| <!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/postings/postings_writer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>postings_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> |
| <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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::io; |
| <span class="kw">use </span>std::marker::PhantomData; |
| <span class="kw">use </span>std::ops::Range; |
| |
| <span class="kw">use </span>rustc_hash::FxHashMap; |
| |
| <span class="kw">use </span><span class="kw">super</span>::stacker::Addr; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::MultiValuedFastFieldWriter; |
| <span class="kw">use </span><span class="kw">crate</span>::fieldnorm::FieldNormReaders; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::doc_id_mapping::DocIdMapping; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::recorder::{BufferLender, Recorder}; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::{ |
| FieldSerializer, IndexingContext, InvertedIndexSerializer, PerFieldPostingsWriter, |
| UnorderedTermId, |
| }; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{Field, FieldType, Schema, Term}; |
| <span class="kw">use </span><span class="kw">crate</span>::termdict::TermOrdinal; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{Token, TokenStream, MAX_TOKEN_LEN}; |
| <span class="kw">use </span><span class="kw">crate</span>::DocId; |
| |
| <span class="kw">const </span>POSITION_GAP: u32 = <span class="number">1</span>; |
| |
| <span class="kw">fn </span>make_field_partition( |
| term_offsets: <span class="kw-2">&</span>[(Term<<span class="kw-2">&</span>[u8]>, Addr, UnorderedTermId)], |
| ) -> Vec<(Field, Range<usize>)> { |
| <span class="kw">let </span>term_offsets_it = term_offsets |
| .iter() |
| .map(|(term, <span class="kw">_</span>, <span class="kw">_</span>)| term.field()) |
| .enumerate(); |
| <span class="kw">let </span><span class="kw-2">mut </span>prev_field_opt = <span class="prelude-val">None</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>fields = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span><span class="kw-2">mut </span>offsets = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>(offset, field) <span class="kw">in </span>term_offsets_it { |
| <span class="kw">if </span><span class="prelude-val">Some</span>(field) != prev_field_opt { |
| prev_field_opt = <span class="prelude-val">Some</span>(field); |
| fields.push(field); |
| offsets.push(offset); |
| } |
| } |
| offsets.push(term_offsets.len()); |
| <span class="kw">let </span><span class="kw-2">mut </span>field_offsets = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..fields.len() { |
| field_offsets.push((fields[i], offsets[i]..offsets[i + <span class="number">1</span>])); |
| } |
| field_offsets |
| } |
| |
| <span class="doccomment">/// Serialize the inverted index. |
| /// It pushes all term, one field at a time, towards the |
| /// postings serializer. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>serialize_postings( |
| ctx: IndexingContext, |
| per_field_postings_writers: <span class="kw-2">&</span>PerFieldPostingsWriter, |
| fieldnorm_readers: FieldNormReaders, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| schema: <span class="kw-2">&</span>Schema, |
| serializer: <span class="kw-2">&mut </span>InvertedIndexSerializer, |
| ) -> <span class="kw">crate</span>::Result<HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>term_offsets: Vec<(Term<<span class="kw-2">&</span>[u8]>, Addr, UnorderedTermId)> = |
| Vec::with_capacity(ctx.term_index.len()); |
| term_offsets.extend(ctx.term_index.iter()); |
| term_offsets.sort_unstable_by_key(|(k, <span class="kw">_</span>, <span class="kw">_</span>)| k.clone()); |
| <span class="kw">let </span><span class="kw-2">mut </span>unordered_term_mappings: HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>> = |
| HashMap::new(); |
| |
| <span class="kw">let </span>field_offsets = make_field_partition(<span class="kw-2">&</span>term_offsets); |
| <span class="kw">for </span>(field, byte_offsets) <span class="kw">in </span>field_offsets { |
| <span class="kw">let </span>field_entry = schema.get_field_entry(field); |
| <span class="kw">match </span><span class="kw-2">*</span>field_entry.field_type() { |
| FieldType::Str(<span class="kw">_</span>) | FieldType::Facet(<span class="kw">_</span>) => { |
| <span class="comment">// populating the (unordered term ord) -> (ordered term ord) mapping |
| // for the field. |
| </span><span class="kw">let </span>unordered_term_ids = term_offsets[byte_offsets.clone()] |
| .iter() |
| .map(|<span class="kw-2">&</span>(<span class="kw">_</span>, <span class="kw">_</span>, bucket)| bucket); |
| <span class="kw">let </span>mapping: FxHashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids |
| .enumerate() |
