| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/aho-corasick-1.0.2/src/packed/rabinkarp.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>rabinkarp.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../aho_corasick/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../aho_corasick/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>alloc::{vec, vec::Vec}; |
| |
| <span class="kw">use crate</span>::{ |
| packed::pattern::{PatternID, Patterns}, |
| util::search::Match, |
| }; |
| |
| <span class="doccomment">/// The type of the rolling hash used in the Rabin-Karp algorithm. |
| </span><span class="kw">type </span>Hash = usize; |
| |
| <span class="doccomment">/// The number of buckets to store our patterns in. We don't want this to be |
| /// too big in order to avoid wasting memory, but we don't want it to be too |
| /// small either to avoid spending too much time confirming literals. |
| /// |
| /// The number of buckets MUST be a power of two. Otherwise, determining the |
| /// bucket from a hash will slow down the code considerably. Using a power |
| /// of two means `hash % NUM_BUCKETS` can compile down to a simple `and` |
| /// instruction. |
| </span><span class="kw">const </span>NUM_BUCKETS: usize = <span class="number">64</span>; |
| |
| <span class="doccomment">/// An implementation of the Rabin-Karp algorithm. The main idea of this |
| /// algorithm is to maintain a rolling hash as it moves through the input, and |
| /// then check whether that hash corresponds to the same hash for any of the |
| /// patterns we're looking for. |
| /// |
| /// A draw back of naively scaling Rabin-Karp to multiple patterns is that |
| /// it requires all of the patterns to be the same length, which in turn |
| /// corresponds to the number of bytes to hash. We adapt this to work for |
| /// multiple patterns of varying size by fixing the number of bytes to hash |
| /// to be the length of the smallest pattern. We also split the patterns into |
| /// several buckets to hopefully make the confirmation step faster. |
| /// |
| /// Wikipedia has a decent explanation, if a bit heavy on the theory: |
| /// https://en.wikipedia.org/wiki/Rabin%E2%80%93Karp_algorithm |
| /// |
| /// But ESMAJ provides something a bit more concrete: |
| /// https://www-igm.univ-mlv.fr/~lecroq/string/node5.html |
| </span><span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">pub struct </span>RabinKarp { |
| <span class="doccomment">/// The order of patterns in each bucket is significant. Namely, they are |
| /// arranged such that the first one to match is the correct match. This |
| /// may not necessarily correspond to the order provided by the caller. |
| /// For example, if leftmost-longest semantics are used, then the patterns |
| /// are sorted by their length in descending order. If leftmost-first |
| /// semantics are used, then the patterns are sorted by their pattern ID |
| /// in ascending order (which corresponds to the caller's order). |
| </span>buckets: Vec<Vec<(Hash, PatternID)>>, |
| <span class="doccomment">/// The length of the hashing window. Generally, this corresponds to the |
| /// length of the smallest pattern. |
| </span>hash_len: usize, |
| <span class="doccomment">/// The factor to subtract out of a hash before updating it with a new |
| /// byte. |
| </span>hash_2pow: usize, |
| <span class="doccomment">/// The maximum identifier of a pattern. This is used as a sanity check |
| /// to ensure that the patterns provided by the caller are the same as |
| /// the patterns that were used to compile the matcher. This sanity check |
| /// possibly permits safely eliminating bounds checks regardless of what |
| /// patterns are provided by the caller. |
| /// |
| /// (Currently, we don't use this to elide bounds checks since it doesn't |
| /// result in a measurable performance improvement, but we do use it for |
| /// better failure modes.) |
| </span>max_pattern_id: PatternID, |
| } |
| |
| <span class="kw">impl </span>RabinKarp { |
| <span class="doccomment">/// Compile a new Rabin-Karp matcher from the patterns given. |
| /// |
| /// This panics if any of the patterns in the collection are empty, or if |
| /// the collection is itself empty. |
| </span><span class="kw">pub fn </span>new(patterns: <span class="kw-2">&</span>Patterns) -> RabinKarp { |
| <span class="macro">assert!</span>(patterns.len() >= <span class="number">1</span>); |
| <span class="kw">let </span>hash_len = patterns.minimum_len(); |
| <span class="macro">assert!</span>(hash_len >= <span class="number">1</span>); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>hash_2pow = <span class="number">1usize</span>; |
| <span class="kw">for _ in </span><span class="number">1</span>..hash_len { |
| hash_2pow = hash_2pow.wrapping_shl(<span class="number">1</span>); |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>rk = RabinKarp { |
| buckets: <span class="macro">vec!</span>[<span class="macro">vec!</span>[]; NUM_BUCKETS], |
| hash_len, |
| hash_2pow, |
| max_pattern_id: patterns.max_pattern_id(), |
| }; |
| <span class="kw">for </span>(id, pat) <span class="kw">in </span>patterns.iter() { |
| <span class="kw">let </span>hash = rk.hash(<span class="kw-2">&</span>pat.bytes()[..rk.hash_len]); |
| <span class="kw">let </span>bucket = hash % NUM_BUCKETS; |
| rk.buckets[bucket].push((hash, id)); |
| } |
| rk |
| } |
| |
| <span class="doccomment">/// Return the first matching pattern in the given haystack, begining the |
| /// search at `at`. |
| </span><span class="kw">pub fn </span>find_at( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| patterns: <span class="kw-2">&</span>Patterns, |
| haystack: <span class="kw-2">&</span>[u8], |
| <span class="kw-2">mut </span>at: usize, |
| ) -> <span class="prelude-ty">Option</span><Match> { |
| <span class="macro">assert_eq!</span>(NUM_BUCKETS, <span class="self">self</span>.buckets.len()); |
| <span class="macro">assert_eq!</span>( |
| <span class="self">self</span>.max_pattern_id, |
| patterns.max_pattern_id(), |
| <span class="string">"Rabin-Karp must be called with same patterns it was built with"</span>, |
| ); |
| |
| <span class="kw">if </span>at + <span class="self">self</span>.hash_len > haystack.len() { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>hash = <span class="self">self</span>.hash(<span class="kw-2">&</span>haystack[at..at + <span class="self">self</span>.hash_len]); |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>bucket = <span class="kw-2">&</span><span class="self">self</span>.buckets[hash % NUM_BUCKETS]; |
| <span class="kw">for </span><span class="kw-2">&</span>(phash, pid) <span class="kw">in </span>bucket { |
| <span class="kw">if </span>phash == hash { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(c) = <span class="self">self</span>.verify(patterns, pid, haystack, at) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(c); |
| } |
| } |
| } |
| <span class="kw">if </span>at + <span class="self">self</span>.hash_len >= haystack.len() { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| hash = <span class="self">self</span>.update_hash( |
| hash, |
| haystack[at], |
| haystack[at + <span class="self">self</span>.hash_len], |
| ); |
| at += <span class="number">1</span>; |
| } |
| } |
| |
| <span class="doccomment">/// Returns the approximate total amount of heap used by this searcher, in |
| /// units of bytes. |
| </span><span class="kw">pub fn </span>memory_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="kw">let </span>num_patterns = <span class="self">self</span>.max_pattern_id <span class="kw">as </span>usize + <span class="number">1</span>; |
| <span class="self">self</span>.buckets.len() * core::mem::size_of::<Vec<(Hash, PatternID)>>() |
| + num_patterns * core::mem::size_of::<(Hash, PatternID)>() |
| } |
| |
| <span class="doccomment">/// Verify whether the pattern with the given id matches at |
| /// `haystack[at..]`. |
| /// |
| /// We tag this function as `cold` because it helps improve codegen. |
| /// Intuitively, it would seem like inlining it would be better. However, |
| /// the only time this is called and a match is not found is when there |
| /// there is a hash collision, or when a prefix of a pattern matches but |
| /// the entire pattern doesn't match. This is hopefully fairly rare, and |
| /// if it does occur a lot, it's going to be slow no matter what we do. |
| </span><span class="attribute">#[cold] |
| </span><span class="kw">fn </span>verify( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| patterns: <span class="kw-2">&</span>Patterns, |
| id: PatternID, |
| haystack: <span class="kw-2">&</span>[u8], |
| at: usize, |
| ) -> <span class="prelude-ty">Option</span><Match> { |
| <span class="kw">let </span>pat = patterns.get(id); |
| <span class="kw">if </span>pat.is_prefix(<span class="kw-2">&</span>haystack[at..]) { |
| <span class="prelude-val">Some</span>(Match::must(id <span class="kw">as </span>usize, at..at + pat.len())) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="doccomment">/// Hash the given bytes. |
| </span><span class="kw">fn </span>hash(<span class="kw-2">&</span><span class="self">self</span>, bytes: <span class="kw-2">&</span>[u8]) -> Hash { |
| <span class="macro">assert_eq!</span>(<span class="self">self</span>.hash_len, bytes.len()); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>hash = <span class="number">0usize</span>; |
| <span class="kw">for </span><span class="kw-2">&</span>b <span class="kw">in </span>bytes { |
| hash = hash.wrapping_shl(<span class="number">1</span>).wrapping_add(b <span class="kw">as </span>usize); |
| } |
| hash |
| } |
| |
| <span class="doccomment">/// Update the hash given based on removing `old_byte` at the beginning |
| /// of some byte string, and appending `new_byte` to the end of that same |
| /// byte string. |
| </span><span class="kw">fn </span>update_hash(<span class="kw-2">&</span><span class="self">self</span>, prev: Hash, old_byte: u8, new_byte: u8) -> Hash { |
| prev.wrapping_sub((old_byte <span class="kw">as </span>usize).wrapping_mul(<span class="self">self</span>.hash_2pow)) |
| .wrapping_shl(<span class="number">1</span>) |
| .wrapping_add(new_byte <span class="kw">as </span>usize) |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="aho_corasick" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
