| <!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/termdict/fst_termdict/merger.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>merger.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>tantivy_fst::map::{OpBuilder, Union}; |
| <span class="kw">use </span>tantivy_fst::raw::IndexedValue; |
| <span class="kw">use </span>tantivy_fst::Streamer; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::postings::TermInfo; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::{TermDictionary, TermOrdinal, TermStreamer}; |
| |
| <span class="doccomment">/// Given a list of sorted term streams, |
| /// returns an iterator over sorted unique terms. |
| /// |
| /// The item yielded is actually a pair with |
| /// - the term |
| /// - a slice with the ordinal of the segments containing |
| /// the term. |
| </span><span class="kw">pub struct </span>TermMerger<<span class="lifetime">'a</span>> { |
| dictionaries: Vec<<span class="kw-2">&</span><span class="lifetime">'a </span>TermDictionary>, |
| <span class="kw">union</span>: Union<<span class="lifetime">'a</span>>, |
| current_key: Vec<u8>, |
| current_segment_and_term_ordinals: Vec<IndexedValue>, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> TermMerger<<span class="lifetime">'a</span>> { |
| <span class="doccomment">/// Stream of merged term dictionary |
| </span><span class="kw">pub fn </span>new(streams: Vec<TermStreamer<<span class="lifetime">'a</span>>>) -> TermMerger<<span class="lifetime">'a</span>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>op_builder = OpBuilder::new(); |
| <span class="kw">let </span><span class="kw-2">mut </span>dictionaries = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>streamer <span class="kw">in </span>streams { |
| op_builder.push(streamer.stream); |
| dictionaries.push(streamer.fst_map); |
| } |
| TermMerger { |
| dictionaries, |
| <span class="kw">union</span>: op_builder.union(), |
| current_key: <span class="macro">vec!</span>[], |
| current_segment_and_term_ordinals: <span class="macro">vec!</span>[], |
| } |
| } |
| |
| <span class="doccomment">/// Iterator over `(segment ordinal, TermOrdinal)` pairs sorted by segment ordinal |
| /// |
| /// This method may be called |
| /// if [`Self::advance`] has been called before |
| /// and `true` was returned. |
| </span><span class="kw">pub fn </span>matching_segments<<span class="lifetime">'b</span>: <span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="lifetime">'b </span><span class="self">self</span>) -> <span class="kw">impl </span><span class="lifetime">'b </span>+ Iterator<Item = (usize, TermOrdinal)> { |
| <span class="self">self</span>.current_segment_and_term_ordinals |
| .iter() |
| .map(|iv| (iv.index, iv.value)) |
| } |
| |
| <span class="doccomment">/// Advance the term iterator to the next term. |
| /// Returns `true` if there is indeed another term |
| /// `false` if there is none. |
| </span><span class="kw">pub fn </span>advance(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="kw">let </span>(key, values) = <span class="kw">if let </span><span class="prelude-val">Some</span>((key, values)) = <span class="self">self</span>.union.next() { |
| (key, values) |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| }; |
| <span class="self">self</span>.current_key.clear(); |
| <span class="self">self</span>.current_key.extend_from_slice(key); |
| <span class="self">self</span>.current_segment_and_term_ordinals.clear(); |
| <span class="self">self</span>.current_segment_and_term_ordinals |
| .extend_from_slice(values); |
| <span class="self">self</span>.current_segment_and_term_ordinals |
| .sort_by_key(|iv| iv.index); |
| <span class="bool-val">true |
| </span>} |
| |
| <span class="doccomment">/// Returns the current term. |
| /// |
| /// This method may be called if [`Self::advance`] has been called before |
| /// and `true` was returned. |
| </span><span class="kw">pub fn </span>key(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[u8] { |
| <span class="kw-2">&</span><span class="self">self</span>.current_key |
| } |
| |
| <span class="doccomment">/// Iterator over `(segment ordinal, TermInfo)` pairs sorted by the ordinal. |
| /// |
| /// This method may be called if [`Self::advance`] has been called before |
