blob: 14471d3d58a12fcdef702b745eb379eb697a1862 [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/reader.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>reader.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>
<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>
<span id="232">232</span>
<span id="233">233</span>
<span id="234">234</span>
<span id="235">235</span>
<span id="236">236</span>
<span id="237">237</span>
<span id="238">238</span>
<span id="239">239</span>
<span id="240">240</span>
<span id="241">241</span>
<span id="242">242</span>
<span id="243">243</span>
<span id="244">244</span>
<span id="245">245</span>
<span id="246">246</span>
<span id="247">247</span>
<span id="248">248</span>
<span id="249">249</span>
<span id="250">250</span>
<span id="251">251</span>
<span id="252">252</span>
<span id="253">253</span>
<span id="254">254</span>
<span id="255">255</span>
<span id="256">256</span>
<span id="257">257</span>
<span id="258">258</span>
<span id="259">259</span>
<span id="260">260</span>
<span id="261">261</span>
<span id="262">262</span>
<span id="263">263</span>
<span id="264">264</span>
<span id="265">265</span>
<span id="266">266</span>
<span id="267">267</span>
<span id="268">268</span>
<span id="269">269</span>
<span id="270">270</span>
<span id="271">271</span>
<span id="272">272</span>
<span id="273">273</span>
<span id="274">274</span>
<span id="275">275</span>
<span id="276">276</span>
<span id="277">277</span>
<span id="278">278</span>
<span id="279">279</span>
<span id="280">280</span>
<span id="281">281</span>
<span id="282">282</span>
<span id="283">283</span>
<span id="284">284</span>
<span id="285">285</span>
<span id="286">286</span>
<span id="287">287</span>
<span id="288">288</span>
<span id="289">289</span>
<span id="290">290</span>
<span id="291">291</span>
<span id="292">292</span>
<span id="293">293</span>
<span id="294">294</span>
<span id="295">295</span>
<span id="296">296</span>
<span id="297">297</span>
<span id="298">298</span>
<span id="299">299</span>
<span id="300">300</span>
<span id="301">301</span>
<span id="302">302</span>
<span id="303">303</span>
<span id="304">304</span>
<span id="305">305</span>
<span id="306">306</span>
<span id="307">307</span>
<span id="308">308</span>
<span id="309">309</span>
<span id="310">310</span>
<span id="311">311</span>
<span id="312">312</span>
<span id="313">313</span>
<span id="314">314</span>
<span id="315">315</span>
<span id="316">316</span>
<span id="317">317</span>
<span id="318">318</span>
<span id="319">319</span>
<span id="320">320</span>
<span id="321">321</span>
<span id="322">322</span>
<span id="323">323</span>
<span id="324">324</span>
<span id="325">325</span>
<span id="326">326</span>
<span id="327">327</span>
<span id="328">328</span>
<span id="329">329</span>
<span id="330">330</span>
<span id="331">331</span>
<span id="332">332</span>
<span id="333">333</span>
<span id="334">334</span>
<span id="335">335</span>
<span id="336">336</span>
<span id="337">337</span>
<span id="338">338</span>
<span id="339">339</span>
<span id="340">340</span>
<span id="341">341</span>
<span id="342">342</span>
<span id="343">343</span>
<span id="344">344</span>
<span id="345">345</span>
<span id="346">346</span>
<span id="347">347</span>
<span id="348">348</span>
<span id="349">349</span>
<span id="350">350</span>
<span id="351">351</span>
<span id="352">352</span>
<span id="353">353</span>
<span id="354">354</span>
<span id="355">355</span>
<span id="356">356</span>
<span id="357">357</span>
<span id="358">358</span>
<span id="359">359</span>
<span id="360">360</span>
<span id="361">361</span>
<span id="362">362</span>
<span id="363">363</span>
<span id="364">364</span>
<span id="365">365</span>
<span id="366">366</span>
<span id="367">367</span>
<span id="368">368</span>
<span id="369">369</span>
<span id="370">370</span>
<span id="371">371</span>
<span id="372">372</span>
<span id="373">373</span>
<span id="374">374</span>
<span id="375">375</span>
<span id="376">376</span>
<span id="377">377</span>
<span id="378">378</span>
<span id="379">379</span>
<span id="380">380</span>
<span id="381">381</span>
<span id="382">382</span>
<span id="383">383</span>
<span id="384">384</span>
<span id="385">385</span>
<span id="386">386</span>
<span id="387">387</span>
<span id="388">388</span>
<span id="389">389</span>
<span id="390">390</span>
<span id="391">391</span>
<span id="392">392</span>
<span id="393">393</span>
<span id="394">394</span>
