<!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 to the Rust file `libcore/char/decode.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>decode.rs.html -- source</title><link rel="stylesheet" type="text/css" href="../../../normalize.css"><link rel="stylesheet" type="text/css" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" type="text/css" href="../../../dark.css"><link rel="stylesheet" type="text/css" href="../../../light.css" id="themeStyle"><script src="../../../storage.js"></script><link rel="shortcut icon" href="https://doc.rust-lang.org/favicon.ico"></head><body class="rustdoc source"><!--[if lte IE 8]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><div class="sidebar-menu">☰</div><a href='../../../core/index.html'><img src='https://www.rust-lang.org/logos/rust-logo-128x128-blk-v2.png' alt='logo' width='100'></a></nav><div class="theme-picker"><button id="theme-picker" aria-label="Pick another theme!"><img src="../../../brush.svg" width="18" alt="Pick another theme!"></button><div id="theme-choices"></div></div><script src="../../../theme.js"></script><nav class="sub"><form class="search-form js-only"><div class="search-container"><input class="search-input" name="search" autocomplete="off" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><a id="settings-menu" href="../../../settings.html"><img src="../../../wheel.svg" width="18" alt="Change settings"></a></div></form></nav><section id="main" class="content"><pre class="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>
</pre><pre class="rust ">
<span class="comment">// Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT</span>
<span class="comment">// file at the top-level directory of this distribution and at</span>
<span class="comment">// http://rust-lang.org/COPYRIGHT.</span>
<span class="comment">//</span>
<span class="comment">// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span>
<span class="comment">// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span>
<span class="comment">// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span>
<span class="comment">// option. This file may not be copied, modified, or distributed</span>
<span class="comment">// except according to those terms.</span>
<span class="doccomment">//! UTF-8 and UTF-16 decoding iterators</span>
<span class="kw">use</span> <span class="ident">fmt</span>;
<span class="kw">use</span> <span class="ident">iter</span>::<span class="ident">FusedIterator</span>;
<span class="kw">use</span> <span class="kw">super</span>::<span class="ident">from_u32_unchecked</span>;
<span class="doccomment">/// An iterator over an iterator of bytes of the characters the bytes represent</span>
<span class="doccomment">/// as UTF-8</span>
<span class="attribute">#[<span class="ident">unstable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf8"</span>, <span class="ident">issue</span> <span class="op">=</span> <span class="string">"33906"</span>)]</span>
<span class="attribute">#[<span class="ident">rustc_deprecated</span>(<span class="ident">since</span> <span class="op">=</span> <span class="string">"1.27.0"</span>, <span class="ident">reason</span> <span class="op">=</span> <span class="string">"Use str::from_utf8 instead:
https://doc.rust-lang.org/nightly/std/str/struct.Utf8Error.html#examples"</span>)]</span>
<span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>, <span class="ident">Debug</span>)]</span>
<span class="attribute">#[<span class="ident">allow</span>(<span class="ident">deprecated</span>)]</span>
<span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">DecodeUtf8</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">Iterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u8</span><span class="op">>></span>(::<span class="ident">iter</span>::<span class="ident">Peekable</span><span class="op"><</span><span class="ident">I</span><span class="op">></span>);
<span class="doccomment">/// Decodes an `Iterator` of bytes as UTF-8.</span>
<span class="attribute">#[<span class="ident">unstable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf8"</span>, <span class="ident">issue</span> <span class="op">=</span> <span class="string">"33906"</span>)]</span>
<span class="attribute">#[<span class="ident">rustc_deprecated</span>(<span class="ident">since</span> <span class="op">=</span> <span class="string">"1.27.0"</span>, <span class="ident">reason</span> <span class="op">=</span> <span class="string">"Use str::from_utf8 instead:
