| <!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 `/home/travis/.cargo/registry/src/github.com-1ecc6299db9ec823/encode_unicode-0.1.3/src/traits.rs`."> |
| <meta name="keywords" content="rust, rustlang, rust-lang"> |
| |
| <title>traits.rs.html -- source</title> |
| |
| <link rel="stylesheet" type="text/css" href="../../normalize.css"> |
| <link rel="stylesheet" type="text/css" href="../../rustdoc.css"> |
| <link rel="stylesheet" type="text/css" href="../../main.css"> |
| |
| |
| |
| |
| </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"> |
| |
| |
| </nav> |
| |
| <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"> |
| </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> |
| <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> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| </pre><pre class="rust "> |
| <span class="comment">/* Copyright 2016 Torbjørn Birch Moltu |
| * |
| * Licensed under the Apache License, Version 2.0, <LICENSE-APACHE or |
| * http://apache.org/licenses/LICENSE-2.0> or the MIT license <LICENSE-MIT or |
| * http://opensource.org/licenses/MIT>, at your option. This file may not be |
| * copied, modified, or distributed except according to those terms. |
| */</span> |
| |
| <span class="attribute">#<span class="op">!</span>[<span class="ident">allow</span>(<span class="ident">unused_unsafe</span>)]</span><span class="comment">// explicit unsafe{} blocks in unsafe functions are a good thing.</span> |
| |
| <span class="kw">use</span> <span class="ident">Utf8Char</span>; |
| <span class="kw">use</span> <span class="ident">Utf16Char</span>; |
| <span class="kw">use</span> <span class="ident">Utf8Iterator</span>; |
| <span class="kw">use</span> <span class="ident">Utf16Iterator</span>; |
| <span class="kw">use</span> <span class="ident">error</span>::<span class="kw-2">*</span>; |
| <span class="kw">extern</span> <span class="kw">crate</span> <span class="ident">std</span>; |
| <span class="kw">use</span> <span class="ident">std</span>::{<span class="ident">char</span>,<span class="ident">u32</span>, <span class="ident">mem</span>}; |
| <span class="kw">use</span> <span class="ident">std</span>::<span class="ident">ops</span>::<span class="ident">Not</span>; |
| |
| <span class="comment">// TODO better docs and tests</span> |
| |
| <span class="doccomment">/// Methods for working with `u8`s UTF-8.</span> |
| <span class="kw">pub</span> <span class="kw">trait</span> <span class="ident">U8UtfExt</span> { |
| <span class="doccomment">/// How many more bytes will you need to complete this codepoint?</span> |
| <span class="doccomment">/// Failures:</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// * `128..192`: ContinuationByte</span> |
| <span class="doccomment">/// * `240..`: TooLongSequence</span> |
| <span class="kw">fn</span> <span class="ident">extra_utf8_bytes</span>(<span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">usize</span>,<span class="ident">InvalidUtf8FirstByte</span><span class="op">></span>; |
| |
| <span class="doccomment">/// How many more bytes will you need to complete this codepoint?</span> |
| <span class="doccomment">/// Assumes that self is a valid UTF-8 start.</span> |
| <span class="doccomment">/// Returns `self.not().leading_zeros().saturating_sub(1)`</span> |
| <span class="kw">fn</span> <span class="ident">extra_utf8_bytes_unchecked</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">usize</span>; |
| } |
| |
| <span class="kw">impl</span> <span class="ident">U8UtfExt</span> <span class="kw">for</span> <span class="ident">u8</span> { |
| <span class="kw">fn</span> <span class="ident">extra_utf8_bytes</span>(<span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="ident">usize</span>,<span class="ident">InvalidUtf8FirstByte</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">error</span>::<span class="ident">InvalidUtf8FirstByte</span>::{<span class="ident">ContinuationByte</span>,<span class="ident">TooLongSeqence</span>}; |
| <span class="kw">match</span> <span class="self">self</span>.<span class="ident">not</span>().<span class="ident">leading_zeros</span>() { |
| <span class="number">0</span> <span class="op">=></span> <span class="prelude-val">Ok</span>(<span class="number">0</span>),<span class="comment">// ascii</span> |
| <span class="number">1</span> <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">ContinuationByte</span>),<span class="comment">// following byte</span> |
| <span class="ident">n</span> <span class="kw">if</span> <span class="ident">n</span> <span class="op"><</span> <span class="number">5</span> <span class="op">=></span> <span class="prelude-val">Ok</span>(<span class="ident">n</span> <span class="kw">as</span> <span class="ident">usize</span><span class="op">-</span><span class="number">1</span>),<span class="comment">// start of multibyte</span> |
| _ <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">TooLongSeqence</span>),<span class="comment">// too big</span> |
| } |
| } |
| <span class="kw">fn</span> <span class="ident">extra_utf8_bytes_unchecked</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">usize</span> { |
| (<span class="self">self</span>.<span class="ident">not</span>().<span class="ident">leading_zeros</span>()<span class="kw">as</span> <span class="ident">usize</span>).<span class="ident">saturating_sub</span>(<span class="number">1</span>) |
| } |
| } |
| |
| |
| <span class="doccomment">/// Methods for working with `u16`s as UTF-16 units.</span> |
| <span class="kw">pub</span> <span class="kw">trait</span> <span class="ident">U16UtfExt</span> { |
| <span class="doccomment">/// Will you need an extra unit to complete this codepoint?</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Failures:</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// 0xdc00..0xe000</span> |
| <span class="kw">fn</span> <span class="ident">utf16_needs_extra_unit</span>(<span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">bool</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Does this `u16` need another `u16` to complete a codepoint?</span> |
| <span class="doccomment">/// Returns `(self & 0xfc00) == 0xd800`</span> |
| <span class="kw">fn</span> <span class="ident">utf16_is_leading_surrogate</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">bool</span>; |
| } |
| <span class="kw">impl</span> <span class="ident">U16UtfExt</span> <span class="kw">for</span> <span class="ident">u16</span> { |
| <span class="kw">fn</span> <span class="ident">utf16_needs_extra_unit</span>(<span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">bool</span><span class="op">></span> {<span class="kw">match</span> <span class="self">self</span> { |
| <span class="comment">// https://en.wikipedia.org/wiki/UTF-16#U.2B10000_to_U.2B10FFFF</span> |
| <span class="number">0x_dc_00</span>...<span class="number">0x_df_ff</span> <span class="op">=></span> <span class="prelude-val">None</span>, |
| <span class="number">0x_d8_00</span>...<span class="number">0x_db_ff</span> <span class="op">=></span> <span class="prelude-val">Some</span>(<span class="bool-val">true</span>), |
| _ <span class="op">=></span> <span class="prelude-val">Some</span>(<span class="bool-val">false</span>), |
| }} |
| |
| <span class="kw">fn</span> <span class="ident">utf16_is_leading_surrogate</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">bool</span> { |
| (<span class="self">self</span> <span class="op">&</span> <span class="number">0xfc00</span>) <span class="op">==</span> <span class="number">0xd800</span><span class="comment">// Clear the ten content bytes of a surrogate,</span> |
| <span class="comment">// and see if it's a leading surrogate.</span> |
| } |
| } |
| |
| |
| |
| |
| <span class="doccomment">/// Extension trait for `char` that adds methods for converting to and from UTF-8 or UTF-16.</span> |
| <span class="kw">pub</span> <span class="kw">trait</span> <span class="ident">CharExt</span>: <span class="ident">Sized</span> { |
| <span class="doccomment">/// Get the UTF-8 representation of this codepoint.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// `Utf8Char` is to `[u8;4]` what `char` is to `u32`:</span> |
| <span class="doccomment">/// a restricted type that cannot be mutated internally.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf8</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf8Char</span>; |
| |
| <span class="doccomment">/// Get the UTF-16 representation of this codepoint.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// `Utf16Char` is to `(u16,Option<u16>)` what `char` is to `u32`:</span> |
| <span class="doccomment">/// a restricted type that cannot be mutated internally.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf16</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf16Char</span>; |
| |
| <span class="doccomment">/// Iterate over or [read](https://doc.rust-lang.org/std/io/trait.Read.html)</span> |
| <span class="doccomment">/// the one to four bytes in the UTF-8 representation of this codepoint.</span> |
| <span class="kw">fn</span> <span class="ident">iter_utf8_bytes</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf8Iterator</span>; |
| |
| <span class="doccomment">/// Iterate over the one or two units in the UTF-16 representation of this codepoint.</span> |
| <span class="kw">fn</span> <span class="ident">iter_utf16_units</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf16Iterator</span>; |
| |
| |
| <span class="doccomment">/// Convert this char to UTF-8, and then</span> |
| <span class="doccomment">/// returns the number of bytes written.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// `None` is returned if the buffer is too small; then the buffer is left unmodified.</span> |
| <span class="doccomment">/// A buffer of length four is always large enough.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// Similar to the unstable `.encode_utf8()`,</span> |
| <span class="doccomment">/// but that method somehow still exist on stable, so I have to use a different name.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf8_slice</span>(<span class="self">self</span>, <span class="ident">dst</span>: <span class="kw-2">&</span><span class="kw-2">mut</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Convert this char to UTF-16, and then</span> |
| <span class="doccomment">/// returns the number of units written.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// `None` is returned if the buffer is too small; then the buffer is left unmodified.</span> |
| <span class="doccomment">/// A buffer of length two is always large enough.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// Similar to the unstable `.encode_utf16()`,</span> |
| <span class="doccomment">/// but that method somehow still exist on stable, so I have to use a different name.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf16_slice</span>(<span class="self">self</span>, <span class="ident">dst</span>: <span class="kw-2">&</span><span class="kw-2">mut</span>[<span class="ident">u16</span>]) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>; |
| |
| |
| <span class="doccomment">/// Convert this char to an UTF-8 array and lenght,</span> |
| <span class="doccomment">/// The returned array is left-aligned, and the usize is how many bytes are used.</span> |
| <span class="doccomment">/// The unused bytes are zero.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf8_array</span>(<span class="self">self</span>) <span class="op">-></span> ([<span class="ident">u8</span>; <span class="number">4</span>], <span class="ident">usize</span>); |
| |
| <span class="doccomment">/// Convert this char to UTF-16.</span> |
| <span class="doccomment">/// The second `u16` is `Some` if a surrogate pair is required.</span> |
| <span class="kw">fn</span> <span class="ident">to_utf16_tuple</span>(<span class="self">self</span>) <span class="op">-></span> (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>); |
| |
| |
| |
| <span class="doccomment">/// Create a `char` from the start of a slice intepreted as UTF-8, and return how many bytes were needed.</span> |
| <span class="kw">fn</span> <span class="ident">from_utf8_slice</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span>(<span class="self">Self</span>,<span class="ident">usize</span>),<span class="ident">InvalidUtf8Slice</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Read one or two UTF-16 units into a `char`, and also return how many units were needed.</span> |
| <span class="kw">fn</span> <span class="ident">from_utf16_slice</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u16</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span>(<span class="self">Self</span>,<span class="ident">usize</span>), <span class="ident">InvalidUtf16Slice</span><span class="op">></span>; |
| |
| |
| <span class="doccomment">/// Convert an UTF-8 sequence as returned from `.to_utf8_array()` into a `char`</span> |
| <span class="kw">fn</span> <span class="ident">from_utf8_array</span>(<span class="ident">utf8</span>: [<span class="ident">u8</span>; <span class="number">4</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>,<span class="ident">InvalidUtf8Array</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Convert a UTF-16 pair as returned from `.to_utf16_tuple()` into a `char`.</span> |
| <span class="kw">fn</span> <span class="ident">from_utf16_tuple</span>(<span class="ident">utf16</span>: (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>)) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>, <span class="ident">InvalidUtf16Tuple</span><span class="op">></span>; |
| |
| |
| <span class="doccomment">/// Convert an UTF-8 sequence into a char.</span> |
| <span class="doccomment">/// The length of the slice is the length of the sequence, should be 1,2,3 or 4.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Panics:</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// If the slice is empty</span> |