<span id="395">395</span>
<span id="396">396</span>
<span id="397">397</span>
<span id="398">398</span>
<span id="399">399</span>
<span id="400">400</span>
<span id="401">401</span>
<span id="402">402</span>
<span id="403">403</span>
<span id="404">404</span>
<span id="405">405</span>
<span id="406">406</span>
<span id="407">407</span>
<span id="408">408</span>
<span id="409">409</span>
<span id="410">410</span>
<span id="411">411</span>
<span id="412">412</span>
<span id="413">413</span>
<span id="414">414</span>
<span id="415">415</span>
<span id="416">416</span>
<span id="417">417</span>
<span id="418">418</span>
<span id="419">419</span>
<span id="420">420</span>
<span id="421">421</span>
</pre><pre class="rust"><code><span class="kw">use </span>std::io;
<span class="kw">use </span>std::iter::Sum;
<span class="kw">use </span>std::ops::{AddAssign, Range};
<span class="kw">use </span>std::sync::atomic::{AtomicUsize, Ordering};
<span class="kw">use </span>std::sync::{Arc, Mutex};
<span class="kw">use </span>common::{BinarySerializable, HasLen};
<span class="kw">use </span>lru::LruCache;
<span class="kw">use </span>ownedbytes::OwnedBytes;
<span class="kw">use </span><span class="kw">super</span>::footer::DocStoreFooter;
<span class="kw">use </span><span class="kw">super</span>::index::SkipIndex;
<span class="kw">use </span><span class="kw">super</span>::Decompressor;
<span class="kw">use </span><span class="kw">crate</span>::directory::FileSlice;
<span class="kw">use </span><span class="kw">crate</span>::error::DataCorruption;
<span class="kw">use </span><span class="kw">crate</span>::fastfield::AliveBitSet;
<span class="kw">use </span><span class="kw">crate</span>::schema::Document;
<span class="kw">use </span><span class="kw">crate</span>::space_usage::StoreSpaceUsage;
<span class="kw">use </span><span class="kw">crate</span>::store::index::Checkpoint;
<span class="kw">use </span><span class="kw">crate</span>::DocId;
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">const </span>DOCSTORE_CACHE_CAPACITY: usize = <span class="number">100</span>;
<span class="kw">type </span>Block = OwnedBytes;
<span class="doccomment">/// Reads document off tantivy&#39;s [`Store`](./index.html)
</span><span class="kw">pub struct </span>StoreReader {
decompressor: Decompressor,
data: FileSlice,
skip_index: Arc&lt;SkipIndex&gt;,
space_usage: StoreSpaceUsage,
cache: BlockCache,
}
<span class="doccomment">/// The cache for decompressed blocks.
</span><span class="kw">struct </span>BlockCache {
cache: Mutex&lt;LruCache&lt;usize, Block&gt;&gt;,
cache_hits: Arc&lt;AtomicUsize&gt;,
cache_misses: Arc&lt;AtomicUsize&gt;,
}
<span class="kw">impl </span>BlockCache {
<span class="kw">fn </span>get_from_cache(<span class="kw-2">&amp;</span><span class="self">self</span>, pos: usize) -&gt; <span class="prelude-ty">Option</span>&lt;Block&gt; {
<span class="kw">if let </span><span class="prelude-val">Some</span>(block) = <span class="self">self</span>.cache.lock().unwrap().get(<span class="kw-2">&amp;</span>pos) {
<span class="self">self</span>.cache_hits.fetch_add(<span class="number">1</span>, Ordering::SeqCst);
<span class="kw">return </span><span class="prelude-val">Some</span>(block.clone());
}
<span class="self">self</span>.cache_misses.fetch_add(<span class="number">1</span>, Ordering::SeqCst);
<span class="prelude-val">None
</span>}
<span class="kw">fn </span>put_into_cache(<span class="kw-2">&amp;</span><span class="self">self</span>, pos: usize, data: Block) {
<span class="self">self</span>.cache.lock().unwrap().put(pos, data);
}
<span class="kw">fn </span>stats(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; CacheStats {
CacheStats {
cache_hits: <span class="self">self</span>.cache_hits.load(Ordering::Relaxed),
cache_misses: <span class="self">self</span>.cache_misses.load(Ordering::Relaxed),
num_entries: <span class="self">self</span>.len(),
}
}
<span class="kw">fn </span>len(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; usize {
<span class="self">self</span>.cache.lock().unwrap().len()
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">fn </span>peek_lru(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="prelude-ty">Option</span>&lt;usize&gt; {
<span class="self">self</span>.cache
.lock()
.unwrap()
.peek_lru()
.map(|(<span class="kw-2">&amp;</span>k, <span class="kw">_</span>)| k <span class="kw">as </span>usize)
}
}
<span class="attribute">#[derive(Debug, Default)]
</span><span class="doccomment">/// CacheStats for the `StoreReader`.
