| <!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/termdict.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>termdict.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::io::{<span class="self">self</span>, Write}; |
| |
| <span class="kw">use </span>common::{BinarySerializable, CountingWriter}; |
| <span class="kw">use </span>once_cell::sync::Lazy; |
| <span class="kw">use </span>tantivy_fst::raw::Fst; |
| <span class="kw">use </span>tantivy_fst::Automaton; |
| |
| <span class="kw">use </span><span class="kw">super</span>::term_info_store::{TermInfoStore, TermInfoStoreWriter}; |
| <span class="kw">use super</span>::{TermStreamer, TermStreamerBuilder}; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::{FileSlice, OwnedBytes}; |
| <span class="kw">use </span><span class="kw">crate</span>::error::DataCorruption; |
| <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">fn </span>convert_fst_error(e: tantivy_fst::Error) -> io::Error { |
| io::Error::new(io::ErrorKind::Other, e) |
| } |
| |
| <span class="doccomment">/// Builder for the new term dictionary. |
| /// |
| /// Inserting must be done in the order of the `keys`. |
| </span><span class="kw">pub struct </span>TermDictionaryBuilder<W> { |
| fst_builder: tantivy_fst::MapBuilder<W>, |
| term_info_store_writer: TermInfoStoreWriter, |
| term_ord: u64, |
| } |
| |
| <span class="kw">impl</span><W> TermDictionaryBuilder<W> |
| <span class="kw">where </span>W: Write |
| { |
| <span class="doccomment">/// Creates a new `TermDictionaryBuilder` |
| </span><span class="kw">pub fn </span>create(w: W) -> io::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>fst_builder = tantivy_fst::MapBuilder::new(w).map_err(convert_fst_error)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(TermDictionaryBuilder { |
| fst_builder, |
| term_info_store_writer: TermInfoStoreWriter::new(), |
| term_ord: <span class="number">0</span>, |
| }) |
| } |
| |
| <span class="doccomment">/// Inserts a `(key, value)` pair in the term dictionary. |
| /// |
| /// *Keys have to be inserted in order.* |
| </span><span class="kw">pub fn </span>insert<K: AsRef<[u8]>>(<span class="kw-2">&mut </span><span class="self">self</span>, key_ref: K, value: <span class="kw-2">&</span>TermInfo) -> io::Result<()> { |
| <span class="kw">let </span>key = key_ref.as_ref(); |
| <span class="self">self</span>.insert_key(key)<span class="question-mark">?</span>; |
| <span class="self">self</span>.insert_value(value)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// # Warning |
| /// Horribly dangerous internal API |
| /// |
| /// If used, it must be used by systematically alternating calls |
| /// to insert_key and insert_value. |
| /// |
| /// Prefer using `.insert(key, value)` |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>insert_key(<span class="kw-2">&mut </span><span class="self">self</span>, key: <span class="kw-2">&</span>[u8]) -> io::Result<()> { |
| <span class="self">self</span>.fst_builder |
| .insert(key, <span class="self">self</span>.term_ord) |
| .map_err(convert_fst_error)<span class="question-mark">?</span>; |
| <span class="self">self</span>.term_ord += <span class="number">1</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// # Warning |
| /// |
| /// Horribly dangerous internal API. See `.insert_key(...)`. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>insert_value(<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>.term_info_store_writer.write_term_info(term_info)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Finalize writing the builder, and returns the underlying |
| /// `Write` object. |
| </span><span class="kw">pub fn </span>finish(<span class="kw-2">mut </span><span class="self">self</span>) -> io::Result<W> { |