| <span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">from_utf8_exact_slice_unchecked</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="self">Self</span>; |
| |
| <span class="doccomment">/// Convert a UTF-16 tuple as returned from `.to_utf16_tuple()` into a `char`.</span> |
| <span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">from_utf16_tuple_unchecked</span>(<span class="ident">utf16</span>: (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>)) <span class="op">-></span> <span class="self">Self</span>; |
| |
| |
| <span class="doccomment">/// Perform some extra validations compared to `char::from_u32_unchecked()`</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Failures:</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// * the value is greater than 0x10ffff</span> |
| <span class="doccomment">/// * the value is between 0xd800 and 0xdfff (inclusive)</span> |
| <span class="kw">fn</span> <span class="ident">from_u32_detailed</span>(<span class="ident">c</span>: <span class="ident">u32</span>) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>,<span class="ident">InvalidCodePoint</span><span class="op">></span>; |
| } |
| |
| |
| |
| <span class="kw">impl</span> <span class="ident">CharExt</span> <span class="kw">for</span> <span class="ident">char</span> { |
| <span class="comment">/////////</span> |
| <span class="comment">//UTF-8//</span> |
| <span class="comment">/////////</span> |
| |
| <span class="kw">fn</span> <span class="ident">to_utf8</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf8Char</span> { |
| <span class="self">self</span>.<span class="ident">into</span>() |
| } |
| <span class="kw">fn</span> <span class="ident">iter_utf8_bytes</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf8Iterator</span> { |
| <span class="self">self</span>.<span class="ident">to_utf8</span>().<span class="ident">into_iter</span>() |
| } |
| <span class="kw">fn</span> <span class="ident">to_utf8_slice</span>(<span class="self">self</span>, <span class="ident">dst</span>: <span class="kw-2">&</span><span class="kw-2">mut</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> { |
| <span class="self">self</span>.<span class="ident">to_utf8</span>().<span class="ident">to_slice</span>(<span class="ident">dst</span>) |
| } |
| |
| <span class="kw">fn</span> <span class="ident">to_utf8_array</span>(<span class="self">self</span>) <span class="op">-></span> ([<span class="ident">u8</span>; <span class="number">4</span>], <span class="ident">usize</span>) { |
| <span class="kw">let</span> <span class="ident">len</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">len_utf8</span>(); |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">c</span> <span class="op">=</span> <span class="self">self</span> <span class="kw">as</span> <span class="ident">u32</span>; |
| <span class="kw">if</span> <span class="ident">len</span> <span class="op">==</span> <span class="number">1</span> {<span class="comment">// ASCII, the common case</span> |
| ([<span class="ident">c</span> <span class="kw">as</span> <span class="ident">u8</span>, <span class="number">0</span>, <span class="number">0</span>, <span class="number">0</span>], <span class="number">1</span>) |
| } <span class="kw">else</span> { |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">parts</span> <span class="op">=</span> <span class="number">0</span>;<span class="comment">// convert to 6-bit bytes</span> |
| <span class="ident">parts</span> <span class="op">|=</span> <span class="ident">c</span> <span class="op">&</span> <span class="number">0x3f</span>; <span class="ident">c</span><span class="op">>>=</span><span class="number">6</span>; |
| <span class="ident">parts</span><span class="op"><<=</span><span class="number">8</span>; <span class="ident">parts</span> <span class="op">|=</span> <span class="ident">c</span> <span class="op">&</span> <span class="number">0x3f</span>; <span class="ident">c</span><span class="op">>>=</span><span class="number">6</span>; |
| <span class="ident">parts</span><span class="op"><<=</span><span class="number">8</span>; <span class="ident">parts</span> <span class="op">|=</span> <span class="ident">c</span> <span class="op">&</span> <span class="number">0x3f</span>; <span class="ident">c</span><span class="op">>>=</span><span class="number">6</span>; |
| <span class="ident">parts</span><span class="op"><<=</span><span class="number">8</span>; <span class="ident">parts</span> <span class="op">|=</span> <span class="ident">c</span> <span class="op">&</span> <span class="number">0x3f</span>; |