</span><span class="kw">pub struct </span>CacheStats {
<span class="doccomment">/// The number of entries in the cache
</span><span class="kw">pub </span>num_entries: usize,
<span class="doccomment">/// The number of cache hits.
</span><span class="kw">pub </span>cache_hits: usize,
<span class="doccomment">/// The number of cache misses.
</span><span class="kw">pub </span>cache_misses: usize,
}
<span class="kw">impl </span>AddAssign <span class="kw">for </span>CacheStats {
<span class="kw">fn </span>add_assign(<span class="kw-2">&amp;mut </span><span class="self">self</span>, other: <span class="self">Self</span>) {
<span class="kw-2">*</span><span class="self">self </span>= <span class="self">Self </span>{
num_entries: <span class="self">self</span>.num_entries + other.num_entries,
cache_hits: <span class="self">self</span>.cache_hits + other.cache_hits,
cache_misses: <span class="self">self</span>.cache_misses + other.cache_misses,
};
}
}
<span class="kw">impl </span>Sum <span class="kw">for </span>CacheStats {
<span class="kw">fn </span>sum&lt;I: Iterator&lt;Item = <span class="self">Self</span>&gt;&gt;(<span class="kw-2">mut </span>iter: I) -&gt; <span class="self">Self </span>{
<span class="kw">let </span><span class="kw-2">mut </span>first = iter.next().unwrap_or_default();
<span class="kw">for </span>el <span class="kw">in </span>iter {
first += el;
}
first
}
}
<span class="kw">impl </span>StoreReader {
<span class="doccomment">/// Opens a store reader
</span><span class="kw">pub fn </span>open(store_file: FileSlice, cache_size: usize) -&gt; io::Result&lt;StoreReader&gt; {
<span class="kw">let </span>(footer, data_and_offset) = DocStoreFooter::extract_footer(store_file)<span class="question-mark">?</span>;
<span class="kw">let </span>(data_file, offset_index_file) = data_and_offset.split(footer.offset <span class="kw">as </span>usize);
<span class="kw">let </span>index_data = offset_index_file.read_bytes()<span class="question-mark">?</span>;
<span class="kw">let </span>space_usage = StoreSpaceUsage::new(data_file.len(), offset_index_file.len());
<span class="kw">let </span>skip_index = SkipIndex::open(index_data);
<span class="prelude-val">Ok</span>(StoreReader {
decompressor: footer.decompressor,
data: data_file,
cache: BlockCache {
cache: Mutex::new(LruCache::new(cache_size)),
cache_hits: Default::default(),
cache_misses: Default::default(),
},
skip_index: Arc::new(skip_index),
space_usage,
})
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>block_checkpoints(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw">impl </span>Iterator&lt;Item = Checkpoint&gt; + <span class="lifetime">&#39;_ </span>{
<span class="self">self</span>.skip_index.checkpoints()
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>decompressor(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; Decompressor {
<span class="self">self</span>.decompressor
}
<span class="doccomment">/// Returns the cache hit and miss statistics of the store reader.
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>cache_stats(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; CacheStats {
<span class="self">self</span>.cache.stats()
}
<span class="doccomment">/// Get checkpoint for `DocId`. The checkpoint can be used to load a block containing the
/// document.
///
/// Advanced API. In most cases use [`get`](Self::get).
