blob: ca66c39c6583e4a152df579c628d56dd453ece37 [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/bitpacker/src/blocked_bitpacker.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>blocked_bitpacker.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_bitpacker/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="../../tantivy_bitpacker/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>
</pre><pre class="rust"><code><span class="kw">use </span><span class="kw">super</span>::bitpacker::BitPacker;
<span class="kw">use </span><span class="kw">super</span>::compute_num_bits;
<span class="kw">use crate</span>::{minmax, BitUnpacker};
<span class="kw">const </span>BLOCK_SIZE: usize = <span class="number">128</span>;
<span class="doccomment">/// `BlockedBitpacker` compresses data in blocks of
/// 128 elements, while keeping an index on it
</span><span class="attribute">#[derive(Debug, Clone)]
</span><span class="kw">pub struct </span>BlockedBitpacker {
<span class="comment">// bitpacked blocks
</span>compressed_blocks: Vec&lt;u8&gt;,
<span class="comment">// uncompressed data, collected until BLOCK_SIZE
</span>buffer: Vec&lt;u64&gt;,
offset_and_bits: Vec&lt;BlockedBitpackerEntryMetaData&gt;,
}
<span class="kw">impl </span>Default <span class="kw">for </span>BlockedBitpacker {
<span class="kw">fn </span>default() -&gt; <span class="self">Self </span>{
BlockedBitpacker::new()
}
}
<span class="doccomment">/// `BlockedBitpackerEntryMetaData` encodes the
/// offset and bit_width into a u64 bit field
///
/// This saves some space, since 7byte is more
/// than enough and also keeps the access fast
/// because of alignment
</span><span class="attribute">#[derive(Debug, Clone, Default)]
</span><span class="kw">struct </span>BlockedBitpackerEntryMetaData {
encoded: u64,
base_value: u64,
}
<span class="kw">impl </span>BlockedBitpackerEntryMetaData {
<span class="kw">fn </span>new(offset: u64, num_bits: u8, base_value: u64) -&gt; <span class="self">Self </span>{
<span class="kw">let </span>encoded = offset | (num_bits <span class="kw">as </span>u64) &lt;&lt; (<span class="number">64 </span>- <span class="number">8</span>);
<span class="self">Self </span>{
encoded,
base_value,
}
}
<span class="kw">fn </span>offset(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u64 {
(<span class="self">self</span>.encoded &lt;&lt; <span class="number">8</span>) &gt;&gt; <span class="number">8
</span>}
<span class="kw">fn </span>num_bits(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u8 {
(<span class="self">self</span>.encoded &gt;&gt; <span class="number">56</span>) <span class="kw">as </span>u8
}
<span class="kw">fn </span>base_value(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u64 {
<span class="self">self</span>.base_value
}
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>metadata_test() {
<span class="kw">let </span>meta = BlockedBitpackerEntryMetaData::new(<span class="number">50000</span>, <span class="number">6</span>, <span class="number">40000</span>);
<span class="macro">assert_eq!</span>(meta.offset(), <span class="number">50000</span>);
<span class="macro">assert_eq!</span>(meta.num_bits(), <span class="number">6</span>);
}
<span class="kw">fn </span>mem_usage&lt;T&gt;(items: <span class="kw-2">&amp;</span>Vec&lt;T&gt;) -&gt; usize {
items.capacity() * std::mem::size_of::&lt;T&gt;()
}
<span class="kw">impl </span>BlockedBitpacker {
<span class="kw">pub fn </span>new() -&gt; <span class="self">Self </span>{
<span class="kw">let </span><span class="kw-2">mut </span>compressed_blocks = <span class="macro">vec!</span>[];
compressed_blocks.resize(<span class="number">8</span>, <span class="number">0</span>);
<span class="self">Self </span>{
compressed_blocks,
buffer: <span class="macro">vec!</span>[],
offset_and_bits: <span class="macro">vec!</span>[],
}
}
<span class="doccomment">/// The memory used (inclusive childs)
</span><span class="kw">pub fn </span>mem_usage(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; usize {
std::mem::size_of::&lt;BlockedBitpacker&gt;()
+ <span class="self">self</span>.compressed_blocks.capacity()
+ mem_usage(<span class="kw-2">&amp;</span><span class="self">self</span>.offset_and_bits)
+ mem_usage(<span class="kw-2">&amp;</span><span class="self">self</span>.buffer)
}
<span class="attribute">#[inline]
</span><span class="kw">pub fn </span>add(<span class="kw-2">&amp;mut </span><span class="self">self</span>, val: u64) {
<span class="self">self</span>.buffer.push(val);
<span class="kw">if </span><span class="self">self</span>.buffer.len() == BLOCK_SIZE <span class="kw">as </span>usize {
<span class="self">self</span>.flush();
}
}
<span class="kw">pub fn </span>flush(<span class="kw-2">&amp;mut </span><span class="self">self</span>) {
<span class="kw">if let </span><span class="prelude-val">Some</span>((min_value, max_value)) = minmax(<span class="self">self</span>.buffer.iter()) {
<span class="kw">let </span><span class="kw-2">mut </span>bit_packer = BitPacker::new();