https://doc.rust-lang.org/nightly/std/str/struct.Utf8Error.html#examples"</span>)]</span>
<span class="attribute">#[<span class="ident">allow</span>(<span class="ident">deprecated</span>)]</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">decode_utf8</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">IntoIterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u8</span><span class="op">>></span>(<span class="ident">i</span>: <span class="ident">I</span>) <span class="op">-></span> <span class="ident">DecodeUtf8</span><span class="op"><</span><span class="ident">I</span>::<span class="ident">IntoIter</span><span class="op">></span> {
<span class="ident">DecodeUtf8</span>(<span class="ident">i</span>.<span class="ident">into_iter</span>().<span class="ident">peekable</span>())
}
<span class="doccomment">/// `<DecodeUtf8 as Iterator>::next` returns this for an invalid input sequence.</span>
<span class="attribute">#[<span class="ident">unstable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf8"</span>, <span class="ident">issue</span> <span class="op">=</span> <span class="string">"33906"</span>)]</span>
<span class="attribute">#[<span class="ident">rustc_deprecated</span>(<span class="ident">since</span> <span class="op">=</span> <span class="string">"1.27.0"</span>, <span class="ident">reason</span> <span class="op">=</span> <span class="string">"Use str::from_utf8 instead:
https://doc.rust-lang.org/nightly/std/str/struct.Utf8Error.html#examples"</span>)]</span>
<span class="attribute">#[<span class="ident">derive</span>(<span class="ident">PartialEq</span>, <span class="ident">Eq</span>, <span class="ident">Debug</span>)]</span>
<span class="attribute">#[<span class="ident">allow</span>(<span class="ident">deprecated</span>)]</span>
<span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">InvalidSequence</span>(());
<span class="attribute">#[<span class="ident">unstable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf8"</span>, <span class="ident">issue</span> <span class="op">=</span> <span class="string">"33906"</span>)]</span>
<span class="attribute">#[<span class="ident">allow</span>(<span class="ident">deprecated</span>)]</span>
<span class="kw">impl</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">Iterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u8</span><span class="op">>></span> <span class="ident">Iterator</span> <span class="kw">for</span> <span class="ident">DecodeUtf8</span><span class="op"><</span><span class="ident">I</span><span class="op">></span> {
<span class="kw">type</span> <span class="ident">Item</span> <span class="op">=</span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">char</span>, <span class="ident">InvalidSequence</span><span class="op">></span>;
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">next</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">char</span>, <span class="ident">InvalidSequence</span><span class="op">>></span> {
<span class="self">self</span>.<span class="number">0</span>.<span class="ident">next</span>().<span class="ident">map</span>(<span class="op">|</span><span class="ident">first_byte</span><span class="op">|</span> {
<span class="comment">// Emit InvalidSequence according to</span>
<span class="comment">// Unicode §5.22 Best Practice for U+FFFD Substitution</span>
<span class="comment">// http://www.unicode.org/versions/Unicode9.0.0/ch05.pdf#G40630</span>
<span class="comment">// Roughly: consume at least one byte,</span>
<span class="comment">// then validate one byte at a time and stop before the first unexpected byte</span>
<span class="comment">// (which might be the valid start of the next byte sequence).</span>
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">code_point</span>;
<span class="macro">macro_rules</span><span class="macro">!</span> <span class="ident">first_byte</span> {
(<span class="macro-nonterminal">$</span><span class="macro-nonterminal">mask</span>: <span class="ident">expr</span>) <span class="op">=></span> {
<span class="ident">code_point</span> <span class="op">=</span> <span class="ident">u32</span>::<span class="ident">from</span>(<span class="ident">first_byte</span> <span class="op">&</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mask</span>)
}
}
<span class="macro">macro_rules</span><span class="macro">!</span> <span class="ident">continuation_byte</span> {