</span><span class="kw">fn </span>block_checkpoint(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id: DocId) -&gt; <span class="kw">crate</span>::Result&lt;Checkpoint&gt; {
<span class="self">self</span>.skip_index.seek(doc_id).ok_or_else(|| {
<span class="kw">crate</span>::TantivyError::InvalidArgument(<span class="macro">format!</span>(<span class="string">&quot;Failed to lookup Doc #{}.&quot;</span>, doc_id))
})
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>block_data(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; io::Result&lt;OwnedBytes&gt; {
<span class="self">self</span>.data.read_bytes()
}
<span class="kw">fn </span>get_compressed_block(<span class="kw-2">&amp;</span><span class="self">self</span>, checkpoint: <span class="kw-2">&amp;</span>Checkpoint) -&gt; io::Result&lt;OwnedBytes&gt; {
<span class="self">self</span>.data.slice(checkpoint.byte_range.clone()).read_bytes()
}
<span class="doccomment">/// Loads and decompresses a block.
///
/// Advanced API. In most cases use [`get`](Self::get).
</span><span class="kw">fn </span>read_block(<span class="kw-2">&amp;</span><span class="self">self</span>, checkpoint: <span class="kw-2">&amp;</span>Checkpoint) -&gt; io::Result&lt;Block&gt; {
<span class="kw">let </span>cache_key = checkpoint.byte_range.start;
<span class="kw">if let </span><span class="prelude-val">Some</span>(block) = <span class="self">self</span>.cache.get_from_cache(cache_key) {
<span class="kw">return </span><span class="prelude-val">Ok</span>(block);
}
<span class="kw">let </span>compressed_block = <span class="self">self</span>.get_compressed_block(checkpoint)<span class="question-mark">?</span>;
<span class="kw">let </span>decompressed_block =
OwnedBytes::new(<span class="self">self</span>.decompressor.decompress(compressed_block.as_ref())<span class="question-mark">?</span>);
<span class="self">self</span>.cache
.put_into_cache(cache_key, decompressed_block.clone());
<span class="prelude-val">Ok</span>(decompressed_block)
}
<span class="doccomment">/// Reads a given document.
///
/// Calling `.get(doc)` is relatively costly as it requires
/// decompressing a compressed block. The store utilizes a LRU cache,
/// so accessing docs from the same compressed block should be faster.
/// For that reason a store reader should be kept and reused.
///
/// It should not be called to score documents
/// for instance.
</span><span class="kw">pub fn </span>get(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id: DocId) -&gt; <span class="kw">crate</span>::Result&lt;Document&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>doc_bytes = <span class="self">self</span>.get_document_bytes(doc_id)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(Document::deserialize(<span class="kw-2">&amp;mut </span>doc_bytes)<span class="question-mark">?</span>)
}
<span class="doccomment">/// Returns raw bytes of a given document.
///
/// Calling `.get(doc)` is relatively costly as it requires
/// decompressing a compressed block. The store utilizes a LRU cache,
/// so accessing docs from the same compressed block should be faster.
/// For that reason a store reader should be kept and reused.
</span><span class="kw">pub fn </span>get_document_bytes(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id: DocId) -&gt; <span class="kw">crate</span>::Result&lt;OwnedBytes&gt; {
<span class="kw">let </span>checkpoint = <span class="self">self</span>.block_checkpoint(doc_id)<span class="question-mark">?</span>;
<span class="kw">let </span>block = <span class="self">self</span>.read_block(<span class="kw-2">&amp;</span>checkpoint)<span class="question-mark">?</span>;
<span class="self">Self</span>::get_document_bytes_from_block(block, doc_id, <span class="kw-2">&amp;</span>checkpoint)
}
<span class="doccomment">/// Advanced API.
///
/// In most cases use [`get_document_bytes`](Self::get_document_bytes).
</span><span class="kw">fn </span>get_document_bytes_from_block(
block: OwnedBytes,
doc_id: DocId,
checkpoint: <span class="kw-2">&amp;</span>Checkpoint,
) -&gt; <span class="kw">crate</span>::Result&lt;OwnedBytes&gt; {
<span class="kw">let </span>doc_pos = doc_id - checkpoint.doc_range.start;
<span class="kw">let </span>range = block_read_index(<span class="kw-2">&amp;</span>block, doc_pos)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(block.slice(range))
}
<span class="doccomment">/// Iterator over all Documents in their order as they are stored in the doc store.
/// Use this, if you want to extract all Documents from the doc store.
/// The `alive_bitset` has to be forwarded from the `SegmentReader` or the results may be wrong.
