blob: 719b6a08d6e96425ef2bc4d084a381502828990a [file] [log] [blame]
<!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/levenshtein_automata-0.2.1/src/levenshtein_nfa.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>levenshtein_nfa.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="../../levenshtein_automata/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="../../levenshtein_automata/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>
<span id="215">215</span>
<span id="216">216</span>
<span id="217">217</span>
<span id="218">218</span>
<span id="219">219</span>
<span id="220">220</span>
<span id="221">221</span>
<span id="222">222</span>
<span id="223">223</span>
<span id="224">224</span>
<span id="225">225</span>
<span id="226">226</span>
<span id="227">227</span>
<span id="228">228</span>
<span id="229">229</span>
<span id="230">230</span>
<span id="231">231</span>
<span id="232">232</span>
<span id="233">233</span>
<span id="234">234</span>
<span id="235">235</span>
<span id="236">236</span>
<span id="237">237</span>
<span id="238">238</span>
<span id="239">239</span>
<span id="240">240</span>
<span id="241">241</span>
<span id="242">242</span>
<span id="243">243</span>
<span id="244">244</span>
<span id="245">245</span>
<span id="246">246</span>
<span id="247">247</span>
<span id="248">248</span>
<span id="249">249</span>
<span id="250">250</span>
<span id="251">251</span>
<span id="252">252</span>
<span id="253">253</span>
<span id="254">254</span>
<span id="255">255</span>
<span id="256">256</span>
<span id="257">257</span>
<span id="258">258</span>
<span id="259">259</span>
<span id="260">260</span>
<span id="261">261</span>
<span id="262">262</span>
<span id="263">263</span>
<span id="264">264</span>
<span id="265">265</span>
<span id="266">266</span>
<span id="267">267</span>
<span id="268">268</span>
<span id="269">269</span>
<span id="270">270</span>
<span id="271">271</span>
<span id="272">272</span>
<span id="273">273</span>
<span id="274">274</span>
<span id="275">275</span>
<span id="276">276</span>
<span id="277">277</span>
<span id="278">278</span>
<span id="279">279</span>
<span id="280">280</span>
<span id="281">281</span>
<span id="282">282</span>
<span id="283">283</span>
<span id="284">284</span>
<span id="285">285</span>
</pre><pre class="rust"><code><span class="kw">use </span>std::cmp::Ordering;
<span class="attribute">#[cfg(test)]
</span><span class="kw">pub fn </span>compute_characteristic_vector(query: <span class="kw-2">&amp;</span>[char], c: char) -&gt; u64 {
<span class="kw">let </span><span class="kw-2">mut </span>chi = <span class="number">0u64</span>;
<span class="kw">for </span>i <span class="kw">in </span><span class="number">0</span>..query.len() {
<span class="kw">if </span>query[i] == c {
chi |= <span class="number">1u64 </span>&lt;&lt; i;
}
}
chi
}
<span class="attribute">#[derive(Debug, Hash, Eq, PartialEq, Clone)]
</span><span class="kw">pub struct </span>MultiState {
states: Vec&lt;NFAState&gt;,
}
<span class="kw">impl </span>MultiState {
<span class="kw">pub fn </span>states(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>[NFAState] {
<span class="kw-2">&amp;</span><span class="self">self</span>.states[..]
}
<span class="kw">fn </span>clear(<span class="kw-2">&amp;mut </span><span class="self">self</span>) {
<span class="self">self</span>.states.clear()
}
<span class="kw">pub fn </span>empty() -&gt; MultiState {
MultiState { states: Vec::new() }
}
<span class="kw">pub fn </span>normalize(<span class="kw-2">&amp;mut </span><span class="self">self</span>) -&gt; u32 {
<span class="kw">let </span>min_offset: u32 = <span class="self">self
</span>.states
.iter()
.map(|state| state.offset)
.min()
.unwrap_or(<span class="number">0u32</span>);
<span class="kw">for </span>state <span class="kw">in </span><span class="kw-2">&amp;mut </span><span class="self">self</span>.states {
state.offset -= min_offset;
}
<span class="self">self</span>.states.sort();
min_offset
}
<span class="kw">fn </span>add_state(<span class="kw-2">&amp;mut </span><span class="self">self</span>, new_state: NFAState) {
<span class="kw">if </span><span class="self">self</span>.states.iter().any(|state| state.imply(new_state)) {
<span class="comment">// this state is already included in the current set of states.
</span><span class="kw">return</span>;
}
<span class="kw">let </span><span class="kw-2">mut </span>i = <span class="number">0</span>;
<span class="kw">while </span>i &lt; <span class="self">self</span>.states.len() {
<span class="kw">if </span>new_state.imply(<span class="self">self</span>.states[i]) {
<span class="self">self</span>.states.swap_remove(i);
} <span class="kw">else </span>{
i += <span class="number">1</span>;
}
}
<span class="self">self</span>.states.push(new_state);
}
}
<span class="doccomment">/// Levenshtein Distance computed by a Levenshtein Automaton.