() <span class="op">=></span> { <span class="macro">continuation_byte</span><span class="macro">!</span>(<span class="number">0x80</span>...<span class="number">0xBF</span>) };
(<span class="macro-nonterminal">$</span><span class="macro-nonterminal">range</span>: <span class="ident">pat</span>) <span class="op">=></span> {
<span class="kw">match</span> <span class="self">self</span>.<span class="number">0</span>.<span class="ident">peek</span>() {
<span class="prelude-val">Some</span>(<span class="kw-2">&</span><span class="ident">byte</span> @ <span class="macro-nonterminal">$</span><span class="macro-nonterminal">range</span>) <span class="op">=></span> {
<span class="ident">code_point</span> <span class="op">=</span> (<span class="ident">code_point</span> <span class="op"><<</span> <span class="number">6</span>) <span class="op">|</span> <span class="ident">u32</span>::<span class="ident">from</span>(<span class="ident">byte</span> <span class="op">&</span> <span class="number">0b0011_1111</span>);
<span class="self">self</span>.<span class="number">0</span>.<span class="ident">next</span>();
}
<span class="kw">_</span> <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">InvalidSequence</span>(()))
}
}
}
<span class="kw">match</span> <span class="ident">first_byte</span> {
<span class="number">0x00</span>...<span class="number">0x7F</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b1111_1111</span>);
}
<span class="number">0xC2</span>...<span class="number">0xDF</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0001_1111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xE0</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_1111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>(<span class="number">0xA0</span>...<span class="number">0xBF</span>); <span class="comment">// 0x80...0x9F here are overlong</span>
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xE1</span>...<span class="number">0xEC</span> <span class="op">|</span> <span class="number">0xEE</span>...<span class="number">0xEF</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_1111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>();
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xED</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_1111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>(<span class="number">0x80</span>...<span class="number">0x9F</span>); <span class="comment">// 0xA0..0xBF here are surrogates</span>
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xF0</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_0111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>(<span class="number">0x90</span>...<span class="number">0xBF</span>); <span class="comment">// 0x80..0x8F here are overlong</span>
<span class="macro">continuation_byte</span><span class="macro">!</span>();
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xF1</span>...<span class="number">0xF3</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_0111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>();
<span class="macro">continuation_byte</span><span class="macro">!</span>();
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="number">0xF4</span> <span class="op">=></span> {
<span class="macro">first_byte</span><span class="macro">!</span>(<span class="number">0b0000_0111</span>);
<span class="macro">continuation_byte</span><span class="macro">!</span>(<span class="number">0x80</span>...<span class="number">0x8F</span>); <span class="comment">// 0x90..0xBF here are beyond char::MAX</span>
<span class="macro">continuation_byte</span><span class="macro">!</span>();
<span class="macro">continuation_byte</span><span class="macro">!</span>();
}
<span class="kw">_</span> <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">InvalidSequence</span>(())) <span class="comment">// Illegal first byte, overlong, or beyond MAX</span>
}
<span class="kw">unsafe</span> {
<span class="prelude-val">Ok</span>(<span class="ident">from_u32_unchecked</span>(<span class="ident">code_point</span>))
}
})
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">size_hint</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> (<span class="ident">usize</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>) {
<span class="kw">let</span> (<span class="ident">lower</span>, <span class="ident">upper</span>) <span class="op">=</span> <span class="self">self</span>.<span class="number">0</span>.<span class="ident">size_hint</span>();