</span><span class="kw">pub fn </span>iter&lt;<span class="lifetime">&#39;a</span>: <span class="lifetime">&#39;b</span>, <span class="lifetime">&#39;b</span>&gt;(
<span class="kw-2">&amp;</span><span class="lifetime">&#39;b </span><span class="self">self</span>,
alive_bitset: <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>AliveBitSet&gt;,
) -&gt; <span class="kw">impl </span>Iterator&lt;Item = <span class="kw">crate</span>::Result&lt;Document&gt;&gt; + <span class="lifetime">&#39;b </span>{
<span class="self">self</span>.iter_raw(alive_bitset).map(|doc_bytes_res| {
<span class="kw">let </span><span class="kw-2">mut </span>doc_bytes = doc_bytes_res<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(Document::deserialize(<span class="kw-2">&amp;mut </span>doc_bytes)<span class="question-mark">?</span>)
})
}
<span class="doccomment">/// Iterator over all raw Documents in their order as they are stored in the doc store.
/// Use this, if you want to extract all Documents from the doc store.
/// The `alive_bitset` has to be forwarded from the `SegmentReader` or the results may be wrong.
</span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>iter_raw&lt;<span class="lifetime">&#39;a</span>: <span class="lifetime">&#39;b</span>, <span class="lifetime">&#39;b</span>&gt;(
<span class="kw-2">&amp;</span><span class="lifetime">&#39;b </span><span class="self">self</span>,
alive_bitset: <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>AliveBitSet&gt;,
) -&gt; <span class="kw">impl </span>Iterator&lt;Item = <span class="kw">crate</span>::Result&lt;OwnedBytes&gt;&gt; + <span class="lifetime">&#39;b </span>{
<span class="kw">let </span>last_doc_id = <span class="self">self
</span>.block_checkpoints()
.last()
.map(|checkpoint| checkpoint.doc_range.end)
.unwrap_or(<span class="number">0</span>);
<span class="kw">let </span><span class="kw-2">mut </span>checkpoint_block_iter = <span class="self">self</span>.block_checkpoints();
<span class="kw">let </span><span class="kw-2">mut </span>curr_checkpoint = checkpoint_block_iter.next();
<span class="kw">let </span><span class="kw-2">mut </span>curr_block = curr_checkpoint
.as_ref()
.map(|checkpoint| <span class="self">self</span>.read_block(checkpoint).map_err(|e| e.kind())); <span class="comment">// map error in order to enable cloning
</span><span class="kw">let </span><span class="kw-2">mut </span>doc_pos = <span class="number">0</span>;
(<span class="number">0</span>..last_doc_id)
.filter_map(<span class="kw">move </span>|doc_id| {
<span class="comment">// filter_map is only used to resolve lifetime issues between the two closures on
// the outer variables
// check move to next checkpoint
</span><span class="kw">if </span>doc_id &gt;= curr_checkpoint.as_ref().unwrap().doc_range.end {
curr_checkpoint = checkpoint_block_iter.next();
curr_block = curr_checkpoint
.as_ref()
.map(|checkpoint| <span class="self">self</span>.read_block(checkpoint).map_err(|e| e.kind()));
doc_pos = <span class="number">0</span>;
}
<span class="kw">let </span>alive = alive_bitset.map_or(<span class="bool-val">true</span>, |bitset| bitset.is_alive(doc_id));
<span class="kw">let </span>res = <span class="kw">if </span>alive {
<span class="prelude-val">Some</span>((curr_block.clone(), doc_pos))
} <span class="kw">else </span>{
<span class="prelude-val">None
</span>};
doc_pos += <span class="number">1</span>;
res
})
.map(<span class="kw">move </span>|(block, doc_pos)| {
<span class="kw">let </span>block = block
.ok_or_else(|| {
DataCorruption::comment_only(
<span class="string">&quot;the current checkpoint in the doc store iterator is none, this \
should never happen&quot;</span>,
)
})<span class="question-mark">?
</span>.map_err(|error_kind| {
std::io::Error::new(error_kind, <span class="string">&quot;error when reading block in doc store&quot;</span>)
})<span class="question-mark">?</span>;
<span class="kw">let </span>range = block_read_index(<span class="kw-2">&amp;</span>block, doc_pos)<span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(block.slice(range))
})
}
<span class="doccomment">/// Summarize total space usage of this store reader.