| <span class="ident">parts</span> <span class="op">|=</span> <span class="number">0x80_80_80_80</span>;<span class="comment">// set the most significant bit</span> |
| <span class="ident">parts</span> <span class="op">>>=</span> <span class="number">8</span><span class="kw-2">*</span>(<span class="number">4</span><span class="op">-</span><span class="ident">len</span>);<span class="comment">// right-align bytes</span> |
| <span class="comment">// Now, unused bytes are zero, (which matters for Utf8Char.eq()) and the rest are 0b10xx_xxxx</span> |
| |
| <span class="comment">// set header on first byte</span> |
| <span class="ident">parts</span> <span class="op">|=</span> (<span class="number">0xff_00u32</span> <span class="op">>></span> <span class="ident">len</span>) <span class="op">&</span> <span class="number">0xff</span>;<span class="comment">// store length</span> |
| <span class="ident">parts</span> <span class="op">&=</span> <span class="ident">Not</span>::<span class="ident">not</span>(<span class="number">1u32</span> <span class="op"><<</span> <span class="number">7</span><span class="op">-</span><span class="ident">len</span>);<span class="comment">// clear the next bit after it</span> |
| |
| <span class="kw">let</span> <span class="ident">bytes</span>: [<span class="ident">u8</span>; <span class="number">4</span>] <span class="op">=</span> <span class="kw">unsafe</span>{ <span class="ident">mem</span>::<span class="ident">transmute</span>(<span class="ident">u32</span>::<span class="ident">from_le</span>(<span class="ident">parts</span>)) }; |
| (<span class="ident">bytes</span>, <span class="ident">len</span>) |
| } |
| } |
| |
| |
| <span class="kw">fn</span> <span class="ident">from_utf8_slice</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span>(<span class="self">Self</span>,<span class="ident">usize</span>),<span class="ident">InvalidUtf8Slice</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf8</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf8Slice</span>::<span class="kw-2">*</span>; |
| <span class="kw">let</span> <span class="ident">first</span> <span class="op">=</span> <span class="kw-2">*</span><span class="macro">try</span><span class="macro">!</span>(<span class="ident">src</span>.<span class="ident">first</span>().<span class="ident">ok_or</span>(<span class="ident">TooShort</span>(<span class="number">1</span>))); |
| <span class="kw">let</span> <span class="ident">extra</span> <span class="op">=</span> <span class="macro">try</span><span class="macro">!</span>(<span class="ident">first</span>.<span class="ident">extra_utf8_bytes</span>().<span class="ident">map_err</span>(<span class="op">|</span><span class="ident">e</span><span class="op">|</span> <span class="ident">Utf8</span>(<span class="ident">FirstByte</span>(<span class="ident">e</span>)) )); |
| <span class="kw">if</span> <span class="ident">extra</span> <span class="op">==</span> <span class="number">0</span> { |
| <span class="kw">return</span> <span class="prelude-val">Ok</span>((<span class="ident">first</span> <span class="kw">as</span> <span class="ident">char</span>, <span class="number">1</span>)); |
| } <span class="kw">else</span> <span class="kw">if</span> <span class="ident">src</span>.<span class="ident">len</span>() <span class="op"><=</span> <span class="ident">extra</span> { |
| <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">TooShort</span>(<span class="ident">extra</span><span class="op">+</span><span class="number">1</span>)) |
| } |
| <span class="kw">let</span> <span class="ident">src</span> <span class="op">=</span> <span class="kw-2">&</span><span class="ident">src</span>[..<span class="number">1</span><span class="op">+</span><span class="ident">extra</span>]; |
| <span class="kw">for</span> (<span class="ident">i</span>, <span class="kw-2">&</span><span class="ident">b</span>) <span class="kw">in</span> <span class="ident">src</span>.<span class="ident">iter</span>().<span class="ident">enumerate</span>().<span class="ident">skip</span>(<span class="number">1</span>) { |
| <span class="kw">if</span> <span class="ident">b</span> <span class="op"><</span> <span class="number">0b1000_0000</span> <span class="op">||</span> <span class="ident">b</span> <span class="op">></span> <span class="number">0b1011_1111</span> { |
| <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">Utf8</span>(<span class="ident">NotAContinuationByte</span>(<span class="ident">i</span>))); |
| } |
| } |
| <span class="kw">if</span> <span class="ident">overlong</span>(<span class="ident">src</span>[<span class="number">0</span>], <span class="ident">src</span>[<span class="number">1</span>]) { |