<span class="comment">// A code point is at most 4 bytes long.</span>
<span class="kw">let</span> <span class="ident">min_code_points</span> <span class="op">=</span> <span class="ident">lower</span> <span class="op">/</span> <span class="number">4</span>;
(<span class="ident">min_code_points</span>, <span class="ident">upper</span>)
}
}
<span class="attribute">#[<span class="ident">unstable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf8"</span>, <span class="ident">issue</span> <span class="op">=</span> <span class="string">"33906"</span>)]</span>
<span class="attribute">#[<span class="ident">allow</span>(<span class="ident">deprecated</span>)]</span>
<span class="kw">impl</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">FusedIterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u8</span><span class="op">>></span> <span class="ident">FusedIterator</span> <span class="kw">for</span> <span class="ident">DecodeUtf8</span><span class="op"><</span><span class="ident">I</span><span class="op">></span> {}
<span class="doccomment">/// An iterator that decodes UTF-16 encoded code points from an iterator of `u16`s.</span>
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>, <span class="ident">Debug</span>)]</span>
<span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">DecodeUtf16</span><span class="op"><</span><span class="ident">I</span><span class="op">></span>
<span class="kw">where</span> <span class="ident">I</span>: <span class="ident">Iterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u16</span><span class="op">></span>
{
<span class="ident">iter</span>: <span class="ident">I</span>,
<span class="ident">buf</span>: <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>,
}
<span class="doccomment">/// An error that can be returned when decoding UTF-16 code points.</span>
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Debug</span>, <span class="ident">Clone</span>, <span class="ident">Eq</span>, <span class="ident">PartialEq</span>)]</span>
<span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">DecodeUtf16Error</span> {
<span class="ident">code</span>: <span class="ident">u16</span>,
}
<span class="doccomment">/// Create an iterator over the UTF-16 encoded code points in `iter`,</span>
<span class="doccomment">/// returning unpaired surrogates as `Err`s.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Examples</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Basic usage:</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use std::char::decode_utf16;</span>
<span class="doccomment">///</span>
<span class="doccomment">/// fn main() {</span>
<span class="doccomment">/// // 𝄞mus<invalid>ic<invalid></span>
<span class="doccomment">/// let v = [0xD834, 0xDD1E, 0x006d, 0x0075,</span>
<span class="doccomment">/// 0x0073, 0xDD1E, 0x0069, 0x0063,</span>
<span class="doccomment">/// 0xD834];</span>
<span class="doccomment">///</span>
<span class="doccomment">/// assert_eq!(decode_utf16(v.iter().cloned())</span>
<span class="doccomment">/// .map(|r| r.map_err(|e| e.unpaired_surrogate()))</span>
<span class="doccomment">/// .collect::<Vec<_>>(),</span>
<span class="doccomment">/// vec![Ok('𝄞'),</span>
<span class="doccomment">/// Ok('m'), Ok('u'), Ok('s'),</span>
<span class="doccomment">/// Err(0xDD1E),</span>
<span class="doccomment">/// Ok('i'), Ok('c'),</span>
<span class="doccomment">/// Err(0xD834)]);</span>
<span class="doccomment">/// }</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">///</span>
<span class="doccomment">/// A lossy decoder can be obtained by replacing `Err` results with the replacement character:</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use std::char::{decode_utf16, REPLACEMENT_CHARACTER};</span>
<span class="doccomment">///</span>
<span class="doccomment">/// fn main() {</span>
<span class="doccomment">/// // 𝄞mus<invalid>ic<invalid></span>
<span class="doccomment">/// let v = [0xD834, 0xDD1E, 0x006d, 0x0075,</span>
<span class="doccomment">/// 0x0073, 0xDD1E, 0x0069, 0x0063,</span>
<span class="doccomment">/// 0xD834];</span>
<span class="doccomment">///</span>
<span class="doccomment">/// assert_eq!(decode_utf16(v.iter().cloned())</span>
<span class="doccomment">/// .map(|r| r.unwrap_or(REPLACEMENT_CHARACTER))</span>
<span class="doccomment">/// .collect::<String>(),</span>
<span class="doccomment">/// "𝄞mus�ic�");</span>
<span class="doccomment">/// }</span>
<span class="doccomment">/// ```</span>
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">decode_utf16</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">IntoIterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u16</span><span class="op">>></span>(<span class="ident">iter</span>: <span class="ident">I</span>) <span class="op">-></span> <span class="ident">DecodeUtf16</span><span class="op"><</span><span class="ident">I</span>::<span class="ident">IntoIter</span><span class="op">></span> {
<span class="ident">DecodeUtf16</span> {
<span class="ident">iter</span>: <span class="ident">iter</span>.<span class="ident">into_iter</span>(),
<span class="ident">buf</span>: <span class="prelude-val">None</span>,
}
}
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="kw">impl</span><span class="op"><</span><span class="ident">I</span>: <span class="ident">Iterator</span><span class="op"><</span><span class="ident">Item</span> <span class="op">=</span> <span class="ident">u16</span><span class="op">>></span> <span class="ident">Iterator</span> <span class="kw">for</span> <span class="ident">DecodeUtf16</span><span class="op"><</span><span class="ident">I</span><span class="op">></span> {
<span class="kw">type</span> <span class="ident">Item</span> <span class="op">=</span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">char</span>, <span class="ident">DecodeUtf16Error</span><span class="op">></span>;
<span class="kw">fn</span> <span class="ident">next</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">char</span>, <span class="ident">DecodeUtf16Error</span><span class="op">>></span> {
<span class="kw">let</span> <span class="ident">u</span> <span class="op">=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">buf</span>.<span class="ident">take</span>() {
<span class="prelude-val">Some</span>(<span class="ident">buf</span>) <span class="op">=></span> <span class="ident">buf</span>,
<span class="prelude-val">None</span> <span class="op">=></span> <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">next</span>()<span class="question-mark">?</span>
};
<span class="kw">if</span> <span class="ident">u</span> <span class="op"><</span> <span class="number">0xD800</span> <span class="op">||</span> <span class="number">0xDFFF</span> <span class="op"><</span> <span class="ident">u</span> {
<span class="comment">// not a surrogate</span>
<span class="prelude-val">Some</span>(<span class="prelude-val">Ok</span>(<span class="kw">unsafe</span> { <span class="ident">from_u32_unchecked</span>(<span class="ident">u</span> <span class="kw">as</span> <span class="ident">u32</span>) }))
} <span class="kw">else</span> <span class="kw">if</span> <span class="ident">u</span> <span class="op">>=</span> <span class="number">0xDC00</span> {
<span class="comment">// a trailing surrogate</span>
<span class="prelude-val">Some</span>(<span class="prelude-val">Err</span>(<span class="ident">DecodeUtf16Error</span> { <span class="ident">code</span>: <span class="ident">u</span> }))
} <span class="kw">else</span> {
<span class="kw">let</span> <span class="ident">u2</span> <span class="op">=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">next</span>() {
<span class="prelude-val">Some</span>(<span class="ident">u2</span>) <span class="op">=></span> <span class="ident">u2</span>,
<span class="comment">// eof</span>
<span class="prelude-val">None</span> <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">Some</span>(<span class="prelude-val">Err</span>(<span class="ident">DecodeUtf16Error</span> { <span class="ident">code</span>: <span class="ident">u</span> })),
};
<span class="kw">if</span> <span class="ident">u2</span> <span class="op"><</span> <span class="number">0xDC00</span> <span class="op">||</span> <span class="ident">u2</span> <span class="op">></span> <span class="number">0xDFFF</span> {
<span class="comment">// not a trailing surrogate so we're not a valid</span>
<span class="comment">// surrogate pair, so rewind to redecode u2 next time.</span>
<span class="self">self</span>.<span class="ident">buf</span> <span class="op">=</span> <span class="prelude-val">Some</span>(<span class="ident">u2</span>);
<span class="kw">return</span> <span class="prelude-val">Some</span>(<span class="prelude-val">Err</span>(<span class="ident">DecodeUtf16Error</span> { <span class="ident">code</span>: <span class="ident">u</span> }));
}
