blob: 8b34800f7d2ced1756a0219b3b12898ce99e72e0 [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/fastfield/alive_bitset.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>alive_bitset.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>
</pre><pre class="rust"><code><span class="kw">use </span>std::io;
<span class="kw">use </span>std::io::Write;
<span class="kw">use </span>common::{intersect_bitsets, BitSet, ReadOnlyBitSet};
<span class="kw">use </span>ownedbytes::OwnedBytes;
<span class="kw">use </span><span class="kw">crate</span>::space_usage::ByteCount;
<span class="kw">use </span><span class="kw">crate</span>::DocId;
<span class="doccomment">/// Write an alive `BitSet`
///
/// where `alive_bitset` is the set of alive `DocId`.
/// Warning: this function does not call terminate. The caller is in charge of
/// closing the writer properly.
</span><span class="kw">pub fn </span>write_alive_bitset&lt;T: Write&gt;(alive_bitset: <span class="kw-2">&amp;</span>BitSet, writer: <span class="kw-2">&amp;mut </span>T) -&gt; io::Result&lt;()&gt; {
alive_bitset.serialize(writer)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Set of alive `DocId`s.
</span><span class="attribute">#[derive(Clone)]
</span><span class="kw">pub struct </span>AliveBitSet {
num_alive_docs: usize,
bitset: ReadOnlyBitSet,
}
<span class="doccomment">/// Intersects two AliveBitSets in a new one.
/// The two bitsets need to have the same max_value.
</span><span class="kw">pub fn </span>intersect_alive_bitsets(left: AliveBitSet, right: AliveBitSet) -&gt; AliveBitSet {
<span class="macro">assert_eq!</span>(left.bitset().max_value(), right.bitset().max_value());
<span class="kw">let </span>bitset = intersect_bitsets(left.bitset(), right.bitset());
<span class="kw">let </span>num_alive_docs = bitset.len();
AliveBitSet {
num_alive_docs,
bitset,
}
}
<span class="kw">impl </span>AliveBitSet {
<span class="attribute">#[cfg(test)]
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>for_test_from_deleted_docs(deleted_docs: <span class="kw-2">&amp;</span>[DocId], max_doc: u32) -&gt; AliveBitSet {
<span class="macro">assert!</span>(deleted_docs.iter().all(|<span class="kw-2">&amp;</span>doc| doc &lt; max_doc));
<span class="kw">let </span><span class="kw-2">mut </span>bitset = BitSet::with_max_value_and_full(max_doc);
<span class="kw">for </span><span class="kw-2">&amp;</span>doc <span class="kw">in </span>deleted_docs {
bitset.remove(doc);
}
<span class="kw">let </span><span class="kw-2">mut </span>alive_bitset_buffer = Vec::new();
write_alive_bitset(<span class="kw-2">&amp;</span>bitset, <span class="kw-2">&amp;mut </span>alive_bitset_buffer).unwrap();
<span class="kw">let </span>alive_bitset_bytes = OwnedBytes::new(alive_bitset_buffer);
<span class="self">Self</span>::open(alive_bitset_bytes)
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>from_bitset(bitset: <span class="kw-2">&amp;</span>BitSet) -&gt; AliveBitSet {
<span class="kw">let </span>readonly_bitset = ReadOnlyBitSet::from(bitset);
AliveBitSet::from(readonly_bitset)
}
<span class="doccomment">/// Opens an alive bitset given its file.
</span><span class="kw">pub fn </span>open(bytes: OwnedBytes) -&gt; AliveBitSet {
<span class="kw">let </span>bitset = ReadOnlyBitSet::open(bytes);
AliveBitSet::from(bitset)
}
<span class="doccomment">/// Returns true if the document is still &quot;alive&quot;. In other words, if it has not been deleted.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>is_alive(<span class="kw-2">&amp;</span><span class="self">self</span>, doc: DocId) -&gt; bool {
<span class="self">self</span>.bitset.contains(doc)
}
<span class="doccomment">/// Returns true if the document has been marked as deleted.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>is_deleted(<span class="kw-2">&amp;</span><span class="self">self</span>, doc: DocId) -&gt; bool {
!<span class="self">self</span>.is_alive(doc)
}
<span class="doccomment">/// Iterate over the alive doc_ids.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>iter_alive(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw">impl </span>Iterator&lt;Item = DocId&gt; + <span class="lifetime">&#39;_ </span>{
<span class="self">self</span>.bitset.iter()
}
<span class="doccomment">/// Get underlying bitset.
</span><span class="attribute">#[inline]
</span><span class="kw">pub fn </span>bitset(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>ReadOnlyBitSet {
<span class="kw-2">&amp;</span><span class="self">self</span>.bitset
}
<span class="doccomment">/// The number of alive documents.
</span><span class="kw">pub fn </span>num_alive_docs(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; usize {
<span class="self">self</span>.num_alive_docs
}
<span class="doccomment">/// Summarize total space usage of this bitset.
