| <!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/regex-syntax-0.7.2/src/parser.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>parser.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="../../regex_syntax/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="../../regex_syntax/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> |
| <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> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| </pre><pre class="rust"><code><span class="kw">use crate</span>::{ast, hir, Error}; |
| |
| <span class="doccomment">/// A convenience routine for parsing a regex using default options. |
| /// |
| /// This is equivalent to `Parser::new().parse(pattern)`. |
| /// |
| /// If you need to set non-default options, then use a [`ParserBuilder`]. |
| /// |
| /// This routine returns an [`Hir`](hir::Hir) value. Namely, it automatically |
| /// parses the pattern as an [`Ast`](ast::Ast) and then invokes the translator |
| /// to convert the `Ast` into an `Hir`. If you need access to the `Ast`, then |
| /// you should use a [`ast::parse::Parser`]. |
| </span><span class="kw">pub fn </span>parse(pattern: <span class="kw-2">&</span>str) -> <span class="prelude-ty">Result</span><hir::Hir, Error> { |
| Parser::new().parse(pattern) |
| } |
| |
| <span class="doccomment">/// A builder for a regular expression parser. |
| /// |
| /// This builder permits modifying configuration options for the parser. |
| /// |
| /// This type combines the builder options for both the [AST |
| /// `ParserBuilder`](ast::parse::ParserBuilder) and the [HIR |
| /// `TranslatorBuilder`](hir::translate::TranslatorBuilder). |
| </span><span class="attribute">#[derive(Clone, Debug, Default)] |
| </span><span class="kw">pub struct </span>ParserBuilder { |
| ast: ast::parse::ParserBuilder, |
| hir: hir::translate::TranslatorBuilder, |
| } |
| |
| <span class="kw">impl </span>ParserBuilder { |
| <span class="doccomment">/// Create a new parser builder with a default configuration. |
| </span><span class="kw">pub fn </span>new() -> ParserBuilder { |
| ParserBuilder::default() |
| } |
| |
| <span class="doccomment">/// Build a parser from this configuration with the given pattern. |
| </span><span class="kw">pub fn </span>build(<span class="kw-2">&</span><span class="self">self</span>) -> Parser { |
| Parser { ast: <span class="self">self</span>.ast.build(), hir: <span class="self">self</span>.hir.build() } |
| } |
| |
| <span class="doccomment">/// Set the nesting limit for this parser. |
| /// |
| /// The nesting limit controls how deep the abstract syntax tree is allowed |
| /// to be. If the AST exceeds the given limit (e.g., with too many nested |
| /// groups), then an error is returned by the parser. |
| /// |
| /// The purpose of this limit is to act as a heuristic to prevent stack |
| /// overflow for consumers that do structural induction on an `Ast` using |
| /// explicit recursion. While this crate never does this (instead using |
| /// constant stack space and moving the call stack to the heap), other |
| /// crates may. |
| /// |
| /// This limit is not checked until the entire Ast is parsed. Therefore, |
| /// if callers want to put a limit on the amount of heap space used, then |
| /// they should impose a limit on the length, in bytes, of the concrete |
| /// pattern string. In particular, this is viable since this parser |
| /// implementation will limit itself to heap space proportional to the |
| /// length of the pattern string. |
| /// |
| /// Note that a nest limit of `0` will return a nest limit error for most |
| /// patterns but not all. For example, a nest limit of `0` permits `a` but |
| /// not `ab`, since `ab` requires a concatenation, which results in a nest |
| /// depth of `1`. In general, a nest limit is not something that manifests |
| /// in an obvious way in the concrete syntax, therefore, it should not be |
| /// used in a granular way. |
| </span><span class="kw">pub fn </span>nest_limit(<span class="kw-2">&mut </span><span class="self">self</span>, limit: u32) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.ast.nest_limit(limit); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Whether to support octal syntax or not. |
| /// |
| /// Octal syntax is a little-known way of uttering Unicode codepoints in |
| /// a regular expression. For example, `a`, `\x61`, `\u0061` and |
| /// `\141` are all equivalent regular expressions, where the last example |
| /// shows octal syntax. |
| /// |
| /// While supporting octal syntax isn't in and of itself a problem, it does |
| /// make good error messages harder. That is, in PCRE based regex engines, |
| /// syntax like `\0` invokes a backreference, which is explicitly |
| /// unsupported in Rust's regex engine. However, many users expect it to |
| /// be supported. Therefore, when octal support is disabled, the error |
| /// message will explicitly mention that backreferences aren't supported. |
| /// |
| /// Octal syntax is disabled by default. |
| </span><span class="kw">pub fn </span>octal(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.ast.octal(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// When disabled, translation will permit the construction of a regular |
| /// expression that may match invalid UTF-8. |
| /// |
| /// When enabled (the default), the translator is guaranteed to produce an |
| /// expression that, for non-empty matches, will only ever produce spans |
| /// that are entirely valid UTF-8 (otherwise, the translator will return an |
| /// error). |
| /// |
| /// Perhaps surprisingly, when UTF-8 is enabled, an empty regex or even |
| /// a negated ASCII word boundary (uttered as `(?-u:\B)` in the concrete |
| /// syntax) will be allowed even though they can produce matches that split |
| /// a UTF-8 encoded codepoint. This only applies to zero-width or "empty" |
| /// matches, and it is expected that the regex engine itself must handle |
