| <!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/tokenized_string.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>tokenized_string.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::cmp::Ordering; |
| |
| <span class="kw">use </span>serde::{Deserialize, Serialize}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{Token, TokenStream}; |
| |
| <span class="doccomment">/// Struct representing pre-tokenized text |
| </span><span class="attribute">#[derive(Debug, Clone, Serialize, Deserialize, Eq, PartialEq)] |
| </span><span class="kw">pub struct </span>PreTokenizedString { |
| <span class="doccomment">/// Original text |
| </span><span class="kw">pub </span>text: String, |
| <span class="doccomment">/// Tokens derived from the text |
| </span><span class="kw">pub </span>tokens: Vec<Token>, |
| } |
| |
| <span class="kw">impl </span>Ord <span class="kw">for </span>PreTokenizedString { |
| <span class="kw">fn </span>cmp(<span class="kw-2">&</span><span class="self">self</span>, other: <span class="kw-2">&</span><span class="self">Self</span>) -> Ordering { |
| <span class="self">self</span>.text.cmp(<span class="kw-2">&</span>other.text) |
| } |
| } |
| |
| <span class="kw">impl </span>PartialOrd <span class="kw">for </span>PreTokenizedString { |
| <span class="kw">fn </span>partial_cmp(<span class="kw-2">&</span><span class="self">self</span>, other: <span class="kw-2">&</span><span class="self">Self</span>) -> <span class="prelude-ty">Option</span><Ordering> { |
| <span class="prelude-val">Some</span>(<span class="self">self</span>.cmp(other)) |
| } |
| } |
| |
| <span class="doccomment">/// [`TokenStream`] implementation which wraps [`PreTokenizedString`] |
| </span><span class="kw">pub struct </span>PreTokenizedStream { |
| tokenized_string: PreTokenizedString, |
| current_token: i64, |
| } |
| |
| <span class="kw">impl </span>From<PreTokenizedString> <span class="kw">for </span>PreTokenizedStream { |
| <span class="kw">fn </span>from(s: PreTokenizedString) -> PreTokenizedStream { |
| PreTokenizedStream { |
| tokenized_string: s, |
| current_token: -<span class="number">1</span>, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>TokenStream <span class="kw">for </span>PreTokenizedStream { |
| <span class="kw">fn </span>advance(<span class="kw-2">&mut </span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.current_token += <span class="number">1</span>; |
| <span class="self">self</span>.current_token < <span class="self">self</span>.tokenized_string.tokens.len() <span class="kw">as </span>i64 |
| } |
| |
| <span class="kw">fn </span>token(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>Token { |
| <span class="macro">assert!</span>( |
| <span class="self">self</span>.current_token >= <span class="number">0</span>, |
| <span class="string">"TokenStream not initialized. You should call advance() at least once." |
| </span>); |
| <span class="kw-2">&</span><span class="self">self</span>.tokenized_string.tokens[<span class="self">self</span>.current_token <span class="kw">as </span>usize] |
| } |
| |
| <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="macro">assert!</span>( |
| <span class="self">self</span>.current_token >= <span class="number">0</span>, |
| <span class="string">"TokenStream not initialized. You should call advance() at least once." |
| </span>); |
| <span class="kw-2">&mut </span><span class="self">self</span>.tokenized_string.tokens[<span class="self">self</span>.current_token <span class="kw">as </span>usize] |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::Token; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_tokenized_stream() { |
| <span class="kw">let </span>tok_text = PreTokenizedString { |
| text: String::from(<span class="string">"A a"</span>), |
| tokens: <span class="macro">vec!</span>[ |
| Token { |
| offset_from: <span class="number">0</span>, |
| offset_to: <span class="number">1</span>, |
| position: <span class="number">0</span>, |
| text: String::from(<span class="string">"A"</span>), |
| position_length: <span class="number">1</span>, |
| }, |
| Token { |
| offset_from: <span class="number">2</span>, |
| offset_to: <span class="number">3</span>, |
| position: <span class="number">1</span>, |
| text: String::from(<span class="string">"a"</span>), |
| position_length: <span class="number">1</span>, |
| }, |
| ], |
| }; |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>token_stream = PreTokenizedStream::from(tok_text.clone()); |
| |
| <span class="kw">for </span>expected_token <span class="kw">in </span>tok_text.tokens { |
| <span class="macro">assert!</span>(token_stream.advance()); |
| <span class="macro">assert_eq!</span>(token_stream.token(), <span class="kw-2">&</span>expected_token); |
| } |
| <span class="macro">assert!</span>(!token_stream.advance()); |
| } |
| } |
| </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> |