| <span class="kw">let </span><span class="kw-2">mut </span>file = <span class="self">self</span>.fst_builder.into_inner().map_err(convert_fst_error)<span class="question-mark">?</span>; |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>counting_writer = CountingWriter::wrap(<span class="kw-2">&mut </span>file); |
| <span class="self">self</span>.term_info_store_writer |
| .serialize(<span class="kw-2">&mut </span>counting_writer)<span class="question-mark">?</span>; |
| <span class="kw">let </span>footer_size = counting_writer.written_bytes(); |
| (footer_size <span class="kw">as </span>u64).serialize(<span class="kw-2">&mut </span>counting_writer)<span class="question-mark">?</span>; |
| } |
| <span class="prelude-val">Ok</span>(file) |
| } |
| } |
| |
| <span class="kw">fn </span>open_fst_index(fst_file: FileSlice) -> <span class="kw">crate</span>::Result<tantivy_fst::Map<OwnedBytes>> { |
| <span class="kw">let </span>bytes = fst_file.read_bytes()<span class="question-mark">?</span>; |
| <span class="kw">let </span>fst = Fst::new(bytes) |
| .map_err(|err| DataCorruption::comment_only(<span class="macro">format!</span>(<span class="string">"Fst data is corrupted: {:?}"</span>, err)))<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(tantivy_fst::Map::from(fst)) |
| } |
| |
| <span class="kw">static </span>EMPTY_TERM_DICT_FILE: Lazy<FileSlice> = Lazy::new(|| { |
| <span class="kw">let </span>term_dictionary_data: Vec<u8> = TermDictionaryBuilder::create(Vec::<u8>::new()) |
| .expect(<span class="string">"Creating a TermDictionaryBuilder in a Vec<u8> should never fail"</span>) |
| .finish() |
| .expect(<span class="string">"Writing in a Vec<u8> should never fail"</span>); |
| FileSlice::from(term_dictionary_data) |
| }); |
| |
| <span class="doccomment">/// The term dictionary contains all of the terms in |
| /// `tantivy index` in a sorted manner. |
| /// |
| /// The `Fst` crate is used to associate terms to their |
| /// respective `TermOrdinal`. The `TermInfoStore` then makes it |
| /// possible to fetch the associated `TermInfo`. |
| </span><span class="kw">pub struct </span>TermDictionary { |
| fst_index: tantivy_fst::Map<OwnedBytes>, |
| term_info_store: TermInfoStore, |
| } |
| |
| <span class="kw">impl </span>TermDictionary { |
| <span class="doccomment">/// Opens a `TermDictionary`. |
| </span><span class="kw">pub fn </span>open(file: FileSlice) -> <span class="kw">crate</span>::Result<<span class="self">Self</span>> { |
| <span class="kw">let </span>(main_slice, footer_len_slice) = file.split_from_end(<span class="number">8</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>footer_len_bytes = footer_len_slice.read_bytes()<span class="question-mark">?</span>; |
| <span class="kw">let </span>footer_size = u64::deserialize(<span class="kw-2">&mut </span>footer_len_bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>(fst_file_slice, values_file_slice) = main_slice.split_from_end(footer_size <span class="kw">as </span>usize); |
| <span class="kw">let </span>fst_index = open_fst_index(fst_file_slice)<span class="question-mark">?</span>; |
| <span class="kw">let </span>term_info_store = TermInfoStore::open(values_file_slice)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(TermDictionary { |
| fst_index, |
| term_info_store, |
| }) |
| } |
| |
| <span class="doccomment">/// Creates an empty term dictionary which contains no terms. |
| </span><span class="kw">pub fn </span>empty() -> <span class="self">Self </span>{ |
| TermDictionary::open(EMPTY_TERM_DICT_FILE.clone()).unwrap() |
| } |
| |
| <span class="doccomment">/// Returns the number of terms in the dictionary. |
| /// Term ordinals range from 0 to `num_terms() - 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>.term_info_store.num_terms() |
| } |
| |
| <span class="doccomment">/// Returns the ordinal associated with a given term. |
| </span><span class="kw">pub fn </span>term_ord<K: AsRef<[u8]>>(<span class="kw-2">&</span><span class="self">self</span>, key: K) -> io::Result<<span class="prelude-ty">Option</span><TermOrdinal>> { |
| <span class="prelude-val">Ok</span>(<span class="self">self</span>.fst_index.get(key)) |
| } |
| |
| <span class="doccomment">/// Stores the term associated with a given term ordinal in |
| /// a `bytes` buffer. |
| /// |
| /// Term ordinals are defined as the position of the term in |
| /// the sorted list of terms. |
| /// |
| /// Returns true if and only if the term has been found. |
| /// |
| /// Regardless of whether the term is found or not, |
| /// the buffer may be modified. |
| </span><span class="kw">pub fn </span>ord_to_term(<span class="kw-2">&</span><span class="self">self</span>, <span class="kw-2">mut </span>ord: TermOrdinal, bytes: <span class="kw-2">&mut </span>Vec<u8>) -> io::Result<bool> { |
| bytes.clear(); |
| <span class="kw">let </span>fst = <span class="self">self</span>.fst_index.as_fst(); |
| <span class="kw">let </span><span class="kw-2">mut </span>node = fst.root(); |
| <span class="kw">while </span>ord != <span class="number">0 </span>|| !node.is_final() { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(transition) = node |
| .transitions() |
| .take_while(|transition| transition.out.value() <= ord) |
| .last() |
| { |
| ord -= transition.out.value(); |
| bytes.push(transition.inp); |
| <span class="kw">let </span>new_node_addr = transition.addr; |
| node = fst.node(new_node_addr); |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(<span class="bool-val">false</span>); |
| } |
| } |
| <span class="prelude-val">Ok</span>(<span class="bool-val">true</span>) |
| } |
| |
| <span class="doccomment">/// Returns the number of terms in the dictionary. |
| </span><span class="kw">pub fn </span>term_info_from_ord(<span class="kw-2">&</span><span class="self">self</span>, term_ord: TermOrdinal) -> TermInfo { |
| <span class="self">self</span>.term_info_store.get(term_ord) |
| } |
| |
| <span class="doccomment">/// Lookups the value corresponding to the key. |
| </span><span class="kw">pub fn </span>get<K: AsRef<[u8]>>(<span class="kw-2">&</span><span class="self">self</span>, key: K) -> io::Result<<span class="prelude-ty">Option</span><TermInfo>> { |
| <span class="prelude-val">Ok</span>(<span class="self">self |
| </span>.term_ord(key)<span class="question-mark">? |
| </span>.map(|term_ord| <span class="self">self</span>.term_info_from_ord(term_ord))) |
| } |
| |
| <span class="doccomment">/// Returns a range builder, to stream all of the terms |
| /// within an interval. |
| </span><span class="kw">pub fn </span>range(<span class="kw-2">&</span><span class="self">self</span>) -> TermStreamerBuilder<<span class="lifetime">'_</span>> { |
| TermStreamerBuilder::new(<span class="self">self</span>, <span class="self">self</span>.fst_index.range()) |
| } |
| |
| <span class="doccomment">/// A stream of all the sorted terms. |
| </span><span class="kw">pub fn </span>stream(<span class="kw-2">&</span><span class="self">self</span>) -> io::Result<TermStreamer<<span class="lifetime">'_</span>>> { |
| <span class="self">self</span>.range().into_stream() |
| } |
| |
| <span class="doccomment">/// Returns a search builder, to stream all of the terms |
| /// within the Automaton |
| </span><span class="kw">pub fn </span>search<<span class="lifetime">'a</span>, A: Automaton + <span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="self">self</span>, automaton: A) -> TermStreamerBuilder<<span class="lifetime">'a</span>, A> { |
| <span class="kw">let </span>stream_builder = <span class="self">self</span>.fst_index.search(automaton); |
| TermStreamerBuilder::<A>::new(<span class="self">self</span>, stream_builder) |
| } |
| } |
| </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> |