| <!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/termdict/fst_termdict/term_info_store.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>term_info_store.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::cmp; |
| <span class="kw">use </span>std::io::{<span class="self">self</span>, Read, Write}; |
| |
| <span class="kw">use </span>byteorder::{ByteOrder, LittleEndian}; |
| <span class="kw">use </span>common::{BinarySerializable, FixedSize}; |
| <span class="kw">use </span>tantivy_bitpacker::{compute_num_bits, BitPacker}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::directory::{FileSlice, OwnedBytes}; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::TermInfo; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::TermOrdinal; |
| |
| <span class="kw">const </span>BLOCK_LEN: usize = <span class="number">256</span>; |
| |
| <span class="attribute">#[derive(Debug, Eq, PartialEq, Default)] |
| </span><span class="kw">struct </span>TermInfoBlockMeta { |
| offset: u64, |
| ref_term_info: TermInfo, |
| doc_freq_nbits: u8, |
| postings_offset_nbits: u8, |
| positions_offset_nbits: u8, |
| } |
| |
| <span class="kw">impl </span>BinarySerializable <span class="kw">for </span>TermInfoBlockMeta { |
| <span class="kw">fn </span>serialize<W: Write>(<span class="kw-2">&</span><span class="self">self</span>, write: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| <span class="self">self</span>.offset.serialize(write)<span class="question-mark">?</span>; |
| <span class="self">self</span>.ref_term_info.serialize(write)<span class="question-mark">?</span>; |
| write.write_all(<span class="kw-2">&</span>[ |
| <span class="self">self</span>.doc_freq_nbits, |
| <span class="self">self</span>.postings_offset_nbits, |
| <span class="self">self</span>.positions_offset_nbits, |
| ])<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>deserialize<R: Read>(reader: <span class="kw-2">&mut </span>R) -> io::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>offset = u64::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="kw">let </span>ref_term_info = TermInfo::deserialize(reader)<span class="question-mark">?</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = [<span class="number">0u8</span>; <span class="number">3</span>]; |
| reader.read_exact(<span class="kw-2">&mut </span>buffer)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(TermInfoBlockMeta { |
| offset, |
| ref_term_info, |
| doc_freq_nbits: buffer[<span class="number">0</span>], |
| postings_offset_nbits: buffer[<span class="number">1</span>], |
| positions_offset_nbits: buffer[<span class="number">2</span>], |
| }) |
| } |
| } |
| |
| <span class="kw">impl </span>FixedSize <span class="kw">for </span>TermInfoBlockMeta { |
| <span class="kw">const </span>SIZE_IN_BYTES: usize = |
| u64::SIZE_IN_BYTES + TermInfo::SIZE_IN_BYTES + <span class="number">3 </span>* u8::SIZE_IN_BYTES; |
| } |
| |
| <span class="kw">impl </span>TermInfoBlockMeta { |
| <span class="kw">fn </span>num_bits(<span class="kw-2">&</span><span class="self">self</span>) -> u8 { |
| <span class="self">self</span>.doc_freq_nbits + <span class="self">self</span>.postings_offset_nbits + <span class="self">self</span>.positions_offset_nbits |
| } |
| |
| <span class="comment">// Here inner_offset is the offset within the block, WITHOUT the first term_info. |
| // In other word, term_info #1,#2,#3 gets inner_offset 0,1,2... While term_info #0 |
| // is encoded without bitpacking. |
| </span><span class="kw">fn </span>deserialize_term_info(<span class="kw-2">&</span><span class="self">self</span>, data: <span class="kw-2">&</span>[u8], inner_offset: usize) -> TermInfo { |
| <span class="macro">assert!</span>(inner_offset < BLOCK_LEN - <span class="number">1</span>); |
| <span class="kw">let </span>num_bits = <span class="self">self</span>.num_bits() <span class="kw">as </span>usize; |
| |
| <span class="kw">let </span>posting_start_addr = num_bits * inner_offset; |
| <span class="comment">// the posting_start is the posting_start of the next term info. |
| </span><span class="kw">let </span>posting_end_addr = posting_start_addr + num_bits; |
| <span class="kw">let </span>positions_start_addr = posting_start_addr + <span class="self">self</span>.postings_offset_nbits <span class="kw">as </span>usize; |
| <span class="comment">// the position_end is the positions_start of the next term info. |
