diff options
| author | 2015-06-29 20:16:15 +0000 | |
|---|---|---|
| committer | 2015-06-29 20:16:15 +0000 | |
| commit | 64106c4d3d4ddba8c7bc2af75376e6d3d3d75601 (patch) | |
| tree | 8c64d6e8be006486d975a651505fbbde61365cd6 /src/regex | |
| download | irsc-gh-pages.tar.gz irsc-gh-pages.tar.xz irsc-gh-pages.zip | |
Update documentationgh-pages
Diffstat (limited to 'src/regex')
| -rw-r--r-- | src/regex/char.rs.html | 311 | ||||
| -rw-r--r-- | src/regex/input.rs.html | 325 | ||||
| -rw-r--r-- | src/regex/lib.rs.html | 959 | ||||
| -rw-r--r-- | src/regex/program.rs.html | 1057 | ||||
| -rw-r--r-- | src/regex/re.rs.html | 2393 |
5 files changed, 5045 insertions, 0 deletions
diff --git a/src/regex/char.rs.html b/src/regex/char.rs.html new file mode 100644 index 0000000..f830f03 --- /dev/null +++ b/src/regex/char.rs.html @@ -0,0 +1,311 @@ +<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/char.rs`."> + <meta name="keywords" content="rust, rustlang, rust-lang"> + + <title>char.rs.html -- source</title> + + <link rel="stylesheet" type="text/css" href="../../main.css"> + + <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico"> + +</head> +<body class="rustdoc"> + <!--[if lte IE 8]> + <div class="warning"> + This old browser is unsupported and will most likely display funky + things. + </div> + <![endif]--> + + + + <section class="sidebar"> + <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a> + + </section> + + <nav class="sub"> + <form class="search-form js-only"> + <div class="search-container"> + <input class="search-input" name="search" + autocomplete="off" + placeholder="Click or press 'S' to search, '?' for more options..." + type="search"> + </div> + </form> + </nav> + + <section id='main' class="content source"><pre class="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> +</pre><pre class='rust '> +<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span> +<span class='comment'>// file at the top-level directory of this distribution and at</span> +<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span> +<span class='comment'>//</span> +<span class='comment'>// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> +<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> +<span class='comment'>// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> +<span class='comment'>// option. This file may not be copied, modified, or distributed</span> +<span class='comment'>// except according to those terms.</span> + +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>char</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>cmp</span>::<span class='ident'>Ordering</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>fmt</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>u32</span>; + +<span class='kw'>use</span> <span class='ident'>syntax</span>; + +<span class='doccomment'>/// An inline representation of `Option<char>`.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// This eliminates the need to do case analysis on `Option<char>` to determine</span> +<span class='doccomment'>/// ordinality with other characters.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// (The `Option<char>` is not related to encoding. Instead, it is used in the</span> +<span class='doccomment'>/// matching engines to represent the beginning and ending boundaries of the</span> +<span class='doccomment'>/// search text.)</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Copy</span>, <span class='ident'>Hash</span>, <span class='ident'>PartialEq</span>, <span class='ident'>Eq</span>, <span class='ident'>PartialOrd</span>, <span class='ident'>Ord</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>Char</span>(<span class='ident'>u32</span>); + +<span class='kw'>impl</span> <span class='ident'>fmt</span>::<span class='ident'>Debug</span> <span class='kw'>for</span> <span class='ident'>Char</span> { + <span class='kw'>fn</span> <span class='ident'>fmt</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>f</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>fmt</span>::<span class='ident'>Formatter</span>) <span class='op'>-></span> <span class='ident'>fmt</span>::<span class='prelude-ty'>Result</span> { + <span class='kw'>match</span> <span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='self'>self</span>.<span class='number'>0</span>) { + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='macro'>write</span><span class='macro'>!</span>(<span class='ident'>f</span>, <span class='string'>"Empty"</span>), + <span class='prelude-val'>Some</span>(<span class='ident'>c</span>) <span class='op'>=></span> <span class='macro'>write</span><span class='macro'>!</span>(<span class='ident'>f</span>, <span class='string'>"{:?}"</span>, <span class='ident'>c</span>), + } + } +} + +<span class='kw'>impl</span> <span class='ident'>Char</span> { + <span class='doccomment'>/// Returns true iff the character is absent.</span> + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_none</span>(<span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>bool</span> { <span class='self'>self</span>.<span class='number'>0</span> <span class='op'>==</span> <span class='ident'>u32</span>::<span class='ident'>MAX</span> } + + <span class='doccomment'>/// Returns the length of the character's UTF-8 encoding.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If the character is absent, then `0` is returned.</span> + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>len_utf8</span>(<span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='self'>self</span>.<span class='number'>0</span>).<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>c</span><span class='op'>|</span> <span class='ident'>c</span>.<span class='ident'>len_utf8</span>()).<span class='ident'>unwrap_or</span>(<span class='number'>0</span>) + } + + <span class='doccomment'>/// Returns the simple case folding of this character.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If the character is absent, then absence is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>case_fold</span>(<span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>Char</span> { + <span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='self'>self</span>.<span class='number'>0</span>).<span class='ident'>map</span>(<span class='ident'>syntax</span>::<span class='ident'>simple_case_fold</span>).<span class='ident'>into</span>() + } + + <span class='doccomment'>/// Returns true iff the character is a word character.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If the character is absent, then false is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_word_char</span>(<span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='self'>self</span>.<span class='number'>0</span>).<span class='ident'>map</span>(<span class='ident'>syntax</span>::<span class='ident'>is_word_char</span>).<span class='ident'>unwrap_or</span>(<span class='boolval'>false</span>) + } + + <span class='doccomment'>/// Converts the character to a real primitive `char`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If the character is absent, then `None` is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>as_char</span>(<span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>char</span><span class='op'>></span> { + <span class='comment'>// This is only used in the `regex!` macro because it expands char</span> + <span class='comment'>// classes into `match` expressions (instead of binary search).</span> + <span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='self'>self</span>.<span class='number'>0</span>) + } +} + +<span class='kw'>impl</span> <span class='ident'>From</span><span class='op'><</span><span class='ident'>char</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>Char</span> { + <span class='kw'>fn</span> <span class='ident'>from</span>(<span class='ident'>c</span>: <span class='ident'>char</span>) <span class='op'>-></span> <span class='ident'>Char</span> { <span class='ident'>Char</span>(<span class='ident'>c</span> <span class='kw'>as</span> <span class='ident'>u32</span>) } +} + +<span class='kw'>impl</span> <span class='ident'>From</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>char</span><span class='op'>>></span> <span class='kw'>for</span> <span class='ident'>Char</span> { + <span class='kw'>fn</span> <span class='ident'>from</span>(<span class='ident'>c</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>char</span><span class='op'>></span>) <span class='op'>-></span> <span class='ident'>Char</span> { + <span class='ident'>c</span>.<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>c</span><span class='op'>|</span> <span class='ident'>c</span>.<span class='ident'>into</span>()).<span class='ident'>unwrap_or</span>(<span class='ident'>Char</span>(<span class='ident'>u32</span>::<span class='ident'>MAX</span>)) + } +} + +<span class='kw'>impl</span> <span class='ident'>PartialEq</span><span class='op'><</span><span class='ident'>char</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>Char</span> { + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>eq</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>other</span>: <span class='kw-2'>&</span><span class='ident'>char</span>) <span class='op'>-></span> <span class='ident'>bool</span> { <span class='self'>self</span>.<span class='number'>0</span> <span class='op'>==</span> <span class='op'>*</span><span class='ident'>other</span> <span class='kw'>as</span> <span class='ident'>u32</span> } +} + +<span class='kw'>impl</span> <span class='ident'>PartialEq</span><span class='op'><</span><span class='ident'>Char</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>char</span> { + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>eq</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>other</span>: <span class='kw-2'>&</span><span class='ident'>Char</span>) <span class='op'>-></span> <span class='ident'>bool</span> { <span class='op'>*</span><span class='self'>self</span> <span class='kw'>as</span> <span class='ident'>u32</span> <span class='op'>==</span> <span class='ident'>other</span>.<span class='number'>0</span> } +} + +<span class='kw'>impl</span> <span class='ident'>PartialOrd</span><span class='op'><</span><span class='ident'>char</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>Char</span> { + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>partial_cmp</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>other</span>: <span class='kw-2'>&</span><span class='ident'>char</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Ordering</span><span class='op'>></span> { + <span class='self'>self</span>.<span class='number'>0</span>.<span class='ident'>partial_cmp</span>(<span class='kw-2'>&</span>(<span class='op'>*</span><span class='ident'>other</span> <span class='kw'>as</span> <span class='ident'>u32</span>)) + } +} + +<span class='kw'>impl</span> <span class='ident'>PartialOrd</span><span class='op'><</span><span class='ident'>Char</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>char</span> { + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>partial_cmp</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>other</span>: <span class='kw-2'>&</span><span class='ident'>Char</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Ordering</span><span class='op'>></span> { + (<span class='op'>*</span><span class='self'>self</span> <span class='kw'>as</span> <span class='ident'>u32</span>).<span class='ident'>partial_cmp</span>(<span class='kw-2'>&</span><span class='ident'>other</span>.<span class='number'>0</span>) + } +} +</pre> +</section> + <section id='search' class="content hidden"></section> + + <section class="footer"></section> + + <div id="help" class="hidden"> + <div class="shortcuts"> + <h1>Keyboard shortcuts</h1> + <dl> + <dt>?</dt> + <dd>Show this help dialog</dd> + <dt>S</dt> + <dd>Focus the search field</dd> + <dt>⇤</dt> + <dd>Move up in search results</dd> + <dt>⇥</dt> + <dd>Move down in search results</dd> + <dt>⏎</dt> + <dd>Go to active search result</dd> + </dl> + </div> + <div class="infos"> + <h1>Search tricks</h1> + <p> + Prefix searches with a type followed by a colon (e.g. + <code>fn:</code>) to restrict the search to a given type. + </p> + <p> + Accepted types are: <code>fn</code>, <code>mod</code>, + <code>struct</code>, <code>enum</code>, + <code>trait</code>, <code>typedef</code> (or + <code>tdef</code>). + </p> + <p> + Search functions by type signature (e.g. + <code>vec -> usize</code>) + </p> + </div> + </div> + + + + <script> + window.rootPath = "../../"; + window.currentCrate = "regex"; + window.playgroundUrl = ""; + </script> + <script src="../../jquery.js"></script> + <script src="../../main.js"></script> + + <script async src="../../search-index.js"></script> +</body> +</html>
\ No newline at end of file diff --git a/src/regex/input.rs.html b/src/regex/input.rs.html new file mode 100644 index 0000000..dfe5571 --- /dev/null +++ b/src/regex/input.rs.html @@ -0,0 +1,325 @@ +<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/input.rs`."> + <meta name="keywords" content="rust, rustlang, rust-lang"> + + <title>input.rs.html -- source</title> + + <link rel="stylesheet" type="text/css" href="../../main.css"> + + <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico"> + +</head> +<body class="rustdoc"> + <!--[if lte IE 8]> + <div class="warning"> + This old browser is unsupported and will most likely display funky + things. + </div> + <![endif]--> + + + + <section class="sidebar"> + <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a> + + </section> + + <nav class="sub"> + <form class="search-form js-only"> + <div class="search-container"> + <input class="search-input" name="search" + autocomplete="off" + placeholder="Click or press 'S' to search, '?' for more options..." + type="search"> + </div> + </form> + </nav> + + <section id='main' class="content source"><pre class="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> +</pre><pre class='rust '> +<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span> +<span class='comment'>// file at the top-level directory of this distribution and at</span> +<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span> +<span class='comment'>//</span> +<span class='comment'>// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> +<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> +<span class='comment'>// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> +<span class='comment'>// option. This file may not be copied, modified, or distributed</span> +<span class='comment'>// except according to those terms.</span> + +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>ops</span>; + +<span class='kw'>use</span> <span class='ident'>char</span>::<span class='ident'>Char</span>; +<span class='kw'>use</span> <span class='ident'>prefix</span>::<span class='ident'>Prefix</span>; + +<span class='doccomment'>/// Represents a location in the input.</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Copy</span>, <span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>InputAt</span> { + <span class='ident'>pos</span>: <span class='ident'>usize</span>, + <span class='ident'>c</span>: <span class='ident'>Char</span>, + <span class='ident'>len</span>: <span class='ident'>usize</span>, +} + +<span class='kw'>impl</span> <span class='ident'>InputAt</span> { + <span class='doccomment'>/// Returns true iff this position is at the beginning of the input.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_beginning</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='self'>self</span>.<span class='ident'>pos</span> <span class='op'>==</span> <span class='number'>0</span> + } + + <span class='doccomment'>/// Returns the character at this position.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If this position is just before or after the input, then an absent</span> + <span class='doccomment'>/// character is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>char</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>Char</span> { + <span class='self'>self</span>.<span class='ident'>c</span> + } + + <span class='doccomment'>/// Returns the UTF-8 width of the character at this position.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>len</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='self'>self</span>.<span class='ident'>len</span> + } + + <span class='doccomment'>/// Returns the byte offset of this position.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>pos</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='self'>self</span>.<span class='ident'>pos</span> + } + + <span class='doccomment'>/// Returns the byte offset of the next position in the input.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>next_pos</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='self'>self</span>.<span class='ident'>pos</span> <span class='op'>+</span> <span class='self'>self</span>.<span class='ident'>len</span> + } +} + +<span class='doccomment'>/// An abstraction over input used in the matching engines.</span> +<span class='kw'>pub</span> <span class='kw'>trait</span> <span class='ident'>Input</span> { + <span class='doccomment'>/// Return an encoding of the position at byte offset `i`.</span> + <span class='kw'>fn</span> <span class='ident'>at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>InputAt</span>; + <span class='doccomment'>/// Return an encoding of the char position just prior to byte offset `i`.</span> + <span class='kw'>fn</span> <span class='ident'>previous_at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>InputAt</span>; + <span class='doccomment'>/// Scan the input for a matching prefix.</span> + <span class='kw'>fn</span> <span class='ident'>prefix_at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>prefixes</span>: <span class='kw-2'>&</span><span class='ident'>Prefix</span>, <span class='ident'>at</span>: <span class='ident'>InputAt</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>InputAt</span><span class='op'>></span>; +} + +<span class='doccomment'>/// An input reader over characters.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// (This is the only implementation of `Input` at the moment.)</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>CharInput</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>); + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>CharInput</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='doccomment'>/// Return a new character input reader for the given string.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>new</span>(<span class='ident'>s</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>CharInput</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>CharInput</span>(<span class='ident'>s</span>) + } +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>ops</span>::<span class='ident'>Deref</span> <span class='kw'>for</span> <span class='ident'>CharInput</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Target</span> <span class='op'>=</span> <span class='ident'>str</span>; + + <span class='kw'>fn</span> <span class='ident'>deref</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='kw-2'>&</span><span class='ident'>str</span> { + <span class='self'>self</span>.<span class='number'>0</span> + } +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Input</span> <span class='kw'>for</span> <span class='ident'>CharInput</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='comment'>// This `inline(always)` increases throughput by almost 25% on the `hard`</span> + <span class='comment'>// benchmarks over a normal `inline` annotation.</span> + <span class='comment'>//</span> + <span class='comment'>// I'm not sure why `#[inline]` isn't enough to convince LLVM, but it is</span> + <span class='comment'>// used *a lot* in the guts of the matching engines.</span> + <span class='attribute'>#[<span class='ident'>inline</span>(<span class='ident'>always</span>)]</span> + <span class='kw'>fn</span> <span class='ident'>at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>InputAt</span> { + <span class='kw'>let</span> <span class='ident'>c</span> <span class='op'>=</span> <span class='self'>self</span>[<span class='ident'>i</span>..].<span class='ident'>chars</span>().<span class='ident'>next</span>().<span class='ident'>into</span>(); + <span class='ident'>InputAt</span> { + <span class='ident'>pos</span>: <span class='ident'>i</span>, + <span class='ident'>c</span>: <span class='ident'>c</span>, + <span class='ident'>len</span>: <span class='ident'>c</span>.<span class='ident'>len_utf8</span>(), + } + } + + <span class='kw'>fn</span> <span class='ident'>previous_at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>InputAt</span> { + <span class='kw'>let</span> <span class='ident'>c</span>: <span class='ident'>Char</span> <span class='op'>=</span> <span class='self'>self</span>[..<span class='ident'>i</span>].<span class='ident'>chars</span>().<span class='ident'>rev</span>().<span class='ident'>next</span>().<span class='ident'>into</span>(); + <span class='kw'>let</span> <span class='ident'>len</span> <span class='op'>=</span> <span class='ident'>c</span>.<span class='ident'>len_utf8</span>(); + <span class='ident'>InputAt</span> { + <span class='ident'>pos</span>: <span class='ident'>i</span> <span class='op'>-</span> <span class='ident'>len</span>, + <span class='ident'>c</span>: <span class='ident'>c</span>, + <span class='ident'>len</span>: <span class='ident'>len</span>, + } + } + + <span class='kw'>fn</span> <span class='ident'>prefix_at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>prefixes</span>: <span class='kw-2'>&</span><span class='ident'>Prefix</span>, <span class='ident'>at</span>: <span class='ident'>InputAt</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>InputAt</span><span class='op'>></span> { + <span class='ident'>prefixes</span>.<span class='ident'>find</span>(<span class='kw-2'>&</span><span class='self'>self</span>[<span class='ident'>at</span>.<span class='ident'>pos</span>()..]).<span class='ident'>map</span>(<span class='op'>|</span>(<span class='ident'>s</span>, _)<span class='op'>|</span> <span class='self'>self</span>.<span class='ident'>at</span>(<span class='ident'>at</span>.<span class='ident'>pos</span>() <span class='op'>+</span> <span class='ident'>s</span>)) + } +} +</pre> +</section> + <section id='search' class="content hidden"></section> + + <section class="footer"></section> + + <div id="help" class="hidden"> + <div class="shortcuts"> + <h1>Keyboard shortcuts</h1> + <dl> + <dt>?</dt> + <dd>Show this help dialog</dd> + <dt>S</dt> + <dd>Focus the search field</dd> + <dt>⇤</dt> + <dd>Move up in search results</dd> + <dt>⇥</dt> + <dd>Move down in search results</dd> + <dt>⏎</dt> + <dd>Go to active search result</dd> + </dl> + </div> + <div class="infos"> + <h1>Search tricks</h1> + <p> + Prefix searches with a type followed by a colon (e.g. + <code>fn:</code>) to restrict the search to a given type. + </p> + <p> + Accepted types are: <code>fn</code>, <code>mod</code>, + <code>struct</code>, <code>enum</code>, + <code>trait</code>, <code>typedef</code> (or + <code>tdef</code>). + </p> + <p> + Search functions by type signature (e.g. + <code>vec -> usize</code>) + </p> + </div> + </div> + + + + <script> + window.rootPath = "../../"; + window.currentCrate = "regex"; + window.playgroundUrl = ""; + </script> + <script src="../../jquery.js"></script> + <script src="../../main.js"></script> + + <script async src="../../search-index.js"></script> +</body> +</html>
\ No newline at end of file diff --git a/src/regex/lib.rs.html b/src/regex/lib.rs.html new file mode 100644 index 0000000..8331db1 --- /dev/null +++ b/src/regex/lib.rs.html @@ -0,0 +1,959 @@ +<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/lib.rs`."> + <meta name="keywords" content="rust, rustlang, rust-lang"> + + <title>lib.rs.html -- source</title> + + <link rel="stylesheet" type="text/css" href="../../main.css"> + + <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico"> + +</head> +<body class="rustdoc"> + <!--[if lte IE 8]> + <div class="warning"> + This old browser is unsupported and will most likely display funky + things. + </div> + <![endif]--> + + + + <section class="sidebar"> + <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a> + + </section> + + <nav class="sub"> + <form class="search-form js-only"> + <div class="search-container"> + <input class="search-input" name="search" + autocomplete="off" + placeholder="Click or press 'S' to search, '?' for more options..." + type="search"> + </div> + </form> + </nav> + + <section id='main' class="content source"><pre class="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> +<span id="230">230</span> +<span id="231">231</span> +<span id="232">232</span> +<span id="233">233</span> +<span id="234">234</span> +<span id="235">235</span> +<span id="236">236</span> +<span id="237">237</span> +<span id="238">238</span> +<span id="239">239</span> +<span id="240">240</span> +<span id="241">241</span> +<span id="242">242</span> +<span id="243">243</span> +<span id="244">244</span> +<span id="245">245</span> +<span id="246">246</span> +<span id="247">247</span> +<span id="248">248</span> +<span id="249">249</span> +<span id="250">250</span> +<span id="251">251</span> +<span id="252">252</span> +<span id="253">253</span> +<span id="254">254</span> +<span id="255">255</span> +<span id="256">256</span> +<span id="257">257</span> +<span id="258">258</span> +<span id="259">259</span> +<span id="260">260</span> +<span id="261">261</span> +<span id="262">262</span> +<span id="263">263</span> +<span id="264">264</span> +<span id="265">265</span> +<span id="266">266</span> +<span id="267">267</span> +<span id="268">268</span> +<span id="269">269</span> +<span id="270">270</span> +<span id="271">271</span> +<span id="272">272</span> +<span id="273">273</span> +<span id="274">274</span> +<span id="275">275</span> +<span id="276">276</span> +<span id="277">277</span> +<span id="278">278</span> +<span id="279">279</span> +<span id="280">280</span> +<span id="281">281</span> +<span id="282">282</span> +<span id="283">283</span> +<span id="284">284</span> +<span id="285">285</span> +<span id="286">286</span> +<span id="287">287</span> +<span id="288">288</span> +<span id="289">289</span> +<span id="290">290</span> +<span id="291">291</span> +<span id="292">292</span> +<span id="293">293</span> +<span id="294">294</span> +<span id="295">295</span> +<span id="296">296</span> +<span id="297">297</span> +<span id="298">298</span> +<span id="299">299</span> +<span id="300">300</span> +<span id="301">301</span> +<span id="302">302</span> +<span id="303">303</span> +<span id="304">304</span> +<span id="305">305</span> +<span id="306">306</span> +<span id="307">307</span> +<span id="308">308</span> +<span id="309">309</span> +<span id="310">310</span> +<span id="311">311</span> +<span id="312">312</span> +<span id="313">313</span> +<span id="314">314</span> +<span id="315">315</span> +<span id="316">316</span> +<span id="317">317</span> +<span id="318">318</span> +<span id="319">319</span> +<span id="320">320</span> +<span id="321">321</span> +<span id="322">322</span> +<span id="323">323</span> +<span id="324">324</span> +<span id="325">325</span> +<span id="326">326</span> +<span id="327">327</span> +<span id="328">328</span> +<span id="329">329</span> +<span id="330">330</span> +<span id="331">331</span> +<span id="332">332</span> +<span id="333">333</span> +<span id="334">334</span> +<span id="335">335</span> +<span id="336">336</span> +<span id="337">337</span> +<span id="338">338</span> +<span id="339">339</span> +<span id="340">340</span> +<span id="341">341</span> +<span id="342">342</span> +<span id="343">343</span> +<span id="344">344</span> +<span id="345">345</span> +<span id="346">346</span> +<span id="347">347</span> +<span id="348">348</span> +<span id="349">349</span> +<span id="350">350</span> +<span id="351">351</span> +<span id="352">352</span> +<span id="353">353</span> +<span id="354">354</span> +<span id="355">355</span> +<span id="356">356</span> +<span id="357">357</span> +<span id="358">358</span> +<span id="359">359</span> +<span id="360">360</span> +<span id="361">361</span> +<span id="362">362</span> +<span id="363">363</span> +<span id="364">364</span> +<span id="365">365</span> +<span id="366">366</span> +<span id="367">367</span> +<span id="368">368</span> +<span id="369">369</span> +<span id="370">370</span> +<span id="371">371</span> +<span id="372">372</span> +<span id="373">373</span> +<span id="374">374</span> +<span id="375">375</span> +<span id="376">376</span> +<span id="377">377</span> +<span id="378">378</span> +<span id="379">379</span> +<span id="380">380</span> +<span id="381">381</span> +<span id="382">382</span> +<span id="383">383</span> +<span id="384">384</span> +<span id="385">385</span> +<span id="386">386</span> +<span id="387">387</span> +<span id="388">388</span> +<span id="389">389</span> +<span id="390">390</span> +<span id="391">391</span> +<span id="392">392</span> +<span id="393">393</span> +<span id="394">394</span> +<span id="395">395</span> +<span id="396">396</span> +<span id="397">397</span> +<span id="398">398</span> +<span id="399">399</span> +<span id="400">400</span> +<span id="401">401</span> +<span id="402">402</span> +<span id="403">403</span> +<span id="404">404</span> +<span id="405">405</span> +<span id="406">406</span> +<span id="407">407</span> +<span id="408">408</span> +<span id="409">409</span> +<span id="410">410</span> +<span id="411">411</span> +<span id="412">412</span> +<span id="413">413</span> +<span id="414">414</span> +<span id="415">415</span> +<span id="416">416</span> +<span id="417">417</span> +<span id="418">418</span> +<span id="419">419</span> +<span id="420">420</span> +<span id="421">421</span> +<span id="422">422</span> +<span id="423">423</span> +<span id="424">424</span> +<span id="425">425</span> +<span id="426">426</span> +<span id="427">427</span> +<span id="428">428</span> +<span id="429">429</span> +<span id="430">430</span> +<span id="431">431</span> +</pre><pre class='rust '> +<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span> +<span class='comment'>// file at the top-level directory of this distribution and at</span> +<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span> +<span class='comment'>//</span> +<span class='comment'>// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> +<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> +<span class='comment'>// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> +<span class='comment'>// option. This file may not be copied, modified, or distributed</span> +<span class='comment'>// except according to those terms.</span> + +<span class='doccomment'>//! This crate provides a native implementation of regular expressions that is</span> +<span class='doccomment'>//! heavily based on RE2 both in syntax and in implementation. Notably,</span> +<span class='doccomment'>//! backreferences and arbitrary lookahead/lookbehind assertions are not</span> +<span class='doccomment'>//! provided. In return, regular expression searching provided by this package</span> +<span class='doccomment'>//! has excellent worst-case performance. The specific syntax supported is</span> +<span class='doccomment'>//! documented further down.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This crate's documentation provides some simple examples, describes Unicode</span> +<span class='doccomment'>//! support and exhaustively lists the supported syntax. For more specific</span> +<span class='doccomment'>//! details on the API, please see the documentation for the `Regex` type.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Usage</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This crate is [on crates.io](https://crates.io/crates/regex) and can be</span> +<span class='doccomment'>//! used by adding `regex` to your dependencies in your project's `Cargo.toml`.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```toml</span> +<span class='doccomment'>//! [dependencies]</span> +<span class='doccomment'>//! regex = "0.1.8"</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! and this to your crate root:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! extern crate regex;</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # First example: find a date</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! General use of regular expressions in this package involves compiling an</span> +<span class='doccomment'>//! expression and then using it to search, split or replace text. For example,</span> +<span class='doccomment'>//! to confirm that some text resembles a date:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! use regex::Regex;</span> +<span class='doccomment'>//! let re = Regex::new(r"^\d{4}-\d{2}-\d{2}$").unwrap();</span> +<span class='doccomment'>//! assert!(re.is_match("2014-01-01"));</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Notice the use of the `^` and `$` anchors. In this crate, every expression</span> +<span class='doccomment'>//! is executed with an implicit `.*?` at the beginning and end, which allows</span> +<span class='doccomment'>//! it to match anywhere in the text. Anchors can be used to ensure that the</span> +<span class='doccomment'>//! full text matches an expression.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This example also demonstrates the utility of</span> +<span class='doccomment'>//! [raw strings](http://doc.rust-lang.org/stable/reference.html#raw-byte-string-literals)</span> +<span class='doccomment'>//! in Rust, which</span> +<span class='doccomment'>//! are just like regular strings except they are prefixed with an `r` and do</span> +<span class='doccomment'>//! not process any escape sequences. For example, `"\\d"` is the same</span> +<span class='doccomment'>//! expression as `r"\d"`.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # The `regex!` macro</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Rust's compile-time meta-programming facilities provide a way to write a</span> +<span class='doccomment'>//! `regex!` macro which compiles regular expressions *when your program</span> +<span class='doccomment'>//! compiles*. Said differently, if you only use `regex!` to build regular</span> +<span class='doccomment'>//! expressions in your program, then your program cannot compile with an</span> +<span class='doccomment'>//! invalid regular expression. Moreover, the `regex!` macro compiles the</span> +<span class='doccomment'>//! given expression to native Rust code, which ideally makes it faster.</span> +<span class='doccomment'>//! Unfortunately (or fortunately), the dynamic implementation has had a lot</span> +<span class='doccomment'>//! more optimization work put it into it currently, so it is faster than</span> +<span class='doccomment'>//! the `regex!` macro in most cases.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! To use the `regex!` macro, you must enable the `plugin` feature and import</span> +<span class='doccomment'>//! the `regex_macros` crate as a syntax extension:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```ignore</span> +<span class='doccomment'>//! #![feature(plugin)]</span> +<span class='doccomment'>//! #![plugin(regex_macros)]</span> +<span class='doccomment'>//! extern crate regex;</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! fn main() {</span> +<span class='doccomment'>//! let re = regex!(r"^\d{4}-\d{2}-\d{2}$");</span> +<span class='doccomment'>//! assert!(re.is_match("2014-01-01"));</span> +<span class='doccomment'>//! }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! There are a few things worth mentioning about using the `regex!` macro.</span> +<span class='doccomment'>//! Firstly, the `regex!` macro *only* accepts string *literals*.</span> +<span class='doccomment'>//! Secondly, the `regex` crate *must* be linked with the name `regex` since</span> +<span class='doccomment'>//! the generated code depends on finding symbols in the `regex` crate.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! One downside of using the `regex!` macro is that it can increase the</span> +<span class='doccomment'>//! size of your program's binary since it generates specialized Rust code.</span> +<span class='doccomment'>//! The extra size probably won't be significant for a small number of</span> +<span class='doccomment'>//! expressions, but 100+ calls to `regex!` will probably result in a</span> +<span class='doccomment'>//! noticeably bigger binary.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! **NOTE**: This is implemented using a compiler plugin, which is not</span> +<span class='doccomment'>//! available on the Rust 1.0 beta/stable channels. Therefore, you'll only</span> +<span class='doccomment'>//! be able to use `regex!` on the nightlies.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Example: iterating over capture groups</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This crate provides convenient iterators for matching an expression</span> +<span class='doccomment'>//! repeatedly against a search string to find successive non-overlapping</span> +<span class='doccomment'>//! matches. For example, to find all dates in a string and be able to access</span> +<span class='doccomment'>//! them by their component pieces:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"(\d{4})-(\d{2})-(\d{2})").unwrap();</span> +<span class='doccomment'>//! let text = "2012-03-14, 2013-01-01 and 2014-07-05";</span> +<span class='doccomment'>//! for cap in re.captures_iter(text) {</span> +<span class='doccomment'>//! println!("Month: {} Day: {} Year: {}",</span> +<span class='doccomment'>//! cap.at(2).unwrap_or(""), cap.at(3).unwrap_or(""),</span> +<span class='doccomment'>//! cap.at(1).unwrap_or(""));</span> +<span class='doccomment'>//! }</span> +<span class='doccomment'>//! // Output:</span> +<span class='doccomment'>//! // Month: 03 Day: 14 Year: 2012</span> +<span class='doccomment'>//! // Month: 01 Day: 01 Year: 2013</span> +<span class='doccomment'>//! // Month: 07 Day: 05 Year: 2014</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Notice that the year is in the capture group indexed at `1`. This is</span> +<span class='doccomment'>//! because the *entire match* is stored in the capture group at index `0`.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Example: replacement with named capture groups</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Building on the previous example, perhaps we'd like to rearrange the date</span> +<span class='doccomment'>//! formats. This can be done with text replacement. But to make the code</span> +<span class='doccomment'>//! clearer, we can *name* our capture groups and use those names as variables</span> +<span class='doccomment'>//! in our replacement text:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"(?P<y>\d{4})-(?P<m>\d{2})-(?P<d>\d{2})").unwrap();</span> +<span class='doccomment'>//! let before = "2012-03-14, 2013-01-01 and 2014-07-05";</span> +<span class='doccomment'>//! let after = re.replace_all(before, "$m/$d/$y");</span> +<span class='doccomment'>//! assert_eq!(after, "03/14/2012, 01/01/2013 and 07/05/2014");</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! The `replace` methods are actually polymorphic in the replacement, which</span> +<span class='doccomment'>//! provides more flexibility than is seen here. (See the documentation for</span> +<span class='doccomment'>//! `Regex::replace` for more details.)</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Note that if your regex gets complicated, you can use the `x` flag to</span> +<span class='doccomment'>//! enable insigificant whitespace mode, which also lets you write comments:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"(?x)</span> +<span class='doccomment'>//! (?P<y>\d{4}) # the year</span> +<span class='doccomment'>//! -</span> +<span class='doccomment'>//! (?P<m>\d{2}) # the month</span> +<span class='doccomment'>//! -</span> +<span class='doccomment'>//! (?P<d>\d{2}) # the day</span> +<span class='doccomment'>//! ").unwrap();</span> +<span class='doccomment'>//! let before = "2012-03-14, 2013-01-01 and 2014-07-05";</span> +<span class='doccomment'>//! let after = re.replace_all(before, "$m/$d/$y");</span> +<span class='doccomment'>//! assert_eq!(after, "03/14/2012, 01/01/2013 and 07/05/2014");</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Pay for what you use</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! With respect to searching text with a regular expression, there are three</span> +<span class='doccomment'>//! questions that can be asked:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! 1. Does the text match this expression?</span> +<span class='doccomment'>//! 2. If so, where does it match?</span> +<span class='doccomment'>//! 3. Where are the submatches?</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Generally speaking, this crate could provide a function to answer only #3,</span> +<span class='doccomment'>//! which would subsume #1 and #2 automatically. However, it can be</span> +<span class='doccomment'>//! significantly more expensive to compute the location of submatches, so it's</span> +<span class='doccomment'>//! best not to do it if you don't need to.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Therefore, only use what you need. For example, don't use `find` if you</span> +<span class='doccomment'>//! only need to test if an expression matches a string. (Use `is_match`</span> +<span class='doccomment'>//! instead.)</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Unicode</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This implementation executes regular expressions **only** on sequences of</span> +<span class='doccomment'>//! Unicode scalar values while exposing match locations as byte indices into</span> +<span class='doccomment'>//! the search string.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Currently, only simple case folding is supported. Namely, when matching</span> +<span class='doccomment'>//! case-insensitively, the characters are first mapped using the</span> +<span class='doccomment'>//! [simple case folding](ftp://ftp.unicode.org/Public/UNIDATA/CaseFolding.txt)</span> +<span class='doccomment'>//! mapping.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Regular expressions themselves are also **only** interpreted as a sequence</span> +<span class='doccomment'>//! of Unicode scalar values. This means you can use Unicode characters</span> +<span class='doccomment'>//! directly in your expression:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"(?i)Δ+").unwrap();</span> +<span class='doccomment'>//! assert_eq!(re.find("ΔδΔ"), Some((0, 6)));</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Finally, Unicode general categories and scripts are available as character</span> +<span class='doccomment'>//! classes. For example, you can match a sequence of numerals, Greek or</span> +<span class='doccomment'>//! Cherokee letters:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"[\pN\p{Greek}\p{Cherokee}]+").unwrap();</span> +<span class='doccomment'>//! assert_eq!(re.find("abcΔᎠβⅠᏴγδⅡxyz"), Some((3, 23)));</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Syntax</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! The syntax supported in this crate is almost in an exact correspondence</span> +<span class='doccomment'>//! with the syntax supported by RE2. It is documented below.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Note that the regular expression parser and abstract syntax are exposed in</span> +<span class='doccomment'>//! a separate crate,</span> +<span class='doccomment'>//! [`regex-syntax`](../regex_syntax/index.html).</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Matching one character</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! . any character except new line (includes new line with s flag)</span> +<span class='doccomment'>//! [xyz] A character class matching either x, y or z.</span> +<span class='doccomment'>//! [^xyz] A character class matching any character except x, y and z.</span> +<span class='doccomment'>//! [a-z] A character class matching any character in range a-z.</span> +<span class='doccomment'>//! \d digit (\p{Nd})</span> +<span class='doccomment'>//! \D not digit</span> +<span class='doccomment'>//! [:alpha:] ASCII character class ([A-Za-z])</span> +<span class='doccomment'>//! [:^alpha:] Negated ASCII character class ([^A-Za-z])</span> +<span class='doccomment'>//! \pN One-letter name Unicode character class</span> +<span class='doccomment'>//! \p{Greek} Unicode character class (general category or script)</span> +<span class='doccomment'>//! \PN Negated one-letter name Unicode character class</span> +<span class='doccomment'>//! \P{Greek} negated Unicode character class (general category or script)</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Any named character class may appear inside a bracketed `[...]` character</span> +<span class='doccomment'>//! class. For example, `[\p{Greek}\pN]` matches any Greek or numeral</span> +<span class='doccomment'>//! character.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Composites</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! xy concatenation (x followed by y)</span> +<span class='doccomment'>//! x|y alternation (x or y, prefer x)</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Repetitions</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! x* zero or more of x (greedy)</span> +<span class='doccomment'>//! x+ one or more of x (greedy)</span> +<span class='doccomment'>//! x? zero or one of x (greedy)</span> +<span class='doccomment'>//! x*? zero or more of x (ungreedy)</span> +<span class='doccomment'>//! x+? one or more of x (ungreedy)</span> +<span class='doccomment'>//! x?? zero or one of x (ungreedy)</span> +<span class='doccomment'>//! x{n,m} at least n x and at most m x (greedy)</span> +<span class='doccomment'>//! x{n,} at least n x (greedy)</span> +<span class='doccomment'>//! x{n} exactly n x</span> +<span class='doccomment'>//! x{n,m}? at least n x and at most m x (ungreedy)</span> +<span class='doccomment'>//! x{n,}? at least n x (ungreedy)</span> +<span class='doccomment'>//! x{n}? exactly n x</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Empty matches</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! ^ the beginning of text (or start-of-line with multi-line mode)</span> +<span class='doccomment'>//! $ the end of text (or end-of-line with multi-line mode)</span> +<span class='doccomment'>//! \A only the beginning of text (even with multi-line mode enabled)</span> +<span class='doccomment'>//! \z only the end of text (even with multi-line mode enabled)</span> +<span class='doccomment'>//! \b a Unicode word boundary (\w on one side and \W, \A, or \z on other)</span> +<span class='doccomment'>//! \B not a Unicode word boundary</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Grouping and flags</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! (exp) numbered capture group (indexed by opening parenthesis)</span> +<span class='doccomment'>//! (?P&lt;name&gt;exp) named (also numbered) capture group (allowed chars: [_0-9a-zA-Z])</span> +<span class='doccomment'>//! (?:exp) non-capturing group</span> +<span class='doccomment'>//! (?flags) set flags within current group</span> +<span class='doccomment'>//! (?flags:exp) set flags for exp (non-capturing)</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Flags are each a single character. For example, `(?x)` sets the flag `x`</span> +<span class='doccomment'>//! and `(?-x)` clears the flag `x`. Multiple flags can be set or cleared at</span> +<span class='doccomment'>//! the same time: `(?xy)` sets both the `x` and `y` flags and `(?x-y)` sets</span> +<span class='doccomment'>//! the `x` flag and clears the `y` flag.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! All flags are by default disabled. They are:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! i case-insensitive</span> +<span class='doccomment'>//! m multi-line mode: ^ and $ match begin/end of line</span> +<span class='doccomment'>//! s allow . to match \n</span> +<span class='doccomment'>//! U swap the meaning of x* and x*?</span> +<span class='doccomment'>//! x ignore whitespace and allow line comments (starting with `#`)</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Here's an example that matches case-insensitively for only part of the</span> +<span class='doccomment'>//! expression:</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ```rust</span> +<span class='doccomment'>//! # extern crate regex; use regex::Regex;</span> +<span class='doccomment'>//! # fn main() {</span> +<span class='doccomment'>//! let re = Regex::new(r"(?i)a+(?-i)b+").unwrap();</span> +<span class='doccomment'>//! let cap = re.captures("AaAaAbbBBBb").unwrap();</span> +<span class='doccomment'>//! assert_eq!(cap.at(0), Some("AaAaAbb"));</span> +<span class='doccomment'>//! # }</span> +<span class='doccomment'>//! ```</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Notice that the `a+` matches either `a` or `A`, but the `b+` only matches</span> +<span class='doccomment'>//! `b`.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Escape sequences</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! \* literal *, works for any punctuation character: \.+*?()|[]{}^$</span> +<span class='doccomment'>//! \a bell (\x07)</span> +<span class='doccomment'>//! \f form feed (\x0C)</span> +<span class='doccomment'>//! \t horizontal tab</span> +<span class='doccomment'>//! \n new line</span> +<span class='doccomment'>//! \r carriage return</span> +<span class='doccomment'>//! \v vertical tab (\x0B)</span> +<span class='doccomment'>//! \123 octal character code (up to three digits)</span> +<span class='doccomment'>//! \x7F hex character code (exactly two digits)</span> +<span class='doccomment'>//! \x{10FFFF} any hex character code corresponding to a Unicode code point</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## Perl character classes (Unicode friendly)</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! These classes are based on the definitions provided in</span> +<span class='doccomment'>//! [UTS#18](http://www.unicode.org/reports/tr18/#Compatibility_Properties):</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! \d digit (\p{Nd})</span> +<span class='doccomment'>//! \D not digit</span> +<span class='doccomment'>//! \s whitespace (\p{White_Space})</span> +<span class='doccomment'>//! \S not whitespace</span> +<span class='doccomment'>//! \w word character (\p{Alphabetic} + \p{M} + \d + \p{Pc} + \p{Join_Control})</span> +<span class='doccomment'>//! \W not word character</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! ## ASCII character classes</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! <pre class="rust"></span> +<span class='doccomment'>//! [:alnum:] alphanumeric ([0-9A-Za-z])</span> +<span class='doccomment'>//! [:alpha:] alphabetic ([A-Za-z])</span> +<span class='doccomment'>//! [:ascii:] ASCII ([\x00-\x7F])</span> +<span class='doccomment'>//! [:blank:] blank ([\t ])</span> +<span class='doccomment'>//! [:cntrl:] control ([\x00-\x1F\x7F])</span> +<span class='doccomment'>//! [:digit:] digits ([0-9])</span> +<span class='doccomment'>//! [:graph:] graphical ([!-~])</span> +<span class='doccomment'>//! [:lower:] lower case ([a-z])</span> +<span class='doccomment'>//! [:print:] printable ([ -~])</span> +<span class='doccomment'>//! [:punct:] punctuation ([!-/:-@[-`{-~])</span> +<span class='doccomment'>//! [:space:] whitespace ([\t\n\v\f\r ])</span> +<span class='doccomment'>//! [:upper:] upper case ([A-Z])</span> +<span class='doccomment'>//! [:word:] word characters ([0-9A-Za-z_])</span> +<span class='doccomment'>//! [:xdigit:] hex digit ([0-9A-Fa-f])</span> +<span class='doccomment'>//! </pre></span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! # Untrusted input</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! This crate can handle both untrusted regular expressions and untrusted</span> +<span class='doccomment'>//! search text.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Untrusted regular expressions are handled by capping the size of a compiled</span> +<span class='doccomment'>//! regular expression. (See `Regex::with_size_limit`.) Without this, it would</span> +<span class='doccomment'>//! be trivial for an attacker to exhaust your system's memory with expressions</span> +<span class='doccomment'>//! like `a{100}{100}{100}`.</span> +<span class='doccomment'>//!</span> +<span class='doccomment'>//! Untrusted search text is allowed because the matching engine(s) in this</span> +<span class='doccomment'>//! crate have time complexity `O(mn)` (with `m ~ regex` and `n ~ search</span> +<span class='doccomment'>//! text`), which means there's no way to cause exponential blow-up like with</span> +<span class='doccomment'>//! some other regular expression engines. (We pay for this by disallowing</span> +<span class='doccomment'>//! features like arbitrary look-ahead and back-references.)</span> + +<span class='attribute'>#<span class='op'>!</span>[<span class='ident'>deny</span>(<span class='ident'>missing_docs</span>)]</span> +<span class='attribute'>#<span class='op'>!</span>[<span class='ident'>cfg_attr</span>(<span class='ident'>test</span>, <span class='ident'>deny</span>(<span class='ident'>warnings</span>))]</span> +<span class='attribute'>#<span class='op'>!</span>[<span class='ident'>cfg_attr</span>(<span class='ident'>feature</span> <span class='op'>=</span> <span class='string'>"pattern"</span>, <span class='ident'>feature</span>(<span class='ident'>pattern</span>))]</span> +<span class='attribute'>#<span class='op'>!</span>[<span class='ident'>doc</span>(<span class='ident'>html_logo_url</span> <span class='op'>=</span> <span class='string'>"http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png"</span>, + <span class='ident'>html_favicon_url</span> <span class='op'>=</span> <span class='string'>"http://www.rust-lang.org/favicon.ico"</span>, + <span class='ident'>html_root_url</span> <span class='op'>=</span> <span class='string'>"http://doc.rust-lang.org/regex/"</span>)]</span> + +<span class='kw'>extern</span> <span class='kw'>crate</span> <span class='ident'>aho_corasick</span>; +<span class='kw'>extern</span> <span class='kw'>crate</span> <span class='ident'>memchr</span>; +<span class='kw'>extern</span> <span class='kw'>crate</span> <span class='ident'>regex_syntax</span> <span class='kw'>as</span> <span class='ident'>syntax</span>; + +<span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>re</span>::{ + <span class='ident'>Regex</span>, <span class='ident'>Error</span>, <span class='ident'>Captures</span>, <span class='ident'>SubCaptures</span>, <span class='ident'>SubCapturesPos</span>, <span class='ident'>SubCapturesNamed</span>, + <span class='ident'>FindCaptures</span>, <span class='ident'>FindMatches</span>, + <span class='ident'>Replacer</span>, <span class='ident'>NoExpand</span>, <span class='ident'>RegexSplits</span>, <span class='ident'>RegexSplitsN</span>, + <span class='ident'>quote</span>, <span class='ident'>is_match</span>, +}; + +<span class='kw'>mod</span> <span class='ident'>backtrack</span>; +<span class='kw'>mod</span> <span class='ident'>char</span>; +<span class='kw'>mod</span> <span class='ident'>compile</span>; +<span class='kw'>mod</span> <span class='ident'>input</span>; +<span class='kw'>mod</span> <span class='ident'>pool</span>; +<span class='kw'>mod</span> <span class='ident'>prefix</span>; +<span class='kw'>mod</span> <span class='ident'>program</span>; +<span class='kw'>mod</span> <span class='ident'>nfa</span>; +<span class='kw'>mod</span> <span class='ident'>re</span>; + +<span class='doccomment'>/// The `internal` module exists to support the `regex!` macro and other</span> +<span class='doccomment'>/// suspicious activity, such as testing different matching engines.</span> +<span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>mod</span> <span class='ident'>internal</span> { + <span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>char</span>::<span class='ident'>Char</span>; + <span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>input</span>::{<span class='ident'>Input</span>, <span class='ident'>CharInput</span>, <span class='ident'>InputAt</span>}; + <span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>program</span>::{ + <span class='ident'>Program</span>, <span class='ident'>MatchEngine</span>, <span class='ident'>CharRanges</span>, <span class='ident'>Inst</span>, <span class='ident'>LookInst</span>, <span class='ident'>OneChar</span>, + }; + <span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>re</span>::<span class='ident'>ExNative</span>; + <span class='kw'>pub</span> <span class='kw'>use</span> <span class='ident'>re</span>::<span class='ident'>Regex</span>::{<span class='ident'>Dynamic</span>, <span class='ident'>Native</span>}; +} +</pre> +</section> + <section id='search' class="content hidden"></section> + + <section class="footer"></section> + + <div id="help" class="hidden"> + <div class="shortcuts"> + <h1>Keyboard shortcuts</h1> + <dl> + <dt>?</dt> + <dd>Show this help dialog</dd> + <dt>S</dt> + <dd>Focus the search field</dd> + <dt>⇤</dt> + <dd>Move up in search results</dd> + <dt>⇥</dt> + <dd>Move down in search results</dd> + <dt>⏎</dt> + <dd>Go to active search result</dd> + </dl> + </div> + <div class="infos"> + <h1>Search tricks</h1> + <p> + Prefix searches with a type followed by a colon (e.g. + <code>fn:</code>) to restrict the search to a given type. + </p> + <p> + Accepted types are: <code>fn</code>, <code>mod</code>, + <code>struct</code>, <code>enum</code>, + <code>trait</code>, <code>typedef</code> (or + <code>tdef</code>). + </p> + <p> + Search functions by type signature (e.g. + <code>vec -> usize</code>) + </p> + </div> + </div> + + + + <script> + window.rootPath = "../../"; + window.currentCrate = "regex"; + window.playgroundUrl = ""; + </script> + <script src="../../jquery.js"></script> + <script src="../../main.js"></script> + + <script async src="../../search-index.js"></script> +</body> +</html>