<span class="comment">// all ok, so lets decode it.</span>
<span class="kw">let</span> <span class="ident">c</span> <span class="op">=</span> (((<span class="ident">u</span> <span class="op">-</span> <span class="number">0xD800</span>) <span class="kw">as</span> <span class="ident">u32</span>) <span class="op"><<</span> <span class="number">10</span> <span class="op">|</span> (<span class="ident">u2</span> <span class="op">-</span> <span class="number">0xDC00</span>) <span class="kw">as</span> <span class="ident">u32</span>) <span class="op">+</span> <span class="number">0x1_0000</span>;
<span class="prelude-val">Some</span>(<span class="prelude-val">Ok</span>(<span class="kw">unsafe</span> { <span class="ident">from_u32_unchecked</span>(<span class="ident">c</span>) }))
}
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">size_hint</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> (<span class="ident">usize</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>) {
<span class="kw">let</span> (<span class="ident">low</span>, <span class="ident">high</span>) <span class="op">=</span> <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">size_hint</span>();
<span class="comment">// we could be entirely valid surrogates (2 elements per</span>
<span class="comment">// char), or entirely non-surrogates (1 element per char)</span>
(<span class="ident">low</span> <span class="op">/</span> <span class="number">2</span>, <span class="ident">high</span>)
}
}
<span class="kw">impl</span> <span class="ident">DecodeUtf16Error</span> {
<span class="doccomment">/// Returns the unpaired surrogate which caused this error.</span>
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">unpaired_surrogate</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> <span class="ident">u16</span> {
<span class="self">self</span>.<span class="ident">code</span>
}
}
<span class="attribute">#[<span class="ident">stable</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"decode_utf16"</span>, <span class="ident">since</span> <span class="op">=</span> <span class="string">"1.9.0"</span>)]</span>
<span class="kw">impl</span> <span class="ident">fmt</span>::<span class="ident">Display</span> <span class="kw">for</span> <span class="ident">DecodeUtf16Error</span> {
<span class="kw">fn</span> <span class="ident">fmt</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">f</span>: <span class="kw-2">&</span><span class="kw-2">mut</span> <span class="ident">fmt</span>::<span class="ident">Formatter</span>) <span class="op">-></span> <span class="ident">fmt</span>::<span class="prelude-ty">Result</span> {
<span class="macro">write</span><span class="macro">!</span>(<span class="ident">f</span>, <span class="string">"unpaired surrogate found: {:x}"</span>, <span class="self">self</span>.<span class="ident">code</span>)
}
}
</pre>
</section><section id="search" class="content hidden"></section><section class="footer"></section><aside id="help" class="hidden"><div><h1 class="hidden">Help</h1><div class="shortcuts"><h2>Keyboard Shortcuts</h2><dl><dt><kbd>?</kbd></dt><dd>Show this help dialog</dd><dt><kbd>S</kbd></dt><dd>Focus the search field</dd><dt><kbd>↑</kbd></dt><dd>Move up in search results</dd><dt><kbd>↓</kbd></dt><dd>Move down in search results</dd><dt><kbd>↹</kbd></dt><dd>Switch tab</dd><dt><kbd>⏎</kbd></dt><dd>Go to active search result</dd><dt><kbd>+</kbd></dt><dd>Expand all sections</dd><dt><kbd>-</kbd></dt><dd>Collapse all sections</dd></dl></div><div class="infos"><h2>Search Tricks</h2><p>Prefix searches with a type followed by a colon (e.g. <code>fn:</code>) to restrict the search to a given type.</p><p>Accepted types are: <code>fn</code>, <code>mod</code>, <code>struct</code>, <code>enum</code>, <code>trait</code>, <code>type</code>, <code>macro</code>, and <code>const</code>.</p><p>Search functions by type signature (e.g. <code>vec -> usize</code> or <code>* -> vec</code>)</p><p>Search multiple things at once by splitting your query with comma (e.g. <code>str,u8</code> or <code>String,struct:Vec,test</code>)</p></div></div></aside><script>window.rootPath = "../../../";window.currentCrate = "core";</script><script src="../../../aliases.js"></script><script src="../../../main.js"></script><script defer src="../../../search-index.js"></script></body></html>
distrib
>
Mageia
>
6
>
armv7hl
>
media
>
core-updates
>
by-pkgid
>
4e2dbb669434a7691662cb2f0ad38972
>
files
>
11536