| <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">Utf8</span>(<span class="ident">OverLong</span>)); |
| } |
| <span class="kw">let</span> <span class="ident">c</span> <span class="op">=</span> <span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_utf8_exact_slice_unchecked</span>(<span class="ident">src</span>) }; |
| <span class="ident">char</span>::<span class="ident">from_u32_detailed</span>(<span class="ident">c</span> <span class="kw">as</span> <span class="ident">u32</span>).<span class="ident">map</span>(<span class="op">|</span><span class="ident">c</span><span class="op">|</span> (<span class="ident">c</span>,<span class="ident">src</span>.<span class="ident">len</span>()) ).<span class="ident">map_err</span>( <span class="ident">CodePoint</span> ) |
| } |
| |
| <span class="kw">fn</span> <span class="ident">from_utf8_array</span>(<span class="ident">utf8</span>: [<span class="ident">u8</span>; <span class="number">4</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>,<span class="ident">InvalidUtf8Array</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf8</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf8Array</span>::<span class="kw-2">*</span>; |
| <span class="kw">let</span> <span class="ident">len</span> <span class="op">=</span> <span class="kw">match</span> <span class="ident">utf8</span>[<span class="number">0</span>].<span class="ident">extra_utf8_bytes</span>() { |
| <span class="prelude-val">Ok</span>(<span class="number">0</span>) <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">Ok</span>(<span class="ident">utf8</span>[<span class="number">0</span>] <span class="kw">as</span> <span class="ident">char</span>), |
| <span class="prelude-val">Ok</span>(<span class="ident">l</span>) <span class="op">=></span> <span class="ident">l</span><span class="op">+</span><span class="number">1</span>, |
| <span class="prelude-val">Err</span>(<span class="ident">err</span>) <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">Utf8</span>(<span class="ident">FirstByte</span>(<span class="ident">err</span>))), |
| }; |
| <span class="kw">for</span> (<span class="ident">i</span>, <span class="kw-2">&</span><span class="ident">b</span>) <span class="kw">in</span> <span class="ident">utf8</span>[..<span class="ident">len</span>].<span class="ident">iter</span>().<span class="ident">enumerate</span>().<span class="ident">skip</span>(<span class="number">1</span>) { |
| <span class="kw">if</span> <span class="ident">b</span> <span class="op"><</span> <span class="number">0b1000_0000</span> <span class="op">||</span> <span class="ident">b</span> <span class="op">></span> <span class="number">0b1011_1111</span> { |
| <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">Utf8</span>(<span class="ident">NotAContinuationByte</span>(<span class="ident">i</span>))); |
| } |
| } |
| |
| <span class="kw">if</span> <span class="ident">overlong</span>(<span class="ident">utf8</span>[<span class="number">0</span>], <span class="ident">utf8</span>[<span class="number">1</span>]) { |
| <span class="kw">return</span> <span class="prelude-val">Err</span>(<span class="ident">Utf8</span>(<span class="ident">OverLong</span>)); |
| } |
| <span class="kw">let</span> <span class="ident">c</span> <span class="op">=</span> <span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_utf8_exact_slice_unchecked</span>(<span class="kw-2">&</span><span class="ident">utf8</span>[..<span class="ident">len</span>]) }; |
| <span class="ident">char</span>::<span class="ident">from_u32_detailed</span>(<span class="ident">c</span> <span class="kw">as</span> <span class="ident">u32</span>).<span class="ident">map_err</span>( <span class="ident">CodePoint</span> ) |
| } |
| |
| <span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">from_utf8_exact_slice_unchecked</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-></span> <span class="self">Self</span> { |
| <span class="kw">if</span> <span class="ident">src</span>.<span class="ident">len</span>() <span class="op">==</span> <span class="number">1</span> { |
| <span class="ident">src</span>[<span class="number">0</span>] <span class="kw">as</span> <span class="ident">char</span> |
| } <span class="kw">else</span> { |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">c</span> <span class="op">=</span> <span class="ident">src</span>[<span class="number">0</span>] <span class="kw">as</span> <span class="ident">u32</span> <span class="op">&</span> (<span class="number">0xff</span> <span class="op">>></span> <span class="number">2</span><span class="op">+</span><span class="ident">src</span>.<span class="ident">len</span>()<span class="op">-</span><span class="number">1</span>); |
| <span class="kw">for</span> <span class="ident">b</span> <span class="kw">in</span> <span class="kw-2">&</span><span class="ident">src</span>[<span class="number">1</span>..] { |
| <span class="ident">c</span> <span class="op">=</span> (<span class="ident">c</span> <span class="op"><<</span> <span class="number">6</span>) <span class="op">|</span> (<span class="ident">b</span> <span class="op">&</span> <span class="number">0b00111111</span>) <span class="kw">as</span> <span class="ident">u32</span>; |
| } |
| <span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_u32_unchecked</span>(<span class="ident">c</span>) } |
| } |
| } |
| |
| |
| |
| <span class="comment">//////////</span> |
| <span class="comment">//UTF-16//</span> |
| <span class="comment">//////////</span> |
| |
| <span class="kw">fn</span> <span class="ident">to_utf16</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf16Char</span> { |
| <span class="ident">Utf16Char</span>::<span class="ident">from</span>(<span class="self">self</span>) |
| } |
| <span class="kw">fn</span> <span class="ident">iter_utf16_units</span>(<span class="self">self</span>) <span class="op">-></span> <span class="ident">Utf16Iterator</span> { |
| <span class="self">self</span>.<span class="ident">to_utf16</span>().<span class="ident">into_iter</span>() |
| } |
| |
| <span class="kw">fn</span> <span class="ident">to_utf16_slice</span>(<span class="self">self</span>, <span class="ident">dst</span>: <span class="kw-2">&</span><span class="kw-2">mut</span>[<span class="ident">u16</span>]) <span class="op">-></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">first</span>, <span class="ident">second</span>) <span class="op">=</span> <span class="self">self</span>.<span class="ident">to_utf16_tuple</span>(); |
| <span class="kw">match</span> (<span class="ident">dst</span>.<span class="ident">len</span>(), <span class="ident">second</span>) { |
| (<span class="number">0</span>, _) <span class="op">=></span> <span class="prelude-val">None</span>, |
| (<span class="number">1</span>, <span class="prelude-val">Some</span>(_)) <span class="op">=></span> <span class="prelude-val">None</span>, |
| (_, <span class="prelude-val">Some</span>(<span class="ident">second</span>)) <span class="op">=></span> {<span class="ident">dst</span>[<span class="number">0</span>] <span class="op">=</span> <span class="ident">first</span>; |
| <span class="ident">dst</span>[<span class="number">1</span>] <span class="op">=</span> <span class="ident">second</span>; |
| <span class="prelude-val">Some</span>(<span class="number">2</span>) |
| }, |
| (_, <span class="prelude-val">None</span>) <span class="op">=></span> {<span class="ident">dst</span>[<span class="number">0</span>] <span class="op">=</span> <span class="ident">first</span>; |
| <span class="prelude-val">Some</span>(<span class="number">1</span>) |
| }, |
| } |
| } |
| |
| <span class="kw">fn</span> <span class="ident">to_utf16_tuple</span>(<span class="self">self</span>) <span class="op">-></span> (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>) { |
| <span class="kw">let</span> <span class="ident">c</span> <span class="op">=</span> <span class="self">self</span> <span class="kw">as</span> <span class="ident">u32</span>; |
| <span class="kw">if</span> <span class="ident">c</span> <span class="op"><=</span> <span class="number">0x_ff_ff</span> {<span class="comment">// single (or reserved, which we ignore)</span> |
| (<span class="ident">c</span> <span class="kw">as</span> <span class="ident">u16</span>, <span class="prelude-val">None</span>) |
| } <span class="kw">else</span> {<span class="comment">// double (or too high, which we ignore)</span> |
| <span class="kw">let</span> <span class="ident">c</span> <span class="op">=</span> <span class="ident">c</span> <span class="op">-</span> <span class="number">0x_01_00_00</span>; |
| <span class="kw">let</span> <span class="ident">high</span> <span class="op">=</span> <span class="number">0x_d8_00</span> <span class="op">+</span> (<span class="ident">c</span> <span class="op">>></span> <span class="number">10</span>); |
| <span class="kw">let</span> <span class="ident">low</span> <span class="op">=</span> <span class="number">0x_dc_00</span> <span class="op">+</span> (<span class="ident">c</span> <span class="op">&</span> <span class="number">0x_03_ff</span>); |
| (<span class="ident">high</span> <span class="kw">as</span> <span class="ident">u16</span>, <span class="prelude-val">Some</span>(<span class="ident">low</span> <span class="kw">as</span> <span class="ident">u16</span>)) |
