| <!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/memchr-2.5.0/src/memmem/rarebytes.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>rarebytes.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="../../../memchr/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="../../../memchr/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| </pre><pre class="rust"><code><span class="doccomment">/// A heuristic frequency based detection of rare bytes for substring search. |
| /// |
| /// This detector attempts to pick out two bytes in a needle that are predicted |
| /// to occur least frequently. The purpose is to use these bytes to implement |
| /// fast candidate search using vectorized code. |
| /// |
| /// A set of offsets is only computed for needles of length 2 or greater. |
| /// Smaller needles should be special cased by the substring search algorithm |
| /// in use. (e.g., Use memchr for single byte needles.) |
| /// |
| /// Note that we use `u8` to represent the offsets of the rare bytes in a |
| /// needle to reduce space usage. This means that rare byte occurring after the |
| /// first 255 bytes in a needle will never be used. |
| </span><span class="attribute">#[derive(Clone, Copy, Debug, Default)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>RareNeedleBytes { |
| <span class="doccomment">/// The leftmost offset of the rarest byte in the needle, according to |
| /// pre-computed frequency analysis. The "leftmost offset" means that |
| /// rare1i <= i for all i where needle[i] == needle[rare1i]. |
| </span>rare1i: u8, |
| <span class="doccomment">/// The leftmost offset of the second rarest byte in the needle, according |
| /// to pre-computed frequency analysis. The "leftmost offset" means that |
| /// rare2i <= i for all i where needle[i] == needle[rare2i]. |
| /// |
| /// The second rarest byte is used as a type of guard for quickly detecting |
| /// a mismatch if the first byte matches. This is a hedge against |
| /// pathological cases where the pre-computed frequency analysis may be |
| /// off. (But of course, does not prevent *all* pathological cases.) |
| /// |
| /// In general, rare1i != rare2i by construction, although there is no hard |
| /// requirement that they be different. However, since the case of a single |
| /// byte needle is handled specially by memchr itself, rare2i generally |
| /// always should be different from rare1i since it would otherwise be |
| /// ineffective as a guard. |
| </span>rare2i: u8, |
| } |
| |
| <span class="kw">impl </span>RareNeedleBytes { |
| <span class="doccomment">/// Create a new pair of rare needle bytes with the given offsets. This is |
| /// only used in tests for generating input data. |
| </span><span class="attribute">#[cfg(all(test, feature = <span class="string">"std"</span>))] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(rare1i: u8, rare2i: u8) -> RareNeedleBytes { |
| RareNeedleBytes { rare1i, rare2i } |
| } |
| |
| <span class="doccomment">/// Detect the leftmost offsets of the two rarest bytes in the given |
| /// needle. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>forward(needle: <span class="kw-2">&</span>[u8]) -> RareNeedleBytes { |
| <span class="kw">if </span>needle.len() <= <span class="number">1 </span>|| needle.len() > core::u8::MAX <span class="kw">as </span>usize { |
| <span class="comment">// For needles bigger than u8::MAX, our offsets aren't big enough. |
| // (We make our offsets small to reduce stack copying.) |
| // If you have a use case for it, please file an issue. In that |
| // case, we should probably just adjust the routine below to pick |
| // some rare bytes from the first 255 bytes of the needle. |
| // |
| // Also note that for needles of size 0 or 1, they are special |
| // cased in Two-Way. |
| // |
| // TODO: Benchmar this. |
| </span><span class="kw">return </span>RareNeedleBytes { rare1i: <span class="number">0</span>, rare2i: <span class="number">0 </span>}; |
| } |
| |
| <span class="comment">// Find the rarest two bytes. We make them distinct by construction. |
| </span><span class="kw">let </span>(<span class="kw-2">mut </span>rare1, <span class="kw-2">mut </span>rare1i) = (needle[<span class="number">0</span>], <span class="number">0</span>); |
| <span class="kw">let </span>(<span class="kw-2">mut </span>rare2, <span class="kw-2">mut </span>rare2i) = (needle[<span class="number">1</span>], <span class="number">1</span>); |
| <span class="kw">if </span>rank(rare2) < rank(rare1) { |
| core::mem::swap(<span class="kw-2">&mut </span>rare1, <span class="kw-2">&mut </span>rare2); |
| core::mem::swap(<span class="kw-2">&mut </span>rare1i, <span class="kw-2">&mut </span>rare2i); |
| } |
| <span class="kw">for </span>(i, <span class="kw-2">&</span>b) <span class="kw">in </span>needle.iter().enumerate().skip(<span class="number">2</span>) { |
| <span class="kw">if </span>rank(b) < rank(rare1) { |
| rare2 = rare1; |
| rare2i = rare1i; |
| rare1 = b; |
| rare1i = i <span class="kw">as </span>u8; |
| } <span class="kw">else if </span>b != rare1 && rank(b) < rank(rare2) { |
| rare2 = b; |
| rare2i = i <span class="kw">as </span>u8; |
| } |
| } |
| <span class="comment">// While not strictly required, we really don't want these to be |
| // equivalent. If they were, it would reduce the effectiveness of |
| // candidate searching using these rare bytes by increasing the rate of |
| // false positives. |
| </span><span class="macro">assert_ne!</span>(rare1i, rare2i); |
| RareNeedleBytes { rare1i, rare2i } |
| } |
| |
| <span class="doccomment">/// Return the rare bytes in the given needle in the forward direction. |
| /// The needle given must be the same one given to the RareNeedleBytes |
| /// constructor. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>as_rare_bytes(<span class="kw-2">&</span><span class="self">self</span>, needle: <span class="kw-2">&</span>[u8]) -> (u8, u8) { |
| (needle[<span class="self">self</span>.rare1i <span class="kw">as </span>usize], needle[<span class="self">self</span>.rare2i <span class="kw">as </span>usize]) |
| } |
| |
| <span class="doccomment">/// Return the rare offsets such that the first offset is always <= to the |
| /// second offset. This is useful when the caller doesn't care whether |
| /// rare1 is rarer than rare2, but just wants to ensure that they are |
| /// ordered with respect to one another. |
| </span><span class="attribute">#[cfg(memchr_runtime_simd)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>as_rare_ordered_usize(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, usize) { |
| <span class="kw">let </span>(rare1i, rare2i) = <span class="self">self</span>.as_rare_ordered_u8(); |
| (rare1i <span class="kw">as </span>usize, rare2i <span class="kw">as </span>usize) |
| } |
| |
| <span class="doccomment">/// Like as_rare_ordered_usize, but returns the offsets as their native |
| /// u8 values. |
| </span><span class="attribute">#[cfg(memchr_runtime_simd)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>as_rare_ordered_u8(<span class="kw-2">&</span><span class="self">self</span>) -> (u8, u8) { |
| <span class="kw">if </span><span class="self">self</span>.rare1i <= <span class="self">self</span>.rare2i { |
| (<span class="self">self</span>.rare1i, <span class="self">self</span>.rare2i) |
| } <span class="kw">else </span>{ |
| (<span class="self">self</span>.rare2i, <span class="self">self</span>.rare1i) |
| } |
| } |
| |
| <span class="doccomment">/// Return the rare offsets as usize values in the order in which they were |
| /// constructed. rare1, for example, is constructed as the "rarer" byte, |
| /// and thus, callers may want to treat it differently from rare2. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>as_rare_usize(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, usize) { |
| (<span class="self">self</span>.rare1i <span class="kw">as </span>usize, <span class="self">self</span>.rare2i <span class="kw">as </span>usize) |
| } |
| |
| <span class="doccomment">/// Return the byte frequency rank of each byte. The higher the rank, the |
| /// more frequency the byte is predicted to be. The needle given must be |
| /// the same one given to the RareNeedleBytes constructor. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>as_ranks(<span class="kw-2">&</span><span class="self">self</span>, needle: <span class="kw-2">&</span>[u8]) -> (usize, usize) { |
| <span class="kw">let </span>(b1, b2) = <span class="self">self</span>.as_rare_bytes(needle); |
| (rank(b1), rank(b2)) |
| } |
| } |
| |
| <span class="doccomment">/// Return the heuristical frequency rank of the given byte. A lower rank |
| /// means the byte is believed to occur less frequently. |
| </span><span class="kw">fn </span>rank(b: u8) -> usize { |
| <span class="kw">crate</span>::memmem::byte_frequencies::BYTE_FREQUENCIES[b <span class="kw">as </span>usize] <span class="kw">as </span>usize |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="memchr" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