| /// these cases if necessary (perhaps by suppressing any zero-width matches |
| /// that split a codepoint). |
| </span><span class="kw">pub fn </span>utf8(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.utf8(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable verbose mode in the regular expression. |
| /// |
| /// When enabled, verbose mode permits insignificant whitespace in many |
| /// places in the regular expression, as well as comments. Comments are |
| /// started using `#` and continue until the end of the line. |
| /// |
| /// By default, this is disabled. It may be selectively enabled in the |
| /// regular expression by using the `x` flag regardless of this setting. |
| </span><span class="kw">pub fn </span>ignore_whitespace(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.ast.ignore_whitespace(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the case insensitive flag by default. |
| /// |
| /// By default this is disabled. It may alternatively be selectively |
| /// enabled in the regular expression itself via the `i` flag. |
| </span><span class="kw">pub fn </span>case_insensitive(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.case_insensitive(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the multi-line matching flag by default. |
| /// |
| /// By default this is disabled. It may alternatively be selectively |
| /// enabled in the regular expression itself via the `m` flag. |
| </span><span class="kw">pub fn </span>multi_line(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.multi_line(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the "dot matches any character" flag by default. |
| /// |
| /// By default this is disabled. It may alternatively be selectively |
| /// enabled in the regular expression itself via the `s` flag. |
| </span><span class="kw">pub fn </span>dot_matches_new_line(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.dot_matches_new_line(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the CRLF mode flag by default. |
| /// |
| /// By default this is disabled. It may alternatively be selectively |
| /// enabled in the regular expression itself via the `R` flag. |
| /// |
| /// When CRLF mode is enabled, the following happens: |
| /// |
| /// * Unless `dot_matches_new_line` is enabled, `.` will match any character |
| /// except for `\r` and `\n`. |
| /// * When `multi_line` mode is enabled, `^` and `$` will treat `\r\n`, |
| /// `\r` and `\n` as line terminators. And in particular, neither will |
| /// match between a `\r` and a `\n`. |
| </span><span class="kw">pub fn </span>crlf(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.crlf(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the "swap greed" flag by default. |
| /// |
| /// By default this is disabled. It may alternatively be selectively |
| /// enabled in the regular expression itself via the `U` flag. |
| </span><span class="kw">pub fn </span>swap_greed(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.swap_greed(yes); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Enable or disable the Unicode flag (`u`) by default. |
| /// |
| /// By default this is **enabled**. It may alternatively be selectively |
| /// disabled in the regular expression itself via the `u` flag. |
| /// |
| /// Note that unless `utf8` is disabled (it's enabled by default), a |
| /// regular expression will fail to parse if Unicode mode is disabled and a |
| /// sub-expression could possibly match invalid UTF-8. |
| </span><span class="kw">pub fn </span>unicode(<span class="kw-2">&mut </span><span class="self">self</span>, yes: bool) -> <span class="kw-2">&mut </span>ParserBuilder { |
| <span class="self">self</span>.hir.unicode(yes); |
| <span class="self">self |
| </span>} |
| } |
| |
| <span class="doccomment">/// A convenience parser for regular expressions. |
| /// |
| /// This parser takes as input a regular expression pattern string (the |
| /// "concrete syntax") and returns a high-level intermediate representation |
| /// (the HIR) suitable for most types of analysis. In particular, this parser |
| /// hides the intermediate state of producing an AST (the "abstract syntax"). |
| /// The AST is itself far more complex than the HIR, so this parser serves as a |
| /// convenience for never having to deal with it at all. |
| /// |
| /// If callers have more fine grained use cases that need an AST, then please |
| /// see the [`ast::parse`] module. |
| /// |
| /// A `Parser` can be configured in more detail via a [`ParserBuilder`]. |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>Parser { |
| ast: ast::parse::Parser, |
| hir: hir::translate::Translator, |
| } |
| |
| <span class="kw">impl </span>Parser { |
| <span class="doccomment">/// Create a new parser with a default configuration. |
| /// |
| /// The parser can be run with `parse` method. The parse method returns |
| /// a high level intermediate representation of the given regular |
| /// expression. |
| /// |
| /// To set configuration options on the parser, use [`ParserBuilder`]. |
| </span><span class="kw">pub fn </span>new() -> Parser { |
| ParserBuilder::new().build() |
| } |
| |
| <span class="doccomment">/// Parse the regular expression into a high level intermediate |
| /// representation. |
| </span><span class="kw">pub fn </span>parse(<span class="kw-2">&mut </span><span class="self">self</span>, pattern: <span class="kw-2">&</span>str) -> <span class="prelude-ty">Result</span><hir::Hir, Error> { |
| <span class="kw">let </span>ast = <span class="self">self</span>.ast.parse(pattern)<span class="question-mark">?</span>; |
| <span class="kw">let </span>hir = <span class="self">self</span>.hir.translate(pattern, <span class="kw-2">&</span>ast)<span class="question-mark">?</span>; |
| <span class="prelude-val">Ok</span>(hir) |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex_syntax" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |