| <!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/fastfield_codecs/src/compact_space/build_compact_space.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>build_compact_space.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="../../../fastfield_codecs/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../fastfield_codecs/index.html"><img class="rust-logo" src="../../../rust-logo.svg" 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> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::collections::{BTreeSet, BinaryHeap}; |
| <span class="kw">use </span>std::iter; |
| <span class="kw">use </span>std::ops::RangeInclusive; |
| |
| <span class="kw">use </span>itertools::Itertools; |
| |
| <span class="kw">use </span><span class="kw">super</span>::blank_range::BlankRange; |
| <span class="kw">use super</span>::{CompactSpace, RangeMapping}; |
| |
| <span class="doccomment">/// Put the blanks for the sorted values into a binary heap |
| </span><span class="kw">fn </span>get_blanks(values_sorted: <span class="kw-2">&</span>BTreeSet<u128>) -> BinaryHeap<BlankRange> { |
| <span class="kw">let </span><span class="kw-2">mut </span>blanks: BinaryHeap<BlankRange> = BinaryHeap::new(); |
| <span class="kw">for </span>(first, second) <span class="kw">in </span>values_sorted.iter().tuple_windows() { |
| <span class="comment">// Correctness Overflow: the values are deduped and sorted (BTreeSet property), that means |
| // there's always space between two values. |
| </span><span class="kw">let </span>blank_range = first + <span class="number">1</span>..=second - <span class="number">1</span>; |
| <span class="kw">let </span>blank_range: <span class="prelude-ty">Result</span><BlankRange, <span class="kw">_</span>> = blank_range.try_into(); |
| <span class="kw">if let </span><span class="prelude-val">Ok</span>(blank_range) = blank_range { |
| blanks.push(blank_range); |
| } |
| } |
| |
| blanks |
| } |
| |
| <span class="kw">struct </span>BlankCollector { |
| blanks: Vec<BlankRange>, |
| staged_blanks_sum: u128, |
| } |
| <span class="kw">impl </span>BlankCollector { |
| <span class="kw">fn </span>new() -> <span class="self">Self </span>{ |
| <span class="self">Self </span>{ |
| blanks: <span class="macro">vec!</span>[], |
| staged_blanks_sum: <span class="number">0</span>, |
| } |
| } |
| <span class="kw">fn </span>stage_blank(<span class="kw-2">&mut </span><span class="self">self</span>, blank: BlankRange) { |
| <span class="self">self</span>.staged_blanks_sum += blank.blank_size(); |
| <span class="self">self</span>.blanks.push(blank); |
| } |
| <span class="kw">fn </span>drain(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw">impl </span>Iterator<Item = BlankRange> + <span class="lifetime">'_ </span>{ |
| <span class="self">self</span>.staged_blanks_sum = <span class="number">0</span>; |
| <span class="self">self</span>.blanks.drain(..) |
| } |
| <span class="kw">fn </span>staged_blanks_sum(<span class="kw-2">&</span><span class="self">self</span>) -> u128 { |
| <span class="self">self</span>.staged_blanks_sum |
| } |
| <span class="kw">fn </span>num_staged_blanks(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.blanks.len() |
| } |
| } |
| <span class="kw">fn </span>num_bits(val: u128) -> u8 { |
| (<span class="number">128u32 </span>- val.leading_zeros()) <span class="kw">as </span>u8 |
| } |
| |
| <span class="doccomment">/// Will collect blanks and add them to compact space if more bits are saved than cost from |
| /// metadata. |
| </span><span class="kw">pub fn </span>get_compact_space( |
| values_deduped_sorted: <span class="kw-2">&</span>BTreeSet<u128>, |
| total_num_values: u32, |
| cost_per_blank: usize, |
| ) -> CompactSpace { |
| <span class="kw">let </span><span class="kw-2">mut </span>compact_space_builder = CompactSpaceBuilder::new(); |
| <span class="kw">if </span>values_deduped_sorted.is_empty() { |
| <span class="kw">return </span>compact_space_builder.finish(); |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>blanks: BinaryHeap<BlankRange> = get_blanks(values_deduped_sorted); |
| <span class="comment">// Replace after stabilization of https://github.com/rust-lang/rust/issues/62924 |
| |
| // We start by space that's limited to min_value..=max_value |
| </span><span class="kw">let </span>min_value = <span class="kw-2">*</span>values_deduped_sorted.iter().next().unwrap_or(<span class="kw-2">&</span><span class="number">0</span>); |