///
/// Levenshtein automata can only compute the exact Levenshtein distance
/// up to a given `max_distance`.
///
/// Over this distance, the automaton will invariably
/// return `Distance::AtLeast(max_distance + 1)`.
</span><span class="attribute">#[derive(Eq, PartialEq, Debug, Clone, Copy)]
</span><span class="kw">pub enum </span>Distance {
Exact(u8),
AtLeast(u8),
}
<span class="kw">impl </span>Distance {
<span class="doccomment">/// Returns the highest lower bound for the distance.
/// It is equivalent to
///
/// ```ignored
/// match distance {
/// Distance::Exact(d) |
/// Distance::AtLeast(d) =&gt; d,
/// }
/// ```
</span><span class="kw">pub fn </span>to_u8(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u8 {
<span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{
Distance::Exact(d) | Distance::AtLeast(d) =&gt; d,
}
}
}
<span class="kw">impl </span>PartialOrd <span class="kw">for </span>Distance {
<span class="kw">fn </span>partial_cmp(<span class="kw-2">&amp;</span><span class="self">self</span>, other: <span class="kw-2">&amp;</span>Distance) -&gt; <span class="prelude-ty">Option</span>&lt;Ordering&gt; {
<span class="kw">use </span><span class="self">self</span>::Distance::<span class="kw-2">*</span>;
<span class="kw">match </span>(<span class="kw-2">*</span><span class="self">self</span>, <span class="kw-2">*</span>other) {
(Exact(left), Exact(right)) =&gt; left.partial_cmp(<span class="kw-2">&amp;</span>right),
(Exact(left), AtLeast(right)) =&gt; {
<span class="kw">if </span>right &gt; left {
<span class="prelude-val">Some</span>(Ordering::Greater)
} <span class="kw">else </span>{
<span class="prelude-val">None
</span>}
}
(AtLeast(left), Exact(right)) =&gt; {
<span class="kw">if </span>left &gt; right {
<span class="prelude-val">Some</span>(Ordering::Less)
} <span class="kw">else </span>{
<span class="prelude-val">None
</span>}
}
(AtLeast(left), AtLeast(right)) =&gt; {
<span class="kw">if </span>left == right {
<span class="prelude-val">Some</span>(Ordering::Equal)
} <span class="kw">else </span>{
<span class="prelude-val">None
</span>}
}
}
}
}
<span class="kw">pub struct </span>LevenshteinNFA {
max_distance: u8,
damerau: bool,
}
<span class="kw">fn </span>extract_bit(bitset: u64, pos: u8) -&gt; bool {
<span class="kw">let </span>pos = pos <span class="kw">as </span>usize;
<span class="kw">let </span>shift = bitset &gt;&gt; pos;
<span class="kw">let </span>bit = shift &amp; <span class="number">1</span>;
bit == <span class="number">1u64
</span>}
<span class="kw">fn </span>dist(left: u32, right: u32) -&gt; u32 {
<span class="kw">if </span>left &gt; right {
left - right
} <span class="kw">else </span>{
right - left
}
}
<span class="kw">impl </span>LevenshteinNFA {
<span class="kw">pub fn </span>levenshtein(max_distance: u8, transposition: bool) -&gt; LevenshteinNFA {
LevenshteinNFA {
max_distance: max_distance,
damerau: transposition,
}
}
<span class="kw">pub fn </span>multistate_distance(<span class="kw-2">&amp;</span><span class="self">self</span>, multistate: <span class="kw-2">&amp;</span>MultiState, query_len: u32) -&gt; Distance {
multistate
.states()
.iter()
.map(|state| state.distance + dist(query_len, state.offset) <span class="kw">as </span>u8)
.filter(|d| <span class="kw-2">*</span>d &lt;= <span class="self">self</span>.max_distance)
.min()
.map(Distance::Exact)
.unwrap_or_else(|| Distance::AtLeast(<span class="self">self</span>.max_distance + <span class="number">1u8</span>))
}
<span class="kw">pub fn </span>max_distance(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u8 {
<span class="self">self</span>.max_distance
}
<span class="kw">pub fn </span>multistate_diameter(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; u8 {
<span class="number">2u8 </span>* <span class="self">self</span>.max_distance + <span class="number">1u8
</span>}
<span class="kw">pub fn </span>initial_states(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; MultiState {
<span class="kw">let </span><span class="kw-2">mut </span>multistate = MultiState::empty();
multistate.add_state(NFAState::default());
multistate
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">pub fn </span>compute_distance(<span class="kw-2">&amp;</span><span class="self">self</span>, query: <span class="kw-2">&amp;</span>str, other: <span class="kw-2">&amp;</span>str) -&gt; Distance {
<span class="kw">use </span>std::mem;
<span class="kw">let </span>query_chars: Vec&lt;char&gt; = query.chars().collect();
<span class="kw">let </span><span class="kw-2">mut </span>current_state = <span class="self">self</span>.initial_states();
<span class="kw">let </span><span class="kw-2">mut </span>next_state = MultiState::empty();
<span class="kw">for </span>chr <span class="kw">in </span>other.chars() {
next_state.clear();
<span class="kw">let </span>chi: u64 = compute_characteristic_vector(<span class="kw-2">&amp;</span>query_chars[..], chr);
<span class="self">self</span>.transition(<span class="kw-2">&amp;</span>current_state, <span class="kw-2">&amp;mut </span>next_state, chi);
mem::swap(<span class="kw-2">&amp;mut </span>current_state, <span class="kw-2">&amp;mut </span>next_state);
}
<span class="self">self</span>.multistate_distance(<span class="kw-2">&amp;</span>current_state, query_chars.len() <span class="kw">as </span>u32)
}
<span class="kw">fn </span>simple_transition(<span class="kw-2">&amp;</span><span class="self">self</span>, state: NFAState, symbol: u64, multistate: <span class="kw-2">&amp;mut </span>MultiState) {
<span class="kw">if </span>state.distance &lt; <span class="self">self</span>.max_distance {
<span class="comment">// apparently we still have room to
// make mistakes.
