| <!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/regex-1.8.3/src/utf8.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>utf8.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="../../regex/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="../../regex/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> |
| </pre><pre class="rust"><code><span class="doccomment">/// A few elementary UTF-8 encoding and decoding functions used by the matching |
| /// engines. |
| /// |
| /// In an ideal world, the matching engines operate on `&str` and we can just |
| /// lean on the standard library for all our UTF-8 needs. However, to support |
| /// byte based regexes (that can match on arbitrary bytes which may contain |
| /// UTF-8), we need to be capable of searching and decoding UTF-8 on a `&[u8]`. |
| /// The standard library doesn't really recognize this use case, so we have |
| /// to build it out ourselves. |
| /// |
| /// Should this be factored out into a separate crate? It seems independently |
| /// useful. There are other crates that already exist (e.g., `utf-8`) that have |
| /// overlapping use cases. Not sure what to do. |
| </span><span class="kw">use </span>std::char; |
| |
| <span class="kw">const </span>TAG_CONT: u8 = <span class="number">0b1000_0000</span>; |
| <span class="kw">const </span>TAG_TWO: u8 = <span class="number">0b1100_0000</span>; |
| <span class="kw">const </span>TAG_THREE: u8 = <span class="number">0b1110_0000</span>; |
| <span class="kw">const </span>TAG_FOUR: u8 = <span class="number">0b1111_0000</span>; |
| |
| <span class="doccomment">/// Returns the smallest possible index of the next valid UTF-8 sequence |
| /// starting after `i`. |
| </span><span class="kw">pub fn </span>next_utf8(text: <span class="kw-2">&</span>[u8], i: usize) -> usize { |
| <span class="kw">let </span>b = <span class="kw">match </span>text.get(i) { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span>i + <span class="number">1</span>, |
| <span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) => b, |
| }; |
| <span class="kw">let </span>inc = <span class="kw">if </span>b <= <span class="number">0x7F </span>{ |
| <span class="number">1 |
| </span>} <span class="kw">else if </span>b <= <span class="number">0b110_11111 </span>{ |
| <span class="number">2 |
| </span>} <span class="kw">else if </span>b <= <span class="number">0b1110_1111 </span>{ |
| <span class="number">3 |
| </span>} <span class="kw">else </span>{ |
| <span class="number">4 |
| </span>}; |
| i + inc |
| } |
| |
| <span class="doccomment">/// Decode a single UTF-8 sequence into a single Unicode codepoint from `src`. |
| /// |
| /// If no valid UTF-8 sequence could be found, then `None` is returned. |
| /// Otherwise, the decoded codepoint and the number of bytes read is returned. |
| /// The number of bytes read (for a valid UTF-8 sequence) is guaranteed to be |
| /// 1, 2, 3 or 4. |
| /// |
| /// Note that a UTF-8 sequence is invalid if it is incorrect UTF-8, encodes a |
| /// codepoint that is out of range (surrogate codepoints are out of range) or |
| /// is not the shortest possible UTF-8 sequence for that codepoint. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>decode_utf8(src: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><(char, usize)> { |
| <span class="kw">let </span>b0 = <span class="kw">match </span>src.get(<span class="number">0</span>) { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) <span class="kw">if </span>b <= <span class="number">0x7F </span>=> <span class="kw">return </span><span class="prelude-val">Some</span>((b <span class="kw">as </span>char, <span class="number">1</span>)), |
| <span class="prelude-val">Some</span>(<span class="kw-2">&</span>b) => b, |
| }; |
| <span class="kw">match </span>b0 { |
| <span class="number">0b110_00000</span>..=<span class="number">0b110_11111 </span>=> { |
| <span class="kw">if </span>src.len() < <span class="number">2 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>b1 = src[<span class="number">1</span>]; |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b1 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>cp = ((b0 & !TAG_TWO) <span class="kw">as </span>u32) << <span class="number">6 </span>| ((b1 & !TAG_CONT) <span class="kw">as </span>u32); |
| <span class="kw">match </span>cp { |
| <span class="number">0x80</span>..=<span class="number">0x7FF </span>=> char::from_u32(cp).map(|cp| (cp, <span class="number">2</span>)), |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| <span class="number">0b1110_0000</span>..=<span class="number">0b1110_1111 </span>=> { |
| <span class="kw">if </span>src.len() < <span class="number">3 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>(b1, b2) = (src[<span class="number">1</span>], src[<span class="number">2</span>]); |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b1 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b2 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>cp = ((b0 & !TAG_THREE) <span class="kw">as </span>u32) << <span class="number">12 |
| </span>| ((b1 & !TAG_CONT) <span class="kw">as </span>u32) << <span class="number">6 |
| </span>| ((b2 & !TAG_CONT) <span class="kw">as </span>u32); |
| <span class="kw">match </span>cp { |
| <span class="comment">// char::from_u32 will disallow surrogate codepoints. |
| </span><span class="number">0x800</span>..=<span class="number">0xFFFF </span>=> char::from_u32(cp).map(|cp| (cp, <span class="number">3</span>)), |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| <span class="number">0b11110_000</span>..=<span class="number">0b11110_111 </span>=> { |
| <span class="kw">if </span>src.len() < <span class="number">4 </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>(b1, b2, b3) = (src[<span class="number">1</span>], src[<span class="number">2</span>], src[<span class="number">3</span>]); |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b1 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b2 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">if </span><span class="number">0b11_000000 </span>& b3 != TAG_CONT { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>cp = ((b0 & !TAG_FOUR) <span class="kw">as </span>u32) << <span class="number">18 |
| </span>| ((b1 & !TAG_CONT) <span class="kw">as </span>u32) << <span class="number">12 |
| </span>| ((b2 & !TAG_CONT) <span class="kw">as </span>u32) << <span class="number">6 |
| </span>| ((b3 & !TAG_CONT) <span class="kw">as </span>u32); |
| <span class="kw">match </span>cp { |
| <span class="number">0x10000</span>..=<span class="number">0x0010_FFFF </span>=> char::from_u32(cp).map(|cp| (cp, <span class="number">4</span>)), |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Like `decode_utf8`, but decodes the last UTF-8 sequence in `src` instead |
| /// of the first. |
| </span><span class="kw">pub fn </span>decode_last_utf8(src: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><(char, usize)> { |
| <span class="kw">if </span>src.is_empty() { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>start = src.len() - <span class="number">1</span>; |
| <span class="kw">if </span>src[start] <= <span class="number">0x7F </span>{ |
| <span class="kw">return </span><span class="prelude-val">Some</span>((src[start] <span class="kw">as </span>char, <span class="number">1</span>)); |
| } |
| <span class="kw">while </span>start > src.len().saturating_sub(<span class="number">4</span>) { |
| start -= <span class="number">1</span>; |
| <span class="kw">if </span>is_start_byte(src[start]) { |
| <span class="kw">break</span>; |
| } |
| } |
| <span class="kw">match </span>decode_utf8(<span class="kw-2">&</span>src[start..]) { |
| <span class="prelude-val">None </span>=> <span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((<span class="kw">_</span>, n)) <span class="kw">if </span>n < src.len() - start => <span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>((cp, n)) => <span class="prelude-val">Some</span>((cp, n)), |
| } |
| } |
| |
| <span class="kw">fn </span>is_start_byte(b: u8) -> bool { |
| b & <span class="number">0b11_000000 </span>!= <span class="number">0b1_0000000 |
| </span>} |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span>std::str; |
| |
| <span class="kw">use </span>quickcheck::quickcheck; |
| |
| <span class="kw">use super</span>::{ |
| decode_last_utf8, decode_utf8, TAG_CONT, TAG_FOUR, TAG_THREE, TAG_TWO, |
| }; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>prop_roundtrip() { |
| <span class="kw">fn </span>p(given_cp: char) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>tmp = [<span class="number">0</span>; <span class="number">4</span>]; |
| <span class="kw">let </span>encoded_len = given_cp.encode_utf8(<span class="kw-2">&mut </span>tmp).len(); |
| <span class="kw">let </span>(got_cp, got_len) = decode_utf8(<span class="kw-2">&</span>tmp[..encoded_len]).unwrap(); |
| encoded_len == got_len && given_cp == got_cp |
| } |
| quickcheck(p <span class="kw">as fn</span>(char) -> bool) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>prop_roundtrip_last() { |
| <span class="kw">fn </span>p(given_cp: char) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>tmp = [<span class="number">0</span>; <span class="number">4</span>]; |
| <span class="kw">let </span>encoded_len = given_cp.encode_utf8(<span class="kw-2">&mut </span>tmp).len(); |
| <span class="kw">let </span>(got_cp, got_len) = |
| decode_last_utf8(<span class="kw-2">&</span>tmp[..encoded_len]).unwrap(); |
| encoded_len == got_len && given_cp == got_cp |
| } |
| quickcheck(p <span class="kw">as fn</span>(char) -> bool) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>prop_encode_matches_std() { |
| <span class="kw">fn </span>p(cp: char) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>got = [<span class="number">0</span>; <span class="number">4</span>]; |
| <span class="kw">let </span>n = cp.encode_utf8(<span class="kw-2">&mut </span>got).len(); |
| <span class="kw">let </span>expected = cp.to_string(); |
| <span class="kw-2">&</span>got[..n] == expected.as_bytes() |
| } |
| quickcheck(p <span class="kw">as fn</span>(char) -> bool) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>prop_decode_matches_std() { |