\ No newline at end of file diff --git a/src/regex/program.rs.html b/src/regex/program.rs.html new file mode 100644 index 0000000..8f6ed02 --- /dev/null +++ b/src/regex/program.rs.html @@ -0,0 +1,1057 @@ +<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/program.rs`."> + <meta name="keywords" content="rust, rustlang, rust-lang"> + + <title>program.rs.html -- source</title> + + <link rel="stylesheet" type="text/css" href="../../main.css"> + + <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico"> + +</head> +<body class="rustdoc"> + <!--[if lte IE 8]> + <div class="warning"> + This old browser is unsupported and will most likely display funky + things. + </div> + <![endif]--> + + + + <section class="sidebar"> + <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a> + + </section> + + <nav class="sub"> + <form class="search-form js-only"> + <div class="search-container"> + <input class="search-input" name="search" + autocomplete="off" + placeholder="Click or press 'S' to search, '?' for more options..." + type="search"> + </div> + </form> + </nav> + + <section id='main' class="content source"><pre class="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> +<span id="230">230</span> +<span id="231">231</span> +<span id="232">232</span> +<span id="233">233</span> +<span id="234">234</span> +<span id="235">235</span> +<span id="236">236</span> +<span id="237">237</span> +<span id="238">238</span> +<span id="239">239</span> +<span id="240">240</span> +<span id="241">241</span> +<span id="242">242</span> +<span id="243">243</span> +<span id="244">244</span> +<span id="245">245</span> +<span id="246">246</span> +<span id="247">247</span> +<span id="248">248</span> +<span id="249">249</span> +<span id="250">250</span> +<span id="251">251</span> +<span id="252">252</span> +<span id="253">253</span> +<span id="254">254</span> +<span id="255">255</span> +<span id="256">256</span> +<span id="257">257</span> +<span id="258">258</span> +<span id="259">259</span> +<span id="260">260</span> +<span id="261">261</span> +<span id="262">262</span> +<span id="263">263</span> +<span id="264">264</span> +<span id="265">265</span> +<span id="266">266</span> +<span id="267">267</span> +<span id="268">268</span> +<span id="269">269</span> +<span id="270">270</span> +<span id="271">271</span> +<span id="272">272</span> +<span id="273">273</span> +<span id="274">274</span> +<span id="275">275</span> +<span id="276">276</span> +<span id="277">277</span> +<span id="278">278</span> +<span id="279">279</span> +<span id="280">280</span> +<span id="281">281</span> +<span id="282">282</span> +<span id="283">283</span> +<span id="284">284</span> +<span id="285">285</span> +<span id="286">286</span> +<span id="287">287</span> +<span id="288">288</span> +<span id="289">289</span> +<span id="290">290</span> +<span id="291">291</span> +<span id="292">292</span> +<span id="293">293</span> +<span id="294">294</span> +<span id="295">295</span> +<span id="296">296</span> +<span id="297">297</span> +<span id="298">298</span> +<span id="299">299</span> +<span id="300">300</span> +<span id="301">301</span> +<span id="302">302</span> +<span id="303">303</span> +<span id="304">304</span> +<span id="305">305</span> +<span id="306">306</span> +<span id="307">307</span> +<span id="308">308</span> +<span id="309">309</span> +<span id="310">310</span> +<span id="311">311</span> +<span id="312">312</span> +<span id="313">313</span> +<span id="314">314</span> +<span id="315">315</span> +<span id="316">316</span> +<span id="317">317</span> +<span id="318">318</span> +<span id="319">319</span> +<span id="320">320</span> +<span id="321">321</span> +<span id="322">322</span> +<span id="323">323</span> +<span id="324">324</span> +<span id="325">325</span> +<span id="326">326</span> +<span id="327">327</span> +<span id="328">328</span> +<span id="329">329</span> +<span id="330">330</span> +<span id="331">331</span> +<span id="332">332</span> +<span id="333">333</span> +<span id="334">334</span> +<span id="335">335</span> +<span id="336">336</span> +<span id="337">337</span> +<span id="338">338</span> +<span id="339">339</span> +<span id="340">340</span> +<span id="341">341</span> +<span id="342">342</span> +<span id="343">343</span> +<span id="344">344</span> +<span id="345">345</span> +<span id="346">346</span> +<span id="347">347</span> +<span id="348">348</span> +<span id="349">349</span> +<span id="350">350</span> +<span id="351">351</span> +<span id="352">352</span> +<span id="353">353</span> +<span id="354">354</span> +<span id="355">355</span> +<span id="356">356</span> +<span id="357">357</span> +<span id="358">358</span> +<span id="359">359</span> +<span id="360">360</span> +<span id="361">361</span> +<span id="362">362</span> +<span id="363">363</span> +<span id="364">364</span> +<span id="365">365</span> +<span id="366">366</span> +<span id="367">367</span> +<span id="368">368</span> +<span id="369">369</span> +<span id="370">370</span> +<span id="371">371</span> +<span id="372">372</span> +<span id="373">373</span> +<span id="374">374</span> +<span id="375">375</span> +<span id="376">376</span> +<span id="377">377</span> +<span id="378">378</span> +<span id="379">379</span> +<span id="380">380</span> +<span id="381">381</span> +<span id="382">382</span> +<span id="383">383</span> +<span id="384">384</span> +<span id="385">385</span> +<span id="386">386</span> +<span id="387">387</span> +<span id="388">388</span> +<span id="389">389</span> +<span id="390">390</span> +<span id="391">391</span> +<span id="392">392</span> +<span id="393">393</span> +<span id="394">394</span> +<span id="395">395</span> +<span id="396">396</span> +<span id="397">397</span> +<span id="398">398</span> +<span id="399">399</span> +<span id="400">400</span> +<span id="401">401</span> +<span id="402">402</span> +<span id="403">403</span> +<span id="404">404</span> +<span id="405">405</span> +<span id="406">406</span> +<span id="407">407</span> +<span id="408">408</span> +<span id="409">409</span> +<span id="410">410</span> +<span id="411">411</span> +<span id="412">412</span> +<span id="413">413</span> +<span id="414">414</span> +<span id="415">415</span> +<span id="416">416</span> +<span id="417">417</span> +<span id="418">418</span> +<span id="419">419</span> +<span id="420">420</span> +<span id="421">421</span> +<span id="422">422</span> +<span id="423">423</span> +<span id="424">424</span> +<span id="425">425</span> +<span id="426">426</span> +<span id="427">427</span> +<span id="428">428</span> +<span id="429">429</span> +<span id="430">430</span> +<span id="431">431</span> +<span id="432">432</span> +<span id="433">433</span> +<span id="434">434</span> +<span id="435">435</span> +<span id="436">436</span> +<span id="437">437</span> +<span id="438">438</span> +<span id="439">439</span> +<span id="440">440</span> +<span id="441">441</span> +<span id="442">442</span> +<span id="443">443</span> +<span id="444">444</span> +<span id="445">445</span> +<span id="446">446</span> +<span id="447">447</span> +<span id="448">448</span> +<span id="449">449</span> +<span id="450">450</span> +<span id="451">451</span> +<span id="452">452</span> +<span id="453">453</span> +<span id="454">454</span> +<span id="455">455</span> +<span id="456">456</span> +<span id="457">457</span> +<span id="458">458</span> +<span id="459">459</span> +<span id="460">460</span> +<span id="461">461</span> +<span id="462">462</span> +<span id="463">463</span> +<span id="464">464</span> +<span id="465">465</span> +<span id="466">466</span> +<span id="467">467</span> +<span id="468">468</span> +<span id="469">469</span> +<span id="470">470</span> +<span id="471">471</span> +<span id="472">472</span> +<span id="473">473</span> +<span id="474">474</span> +<span id="475">475</span> +<span id="476">476</span> +<span id="477">477</span> +<span id="478">478</span> +<span id="479">479</span> +<span id="480">480</span> +</pre><pre class='rust '> +<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span> +<span class='comment'>// file at the top-level directory of this distribution and at</span> +<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span> +<span class='comment'>//</span> +<span class='comment'>// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> +<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> +<span class='comment'>// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> +<span class='comment'>// option. This file may not be copied, modified, or distributed</span> +<span class='comment'>// except according to those terms.</span> + +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>cmp</span>::{<span class='self'>self</span>, <span class='ident'>Ordering</span>}; + +<span class='kw'>use</span> <span class='ident'>syntax</span>; + +<span class='kw'>use</span> <span class='ident'>Error</span>; +<span class='kw'>use</span> <span class='ident'>backtrack</span>::{<span class='ident'>Backtrack</span>, <span class='ident'>BackMachine</span>}; +<span class='kw'>use</span> <span class='ident'>char</span>::<span class='ident'>Char</span>; +<span class='kw'>use</span> <span class='ident'>compile</span>::<span class='ident'>Compiler</span>; +<span class='kw'>use</span> <span class='ident'>nfa</span>::{<span class='ident'>Nfa</span>, <span class='ident'>NfaThreads</span>}; +<span class='kw'>use</span> <span class='ident'>pool</span>::<span class='ident'>Pool</span>; +<span class='kw'>use</span> <span class='ident'>prefix</span>::<span class='ident'>Prefix</span>; +<span class='kw'>use</span> <span class='ident'>re</span>::<span class='ident'>CaptureIdxs</span>; + +<span class='kw'>const</span> <span class='ident'>NUM_PREFIX_LIMIT</span>: <span class='ident'>usize</span> <span class='op'>=</span> <span class='number'>30</span>; +<span class='kw'>const</span> <span class='ident'>PREFIX_LENGTH_LIMIT</span>: <span class='ident'>usize</span> <span class='op'>=</span> <span class='number'>15</span>; + +<span class='kw'>pub</span> <span class='kw'>type</span> <span class='ident'>InstIdx</span> <span class='op'>=</span> <span class='ident'>usize</span>; + +<span class='doccomment'>/// An instruction, the underlying unit of a compiled regular expression</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>Inst</span> { + <span class='doccomment'>/// A match has occurred.</span> + <span class='doccomment'>/// This is always the last instruction and only occurs in a single spot.</span> + <span class='doccomment'>/// We could special case this in the code, but it is much clearer to</span> + <span class='doccomment'>/// handle it as a proper instruction.</span> + <span class='ident'>Match</span>, + <span class='doccomment'>/// Save the current location in the input into the given capture location.</span> + <span class='ident'>Save</span>(<span class='ident'>usize</span>), + <span class='doccomment'>/// Jump to the instruction given.</span> + <span class='ident'>Jump</span>(<span class='ident'>InstIdx</span>), + <span class='doccomment'>/// Match either instruction, preferring the first.</span> + <span class='ident'>Split</span>(<span class='ident'>InstIdx</span>, <span class='ident'>InstIdx</span>), + <span class='doccomment'>/// A zero-width instruction. When this instruction matches, the input</span> + <span class='doccomment'>/// is not advanced.</span> + <span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>), + <span class='doccomment'>/// Match a single possibly case insensitive character.</span> + <span class='ident'>Char</span>(<span class='ident'>OneChar</span>), + <span class='doccomment'>/// Match one or more possibly case insensitive character ranges.</span> + <span class='ident'>Ranges</span>(<span class='ident'>CharRanges</span>), +} + +<span class='doccomment'>/// A single character instruction.</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>OneChar</span> { + <span class='doccomment'>/// The character.</span> + <span class='kw'>pub</span> <span class='ident'>c</span>: <span class='ident'>char</span>, + <span class='doccomment'>/// True if the character should be matched case insensitively.</span> + <span class='doccomment'>/// (i.e., The input character will need to be case folded.)</span> + <span class='kw'>pub</span> <span class='ident'>casei</span>: <span class='ident'>bool</span>, +} + +<span class='doccomment'>/// A multi-range character class instruction.</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>CharRanges</span> { + <span class='doccomment'>/// Sorted sequence of non-overlapping ranges.</span> + <span class='kw'>pub</span> <span class='ident'>ranges</span>: <span class='ident'>Vec</span><span class='op'><</span>(<span class='ident'>char</span>, <span class='ident'>char</span>)<span class='op'>></span>, + <span class='doccomment'>/// Whether to match case insensitively.</span> + <span class='kw'>pub</span> <span class='ident'>casei</span>: <span class='ident'>bool</span>, +} + +<span class='doccomment'>/// The set of zero-width match instructions.</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Debug</span>, <span class='ident'>PartialEq</span>, <span class='ident'>Eq</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>LookInst</span> { + <span class='doccomment'>/// Start of line or input.</span> + <span class='ident'>StartLine</span>, + <span class='doccomment'>/// End of line or input.</span> + <span class='ident'>EndLine</span>, + <span class='doccomment'>/// Start of input.</span> + <span class='ident'>StartText</span>, + <span class='doccomment'>/// End of input.</span> + <span class='ident'>EndText</span>, + <span class='doccomment'>/// Word character on one side and non-word character on other.</span> + <span class='ident'>WordBoundary</span>, + <span class='doccomment'>/// Word character on both sides or non-word character on both sides.</span> + <span class='ident'>NotWordBoundary</span>, +} + +<span class='kw'>impl</span> <span class='ident'>OneChar</span> { + <span class='doccomment'>/// Tests whether the given input character matches this instruction.</span> + <span class='attribute'>#[<span class='ident'>inline</span>(<span class='ident'>always</span>)]</span> <span class='comment'>// About ~5-15% more throughput then `#[inline]`</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>c</span>: <span class='ident'>Char</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='self'>self</span>.<span class='ident'>c</span> <span class='op'>==</span> <span class='ident'>c</span> <span class='op'>||</span> (<span class='self'>self</span>.<span class='ident'>casei</span> <span class='op'>&&</span> <span class='self'>self</span>.<span class='ident'>c</span> <span class='op'>==</span> <span class='ident'>c</span>.<span class='ident'>case_fold</span>()) + } +} + +<span class='kw'>impl</span> <span class='ident'>CharRanges</span> { + <span class='doccomment'>/// Emits a range specifically for the `.` expression.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>any</span>() <span class='op'>-></span> <span class='ident'>CharRanges</span> { + <span class='ident'>CharRanges</span> { + <span class='ident'>ranges</span>: <span class='macro'>vec</span><span class='macro'>!</span>[(<span class='string'>'\x00'</span>, <span class='string'>'\u{10ffff}'</span>)], + <span class='ident'>casei</span>: <span class='boolval'>false</span>, + } + } + + <span class='doccomment'>/// Emits a range specifically for the `(?s).` expression.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>any_nonl</span>() <span class='op'>-></span> <span class='ident'>CharRanges</span> { + <span class='ident'>CharRanges</span> { + <span class='ident'>ranges</span>: <span class='macro'>vec</span><span class='macro'>!</span>[(<span class='string'>'\x00'</span>, <span class='string'>'\x09'</span>), (<span class='string'>'\x0B'</span>, <span class='string'>'\u{10ffff}'</span>)], + <span class='ident'>casei</span>: <span class='boolval'>false</span>, + } + } + + <span class='doccomment'>/// Emits a range from the AST character class.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>from_class</span>(<span class='ident'>cls</span>: <span class='ident'>syntax</span>::<span class='ident'>CharClass</span>) <span class='op'>-></span> <span class='ident'>CharRanges</span> { + <span class='kw'>let</span> <span class='ident'>casei</span> <span class='op'>=</span> <span class='ident'>cls</span>.<span class='ident'>is_case_insensitive</span>(); + <span class='ident'>CharRanges</span> { + <span class='ident'>ranges</span>: <span class='ident'>cls</span>.<span class='ident'>into_iter</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>r</span><span class='op'>|</span> (<span class='ident'>r</span>.<span class='ident'>start</span>, <span class='ident'>r</span>.<span class='ident'>end</span>)).<span class='ident'>collect</span>(), + <span class='ident'>casei</span>: <span class='ident'>casei</span>, + } + } + + <span class='doccomment'>/// Tests whether the given input character matches this instruction.</span> + <span class='attribute'>#[<span class='ident'>inline</span>(<span class='ident'>always</span>)]</span> <span class='comment'>// About ~5-15% more throughput then `#[inline]`</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>c</span>: <span class='ident'>Char</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>casei</span> { + <span class='ident'>c</span> <span class='op'>=</span> <span class='ident'>c</span>.<span class='ident'>case_fold</span>(); + } + <span class='comment'>// This speeds up the `match_class_unicode` benchmark by checking</span> + <span class='comment'>// some common cases quickly without binary search. e.g., Matching</span> + <span class='comment'>// a Unicode class on predominantly ASCII text.</span> + <span class='kw'>for</span> <span class='ident'>i</span> <span class='kw'>in</span> <span class='number'>0</span>..<span class='ident'>cmp</span>::<span class='ident'>min</span>(<span class='self'>self</span>.<span class='ident'>ranges</span>.<span class='ident'>len</span>(), <span class='number'>4</span>) { + <span class='kw'>let</span> <span class='ident'>r</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>ranges</span>[<span class='ident'>i</span>]; + <span class='kw'>if</span> <span class='ident'>c</span> <span class='op'><</span> <span class='ident'>r</span>.<span class='number'>0</span> { + <span class='kw'>return</span> <span class='prelude-val'>None</span>; + } + <span class='kw'>if</span> <span class='ident'>c</span> <span class='op'><=</span> <span class='ident'>r</span>.<span class='number'>1</span> { + <span class='kw'>return</span> <span class='prelude-val'>Some</span>(<span class='ident'>i</span>); + } + } + <span class='self'>self</span>.<span class='ident'>ranges</span>.<span class='ident'>binary_search_by</span>(<span class='op'>|</span><span class='ident'>r</span><span class='op'>|</span> { + <span class='kw'>if</span> <span class='ident'>r</span>.<span class='number'>1</span> <span class='op'><</span> <span class='ident'>c</span> { + <span class='ident'>Ordering</span>::<span class='ident'>Less</span> + } <span class='kw'>else</span> <span class='kw'>if</span> <span class='ident'>r</span>.<span class='number'>0</span> <span class='op'>></span> <span class='ident'>c</span> { + <span class='ident'>Ordering</span>::<span class='ident'>Greater</span> + } <span class='kw'>else</span> { + <span class='ident'>Ordering</span>::<span class='ident'>Equal</span> + } + }).<span class='ident'>ok</span>() + } +} + +<span class='kw'>impl</span> <span class='ident'>LookInst</span> { + <span class='doccomment'>/// Tests whether the pair of characters matches this zero-width</span> + <span class='doccomment'>/// instruction.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>matches</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>c1</span>: <span class='ident'>Char</span>, <span class='ident'>c2</span>: <span class='ident'>Char</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>LookInst</span>::<span class='op'>*</span>; + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>StartLine</span> <span class='op'>=></span> <span class='ident'>c1</span>.<span class='ident'>is_none</span>() <span class='op'>||</span> <span class='ident'>c1</span> <span class='op'>==</span> <span class='string'>'\n'</span>, + <span class='ident'>EndLine</span> <span class='op'>=></span> <span class='ident'>c2</span>.<span class='ident'>is_none</span>() <span class='op'>||</span> <span class='ident'>c2</span> <span class='op'>==</span> <span class='string'>'\n'</span>, + <span class='ident'>StartText</span> <span class='op'>=></span> <span class='ident'>c1</span>.<span class='ident'>is_none</span>(), + <span class='ident'>EndText</span> <span class='op'>=></span> <span class='ident'>c2</span>.<span class='ident'>is_none</span>(), + <span class='kw-2'>ref</span> <span class='ident'>wbty</span> <span class='op'>=></span> { + <span class='kw'>let</span> (<span class='ident'>w1</span>, <span class='ident'>w2</span>) <span class='op'>=</span> (<span class='ident'>c1</span>.<span class='ident'>is_word_char</span>(), <span class='ident'>c2</span>.<span class='ident'>is_word_char</span>()); + (<span class='op'>*</span><span class='ident'>wbty</span> <span class='op'>==</span> <span class='ident'>WordBoundary</span> <span class='op'>&&</span> <span class='ident'>w1</span> <span class='op'>^</span> <span class='ident'>w2</span>) + <span class='op'>||</span> (<span class='op'>*</span><span class='ident'>wbty</span> <span class='op'>==</span> <span class='ident'>NotWordBoundary</span> <span class='op'>&&</span> <span class='op'>!</span>(<span class='ident'>w1</span> <span class='op'>^</span> <span class='ident'>w2</span>)) + } + } + } +} + +<span class='doccomment'>/// The matching engines offered by this regex implementation.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// N.B. This is exported for use in testing.</span> +<span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>, <span class='ident'>Copy</span>, <span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>MatchEngine</span> { + <span class='doccomment'>/// A bounded backtracking implementation. About twice as fast as the</span> + <span class='doccomment'>/// NFA, but can only work on small regexes and small input.</span> + <span class='ident'>Backtrack</span>, + <span class='doccomment'>/// A full NFA simulation. Can always be employed but almost always the</span> + <span class='doccomment'>/// slowest choice.</span> + <span class='ident'>Nfa</span>, + <span class='doccomment'>/// If the entire regex is a literal and no capture groups have been</span> + <span class='doccomment'>/// requested, then we can degrade to a simple substring match.</span> + <span class='ident'>Literals</span>, +} + +<span class='doccomment'>/// Program represents a compiled regular expression. Once an expression is</span> +<span class='doccomment'>/// compiled, its representation is immutable and will never change.</span> +<span class='doccomment'>/// (Well, almost. In fact, the matching engines cache state that can be</span> +<span class='doccomment'>/// reused on subsequent searches. But this is interior mutability that</span> +<span class='doccomment'>/// shouldn't be observable by the caller.)</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>Program</span> { + <span class='doccomment'>/// The original regular expression string.</span> + <span class='kw'>pub</span> <span class='ident'>original</span>: <span class='ident'>String</span>, + <span class='doccomment'>/// A sequence of instructions.</span> + <span class='kw'>pub</span> <span class='ident'>insts</span>: <span class='ident'>Vec</span><span class='op'><</span><span class='ident'>Inst</span><span class='op'>></span>, + <span class='doccomment'>/// The sequence of capture group names. There is an entry for each capture</span> + <span class='doccomment'>/// group index and a name exists only if the capture group is named.</span> + <span class='kw'>pub</span> <span class='ident'>cap_names</span>: <span class='ident'>Vec</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>String</span><span class='op'>>></span>, + <span class='doccomment'>/// If the regular expression requires a literal prefix in order to have a</span> + <span class='doccomment'>/// match, that prefix is stored here as a DFA.</span> + <span class='kw'>pub</span> <span class='ident'>prefixes</span>: <span class='ident'>Prefix</span>, + <span class='doccomment'>/// True iff matching any literal prefix indicates a match.</span> + <span class='kw'>pub</span> <span class='ident'>prefixes_complete</span>: <span class='ident'>bool</span>, + <span class='doccomment'>/// True iff program is anchored at the beginning.</span> + <span class='kw'>pub</span> <span class='ident'>anchored_begin</span>: <span class='ident'>bool</span>, + <span class='doccomment'>/// True iff program is anchored at the end.</span> + <span class='kw'>pub</span> <span class='ident'>anchored_end</span>: <span class='ident'>bool</span>, + <span class='doccomment'>/// The type of matching engine to use.</span> + <span class='doccomment'>/// When `None` (the default), pick an engine automatically.</span> + <span class='kw'>pub</span> <span class='ident'>engine</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>MatchEngine</span><span class='op'>></span>, + <span class='doccomment'>/// Cached NFA threads.</span> + <span class='kw'>pub</span> <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span><span class='op'><</span><span class='ident'>NfaThreads</span><span class='op'>></span>, + <span class='doccomment'>/// Cached backtracking memory.</span> + <span class='kw'>pub</span> <span class='ident'>backtrack</span>: <span class='ident'>Pool</span><span class='op'><</span><span class='ident'>BackMachine</span><span class='op'>></span>, +} + +<span class='kw'>impl</span> <span class='ident'>Program</span> { + <span class='doccomment'>/// Compiles a Regex.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>new</span>( + <span class='ident'>engine</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>MatchEngine</span><span class='op'>></span>, + <span class='ident'>size_limit</span>: <span class='ident'>usize</span>, + <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, + ) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>Program</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='kw'>let</span> <span class='ident'>expr</span> <span class='op'>=</span> <span class='macro'>try</span><span class='macro'>!</span>(<span class='ident'>syntax</span>::<span class='ident'>Expr</span>::<span class='ident'>parse</span>(<span class='ident'>re</span>)); + <span class='kw'>let</span> (<span class='ident'>insts</span>, <span class='ident'>cap_names</span>) <span class='op'>=</span> <span class='macro'>try</span><span class='macro'>!</span>(<span class='ident'>Compiler</span>::<span class='ident'>new</span>(<span class='ident'>size_limit</span>).<span class='ident'>compile</span>(<span class='ident'>expr</span>)); + <span class='kw'>let</span> (<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>) <span class='op'>=</span> (<span class='ident'>insts</span>.<span class='ident'>len</span>(), <span class='ident'>num_captures</span>(<span class='kw-2'>&</span><span class='ident'>insts</span>)); + <span class='kw'>let</span> <span class='ident'>create_threads</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>NfaThreads</span>::<span class='ident'>new</span>(<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>); + <span class='kw'>let</span> <span class='ident'>create_backtrack</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>BackMachine</span>::<span class='ident'>new</span>(); + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>prog</span> <span class='op'>=</span> <span class='ident'>Program</span> { + <span class='ident'>original</span>: <span class='ident'>re</span>.