</span><span class="kw">pub fn </span>space_usage(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; ByteCount {
<span class="self">self</span>.bitset().num_bytes()
}
}
<span class="kw">impl </span>From&lt;ReadOnlyBitSet&gt; <span class="kw">for </span>AliveBitSet {
<span class="kw">fn </span>from(bitset: ReadOnlyBitSet) -&gt; AliveBitSet {
<span class="kw">let </span>num_alive_docs = bitset.len();
AliveBitSet {
num_alive_docs,
bitset,
}
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span><span class="kw">super</span>::AliveBitSet;
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_alive_bitset_empty() {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[], <span class="number">10</span>);
<span class="kw">for </span>doc <span class="kw">in </span><span class="number">0</span>..<span class="number">10 </span>{
<span class="macro">assert_eq!</span>(alive_bitset.is_deleted(doc), !alive_bitset.is_alive(doc));
<span class="macro">assert!</span>(!alive_bitset.is_deleted(doc));
}
<span class="macro">assert_eq!</span>(alive_bitset.num_alive_docs(), <span class="number">10</span>);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_alive_bitset() {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">1</span>, <span class="number">9</span>], <span class="number">10</span>);
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">0</span>));
<span class="macro">assert!</span>(alive_bitset.is_deleted(<span class="number">1</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">2</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">3</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">4</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">5</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">6</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">6</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">7</span>));
<span class="macro">assert!</span>(alive_bitset.is_alive(<span class="number">8</span>));
<span class="macro">assert!</span>(alive_bitset.is_deleted(<span class="number">9</span>));
<span class="kw">for </span>doc <span class="kw">in </span><span class="number">0</span>..<span class="number">10 </span>{
<span class="macro">assert_eq!</span>(alive_bitset.is_deleted(doc), !alive_bitset.is_alive(doc));
}
<span class="macro">assert_eq!</span>(alive_bitset.num_alive_docs(), <span class="number">8</span>);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_alive_bitset_iter_minimal() {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">7</span>], <span class="number">8</span>);
<span class="kw">let </span>data: Vec&lt;<span class="kw">_</span>&gt; = alive_bitset.iter_alive().collect();
<span class="macro">assert_eq!</span>(data, <span class="macro">vec!</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">4</span>, <span class="number">5</span>, <span class="number">6</span>]);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_alive_bitset_iter_small() {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">0</span>, <span class="number">2</span>, <span class="number">3</span>, <span class="number">6</span>], <span class="number">7</span>);
<span class="kw">let </span>data: Vec&lt;<span class="kw">_</span>&gt; = alive_bitset.iter_alive().collect();
<span class="macro">assert_eq!</span>(data, <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">4</span>, <span class="number">5</span>]);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_alive_bitset_iter() {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">1000</span>], <span class="number">1001</span>);
<span class="kw">let </span>data: Vec&lt;<span class="kw">_</span>&gt; = alive_bitset.iter_alive().collect();
<span class="macro">assert_eq!</span>(data, (<span class="number">2</span>..=<span class="number">999</span>).collect::&lt;Vec&lt;<span class="kw">_</span>&gt;&gt;());
}
}
<span class="attribute">#[cfg(all(test, feature = <span class="string">&quot;unstable&quot;</span>))]
</span><span class="kw">mod </span>bench {
<span class="kw">use </span>rand::prelude::IteratorRandom;
<span class="kw">use </span>rand::thread_rng;
<span class="kw">use </span>test::Bencher;
<span class="kw">use </span><span class="kw">super</span>::AliveBitSet;
<span class="kw">fn </span>get_alive() -&gt; Vec&lt;u32&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>data = (<span class="number">0</span>..<span class="number">1_000_000_u32</span>).collect::&lt;Vec&lt;u32&gt;&gt;();
<span class="kw">for _ in </span><span class="number">0</span>..(<span class="number">1_000_000</span>) * <span class="number">1 </span>/ <span class="number">8 </span>{
remove_rand(<span class="kw-2">&amp;mut </span>data);
}
data
}
<span class="kw">fn </span>remove_rand(raw: <span class="kw-2">&amp;mut </span>Vec&lt;u32&gt;) {
<span class="kw">let </span>i = (<span class="number">0</span>..raw.len()).choose(<span class="kw-2">&amp;mut </span>thread_rng()).unwrap();
raw.remove(i);
}
<span class="attribute">#[bench]
</span><span class="kw">fn </span>bench_alive_bitset_iter_deser_on_fly(bench: <span class="kw-2">&amp;mut </span>Bencher) {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">1000</span>, <span class="number">10000</span>], <span class="number">1_000_000</span>);
bench.iter(|| alive_bitset.iter_alive().collect::&lt;Vec&lt;<span class="kw">_</span>&gt;&gt;());
}
<span class="attribute">#[bench]
</span><span class="kw">fn </span>bench_alive_bitset_access(bench: <span class="kw-2">&amp;mut </span>Bencher) {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>[<span class="number">0</span>, <span class="number">1</span>, <span class="number">1000</span>, <span class="number">10000</span>], <span class="number">1_000_000</span>);
bench.iter(|| {
(<span class="number">0</span>..<span class="number">1_000_000_u32</span>)
.filter(|doc| alive_bitset.is_alive(<span class="kw-2">*</span>doc))
.collect::&lt;Vec&lt;<span class="kw">_</span>&gt;&gt;()
});
}
<span class="attribute">#[bench]
</span><span class="kw">fn </span>bench_alive_bitset_iter_deser_on_fly_1_8_alive(bench: <span class="kw-2">&amp;mut </span>Bencher) {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>get_alive(), <span class="number">1_000_000</span>);
bench.iter(|| alive_bitset.iter_alive().collect::&lt;Vec&lt;<span class="kw">_</span>&gt;&gt;());
}
<span class="attribute">#[bench]
</span><span class="kw">fn </span>bench_alive_bitset_access_1_8_alive(bench: <span class="kw-2">&amp;mut </span>Bencher) {
<span class="kw">let </span>alive_bitset = AliveBitSet::for_test_from_deleted_docs(<span class="kw-2">&amp;</span>get_alive(), <span class="number">1_000_000</span>);
bench.iter(|| {
(<span class="number">0</span>..<span class="number">1_000_000_u32</span>)
.filter(|doc| alive_bitset.is_alive(<span class="kw-2">*</span>doc))
.collect::&lt;Vec&lt;<span class="kw">_</span>&gt;&gt;()
});
}
}
</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>