| <!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/tokenizer/stop_word_filter/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.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> |
| </pre><pre class="rust"><code><span class="doccomment">//! # Example |
| //! ```rust |
| //! use tantivy::tokenizer::*; |
| //! |
| //! let tokenizer = TextAnalyzer::from(SimpleTokenizer) |
| //! .filter(StopWordFilter::remove(vec!["the".to_string(), "is".to_string()])); |
| //! |
| //! let mut stream = tokenizer.token_stream("the fox is crafty"); |
| //! assert_eq!(stream.next().unwrap().text, "fox"); |
| //! assert_eq!(stream.next().unwrap().text, "crafty"); |
| //! assert!(stream.next().is_none()); |
| //! ``` |
| </span><span class="attribute">#[cfg(feature = <span class="string">"stopwords"</span>)] |
| #[rustfmt::skip] |
| </span><span class="kw">mod </span>stopwords; |
| |
| <span class="kw">use </span>std::sync::Arc; |
| |
| <span class="kw">use </span>rustc_hash::FxHashSet; |
| |
| <span class="kw">use super</span>::{BoxTokenStream, Language, Token, TokenFilter, TokenStream}; |
| |
| <span class="doccomment">/// `TokenFilter` that removes stop words from a token stream |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>StopWordFilter { |
| words: Arc<FxHashSet<String>>, |
| } |
| |
| <span class="kw">impl </span>StopWordFilter { |
| <span class="doccomment">/// Creates a new [`StopWordFilter`] for the given [`Language`] |
| /// |
| /// Returns `Some` if a list of stop words is available and `None` otherwise. |
| </span><span class="attribute">#[cfg(feature = <span class="string">"stopwords"</span>)] |
| </span><span class="kw">pub fn </span>new(language: Language) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>> { |
| <span class="kw">let </span>words = <span class="kw">match </span>language { |
| Language::Danish => stopwords::DANISH, |
| Language::Dutch => stopwords::DUTCH, |
| Language::English => { |
| <span class="comment">// This is the same list of words used by the Apache-licensed Lucene project, |
| // c.f. https://github.com/apache/lucene/blob/d5d6dc079395c47cd6d12dcce3bcfdd2c7d9dc63/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java#L46 |
| </span><span class="kw-2">&</span>[ |
| <span class="string">"a"</span>, <span class="string">"an"</span>, <span class="string">"and"</span>, <span class="string">"are"</span>, <span class="string">"as"</span>, <span class="string">"at"</span>, <span class="string">"be"</span>, <span class="string">"but"</span>, <span class="string">"by"</span>, <span class="string">"for"</span>, <span class="string">"if"</span>, <span class="string">"in"</span>, |
| <span class="string">"into"</span>, <span class="string">"is"</span>, <span class="string">"it"</span>, <span class="string">"no"</span>, <span class="string">"not"</span>, <span class="string">"of"</span>, <span class="string">"on"</span>, <span class="string">"or"</span>, <span class="string">"such"</span>, <span class="string">"that"</span>, <span class="string">"the"</span>, |
| <span class="string">"their"</span>, <span class="string">"then"</span>, <span class="string">"there"</span>, <span class="string">"these"</span>, <span class="string">"they"</span>, <span class="string">"this"</span>, <span class="string">"to"</span>, <span class="string">"was"</span>, <span class="string">"will"</span>, <span class="string">"with"</span>, |
| ] |
| } |
| Language::Finnish => stopwords::FINNISH, |
| Language::French => stopwords::FRENCH, |
| Language::German => stopwords::GERMAN, |
| Language::Italian => stopwords::ITALIAN, |
| Language::Norwegian => stopwords::NORWEGIAN, |
| Language::Portuguese => stopwords::PORTUGUESE, |
| Language::Russian => stopwords::RUSSIAN, |
| Language::Spanish => stopwords::SPANISH, |
| Language::Swedish => stopwords::SWEDISH, |
| <span class="kw">_ </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| }; |
| |
| <span class="prelude-val">Some</span>(<span class="self">Self</span>::remove(words.iter().map(|<span class="kw-2">&</span>word| word.to_owned()))) |
| } |
| |
| <span class="doccomment">/// Creates a `StopWordFilter` given a list of words to remove |
| </span><span class="kw">pub fn </span>remove<W: IntoIterator<Item = String>>(words: W) -> StopWordFilter { |
| StopWordFilter { |
| words: Arc::new(words.into_iter().collect()), |
| } |
| } |
| } |
| |