<span class='ident'>into</span>(), + <span class='ident'>insts</span>: <span class='ident'>insts</span>, + <span class='ident'>cap_names</span>: <span class='ident'>cap_names</span>, + <span class='ident'>prefixes</span>: <span class='ident'>Prefix</span>::<span class='ident'>Empty</span>, + <span class='ident'>prefixes_complete</span>: <span class='boolval'>false</span>, + <span class='ident'>anchored_begin</span>: <span class='boolval'>false</span>, + <span class='ident'>anchored_end</span>: <span class='boolval'>false</span>, + <span class='ident'>engine</span>: <span class='ident'>engine</span>, + <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_threads</span>)), + <span class='ident'>backtrack</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_backtrack</span>)), + }; + + <span class='ident'>prog</span>.<span class='ident'>find_prefixes</span>(); + <span class='ident'>prog</span>.<span class='ident'>anchored_begin</span> <span class='op'>=</span> <span class='kw'>match</span> <span class='ident'>prog</span>.<span class='ident'>insts</span>[<span class='number'>1</span>] { + <span class='ident'>Inst</span>::<span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>::<span class='ident'>StartText</span>) <span class='op'>=></span> <span class='boolval'>true</span>, + _ <span class='op'>=></span> <span class='boolval'>false</span>, + }; + <span class='ident'>prog</span>.<span class='ident'>anchored_end</span> <span class='op'>=</span> <span class='kw'>match</span> <span class='ident'>prog</span>.<span class='ident'>insts</span>[<span class='ident'>prog</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>() <span class='op'>-</span> <span class='number'>3</span>] { + <span class='ident'>Inst</span>::<span class='ident'>EmptyLook</span>(<span class='ident'>LookInst</span>::<span class='ident'>EndText</span>) <span class='op'>=></span> <span class='boolval'>true</span>, + _ <span class='op'>=></span> <span class='boolval'>false</span>, + }; + <span class='prelude-val'>Ok</span>(<span class='ident'>prog</span>) + } + + <span class='doccomment'>/// Executes a compiled regex program.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>exec</span>( + <span class='kw-2'>&</span><span class='self'>self</span>, + <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>CaptureIdxs</span>, + <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, + <span class='ident'>start</span>: <span class='ident'>usize</span>, + ) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>choose_engine</span>(<span class='ident'>caps</span>.<span class='ident'>len</span>(), <span class='ident'>text</span>) { + <span class='ident'>MatchEngine</span>::<span class='ident'>Backtrack</span> <span class='op'>=></span> <span class='ident'>Backtrack</span>::<span class='ident'>exec</span>(<span class='self'>self</span>, <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>), + <span class='ident'>MatchEngine</span>::<span class='ident'>Nfa</span> <span class='op'>=></span> <span class='ident'>Nfa</span>::<span class='ident'>exec</span>(<span class='self'>self</span>, <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>), + <span class='ident'>MatchEngine</span>::<span class='ident'>Literals</span> <span class='op'>=></span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>find</span>(<span class='kw-2'>&</span><span class='ident'>text</span>[<span class='ident'>start</span>..]) { + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='boolval'>false</span>, + <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=></span> { + <span class='kw'>if</span> <span class='ident'>caps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>2</span> { + <span class='ident'>caps</span>[<span class='number'>0</span>] <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='ident'>start</span> <span class='op'>+</span> <span class='ident'>s</span>); + <span class='ident'>caps</span>[<span class='number'>1</span>] <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='ident'>start</span> <span class='op'>+</span> <span class='ident'>e</span>); + } + <span class='boolval'>true</span> + } + } + } + } + } + + <span class='kw'>fn</span> <span class='ident'>choose_engine</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>cap_len</span>: <span class='ident'>usize</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>MatchEngine</span> { + <span class='comment'>// If the engine is already chosen, then we use it.</span> + <span class='comment'>// But that might not be a good idea. e.g., What if `Literals` is</span> + <span class='comment'>// chosen and it can't work? I guess we should probably check whether</span> + <span class='comment'>// the chosen engine is appropriate or not.</span> + <span class='self'>self</span>.<span class='ident'>engine</span>.<span class='ident'>unwrap_or_else</span>(<span class='op'>||</span> { + <span class='kw'>if</span> <span class='ident'>cap_len</span> <span class='op'><=</span> <span class='number'>2</span> + <span class='op'>&&</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>preserves_priority</span>() + <span class='op'>&&</span> <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> { + <span class='ident'>MatchEngine</span>::<span class='ident'>Literals</span> + } <span class='kw'>else</span> <span class='kw'>if</span> <span class='ident'>Backtrack</span>::<span class='ident'>should_exec</span>(<span class='self'>self</span>, <span class='ident'>text</span>) { + <span class='comment'>// We're only here if the input and regex combined are small.</span> + <span class='ident'>MatchEngine</span>::<span class='ident'>Backtrack</span> + } <span class='kw'>else</span> { + <span class='ident'>MatchEngine</span>::<span class='ident'>Nfa</span> + } + }) + } + + <span class='doccomment'>/// Returns the total number of capture groups in the regular expression.</span> + <span class='doccomment'>/// This includes the zeroth capture.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>num_captures</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='ident'>num_captures</span>(<span class='kw-2'>&</span><span class='self'>self</span>.<span class='ident'>insts</span>) + } + + <span class='doccomment'>/// Allocate new capture groups.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>alloc_captures</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>Vec</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>>></span> { + <span class='macro'>vec</span><span class='macro'>!</span>[<span class='prelude-val'>None</span>; <span class='number'>2</span> <span class='op'>*</span> <span class='self'>self</span>.<span class='ident'>num_captures</span>()] + } + + <span class='doccomment'>/// Find and store a prefix machine for the current program.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>find_prefixes</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) { + <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>Inst</span>::<span class='op'>*</span>; + + <span class='kw'>let</span> (<span class='ident'>ps</span>, <span class='ident'>complete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='number'>1</span>); + <span class='kw'>if</span> <span class='ident'>ps</span>.<span class='ident'>len</span>() <span class='op'>></span> <span class='number'>0</span> { + <span class='self'>self</span>.<span class='ident'>prefixes</span> <span class='op'>=</span> <span class='ident'>Prefix</span>::<span class='ident'>new</span>(<span class='ident'>ps</span>); + <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> <span class='op'>=</span> <span class='ident'>complete</span>; + <span class='kw'>return</span>; + } + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='number'>1</span>; + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>prefixes</span> <span class='op'>=</span> <span class='macro'>vec</span><span class='macro'>!</span>[]; + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='boolval'>true</span>; + <span class='kw'>while</span> <span class='kw'>let</span> <span class='ident'>Split</span>(<span class='ident'>x</span>, <span class='ident'>y</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>] { + <span class='kw'>let</span> (<span class='ident'>xps</span>, <span class='ident'>xcomplete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='ident'>x</span>); + <span class='kw'>let</span> (<span class='ident'>yps</span>, <span class='ident'>ycomplete</span>) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>prefixes_from_insts</span>(<span class='ident'>y</span>); + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>done</span> <span class='op'>=</span> <span class='boolval'>false</span>; + <span class='kw'>match</span> (<span class='kw-2'>&</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>x</span>], <span class='kw-2'>&</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>y</span>]) { + <span class='comment'>// We should be able to support this. Add explicit stack. ---AG</span> + (<span class='kw-2'>&</span><span class='ident'>Split</span>(_, _), <span class='kw-2'>&</span><span class='ident'>Split</span>(_, _)) <span class='op'>=></span> <span class='kw'>return</span>, + (_, <span class='kw-2'>&</span><span class='ident'>Split</span>(_, _)) <span class='kw'>if</span> <span class='ident'>xps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=></span> <span class='kw'>return</span>, + (_, <span class='kw-2'>&</span><span class='ident'>Split</span>(_, _)) <span class='op'>=></span> { + <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&&</span> <span class='ident'>xcomplete</span>; + <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>xps</span>); + <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>y</span>; + } + (<span class='kw-2'>&</span><span class='ident'>Split</span>(_, _), _) <span class='kw'>if</span> <span class='ident'>yps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=></span> <span class='kw'>return</span>, + (<span class='kw-2'>&</span><span class='ident'>Split</span>(_, _), _) <span class='op'>=></span> { + <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&&</span> <span class='ident'>ycomplete</span>; + <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>yps</span>); + <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>x</span>; + } + _ <span class='kw'>if</span> <span class='ident'>xps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>||</span> <span class='ident'>yps</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> <span class='op'>=></span> <span class='kw'>return</span>, + <span class='comment'>// This is our base case. We've followed splits the whole</span> + <span class='comment'>// way, which means both instructions lead to a match.</span> + _ <span class='op'>=></span> { + <span class='ident'>pcomplete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&&</span> <span class='ident'>xcomplete</span> <span class='op'>&&</span> <span class='ident'>ycomplete</span>; + <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>xps</span>); + <span class='ident'>prefixes</span>.<span class='ident'>extend</span>(<span class='ident'>yps</span>); + <span class='ident'>done</span> <span class='op'>=</span> <span class='boolval'>true</span>; + } + } + <span class='comment'>// Arg. We've over-extended ourselves, quit with nothing to</span> + <span class='comment'>// show for it.</span> + <span class='kw'>if</span> <span class='ident'>prefixes</span>.<span class='ident'>len</span>() <span class='op'>></span> <span class='ident'>NUM_PREFIX_LIMIT</span> { + <span class='kw'>return</span>; + } + <span class='kw'>if</span> <span class='ident'>done</span> { <span class='kw'>break</span>; } + } + <span class='self'>self</span>.<span class='ident'>prefixes</span> <span class='op'>=</span> <span class='ident'>Prefix</span>::<span class='ident'>new</span>(<span class='ident'>prefixes</span>); + <span class='self'>self</span>.<span class='ident'>prefixes_complete</span> <span class='op'>=</span> <span class='ident'>pcomplete</span> <span class='op'>&&</span> <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>len</span>() <span class='op'>></span> <span class='number'>0</span>; + } + + <span class='doccomment'>/// Find a prefix starting at the given instruction.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Returns `true` in the tuple if the end of the prefix leads trivially</span> + <span class='doccomment'>/// to a match. (This may report false negatives, but being conservative</span> + <span class='doccomment'>/// is OK.)</span> + <span class='kw'>fn</span> <span class='ident'>prefixes_from_insts</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>pc</span>: <span class='ident'>usize</span>) <span class='op'>-></span> (<span class='ident'>Vec</span><span class='op'><</span><span class='ident'>String</span><span class='op'>></span>, <span class='ident'>bool</span>) { + <span class='kw'>use</span> <span class='self'>self</span>::<span class='ident'>Inst</span>::<span class='op'>*</span>; + + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>true</span>; + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>alts</span> <span class='op'>=</span> <span class='macro'>vec</span><span class='macro'>!</span>[<span class='ident'>String</span>::<span class='ident'>new</span>()]; + <span class='kw'>while</span> <span class='ident'>pc</span> <span class='op'><</span> <span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>() { + <span class='kw'>let</span> <span class='ident'>inst</span> <span class='op'>=</span> <span class='kw-2'>&</span><span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>]; + + <span class='comment'>// Each iteration adds one character to every alternate prefix *or*</span> + <span class='comment'>// it stops. Thus, the prefix alternates grow in lock step, and it</span> + <span class='comment'>// suffices to check one of them to see if the prefix limit has been</span> + <span class='comment'>// exceeded.</span> + <span class='kw'>if</span> <span class='ident'>alts</span>[<span class='number'>0</span>].<span class='ident'>len</span>() <span class='op'>></span> <span class='ident'>PREFIX_LENGTH_LIMIT</span> { + <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>false</span>; + <span class='kw'>break</span>; + } + <span class='kw'>match</span> <span class='op'>*</span><span class='ident'>inst</span> { + <span class='ident'>Save</span>(_) <span class='op'>=></span> { <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>; <span class='kw'>continue</span> } <span class='comment'>// completely ignore it</span> + <span class='ident'>Char</span>(<span class='ident'>OneChar</span> { <span class='ident'>c</span>, <span class='ident'>casei</span>: <span class='boolval'>false</span> }) <span class='op'>=></span> { + <span class='kw'>for</span> <span class='ident'>alt</span> <span class='kw'>in</span> <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>alts</span> { + <span class='ident'>alt</span>.<span class='ident'>push</span>(<span class='ident'>c</span>); + } + <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>; + } + <span class='ident'>Ranges</span>(<span class='ident'>CharRanges</span> { <span class='kw-2'>ref</span> <span class='ident'>ranges</span>, <span class='ident'>casei</span>: <span class='boolval'>false</span> }) <span class='op'>=></span> { + <span class='kw'>let</span> <span class='ident'>nchars</span> <span class='op'>=</span> <span class='ident'>num_chars_in_ranges</span>(<span class='ident'>ranges</span>); + <span class='kw'>if</span> <span class='ident'>alts</span>.<span class='ident'>len</span>() <span class='op'>*</span> <span class='ident'>nchars</span> <span class='op'>></span> <span class='ident'>NUM_PREFIX_LIMIT</span> { + <span class='ident'>complete</span> <span class='op'>=</span> <span class='boolval'>false</span>; + <span class='kw'>break</span>; + } + + <span class='kw'>let</span> <span class='ident'>orig</span> <span class='op'>=</span> <span class='ident'>alts</span>; + <span class='ident'>alts</span> <span class='op'>=</span> <span class='ident'>Vec</span>::<span class='ident'>with_capacity</span>(<span class='ident'>orig</span>.<span class='ident'>len</span>()); + <span class='kw'>for</span> <span class='kw-2'>&</span>(<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='kw'>in</span> <span class='ident'>ranges</span> { + <span class='kw'>for</span> <span class='ident'>c</span> <span class='kw'>in</span> (<span class='ident'>s</span> <span class='kw'>as</span> <span class='ident'>u32</span>)..(<span class='ident'>e</span> <span class='kw'>as</span> <span class='ident'>u32</span> <span class='op'>+</span> <span class='number'>1</span>){ + <span class='kw'>for</span> <span class='ident'>alt</span> <span class='kw'>in</span> <span class='kw-2'>&</span><span class='ident'>orig</span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>alt</span> <span class='op'>=</span> <span class='ident'>alt</span>.<span class='ident'>clone</span>(); + <span class='ident'>alt</span>.<span class='ident'>push</span>(::<span class='ident'>std</span>::<span class='ident'>char</span>::<span class='ident'>from_u32</span>(<span class='ident'>c</span>).<span class='ident'>unwrap</span>()); + <span class='ident'>alts</span>.<span class='ident'>push</span>(<span class='ident'>alt</span>); + } + } + } + <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>; + } + <span class='ident'>Jump</span>(<span class='ident'>pc2</span>) <span class='op'>=></span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>pc2</span>, + _ <span class='op'>=></span> { <span class='ident'>complete</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>leads_to_match</span>(<span class='ident'>pc</span>); <span class='kw'>break</span> } + } + } + <span class='kw'>if</span> <span class='ident'>alts</span>[<span class='number'>0</span>].<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> { + (<span class='macro'>vec</span><span class='macro'>!</span>[], <span class='boolval'>false</span>) + } <span class='kw'>else</span> { + (<span class='ident'>alts</span>, <span class='ident'>complete</span>) + } + } + + <span class='kw'>fn</span> <span class='ident'>leads_to_match</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='kw-2'>mut</span> <span class='ident'>pc</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='comment'>// I'm pretty sure this is conservative, so it might have some</span> + <span class='comment'>// false negatives.</span> + <span class='kw'>loop</span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>insts</span>[<span class='ident'>pc</span>] { + <span class='ident'>Inst</span>::<span class='ident'>Match</span> <span class='op'>=></span> <span class='kw'>return</span> <span class='boolval'>true</span>, + <span class='ident'>Inst</span>::<span class='ident'>Save</span>(_) <span class='op'>=></span> <span class='ident'>pc</span> <span class='op'>+=</span> <span class='number'>1</span>, + <span class='ident'>Inst</span>::<span class='ident'>Jump</span>(<span class='ident'>pc2</span>) <span class='op'>=></span> <span class='ident'>pc</span> <span class='op'>=</span> <span class='ident'>pc2</span>, + _ <span class='op'>=></span> <span class='kw'>return</span> <span class='boolval'>false</span>, + } + } + } +} + +<span class='kw'>impl</span> <span class='ident'>Clone</span> <span class='kw'>for</span> <span class='ident'>Program</span> { + <span class='kw'>fn</span> <span class='ident'>clone</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>Program</span> { + <span class='kw'>let</span> (<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>) <span class='op'>=</span> (<span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>len</span>(), <span class='self'>self</span>.<span class='ident'>num_captures</span>()); + <span class='kw'>let</span> <span class='ident'>create_threads</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>NfaThreads</span>::<span class='ident'>new</span>(<span class='ident'>insts_len</span>, <span class='ident'>ncaps</span>); + <span class='kw'>let</span> <span class='ident'>create_backtrack</span> <span class='op'>=</span> <span class='kw'>move</span> <span class='op'>||</span> <span class='ident'>BackMachine</span>::<span class='ident'>new</span>(); + <span class='ident'>Program</span> { + <span class='ident'>original</span>: <span class='self'>self</span>.<span class='ident'>original</span>.<span class='ident'>clone</span>(), + <span class='ident'>insts</span>: <span class='self'>self</span>.<span class='ident'>insts</span>.<span class='ident'>clone</span>(), + <span class='ident'>cap_names</span>: <span class='self'>self</span>.<span class='ident'>cap_names</span>.<span class='ident'>clone</span>(), + <span class='ident'>prefixes</span>: <span class='self'>self</span>.<span class='ident'>prefixes</span>.<span class='ident'>clone</span>(), + <span class='ident'>prefixes_complete</span>: <span class='self'>self</span>.<span class='ident'>prefixes_complete</span>, + <span class='ident'>anchored_begin</span>: <span class='self'>self</span>.<span class='ident'>anchored_begin</span>, + <span class='ident'>anchored_end</span>: <span class='self'>self</span>.<span class='ident'>anchored_end</span>, + <span class='ident'>engine</span>: <span class='self'>self</span>.<span class='ident'>engine</span>, + <span class='ident'>nfa_threads</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_threads</span>)), + <span class='ident'>backtrack</span>: <span class='ident'>Pool</span>::<span class='ident'>new</span>(<span class='ident'>Box</span>::<span class='ident'>new</span>(<span class='ident'>create_backtrack</span>)), + } + } +} + +<span class='doccomment'>/// Return the number of captures in the given sequence of instructions.</span> +<span class='kw'>fn</span> <span class='ident'>num_captures</span>(<span class='ident'>insts</span>: <span class='kw-2'>&</span>[<span class='ident'>Inst</span>]) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>n</span> <span class='op'>=</span> <span class='number'>0</span>; + <span class='kw'>for</span> <span class='ident'>inst</span> <span class='kw'>in</span> <span class='ident'>insts</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='ident'>inst</span> { + <span class='ident'>Inst</span>::<span class='ident'>Save</span>(<span class='ident'>c</span>) <span class='op'>=></span> <span class='ident'>n</span> <span class='op'>=</span> <span class='ident'>cmp</span>::<span class='ident'>max</span>(<span class='ident'>n</span>, <span class='ident'>c</span><span class='op'>+</span><span class='number'>1</span>), + _ <span class='op'>=></span> {} + } + } + <span class='comment'>// There's exactly 2 Save slots for every capture.</span> + <span class='ident'>n</span> <span class='op'>/</span> <span class='number'>2</span> +} + +<span class='doccomment'>/// Count the number of characters in the given range.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// This is useful for pre-emptively limiting the number of prefix literals</span> +<span class='doccomment'>/// we extract from a regex program.</span> +<span class='kw'>fn</span> <span class='ident'>num_chars_in_ranges</span>(<span class='ident'>ranges</span>: <span class='kw-2'>&</span>[(<span class='ident'>char</span>, <span class='ident'>char</span>)]) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='ident'>ranges</span>.<span class='ident'>iter</span>() + .<span class='ident'>map</span>(<span class='op'>|</span><span class='kw-2'>&</span>(<span class='ident'>s</span>, <span class='ident'>e</span>)<span class='op'>|</span> (<span class='ident'>e</span> <span class='kw'>as</span> <span class='ident'>u32</span>) <span class='op'>-</span> (<span class='ident'>s</span> <span class='kw'>as</span> <span class='ident'>u32</span>)) + .<span class='ident'>fold</span>(<span class='number'>0</span>, <span class='op'>|</span><span class='ident'>acc</span>, <span class='ident'>len</span><span class='op'>|</span> <span class='ident'>acc</span> <span class='op'>+</span> <span class='ident'>len</span>) <span class='kw'>as</span> <span class='ident'>usize</span> +} +</pre> +</section> + <section id='search' class="content hidden"></section> + + <section class="footer"></section> + + <div id="help" class="hidden"> + <div class="shortcuts"> + <h1>Keyboard shortcuts</h1> + <dl> + <dt>?</dt> + <dd>Show this help dialog</dd> + <dt>S</dt> + <dd>Focus the search field</dd> + <dt>⇤</dt> + <dd>Move up in search results</dd> + <dt>⇥</dt> + <dd>Move down in search results</dd> + <dt>⏎</dt> + <dd>Go to active search result</dd> + </dl> + </div> + <div class="infos"> + <h1>Search tricks</h1> + <p> + Prefix searches with a type followed by a colon (e.g. + <code>fn:</code>) to restrict the search to a given type. + </p> + <p> + Accepted types are: <code>fn</code>, <code>mod</code>, + <code>struct</code>, <code>enum</code>, + <code>trait</code>, <code>typedef</code> (or + <code>tdef</code>). + </p> + <p> + Search functions by type signature (e.g. + <code>vec -> usize</code>) + </p> + </div> + </div> + + + + <script> + window.rootPath = "../../"; + window.currentCrate = "regex"; + window.playgroundUrl = ""; + </script> + <script src="../../jquery.js"></script> + <script src="../../main.js"></script> + + <script async src="../../search-index.js"></script> +</body> +</html>
\ No newline at end of file diff --git a/src/regex/re.rs.html b/src/regex/re.rs.html new file mode 100644 index 0000000..3472b45 --- /dev/null +++ b/src/regex/re.rs.html @@ -0,0 +1,2393 @@ +<!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 to the Rust file `/home/travis/.cargo/registry/src/github.com-0a35038f75765ae4/regex-0.1.38/src/re.rs`."> + <meta name="keywords" content="rust, rustlang, rust-lang"> + + <title>re.rs.html -- source</title> + + <link rel="stylesheet" type="text/css" href="../../main.css"> + + <link rel="shortcut icon" href="http://www.rust-lang.org/favicon.ico"> + +</head> +<body class="rustdoc"> + <!--[if lte IE 8]> + <div class="warning"> + This old browser is unsupported and will most likely display funky + things. + </div> + <![endif]--> + + + + <section class="sidebar"> + <a href='../../regex/index.html'><img src='http://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='' width='100'></a> + + </section> + + <nav class="sub"> + <form class="search-form js-only"> + <div class="search-container"> + <input class="search-input" name="search" + autocomplete="off" + placeholder="Click or press 'S' to search, '?' for more options..." + type="search"> + </div> + </form> + </nav> + + <section id='main' class="content source"><pre class="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> +<span id="230"> 230</span> +<span id="231"> 231</span> +<span id="232"> 232</span> +<span id="233"> 233</span> +<span id="234"> 234</span> +<span id="235"> 235</span> +<span id="236"> 236</span> +<span id="237"> 237</span> +<span id="238"> 238</span> +<span id="239"> 239</span> +<span id="240"> 240</span> +<span id="241"> 241</span> +<span id="242"> 242</span> +<span id="243"> 243</span> +<span id="244"> 244</span> +<span id="245"> 245</span> +<span id="246"> 246</span> +<span id="247"> 247</span> +<span id="248"> 248</span> +<span id="249"> 249</span> +<span id="250"> 250</span> +<span id="251"> 251</span> +<span id="252"> 252</span> +<span id="253"> 253</span> +<span id="254"> 254</span> +<span id="255"> 255</span> +<span id="256"> 256</span> +<span id="257"> 257</span> +<span id="258"> 258</span> +<span id="259"> 259</span> +<span id="260"> 260</span> +<span id="261"> 261</span> +<span id="262"> 262</span> +<span id="263"> 263</span> +<span id="264"> 264</span> +<span id="265"> 265</span> +<span id="266"> 266</span> +<span id="267"> 267</span> +<span id="268"> 268</span> +<span id="269"> 269</span> +<span id="270"> 270</span> +<span id="271"> 271</span> +<span id="272"> 272</span> +<span id="273"> 273</span> +<span id="274"> 274</span> +<span id="275"> 275</span> +<span id="276"> 276</span> +<span id="277"> 277</span> +<span id="278"> 278</span> +<span id="279"> 279</span> +<span id="280"> 280</span> +<span id="281"> 281</span> +<span id="282"> 282</span> +<span id="283"> 283</span> +<span id="284"> 284</span> +<span id="285"> 285</span> +<span id="286"> 286</span> +<span id="287"> 287</span> +<span id="288"> 288</span> +<span id="289"> 289</span> +<span id="290"> 290</span> +<span id="291"> 291</span> +<span id="292"> 292</span> +<span id="293"> 293</span> +<span id="294"> 294</span> +<span id="295"> 295</span> +<span id="296"> 296</span> +<span id="297"> 297</span> +<span id="298"> 298</span> +<span id="299"> 299</span> +<span id="300"> 300</span> +<span id="301"> 301</span> +<span id="302"> 302</span> +<span id="303"> 303</span> +<span id="304"> 304</span> +<span id="305"> 305</span> +<span id="306"> 306</span> +<span id="307"> 307</span> +<span id="308"> 308</span> +<span id="309"> 309</span> +<span id="310"> 310</span> +<span id="311"> 311</span> +<span id="312"> 312</span> +<span id="313"> 313</span> +<span id="314"> 314</span> +<span id="315"> 315</span> +<span id="316"> 316</span> +<span id="317"> 317</span> +<span id="318"> 318</span> +<span id="319"> 319</span> +<span id="320"> 320</span> +<span id="321"> 321</span> +<span id="322"> 322</span> +<span id="323"> 323</span> +<span id="324"> 324</span> +<span id="325"> 325</span> +<span id="326"> 326</span> +<span id="327"> 327</span> +<span id="328"> 328</span> +<span id="329"> 329</span> +<span id="330"> 330</span> +<span id="331"> 331</span> +<span id="332"> 332</span> +<span id="333"> 333</span> +<span id="334"> 334</span> +<span id="335"> 335</span> +<span id="336"> 336</span> +<span id="337"> 337</span> +<span id="338"> 338</span> +<span id="339"> 339</span> +<span id="340"> 340</span> +<span id="341"> 341</span> +<span id="342"> 342</span> +<span id="343"> 343</span> +<span id="344"> 344</span> +<span id="345"> 345</span> +<span id="346"> 346</span> +<span id="347"> 347</span> +<span id="348"> 348</span> +<span id="349"> 349</span> +<span id="350"> 350</span> +<span id="351"> 351</span> +<span id="352"> 352</span> +<span id="353"> 353</span> +<span id="354"> 354</span> +<span id="355"> 355</span> +<span id="356"> 356</span> +<span id="357"> 357</span> +<span id="358"> 358</span> +<span id="359"> 359</span> +<span id="360"> 360</span> +<span id="361"> 361</span> +<span id="362"> 362</span> +<span id="363"> 363</span> +<span id="364"> 364</span> +<span id="365"> 365</span> +<span id="366"> 366</span> +<span id="367"> 367</span> +<span id="368"> 368</span> +<span id="369"> 369</span> +<span id="370"> 370</span> +<span id="371"> 371</span> +<span id="372"> 372</span> +<span id="373"> 373</span> +<span id="374"> 374</span> +<span id="375"> 375</span> +<span id="376"> 376</span> +<span id="377"> 377</span> +<span id="378"> 378</span> +<span id="379"> 379</span> +<span id="380"> 380</span> +<span id="381"> 381</span> +<span id="382"> 382</span> +<span id="383"> 383</span> +<span id="384"> 384</span> +<span id="385"> 385</span> +<span id="386"> 386</span> +<span id="387"> 387</span> +<span id="388"> 388</span> +<span id="389"> 389</span> +<span id="390"> 390</span> +<span id="391"> 391</span> +<span id="392"> 392</span> +<span id="393"> 393</span> +<span id="394"> 394</span> +<span id="395"> 395</span> +<span id="396"> 396</span> +<span id="397"> 397</span> +<span id="398"> 398</span> +<span id="399"> 399</span> +<span id="400"> 400</span> +<span id="401"> 401</span> +<span id="402"> 402</span> +<span id="403"> 403</span> +<span id="404"> 404</span> +<span id="405"> 405</span> +<span id="406"> 406</span> +<span id="407"> 407</span> +<span id="408"> 408</span> +<span id="409"> 409</span> +<span id="410"> 410</span> +<span id="411"> 411</span> +<span id="412"> 412</span> +<span id="413"> 413</span> +<span id="414"> 414</span> +<span id="415"> 415</span> +<span id="416"> 416</span> +<span id="417"> 417</span> +<span id="418"> 418</span> +<span id="419"> 419</span> +<span id="420"> 420</span> +<span id="421"> 421</span> +<span id="422"> 422</span> +<span id="423"> 423</span> +<span id="424"> 424</span> +<span id="425"> 425</span> +<span id="426"> 426</span> +<span id="427"> 427</span> +<span id="428"> 428</span> +<span id="429"> 429</span> +<span id="430"> 430</span> +<span id="431"> 431</span> +<span id="432"> 432</span> +<span id="433"> 433</span> +<span id="434"> 434</span> +<span id="435"> 435</span> +<span id="436"> 436</span> +<span id="437"> 437</span> +<span id="438"> 438</span> +<span id="439"> 439</span> +<span id="440"> 440</span> +<span id="441"> 441</span> +<span id="442"> 442</span> +<span id="443"> 443</span> +<span id="444"> 444</span> +<span id="445"> 445</span> +<span id="446"> 446</span> +<span id="447"> 447</span> +<span id="448"> 448</span> +<span id="449"> 449</span> +<span id="450"> 450</span> +<span id="451"> 451</span> +<span id="452"> 452</span> +<span id="453"> 453</span> +<span id="454"> 454</span> +<span id="455"> 455</span> +<span id="456"> 456</span> +<span id="457"> 457</span> +<span id="458"> 458</span> +<span id="459"> 459</span> +<span id="460"> 460</span> +<span id="461"> 461</span> +<span id="462"> 462</span> +<span id="463"> 463</span> +<span id="464"> 464</span> +<span id="465"> 465</span> +<span id="466"> 466</span> +<span id="467"> 467</span> +<span id="468"> 468</span> +<span id="469"> 469</span> +<span id="470"> 470</span> +<span id="471"> 471</span> +<span id="472"> 472</span> +<span id="473"> 473</span> +<span id="474"> 474</span> +<span id="475"> 475</span> +<span id="476"> 476</span> +<span id="477"> 477</span> +<span id="478"> 478</span> +<span id="479"> 479</span> +<span id="480"> 480</span> +<span id="481"> 481</span> +<span id="482"> 482</span> +<span id="483"> 483</span> +<span id="484"> 484</span> +<span id="485"> 485</span> +<span id="486"> 486</span> +<span id="487"> 487</span> +<span id="488"> 488</span> +<span id="489"> 489</span> +<span id="490"> 490</span> +<span id="491"> 491</span> +<span id="492"> 492</span> +<span id="493"> 493</span> +<span id="494"> 494</span> +<span id="495"> 495</span> +<span id="496"> 496</span> +<span id="497"> 497</span> +<span id="498"> 498</span> +<span id="499"> 499</span> +<span id="500"> 500</span> +<span id="501"> 501</span> +<span id="502"> 502</span> +<span id="503"> 503</span> +<span id="504"> 504</span> +<span id="505"> 505</span> +<span id="506"> 506</span> +<span id="507"> 507</span> +<span id="508"> 508</span> +<span id="509"> 509</span> +<span id="510"> 510</span> +<span id="511"> 511</span> +<span id="512"> 512</span> +<span id="513"> 513</span> +<span id="514"> 514</span> +<span id="515"> 515</span> +<span id="516"> 516</span> +<span id="517"> 517</span> +<span id="518"> 518</span> +<span id="519"> 519</span> +<span id="520"> 520</span> +<span id="521"> 521</span> +<span id="522"> 522</span> +<span id="523"> 523</span> +<span id="524"> 524</span> +<span id="525"> 525</span> +<span id="526"> 526</span> +<span id="527"> 527</span> +<span id="528"> 528</span> +<span id="529"> 529</span> +<span id="530"> 530</span> +<span id="531"> 531</span> +<span id="532"> 532</span> +<span id="533"> 533</span> +<span id="534"> 534</span> +<span id="535"> 535</span> +<span id="536"> 536</span> +<span id="537"> 537</span> +<span id="538"> 538</span> +<span id="539"> 539</span> +<span id="540"> 540</span> +<span id="541"> 541</span> +<span id="542"> 542</span> +<span id="543"> 543</span> +<span id="544"> 544</span> +<span id="545"> 545</span> +<span id="546"> 546</span> +<span id="547"> 547</span> +<span id="548"> 548</span> +<span id="549"> 549</span> +<span id="550"> 550</span> +<span id="551"> 551</span> +<span id="552"> 552</span> +<span id="553"> 553</span> +<span id="554"> 554</span> +<span id="555"> 555</span> +<span id="556"> 556</span> +<span id="557"> 557</span> +<span id="558"> 558</span> +<span id="559"> 559</span> +<span id="560"> 560</span> +<span id="561"> 561</span> +<span id="562"> 562</span> +<span id="563"> 563</span> +<span id="564"> 564</span> +<span id="565"> 565</span> +<span id="566"> 566</span> +<span id="567"> 567</span> +<span id="568"> 568</span> +<span id="569"> 569</span> +<span id="570"> 570</span> +<span id="571"> 571</span> +<span id="572"> 572</span> +<span id="573"> 573</span> +<span id="574"> 574</span> +<span id="575"> 575</span> +<span id="576"> 576</span> +<span id="577"> 577</span> +<span id="578"> 578</span> +<span id="579"> 579</span> +<span id="580"> 580</span> +<span id="581"> 581</span> +<span id="582"> 582</span> +<span id="583"> 583</span> +<span id="584"> 584</span> +<span id="585"> 585</span> +<span id="586"> 586</span> +<span id="587"> 587</span> +<span id="588"> 588</span> +<span id="589"> 589</span> +<span id="590"> 590</span> +<span id="591"> 591</span> +<span id="592"> 592</span> +<span id="593"> 593</span> +<span id="594"> 594</span> +<span id="595"> 595</span> +<span id="596"> 596</span> +<span id="597"> 597</span> +<span id="598"> 598</span> +<span id="599"> 599</span> +<span id="600"> 600</span> +<span id="601"> 601</span> +<span id="602"> 602</span> +<span id="603"> 603</span> +<span id="604"> 604</span> +<span id="605"> 605</span> +<span id="606"> 606</span> +<span id="607"> 607</span> +<span id="608"> 608</span> +<span id="609"> 609</span> +<span id="610"> 610</span> +<span id="611"> 611</span> +<span id="612"> 612</span> +<span id="613"> 613</span> +<span id="614"> 614</span> +<span id="615"> 615</span> +<span id="616"> 616</span> +<span id="617"> 617</span> +<span id="618"> 618</span> +<span id="619"> 619</span> +<span id="620"> 620</span> +<span id="621"> 621</span> +<span id="622"> 622</span> +<span id="623"> 623</span> +<span id="624"> 624</span> +<span id="625"> 625</span> +<span id="626"> 626</span> +<span id="627"> 627</span> +<span id="628"> 628</span> +<span id="629"> 629</span> +<span id="630"> 630</span> +<span id="631"> 631</span> +<span id="632"> 632</span> +<span id="633"> 633</span> +<span id="634"> 634</span> +<span id="635"> 635</span> +<span id="636"> 636</span> +<span id="637"> 637</span> +<span id="638"> 638</span> +<span id="639"> 639</span> +<span id="640"> 640</span> +<span id="641"> 641</span> +<span id="642"> 642</span> +<span id="643"> 643</span> +<span id="644"> 644</span> +<span id="645"> 645</span> +<span id="646"> 646</span> +<span id="647"> 647</span> +<span id="648"> 648</span> +<span id="649"> 649</span> +<span id="650"> 650</span> +<span id="651"> 651</span> +<span id="652"> 652</span> +<span id="653"> 653</span> +<span id="654"> 654</span> +<span id="655"> 655</span> +<span id="656"> 656</span> +<span id="657"> 657</span> +<span id="658"> 658</span> +<span id="659"> 659</span> +<span id="660"> 660</span> +<span id="661"> 661</span> +<span id="662"> 662</span> +<span id="663"> 663</span> +<span id="664"> 664</span> +<span id="665"> 665</span> +<span id="666"> 666</span> +<span id="667"> 667</span> +<span id="668"> 668</span> +<span id="669"> 669</span> +<span id="670"> 670</span> +<span id="671"> 671</span> +<span id="672"> 672</span> +<span id="673"> 673</span> +<span id="674"> 674</span> +<span id="675"> 675</span> +<span id="676"> 676</span> +<span id="677"> 677</span> +<span id="678"> 678</span> +<span id="679"> 679</span> +<span id="680"> 680</span> +<span id="681"> 681</span> +<span id="682"> 682</span> +<span id="683"> 683</span> +<span id="684"> 684</span> +<span id="685"> 685</span> +<span id="686"> 686</span> +<span id="687"> 687</span> +<span id="688"> 688</span> +<span id="689"> 689</span> +<span id="690"> 690</span> +<span id="691"> 691</span> +<span id="692"> 692</span> +<span id="693"> 693</span> +<span id="694"> 694</span> +<span id="695"> 695</span> +<span id="696"> 696</span> +<span id="697"> 697</span> +<span id="698"> 698</span> +<span id="699"> 699</span> +<span id="700"> 700</span> +<span id="701"> 701</span> +<span id="702"> 702</span> +<span id="703"> 703</span> +<span id="704"> 704</span> +<span id="705"> 705</span> +<span id="706"> 706</span> +<span id="707"> 707</span> +<span id="708"> 708</span> +<span id="709"> 709</span> +<span id="710"> 710</span> +<span id="711"> 711</span> +<span id="712"> 712</span> +<span id="713"> 713</span> +<span id="714"> 714</span> +<span id="715"> 715</span> +<span id="716"> 716</span> +<span id="717"> 717</span> +<span id="718"> 718</span> +<span id="719"> 719</span> +<span id="720"> 720</span> +<span id="721"> 721</span> +<span id="722"> 722</span> +<span id="723"> 723</span> +<span id="724"> 724</span> +<span id="725"> 725</span> +<span id="726"> 726</span> +<span id="727"> 727</span> +<span id="728"> 728</span> +<span id="729"> 729</span> +<span id="730"> 730</span> +<span id="731"> 731</span> +<span id="732"> 732</span> +<span id="733"> 733</span> +<span id="734"> 734</span> +<span id="735"> 735</span> +<span id="736"> 736</span> +<span id="737"> 737</span> +<span id="738"> 738</span> +<span id="739"> 739</span> +<span id="740"> 740</span> +<span id="741"> 741</span> +<span id="742"> 742</span> +<span id="743"> 743</span> +<span id="744"> 744</span> +<span id="745"> 745</span> +<span id="746"> 746</span> +<span id="747"> 747</span> +<span id="748"> 748</span> +<span id="749"> 749</span> +<span id="750"> 750</span> +<span id="751"> 751</span> +<span id="752"> 752</span> +<span id="753"> 753</span> +<span id="754"> 754</span> +<span id="755"> 755</span> +<span id="756"> 756</span> +<span id="757"> 757</span> +<span id="758"> 758</span> +<span id="759"> 759</span> +<span id="760"> 760</span> +<span id="761"> 761</span> +<span id="762"> 762</span> +<span id="763"> 763</span> +<span id="764"> 764</span> +<span id="765"> 765</span> +<span id="766"> 766</span> +<span id="767"> 767</span> +<span id="768"> 768</span> +<span id="769"> 769</span> +<span id="770"> 770</span> +<span id="771"> 771</span> +<span id="772"> 772</span> +<span id="773"> 773</span> +<span id="774"> 774</span> +<span id="775"> 775</span> +<span id="776"> 776</span> +<span id="777"> 777</span> +<span id="778"> 778</span> +<span id="779"> 779</span> +<span id="780"> 780</span> +<span id="781"> 781</span> +<span id="782"> 782</span> +<span id="783"> 783</span> +<span id="784"> 784</span> +<span id="785"> 785</span> +<span id="786"> 786</span> +<span id="787"> 787</span> +<span id="788"> 788</span> +<span id="789"> 789</span> +<span id="790"> 790</span> +<span id="791"> 791</span> +<span id="792"> 792</span> +<span id="793"> 793</span> +<span id="794"> 794</span> +<span id="795"> 795</span> +<span id="796"> 796</span> +<span id="797"> 797</span> +<span id="798"> 798</span> +<span id="799"> 799</span> +<span id="800"> 800</span> +<span id="801"> 801</span> +<span id="802"> 802</span> +<span id="803"> 803</span> +<span id="804"> 804</span> +<span id="805"> 805</span> +<span id="806"> 806</span> +<span id="807"> 807</span> +<span id="808"> 808</span> +<span id="809"> 809</span> +<span id="810"> 810</span> +<span id="811"> 811</span> +<span id="812"> 812</span> +<span id="813"> 813</span> +<span id="814"> 814</span> +<span id="815"> 815</span> +<span id="816"> 816</span> +<span id="817"> 817</span> +<span id="818"> 818</span> +<span id="819"> 819</span> +<span id="820"> 820</span> +<span id="821"> 821</span> +<span id="822"> 822</span> +<span id="823"> 823</span> +<span id="824"> 824</span> +<span id="825"> 825</span> +<span id="826"> 826</span> +<span id="827"> 827</span> +<span id="828"> 828</span> +<span id="829"> 829</span> +<span id="830"> 830</span> +<span id="831"> 831</span> +<span id="832"> 832</span> +<span id="833"> 833</span> +<span id="834"> 834</span> +<span id="835"> 835</span> +<span id="836"> 836</span> +<span id="837"> 837</span> +<span id="838"> 838</span> +<span id="839"> 839</span> +<span id="840"> 840</span> +<span id="841"> 841</span> +<span id="842"> 842</span> +<span id="843"> 843</span> +<span id="844"> 844</span> +<span id="845"> 845</span> +<span id="846"> 846</span> +<span id="847"> 847</span> +<span id="848"> 848</span> +<span id="849"> 849</span> +<span id="850"> 850</span> +<span id="851"> 851</span> +<span id="852"> 852</span> +<span id="853"> 853</span> +<span id="854"> 854</span> +<span id="855"> 855</span> +<span id="856"> 856</span> +<span id="857"> 857</span> +<span id="858"> 858</span> +<span id="859"> 859</span> +<span id="860"> 860</span> +<span id="861"> 861</span> +<span id="862"> 862</span> +<span id="863"> 863</span> +<span id="864"> 864</span> +<span id="865"> 865</span> +<span id="866"> 866</span> +<span id="867"> 867</span> +<span id="868"> 868</span> +<span id="869"> 869</span> +<span id="870"> 870</span> +<span id="871"> 871</span> +<span id="872"> 872</span> +<span id="873"> 873</span> +<span id="874"> 874</span> +<span id="875"> 875</span> +<span id="876"> 876</span> +<span id="877"> 877</span> +<span id="878"> 878</span> +<span id="879"> 879</span> +<span id="880"> 880</span> +<span id="881"> 881</span> +<span id="882"> 882</span> +<span id="883"> 883</span> +<span id="884"> 884</span> +<span id="885"> 885</span> +<span id="886"> 886</span> +<span id="887"> 887</span> +<span id="888"> 888</span> +<span id="889"> 889</span> +<span id="890"> 890</span> +<span id="891"> 891</span> +<span id="892"> 892</span> +<span id="893"> 893</span> +<span id="894"> 894</span> +<span id="895"> 895</span> +<span id="896"> 896</span> +<span id="897"> 897</span> +<span id="898"> 898</span> +<span id="899"> 899</span> +<span id="900"> 900</span> +<span id="901"> 901</span> +<span id="902"> 902</span> +<span id="903"> 903</span> +<span id="904"> 904</span> +<span id="905"> 905</span> +<span id="906"> 906</span> +<span id="907"> 907</span> +<span id="908"> 908</span> +<span id="909"> 909</span> +<span id="910"> 910</span> +<span id="911"> 911</span> +<span id="912"> 912</span> +<span id="913"> 913</span> +<span id="914"> 914</span> +<span id="915"> 915</span> +<span id="916"> 916</span> +<span id="917"> 917</span> +<span id="918"> 918</span> +<span id="919"> 919</span> +<span id="920"> 920</span> +<span id="921"> 921</span> +<span id="922"> 922</span> +<span id="923"> 923</span> +<span id="924"> 924</span> +<span id="925"> 925</span> +<span id="926"> 926</span> +<span id="927"> 927</span> +<span id="928"> 928</span> +<span id="929"> 929</span> +<span id="930"> 930</span> +<span id="931"> 931</span> +<span id="932"> 932</span> +<span id="933"> 933</span> +<span id="934"> 934</span> +<span id="935"> 935</span> +<span id="936"> 936</span> +<span id="937"> 937</span> +<span id="938"> 938</span> +<span id="939"> 939</span> +<span id="940"> 940</span> +<span id="941"> 941</span> +<span id="942"> 942</span> +<span id="943"> 943</span> +<span id="944"> 944</span> +<span id="945"> 945</span> +<span id="946"> 946</span> +<span id="947"> 947</span> +<span id="948"> 948</span> +<span id="949"> 949</span> +<span id="950"> 950</span> +<span id="951"> 951</span> +<span id="952"> 952</span> +<span id="953"> 953</span> +<span id="954"> 954</span> +<span id="955"> 955</span> +<span id="956"> 956</span> +<span id="957"> 957</span> +<span id="958"> 958</span> +<span id="959"> 959</span> +<span id="960"> 960</span> +<span id="961"> 961</span> +<span id="962"> 962</span> +<span id="963"> 963</span> +<span id="964"> 964</span> +<span id="965"> 965</span> +<span id="966"> 966</span> +<span id="967"> 967</span> +<span id="968"> 968</span> +<span id="969"> 969</span> +<span id="970"> 970</span> +<span id="971"> 971</span> +<span id="972"> 972</span> +<span id="973"> 973</span> +<span id="974"> 974</span> +<span id="975"> 975</span> +<span id="976"> 976</span> +<span id="977"> 977</span> +<span id="978"> 978</span> +<span id="979"> 979</span> +<span id="980"> 980</span> +<span id="981"> 981</span> +<span id="982"> 982</span> +<span id="983"> 983</span> +<span id="984"> 984</span> +<span id="985"> 985</span> +<span id="986"> 986</span> +<span id="987"> 987</span> +<span id="988"> 988</span> +<span id="989"> 989</span> +<span id="990"> 990</span> +<span id="991"> 991</span> +<span id="992"> 992</span> +<span id="993"> 993</span> +<span id="994"> 994</span> +<span id="995"> 995</span> +<span id="996"> 996</span> +<span id="997"> 997</span> +<span id="998"> 998</span> +<span id="999"> 999</span> +<span id="1000">1000</span> +<span id="1001">1001</span> +<span id="1002">1002</span> +<span id="1003">1003</span> +<span id="1004">1004</span> +<span id="1005">1005</span> +<span id="1006">1006</span> +<span id="1007">1007</span> +<span id="1008">1008</span> +<span id="1009">1009</span> +<span id="1010">1010</span> +<span id="1011">1011</span> +<span id="1012">1012</span> +<span id="1013">1013</span> +<span id="1014">1014</span> +<span id="1015">1015</span> +<span id="1016">1016</span> +<span id="1017">1017</span> +<span id="1018">1018</span> +<span id="1019">1019</span> +<span id="1020">1020</span> +<span id="1021">1021</span> +<span id="1022">1022</span> +<span id="1023">1023</span> +<span id="1024">1024</span> +<span id="1025">1025</span> +<span id="1026">1026</span> +<span id="1027">1027</span> +<span id="1028">1028</span> +<span id="1029">1029</span> +<span id="1030">1030</span> +<span id="1031">1031</span> +<span id="1032">1032</span> +<span id="1033">1033</span> +<span id="1034">1034</span> +<span id="1035">1035</span> +<span id="1036">1036</span> +<span id="1037">1037</span> +<span id="1038">1038</span> +<span id="1039">1039</span> +<span id="1040">1040</span> +<span id="1041">1041</span> +<span id="1042">1042</span> +<span id="1043">1043</span> +<span id="1044">1044</span> +<span id="1045">1045</span> +<span id="1046">1046</span> +<span id="1047">1047</span> +<span id="1048">1048</span> +<span id="1049">1049</span> +<span id="1050">1050</span> +<span id="1051">1051</span> +<span id="1052">1052</span> +<span id="1053">1053</span> +<span id="1054">1054</span> +<span id="1055">1055</span> +<span id="1056">1056</span> +<span id="1057">1057</span> +<span id="1058">1058</span> +<span id="1059">1059</span> +<span id="1060">1060</span> +<span id="1061">1061</span> +<span id="1062">1062</span> +<span id="1063">1063</span> +<span id="1064">1064</span> +<span id="1065">1065</span> +<span id="1066">1066</span> +<span id="1067">1067</span> +<span id="1068">1068</span> +<span id="1069">1069</span> +<span id="1070">1070</span> +<span id="1071">1071</span> +<span id="1072">1072</span> +<span id="1073">1073</span> +<span id="1074">1074</span> +<span id="1075">1075</span> +<span id="1076">1076</span> +<span id="1077">1077</span> +<span id="1078">1078</span> +<span id="1079">1079</span> +<span id="1080">1080</span> +<span id="1081">1081</span> +<span id="1082">1082</span> +<span id="1083">1083</span> +<span id="1084">1084</span> +<span id="1085">1085</span> +<span id="1086">1086</span> +<span id="1087">1087</span> +<span id="1088">1088</span> +<span id="1089">1089</span> +<span id="1090">1090</span> +<span id="1091">1091</span> +<span id="1092">1092</span> +<span id="1093">1093</span> +<span id="1094">1094</span> +<span id="1095">1095</span> +<span id="1096">1096</span> +<span id="1097">1097</span> +<span id="1098">1098</span> +<span id="1099">1099</span> +<span id="1100">1100</span> +<span id="1101">1101</span> +<span id="1102">1102</span> +<span id="1103">1103</span> +<span id="1104">1104</span> +<span id="1105">1105</span> +<span id="1106">1106</span> +<span id="1107">1107</span> +<span id="1108">1108</span> +<span id="1109">1109</span> +<span id="1110">1110</span> +<span id="1111">1111</span> +<span id="1112">1112</span> +<span id="1113">1113</span> +<span id="1114">1114</span> +<span id="1115">1115</span> +<span id="1116">1116</span> +<span id="1117">1117</span> +<span id="1118">1118</span> +<span id="1119">1119</span> +<span id="1120">1120</span> +<span id="1121">1121</span> +<span id="1122">1122</span> +<span id="1123">1123</span> +<span id="1124">1124</span> +<span id="1125">1125</span> +<span id="1126">1126</span> +<span id="1127">1127</span> +<span id="1128">1128</span> +<span id="1129">1129</span> +<span id="1130">1130</span> +<span id="1131">1131</span> +<span id="1132">1132</span> +<span id="1133">1133</span> +<span id="1134">1134</span> +<span id="1135">1135</span> +<span id="1136">1136</span> +<span id="1137">1137</span> +<span id="1138">1138</span> +<span id="1139">1139</span> +<span id="1140">1140</span> +<span id="1141">1141</span> +<span id="1142">1142</span> +<span id="1143">1143</span> +<span id="1144">1144</span> +<span id="1145">1145</span> +<span id="1146">1146</span> +<span id="1147">1147</span> +<span id="1148">1148</span> +</pre><pre class='rust '> +<span class='comment'>// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT</span> +<span class='comment'>// file at the top-level directory of this distribution and at</span> +<span class='comment'>// http://rust-lang.org/COPYRIGHT.</span> +<span class='comment'>//</span> +<span class='comment'>// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> +<span class='comment'>// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> +<span class='comment'>// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> +<span class='comment'>// option. This file may not be copied, modified, or distributed</span> +<span class='comment'>// except according to those terms.</span> + +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>borrow</span>::<span class='ident'>Cow</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>collections</span>::<span class='ident'>HashMap</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>collections</span>::<span class='ident'>hash_map</span>::<span class='ident'>Iter</span>; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>fmt</span>; +<span class='attribute'>#[<span class='ident'>cfg</span>(<span class='ident'>feature</span> <span class='op'>=</span> <span class='string'>"pattern"</span>)]</span> +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>str</span>::<span class='ident'>pattern</span>::{<span class='ident'>Pattern</span>, <span class='ident'>Searcher</span>, <span class='ident'>SearchStep</span>}; +<span class='kw'>use</span> <span class='ident'>std</span>::<span class='ident'>str</span>::<span class='ident'>FromStr</span>; + +<span class='kw'>use</span> <span class='ident'>program</span>::{<span class='ident'>Program</span>, <span class='ident'>MatchEngine</span>}; +<span class='kw'>use</span> <span class='ident'>syntax</span>; + +<span class='kw'>const</span> <span class='ident'>REPLACE_EXPAND</span>: <span class='kw-2'>&</span><span class='lifetime'>'static</span> <span class='ident'>str</span> <span class='op'>=</span> <span class='string'>r"(?x) + (?P<before>^|\b|[^$]) # Ignore `$$name`. + \$ + (?P<name> # Match the actual capture name. Can be... + [0-9]+ # A sequence of digits (for indexed captures), or... + | + [_a-zA-Z][_0-9a-zA-Z]* # A name for named captures. + ) +"</span>; + +<span class='doccomment'>/// Type alias for representing capture indices.</span> +<span class='kw'>pub</span> <span class='kw'>type</span> <span class='ident'>CaptureIdxs</span> <span class='op'>=</span> [<span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>></span>]; + +<span class='doccomment'>/// Escapes all regular expression meta characters in `text`.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The string returned may be safely used as a literal in a regular</span> +<span class='doccomment'>/// expression.</span> +<span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>quote</span>(<span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>quoted</span> <span class='op'>=</span> <span class='ident'>String</span>::<span class='ident'>with_capacity</span>(<span class='ident'>text</span>.<span class='ident'>len</span>()); + <span class='kw'>for</span> <span class='ident'>c</span> <span class='kw'>in</span> <span class='ident'>text</span>.<span class='ident'>chars</span>() { + <span class='kw'>if</span> <span class='ident'>syntax</span>::<span class='ident'>is_punct</span>(<span class='ident'>c</span>) { + <span class='ident'>quoted</span>.<span class='ident'>push</span>(<span class='string'>'\\'</span>) + } + <span class='ident'>quoted</span>.<span class='ident'>push</span>(<span class='ident'>c</span>); + } + <span class='ident'>quoted</span> +} + +<span class='doccomment'>/// Tests if the given regular expression matches somewhere in the text given.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// If there was a problem compiling the regular expression, an error is</span> +<span class='doccomment'>/// returned.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// To find submatches, split or replace text, you'll need to compile an</span> +<span class='doccomment'>/// expression first.</span> +<span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_match</span>(<span class='ident'>regex</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>bool</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='ident'>Regex</span>::<span class='ident'>new</span>(<span class='ident'>regex</span>).<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>r</span><span class='op'>|</span> <span class='ident'>r</span>.<span class='ident'>is_match</span>(<span class='ident'>text</span>)) +} + +<span class='doccomment'>/// An error that occurred during parsing or compiling a regular expression.</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Debug</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>Error</span> { + <span class='doccomment'>/// A syntax error.</span> + <span class='ident'>Syntax</span>(<span class='ident'>syntax</span>::<span class='ident'>Error</span>), + <span class='doccomment'>/// The compiled program exceeded the set size limit.