| .map(|(term_ord, unord_term_id)| { |
| (unord_term_id <span class="kw">as </span>UnorderedTermId, term_ord <span class="kw">as </span>TermOrdinal) |
| }) |
| .collect(); |
| unordered_term_mappings.insert(field, mapping); |
| } |
| FieldType::U64(<span class="kw">_</span>) |
| | FieldType::I64(<span class="kw">_</span>) |
| | FieldType::F64(<span class="kw">_</span>) |
| | FieldType::Date(<span class="kw">_</span>) |
| | FieldType::Bool(<span class="kw">_</span>) => {} |
| FieldType::Bytes(<span class="kw">_</span>) => {} |
| FieldType::JsonObject(<span class="kw">_</span>) => {} |
| FieldType::IpAddr(<span class="kw">_</span>) => {} |
| } |
| |
| <span class="kw">let </span>postings_writer = per_field_postings_writers.get_for_field(field); |
| <span class="kw">let </span>fieldnorm_reader = fieldnorm_readers.get_field(field)<span class="question-mark">?</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>field_serializer = |
| serializer.new_field(field, postings_writer.total_num_tokens(), fieldnorm_reader)<span class="question-mark">?</span>; |
| postings_writer.serialize( |
| <span class="kw-2">&</span>term_offsets[byte_offsets], |
| doc_id_map, |
| <span class="kw-2">&</span>ctx, |
| <span class="kw-2">&mut </span>field_serializer, |
| )<span class="question-mark">?</span>; |
| field_serializer.close()<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(unordered_term_mappings) |
| } |
| |
| <span class="attribute">#[derive(Default)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>IndexingPosition { |
| <span class="kw">pub </span>num_tokens: u32, |
| <span class="kw">pub </span>end_position: u32, |
| } |
| |
| <span class="doccomment">/// The `PostingsWriter` is in charge of receiving documenting |
| /// and building a `Segment` in anonymous memory. |
| /// |
| /// `PostingsWriter` writes in a `MemoryArena`. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait </span>PostingsWriter: Send + Sync { |
| <span class="doccomment">/// Record that a document contains a term at a given position. |
| /// |
| /// * doc - the document id |
| /// * pos - the term position (expressed in tokens) |
| /// * term - the term |
| /// * ctx - Contains a term hashmap and a memory arena to store all necessary posting list |
| /// information. |
| </span><span class="kw">fn </span>subscribe( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| doc: DocId, |
| pos: u32, |
| term: <span class="kw-2">&</span>Term, |
| ctx: <span class="kw-2">&mut </span>IndexingContext, |
| ) -> UnorderedTermId; |
| |
| <span class="doccomment">/// Serializes the postings on disk. |
| /// The actual serialization format is handled by the `PostingsSerializer`. |
| </span><span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| term_addrs: <span class="kw-2">&</span>[(Term<<span class="kw-2">&</span>[u8]>, Addr, UnorderedTermId)], |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ctx: <span class="kw-2">&</span>IndexingContext, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer, |
| ) -> io::Result<()>; |
| |
| <span class="doccomment">/// Tokenize a text and subscribe all of its token. |
| </span><span class="kw">fn </span>index_text( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| doc_id: DocId, |
| token_stream: <span class="kw-2">&mut </span><span class="kw">dyn </span>TokenStream, |
| term_buffer: <span class="kw-2">&mut </span>Term, |
| ctx: <span class="kw-2">&mut </span>IndexingContext, |
| indexing_position: <span class="kw-2">&mut </span>IndexingPosition, |
| <span class="kw-2">mut </span>term_id_fast_field_writer_opt: <span class="prelude-ty">Option</span><<span class="kw-2">&mut </span>MultiValuedFastFieldWriter>, |
| ) { |
| <span class="kw">let </span>end_of_path_idx = term_buffer.len_bytes(); |
| <span class="kw">let </span><span class="kw-2">mut </span>num_tokens = <span class="number">0</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>end_position = indexing_position.end_position; |
| token_stream.process(<span class="kw-2">&mut </span>|token: <span class="kw-2">&</span>Token| { |
| <span class="comment">// We skip all tokens with a len greater than u16. |
| </span><span class="kw">if </span>token.text.len() > MAX_TOKEN_LEN { |
| <span class="macro">warn!</span>( |
| <span class="string">"A token exceeding MAX_TOKEN_LEN ({}>{}) was dropped. Search for \ |
| MAX_TOKEN_LEN in the documentation for more information."</span>, |
| token.text.len(), |
| MAX_TOKEN_LEN |
| ); |
| <span class="kw">return</span>; |
| } |
| term_buffer.truncate_value_bytes(end_of_path_idx); |
| term_buffer.append_bytes(token.text.as_bytes()); |
| <span class="kw">let </span>start_position = indexing_position.end_position + token.position <span class="kw">as </span>u32; |
| end_position = end_position.max(start_position + token.position_length <span class="kw">as </span>u32); |
| <span class="kw">let </span>unordered_term_id = <span class="self">self</span>.subscribe(doc_id, start_position, term_buffer, ctx); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(term_id_fast_field_writer) = term_id_fast_field_writer_opt.as_mut() { |
| term_id_fast_field_writer.add_val(unordered_term_id); |
| } |
| |
| num_tokens += <span class="number">1</span>; |
| }); |
| |
| indexing_position.end_position = end_position + POSITION_GAP; |
| indexing_position.num_tokens += num_tokens; |
| term_buffer.truncate_value_bytes(end_of_path_idx); |
| } |
| |
| <span class="kw">fn </span>total_num_tokens(<span class="kw-2">&</span><span class="self">self</span>) -> u64; |
| } |
| |
| <span class="doccomment">/// The `SpecializedPostingsWriter` is just here to remove dynamic |
| /// dispatch to the recorder information. |
| </span><span class="attribute">#[derive(Default)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>SpecializedPostingsWriter<Rec: Recorder> { |
| total_num_tokens: u64, |
| _recorder_type: PhantomData<Rec>, |
| } |
| |
| <span class="kw">impl</span><Rec: Recorder> From<SpecializedPostingsWriter<Rec>> <span class="kw">for </span>Box<<span class="kw">dyn </span>PostingsWriter> { |
| <span class="kw">fn </span>from( |
| specialized_postings_writer: SpecializedPostingsWriter<Rec>, |
| ) -> Box<<span class="kw">dyn </span>PostingsWriter> { |
| Box::new(specialized_postings_writer) |
| } |
| } |
| |
| <span class="kw">impl</span><Rec: Recorder> SpecializedPostingsWriter<Rec> { |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>serialize_one_term( |
| term: <span class="kw-2">&</span>Term<<span class="kw-2">&</span>[u8]>, |
| addr: Addr, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| buffer_lender: <span class="kw-2">&mut </span>BufferLender, |
| ctx: <span class="kw-2">&</span>IndexingContext, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer, |
| ) -> io::Result<()> { |
| <span class="kw">let </span>recorder: Rec = ctx.term_index.read(addr); |
| <span class="kw">let </span>term_doc_freq = recorder.term_doc_freq().unwrap_or(<span class="number">0u32</span>); |
| serializer.new_term(term.value_bytes(), term_doc_freq)<span class="question-mark">?</span>; |
| recorder.serialize(<span class="kw-2">&</span>ctx.arena, doc_id_map, serializer, buffer_lender); |
| serializer.close_term()<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="kw">impl</span><Rec: Recorder> PostingsWriter <span class="kw">for </span>SpecializedPostingsWriter<Rec> { |
| <span class="kw">fn </span>subscribe( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| doc: DocId, |
| position: u32, |
| term: <span class="kw-2">&</span>Term, |
| ctx: <span class="kw-2">&mut </span>IndexingContext, |
| ) -> UnorderedTermId { |
| <span class="macro">debug_assert!</span>(term.as_slice().len() >= <span class="number">4</span>); |
| <span class="self">self</span>.total_num_tokens += <span class="number">1</span>; |
| <span class="kw">let </span>(term_index, arena) = (<span class="kw-2">&mut </span>ctx.term_index, <span class="kw-2">&mut </span>ctx.arena); |
| term_index.mutate_or_create(term.as_slice(), |opt_recorder: <span class="prelude-ty">Option</span><Rec>| { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">mut </span>recorder) = opt_recorder { |
| <span class="kw">let </span>current_doc = recorder.current_doc(); |
| <span class="kw">if </span>current_doc != doc { |
| recorder.close_doc(arena); |
| recorder.new_doc(doc, arena); |
| } |
| recorder.record_position(position, arena); |
| recorder |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>recorder = Rec::default(); |
| recorder.new_doc(doc, arena); |
| recorder.record_position(position, arena); |
| recorder |
| } |
| }) <span class="kw">as </span>UnorderedTermId |
| } |
| |
| <span class="kw">fn </span>serialize( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| term_addrs: <span class="kw-2">&</span>[(Term<<span class="kw-2">&</span>[u8]>, Addr, UnorderedTermId)], |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ctx: <span class="kw-2">&</span>IndexingContext, |
| serializer: <span class="kw-2">&mut </span>FieldSerializer, |
| ) -> io::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>buffer_lender = BufferLender::default(); |
| <span class="kw">for </span>(term, addr, <span class="kw">_</span>) <span class="kw">in </span>term_addrs { |
| <span class="self">Self</span>::serialize_one_term(term, <span class="kw-2">*</span>addr, doc_id_map, <span class="kw-2">&mut </span>buffer_lender, ctx, serializer)<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>total_num_tokens(<span class="kw-2">&</span><span class="self">self</span>) -> u64 { |
| <span class="self">self</span>.total_num_tokens |
| } |
| } |
| </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> |