| <!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/util.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>util.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> |
| </pre><pre class="rust"><code><span class="comment">// These routines are meant to be optimized specifically for low latency as |
| // compared to the equivalent routines offered by std. (Which may invoke the |
| // dynamic linker and call out to libc, which introduces a bit more latency |
| // than we'd like.) |
| |
| </span><span class="doccomment">/// Returns true if and only if needle is a prefix of haystack. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>is_prefix(haystack: <span class="kw-2">&</span>[u8], needle: <span class="kw-2">&</span>[u8]) -> bool { |
| needle.len() <= haystack.len() && memcmp(<span class="kw-2">&</span>haystack[..needle.len()], needle) |
| } |
| |
| <span class="doccomment">/// Returns true if and only if needle is a suffix of haystack. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>is_suffix(haystack: <span class="kw-2">&</span>[u8], needle: <span class="kw-2">&</span>[u8]) -> bool { |
| needle.len() <= haystack.len() |
| && memcmp(<span class="kw-2">&</span>haystack[haystack.len() - needle.len()..], needle) |
| } |
| |
| <span class="doccomment">/// Return true if and only if x.len() == y.len() && x[i] == y[i] for all |
| /// 0 <= i < x.len(). |
| /// |
| /// Why not just use actual memcmp for this? Well, memcmp requires calling out |
| /// to libc, and this routine is called in fairly hot code paths. Other than |
| /// just calling out to libc, it also seems to result in worse codegen. By |
| /// rolling our own memcmp in pure Rust, it seems to appear more friendly to |
| /// the optimizer. |
| /// |
| /// We mark this as inline always, although, some callers may not want it |
| /// inlined for better codegen (like Rabin-Karp). In that case, callers are |
| /// advised to create a non-inlineable wrapper routine that calls memcmp. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>memcmp(x: <span class="kw-2">&</span>[u8], y: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="kw">if </span>x.len() != y.len() { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| <span class="comment">// If we don't have enough bytes to do 4-byte at a time loads, then |
| // fall back to the naive slow version. |
| // |
| // TODO: We could do a copy_nonoverlapping combined with a mask instead |
| // of a loop. Benchmark it. |
| </span><span class="kw">if </span>x.len() < <span class="number">4 </span>{ |
| <span class="kw">for </span>(<span class="kw-2">&</span>b1, <span class="kw-2">&</span>b2) <span class="kw">in </span>x.iter().zip(y) { |
| <span class="kw">if </span>b1 != b2 { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| } |
| <span class="kw">return </span><span class="bool-val">true</span>; |
| } |
| <span class="comment">// When we have 4 or more bytes to compare, then proceed in chunks of 4 at |
| // a time using unaligned loads. |
| // |
| // Also, why do 4 byte loads instead of, say, 8 byte loads? The reason is |
| // that this particular version of memcmp is likely to be called with tiny |
| // needles. That means that if we do 8 byte loads, then a higher proportion |
| // of memcmp calls will use the slower variant above. With that said, this |
| // is a hypothesis and is only loosely supported by benchmarks. There's |
| // likely some improvement that could be made here. The main thing here |
| // though is to optimize for latency, not throughput. |
| |
| // SAFETY: Via the conditional above, we know that both `px` and `py` |
| // have the same length, so `px < pxend` implies that `py < pyend`. |
| // Thus, derefencing both `px` and `py` in the loop below is safe. |
| // |
| // Moreover, we set `pxend` and `pyend` to be 4 bytes before the actual |
| // end of of `px` and `py`. Thus, the final dereference outside of the |
| // loop is guaranteed to be valid. (The final comparison will overlap with |
| // the last comparison done in the loop for lengths that aren't multiples |
| // of four.) |
| // |
| // Finally, we needn't worry about alignment here, since we do unaligned |
| // loads. |
| </span><span class="kw">unsafe </span>{ |
| <span class="kw">let </span>(<span class="kw-2">mut </span>px, <span class="kw-2">mut </span>py) = (x.as_ptr(), y.as_ptr()); |
| <span class="kw">let </span>(pxend, pyend) = (px.add(x.len() - <span class="number">4</span>), py.add(y.len() - <span class="number">4</span>)); |
| <span class="kw">while </span>px < pxend { |
| <span class="kw">let </span>vx = (px <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">let </span>vy = (py <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">if </span>vx != vy { |
| <span class="kw">return </span><span class="bool-val">false</span>; |
| } |
| px = px.add(<span class="number">4</span>); |
| py = py.add(<span class="number">4</span>); |
| } |
| <span class="kw">let </span>vx = (pxend <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| <span class="kw">let </span>vy = (pyend <span class="kw">as </span><span class="kw-2">*const </span>u32).read_unaligned(); |
| vx == vy |
| } |
| } |
| </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> |