| </span><span class="kw">let </span>positions_end_addr = positions_start_addr + num_bits <span class="kw">as </span>usize; |
| |
| <span class="kw">let </span>doc_freq_addr = positions_start_addr + <span class="self">self</span>.positions_offset_nbits <span class="kw">as </span>usize; |
| |
| <span class="kw">let </span>postings_start_offset = <span class="self">self</span>.ref_term_info.postings_range.start |
| + extract_bits(data, posting_start_addr, <span class="self">self</span>.postings_offset_nbits) <span class="kw">as </span>usize; |
| <span class="kw">let </span>postings_end_offset = <span class="self">self</span>.ref_term_info.postings_range.start |
| + extract_bits(data, posting_end_addr, <span class="self">self</span>.postings_offset_nbits) <span class="kw">as </span>usize; |
| |
| <span class="kw">let </span>positions_start_offset = <span class="self">self</span>.ref_term_info.positions_range.start |
| + extract_bits(data, positions_start_addr, <span class="self">self</span>.positions_offset_nbits) <span class="kw">as </span>usize; |
| <span class="kw">let </span>positions_end_offset = <span class="self">self</span>.ref_term_info.positions_range.start |
| + extract_bits(data, positions_end_addr, <span class="self">self</span>.positions_offset_nbits) <span class="kw">as </span>usize; |
| |
| <span class="kw">let </span>doc_freq = extract_bits(data, doc_freq_addr, <span class="self">self</span>.doc_freq_nbits) <span class="kw">as </span>u32; |
| |
| TermInfo { |
| doc_freq, |
| postings_range: postings_start_offset..postings_end_offset, |
| positions_range: positions_start_offset..positions_end_offset, |
| } |
| } |
| } |
| |
| <span class="kw">pub struct </span>TermInfoStore { |
| num_terms: usize, |
| block_meta_bytes: OwnedBytes, |
| term_info_bytes: OwnedBytes, |
| } |
| |
| <span class="kw">fn </span>extract_bits(data: <span class="kw-2">&</span>[u8], addr_bits: usize, num_bits: u8) -> u64 { |
| <span class="macro">assert!</span>(num_bits <= <span class="number">56</span>); |
| <span class="kw">let </span>addr_byte = addr_bits / <span class="number">8</span>; |
| <span class="kw">let </span>bit_shift = (addr_bits % <span class="number">8</span>) <span class="kw">as </span>u64; |
| <span class="kw">let </span>val_unshifted_unmasked: u64 = <span class="kw">if </span>data.len() >= addr_byte + <span class="number">8 </span>{ |
| LittleEndian::read_u64(<span class="kw-2">&</span>data[addr_byte..][..<span class="number">8</span>]) |
| } <span class="kw">else </span>{ |
| <span class="comment">// the buffer is not large enough. |
| // Let's copy the few remaining bytes to a 8 byte buffer |
| // padded with 0s. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>buf = [<span class="number">0u8</span>; <span class="number">8</span>]; |
| <span class="kw">let </span>data_to_copy = <span class="kw-2">&</span>data[addr_byte..]; |
| <span class="kw">let </span>nbytes = data_to_copy.len(); |
| buf[..nbytes].copy_from_slice(data_to_copy); |
| LittleEndian::read_u64(<span class="kw-2">&</span>buf) |
| }; |
| <span class="kw">let </span>val_shifted_unmasked = val_unshifted_unmasked >> bit_shift; |
| <span class="kw">let </span>mask = (<span class="number">1u64 </span><< u64::from(num_bits)) - <span class="number">1</span>; |
| val_shifted_unmasked & mask |
| } |
| |
| <span class="kw">impl </span>TermInfoStore { |
| <span class="kw">pub fn </span>open(term_info_store_file: FileSlice) -> <span class="kw">crate</span>::Result<TermInfoStore> { |
| <span class="kw">let </span>(len_slice, main_slice) = term_info_store_file.split(<span class="number">16</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>bytes = len_slice.read_bytes()<span class="question-mark">?</span>; |
| <span class="kw">let </span>len = u64::deserialize(<span class="kw-2">&mut </span>bytes)<span class="question-mark">? </span><span class="kw">as </span>usize; |
| <span class="kw">let </span>num_terms = u64::deserialize(<span class="kw-2">&mut </span>bytes)<span class="question-mark">? </span><span class="kw">as </span>usize; |
| <span class="kw">let </span>(block_meta_file, term_info_file) = main_slice.split(len); |
| <span class="kw">let </span>term_info_bytes = term_info_file.read_bytes()<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(TermInfoStore { |
| num_terms, |
| block_meta_bytes: block_meta_file.read_bytes()<span class="question-mark">?</span>, |
| term_info_bytes, |
| }) |
| } |
| |
| <span class="kw">pub fn </span>get(<span class="kw-2">&</span><span class="self">self</span>, term_ord: TermOrdinal) -> TermInfo { |
| <span class="kw">let </span>block_id = (term_ord <span class="kw">as </span>usize) / BLOCK_LEN; |
| <span class="kw">let </span>buffer = <span class="self">self</span>.block_meta_bytes.as_slice(); |
| <span class="kw">let </span><span class="kw-2">mut </span>block_data: <span class="kw-2">&</span>[u8] = <span class="kw-2">&</span>buffer[block_id * TermInfoBlockMeta::SIZE_IN_BYTES..]; |
| <span class="kw">let </span>term_info_block_data = TermInfoBlockMeta::deserialize(<span class="kw-2">&mut </span>block_data) |
| .expect(<span class="string">"Failed to deserialize terminfoblockmeta"</span>); |
| <span class="kw">let </span>inner_offset = (term_ord <span class="kw">as </span>usize) % BLOCK_LEN; |
| <span class="kw">if </span>inner_offset == <span class="number">0 </span>{ |
| <span class="kw">return </span>term_info_block_data.ref_term_info; |
| } |
| <span class="kw">let </span>term_info_data = <span class="self">self</span>.term_info_bytes.as_slice(); |
| term_info_block_data.deserialize_term_info( |
| <span class="kw-2">&</span>term_info_data[term_info_block_data.offset <span class="kw">as </span>usize..], |
| inner_offset - <span class="number">1</span>, |
| ) |
| } |
| |
| <span class="kw">pub fn </span>num_terms(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.num_terms |
| } |
| } |
| |
| <span class="kw">pub struct </span>TermInfoStoreWriter { |
| buffer_block_metas: Vec<u8>, |
| buffer_term_infos: Vec<u8>, |
| term_infos: Vec<TermInfo>, |
| num_terms: u64, |
| } |
| |
| <span class="kw">fn </span>bitpack_serialize<W: Write>( |
| write: <span class="kw-2">&mut </span>W, |
| bit_packer: <span class="kw-2">&mut </span>BitPacker, |
| term_info_block_meta: <span class="kw-2">&</span>TermInfoBlockMeta, |
| term_info: <span class="kw-2">&</span>TermInfo, |
| ) -> io::Result<()> { |
| bit_packer.write( |
| term_info.postings_range.start <span class="kw">as </span>u64, |
| term_info_block_meta.postings_offset_nbits, |
| write, |
| )<span class="question-mark">?</span>; |
| bit_packer.write( |
| term_info.positions_range.start <span class="kw">as </span>u64, |
| term_info_block_meta.positions_offset_nbits, |
| write, |
| )<span class="question-mark">?</span>; |
| bit_packer.write( |
| u64::from(term_info.doc_freq), |
| term_info_block_meta.doc_freq_nbits, |
| write, |
| )<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">impl </span>TermInfoStoreWriter { |
| <span class="kw">pub fn </span>new() -> TermInfoStoreWriter { |
| TermInfoStoreWriter { |
| buffer_block_metas: Vec::new(), |
| buffer_term_infos: Vec::new(), |
| term_infos: Vec::with_capacity(BLOCK_LEN), |
| num_terms: <span class="number">0u64</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>flush_block(<span class="kw-2">&mut </span><span class="self">self</span>) -> io::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>bit_packer = BitPacker::new(); |
| <span class="kw">let </span>ref_term_info = <span class="self">self</span>.term_infos[<span class="number">0</span>].clone(); |
| |
| <span class="kw">let </span>last_term_info = <span class="kw">if let </span><span class="prelude-val">Some</span>(last_term_info) = <span class="self">self</span>.term_infos.last().cloned() { |
| last_term_info |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(()); |
| }; |
| <span class="kw">let </span>postings_end_offset = |
| last_term_info.postings_range.end - ref_term_info.postings_range.start; |
| <span class="kw">let </span>positions_end_offset = |
| last_term_info.positions_range.end - ref_term_info.positions_range.start; |
| <span class="kw">for </span>term_info <span class="kw">in </span><span class="kw-2">&mut </span><span class="self">self</span>.term_infos[<span class="number">1</span>..] { |
| term_info.postings_range.start -= ref_term_info.postings_range.start; |
| term_info.positions_range.start -= ref_term_info.positions_range.start; |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>max_doc_freq: u32 = <span class="number">0u32</span>; |
| |
| <span class="kw">for </span>term_info <span class="kw">in </span><span class="kw-2">&</span><span class="self">self</span>.term_infos[<span class="number">1</span>..] { |