</span> + <span class='doccomment'>/// The argument is the size limit imposed.</span> + <span class='ident'>CompiledTooBig</span>(<span class='ident'>usize</span>), + <span class='doccomment'>/// Hints that destructuring should not be exhaustive.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// This enum may grow additional variants, so this makes sure clients</span> + <span class='doccomment'>/// don't count on exhaustive matching. (Otherwise, adding a new variant</span> + <span class='doccomment'>/// could break existing code.)</span> + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='ident'>__Nonexhaustive</span>, +} + +<span class='kw'>impl</span> ::<span class='ident'>std</span>::<span class='ident'>error</span>::<span class='ident'>Error</span> <span class='kw'>for</span> <span class='ident'>Error</span> { + <span class='kw'>fn</span> <span class='ident'>description</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='kw-2'>&</span><span class='ident'>str</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Error</span>::<span class='ident'>Syntax</span>(<span class='kw-2'>ref</span> <span class='ident'>err</span>) <span class='op'>=></span> <span class='ident'>err</span>.<span class='ident'>description</span>(), + <span class='ident'>Error</span>::<span class='ident'>CompiledTooBig</span>(_) <span class='op'>=></span> <span class='string'>"compiled program too big"</span>, + <span class='ident'>Error</span>::<span class='ident'>__Nonexhaustive</span> <span class='op'>=></span> <span class='macro'>unreachable</span><span class='macro'>!</span>(), + } + } + + <span class='kw'>fn</span> <span class='ident'>cause</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span>::<span class='ident'>std</span>::<span class='ident'>error</span>::<span class='ident'>Error</span><span class='op'>></span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Error</span>::<span class='ident'>Syntax</span>(<span class='kw-2'>ref</span> <span class='ident'>err</span>) <span class='op'>=></span> <span class='prelude-val'>Some</span>(<span class='ident'>err</span>), + _ <span class='op'>=></span> <span class='prelude-val'>None</span>, + } + } +} + +<span class='kw'>impl</span> <span class='ident'>fmt</span>::<span class='ident'>Display</span> <span class='kw'>for</span> <span class='ident'>Error</span> { + <span class='kw'>fn</span> <span class='ident'>fmt</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>f</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>fmt</span>::<span class='ident'>Formatter</span>) <span class='op'>-></span> <span class='ident'>fmt</span>::<span class='prelude-ty'>Result</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Error</span>::<span class='ident'>Syntax</span>(<span class='kw-2'>ref</span> <span class='ident'>err</span>) <span class='op'>=></span> <span class='ident'>err</span>.<span class='ident'>fmt</span>(<span class='ident'>f</span>), + <span class='ident'>Error</span>::<span class='ident'>CompiledTooBig</span>(<span class='ident'>limit</span>) <span class='op'>=></span> { + <span class='macro'>write</span><span class='macro'>!</span>(<span class='ident'>f</span>, <span class='string'>"Compiled regex exceeds size limit of {} bytes."</span>, + <span class='ident'>limit</span>) + } + <span class='ident'>Error</span>::<span class='ident'>__Nonexhaustive</span> <span class='op'>=></span> <span class='macro'>unreachable</span><span class='macro'>!</span>(), + } + } +} + +<span class='kw'>impl</span> <span class='ident'>From</span><span class='op'><</span><span class='ident'>syntax</span>::<span class='ident'>Error</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>Error</span> { + <span class='kw'>fn</span> <span class='ident'>from</span>(<span class='ident'>err</span>: <span class='ident'>syntax</span>::<span class='ident'>Error</span>) <span class='op'>-></span> <span class='ident'>Error</span> { + <span class='ident'>Error</span>::<span class='ident'>Syntax</span>(<span class='ident'>err</span>) + } +} + +<span class='doccomment'>/// A compiled regular expression</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// It is represented as either a sequence of bytecode instructions (dynamic)</span> +<span class='doccomment'>/// or as a specialized Rust function (native). It can be used to search, split</span> +<span class='doccomment'>/// or replace text. All searching is done with an implicit `.*?` at the</span> +<span class='doccomment'>/// beginning and end of an expression. To force an expression to match the</span> +<span class='doccomment'>/// whole string (or a prefix or a suffix), you must use an anchor like `^` or</span> +<span class='doccomment'>/// `$` (or `\A` and `\z`).</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// While this crate will handle Unicode strings (whether in the regular</span> +<span class='doccomment'>/// expression or in the search text), all positions returned are **byte</span> +<span class='doccomment'>/// indices**. Every byte index is guaranteed to be at a Unicode code point</span> +<span class='doccomment'>/// boundary.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The lifetimes `'r` and `'t` in this crate correspond to the lifetime of a</span> +<span class='doccomment'>/// compiled regular expression and text to search, respectively.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The only methods that allocate new strings are the string replacement</span> +<span class='doccomment'>/// methods. All other methods (searching and splitting) return borrowed</span> +<span class='doccomment'>/// pointers into the string given.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// # Examples</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// Find the location of a US phone number:</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// ```rust</span> +<span class='doccomment'>/// # use regex::Regex;</span> +<span class='doccomment'>/// let re = Regex::new("[0-9]{3}-[0-9]{3}-[0-9]{4}").unwrap();</span> +<span class='doccomment'>/// assert_eq!(re.find("phone: 111-222-3333"), Some((7, 19)));</span> +<span class='doccomment'>/// ```</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// # Using the `std::str::StrExt` methods with `Regex`</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// > **Note**: This section requires that this crate is currently compiled with</span> +<span class='doccomment'>/// > the `pattern` Cargo feature enabled.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// Since `Regex` implements `Pattern`, you can use regexes with methods</span> +<span class='doccomment'>/// defined on `std::str::StrExt`. For example, `is_match`, `find`, `find_iter`</span> +<span class='doccomment'>/// and `split` can be replaced with `StrExt::contains`, `StrExt::find`,</span> +<span class='doccomment'>/// `StrExt::match_indices` and `StrExt::split`.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// Here are some examples:</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// ```rust,ignore</span> +<span class='doccomment'>/// # use regex::Regex;</span> +<span class='doccomment'>/// let re = Regex::new(r"\d+").unwrap();</span> +<span class='doccomment'>/// let haystack = "a111b222c";</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// assert!(haystack.contains(&re));</span> +<span class='doccomment'>/// assert_eq!(haystack.find(&re), Some(1));</span> +<span class='doccomment'>/// assert_eq!(haystack.match_indices(&re).collect::<Vec<_>>(),</span> +<span class='doccomment'>/// vec![(1, 4), (5, 8)]);</span> +<span class='doccomment'>/// assert_eq!(haystack.split(&re).collect::<Vec<_>>(), vec!["a", "b", "c"]);</span> +<span class='doccomment'>/// ```</span> +<span class='attribute'>#[<span class='ident'>derive</span>(<span class='ident'>Clone</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>Regex</span> { + <span class='comment'>// The representation of `Regex` is exported to support the `regex!`</span> + <span class='comment'>// syntax extension. Do not rely on it.</span> + <span class='comment'>//</span> + <span class='comment'>// See the comments for the `program` module in `lib.rs` for a more</span> + <span class='comment'>// detailed explanation for what `regex!` requires.</span> + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='ident'>Dynamic</span>(<span class='ident'>Program</span>), + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='ident'>Native</span>(<span class='ident'>ExNative</span>), +} + +<span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>ExNative</span> { + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='kw'>pub</span> <span class='ident'>original</span>: <span class='kw-2'>&</span><span class='lifetime'>'static</span> <span class='ident'>str</span>, + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='kw'>pub</span> <span class='ident'>names</span>: <span class='kw-2'>&</span><span class='lifetime'>'static</span> <span class='kw-2'>&</span><span class='lifetime'>'static</span> [<span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'static</span> <span class='ident'>str</span><span class='op'>></span>], + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='kw'>pub</span> <span class='ident'>prog</span>: <span class='kw'>fn</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>CaptureIdxs</span>, <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>bool</span>, +} + +<span class='kw'>impl</span> <span class='ident'>Copy</span> <span class='kw'>for</span> <span class='ident'>ExNative</span> {} + +<span class='kw'>impl</span> <span class='ident'>Clone</span> <span class='kw'>for</span> <span class='ident'>ExNative</span> { + <span class='kw'>fn</span> <span class='ident'>clone</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>ExNative</span> { + <span class='op'>*</span><span class='self'>self</span> + } +} + +<span class='kw'>impl</span> <span class='ident'>fmt</span>::<span class='ident'>Display</span> <span class='kw'>for</span> <span class='ident'>Regex</span> { + <span class='doccomment'>/// Shows the original regular expression.</span> + <span class='kw'>fn</span> <span class='ident'>fmt</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>f</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>fmt</span>::<span class='ident'>Formatter</span>) <span class='op'>-></span> <span class='ident'>fmt</span>::<span class='prelude-ty'>Result</span> { + <span class='macro'>write</span><span class='macro'>!</span>(<span class='ident'>f</span>, <span class='string'>"{}"</span>, <span class='self'>self</span>.<span class='ident'>as_str</span>()) + } +} + +<span class='kw'>impl</span> <span class='ident'>fmt</span>::<span class='ident'>Debug</span> <span class='kw'>for</span> <span class='ident'>Regex</span> { + <span class='doccomment'>/// Shows the original regular expression.</span> + <span class='kw'>fn</span> <span class='ident'>fmt</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>f</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>fmt</span>::<span class='ident'>Formatter</span>) <span class='op'>-></span> <span class='ident'>fmt</span>::<span class='prelude-ty'>Result</span> { + <span class='ident'>fmt</span>::<span class='ident'>Display</span>::<span class='ident'>fmt</span>(<span class='self'>self</span>, <span class='ident'>f</span>) + } +} + +<span class='doccomment'>/// Equality comparison is based on the original string. It is possible that</span> +<span class='doccomment'>/// different regular expressions have the same matching behavior, but are</span> +<span class='doccomment'>/// still compared unequal. For example, `\d+` and `\d\d*` match the same set</span> +<span class='doccomment'>/// of strings, but are not considered equal.</span> +<span class='kw'>impl</span> <span class='ident'>PartialEq</span> <span class='kw'>for</span> <span class='ident'>Regex</span> { + <span class='kw'>fn</span> <span class='ident'>eq</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>other</span>: <span class='kw-2'>&</span><span class='ident'>Regex</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='self'>self</span>.<span class='ident'>as_str</span>() <span class='op'>==</span> <span class='ident'>other</span>.<span class='ident'>as_str</span>() + } +} + +<span class='kw'>impl</span> <span class='ident'>Eq</span> <span class='kw'>for</span> <span class='ident'>Regex</span> {} + +<span class='kw'>impl</span> <span class='ident'>FromStr</span> <span class='kw'>for</span> <span class='ident'>Regex</span> { + <span class='kw'>type</span> <span class='prelude-val'>Err</span> <span class='op'>=</span> <span class='ident'>Error</span>; + + <span class='doccomment'>/// Attempts to parse a string into a regular expression</span> + <span class='kw'>fn</span> <span class='ident'>from_str</span>(<span class='ident'>s</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>Regex</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='ident'>Regex</span>::<span class='ident'>new</span>(<span class='ident'>s</span>) + } +} + +<span class='kw'>impl</span> <span class='ident'>Regex</span> { + <span class='doccomment'>/// Compiles a dynamic regular expression. Once compiled, it can be</span> + <span class='doccomment'>/// used repeatedly to search, split or replace text in a string.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If an invalid expression is given, then an error is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>new</span>(<span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>Regex</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='ident'>Regex</span>::<span class='ident'>with_size_limit</span>(<span class='number'>10</span> <span class='op'>*</span> (<span class='number'>1</span> <span class='op'><<</span> <span class='number'>20</span>), <span class='ident'>re</span>) + } + + <span class='doccomment'>/// Compiles a dynamic regular expression with the given size limit.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// The size limit is applied to the size of the *compiled* data structure.</span> + <span class='doccomment'>/// If the data structure exceeds the size given, then an error is</span> + <span class='doccomment'>/// returned.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// The default size limit used in `new` is 10MB.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>with_size_limit</span>(<span class='ident'>size</span>: <span class='ident'>usize</span>, <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>Regex</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='ident'>Regex</span>::<span class='ident'>with_engine</span>(<span class='prelude-val'>None</span>, <span class='ident'>size</span>, <span class='ident'>re</span>) + } + + <span class='doccomment'>/// Compiles a dynamic regular expression and uses given matching engine.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// This is exposed for use in testing and shouldn't be used by clients.</span> + <span class='doccomment'>/// Instead, the regex program should choose the correct matching engine</span> + <span class='doccomment'>/// to use automatically. (Based on the regex, the size of the input and</span> + <span class='doccomment'>/// the type of search.)</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// A value of `None` means that the engine is automatically selected,</span> + <span class='doccomment'>/// which is the default behavior.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// **WARNING**: Passing an unsuitable engine for the given regex/input</span> + <span class='doccomment'>/// could lead to bad things. (Not unsafe things, but panics, incorrect</span> + <span class='doccomment'>/// matches and large memory use are all things that could happen.)</span> + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>with_engine</span>( + <span class='ident'>engine</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>MatchEngine</span><span class='op'>></span>, + <span class='ident'>size</span>: <span class='ident'>usize</span>, + <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, + ) <span class='op'>-></span> <span class='prelude-ty'>Result</span><span class='op'><</span><span class='ident'>Regex</span>, <span class='ident'>Error</span><span class='op'>></span> { + <span class='ident'>Program</span>::<span class='ident'>new</span>(<span class='ident'>engine</span>, <span class='ident'>size</span>, <span class='ident'>re</span>).<span class='ident'>map</span>(<span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>) + } + + + <span class='doccomment'>/// Returns true if and only if the regex matches the string given.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Test if some text contains at least one word with exactly 13</span> + <span class='doccomment'>/// characters:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let text = "I categorically deny having triskaidekaphobia.";</span> + <span class='doccomment'>/// assert!(Regex::new(r"\b\w{13}\b").unwrap().is_match(text));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_match</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='ident'>exec</span>(<span class='self'>self</span>, <span class='kw-2'>&</span><span class='kw-2'>mut</span> [], <span class='ident'>text</span>, <span class='number'>0</span>) + } + + <span class='doccomment'>/// Returns the start and end byte range of the leftmost-first match in</span> + <span class='doccomment'>/// `text`. If no match exists, then `None` is returned.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Note that this should only be used if you want to discover the position</span> + <span class='doccomment'>/// of the match. Testing the existence of a match is faster if you use</span> + <span class='doccomment'>/// `is_match`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Find the start and end location of the first word with exactly 13</span> + <span class='doccomment'>/// characters:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let text = "I categorically deny having triskaidekaphobia.";</span> + <span class='doccomment'>/// let pos = Regex::new(r"\b\w{13}\b").unwrap().find(text);</span> + <span class='doccomment'>/// assert_eq!(pos, Some((2, 15)));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>find</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>></span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>caps</span> <span class='op'>=</span> [<span class='prelude-val'>None</span>, <span class='prelude-val'>None</span>]; + <span class='kw'>if</span> <span class='ident'>exec</span>(<span class='self'>self</span>, <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='number'>0</span>) { + <span class='prelude-val'>Some</span>((<span class='ident'>caps</span>[<span class='number'>0</span>].<span class='ident'>unwrap</span>(), <span class='ident'>caps</span>[<span class='number'>1</span>].<span class='ident'>unwrap</span>())) + } <span class='kw'>else</span> { + <span class='prelude-val'>None</span> + } + } + + <span class='doccomment'>/// Returns an iterator for each successive non-overlapping match in</span> + <span class='doccomment'>/// `text`, returning the start and end byte indices with respect to</span> + <span class='doccomment'>/// `text`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Find the start and end location of every word with exactly 13</span> + <span class='doccomment'>/// characters:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let text = "Retroactively relinquishing remunerations is reprehensible.";</span> + <span class='doccomment'>/// for pos in Regex::new(r"\b\w{13}\b").unwrap().find_iter(text) {</span> + <span class='doccomment'>/// println!("{:?}", pos);</span> + <span class='doccomment'>/// }</span> + <span class='doccomment'>/// // Output:</span> + <span class='doccomment'>/// // (0, 13)</span> + <span class='doccomment'>/// // (14, 27)</span> + <span class='doccomment'>/// // (28, 41)</span> + <span class='doccomment'>/// // (45, 58)</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>find_iter</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>FindMatches</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>FindMatches</span> { + <span class='ident'>re</span>: <span class='self'>self</span>, + <span class='ident'>search</span>: <span class='ident'>text</span>, + <span class='ident'>last_end</span>: <span class='number'>0</span>, + <span class='ident'>last_match</span>: <span class='prelude-val'>None</span>, + } + } + + <span class='doccomment'>/// Returns the capture groups corresponding to the leftmost-first</span> + <span class='doccomment'>/// match in `text`. Capture group `0` always corresponds to the entire</span> + <span class='doccomment'>/// match. If no match is found, then `None` is returned.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// You should only use `captures` if you need access to submatches.</span> + <span class='doccomment'>/// Otherwise, `find` is faster for discovering the location of the overall</span> + <span class='doccomment'>/// match.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Examples</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Say you have some text with movie names and their release years,</span> + <span class='doccomment'>/// like "'Citizen Kane' (1941)". It'd be nice if we could search for text</span> + <span class='doccomment'>/// looking like that, while also extracting the movie name and its release</span> + <span class='doccomment'>/// year separately.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"'([^']+)'\s+\((\d{4})\)").unwrap();</span> + <span class='doccomment'>/// let text = "Not my favorite movie: 'Citizen Kane' (1941).";</span> + <span class='doccomment'>/// let caps = re.captures(text).unwrap();</span> + <span class='doccomment'>/// assert_eq!(caps.at(1), Some("Citizen Kane"));</span> + <span class='doccomment'>/// assert_eq!(caps.at(2), Some("1941"));</span> + <span class='doccomment'>/// assert_eq!(caps.at(0), Some("'Citizen Kane' (1941)"));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Note that the full match is at capture group `0`. Each subsequent</span> + <span class='doccomment'>/// capture group is indexed by the order of its opening `(`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// We can make this example a bit clearer by using *named* capture groups:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"'(?P<title>[^']+)'\s+\((?P<year>\d{4})\)")</span> + <span class='doccomment'>/// .unwrap();</span> + <span class='doccomment'>/// let text = "Not my favorite movie: 'Citizen Kane' (1941).";</span> + <span class='doccomment'>/// let caps = re.captures(text).unwrap();</span> + <span class='doccomment'>/// assert_eq!(caps.name("title"), Some("Citizen Kane"));</span> + <span class='doccomment'>/// assert_eq!(caps.name("year"), Some("1941"));</span> + <span class='doccomment'>/// assert_eq!(caps.at(0), Some("'Citizen Kane' (1941)"));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Here we name the capture groups, which we can access with the `name`</span> + <span class='doccomment'>/// method. Note that the named capture groups are still accessible with</span> + <span class='doccomment'>/// `at`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// The `0`th capture group is always unnamed, so it must always be</span> + <span class='doccomment'>/// accessed with `at(0)`.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>>></span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>caps</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>alloc_captures</span>(); + <span class='kw'>if</span> <span class='ident'>exec</span>(<span class='self'>self</span>, <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='number'>0</span>) { + <span class='prelude-val'>Some</span>(<span class='ident'>Captures</span>::<span class='ident'>new</span>(<span class='self'>self</span>, <span class='ident'>text</span>, <span class='ident'>caps</span>)) + } <span class='kw'>else</span> { + <span class='prelude-val'>None</span> + } + } + + <span class='doccomment'>/// Returns an iterator over all the non-overlapping capture groups matched</span> + <span class='doccomment'>/// in `text`. This is operationally the same as `find_iter` (except it</span> + <span class='doccomment'>/// yields information about submatches).</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// We can use this to find all movie titles and their release years in</span> + <span class='doccomment'>/// some text, where the movie is formatted like "'Title' (xxxx)":</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"'(?P<title>[^']+)'\s+\((?P<year>\d{4})\)")</span> + <span class='doccomment'>/// .unwrap();</span> + <span class='doccomment'>/// let text = "'Citizen Kane' (1941), 'The Wizard of Oz' (1939), 'M' (1931).";</span> + <span class='doccomment'>/// for caps in re.captures_iter(text) {</span> + <span class='doccomment'>/// println!("Movie: {:?}, Released: {:?}", caps.name("title"), caps.name("year"));</span> + <span class='doccomment'>/// }</span> + <span class='doccomment'>/// // Output:</span> + <span class='doccomment'>/// // Movie: Citizen Kane, Released: 1941</span> + <span class='doccomment'>/// // Movie: The Wizard of Oz, Released: 1939</span> + <span class='doccomment'>/// // Movie: M, Released: 1931</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>captures_iter</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) + <span class='op'>-></span> <span class='ident'>FindCaptures</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>FindCaptures</span> { + <span class='ident'>re</span>: <span class='self'>self</span>, + <span class='ident'>search</span>: <span class='ident'>text</span>, + <span class='ident'>last_match</span>: <span class='prelude-val'>None</span>, + <span class='ident'>last_end</span>: <span class='number'>0</span>, + } + } + + <span class='doccomment'>/// Returns an iterator of substrings of `text` delimited by a match</span> + <span class='doccomment'>/// of the regular expression.</span> + <span class='doccomment'>/// Namely, each element of the iterator corresponds to text that *isn't*</span> + <span class='doccomment'>/// matched by the regular expression.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// This method will *not* copy the text given.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// To split a string delimited by arbitrary amounts of spaces or tabs:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"[ \t]+").unwrap();</span> + <span class='doccomment'>/// let fields: Vec<&str> = re.split("a b \t c\td e").collect();</span> + <span class='doccomment'>/// assert_eq!(fields, vec!("a", "b", "c", "d", "e"));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>split</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>RegexSplits</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>RegexSplits</span> { + <span class='ident'>finder</span>: <span class='self'>self</span>.<span class='ident'>find_iter</span>(<span class='ident'>text</span>), + <span class='ident'>last</span>: <span class='number'>0</span>, + } + } + + <span class='doccomment'>/// Returns an iterator of at most `limit` substrings of `text` delimited</span> + <span class='doccomment'>/// by a match of the regular expression. (A `limit` of `0` will return no</span> + <span class='doccomment'>/// substrings.)</span> + <span class='doccomment'>/// Namely, each element of the iterator corresponds to text that *isn't*</span> + <span class='doccomment'>/// matched by the regular expression.</span> + <span class='doccomment'>/// The remainder of the string that is not split will be the last element</span> + <span class='doccomment'>/// in the iterator.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// This method will *not* copy the text given.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Example</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Get the first two words in some text:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"\W+").unwrap();</span> + <span class='doccomment'>/// let fields: Vec<&str> = re.splitn("Hey! How are you?", 3).collect();</span> + <span class='doccomment'>/// assert_eq!(fields, vec!("Hey", "How", "are you?"));</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>splitn</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, <span class='ident'>limit</span>: <span class='ident'>usize</span>) + <span class='op'>-></span> <span class='ident'>RegexSplitsN</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>RegexSplitsN</span> { + <span class='ident'>splits</span>: <span class='self'>self</span>.<span class='ident'>split</span>(<span class='ident'>text</span>), + <span class='ident'>cur</span>: <span class='number'>0</span>, + <span class='ident'>limit</span>: <span class='ident'>limit</span>, + } + } + + <span class='doccomment'>/// Replaces the leftmost-first match with the replacement provided.