</span><span class="kw">pub fn </span>space_usage(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; StoreSpaceUsage {
<span class="self">self</span>.space_usage.clone()
}
}
<span class="kw">fn </span>block_read_index(block: <span class="kw-2">&amp;</span>[u8], doc_pos: u32) -&gt; <span class="kw">crate</span>::Result&lt;Range&lt;usize&gt;&gt; {
<span class="kw">let </span>doc_pos = doc_pos <span class="kw">as </span>usize;
<span class="kw">let </span>size_of_u32 = std::mem::size_of::&lt;u32&gt;();
<span class="kw">let </span>index_len_pos = block.len() - size_of_u32;
<span class="kw">let </span>index_len = u32::deserialize(<span class="kw-2">&amp;mut &amp;</span>block[index_len_pos..])<span class="question-mark">? </span><span class="kw">as </span>usize;
<span class="kw">if </span>doc_pos &gt; index_len {
<span class="kw">return </span><span class="prelude-val">Err</span>(<span class="kw">crate</span>::TantivyError::InternalError(
<span class="string">&quot;Attempted to read doc from wrong block&quot;</span>.to_owned(),
));
}
<span class="kw">let </span>index_start = block.len() - (index_len + <span class="number">1</span>) * size_of_u32;
<span class="kw">let </span>index = <span class="kw-2">&amp;</span>block[index_start..index_start + index_len * size_of_u32];
<span class="kw">let </span>start_offset = u32::deserialize(<span class="kw-2">&amp;mut &amp;</span>index[doc_pos * size_of_u32..])<span class="question-mark">? </span><span class="kw">as </span>usize;
<span class="kw">let </span>end_offset = u32::deserialize(<span class="kw-2">&amp;mut &amp;</span>index[(doc_pos + <span class="number">1</span>) * size_of_u32..])
.unwrap_or(index_start <span class="kw">as </span>u32) <span class="kw">as </span>usize;
<span class="prelude-val">Ok</span>(start_offset..end_offset)
}
<span class="attribute">#[cfg(feature = <span class="string">&quot;quickwit&quot;</span>)]
</span><span class="kw">impl </span>StoreReader {
<span class="doccomment">/// Advanced API.
///
/// In most cases use [`get_async`](Self::get_async)
///
/// Loads and decompresses a block asynchronously.
</span><span class="kw">async fn </span>read_block_async(<span class="kw-2">&amp;</span><span class="self">self</span>, checkpoint: <span class="kw-2">&amp;</span>Checkpoint) -&gt; <span class="kw">crate</span>::AsyncIoResult&lt;Block&gt; {
<span class="kw">let </span>cache_key = checkpoint.byte_range.start;
<span class="kw">if let </span><span class="prelude-val">Some</span>(block) = <span class="self">self</span>.cache.get_from_cache(checkpoint.byte_range.start) {
<span class="kw">return </span><span class="prelude-val">Ok</span>(block);
}
<span class="kw">let </span>compressed_block = <span class="self">self
</span>.data
.slice(checkpoint.byte_range.clone())
.read_bytes_async()
.<span class="kw">await</span><span class="question-mark">?</span>;
<span class="kw">let </span>decompressed_block =
OwnedBytes::new(<span class="self">self</span>.decompressor.decompress(compressed_block.as_ref())<span class="question-mark">?</span>);
<span class="self">self</span>.cache
.put_into_cache(cache_key, decompressed_block.clone());
<span class="prelude-val">Ok</span>(decompressed_block)
}
<span class="doccomment">/// Reads raw bytes of a given document asynchronously.
</span><span class="kw">pub async fn </span>get_document_bytes_async(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id: DocId) -&gt; <span class="kw">crate</span>::Result&lt;OwnedBytes&gt; {
<span class="kw">let </span>checkpoint = <span class="self">self</span>.block_checkpoint(doc_id)<span class="question-mark">?</span>;
<span class="kw">let </span>block = <span class="self">self</span>.read_block_async(<span class="kw-2">&amp;</span>checkpoint).<span class="kw">await</span><span class="question-mark">?</span>;
<span class="self">Self</span>::get_document_bytes_from_block(block, doc_id, <span class="kw-2">&amp;</span>checkpoint)
}
<span class="doccomment">/// Fetches a document asynchronously. Async version of [`get`](Self::get).