// insertion
</span>multistate.add_state(NFAState {
offset: state.offset,
distance: state.distance + <span class="number">1</span>,
in_transpose: <span class="bool-val">false</span>,
});
<span class="comment">// substitution
</span>multistate.add_state(NFAState {
offset: state.offset + <span class="number">1</span>,
distance: state.distance + <span class="number">1</span>,
in_transpose: <span class="bool-val">false</span>,
});
<span class="kw">for </span>d <span class="kw">in </span><span class="number">1u8</span>..<span class="self">self</span>.max_distance + <span class="number">1u8 </span>- state.distance {
<span class="kw">if </span>extract_bit(symbol, d) {
<span class="comment">// for d &gt; 0, as many deletion and character match
</span>multistate.add_state(NFAState {
offset: state.offset + <span class="number">1 </span>+ u32::from(d),
distance: state.distance + d,
in_transpose: <span class="bool-val">false</span>,
});
}
}
<span class="kw">if </span><span class="self">self</span>.damerau &amp;&amp; extract_bit(symbol, <span class="number">1</span>) {
multistate.add_state(NFAState {
offset: state.offset,
distance: state.distance + <span class="number">1</span>,
in_transpose: <span class="bool-val">true</span>,
});
}
}
<span class="kw">if </span>extract_bit(symbol, <span class="number">0</span>) {
multistate.add_state(NFAState {
offset: state.offset + <span class="number">1</span>,
distance: state.distance,
in_transpose: <span class="bool-val">false</span>,
});
}
<span class="kw">if </span>state.in_transpose &amp;&amp; extract_bit(symbol, <span class="number">0u8</span>) {
multistate.add_state(NFAState {
offset: state.offset + <span class="number">2</span>,
distance: state.distance,
in_transpose: <span class="bool-val">false</span>,
});
}
}
<span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>transition(
<span class="kw-2">&amp;</span><span class="self">self</span>,
current_state: <span class="kw-2">&amp;</span>MultiState,
dest_state: <span class="kw-2">&amp;mut </span>MultiState,
shifted_chi_vector: u64,
) {
dest_state.clear();
<span class="kw">let </span>mask = (<span class="number">1u64 </span>&lt;&lt; <span class="self">self</span>.multistate_diameter()) - <span class="number">1u64</span>;
<span class="kw">for </span><span class="kw-2">&amp;</span>state <span class="kw">in </span>current_state.states() {
<span class="kw">let </span>shifted_chi_vector = (shifted_chi_vector &gt;&gt; state.offset <span class="kw">as </span>usize) &amp; mask;
<span class="self">self</span>.simple_transition(state, shifted_chi_vector, dest_state);
}
dest_state.states.sort();
}
}
<span class="attribute">#[derive(Default, Hash, Eq, PartialOrd, Ord, PartialEq, Copy, Clone, Debug)]
</span><span class="kw">pub struct </span>NFAState {
offset: u32,
distance: u8,
in_transpose: bool,
}
<span class="kw">impl </span>NFAState {
<span class="kw">fn </span>imply(<span class="kw-2">&amp;</span><span class="self">self</span>, other: NFAState) -&gt; bool {
<span class="kw">let </span>tranpose_imply = <span class="self">self</span>.in_transpose | !other.in_transpose;
<span class="kw">let </span>delta_offset: u32 = <span class="kw">if </span><span class="self">self</span>.offset &gt;= other.offset {
<span class="self">self</span>.offset - other.offset
} <span class="kw">else </span>{
other.offset - <span class="self">self</span>.offset
};
<span class="kw">if </span>tranpose_imply {
u32::from(other.distance) &gt;= u32::from(<span class="self">self</span>.distance) + delta_offset
} <span class="kw">else </span>{
u32::from(other.distance) &gt; u32::from(<span class="self">self</span>.distance) + delta_offset
}
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="levenshtein_automata" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>