| <span class="kw">fn </span>p(given_cp: char) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>tmp = [<span class="number">0</span>; <span class="number">4</span>]; |
| <span class="kw">let </span>n = given_cp.encode_utf8(<span class="kw-2">&mut </span>tmp).len(); |
| <span class="kw">let </span>(got_cp, <span class="kw">_</span>) = decode_utf8(<span class="kw-2">&</span>tmp[..n]).unwrap(); |
| <span class="kw">let </span>expected_cp = |
| str::from_utf8(<span class="kw-2">&</span>tmp[..n]).unwrap().chars().next().unwrap(); |
| got_cp == expected_cp |
| } |
| quickcheck(p <span class="kw">as fn</span>(char) -> bool) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>prop_decode_last_matches_std() { |
| <span class="kw">fn </span>p(given_cp: char) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>tmp = [<span class="number">0</span>; <span class="number">4</span>]; |
| <span class="kw">let </span>n = given_cp.encode_utf8(<span class="kw-2">&mut </span>tmp).len(); |
| <span class="kw">let </span>(got_cp, <span class="kw">_</span>) = decode_last_utf8(<span class="kw-2">&</span>tmp[..n]).unwrap(); |
| <span class="kw">let </span>expected_cp = str::from_utf8(<span class="kw-2">&</span>tmp[..n]) |
| .unwrap() |
| .chars() |
| .rev() |
| .next() |
| .unwrap(); |
| got_cp == expected_cp |
| } |
| quickcheck(p <span class="kw">as fn</span>(char) -> bool) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>reject_invalid() { |
| <span class="comment">// Invalid start byte |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xFF</span>]), <span class="prelude-val">None</span>); |
| <span class="comment">// Surrogate pair |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xED</span>, <span class="number">0xA0</span>, <span class="number">0x81</span>]), <span class="prelude-val">None</span>); |
| <span class="comment">// Invalid continuation byte. |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xD4</span>, <span class="number">0xC2</span>]), <span class="prelude-val">None</span>); |
| <span class="comment">// Bad lengths |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xC3</span>]), <span class="prelude-val">None</span>); <span class="comment">// 2 bytes |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xEF</span>, <span class="number">0xBF</span>]), <span class="prelude-val">None</span>); <span class="comment">// 3 bytes |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[<span class="number">0xF4</span>, <span class="number">0x8F</span>, <span class="number">0xBF</span>]), <span class="prelude-val">None</span>); <span class="comment">// 4 bytes |
| // Not a minimal UTF-8 sequence |
| </span><span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[TAG_TWO, TAG_CONT | <span class="string">b'a'</span>]), <span class="prelude-val">None</span>); |
| <span class="macro">assert_eq!</span>(decode_utf8(<span class="kw-2">&</span>[TAG_THREE, TAG_CONT, TAG_CONT | <span class="string">b'a'</span>]), <span class="prelude-val">None</span>); |
| <span class="macro">assert_eq!</span>( |
| decode_utf8(<span class="kw-2">&</span>[TAG_FOUR, TAG_CONT, TAG_CONT, TAG_CONT | <span class="string">b'a'</span>,]), |
| <span class="prelude-val">None |
| </span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>reject_invalid_last() { |
| <span class="comment">// Invalid start byte |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[<span class="number">0xFF</span>]), <span class="prelude-val">None</span>); |
| <span class="comment">// Surrogate pair |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[<span class="number">0xED</span>, <span class="number">0xA0</span>, <span class="number">0x81</span>]), <span class="prelude-val">None</span>); |
| <span class="comment">// Bad lengths |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[<span class="number">0xC3</span>]), <span class="prelude-val">None</span>); <span class="comment">// 2 bytes |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[<span class="number">0xEF</span>, <span class="number">0xBF</span>]), <span class="prelude-val">None</span>); <span class="comment">// 3 bytes |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[<span class="number">0xF4</span>, <span class="number">0x8F</span>, <span class="number">0xBF</span>]), <span class="prelude-val">None</span>); <span class="comment">// 4 bytes |
| // Not a minimal UTF-8 sequence |
| </span><span class="macro">assert_eq!</span>(decode_last_utf8(<span class="kw-2">&</span>[TAG_TWO, TAG_CONT | <span class="string">b'a'</span>]), <span class="prelude-val">None</span>); |
| <span class="macro">assert_eq!</span>( |
| decode_last_utf8(<span class="kw-2">&</span>[TAG_THREE, TAG_CONT, TAG_CONT | <span class="string">b'a'</span>,]), |
| <span class="prelude-val">None |
| </span>); |
| <span class="macro">assert_eq!</span>( |
| decode_last_utf8( |
| <span class="kw-2">&</span>[TAG_FOUR, TAG_CONT, TAG_CONT, TAG_CONT | <span class="string">b'a'</span>,] |
| ), |
| <span class="prelude-val">None |
| </span>); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |