blob: fff7ede11185d3f6d6cc2d494701fec8c77f2693 [file] [log] [blame]
<!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/simple_tokenizer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>simple_tokenizer.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>
</pre><pre class="rust"><code><span class="kw">use </span>std::str::CharIndices;
<span class="kw">use super</span>::{BoxTokenStream, Token, TokenStream, Tokenizer};
<span class="doccomment">/// Tokenize the text by splitting on whitespaces and punctuation.
</span><span class="attribute">#[derive(Clone)]
</span><span class="kw">pub struct </span>SimpleTokenizer;
<span class="kw">pub struct </span>SimpleTokenStream&lt;<span class="lifetime">&#39;a</span>&gt; {
text: <span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>str,
chars: CharIndices&lt;<span class="lifetime">&#39;a</span>&gt;,
token: Token,
}
<span class="kw">impl </span>Tokenizer <span class="kw">for </span>SimpleTokenizer {
<span class="kw">fn </span>token_stream&lt;<span class="lifetime">&#39;a</span>&gt;(<span class="kw-2">&amp;</span><span class="self">self</span>, text: <span class="kw-2">&amp;</span><span class="lifetime">&#39;a </span>str) -&gt; BoxTokenStream&lt;<span class="lifetime">&#39;a</span>&gt; {
BoxTokenStream::from(SimpleTokenStream {
text,
chars: text.char_indices(),
token: Token::default(),
})
}
}
<span class="kw">impl</span>&lt;<span class="lifetime">&#39;a</span>&gt; SimpleTokenStream&lt;<span class="lifetime">&#39;a</span>&gt; {
<span class="comment">// search for the end of the current token.
</span><span class="kw">fn </span>search_token_end(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; usize {
(<span class="kw-2">&amp;mut </span><span class="self">self</span>.chars)
.filter(|<span class="kw-2">&amp;</span>(<span class="kw">_</span>, <span class="kw-2">ref </span>c)| !c.is_alphanumeric())
.map(|(offset, <span class="kw">_</span>)| offset)
.next()
.unwrap_or(<span class="self">self</span>.text.len())
}
}
<span class="kw">impl</span>&lt;<span class="lifetime">&#39;a</span>&gt; TokenStream <span class="kw">for </span>SimpleTokenStream&lt;<span class="lifetime">&#39;a</span>&gt; {
<span class="kw">fn </span>advance(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; bool {
<span class="self">self</span>.token.text.clear();
<span class="self">self</span>.token.position = <span class="self">self</span>.token.position.wrapping_add(<span class="number">1</span>);
<span class="kw">while let </span><span class="prelude-val">Some</span>((offset_from, c)) = <span class="self">self</span>.chars.next() {
<span class="kw">if </span>c.is_alphanumeric() {
<span class="kw">let </span>offset_to = <span class="self">self</span>.search_token_end();
<span class="self">self</span>.token.offset_from = offset_from;
<span class="self">self</span>.token.offset_to = offset_to;
<span class="self">self</span>.token.text.push_str(<span class="kw-2">&amp;</span><span class="self">self</span>.text[offset_from..offset_to]);
<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">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>Token {
<span class="kw-2">&amp;</span><span class="self">self</span>.token
}
<span class="kw">fn </span>token_mut(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;mut </span>Token {
<span class="kw-2">&amp;mut </span><span class="self">self</span>.token
}
}
<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, TextAnalyzer, Token};
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_simple_tokenizer() {
<span class="kw">let </span>tokens = token_stream_helper(<span class="string">&quot;Hello, happy tax payer!&quot;</span>);
<span class="macro">assert_eq!</span>(tokens.len(), <span class="number">4</span>);
assert_token(<span class="kw-2">&amp;</span>tokens[<span class="number">0</span>], <span class="number">0</span>, <span class="string">&quot;Hello&quot;</span>, <span class="number">0</span>, <span class="number">5</span>);
assert_token(<span class="kw-2">&amp;</span>tokens[<span class="number">1</span>], <span class="number">1</span>, <span class="string">&quot;happy&quot;</span>, <span class="number">7</span>, <span class="number">12</span>);
assert_token(<span class="kw-2">&amp;</span>tokens[<span class="number">2</span>], <span class="number">2</span>, <span class="string">&quot;tax&quot;</span>, <span class="number">13</span>, <span class="number">16</span>);
assert_token(<span class="kw-2">&amp;</span>tokens[<span class="number">3</span>], <span class="number">3</span>, <span class="string">&quot;payer&quot;</span>, <span class="number">17</span>, <span class="number">22</span>);
}
<span class="kw">fn </span>token_stream_helper(text: <span class="kw-2">&amp;</span>str) -&gt; Vec&lt;Token&gt; {
<span class="kw">let </span>a = TextAnalyzer::from(SimpleTokenizer);
<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&lt;Token&gt; = <span class="macro">vec!</span>[];
<span class="kw">let </span><span class="kw-2">mut </span>add_token = |token: <span class="kw-2">&amp;</span>Token| {
tokens.push(token.clone());
};
token_stream.process(<span class="kw-2">&amp;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>