| max_doc_freq = cmp::max(max_doc_freq, term_info.doc_freq); |
| } |
| |
| <span class="kw">let </span>max_doc_freq_nbits: u8 = compute_num_bits(u64::from(max_doc_freq)); |
| <span class="kw">let </span>max_postings_offset_nbits = compute_num_bits(postings_end_offset <span class="kw">as </span>u64); |
| <span class="kw">let </span>max_positions_offset_nbits = compute_num_bits(positions_end_offset <span class="kw">as </span>u64); |
| |
| <span class="kw">let </span>term_info_block_meta = TermInfoBlockMeta { |
| offset: <span class="self">self</span>.buffer_term_infos.len() <span class="kw">as </span>u64, |
| ref_term_info, |
| doc_freq_nbits: max_doc_freq_nbits, |
| postings_offset_nbits: max_postings_offset_nbits, |
| positions_offset_nbits: max_positions_offset_nbits, |
| }; |
| |
| term_info_block_meta.serialize(<span class="kw-2">&mut </span><span class="self">self</span>.buffer_block_metas)<span class="question-mark">?</span>; |
| <span class="kw">for </span>term_info <span class="kw">in </span><span class="kw-2">&</span><span class="self">self</span>.term_infos[<span class="number">1</span>..] { |
| bitpack_serialize( |
| <span class="kw-2">&mut </span><span class="self">self</span>.buffer_term_infos, |
| <span class="kw-2">&mut </span>bit_packer, |
| <span class="kw-2">&</span>term_info_block_meta, |
| term_info, |
| )<span class="question-mark">?</span>; |
| } |
| |
| <span class="comment">// We still need to serialize the end offset for postings & positions. |
| </span>bit_packer.write( |
| postings_end_offset <span class="kw">as </span>u64, |
| term_info_block_meta.postings_offset_nbits, |
| <span class="kw-2">&mut </span><span class="self">self</span>.buffer_term_infos, |
| )<span class="question-mark">?</span>; |
| bit_packer.write( |
| positions_end_offset <span class="kw">as </span>u64, |
| term_info_block_meta.positions_offset_nbits, |
| <span class="kw-2">&mut </span><span class="self">self</span>.buffer_term_infos, |
| )<span class="question-mark">?</span>; |
| |
| <span class="comment">// Block need end up at the end of a byte. |
| </span>bit_packer.flush(<span class="kw-2">&mut </span><span class="self">self</span>.buffer_term_infos)<span class="question-mark">?</span>; |
| <span class="self">self</span>.term_infos.clear(); |
| |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">pub fn </span>write_term_info(<span class="kw-2">&mut </span><span class="self">self</span>, term_info: <span class="kw-2">&</span>TermInfo) -> io::Result<()> { |
| <span class="self">self</span>.num_terms += <span class="number">1u64</span>; |
| <span class="self">self</span>.term_infos.push(term_info.clone()); |
| <span class="kw">if </span><span class="self">self</span>.term_infos.len() >= BLOCK_LEN { |
| <span class="self">self</span>.flush_block()<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">pub fn </span>serialize<W: io::Write>(<span class="kw-2">&mut </span><span class="self">self</span>, write: <span class="kw-2">&mut </span>W) -> io::Result<()> { |
| <span class="kw">if </span>!<span class="self">self</span>.term_infos.is_empty() { |
| <span class="self">self</span>.flush_block()<span class="question-mark">?</span>; |
| } |
| <span class="kw">let </span>len = <span class="self">self</span>.buffer_block_metas.len() <span class="kw">as </span>u64; |
| len.serialize(write)<span class="question-mark">?</span>; |
| <span class="self">self</span>.num_terms.serialize(write)<span class="question-mark">?</span>; |
| write.write_all(<span class="kw-2">&</span><span class="self">self</span>.buffer_block_metas)<span class="question-mark">?</span>; |
| write.write_all(<span class="kw-2">&</span><span class="self">self</span>.buffer_term_infos)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>common; |
| <span class="kw">use </span>common::BinarySerializable; |
| <span class="kw">use </span>tantivy_bitpacker::{compute_num_bits, BitPacker}; |
| |
| <span class="kw">use super</span>::{extract_bits, TermInfoBlockMeta, TermInfoStore, TermInfoStoreWriter}; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::FileSlice; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::TermInfo; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_term_info_block() { |
| <span class="kw">crate</span>::tests::fixed_size_test::<TermInfoBlockMeta>(); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_bitpacked() { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| <span class="kw">let </span><span class="kw-2">mut </span>bitpack = BitPacker::new(); |