</span> + <span class='doccomment'>/// The replacement can be a regular string (where `$N` and `$name` are</span> + <span class='doccomment'>/// expanded to match capture groups) or a function that takes the matches'</span> + <span class='doccomment'>/// `Captures` and returns the replaced string.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If no match is found, then a copy of the string is returned unchanged.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// # Examples</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Note that this function is polymorphic with respect to the replacement.</span> + <span class='doccomment'>/// In typical usage, this can just be a normal string:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new("[^01]+").unwrap();</span> + <span class='doccomment'>/// assert_eq!(re.replace("1078910", ""), "1010");</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// But anything satisfying the `Replacer` trait will work. For example,</span> + <span class='doccomment'>/// a closure of type `|&Captures| -> String` provides direct access to the</span> + <span class='doccomment'>/// captures corresponding to a match. This allows one to access</span> + <span class='doccomment'>/// submatches easily:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # use regex::Captures; fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"([^,\s]+),\s+(\S+)").unwrap();</span> + <span class='doccomment'>/// let result = re.replace("Springsteen, Bruce", |caps: &Captures| {</span> + <span class='doccomment'>/// format!("{} {}", caps.at(2).unwrap_or(""), caps.at(1).unwrap_or(""))</span> + <span class='doccomment'>/// });</span> + <span class='doccomment'>/// assert_eq!(result, "Bruce Springsteen");</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// But this is a bit cumbersome to use all the time. Instead, a simple</span> + <span class='doccomment'>/// syntax is supported that expands `$name` into the corresponding capture</span> + <span class='doccomment'>/// group. Here's the last example, but using this expansion technique</span> + <span class='doccomment'>/// with named capture groups:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// let re = Regex::new(r"(?P<last>[^,\s]+),\s+(?P<first>\S+)").unwrap();</span> + <span class='doccomment'>/// let result = re.replace("Springsteen, Bruce", "$first $last");</span> + <span class='doccomment'>/// assert_eq!(result, "Bruce Springsteen");</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Note that using `$2` instead of `$first` or `$1` instead of `$last`</span> + <span class='doccomment'>/// would produce the same result. To write a literal `$` use `$$`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// Finally, sometimes you just want to replace a literal string with no</span> + <span class='doccomment'>/// submatch expansion. This can be done by wrapping a string with</span> + <span class='doccomment'>/// `NoExpand`:</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// ```rust</span> + <span class='doccomment'>/// # extern crate regex; use regex::Regex;</span> + <span class='doccomment'>/// # fn main() {</span> + <span class='doccomment'>/// use regex::NoExpand;</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// let re = Regex::new(r"(?P<last>[^,\s]+),\s+(\S+)").unwrap();</span> + <span class='doccomment'>/// let result = re.replace("Springsteen, Bruce", NoExpand("$2 $last"));</span> + <span class='doccomment'>/// assert_eq!(result, "$2 $last");</span> + <span class='doccomment'>/// # }</span> + <span class='doccomment'>/// ```</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>replace</span><span class='op'><</span><span class='ident'>R</span>: <span class='ident'>Replacer</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>rep</span>: <span class='ident'>R</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='self'>self</span>.<span class='ident'>replacen</span>(<span class='ident'>text</span>, <span class='number'>1</span>, <span class='ident'>rep</span>) + } + + <span class='doccomment'>/// Replaces all non-overlapping matches in `text` with the</span> + <span class='doccomment'>/// replacement provided. This is the same as calling `replacen` with</span> + <span class='doccomment'>/// `limit` set to `0`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// See the documentation for `replace` for details on how to access</span> + <span class='doccomment'>/// submatches in the replacement string.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>replace_all</span><span class='op'><</span><span class='ident'>R</span>: <span class='ident'>Replacer</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>rep</span>: <span class='ident'>R</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='self'>self</span>.<span class='ident'>replacen</span>(<span class='ident'>text</span>, <span class='number'>0</span>, <span class='ident'>rep</span>) + } + + <span class='doccomment'>/// Replaces at most `limit` non-overlapping matches in `text` with the</span> + <span class='doccomment'>/// replacement provided. If `limit` is 0, then all non-overlapping matches</span> + <span class='doccomment'>/// are replaced.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// See the documentation for `replace` for details on how to access</span> + <span class='doccomment'>/// submatches in the replacement string.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>replacen</span><span class='op'><</span><span class='ident'>R</span>: <span class='ident'>Replacer</span><span class='op'>></span> + (<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>limit</span>: <span class='ident'>usize</span>, <span class='kw-2'>mut</span> <span class='ident'>rep</span>: <span class='ident'>R</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>new</span> <span class='op'>=</span> <span class='ident'>String</span>::<span class='ident'>with_capacity</span>(<span class='ident'>text</span>.<span class='ident'>len</span>()); + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>last_match</span> <span class='op'>=</span> <span class='number'>0</span>; + + <span class='kw'>if</span> <span class='ident'>rep</span>.<span class='ident'>no_expand</span>().<span class='ident'>is_some</span>() { + <span class='comment'>// borrow checker pains. `rep` is borrowed mutably in the `else`</span> + <span class='comment'>// branch below.</span> + <span class='kw'>let</span> <span class='ident'>rep</span> <span class='op'>=</span> <span class='ident'>rep</span>.<span class='ident'>no_expand</span>().<span class='ident'>unwrap</span>(); + <span class='kw'>for</span> (<span class='ident'>i</span>, (<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='kw'>in</span> <span class='self'>self</span>.<span class='ident'>find_iter</span>(<span class='ident'>text</span>).<span class='ident'>enumerate</span>() { + <span class='kw'>if</span> <span class='ident'>limit</span> <span class='op'>></span> <span class='number'>0</span> <span class='op'>&&</span> <span class='ident'>i</span> <span class='op'>>=</span> <span class='ident'>limit</span> { + <span class='kw'>break</span> + } + <span class='ident'>new</span>.<span class='ident'>push_str</span>(<span class='kw-2'>&</span><span class='ident'>text</span>[<span class='ident'>last_match</span>..<span class='ident'>s</span>]); + <span class='ident'>new</span>.<span class='ident'>push_str</span>(<span class='kw-2'>&</span><span class='ident'>rep</span>); + <span class='ident'>last_match</span> <span class='op'>=</span> <span class='ident'>e</span>; + } + } <span class='kw'>else</span> { + <span class='kw'>for</span> (<span class='ident'>i</span>, <span class='ident'>cap</span>) <span class='kw'>in</span> <span class='self'>self</span>.<span class='ident'>captures_iter</span>(<span class='ident'>text</span>).<span class='ident'>enumerate</span>() { + <span class='kw'>if</span> <span class='ident'>limit</span> <span class='op'>></span> <span class='number'>0</span> <span class='op'>&&</span> <span class='ident'>i</span> <span class='op'>>=</span> <span class='ident'>limit</span> { + <span class='kw'>break</span> + } + <span class='comment'>// unwrap on 0 is OK because captures only reports matches</span> + <span class='kw'>let</span> (<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='op'>=</span> <span class='ident'>cap</span>.<span class='ident'>pos</span>(<span class='number'>0</span>).<span class='ident'>unwrap</span>(); + <span class='ident'>new</span>.<span class='ident'>push_str</span>(<span class='kw-2'>&</span><span class='ident'>text</span>[<span class='ident'>last_match</span>..<span class='ident'>s</span>]); + <span class='ident'>new</span>.<span class='ident'>push_str</span>(<span class='kw-2'>&</span><span class='ident'>rep</span>.<span class='ident'>reg_replace</span>(<span class='kw-2'>&</span><span class='ident'>cap</span>)); + <span class='ident'>last_match</span> <span class='op'>=</span> <span class='ident'>e</span>; + } + } + <span class='ident'>new</span>.<span class='ident'>push_str</span>(<span class='kw-2'>&</span><span class='ident'>text</span>[<span class='ident'>last_match</span>..]); + <span class='ident'>new</span> + } + + <span class='doccomment'>/// Returns the original string of this regex.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>as_str</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='ident'>str</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>(<span class='ident'>Program</span> { <span class='kw-2'>ref</span> <span class='ident'>original</span>, .. }) <span class='op'>=></span> <span class='ident'>original</span>, + <span class='ident'>Regex</span>::<span class='ident'>Native</span>(<span class='ident'>ExNative</span> { <span class='kw-2'>ref</span> <span class='ident'>original</span>, .. }) <span class='op'>=></span> <span class='ident'>original</span>, + } + } + + <span class='attribute'>#[<span class='ident'>doc</span>(<span class='ident'>hidden</span>)]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>names_iter</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>NamesIter</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Regex</span>::<span class='ident'>Native</span>(<span class='kw-2'>ref</span> <span class='ident'>n</span>) <span class='op'>=></span> <span class='ident'>NamesIter</span>::<span class='ident'>Native</span>(<span class='ident'>n</span>.<span class='ident'>names</span>.<span class='ident'>iter</span>()), + <span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>(<span class='kw-2'>ref</span> <span class='ident'>d</span>) <span class='op'>=></span> <span class='ident'>NamesIter</span>::<span class='ident'>Dynamic</span>(<span class='ident'>d</span>.<span class='ident'>cap_names</span>.<span class='ident'>iter</span>()) + } + } + + <span class='kw'>fn</span> <span class='ident'>names_len</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Regex</span>::<span class='ident'>Native</span>(<span class='kw-2'>ref</span> <span class='ident'>n</span>) <span class='op'>=></span> <span class='ident'>n</span>.<span class='ident'>names</span>.<span class='ident'>len</span>(), + <span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>(<span class='kw-2'>ref</span> <span class='ident'>d</span>) <span class='op'>=></span> <span class='ident'>d</span>.<span class='ident'>cap_names</span>.<span class='ident'>len</span>() + } + } + + <span class='kw'>fn</span> <span class='ident'>alloc_captures</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>Vec</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>>></span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>Regex</span>::<span class='ident'>Native</span>(<span class='kw-2'>ref</span> <span class='ident'>n</span>) <span class='op'>=></span> <span class='macro'>vec</span><span class='macro'>!</span>[<span class='prelude-val'>None</span>; <span class='number'>2</span> <span class='op'>*</span> <span class='ident'>n</span>.<span class='ident'>names</span>.<span class='ident'>len</span>()], + <span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>(<span class='kw-2'>ref</span> <span class='ident'>d</span>) <span class='op'>=></span> <span class='ident'>d</span>.<span class='ident'>alloc_captures</span>(), + } + } +} + +<span class='kw'>pub</span> <span class='kw'>enum</span> <span class='ident'>NamesIter</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span> { + <span class='ident'>Native</span>(::<span class='ident'>std</span>::<span class='ident'>slice</span>::<span class='ident'>Iter</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'static</span> <span class='ident'>str</span><span class='op'>>></span>), + <span class='ident'>Dynamic</span>(::<span class='ident'>std</span>::<span class='ident'>slice</span>::<span class='ident'>Iter</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>String</span><span class='op'>>></span>) +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>NamesIter</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span><span class='op'>=</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>String</span><span class='op'>></span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>String</span><span class='op'>>></span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='self'>self</span> { + <span class='ident'>NamesIter</span>::<span class='ident'>Native</span>(<span class='kw-2'>ref</span> <span class='kw-2'>mut</span> <span class='ident'>i</span>) <span class='op'>=></span> + <span class='ident'>i</span>.<span class='ident'>next</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>x</span><span class='op'>|</span> <span class='ident'>x</span>.<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>s</span><span class='op'>|</span> <span class='ident'>s</span>.<span class='ident'>to_owned</span>())), + <span class='ident'>NamesIter</span>::<span class='ident'>Dynamic</span>(<span class='kw-2'>ref</span> <span class='kw-2'>mut</span> <span class='ident'>i</span>) <span class='op'>=></span> + <span class='ident'>i</span>.<span class='ident'>next</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>x</span><span class='op'>|</span> <span class='ident'>x</span>.<span class='ident'>as_ref</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>s</span><span class='op'>|</span> <span class='ident'>s</span>.<span class='ident'>to_owned</span>())), + } + } +} + +<span class='doccomment'>/// NoExpand indicates literal string replacement.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// It can be used with `replace` and `replace_all` to do a literal</span> +<span class='doccomment'>/// string replacement without expanding `$name` to their corresponding</span> +<span class='doccomment'>/// capture groups.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'r` is the lifetime of the literal text.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>NoExpand</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>(<span class='kw'>pub</span> <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>); + +<span class='doccomment'>/// Replacer describes types that can be used to replace matches in a string.</span> +<span class='kw'>pub</span> <span class='kw'>trait</span> <span class='ident'>Replacer</span> { + <span class='doccomment'>/// Returns a possibly owned string that is used to replace the match</span> + <span class='doccomment'>/// corresponding to the `caps` capture group.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// The `'a` lifetime refers to the lifetime of a borrowed string when</span> + <span class='doccomment'>/// a new owned string isn't needed (e.g., for `NoExpand`).</span> + <span class='kw'>fn</span> <span class='ident'>reg_replace</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>, <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='ident'>Captures</span>) <span class='op'>-></span> <span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>></span>; + + <span class='doccomment'>/// Returns a possibly owned string that never needs expansion.</span> + <span class='kw'>fn</span> <span class='ident'>no_expand</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>>></span> { <span class='prelude-val'>None</span> } +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Replacer</span> <span class='kw'>for</span> <span class='ident'>NoExpand</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>fn</span> <span class='ident'>reg_replace</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>, _: <span class='kw-2'>&</span><span class='ident'>Captures</span>) <span class='op'>-></span> <span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>></span> { + <span class='self'>self</span>.<span class='number'>0</span>.<span class='ident'>into</span>() + } + + <span class='kw'>fn</span> <span class='ident'>no_expand</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>>></span> { + <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='number'>0</span>.<span class='ident'>into</span>()) + } +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Replacer</span> <span class='kw'>for</span> <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span> { + <span class='kw'>fn</span> <span class='ident'>reg_replace</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>, <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='ident'>Captures</span>) <span class='op'>-></span> <span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>></span> { + <span class='ident'>caps</span>.<span class='ident'>expand</span>(<span class='op'>*</span><span class='self'>self</span>).<span class='ident'>into</span>() + } + + <span class='kw'>fn</span> <span class='ident'>no_expand</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>>></span> { + <span class='kw'>let</span> <span class='ident'>re</span> <span class='op'>=</span> <span class='ident'>Regex</span>::<span class='ident'>new</span>(<span class='ident'>REPLACE_EXPAND</span>).<span class='ident'>unwrap</span>(); + <span class='kw'>if</span> <span class='op'>!</span><span class='ident'>re</span>.<span class='ident'>is_match</span>(<span class='self'>self</span>) { + <span class='prelude-val'>Some</span>((<span class='op'>*</span><span class='self'>self</span>).<span class='ident'>into</span>()) + } <span class='kw'>else</span> { + <span class='prelude-val'>None</span> + } + } +} + +<span class='kw'>impl</span><span class='op'><</span><span class='ident'>F</span><span class='op'>></span> <span class='ident'>Replacer</span> <span class='kw'>for</span> <span class='ident'>F</span> <span class='kw'>where</span> <span class='ident'>F</span>: <span class='ident'>FnMut</span>(<span class='kw-2'>&</span><span class='ident'>Captures</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='kw'>fn</span> <span class='ident'>reg_replace</span><span class='op'><</span><span class='lifetime'>'a</span><span class='op'>></span>(<span class='kw-2'>&</span><span class='lifetime'>'a</span> <span class='kw-2'>mut</span> <span class='self'>self</span>, <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='ident'>Captures</span>) <span class='op'>-></span> <span class='ident'>Cow</span><span class='op'><</span><span class='lifetime'>'a</span>, <span class='ident'>str</span><span class='op'>></span> { + (<span class='op'>*</span><span class='self'>self</span>)(<span class='ident'>caps</span>).<span class='ident'>into</span>() + } +} + +<span class='doccomment'>/// Yields all substrings delimited by a regular expression match.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'r` is the lifetime of the compiled expression and `'t` is the lifetime</span> +<span class='doccomment'>/// of the string being split.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>RegexSplits</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>finder</span>: <span class='ident'>FindMatches</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>, + <span class='ident'>last</span>: <span class='ident'>usize</span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>RegexSplits</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span> { + <span class='kw'>let</span> <span class='ident'>text</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>finder</span>.<span class='ident'>search</span>; + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>finder</span>.<span class='ident'>next</span>() { + <span class='prelude-val'>None</span> <span class='op'>=></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last</span> <span class='op'>>=</span> <span class='ident'>text</span>.<span class='ident'>len</span>() { + <span class='prelude-val'>None</span> + } <span class='kw'>else</span> { + <span class='kw'>let</span> <span class='ident'>s</span> <span class='op'>=</span> <span class='kw-2'>&</span><span class='ident'>text</span>[<span class='self'>self</span>.<span class='ident'>last</span>..]; + <span class='self'>self</span>.<span class='ident'>last</span> <span class='op'>=</span> <span class='ident'>text</span>.<span class='ident'>len</span>(); + <span class='prelude-val'>Some</span>(<span class='ident'>s</span>) + } + } + <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=></span> { + <span class='kw'>let</span> <span class='ident'>matched</span> <span class='op'>=</span> <span class='kw-2'>&</span><span class='ident'>text</span>[<span class='self'>self</span>.<span class='ident'>last</span>..<span class='ident'>s</span>]; + <span class='self'>self</span>.<span class='ident'>last</span> <span class='op'>=</span> <span class='ident'>e</span>; + <span class='prelude-val'>Some</span>(<span class='ident'>matched</span>) + } + } + } +} + +<span class='doccomment'>/// Yields at most `N` substrings delimited by a regular expression match.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The last substring will be whatever remains after splitting.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'r` is the lifetime of the compiled expression and `'t` is the lifetime</span> +<span class='doccomment'>/// of the string being split.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>RegexSplitsN</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>splits</span>: <span class='ident'>RegexSplits</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>, + <span class='ident'>cur</span>: <span class='ident'>usize</span>, + <span class='ident'>limit</span>: <span class='ident'>usize</span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>RegexSplitsN</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span> { + <span class='kw'>let</span> <span class='ident'>text</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>splits</span>.<span class='ident'>finder</span>.<span class='ident'>search</span>; + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>cur</span> <span class='op'>>=</span> <span class='self'>self</span>.<span class='ident'>limit</span> { + <span class='prelude-val'>None</span> + } <span class='kw'>else</span> { + <span class='self'>self</span>.<span class='ident'>cur</span> <span class='op'>+=</span> <span class='number'>1</span>; + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>cur</span> <span class='op'>>=</span> <span class='self'>self</span>.<span class='ident'>limit</span> { + <span class='prelude-val'>Some</span>(<span class='kw-2'>&</span><span class='ident'>text</span>[<span class='self'>self</span>.<span class='ident'>splits</span>.<span class='ident'>last</span>..]) + } <span class='kw'>else</span> { + <span class='self'>self</span>.<span class='ident'>splits</span>.<span class='ident'>next</span>() + } + } + } +} + +<span class='doccomment'>/// Captures represents a group of captured strings for a single match.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The 0th capture always corresponds to the entire match. Each subsequent</span> +<span class='doccomment'>/// index corresponds to the next capture group in the regex.</span> +<span class='doccomment'>/// If a capture group is named, then the matched string is *also* available</span> +<span class='doccomment'>/// via the `name` method. (Note that the 0th capture is always unnamed and so</span> +<span class='doccomment'>/// must be accessed with the `at` method.)</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// Positions returned from a capture group are always byte indices.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'t` is the lifetime of the matched text.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, + <span class='ident'>locs</span>: <span class='ident'>Vec</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>>></span>, + <span class='ident'>named</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>HashMap</span><span class='op'><</span><span class='ident'>String</span>, <span class='ident'>usize</span><span class='op'>>></span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>fn</span> <span class='ident'>new</span>( + <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>Regex</span>, + <span class='ident'>search</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, + <span class='ident'>locs</span>: <span class='ident'>Vec</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>>></span>, + ) <span class='op'>-></span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>let</span> <span class='ident'>named</span> <span class='op'>=</span> + <span class='kw'>if</span> <span class='ident'>re</span>.<span class='ident'>names_len</span>() <span class='op'>==</span> <span class='number'>0</span> { + <span class='prelude-val'>None</span> + } <span class='kw'>else</span> { + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>named</span> <span class='op'>=</span> <span class='ident'>HashMap</span>::<span class='ident'>new</span>(); + <span class='kw'>for</span> (<span class='ident'>i</span>, <span class='ident'>name</span>) <span class='kw'>in</span> <span class='ident'>re</span>.<span class='ident'>names_iter</span>().<span class='ident'>enumerate</span>() { + <span class='kw'>if</span> <span class='kw'>let</span> <span class='prelude-val'>Some</span>(<span class='ident'>name</span>) <span class='op'>=</span> <span class='ident'>name</span> { + <span class='ident'>named</span>.<span class='ident'>insert</span>(<span class='ident'>name</span>, <span class='ident'>i</span>); + } + } + <span class='prelude-val'>Some</span>(<span class='ident'>named</span>) + }; + <span class='ident'>Captures</span> { + <span class='ident'>text</span>: <span class='ident'>search</span>, + <span class='ident'>locs</span>: <span class='ident'>locs</span>, + <span class='ident'>named</span>: <span class='ident'>named</span>, + } + } + + <span class='doccomment'>/// Returns the start and end positions of the Nth capture group.</span> + <span class='doccomment'>/// Returns `None` if `i` is not a valid capture group or if the capture</span> + <span class='doccomment'>/// group did not match anything.</span> + <span class='doccomment'>/// The positions returned are *always* byte indices with respect to the</span> + <span class='doccomment'>/// original string matched.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>pos</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>></span> { + <span class='kw'>let</span> (<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='op'>=</span> (<span class='ident'>i</span> <span class='op'>*</span> <span class='number'>2</span>, <span class='ident'>i</span> <span class='op'>*</span> <span class='number'>2</span> <span class='op'>+</span> <span class='number'>1</span>); + <span class='kw'>if</span> <span class='ident'>e</span> <span class='op'>>=</span> <span class='self'>self</span>.<span class='ident'>locs</span>.<span class='ident'>len</span>() <span class='op'>||</span> <span class='self'>self</span>.<span class='ident'>locs</span>[<span class='ident'>s</span>].<span class='ident'>is_none</span>() { + <span class='comment'>// VM guarantees that each pair of locations are both Some or None.</span> + <span class='kw'>return</span> <span class='prelude-val'>None</span> + } + <span class='prelude-val'>Some</span>((<span class='self'>self</span>.<span class='ident'>locs</span>[<span class='ident'>s</span>].<span class='ident'>unwrap</span>(), <span class='self'>self</span>.<span class='ident'>locs</span>[<span class='ident'>e</span>].<span class='ident'>unwrap</span>())) + } + + <span class='doccomment'>/// Returns the matched string for the capture group `i`. If `i` isn't</span> + <span class='doccomment'>/// a valid capture group or didn't match anything, then `None` is</span> + <span class='doccomment'>/// returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>at</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>i</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>pos</span>(<span class='ident'>i</span>) { + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='prelude-val'>None</span>, + <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=></span> <span class='prelude-val'>Some</span>(<span class='kw-2'>&</span><span class='self'>self</span>.