| <span class="kw">let </span>max_value = <span class="kw-2">*</span>values_deduped_sorted.iter().last().unwrap_or(<span class="kw-2">&</span><span class="number">0</span>); |
| |
| <span class="comment">// +1 for null, in case min and max covers the whole space, we are off by one. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>amplitude_compact_space = (max_value - min_value).saturating_add(<span class="number">1</span>); |
| <span class="kw">if </span>min_value != <span class="number">0 </span>{ |
| compact_space_builder.add_blanks(iter::once(<span class="number">0</span>..=min_value - <span class="number">1</span>)); |
| } |
| <span class="kw">if </span>max_value != u128::MAX { |
| compact_space_builder.add_blanks(iter::once(max_value + <span class="number">1</span>..=u128::MAX)); |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>amplitude_bits: u8 = num_bits(amplitude_compact_space); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>blank_collector = BlankCollector::new(); |
| <span class="comment">// We will stage blanks until they reduce the compact space by at least 1 bit and then flush |
| // them if the metadata cost is lower than the total number of saved bits. |
| // Binary heap to process the gaps by their size |
| </span><span class="kw">while let </span><span class="prelude-val">Some</span>(blank_range) = blanks.pop() { |
| blank_collector.stage_blank(blank_range); |
| |
| <span class="kw">let </span>staged_spaces_sum: u128 = blank_collector.staged_blanks_sum(); |
| <span class="kw">let </span>amplitude_new_compact_space = amplitude_compact_space - staged_spaces_sum; |
| <span class="kw">let </span>amplitude_new_bits = num_bits(amplitude_new_compact_space); |
| <span class="kw">if </span>amplitude_bits == amplitude_new_bits { |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">let </span>saved_bits = (amplitude_bits - amplitude_new_bits) <span class="kw">as </span>usize * total_num_values <span class="kw">as </span>usize; |
| <span class="comment">// TODO: Maybe calculate exact cost of blanks and run this more expensive computation only, |
| // when amplitude_new_bits changes |
| </span><span class="kw">let </span>cost = blank_collector.num_staged_blanks() * cost_per_blank; |
| <span class="kw">if </span>cost >= saved_bits { |
| <span class="comment">// Continue here, since although we walk over the blanks by size, |
| // we can potentially save a lot at the last bits, which are smaller blanks |
| // |
| // E.g. if the first range reduces the compact space by 1000 from 2000 to 1000, which |
| // saves 11-10=1 bit and the next range reduces the compact space by 950 to |
| // 50, which saves 10-6=4 bit |
| </span><span class="kw">continue</span>; |
| } |
| |
| amplitude_compact_space = amplitude_new_compact_space; |
| amplitude_bits = amplitude_new_bits; |
| compact_space_builder.add_blanks(blank_collector.drain().map(|blank| blank.blank_range())); |
| } |
| |
| <span class="comment">// special case, when we don't collected any blanks because: |
| // * the data is empty (early exit) |
| // * the algorithm did decide it's not worth the cost, which can be the case for single values |
| // |
| // We drain one collected blank unconditionally, so the empty case is reserved for empty |
| // data, and therefore empty compact_space means the data is empty and no data is covered |
| // (conversely to all data) and we can assign null to it. |
| </span><span class="kw">if </span>compact_space_builder.is_empty() { |
| compact_space_builder.add_blanks( |
| blank_collector |
| .drain() |
| .map(|blank| blank.blank_range()) |
| .take(<span class="number">1</span>), |
| ); |
| } |
| |
| <span class="kw">let </span>compact_space = compact_space_builder.finish(); |
| <span class="kw">if </span>max_value - min_value != u128::MAX { |
| <span class="macro">debug_assert_eq!</span>( |
| compact_space.amplitude_compact_space(), |
| amplitude_compact_space |
| ); |
| } |
| compact_space |
| } |
| |
| <span class="attribute">#[derive(Debug, Clone, Eq, PartialEq)] |
| </span><span class="kw">struct </span>CompactSpaceBuilder { |
| blanks: Vec<RangeInclusive<u128>>, |
| } |
| |
| <span class="kw">impl </span>CompactSpaceBuilder { |
| <span class="doccomment">/// Creates a new compact space builder which will initially cover the whole space. |
| </span><span class="kw">fn </span>new() -> <span class="self">Self </span>{ |
| <span class="self">Self </span>{ blanks: Vec::new() } |
