blob: 253f19e72a4462ab09fbd2c0987a27976de4a718 [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/fastfield_codecs/src/blockwise_linear.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>blockwise_linear.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>
</pre><pre class="rust"><code><span class="kw">use </span>std::sync::Arc;
<span class="kw">use </span>std::{io, iter};
<span class="kw">use </span>common::{BinarySerializable, CountingWriter, DeserializeFrom};
<span class="kw">use </span>ownedbytes::OwnedBytes;
<span class="kw">use </span>tantivy_bitpacker::{compute_num_bits, BitPacker, BitUnpacker};
<span class="kw">use </span><span class="kw">crate</span>::line::Line;
<span class="kw">use </span><span class="kw">crate</span>::serialize::NormalizedHeader;
<span class="kw">use crate</span>::{Column, FastFieldCodec, FastFieldCodecType, VecColumn};
<span class="kw">const </span>CHUNK_SIZE: usize = <span class="number">512</span>;
<span class="attribute">#[derive(Debug, Default)]
</span><span class="kw">struct </span>Block {
line: Line,
bit_unpacker: BitUnpacker,
data_start_offset: usize,
}
<span class="kw">impl </span>BinarySerializable <span class="kw">for </span>Block {
<span class="kw">fn </span>serialize&lt;W: io::Write&gt;(<span class="kw-2">&amp;</span><span class="self">self</span>, writer: <span class="kw-2">&amp;mut </span>W) -&gt; io::Result&lt;()&gt; {
<span class="self">self</span>.line.serialize(writer)<span class="question-mark">?</span>;
<span class="self">self</span>.bit_unpacker.bit_width().serialize(writer)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="kw">fn </span>deserialize&lt;R: io::Read&gt;(reader: <span class="kw-2">&amp;mut </span>R) -&gt; io::Result&lt;<span class="self">Self</span>&gt; {
<span class="kw">let </span>line = Line::deserialize(reader)<span class="question-mark">?</span>;
<span class="kw">let </span>bit_width = u8::deserialize(reader)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(Block {
line,
bit_unpacker: BitUnpacker::new(bit_width),
data_start_offset: <span class="number">0</span>,
})
}
}
<span class="kw">fn </span>compute_num_blocks(num_vals: u32) -&gt; usize {
(num_vals <span class="kw">as </span>usize + CHUNK_SIZE - <span class="number">1</span>) / CHUNK_SIZE
}
<span class="kw">pub struct </span>BlockwiseLinearCodec;
<span class="kw">impl </span>FastFieldCodec <span class="kw">for </span>BlockwiseLinearCodec {
<span class="kw">const </span>CODEC_TYPE: <span class="kw">crate</span>::FastFieldCodecType = FastFieldCodecType::BlockwiseLinear;
<span class="kw">type </span>Reader = BlockwiseLinearReader;
<span class="kw">fn </span>open_from_bytes(
bytes: ownedbytes::OwnedBytes,
normalized_header: NormalizedHeader,
) -&gt; io::Result&lt;<span class="self">Self</span>::Reader&gt; {
<span class="kw">let </span>footer_len: u32 = (<span class="kw-2">&amp;</span>bytes[bytes.len() - <span class="number">4</span>..]).deserialize()<span class="question-mark">?</span>;
<span class="kw">let </span>footer_offset = bytes.len() - <span class="number">4 </span>- footer_len <span class="kw">as </span>usize;
<span class="kw">let </span>(data, <span class="kw-2">mut </span>footer) = bytes.split(footer_offset);
<span class="kw">let </span>num_blocks = compute_num_blocks(normalized_header.num_vals);
<span class="kw">let </span><span class="kw-2">mut </span>blocks: Vec&lt;Block&gt; = iter::repeat_with(|| Block::deserialize(<span class="kw-2">&amp;mut </span>footer))
.take(num_blocks)
.collect::&lt;io::Result&lt;<span class="kw">_</span>&gt;&gt;()<span class="question-mark">?</span>;
<span class="kw">let </span><span class="kw-2">mut </span>start_offset = <span class="number">0</span>;
<span class="kw">for </span>block <span class="kw">in </span><span class="kw-2">&amp;mut </span>blocks {
block.data_start_offset = start_offset;
start_offset += (block.bit_unpacker.bit_width() <span class="kw">as </span>usize) * CHUNK_SIZE / <span class="number">8</span>;
}
<span class="prelude-val">Ok</span>(BlockwiseLinearReader {
blocks: Arc::new(blocks),
data,
normalized_header,
})
}
<span class="comment">// Estimate first_chunk and extrapolate
</span><span class="kw">fn </span>estimate(column: <span class="kw-2">&amp;</span><span class="kw">dyn </span><span class="kw">crate</span>::Column) -&gt; <span class="prelude-ty">Option</span>&lt;f32&gt; {
<span class="kw">if </span>column.num_vals() &lt; <span class="number">10 </span>* CHUNK_SIZE <span class="kw">as </span>u32 {
<span class="kw">return </span><span class="prelude-val">None</span>;
}
<span class="kw">let </span><span class="kw-2">mut </span>first_chunk: Vec&lt;u64&gt; = column.iter().take(CHUNK_SIZE <span class="kw">as </span>usize).collect();
<span class="kw">let </span>line = Line::train(<span class="kw-2">&amp;</span>VecColumn::from(<span class="kw-2">&amp;</span>first_chunk));
<span class="kw">for </span>(i, buffer_val) <span class="kw">in </span>first_chunk.iter_mut().enumerate() {
<span class="kw">let </span>interpolated_val = line.eval(i <span class="kw">as </span>u32);
<span class="kw-2">*</span>buffer_val = buffer_val.wrapping_sub(interpolated_val);
}
<span class="kw">let </span>estimated_bit_width = first_chunk
.iter()
.map(|el| ((el + <span class="number">1</span>) <span class="kw">as </span>f32 * <span class="number">3.0</span>) <span class="kw">as </span>u64)
.map(compute_num_bits)
.max()
.unwrap();
<span class="kw">let </span>metadata_per_block = {
<span class="kw">let </span><span class="kw-2">mut </span>out = <span class="macro">vec!</span>[];
Block::default().serialize(<span class="kw-2">&amp;mut </span>out).unwrap();
out.len()
};
<span class="kw">let </span>num_bits = estimated_bit_width <span class="kw">as </span>u64 * column.num_vals() <span class="kw">as </span>u64
<span class="comment">// function metadata per block
</span>+ metadata_per_block <span class="kw">as </span>u64 * (column.num_vals() <span class="kw">as </span>u64 / CHUNK_SIZE <span class="kw">as </span>u64);
<span class="kw">let </span>num_bits_uncompressed = <span class="number">64 </span>* column.num_vals();
<span class="prelude-val">Some</span>(num_bits <span class="kw">as </span>f32 / num_bits_uncompressed <span class="kw">as </span>f32)
}
<span class="kw">fn </span>serialize(column: <span class="kw-2">&amp;</span><span class="kw">dyn </span>Column, wrt: <span class="kw-2">&amp;mut </span><span class="kw">impl </span>io::Write) -&gt; io::Result&lt;()&gt; {
<span class="comment">// The BitpackedReader assumes a normalized vector.
