| <!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/remapper.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>remapper.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> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>alloc::vec::Vec; |
| |
| <span class="kw">use crate</span>::{nfa::noncontiguous, util::primitives::StateID}; |
| |
| <span class="doccomment">/// Remappable is a tightly coupled abstraction that facilitates remapping |
| /// state identifiers in DFAs. |
| /// |
| /// The main idea behind remapping state IDs is that DFAs often need to check |
| /// if a certain state is a "special" state of some kind (like a match state) |
| /// during a search. Since this is extremely perf critical code, we want this |
| /// check to be as fast as possible. Partitioning state IDs into, for example, |
| /// into "non-match" and "match" states means one can tell if a state is a |
| /// match state via a simple comparison of the state ID. |
| /// |
| /// The issue is that during the DFA construction process, it's not |
| /// particularly easy to partition the states. Instead, the simplest thing is |
| /// to often just do a pass over all of the states and shuffle them into their |
| /// desired partitionings. To do that, we need a mechanism for swapping states. |
| /// Hence, this abstraction. |
| /// |
| /// Normally, for such little code, I would just duplicate it. But this is a |
| /// key optimization and the implementation is a bit subtle. So the abstraction |
| /// is basically a ham-fisted attempt at DRY. The only place we use this is in |
| /// the dense and one-pass DFAs. |
| /// |
| /// See also src/dfa/special.rs for a more detailed explanation of how dense |
| /// DFAs are partitioned. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait </span>Remappable: core::fmt::Debug { |
| <span class="doccomment">/// Return the total number of states. |
| </span><span class="kw">fn </span>state_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize; |
| |
| <span class="doccomment">/// Swap the states pointed to by the given IDs. The underlying finite |
| /// state machine should be mutated such that all of the transitions in |
| /// `id1` are now in the memory region where the transitions for `id2` |
| /// were, and all of the transitions in `id2` are now in the memory region |
| /// where the transitions for `id1` were. |
| /// |
| /// Essentially, this "moves" `id1` to `id2` and `id2` to `id1`. |
| /// |
| /// It is expected that, after calling this, the underlying state machine |
| /// will be left in an inconsistent state, since any other transitions |
| /// pointing to, e.g., `id1` need to be updated to point to `id2`, since |
| /// that's where `id1` moved to. |
| /// |
| /// In order to "fix" the underlying inconsistent state, a `Remapper` |
| /// should be used to guarantee that `remap` is called at the appropriate |
| /// time. |
| </span><span class="kw">fn </span>swap_states(<span class="kw-2">&mut </span><span class="self">self</span>, id1: StateID, id2: StateID); |
| |
| <span class="doccomment">/// This must remap every single state ID in the underlying value according |
| /// to the function given. For example, in a DFA, this should remap every |
| /// transition and every starting state ID. |
| </span><span class="kw">fn </span>remap(<span class="kw-2">&mut </span><span class="self">self</span>, map: <span class="kw">impl </span>Fn(StateID) -> StateID); |
| } |
| |
| <span class="doccomment">/// Remapper is an abstraction the manages the remapping of state IDs in a |
| /// finite state machine. This is useful when one wants to shuffle states into |
| /// different positions in the machine. |
| /// |
| /// One of the key complexities this manages is the ability to correctly move |
| /// one state multiple times. |
| /// |
| /// Once shuffling is complete, `remap` must be called, which will rewrite |
| /// all pertinent transitions to updated state IDs. Neglecting to call `remap` |
| /// will almost certainly result in a corrupt machine. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Remapper { |
| <span class="doccomment">/// A map from the index of a state to its pre-multiplied identifier. |
| /// |
| /// When a state is swapped with another, then their corresponding |
| /// locations in this map are also swapped. Thus, its new position will |
| /// still point to its old pre-multiplied StateID. |
| /// |
| /// While there is a bit more to it, this then allows us to rewrite the |
| /// state IDs in a DFA's transition table in a single pass. This is done |
| /// by iterating over every ID in this map, then iterating over each |
| /// transition for the state at that ID and re-mapping the transition from |
| /// `old_id` to `map[dfa.to_index(old_id)]`. That is, we find the position |
| /// in this map where `old_id` *started*, and set it to where it ended up |
| /// after all swaps have been completed. |
| </span>map: Vec<StateID>, |
| <span class="doccomment">/// A way to map indices to state IDs (and back). |
| </span>idx: IndexMapper, |
| } |
| |
| <span class="kw">impl </span>Remapper { |
| <span class="doccomment">/// Create a new remapper from the given remappable implementation. The |
| /// remapper can then be used to swap states. The remappable value given |
| /// here must the same one given to `swap` and `remap`. |
| /// |
| /// The given stride should be the stride of the transition table expressed |
| /// as a power of 2. This stride is used to map between state IDs and state |
| /// indices. If state IDs and state indices are equivalent, then provide |
| /// a `stride2` of `0`, which acts as an identity. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(r: <span class="kw-2">&</span><span class="kw">impl </span>Remappable, stride2: usize) -> Remapper { |
| <span class="kw">let </span>idx = IndexMapper { stride2 }; |
| <span class="kw">let </span>map = (<span class="number">0</span>..r.state_len()).map(|i| idx.to_state_id(i)).collect(); |
| Remapper { map, idx } |
| } |
| |
| <span class="doccomment">/// Swap two states. Once this is called, callers must follow through to |
| /// call `remap`, or else it's possible for the underlying remappable |
| /// value to be in a corrupt state. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>swap( |
| <span class="kw-2">&mut </span><span class="self">self</span>, |
| r: <span class="kw-2">&mut </span><span class="kw">impl </span>Remappable, |
| id1: StateID, |
| id2: StateID, |
| ) { |
| <span class="kw">if </span>id1 == id2 { |
| <span class="kw">return</span>; |
| } |
| r.swap_states(id1, id2); |
| <span class="self">self</span>.map.swap(<span class="self">self</span>.idx.to_index(id1), <span class="self">self</span>.idx.to_index(id2)); |
| } |
| |
| <span class="doccomment">/// Complete the remapping process by rewriting all state IDs in the |
| /// remappable value according to the swaps performed. |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>remap(<span class="kw-2">mut </span><span class="self">self</span>, r: <span class="kw-2">&mut </span><span class="kw">impl </span>Remappable) { |
| <span class="comment">// Update the map to account for states that have been swapped |
| // multiple times. For example, if (A, C) and (C, G) are swapped, then |
| // transitions previously pointing to A should now point to G. But if |
| // we don't update our map, they will erroneously be set to C. All we |
| // do is follow the swaps in our map until we see our original state |
| // ID. |
| // |
| // The intuition here is to think about how changes are made to the |
| // map: only through pairwise swaps. That means that starting at any |
| // given state, it is always possible to find the loop back to that |
| // state by following the swaps represented in the map (which might be |
| // 0 swaps). |
| // |
| // We are also careful to clone the map before starting in order to |
| // freeze it. We use the frozen map to find our loops, since we need to |
| // update our map as well. Without freezing it, our updates could break |
| // the loops referenced above and produce incorrect results. |
| </span><span class="kw">let </span>oldmap = <span class="self">self</span>.map.clone(); |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..r.state_len() { |
| <span class="kw">let </span>cur_id = <span class="self">self</span>.idx.to_state_id(i); |
| <span class="kw">let </span><span class="kw-2">mut </span>new_id = oldmap[i]; |
| <span class="kw">if </span>cur_id == new_id { |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>id = oldmap[<span class="self">self</span>.idx.to_index(new_id)]; |
| <span class="kw">if </span>cur_id == id { |
| <span class="self">self</span>.map[i] = new_id; |
| <span class="kw">break</span>; |
| } |
| new_id = id; |
| } |
| } |
| r.remap(|sid| <span class="self">self</span>.map[<span class="self">self</span>.idx.to_index(sid)]); |
| } |
| } |
| |
| <span class="doccomment">/// A simple type for mapping between state indices and state IDs. |
| /// |
| /// The reason why this exists is because state IDs are "premultiplied" in a |
| /// DFA. That is, in order to get to the transitions for a particular state, |
| /// one need only use the state ID as-is, instead of having to multiply it by |
| /// transition table's stride. |
| /// |
| /// The downside of this is that it's inconvenient to map between state IDs |
| /// using a dense map, e.g., Vec<StateID>. That's because state IDs look like |
| /// `0`, `stride`, `2*stride`, `3*stride`, etc., instead of `0`, `1`, `2`, `3`, |
| /// etc. |
| /// |
| /// Since our state IDs are premultiplied, we can convert back-and-forth |
| /// between IDs and indices by simply unmultiplying the IDs and multiplying the |
| /// indices. |
| /// |
| /// Note that for a sparse NFA, state IDs and indices are equivalent. In this |
| /// case, we set the stride of the index mapped to be `0`, which acts as an |
| /// identity. |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">struct </span>IndexMapper { |
| <span class="doccomment">/// The power of 2 corresponding to the stride of the corresponding |
| /// transition table. 'id >> stride2' de-multiplies an ID while 'index << |
| /// stride2' pre-multiplies an index to an ID. |
| </span>stride2: usize, |
| } |
| |
| <span class="kw">impl </span>IndexMapper { |
| <span class="doccomment">/// Convert a state ID to a state index. |
| </span><span class="kw">fn </span>to_index(<span class="kw-2">&</span><span class="self">self</span>, id: StateID) -> usize { |
| id.as_usize() >> <span class="self">self</span>.stride2 |
| } |
| |
| <span class="doccomment">/// Convert a state index to a state ID. |
| </span><span class="kw">fn </span>to_state_id(<span class="kw-2">&</span><span class="self">self</span>, index: usize) -> StateID { |
| <span class="comment">// CORRECTNESS: If the given index is not valid, then it is not |
| // required for this to panic or return a valid state ID. We'll "just" |
| // wind up with panics or silent logic errors at some other point. But |
| // this is OK because if Remappable::state_len is correct and so is |
| // 'to_index', then all inputs to 'to_state_id' should be valid indices |
| // and thus transform into valid state IDs. |
| </span>StateID::new_unchecked(index << <span class="self">self</span>.stride2) |
| } |
| } |
| |
| <span class="kw">impl </span>Remappable <span class="kw">for </span>noncontiguous::NFA { |
| <span class="kw">fn </span>state_len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| noncontiguous::NFA::states(<span class="self">self</span>).len() |
| } |
| |
| <span class="kw">fn </span>swap_states(<span class="kw-2">&mut </span><span class="self">self</span>, id1: StateID, id2: StateID) { |
| noncontiguous::NFA::swap_states(<span class="self">self</span>, id1, id2) |
| } |
| |
| <span class="kw">fn </span>remap(<span class="kw-2">&mut </span><span class="self">self</span>, map: <span class="kw">impl </span>Fn(StateID) -> StateID) { |
| noncontiguous::NFA::remap(<span class="self">self</span>, map) |
| } |
| } |
| </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> |