| } |
| |
| <span class="doccomment">/// Assumes that repeated add_blank calls don't overlap and are not adjacent, |
| /// e.g. [3..=5, 5..=10] is not allowed |
| /// |
| /// Both of those assumptions are true when blanks are produced from sorted values. |
| </span><span class="kw">fn </span>add_blanks(<span class="kw-2">&mut </span><span class="self">self</span>, blank: <span class="kw">impl </span>Iterator<Item = RangeInclusive<u128>>) { |
| <span class="self">self</span>.blanks.extend(blank); |
| } |
| |
| <span class="kw">fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.blanks.is_empty() |
| } |
| |
| <span class="doccomment">/// Convert blanks to covered space and assign null value |
| </span><span class="kw">fn </span>finish(<span class="kw-2">mut </span><span class="self">self</span>) -> CompactSpace { |
| <span class="comment">// sort by start. ranges are not allowed to overlap |
| </span><span class="self">self</span>.blanks.sort_unstable_by_key(|blank| <span class="kw-2">*</span>blank.start()); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>covered_space = Vec::with_capacity(<span class="self">self</span>.blanks.len()); |
| |
| <span class="comment">// begining of the blanks |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(first_blank_start) = <span class="self">self</span>.blanks.first().map(RangeInclusive::start) { |
| <span class="kw">if </span><span class="kw-2">*</span>first_blank_start != <span class="number">0 </span>{ |
| covered_space.push(<span class="number">0</span>..=first_blank_start - <span class="number">1</span>); |
| } |
| } |
| |
| <span class="comment">// Between the blanks |
| </span><span class="kw">let </span>between_blanks = <span class="self">self</span>.blanks.iter().tuple_windows().map(|(left, right)| { |
| <span class="macro">assert!</span>( |
| left.end() < right.start(), |
| <span class="string">"overlapping or adjacent ranges detected" |
| </span>); |
| <span class="kw-2">*</span>left.end() + <span class="number">1</span>..=<span class="kw-2">*</span>right.start() - <span class="number">1 |
| </span>}); |
| covered_space.extend(between_blanks); |
| |
| <span class="comment">// end of the blanks |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(last_blank_end) = <span class="self">self</span>.blanks.last().map(RangeInclusive::end) { |
| <span class="kw">if </span><span class="kw-2">*</span>last_blank_end != u128::MAX { |
| covered_space.push(last_blank_end + <span class="number">1</span>..=u128::MAX); |
| } |
| } |
| |
| <span class="kw">if </span>covered_space.is_empty() { |
| covered_space.push(<span class="number">0</span>..=<span class="number">0</span>); <span class="comment">// empty data case |
| </span>}; |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>compact_start: u64 = <span class="number">1</span>; <span class="comment">// 0 is reserved for `null` |
| </span><span class="kw">let </span><span class="kw-2">mut </span>ranges_mapping: Vec<RangeMapping> = Vec::with_capacity(covered_space.len()); |
| <span class="kw">for </span>cov <span class="kw">in </span>covered_space { |
| <span class="kw">let </span>range_mapping = <span class="kw">super</span>::RangeMapping { |
| value_range: cov, |
| compact_start, |
| }; |
| <span class="kw">let </span>covered_range_len = range_mapping.range_length(); |
| ranges_mapping.push(range_mapping); |
| compact_start += covered_range_len <span class="kw">as </span>u64; |
| } |
| <span class="comment">// println!("num ranges {}", ranges_mapping.len()); |
| </span>CompactSpace { ranges_mapping } |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_binary_heap_pop_order() { |
| <span class="kw">let </span><span class="kw-2">mut </span>blanks: BinaryHeap<BlankRange> = BinaryHeap::new(); |
| blanks.push((<span class="number">0</span>..=<span class="number">10</span>).try_into().unwrap()); |
| blanks.push((<span class="number">100</span>..=<span class="number">200</span>).try_into().unwrap()); |
| blanks.push((<span class="number">100</span>..=<span class="number">110</span>).try_into().unwrap()); |
| <span class="macro">assert_eq!</span>(blanks.pop().unwrap().blank_size(), <span class="number">101</span>); |
| <span class="macro">assert_eq!</span>(blanks.pop().unwrap().blank_size(), <span class="number">11</span>); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="fastfield_codecs" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |