| <!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/util/buffer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>buffer.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> |
| </pre><pre class="rust"><code><span class="kw">use </span>alloc::{vec, vec::Vec}; |
| |
| <span class="doccomment">/// The default buffer capacity that we use for the stream buffer. |
| </span><span class="kw">const </span>DEFAULT_BUFFER_CAPACITY: usize = <span class="number">64 </span>* (<span class="number">1 </span><< <span class="number">10</span>); <span class="comment">// 64 KB |
| |
| </span><span class="doccomment">/// A fairly simple roll buffer for supporting stream searches. |
| /// |
| /// This buffer acts as a temporary place to store a fixed amount of data when |
| /// reading from a stream. Its central purpose is to allow "rolling" some |
| /// suffix of the data to the beginning of the buffer before refilling it with |
| /// more data from the stream. For example, let's say we are trying to match |
| /// "foobar" on a stream. When we report the match, we'd like to not only |
| /// report the correct offsets at which the match occurs, but also the matching |
| /// bytes themselves. So let's say our stream is a file with the following |
| /// contents: `test test foobar test test`. Now assume that we happen to read |
| /// the aforementioned file in two chunks: `test test foo` and `bar test test`. |
| /// Naively, it would not be possible to report a single contiguous `foobar` |
| /// match, but this roll buffer allows us to do that. Namely, after the second |
| /// read, the contents of the buffer should be `st foobar test test`, where the |
| /// search should ultimately resume immediately after `foo`. (The prefix `st ` |
| /// is included because the roll buffer saves N bytes at the end of the buffer, |
| /// where N is the maximum possible length of a match.) |
| /// |
| /// A lot of the logic for dealing with this is unfortunately split out between |
| /// this roll buffer and the `StreamChunkIter`. |
| /// |
| /// Note also that this buffer is not actually required to just report matches. |
| /// Because a `Match` is just some offsets. But it *is* required for supporting |
| /// things like `try_stream_replace_all` because that needs some mechanism for |
| /// knowing which bytes in the stream correspond to a match and which don't. So |
| /// when a match occurs across two `read` calls, *something* needs to retain |
| /// the bytes from the previous `read` call because you don't know before the |
| /// second read call whether a match exists or not. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Buffer { |
| <span class="doccomment">/// The raw buffer contents. This has a fixed size and never increases. |
| </span>buf: Vec<u8>, |
| <span class="doccomment">/// The minimum size of the buffer, which is equivalent to the maximum |
| /// possible length of a match. This corresponds to the amount that we |
| /// roll |
| </span>min: usize, |
| <span class="doccomment">/// The end of the contents of this buffer. |
| </span>end: usize, |
| } |
| |
| <span class="kw">impl </span>Buffer { |
| <span class="doccomment">/// Create a new buffer for stream searching. The minimum buffer length |
| /// given should be the size of the maximum possible match length. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(min_buffer_len: usize) -> Buffer { |
| <span class="kw">let </span>min = core::cmp::max(<span class="number">1</span>, min_buffer_len); |
| <span class="comment">// The minimum buffer amount is also the amount that we roll our |
| // buffer in order to support incremental searching. To this end, |
| // our actual capacity needs to be at least 1 byte bigger than our |
| // minimum amount, otherwise we won't have any overlap. In actuality, |
| // we want our buffer to be a bit bigger than that for performance |
| // reasons, so we set a lower bound of `8 * min`. |
| // |
| // TODO: It would be good to find a way to test the streaming |
| // implementation with the minimal buffer size. For now, we just |
| // uncomment out the next line and comment out the subsequent line. |
| // let capacity = 1 + min; |
| </span><span class="kw">let </span>capacity = core::cmp::max(min * <span class="number">8</span>, DEFAULT_BUFFER_CAPACITY); |
| Buffer { buf: <span class="macro">vec!</span>[<span class="number">0</span>; capacity], min, end: <span class="number">0 </span>} |
| } |
| |
| <span class="doccomment">/// Return the contents of this buffer. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>buffer(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[u8] { |
| <span class="kw-2">&</span><span class="self">self</span>.buf[..<span class="self">self</span>.end] |
| } |
| |
| <span class="doccomment">/// Return the minimum size of the buffer. The only way a buffer may be |
| /// smaller than this is if the stream itself contains less than the |
| /// minimum buffer amount. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>min_buffer_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.min |
| } |
| |
| <span class="doccomment">/// Return all free capacity in this buffer. |
| </span><span class="kw">fn </span>free_buffer(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw-2">&mut </span>[u8] { |
| <span class="kw-2">&mut </span><span class="self">self</span>.buf[<span class="self">self</span>.end..] |
| } |
| |
| <span class="doccomment">/// Refill the contents of this buffer by reading as much as possible into |
| /// this buffer's free capacity. If no more bytes could be read, then this |
| /// returns false. Otherwise, this reads until it has filled the buffer |
| /// past the minimum amount. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>fill<R: std::io::Read>( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| <span class="kw-2">mut </span>rdr: R, |
| ) -> std::io::Result<bool> { |
| <span class="kw">let </span><span class="kw-2">mut </span>readany = <span class="bool-val">false</span>; |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>readlen = rdr.read(<span class="self">self</span>.free_buffer())<span class="question-mark">?</span>; |
| <span class="kw">if </span>readlen == <span class="number">0 </span>{ |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(readany); |
| } |
| readany = <span class="bool-val">true</span>; |
| <span class="self">self</span>.end += readlen; |
| <span class="kw">if </span><span class="self">self</span>.buffer().len() >= <span class="self">self</span>.min { |
| <span class="kw">return </span><span class="prelude-val">Ok</span>(<span class="bool-val">true</span>); |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Roll the contents of the buffer so that the suffix of this buffer is |
| /// moved to the front and all other contents are dropped. The size of the |
| /// suffix corresponds precisely to the minimum buffer length. |
| /// |
| /// This should only be called when the entire contents of this buffer have |
| /// been searched. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>roll(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="kw">let </span>roll_start = <span class="self">self |
| </span>.end |
| .checked_sub(<span class="self">self</span>.min) |
| .expect(<span class="string">"buffer capacity should be bigger than minimum amount"</span>); |
| <span class="kw">let </span>roll_end = roll_start + <span class="self">self</span>.min; |
| |
| <span class="macro">assert!</span>(roll_end <= <span class="self">self</span>.end); |
| <span class="self">self</span>.buf.copy_within(roll_start..roll_end, <span class="number">0</span>); |
| <span class="self">self</span>.end = <span class="self">self</span>.min; |
| } |
| } |
| </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> |
