| <!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/registry/src/github.com-1ecc6299db9ec823/tantivy-fst-0.4.0/src/regex/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_fst/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy_fst/index.html"><img class="rust-logo" src="../../../rust-logo.svg" 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> |
| </pre><pre class="rust"><code><span class="kw">use </span><span class="kw">crate</span>::Automaton; |
| <span class="kw">use </span>regex_syntax; |
| <span class="kw">use </span>std::fmt; |
| |
| <span class="kw">mod </span>compile; |
| <span class="kw">mod </span>dfa; |
| <span class="kw">mod </span>error; |
| <span class="kw">mod </span>sparse; |
| |
| <span class="kw">pub use </span><span class="self">self</span>::error::Error; |
| |
| <span class="doccomment">/// A regular expression for searching FSTs with Unicode support. |
| /// |
| /// Regular expressions are compiled down to a deterministic finite automaton |
| /// that can efficiently search any finite state transducer. Notably, most |
| /// regular expressions only need to explore a small portion of a finite state |
| /// transducer without loading all of it into memory. |
| /// |
| /// # Syntax |
| /// |
| /// `Regex` supports fully featured regular expressions. Namely, it supports |
| /// all of the same constructs as the standard `regex` crate except for the |
| /// following things: |
| /// |
| /// 1. Lazy quantifiers, since a regular expression automaton only reports |
| /// whether a key matches at all, and not its location. Namely, lazy |
| /// quantifiers such as `+?` only modify the location of a match, but never |
| /// change a non-match into a match or a match into a non-match. |
| /// 2. Word boundaries (i.e., `\b`). Because such things are hard to do in |
| /// a deterministic finite automaton, but not impossible. As such, these |
| /// may be allowed some day. |
| /// 3. Other zero width assertions like `^` and `$`. These are easier to |
| /// support than word boundaries, but are still tricky and usually aren't |
| /// as useful when searching dictionaries. |
| /// |
| /// Otherwise, the [full syntax of the `regex` |
| /// crate](http://doc.rust-lang.org/regex/regex/index.html#syntax) |
| /// is supported. This includes all Unicode support and relevant flags. |
| /// (The `U` and `m` flags are no-ops because of (1) and (3) above, |
| /// respectively.) |
| /// |
| /// # Matching semantics |
| /// |
| /// A regular expression matches a key in a finite state transducer if and only |
| /// if it matches from the start of a key all the way to end. Stated |
| /// differently, every regular expression `(re)` is matched as if it were |
| /// `^(re)$`. This means that if you want to do a substring match, then you |
| /// must use `.*substring.*`. |
| /// |
| /// **Caution**: Starting a regular expression with `.*` means that it could |
| /// potentially match *any* key in a finite state transducer. This implies that |
| /// all keys could be visited, which could be slow. It is possible that this |
| /// crate will grow facilities for detecting regular expressions that will |
| /// scan a large portion of a transducer and optionally disallow them. |
| /// |
| </span><span class="kw">pub struct </span>Regex { |
| original: String, |
| dfa: dfa::Dfa, |
| } |
| |
| <span class="attribute">#[derive(Eq, PartialEq)] |
| </span><span class="kw">pub enum </span>Inst { |
| Match, |
| Jump(usize), |
| Split(usize, usize), |
| Range(u8, u8), |
| } |
| |
| <span class="kw">impl </span>Regex { |
| <span class="doccomment">/// Create a new regular expression query. |
| /// |
| /// The query finds all terms matching the regular expression. |
| /// |
| /// If the regular expression is malformed or if it results in an automaton |
| /// that is too big, then an error is returned. |
| /// |
| /// A `Regex` value satisfies the `Automaton` trait, which means it can be |
| /// used with the `search` method of any finite state transducer. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>new(re: <span class="kw-2">&</span>str) -> <span class="prelude-ty">Result</span><Regex, Error> { |
| Regex::with_size_limit(<span class="number">10 </span>* (<span class="number">1 </span><< <span class="number">20</span>), re) |
| } |
| |
| <span class="kw">fn </span>with_size_limit(size: usize, re: <span class="kw-2">&</span>str) -> <span class="prelude-ty">Result</span><Regex, Error> { |
| <span class="kw">let </span>hir = regex_syntax::Parser::new().parse(re)<span class="question-mark">?</span>; |
| <span class="kw">let </span>insts = <span class="self">self</span>::compile::Compiler::new(size).compile(<span class="kw-2">&</span>hir)<span class="question-mark">?</span>; |
| <span class="kw">let </span>dfa = <span class="self">self</span>::dfa::DfaBuilder::new(insts).build()<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(Regex { |
| original: re.to_owned(), |
| dfa, |
| }) |
| } |
| } |
| |
| <span class="kw">impl </span>Automaton <span class="kw">for </span>Regex { |
| <span class="kw">type </span>State = <span class="prelude-ty">Option</span><usize>; |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>start(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="prelude-val">Some</span>(<span class="number">0</span>) |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>is_match(<span class="kw-2">&</span><span class="self">self</span>, state: <span class="kw-2">&</span><span class="prelude-ty">Option</span><usize>) -> bool { |
| state.map(|state| <span class="self">self</span>.dfa.is_match(state)).unwrap_or(<span class="bool-val">false</span>) |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>can_match(<span class="kw-2">&</span><span class="self">self</span>, state: <span class="kw-2">&</span><span class="prelude-ty">Option</span><usize>) -> bool { |
| state.is_some() |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>accept(<span class="kw-2">&</span><span class="self">self</span>, state: <span class="kw-2">&</span><span class="prelude-ty">Option</span><usize>, byte: u8) -> <span class="prelude-ty">Option</span><usize> { |
| state.and_then(|state| <span class="self">self</span>.dfa.accept(state, byte)) |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Regex { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter) -> fmt::Result { |
| <span class="macro">writeln!</span>(f, <span class="string">"Regex({:?})"</span>, <span class="self">self</span>.original)<span class="question-mark">?</span>; |
| <span class="self">self</span>.dfa.fmt(f) |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Inst { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter) -> fmt::Result { |
| <span class="kw">use </span><span class="self">self</span>::Inst::<span class="kw-2">*</span>; |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Match => <span class="macro">write!</span>(f, <span class="string">"Match"</span>), |
| Jump(ip) => <span class="macro">write!</span>(f, <span class="string">"JUMP {}"</span>, ip), |
| Split(ip1, ip2) => <span class="macro">write!</span>(f, <span class="string">"SPLIT {}, {}"</span>, ip1, ip2), |
| Range(s, e) => <span class="macro">write!</span>(f, <span class="string">"RANGE {:X}-{:X}"</span>, s, e), |
| } |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy_fst" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |