blob: 04810aa78ba72bb4e729e7c3f524bc155f899102 [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/store/writer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>writer.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>
</pre><pre class="rust"><code><span class="kw">use </span>std::io;
<span class="kw">use </span>common::BinarySerializable;
<span class="kw">use </span><span class="kw">super</span>::compressors::Compressor;
<span class="kw">use </span><span class="kw">super</span>::StoreReader;
<span class="kw">use </span><span class="kw">crate</span>::directory::WritePtr;
<span class="kw">use </span><span class="kw">crate</span>::schema::{Document, Schema};
<span class="kw">use </span><span class="kw">crate</span>::store::store_compressor::BlockCompressor;
<span class="kw">use </span><span class="kw">crate</span>::DocId;
<span class="doccomment">/// Write tantivy&#39;s [`Store`](./index.html)
///
/// Contrary to the other components of `tantivy`,
/// the store is written to disc as document as being added,
/// as opposed to when the segment is getting finalized.
///
/// The skip list index on the other hand, is built in memory.
</span><span class="kw">pub struct </span>StoreWriter {
compressor: Compressor,
block_size: usize,
num_docs_in_current_block: DocId,
current_block: Vec&lt;u8&gt;,
doc_pos: Vec&lt;u32&gt;,
block_compressor: BlockCompressor,
}
<span class="kw">impl </span>StoreWriter {
<span class="doccomment">/// Create a store writer.
///
/// The store writer will writes blocks on disc as
/// document are added.
</span><span class="kw">pub fn </span>new(
writer: WritePtr,
compressor: Compressor,
block_size: usize,
dedicated_thread: bool,
) -&gt; io::Result&lt;StoreWriter&gt; {
<span class="kw">let </span>block_compressor = BlockCompressor::new(compressor, writer, dedicated_thread)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(StoreWriter {
compressor,
block_size,
num_docs_in_current_block: <span class="number">0</span>,
doc_pos: Vec::new(),
current_block: Vec::new(),
block_compressor,
})
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>compressor(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; Compressor {
<span class="self">self</span>.compressor
}
<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 {
<span class="self">self</span>.current_block.capacity() + <span class="self">self</span>.doc_pos.capacity() * std::mem::size_of::&lt;u32&gt;()
}
<span class="doccomment">/// Checks if the current block is full, and if so, compresses and flushes it.
</span><span class="kw">fn </span>check_flush_block(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; io::Result&lt;()&gt; {
<span class="comment">// this does not count the VInt storing the index lenght itself, but it is negligible in
// front of everything else.
</span><span class="kw">let </span>index_len = <span class="self">self</span>.doc_pos.len() * std::mem::size_of::&lt;usize&gt;();
<span class="kw">if </span><span class="self">self</span>.current_block.len() + index_len &gt; <span class="self">self</span>.block_size {
<span class="self">self</span>.send_current_block_to_compressor()<span class="question-mark">?</span>;
}
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Flushes current uncompressed block and sends to compressor.
</span><span class="kw">fn </span>send_current_block_to_compressor(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; io::Result&lt;()&gt; {
<span class="comment">// We don&#39;t do anything if the current block is empty to begin with.
</span><span class="kw">if </span><span class="self">self</span>.current_block.is_empty() {
<span class="kw">return </span><span class="prelude-val">Ok</span>(());
}
<span class="kw">let </span>size_of_u32 = std::mem::size_of::&lt;u32&gt;();
<span class="self">self</span>.current_block
.reserve((<span class="self">self</span>.doc_pos.len() + <span class="number">1</span>) * size_of_u32);
<span class="kw">for </span>pos <span class="kw">in </span><span class="self">self</span>.doc_pos.iter() {
pos.serialize(<span class="kw-2">&amp;mut </span><span class="self">self</span>.current_block)<span class="question-mark">?</span>;
}
(<span class="self">self</span>.doc_pos.len() <span class="kw">as </span>u32).serialize(<span class="kw-2">&amp;mut </span><span class="self">self</span>.current_block)<span class="question-mark">?</span>;
<span class="self">self</span>.block_compressor
.compress_block_and_write(<span class="kw-2">&amp;</span><span class="self">self</span>.current_block, <span class="self">self</span>.num_docs_in_current_block)<span class="question-mark">?</span>;
<span class="self">self</span>.doc_pos.clear();
<span class="self">self</span>.current_block.clear();
<span class="self">self</span>.num_docs_in_current_block = <span class="number">0</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Store a new document.
///
/// The document id is implicitly the current number
/// of documents.
</span><span class="kw">pub fn </span>store(<span class="kw-2">&amp;mut </span><span class="self">self</span>, document: <span class="kw-2">&amp;</span>Document, schema: <span class="kw-2">&amp;</span>Schema) -&gt; io::Result&lt;()&gt; {
<span class="self">self</span>.doc_pos.push(<span class="self">self</span>.current_block.len() <span class="kw">as </span>u32);
document.serialize_stored(schema, <span class="kw-2">&amp;mut </span><span class="self">self</span>.current_block)<span class="question-mark">?</span>;
<span class="self">self</span>.num_docs_in_current_block += <span class="number">1</span>;
<span class="self">self</span>.check_flush_block()<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Store bytes of a serialized document.
///
/// The document id is implicitly the current number
/// of documents.
</span><span class="kw">pub fn </span>store_bytes(<span class="kw-2">&amp;mut </span><span class="self">self</span>, serialized_document: <span class="kw-2">&amp;</span>[u8]) -&gt; io::Result&lt;()&gt; {
<span class="self">self</span>.doc_pos.push(<span class="self">self</span>.current_block.len() <span class="kw">as </span>u32);
<span class="self">self</span>.current_block.extend_from_slice(serialized_document);
<span class="self">self</span>.num_docs_in_current_block += <span class="number">1</span>;
<span class="self">self</span>.check_flush_block()<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Stacks a store reader on top of the documents written so far.
/// This method is an optimization compared to iterating over the documents
/// in the store and adding them one by one, as the store&#39;s data will
/// not be decompressed and then recompressed.
</span><span class="kw">pub fn </span>stack(<span class="kw-2">&amp;mut </span><span class="self">self</span>, store_reader: StoreReader) -&gt; io::Result&lt;()&gt; {
<span class="comment">// We flush the current block first before stacking
</span><span class="self">self</span>.send_current_block_to_compressor()<span class="question-mark">?</span>;
<span class="self">self</span>.block_compressor.stack_reader(store_reader)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(())
}
<span class="doccomment">/// Finalized the store writer.
///
/// Compress the last unfinished block if any,
/// and serializes the skip list index on disc.
</span><span class="kw">pub fn </span>close(<span class="kw-2">mut </span><span class="self">self</span>) -&gt; io::Result&lt;()&gt; {
<span class="self">self</span>.send_current_block_to_compressor()<span class="question-mark">?</span>;
<span class="self">self</span>.block_compressor.close()<span class="question-mark">?</span>;
<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>