<span class="kw">let </span>num_bits_block = compute_num_bits(<span class="kw-2">*</span>max_value - min_value);
<span class="comment">// todo performance: the padding handling could be done better, e.g. use a slice and
// return num_bytes written from bitpacker
</span><span class="self">self</span>.compressed_blocks
.resize(<span class="self">self</span>.compressed_blocks.len() - <span class="number">8</span>, <span class="number">0</span>); <span class="comment">// remove padding for bitpacker
</span><span class="kw">let </span>offset = <span class="self">self</span>.compressed_blocks.len() <span class="kw">as </span>u64;
<span class="comment">// todo performance: for some bit_width we
// can encode multiple vals into the
// mini_buffer before checking to flush
// (to be done in BitPacker)
</span><span class="kw">for </span>val <span class="kw">in </span><span class="self">self</span>.buffer.iter() {
bit_packer
.write(
<span class="kw-2">*</span>val - min_value,
num_bits_block,
<span class="kw-2">&amp;mut </span><span class="self">self</span>.compressed_blocks,
)
.expect(<span class="string">&quot;cannot write bitpacking to output&quot;</span>); <span class="comment">// write to in memory can&#39;t fail
</span>}
bit_packer.flush(<span class="kw-2">&amp;mut </span><span class="self">self</span>.compressed_blocks).unwrap();
<span class="self">self</span>.offset_and_bits
.push(BlockedBitpackerEntryMetaData::new(
offset,
num_bits_block,
<span class="kw-2">*</span>min_value,
));
<span class="self">self</span>.buffer.clear();
<span class="self">self</span>.compressed_blocks
.resize(<span class="self">self</span>.compressed_blocks.len() + <span class="number">8</span>, <span class="number">0</span>); <span class="comment">// add padding for bitpacker
</span>}
}
<span class="attribute">#[inline]
</span><span class="kw">pub fn </span>get(<span class="kw-2">&amp;</span><span class="self">self</span>, idx: usize) -&gt; u64 {
<span class="kw">let </span>metadata_pos = idx / BLOCK_SIZE <span class="kw">as </span>usize;
<span class="kw">let </span>pos_in_block = idx % BLOCK_SIZE <span class="kw">as </span>usize;
<span class="kw">if let </span><span class="prelude-val">Some</span>(metadata) = <span class="self">self</span>.offset_and_bits.get(metadata_pos) {
<span class="kw">let </span>unpacked = BitUnpacker::new(metadata.num_bits()).get(
pos_in_block <span class="kw">as </span>u32,
<span class="kw-2">&amp;</span><span class="self">self</span>.compressed_blocks[metadata.offset() <span class="kw">as </span>usize..],
);
unpacked + metadata.base_value()
} <span class="kw">else </span>{
<span class="self">self</span>.buffer[pos_in_block]
}
}
<span class="kw">pub fn </span>iter(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw">impl </span>Iterator&lt;Item = u64&gt; + <span class="lifetime">&#39;_ </span>{
<span class="comment">// todo performance: we could decompress a whole block and cache it instead
</span><span class="kw">let </span>bitpacked_elems = <span class="self">self</span>.offset_and_bits.len() * BLOCK_SIZE;
<span class="kw">let </span>iter = (<span class="number">0</span>..bitpacked_elems)
.map(<span class="kw">move </span>|idx| <span class="self">self</span>.get(idx))
.chain(<span class="self">self</span>.buffer.iter().cloned());
iter
}
}
<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>blocked_bitpacker_empty() {
<span class="kw">let </span>blocked_bitpacker = BlockedBitpacker::new();
<span class="macro">assert_eq!</span>(blocked_bitpacker.iter().collect::&lt;Vec&lt;u64&gt;&gt;(), <span class="macro">vec!</span>[]);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>blocked_bitpacker_one() {
<span class="kw">let </span><span class="kw-2">mut </span>blocked_bitpacker = BlockedBitpacker::new();
blocked_bitpacker.add(<span class="number">50000</span>);
<span class="macro">assert_eq!</span>(blocked_bitpacker.get(<span class="number">0</span>), <span class="number">50000</span>);
<span class="macro">assert_eq!</span>(blocked_bitpacker.iter().collect::&lt;Vec&lt;u64&gt;&gt;(), <span class="macro">vec!</span>[<span class="number">50000</span>]);
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>blocked_bitpacker_test() {
<span class="kw">let </span><span class="kw-2">mut </span>blocked_bitpacker = BlockedBitpacker::new();
<span class="kw">for </span>val <span class="kw">in </span><span class="number">0</span>..<span class="number">21500 </span>{
blocked_bitpacker.add(val);
}
<span class="kw">for </span>val <span class="kw">in </span><span class="number">0</span>..<span class="number">21500 </span>{
<span class="macro">assert_eq!</span>(blocked_bitpacker.get(val <span class="kw">as </span>usize), val);
}
<span class="macro">assert_eq!</span>(blocked_bitpacker.iter().count(), <span class="number">21500</span>);
<span class="macro">assert_eq!</span>(blocked_bitpacker.iter().last().unwrap(), <span class="number">21499</span>);
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="tantivy_bitpacker" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>