| bitpack.write(<span class="number">321u64</span>, <span class="number">9</span>, <span class="kw-2">&mut </span>buffer).unwrap(); |
| <span class="macro">assert_eq!</span>(compute_num_bits(<span class="number">321u64</span>), <span class="number">9</span>); |
| bitpack.write(<span class="number">2u64</span>, <span class="number">2</span>, <span class="kw-2">&mut </span>buffer).unwrap(); |
| <span class="macro">assert_eq!</span>(compute_num_bits(<span class="number">2u64</span>), <span class="number">2</span>); |
| bitpack.write(<span class="number">51</span>, <span class="number">6</span>, <span class="kw-2">&mut </span>buffer).unwrap(); |
| <span class="macro">assert_eq!</span>(compute_num_bits(<span class="number">51</span>), <span class="number">6</span>); |
| bitpack.close(<span class="kw-2">&mut </span>buffer).unwrap(); |
| <span class="macro">assert_eq!</span>(buffer.len(), <span class="number">3 </span>+ <span class="number">7</span>); |
| <span class="macro">assert_eq!</span>(extract_bits(<span class="kw-2">&</span>buffer[..], <span class="number">0</span>, <span class="number">9</span>), <span class="number">321u64</span>); |
| <span class="macro">assert_eq!</span>(extract_bits(<span class="kw-2">&</span>buffer[..], <span class="number">9</span>, <span class="number">2</span>), <span class="number">2u64</span>); |
| <span class="macro">assert_eq!</span>(extract_bits(<span class="kw-2">&</span>buffer[..], <span class="number">11</span>, <span class="number">6</span>), <span class="number">51u64</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_term_info_block_meta_serialization() { |
| <span class="kw">let </span>term_info_block_meta = TermInfoBlockMeta { |
| offset: <span class="number">2009u64</span>, |
| ref_term_info: TermInfo { |
| doc_freq: <span class="number">512</span>, |
| postings_range: <span class="number">51</span>..<span class="number">57</span>, |
| positions_range: <span class="number">110</span>..<span class="number">134</span>, |
| }, |
| doc_freq_nbits: <span class="number">10</span>, |
| postings_offset_nbits: <span class="number">5</span>, |
| positions_offset_nbits: <span class="number">8</span>, |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer: Vec<u8> = Vec::new(); |
| term_info_block_meta.serialize(<span class="kw-2">&mut </span>buffer).unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>cursor: <span class="kw-2">&</span>[u8] = <span class="kw-2">&</span>buffer[..]; |
| <span class="kw">let </span>term_info_block_meta_serde = TermInfoBlockMeta::deserialize(<span class="kw-2">&mut </span>cursor).unwrap(); |
| <span class="macro">assert_eq!</span>(term_info_block_meta_serde, term_info_block_meta); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_pack() -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>store_writer = TermInfoStoreWriter::new(); |
| <span class="kw">let </span><span class="kw-2">mut </span>term_infos = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span>offset = |i| (i * <span class="number">13 </span>+ i * i); |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0usize</span>..<span class="number">1000usize </span>{ |
| <span class="kw">let </span>term_info = TermInfo { |
| doc_freq: i <span class="kw">as </span>u32, |
| postings_range: offset(i)..offset(i + <span class="number">1</span>), |
| positions_range: offset(i) * <span class="number">3</span>..offset(i + <span class="number">1</span>) * <span class="number">3</span>, |
| }; |
| store_writer.write_term_info(<span class="kw-2">&</span>term_info)<span class="question-mark">?</span>; |
| term_infos.push(term_info); |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer = Vec::new(); |
| store_writer.serialize(<span class="kw-2">&mut </span>buffer)<span class="question-mark">?</span>; |
| <span class="kw">let </span>term_info_store = TermInfoStore::open(FileSlice::from(buffer))<span class="question-mark">?</span>; |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..<span class="number">1000 </span>{ |
| <span class="macro">assert_eq!</span>( |
| term_info_store.get(i <span class="kw">as </span>u64), |
| term_infos[i], |
| <span class="string">"term info {}"</span>, |
| i |
| ); |
| } |
| <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> |