| /// and `true` was returned. |
| </span><span class="kw">pub fn </span>current_segment_ords_and_term_infos<<span class="lifetime">'b</span>: <span class="lifetime">'a</span>>( |
| <span class="kw-2">&</span><span class="lifetime">'b </span><span class="self">self</span>, |
| ) -> <span class="kw">impl </span><span class="lifetime">'b </span>+ Iterator<Item = (usize, TermInfo)> { |
| <span class="self">self</span>.current_segment_and_term_ordinals |
| .iter() |
| .map(<span class="kw">move </span>|iv| { |
| ( |
| iv.index, |
| <span class="self">self</span>.dictionaries[iv.index].term_info_from_ord(iv.value), |
| ) |
| }) |
| } |
| } |
| |
| <span class="attribute">#[cfg(all(test, feature = <span class="string">"unstable"</span>))] |
| </span><span class="kw">mod </span>bench { |
| <span class="kw">use </span>rand::distributions::Alphanumeric; |
| <span class="kw">use </span>rand::{thread_rng, Rng}; |
| <span class="kw">use </span>test::{<span class="self">self</span>, Bencher}; |
| |
| <span class="kw">use </span><span class="kw">super</span>::TermMerger; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::FileSlice; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::TermInfo; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::{TermDictionary, TermDictionaryBuilder}; |
| |
| <span class="kw">fn </span>make_term_info(term_ord: u64) -> TermInfo { |
| <span class="kw">let </span>offset = |term_ord: u64| (term_ord * <span class="number">100 </span>+ term_ord * term_ord) <span class="kw">as </span>usize; |
| TermInfo { |
| doc_freq: term_ord <span class="kw">as </span>u32, |
| postings_range: offset(term_ord)..offset(term_ord + <span class="number">1</span>), |
| positions_range: offset(term_ord)..offset(term_ord + <span class="number">1</span>), |
| } |
| } |
| |
| <span class="doccomment">/// Create a dictionary of random strings. |
| </span><span class="kw">fn </span>rand_dict(num_terms: usize) -> <span class="kw">crate</span>::Result<TermDictionary> { |
| <span class="kw">let </span>buffer: Vec<u8> = { |
| <span class="kw">let </span><span class="kw-2">mut </span>terms = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>_i <span class="kw">in </span><span class="number">0</span>..num_terms { |
| <span class="kw">let </span>rand_string: String = thread_rng() |
| .sample_iter(<span class="kw-2">&</span>Alphanumeric) |
| .take(thread_rng().gen_range(<span class="number">30</span>..<span class="number">42</span>)) |
| .map(char::from) |
| .collect(); |
| terms.push(rand_string); |
| } |
| terms.sort(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>term_dictionary_builder = TermDictionaryBuilder::create(Vec::new())<span class="question-mark">?</span>; |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..num_terms { |
| term_dictionary_builder.insert(terms[i].as_bytes(), <span class="kw-2">&</span>make_term_info(i <span class="kw">as </span>u64))<span class="question-mark">?</span>; |
| } |
| term_dictionary_builder.finish()<span class="question-mark">? |
| </span>}; |
| <span class="kw">let </span>file = FileSlice::from(buffer); |
| TermDictionary::open(file) |
| } |
| |
| <span class="attribute">#[bench] |
| </span><span class="kw">fn </span>bench_termmerger(b: <span class="kw-2">&mut </span>Bencher) -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span>dict1 = rand_dict(<span class="number">100_000</span>)<span class="question-mark">?</span>; |
| <span class="kw">let </span>dict2 = rand_dict(<span class="number">100_000</span>)<span class="question-mark">?</span>; |
| b.iter(|| -> <span class="kw">crate</span>::Result<u32> { |
| <span class="kw">let </span>stream1 = dict1.stream()<span class="question-mark">?</span>; |
| <span class="kw">let </span>stream2 = dict2.stream()<span class="question-mark">?</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>merger = TermMerger::new(<span class="macro">vec!</span>[stream1, stream2]); |
| <span class="kw">let </span><span class="kw-2">mut </span>count = <span class="number">0</span>; |
| <span class="kw">while </span>merger.advance() { |
| count += <span class="number">1</span>; |
| } |
| <span class="prelude-val">Ok</span>(count) |
| }); |
| <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> |