<span class='ident'>text</span>[<span class='ident'>s</span>..<span class='ident'>e</span>]) + } + } + + <span class='doccomment'>/// Returns the matched string for the capture group named `name`. If</span> + <span class='doccomment'>/// `name` isn't a valid capture group or didn't match anything, then</span> + <span class='doccomment'>/// `None` is returned.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>name</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>name</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>named</span> { + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='prelude-val'>None</span>, + <span class='prelude-val'>Some</span>(<span class='kw-2'>ref</span> <span class='ident'>h</span>) <span class='op'>=></span> { + <span class='kw'>match</span> <span class='ident'>h</span>.<span class='ident'>get</span>(<span class='ident'>name</span>) { + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='prelude-val'>None</span>, + <span class='prelude-val'>Some</span>(<span class='ident'>i</span>) <span class='op'>=></span> <span class='self'>self</span>.<span class='ident'>at</span>(<span class='op'>*</span><span class='ident'>i</span>), + } + } + } + } + + <span class='doccomment'>/// Creates an iterator of all the capture groups in order of appearance</span> + <span class='doccomment'>/// in the regular expression.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>iter</span>(<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>SubCaptures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>SubCaptures</span> { <span class='ident'>idx</span>: <span class='number'>0</span>, <span class='ident'>caps</span>: <span class='self'>self</span>, } + } + + <span class='doccomment'>/// Creates an iterator of all the capture group positions in order of</span> + <span class='doccomment'>/// appearance in the regular expression. Positions are byte indices</span> + <span class='doccomment'>/// in terms of the original string matched.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>iter_pos</span>(<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>SubCapturesPos</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>SubCapturesPos</span> { <span class='ident'>idx</span>: <span class='number'>0</span>, <span class='ident'>caps</span>: <span class='self'>self</span>, } + } + + <span class='doccomment'>/// Creates an iterator of all named groups as an tuple with the group</span> + <span class='doccomment'>/// name and the value. The iterator returns these values in arbitrary</span> + <span class='doccomment'>/// order.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>iter_named</span>(<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>SubCapturesNamed</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>SubCapturesNamed</span> { <span class='ident'>caps</span>: <span class='self'>self</span>, <span class='ident'>inner</span>: <span class='self'>self</span>.<span class='ident'>named</span>.<span class='ident'>as_ref</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>n</span><span class='op'>|</span> <span class='ident'>n</span>.<span class='ident'>iter</span>()) } + } + + <span class='doccomment'>/// Expands all instances of `$name` in `text` to the corresponding capture</span> + <span class='doccomment'>/// group `name`.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// `name` may be an integer corresponding to the index of the</span> + <span class='doccomment'>/// capture group (counted by order of opening parenthesis where `0` is the</span> + <span class='doccomment'>/// entire match) or it can be a name (consisting of letters, digits or</span> + <span class='doccomment'>/// underscores) corresponding to a named capture group.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// If `name` isn't a valid capture group (whether the name doesn't exist or</span> + <span class='doccomment'>/// isn't a valid index), then it is replaced with the empty string.</span> + <span class='doccomment'>///</span> + <span class='doccomment'>/// To write a literal `$` use `$$`.</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>expand</span>(<span class='kw-2'>&</span><span class='self'>self</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>String</span> { + <span class='comment'>// How evil can you get?</span> + <span class='kw'>let</span> <span class='ident'>re</span> <span class='op'>=</span> <span class='ident'>Regex</span>::<span class='ident'>new</span>(<span class='ident'>REPLACE_EXPAND</span>).<span class='ident'>unwrap</span>(); + <span class='kw'>let</span> <span class='ident'>text</span> <span class='op'>=</span> <span class='ident'>re</span>.<span class='ident'>replace_all</span>(<span class='ident'>text</span>, <span class='op'>|</span><span class='ident'>refs</span>: <span class='kw-2'>&</span><span class='ident'>Captures</span><span class='op'>|</span> <span class='op'>-></span> <span class='ident'>String</span> { + <span class='kw'>let</span> <span class='ident'>before</span> <span class='op'>=</span> <span class='ident'>refs</span>.<span class='ident'>name</span>(<span class='string'>"before"</span>).<span class='ident'>unwrap_or</span>(<span class='string'>""</span>); + <span class='kw'>let</span> <span class='ident'>name</span> <span class='op'>=</span> <span class='ident'>refs</span>.<span class='ident'>name</span>(<span class='string'>"name"</span>).<span class='ident'>unwrap_or</span>(<span class='string'>""</span>); + <span class='macro'>format</span><span class='macro'>!</span>(<span class='string'>"{}{}"</span>, <span class='ident'>before</span>, <span class='kw'>match</span> <span class='ident'>name</span>.<span class='ident'>parse</span>::<span class='op'><</span><span class='ident'>usize</span><span class='op'>></span>() { + <span class='prelude-val'>Err</span>(_) <span class='op'>=></span> <span class='self'>self</span>.<span class='ident'>name</span>(<span class='ident'>name</span>).<span class='ident'>unwrap_or</span>(<span class='string'>""</span>).<span class='ident'>to_string</span>(), + <span class='prelude-val'>Ok</span>(<span class='ident'>i</span>) <span class='op'>=></span> <span class='self'>self</span>.<span class='ident'>at</span>(<span class='ident'>i</span>).<span class='ident'>unwrap_or</span>(<span class='string'>""</span>).<span class='ident'>to_string</span>(), + }) + }); + <span class='kw'>let</span> <span class='ident'>re</span> <span class='op'>=</span> <span class='ident'>Regex</span>::<span class='ident'>new</span>(<span class='string'>r"\$\$"</span>).<span class='ident'>unwrap</span>(); + <span class='ident'>re</span>.<span class='ident'>replace_all</span>(<span class='kw-2'>&</span><span class='ident'>text</span>, <span class='ident'>NoExpand</span>(<span class='string'>"$"</span>)) + } + + <span class='doccomment'>/// Returns the number of captured groups.</span> + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>len</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>usize</span> { <span class='self'>self</span>.<span class='ident'>locs</span>.<span class='ident'>len</span>() <span class='op'>/</span> <span class='number'>2</span> } + + <span class='doccomment'>/// Returns true if and only if there are no captured groups.</span> + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>pub</span> <span class='kw'>fn</span> <span class='ident'>is_empty</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>bool</span> { <span class='self'>self</span>.<span class='ident'>len</span>() <span class='op'>==</span> <span class='number'>0</span> } +} + +<span class='doccomment'>/// An iterator over capture groups for a particular match of a regular</span> +<span class='doccomment'>/// expression.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'t` is the lifetime of the matched text.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>SubCaptures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>idx</span>: <span class='ident'>usize</span>, + <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>SubCaptures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>>></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'><</span> <span class='self'>self</span>.<span class='ident'>caps</span>.<span class='ident'>len</span>() { + <span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'>+=</span> <span class='number'>1</span>; + <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>caps</span>.<span class='ident'>at</span>(<span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'>-</span> <span class='number'>1</span>)) + } <span class='kw'>else</span> { + <span class='prelude-val'>None</span> + } + } +} + +<span class='doccomment'>/// An iterator over capture group positions for a particular match of a</span> +<span class='doccomment'>/// regular expression.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// Positions are byte indices in terms of the original string matched.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'t` is the lifetime of the matched text.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>SubCapturesPos</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>idx</span>: <span class='ident'>usize</span>, + <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>SubCapturesPos</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>></span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>>></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'><</span> <span class='self'>self</span>.<span class='ident'>caps</span>.<span class='ident'>len</span>() { + <span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'>+=</span> <span class='number'>1</span>; + <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>caps</span>.<span class='ident'>pos</span>(<span class='self'>self</span>.<span class='ident'>idx</span> <span class='op'>-</span> <span class='number'>1</span>)) + } <span class='kw'>else</span> { + <span class='prelude-val'>None</span> + } + } +} + +<span class='doccomment'>/// An Iterator over named capture groups as a tuple with the group</span> +<span class='doccomment'>/// name and the value.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'t` is the lifetime of the matched text.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>SubCapturesNamed</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>{ + <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>, + <span class='ident'>inner</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Iter</span><span class='op'><</span><span class='lifetime'>'t</span>, <span class='ident'>String</span>, <span class='ident'>usize</span><span class='op'>>></span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>SubCapturesNamed</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> (<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span>); + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, <span class='prelude-ty'>Option</span><span class='op'><</span><span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span><span class='op'>></span>)<span class='op'>></span> { + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>inner</span>.<span class='ident'>as_mut</span>().<span class='ident'>map</span>(<span class='op'>|</span><span class='ident'>it</span><span class='op'>|</span> <span class='ident'>it</span>.<span class='ident'>next</span>()).<span class='ident'>unwrap_or</span>(<span class='prelude-val'>None</span>) { + <span class='prelude-val'>Some</span>((<span class='ident'>name</span>, <span class='ident'>pos</span>)) <span class='op'>=></span> <span class='prelude-val'>Some</span>((<span class='ident'>name</span>, <span class='self'>self</span>.<span class='ident'>caps</span>.<span class='ident'>at</span>(<span class='op'>*</span><span class='ident'>pos</span>))), + <span class='prelude-val'>None</span> <span class='op'>=></span> <span class='prelude-val'>None</span> + } + } +} + +<span class='doccomment'>/// An iterator that yields all non-overlapping capture groups matching a</span> +<span class='doccomment'>/// particular regular expression.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The iterator stops when no more matches can be found.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'r` is the lifetime of the compiled expression and `'t` is the lifetime</span> +<span class='doccomment'>/// of the matched string.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>FindCaptures</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='ident'>Regex</span>, + <span class='ident'>search</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, + <span class='ident'>last_match</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>></span>, + <span class='ident'>last_end</span>: <span class='ident'>usize</span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>FindCaptures</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> <span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span>; + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>Captures</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>>></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>></span> <span class='self'>self</span>.<span class='ident'>search</span>.<span class='ident'>len</span>() { + <span class='kw'>return</span> <span class='prelude-val'>None</span> + } + + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>caps</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>re</span>.<span class='ident'>alloc_captures</span>(); + <span class='kw'>if</span> <span class='op'>!</span><span class='ident'>exec</span>(<span class='self'>self</span>.<span class='ident'>re</span>, <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>caps</span>, <span class='self'>self</span>.<span class='ident'>search</span>, <span class='self'>self</span>.<span class='ident'>last_end</span>) { + <span class='kw'>return</span> <span class='prelude-val'>None</span> + } + <span class='kw'>let</span> (<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='op'>=</span> (<span class='ident'>caps</span>[<span class='number'>0</span>].<span class='ident'>unwrap</span>(), <span class='ident'>caps</span>[<span class='number'>1</span>].<span class='ident'>unwrap</span>()); + + <span class='comment'>// Don't accept empty matches immediately following a match.</span> + <span class='comment'>// i.e., no infinite loops please.</span> + <span class='kw'>if</span> <span class='ident'>e</span> <span class='op'>==</span> <span class='ident'>s</span> <span class='op'>&&</span> <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>last_end</span>) <span class='op'>==</span> <span class='self'>self</span>.<span class='ident'>last_match</span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>>=</span> <span class='self'>self</span>.<span class='ident'>search</span>.<span class='ident'>len</span>() { + <span class='kw'>return</span> <span class='prelude-val'>None</span>; + } + <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>+=</span> <span class='self'>self</span>.<span class='ident'>search</span>[<span class='self'>self</span>.<span class='ident'>last_end</span>..].<span class='ident'>chars</span>() + .<span class='ident'>next</span>().<span class='ident'>unwrap</span>().<span class='ident'>len_utf8</span>(); + <span class='kw'>return</span> <span class='self'>self</span>.<span class='ident'>next</span>() + } + <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>=</span> <span class='ident'>e</span>; + <span class='self'>self</span>.<span class='ident'>last_match</span> <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>last_end</span>); + <span class='prelude-val'>Some</span>(<span class='ident'>Captures</span>::<span class='ident'>new</span>(<span class='self'>self</span>.<span class='ident'>re</span>, <span class='self'>self</span>.<span class='ident'>search</span>, <span class='ident'>caps</span>)) + } +} + +<span class='doccomment'>/// An iterator over all non-overlapping matches for a particular string.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// The iterator yields a tuple of integers corresponding to the start and end</span> +<span class='doccomment'>/// of the match. The indices are byte offsets. The iterator stops when no more</span> +<span class='doccomment'>/// matches can be found.</span> +<span class='doccomment'>///</span> +<span class='doccomment'>/// `'r` is the lifetime of the compiled expression and `'t` is the lifetime</span> +<span class='doccomment'>/// of the matched string.</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>FindMatches</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>re</span>: <span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='ident'>Regex</span>, + <span class='ident'>search</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>, + <span class='ident'>last_match</span>: <span class='prelude-ty'>Option</span><span class='op'><</span><span class='ident'>usize</span><span class='op'>></span>, + <span class='ident'>last_end</span>: <span class='ident'>usize</span>, +} + +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Iterator</span> <span class='kw'>for</span> <span class='ident'>FindMatches</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='kw'>type</span> <span class='ident'>Item</span> <span class='op'>=</span> (<span class='ident'>usize</span>, <span class='ident'>usize</span>); + + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>></span> <span class='self'>self</span>.<span class='ident'>search</span>.<span class='ident'>len</span>() { + <span class='kw'>return</span> <span class='prelude-val'>None</span> + } + + <span class='kw'>let</span> <span class='kw-2'>mut</span> <span class='ident'>caps</span> <span class='op'>=</span> [<span class='prelude-val'>None</span>, <span class='prelude-val'>None</span>]; + <span class='kw'>if</span> <span class='op'>!</span><span class='ident'>exec</span>(<span class='self'>self</span>.<span class='ident'>re</span>, <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>caps</span>, <span class='self'>self</span>.<span class='ident'>search</span>, <span class='self'>self</span>.<span class='ident'>last_end</span>) { + <span class='kw'>return</span> <span class='prelude-val'>None</span>; + } + <span class='kw'>let</span> (<span class='ident'>s</span>, <span class='ident'>e</span>) <span class='op'>=</span> (<span class='ident'>caps</span>[<span class='number'>0</span>].<span class='ident'>unwrap</span>(), <span class='ident'>caps</span>[<span class='number'>1</span>].<span class='ident'>unwrap</span>()); + + <span class='comment'>// Don't accept empty matches immediately following a match.</span> + <span class='comment'>// i.e., no infinite loops please.</span> + <span class='kw'>if</span> <span class='ident'>e</span> <span class='op'>==</span> <span class='ident'>s</span> <span class='op'>&&</span> <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>last_end</span>) <span class='op'>==</span> <span class='self'>self</span>.<span class='ident'>last_match</span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>>=</span> <span class='self'>self</span>.<span class='ident'>search</span>.<span class='ident'>len</span>() { + <span class='kw'>return</span> <span class='prelude-val'>None</span>; + } + <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>+=</span> <span class='self'>self</span>.<span class='ident'>search</span>[<span class='self'>self</span>.<span class='ident'>last_end</span>..].<span class='ident'>chars</span>() + .<span class='ident'>next</span>().<span class='ident'>unwrap</span>().<span class='ident'>len_utf8</span>(); + <span class='kw'>return</span> <span class='self'>self</span>.<span class='ident'>next</span>() + } + <span class='self'>self</span>.<span class='ident'>last_end</span> <span class='op'>=</span> <span class='ident'>e</span>; + <span class='self'>self</span>.<span class='ident'>last_match</span> <span class='op'>=</span> <span class='prelude-val'>Some</span>(<span class='self'>self</span>.<span class='ident'>last_end</span>); + <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) + } +} + +<span class='attribute'>#[<span class='ident'>cfg</span>(<span class='ident'>feature</span> <span class='op'>=</span> <span class='string'>"pattern"</span>)]</span> +<span class='kw'>pub</span> <span class='kw'>struct</span> <span class='ident'>RegexSearcher</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>it</span>: <span class='ident'>FindMatches</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>, + <span class='ident'>last_step_end</span>: <span class='ident'>usize</span>, + <span class='ident'>next_match</span>: <span class='prelude-ty'>Option</span><span class='op'><</span>(<span class='ident'>usize</span>, <span class='ident'>usize</span>)<span class='op'>></span>, +} + +<span class='attribute'>#[<span class='ident'>cfg</span>(<span class='ident'>feature</span> <span class='op'>=</span> <span class='string'>"pattern"</span>)]</span> +<span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Pattern</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='kw'>for</span> <span class='kw-2'>&</span><span class='lifetime'>'r</span> <span class='ident'>Regex</span> { + <span class='kw'>type</span> <span class='ident'>Searcher</span> <span class='op'>=</span> <span class='ident'>RegexSearcher</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span>; + + <span class='kw'>fn</span> <span class='ident'>into_searcher</span>(<span class='self'>self</span>, <span class='ident'>haystack</span>: <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span>) <span class='op'>-></span> <span class='ident'>RegexSearcher</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='ident'>RegexSearcher</span> { + <span class='ident'>it</span>: <span class='self'>self</span>.<span class='ident'>find_iter</span>(<span class='ident'>haystack</span>), + <span class='ident'>last_step_end</span>: <span class='number'>0</span>, + <span class='ident'>next_match</span>: <span class='prelude-val'>None</span>, + } + } +} + +<span class='attribute'>#[<span class='ident'>cfg</span>(<span class='ident'>feature</span> <span class='op'>=</span> <span class='string'>"pattern"</span>)]</span> +<span class='kw'>unsafe</span> <span class='kw'>impl</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> <span class='ident'>Searcher</span><span class='op'><</span><span class='lifetime'>'t</span><span class='op'>></span> <span class='kw'>for</span> <span class='ident'>RegexSearcher</span><span class='op'><</span><span class='lifetime'>'r</span>, <span class='lifetime'>'t</span><span class='op'>></span> { + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>haystack</span>(<span class='kw-2'>&</span><span class='self'>self</span>) <span class='op'>-></span> <span class='kw-2'>&</span><span class='lifetime'>'t</span> <span class='ident'>str</span> { + <span class='self'>self</span>.<span class='ident'>it</span>.<span class='ident'>search</span> + } + + <span class='attribute'>#[<span class='ident'>inline</span>]</span> + <span class='kw'>fn</span> <span class='ident'>next</span>(<span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='self'>self</span>) <span class='op'>-></span> <span class='ident'>SearchStep</span> { + <span class='kw'>if</span> <span class='kw'>let</span> <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>next_match</span> { + <span class='self'>self</span>.<span class='ident'>next_match</span> <span class='op'>=</span> <span class='prelude-val'>None</span>; + <span class='self'>self</span>.<span class='ident'>last_step_end</span> <span class='op'>=</span> <span class='ident'>e</span>; + <span class='kw'>return</span> <span class='ident'>SearchStep</span>::<span class='ident'>Match</span>(<span class='ident'>s</span>, <span class='ident'>e</span>); + } + <span class='kw'>match</span> <span class='self'>self</span>.<span class='ident'>it</span>.<span class='ident'>next</span>() { + <span class='prelude-val'>None</span> <span class='op'>=></span> { + <span class='kw'>if</span> <span class='self'>self</span>.<span class='ident'>last_step_end</span> <span class='op'><</span> <span class='self'>self</span>.<span class='ident'>haystack</span>().<span class='ident'>len</span>() { + <span class='kw'>let</span> <span class='ident'>last</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>last_step_end</span>; + <span class='self'>self</span>.<span class='ident'>last_step_end</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>haystack</span>().<span class='ident'>len</span>(); + <span class='ident'>SearchStep</span>::<span class='ident'>Reject</span>(<span class='ident'>last</span>, <span class='self'>self</span>.<span class='ident'>haystack</span>().<span class='ident'>len</span>()) + } <span class='kw'>else</span> { + <span class='ident'>SearchStep</span>::<span class='ident'>Done</span> + } + } + <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)) <span class='op'>=></span> { + <span class='kw'>if</span> <span class='ident'>s</span> <span class='op'>==</span> <span class='self'>self</span>.<span class='ident'>last_step_end</span> { + <span class='self'>self</span>.<span class='ident'>last_step_end</span> <span class='op'>=</span> <span class='ident'>e</span>; + <span class='ident'>SearchStep</span>::<span class='ident'>Match</span>(<span class='ident'>s</span>, <span class='ident'>e</span>) + } <span class='kw'>else</span> { + <span class='self'>self</span>.<span class='ident'>next_match</span> <span class='op'>=</span> <span class='prelude-val'>Some</span>((<span class='ident'>s</span>, <span class='ident'>e</span>)); + <span class='kw'>let</span> <span class='ident'>last</span> <span class='op'>=</span> <span class='self'>self</span>.<span class='ident'>last_step_end</span>; + <span class='self'>self</span>.<span class='ident'>last_step_end</span> <span class='op'>=</span> <span class='ident'>s</span>; + <span class='ident'>SearchStep</span>::<span class='ident'>Reject</span>(<span class='ident'>last</span>, <span class='ident'>s</span>) + } + } + } + } +} + +<span class='kw'>fn</span> <span class='ident'>exec</span>(<span class='ident'>re</span>: <span class='kw-2'>&</span><span class='ident'>Regex</span>, <span class='ident'>caps</span>: <span class='kw-2'>&</span><span class='kw-2'>mut</span> <span class='ident'>CaptureIdxs</span>, <span class='ident'>text</span>: <span class='kw-2'>&</span><span class='ident'>str</span>, <span class='ident'>start</span>: <span class='ident'>usize</span>) <span class='op'>-></span> <span class='ident'>bool</span> { + <span class='kw'>match</span> <span class='op'>*</span><span class='ident'>re</span> { + <span class='ident'>Regex</span>::<span class='ident'>Native</span>(<span class='ident'>ExNative</span> { <span class='kw-2'>ref</span> <span class='ident'>prog</span>, .. }) <span class='op'>=></span> (<span class='op'>*</span><span class='ident'>prog</span>)(<span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>), + <span class='ident'>Regex</span>::<span class='ident'>Dynamic</span>(<span class='kw-2'>ref</span> <span class='ident'>prog</span>) <span class='op'>=></span> <span class='ident'>prog</span>.<span class='ident'>exec</span>(<span class='ident'>caps</span>, <span class='ident'>text</span>, <span class='ident'>start</span>), + } +} +</pre> +</section> + <section id='search' class="content hidden"></section> + + <section class="footer"></section> + + <div id="help" class="hidden"> + <div class="shortcuts"> + <h1>Keyboard shortcuts</h1> + <dl> + <dt>?</dt> + <dd>Show this help dialog</dd> + <dt>S</dt> + <dd>Focus the search field</dd> + <dt>⇤</dt> + <dd>Move up in search results</dd> + <dt>⇥</dt> + <dd>Move down in search results</dd> + <dt>⏎</dt> + <dd>Go to active search result</dd> + </dl> + </div> + <div class="infos"> + <h1>Search tricks</h1> + <p> + Prefix searches with a type followed by a colon (e.g. + <code>fn:</code>) to restrict the search to a given type. + </p> + <p> + Accepted types are: <code>fn</code>, <code>mod</code>, + <code>struct</code>, <code>enum</code>, + <code>trait</code>, <code>typedef</code> (or + <code>tdef</code>). + </p> + <p> + Search functions by type signature (e.g. + <code>vec -> usize</code>) + </p> + </div> + </div> + + + + <script> + window.rootPath = "../../"; + window.currentCrate = "regex"; + window.playgroundUrl = ""; + </script> + <script src="../../jquery.js"></script> + <script src="../../main.js"></script> + + <script async src="../../search-index.js"></script> +</body> +</html>
\ No newline at end of file |