</span><span class="macro">assert_eq!</span>(column.min_value(), <span class="number">0</span>);
<span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::with_capacity(CHUNK_SIZE);
<span class="kw">let </span>num_vals = column.num_vals();
<span class="kw">let </span>num_blocks = compute_num_blocks(num_vals);
<span class="kw">let </span><span class="kw-2">mut </span>blocks = Vec::with_capacity(num_blocks);
<span class="kw">let </span><span class="kw-2">mut </span>vals = column.iter();
<span class="kw">let </span><span class="kw-2">mut </span>bit_packer = BitPacker::new();
<span class="kw">for _ in </span><span class="number">0</span>..num_blocks {
buffer.clear();
buffer.extend((<span class="kw-2">&amp;mut </span>vals).take(CHUNK_SIZE));
<span class="kw">let </span>line = Line::train(<span class="kw-2">&amp;</span>VecColumn::from(<span class="kw-2">&amp;</span>buffer));
<span class="macro">assert!</span>(!buffer.is_empty());
<span class="kw">for </span>(i, buffer_val) <span class="kw">in </span>buffer.iter_mut().enumerate() {
<span class="kw">let </span>interpolated_val = line.eval(i <span class="kw">as </span>u32);
<span class="kw-2">*</span>buffer_val = buffer_val.wrapping_sub(interpolated_val);
}
<span class="kw">let </span>bit_width = buffer.iter().copied().map(compute_num_bits).max().unwrap();
<span class="kw">for </span><span class="kw-2">&amp;</span>buffer_val <span class="kw">in </span><span class="kw-2">&amp;</span>buffer {
bit_packer.write(buffer_val, bit_width, wrt)<span class="question-mark">?</span>;
}
blocks.push(Block {
line,
bit_unpacker: BitUnpacker::new(bit_width),
data_start_offset: <span class="number">0</span>,
});
}
bit_packer.close(wrt)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(blocks.len(), compute_num_blocks(num_vals));
<span class="kw">let </span><span class="kw-2">mut </span>counting_wrt = CountingWriter::wrap(wrt);
<span class="kw">for </span>block <span class="kw">in </span><span class="kw-2">&amp;</span>blocks {
block.serialize(<span class="kw-2">&amp;mut </span>counting_wrt)<span class="question-mark">?</span>;
}
<span class="kw">let </span>footer_len = counting_wrt.written_bytes();
(footer_len <span class="kw">as </span>u32).serialize(<span class="kw-2">&amp;mut </span>counting_wrt)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
}
<span class="attribute">#[derive(Clone)]
</span><span class="kw">pub struct </span>BlockwiseLinearReader {
blocks: Arc&lt;Vec&lt;Block&gt;&gt;,
normalized_header: NormalizedHeader,
data: OwnedBytes,
}
<span class="kw">impl </span>Column <span class="kw">for </span>BlockwiseLinearReader {
<span class="attribute">#[inline(always)]
</span><span class="kw">fn </span>get_val(<span class="kw-2">&amp;</span><span class="self">self</span>, idx: u32) -&gt; u64 {
<span class="kw">let </span>block_id = (idx / CHUNK_SIZE <span class="kw">as </span>u32) <span class="kw">as </span>usize;
<span class="kw">let </span>idx_within_block = idx % (CHUNK_SIZE <span class="kw">as </span>u32);
<span class="kw">let </span>block = <span class="kw-2">&amp;</span><span class="self">self</span>.blocks[block_id];
<span class="kw">let </span>interpoled_val: u64 = block.line.eval(idx_within_block);
<span class="kw">let </span>block_bytes = <span class="kw-2">&amp;</span><span class="self">self</span>.data[block.data_start_offset..];
<span class="kw">let </span>bitpacked_diff = block.bit_unpacker.get(idx_within_block, block_bytes);
interpoled_val.wrapping_add(bitpacked_diff)
}
<span class="kw">fn </span>min_value(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u64 {
<span class="comment">// The BlockwiseLinearReader assumes a normalized vector.
</span><span class="number">0u64
</span>}
<span class="kw">fn </span>max_value(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u64 {
<span class="self">self</span>.normalized_header.max_value
}
<span class="kw">fn </span>num_vals(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u32 {
<span class="self">self</span>.normalized_header.num_vals
}
}
</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>