22920431</span>).abs() &lt; <span class="number">0.001f32</span>);
<span class="macro">assert_eq!</span>(scorer.advance(), <span class="number">1</span>);
<span class="macro">assert_eq!</span>(scorer.doc(), <span class="number">1</span>);
<span class="macro">assert!</span>((scorer.score() - <span class="number">0.15136132</span>).abs() &lt; <span class="number">0.001f32</span>);
<span class="macro">assert_eq!</span>(scorer.advance(), TERMINATED);
<span class="prelude-val">Ok</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>