| <span class="kw">pub struct </span>StopWordFilterStream<<span class="lifetime">'a</span>> { |
| words: Arc<FxHashSet<String>>, |
| tail: BoxTokenStream<<span class="lifetime">'a</span>>, |
| } |
| |
| <span class="kw">impl </span>TokenFilter <span class="kw">for </span>StopWordFilter { |
| <span class="kw">fn </span>transform<<span class="lifetime">'a</span>>(<span class="kw-2">&</span><span class="self">self</span>, token_stream: BoxTokenStream<<span class="lifetime">'a</span>>) -> BoxTokenStream<<span class="lifetime">'a</span>> { |
| BoxTokenStream::from(StopWordFilterStream { |
| words: <span class="self">self</span>.words.clone(), |
| tail: token_stream, |
| }) |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> StopWordFilterStream<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>predicate(<span class="kw-2">&</span><span class="self">self</span>, token: <span class="kw-2">&</span>Token) -> bool { |
| !<span class="self">self</span>.words.contains(<span class="kw-2">&</span>token.text) |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> TokenStream <span class="kw">for </span>StopWordFilterStream<<span class="lifetime">'a</span>> { |
| <span class="kw">fn </span>advance(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="kw">while </span><span class="self">self</span>.tail.advance() { |
| <span class="kw">if </span><span class="self">self</span>.predicate(<span class="self">self</span>.tail.token()) { |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| } |
| <span class="bool-val">false |
| </span>} |
| |
| <span class="kw">fn </span>token(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>Token { |
| <span class="self">self</span>.tail.token() |
| } |
| |
| <span class="kw">fn </span>token_mut(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw-2">&mut </span>Token { |
| <span class="self">self</span>.tail.token_mut() |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::tests::assert_token; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{SimpleTokenizer, StopWordFilter, TextAnalyzer, Token}; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_stop_word() { |
| <span class="kw">let </span>tokens = token_stream_helper(<span class="string">"i am a cat. as yet i have no name."</span>); |
| <span class="macro">assert_eq!</span>(tokens.len(), <span class="number">5</span>); |
| assert_token(<span class="kw-2">&</span>tokens[<span class="number">0</span>], <span class="number">3</span>, <span class="string">"cat"</span>, <span class="number">7</span>, <span class="number">10</span>); |
| assert_token(<span class="kw-2">&</span>tokens[<span class="number">1</span>], <span class="number">5</span>, <span class="string">"yet"</span>, <span class="number">15</span>, <span class="number">18</span>); |
| assert_token(<span class="kw-2">&</span>tokens[<span class="number">2</span>], <span class="number">7</span>, <span class="string">"have"</span>, <span class="number">21</span>, <span class="number">25</span>); |
| assert_token(<span class="kw-2">&</span>tokens[<span class="number">3</span>], <span class="number">8</span>, <span class="string">"no"</span>, <span class="number">26</span>, <span class="number">28</span>); |
| assert_token(<span class="kw-2">&</span>tokens[<span class="number">4</span>], <span class="number">9</span>, <span class="string">"name"</span>, <span class="number">29</span>, <span class="number">33</span>); |
| } |
| |
| <span class="kw">fn </span>token_stream_helper(text: <span class="kw-2">&</span>str) -> Vec<Token> { |
| <span class="kw">let </span>stops = <span class="macro">vec!</span>[ |
| <span class="string">"a"</span>.to_string(), |
| <span class="string">"as"</span>.to_string(), |
| <span class="string">"am"</span>.to_string(), |
| <span class="string">"i"</span>.to_string(), |
| ]; |
| <span class="kw">let </span>a = TextAnalyzer::from(SimpleTokenizer).filter(StopWordFilter::remove(stops)); |
| <span class="kw">let </span><span class="kw-2">mut </span>token_stream = a.token_stream(text); |
| <span class="kw">let </span><span class="kw-2">mut </span>tokens: Vec<Token> = <span class="macro">vec!</span>[]; |
| <span class="kw">let </span><span class="kw-2">mut </span>add_token = |token: <span class="kw-2">&</span>Token| { |
| tokens.push(token.clone()); |
| }; |
| token_stream.process(<span class="kw-2">&mut </span>add_token); |
| 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> |
