| <!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/prefilter/fallback.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>fallback.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> |
| </pre><pre class="rust"><code><span class="comment">/* |
| This module implements a "fallback" prefilter that only relies on memchr to |
| function. While memchr works best when it's explicitly vectorized, its |
| fallback implementations are fast enough to make a prefilter like this |
| worthwhile. |
| |
| The essence of this implementation is to identify two rare bytes in a needle |
| based on a background frequency distribution of bytes. We then run memchr on the |
| rarer byte. For each match, we use the second rare byte as a guard to quickly |
| check if a match is possible. If the position passes the guard test, then we do |
| a naive memcmp to confirm the match. |
| |
| In practice, this formulation works amazingly well, primarily because of the |
| heuristic use of a background frequency distribution. However, it does have a |
| number of weaknesses where it can get quite slow when its background frequency |
| distribution doesn't line up with the haystack being searched. This is why we |
| have specialized vector routines that essentially take this idea and move the |
| guard check into vectorized code. (Those specialized vector routines do still |
| make use of the background frequency distribution of bytes though.) |
| |
| This fallback implementation was originally formulated in regex many moons ago: |
| https://github.com/rust-lang/regex/blob/3db8722d0b204a85380fe2a65e13d7065d7dd968/src/literal/imp.rs#L370-L501 |
| Prior to that, I'm not aware of anyone using this technique in any prominent |
| substring search implementation. Although, I'm sure folks have had this same |
| insight long before me. |
| |
| Another version of this also appeared in bstr: |
| https://github.com/BurntSushi/bstr/blob/a444256ca7407fe180ee32534688549655b7a38e/src/search/prefilter.rs#L83-L340 |
| */ |
| |
| </span><span class="kw">use </span><span class="kw">crate</span>::memmem::{ |
| prefilter::{PrefilterFnTy, PrefilterState}, |
| NeedleInfo, |
| }; |
| |
| <span class="comment">// Check that the functions below satisfy the Prefilter function type. |
| </span><span class="kw">const _</span>: PrefilterFnTy = find; |
| |
| <span class="doccomment">/// Look for a possible occurrence of needle. The position returned |
| /// corresponds to the beginning of the occurrence, if one exists. |
| /// |
| /// Callers may assume that this never returns false negatives (i.e., it |
| /// never misses an actual occurrence), but must check that the returned |
| /// position corresponds to a match. That is, it can return false |
| /// positives. |
| /// |
| /// This should only be used when Freqy is constructed for forward |
| /// searching. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>find( |
| prestate: <span class="kw-2">&mut </span>PrefilterState, |
| ninfo: <span class="kw-2">&</span>NeedleInfo, |
| haystack: <span class="kw-2">&</span>[u8], |
| needle: <span class="kw-2">&</span>[u8], |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">let </span><span class="kw-2">mut </span>i = <span class="number">0</span>; |
| <span class="kw">let </span>(rare1i, rare2i) = ninfo.rarebytes.as_rare_usize(); |
| <span class="kw">let </span>(rare1, rare2) = ninfo.rarebytes.as_rare_bytes(needle); |
| <span class="kw">while </span>prestate.is_effective() { |
| <span class="comment">// Use a fast vectorized implementation to skip to the next |
| // occurrence of the rarest byte (heuristically chosen) in the |
| // needle. |
| </span><span class="kw">let </span>found = <span class="kw">crate</span>::memchr(rare1, <span class="kw-2">&</span>haystack[i..])<span class="question-mark">?</span>; |
| prestate.update(found); |
| i += found; |
| |
| <span class="comment">// If we can't align our first match with the haystack, then a |
| // match is impossible. |
| </span><span class="kw">if </span>i < rare1i { |
| i += <span class="number">1</span>; |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="comment">// Align our rare2 byte with the haystack. A mismatch means that |
| // a match is impossible. |
| </span><span class="kw">let </span>aligned_rare2i = i - rare1i + rare2i; |
| <span class="kw">if </span>haystack.get(aligned_rare2i) != <span class="prelude-val">Some</span>(<span class="kw-2">&</span>rare2) { |
| i += <span class="number">1</span>; |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="comment">// We've done what we can. There might be a match here. |
| </span><span class="kw">return </span><span class="prelude-val">Some</span>(i - rare1i); |
| } |
| <span class="comment">// The only way we get here is if we believe our skipping heuristic |
| // has become ineffective. We're allowed to return false positives, |
| // so return the position at which we advanced to, aligned to the |
| // haystack. |
| </span><span class="prelude-val">Some</span>(i.saturating_sub(rare1i)) |
| } |
| |
| <span class="attribute">#[cfg(all(test, feature = <span class="string">"std"</span>))] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| |
| <span class="kw">fn </span>freqy_find(haystack: <span class="kw-2">&</span>[u8], needle: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">let </span>ninfo = NeedleInfo::new(needle); |
| <span class="kw">let </span><span class="kw-2">mut </span>prestate = PrefilterState::new(); |
| find(<span class="kw-2">&mut </span>prestate, <span class="kw-2">&</span>ninfo, haystack, needle) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>freqy_forward() { |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">0</span>), freqy_find(<span class="string">b"BARFOO"</span>, <span class="string">b"BAR"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">3</span>), freqy_find(<span class="string">b"FOOBAR"</span>, <span class="string">b"BAR"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">0</span>), freqy_find(<span class="string">b"zyzz"</span>, <span class="string">b"zyzy"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">2</span>), freqy_find(<span class="string">b"zzzy"</span>, <span class="string">b"zyzy"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">None</span>, freqy_find(<span class="string">b"zazb"</span>, <span class="string">b"zyzy"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">0</span>), freqy_find(<span class="string">b"yzyy"</span>, <span class="string">b"yzyz"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">Some</span>(<span class="number">2</span>), freqy_find(<span class="string">b"yyyz"</span>, <span class="string">b"yzyz"</span>)); |
| <span class="macro">assert_eq!</span>(<span class="prelude-val">None</span>, freqy_find(<span class="string">b"yayb"</span>, <span class="string">b"yzyz"</span>)); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg(not(miri))] |
| </span><span class="kw">fn </span>prefilter_permutations() { |
| <span class="kw">use </span><span class="kw">crate</span>::memmem::prefilter::tests::PrefilterTest; |
| |
| <span class="comment">// SAFETY: super::find is safe to call for all inputs and on all |
| // platforms. |
| </span><span class="kw">unsafe </span>{ PrefilterTest::run_all_tests(<span class="kw">super</span>::find) }; |
| } |
| } |
| </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> |