</span><span class="kw">pub async fn </span>get_async(<span class="kw-2">&amp;</span><span class="self">self</span>, doc_id: DocId) -&gt; <span class="kw">crate</span>::Result&lt;Document&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>doc_bytes = <span class="self">self</span>.get_document_bytes_async(doc_id).<span class="kw">await</span><span class="question-mark">?</span>;
<span class="prelude-val">Ok</span>(Document::deserialize(<span class="kw-2">&amp;mut </span>doc_bytes)<span class="question-mark">?</span>)
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span>std::path::Path;
<span class="kw">use super</span>::<span class="kw-2">*</span>;
<span class="kw">use </span><span class="kw">crate</span>::directory::RamDirectory;
<span class="kw">use </span><span class="kw">crate</span>::schema::{Document, Field};
<span class="kw">use </span><span class="kw">crate</span>::store::tests::write_lorem_ipsum_store;
<span class="kw">use </span><span class="kw">crate</span>::store::Compressor;
<span class="kw">use </span><span class="kw">crate</span>::Directory;
<span class="kw">const </span>BLOCK_SIZE: usize = <span class="number">16_384</span>;
<span class="kw">fn </span>get_text_field&lt;<span class="lifetime">&#39;a</span>&gt;(doc: <span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>Document, field: <span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>Field) -&gt; <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>str&gt; {
doc.get_first(<span class="kw-2">*</span>field).and_then(|f| f.as_text())
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_store_lru_cache() -&gt; <span class="kw">crate</span>::Result&lt;()&gt; {
<span class="kw">let </span>directory = RamDirectory::create();
<span class="kw">let </span>path = Path::new(<span class="string">&quot;store&quot;</span>);
<span class="kw">let </span>writer = directory.open_write(path)<span class="question-mark">?</span>;
<span class="kw">let </span>schema = write_lorem_ipsum_store(writer, <span class="number">500</span>, Compressor::default(), BLOCK_SIZE, <span class="bool-val">true</span>);
<span class="kw">let </span>title = schema.get_field(<span class="string">&quot;title&quot;</span>).unwrap();
<span class="kw">let </span>store_file = directory.open_read(path)<span class="question-mark">?</span>;
<span class="kw">let </span>store = StoreReader::open(store_file, DOCSTORE_CACHE_CAPACITY)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(store.cache.len(), <span class="number">0</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_hits, <span class="number">0</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_misses, <span class="number">0</span>);
<span class="kw">let </span>doc = store.get(<span class="number">0</span>)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(get_text_field(<span class="kw-2">&amp;</span>doc, <span class="kw-2">&amp;</span>title), <span class="prelude-val">Some</span>(<span class="string">&quot;Doc 0&quot;</span>));
<span class="macro">assert_eq!</span>(store.cache.len(), <span class="number">1</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_hits, <span class="number">0</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_misses, <span class="number">1</span>);
<span class="macro">assert_eq!</span>(store.cache.peek_lru(), <span class="prelude-val">Some</span>(<span class="number">0</span>));
<span class="kw">let </span>doc = store.get(<span class="number">499</span>)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(get_text_field(<span class="kw-2">&amp;</span>doc, <span class="kw-2">&amp;</span>title), <span class="prelude-val">Some</span>(<span class="string">&quot;Doc 499&quot;</span>));
<span class="macro">assert_eq!</span>(store.cache.len(), <span class="number">2</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_hits, <span class="number">0</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_misses, <span class="number">2</span>);
<span class="macro">assert_eq!</span>(store.cache.peek_lru(), <span class="prelude-val">Some</span>(<span class="number">0</span>));
<span class="kw">let </span>doc = store.get(<span class="number">0</span>)<span class="question-mark">?</span>;
<span class="macro">assert_eq!</span>(get_text_field(<span class="kw-2">&amp;</span>doc, <span class="kw-2">&amp;</span>title), <span class="prelude-val">Some</span>(<span class="string">&quot;Doc 0&quot;</span>));
<span class="macro">assert_eq!</span>(store.cache.len(), <span class="number">2</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_hits, <span class="number">1</span>);
<span class="macro">assert_eq!</span>(store.cache_stats().cache_misses, <span class="number">2</span>);
<span class="macro">assert_eq!</span>(store.cache.peek_lru(), <span class="prelude-val">Some</span>(<span class="number">11163</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>