| } |
| } |
| |
| |
| <span class="kw">fn</span> <span class="ident">from_utf16_slice</span>(<span class="ident">src</span>: <span class="kw-2">&</span>[<span class="ident">u16</span>]) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span>(<span class="self">Self</span>,<span class="ident">usize</span>), <span class="ident">InvalidUtf16Slice</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf16Slice</span>::<span class="kw-2">*</span>; |
| <span class="kw">let</span> <span class="ident">first</span> <span class="op">=</span> <span class="kw-2">*</span><span class="macro">try</span><span class="macro">!</span>(<span class="ident">src</span>.<span class="ident">first</span>().<span class="ident">ok_or</span>(<span class="ident">EmptySlice</span>)); |
| <span class="kw">match</span> (<span class="ident">first</span>.<span class="ident">utf16_needs_extra_unit</span>(), <span class="ident">src</span>.<span class="ident">get</span>(<span class="number">1</span>).<span class="ident">cloned</span>()) { |
| (<span class="prelude-val">Some</span>(<span class="bool-val">false</span>), _ ) <span class="op">=></span> <span class="prelude-val">Ok</span>((<span class="number">1</span>, <span class="prelude-val">None</span>)), |
| (<span class="prelude-val">Some</span>(<span class="bool-val">true</span>) , <span class="prelude-val">Some</span>(<span class="number">0x_dc_00</span>...<span class="number">0x_df_ff</span>)) <span class="op">=></span> <span class="prelude-val">Ok</span>((<span class="number">2</span>, <span class="prelude-val">Some</span>(<span class="ident">src</span>[<span class="number">1</span>]))), |
| (<span class="prelude-val">Some</span>(<span class="bool-val">true</span>) , <span class="prelude-val">Some</span>( _ )) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">SecondNotLowSurrogate</span>), |
| (<span class="prelude-val">Some</span>(<span class="bool-val">true</span>) , <span class="prelude-val">None</span> ) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">MissingSecond</span>), |
| (<span class="prelude-val">None</span> , _ ) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">FirstLowSurrogate</span>), |
| }.<span class="ident">map</span>(<span class="op">|</span>(<span class="ident">len</span>,<span class="ident">second</span>)<span class="op">|</span> (<span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_utf16_tuple_unchecked</span>((<span class="ident">first</span>,<span class="ident">second</span>)) }, <span class="ident">len</span>) ) |
| } |
| |
| <span class="kw">fn</span> <span class="ident">from_utf16_tuple</span>(<span class="ident">utf16</span>: (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>)) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>, <span class="ident">InvalidUtf16Tuple</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidUtf16Tuple</span>::<span class="kw-2">*</span>; |
| <span class="kw">match</span> <span class="ident">utf16</span> { |
| (<span class="number">0x_00_00</span>...<span class="number">0x_d7_ff</span>, <span class="prelude-val">None</span>) <span class="op">=></span> <span class="prelude-val">Ok</span>(()),<span class="comment">// single</span> |
| (<span class="number">0x_e0_00</span>...<span class="number">0x_ff_ff</span>, <span class="prelude-val">None</span>) <span class="op">=></span> <span class="prelude-val">Ok</span>(()),<span class="comment">// single</span> |
| (<span class="number">0x_d8_00</span>...<span class="number">0x_db_ff</span>, <span class="prelude-val">Some</span>(<span class="number">0x_dc_00</span>...<span class="number">0x_df_ff</span>)) <span class="op">=></span> <span class="prelude-val">Ok</span>(()),<span class="comment">// correct surrogate pair</span> |
| (<span class="number">0x_d8_00</span>...<span class="number">0x_db_ff</span>, <span class="prelude-val">Some</span>(_)) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">InvalidSecond</span>), |
| (<span class="number">0x_d8_00</span>...<span class="number">0x_db_ff</span>, <span class="prelude-val">None</span>) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">MissingSecond</span>), |
| (<span class="number">0x_dc_00</span>...<span class="number">0x_df_ff</span>, _) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">FirstIsTrailingSurrogate</span>), |
| (_, <span class="prelude-val">Some</span>(_)) <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">SuperfluousSecond</span>),<span class="comment">// should be no second</span> |
| (_, _) <span class="op">=></span> <span class="macro">unreachable</span><span class="macro">!</span>() |
| }.<span class="ident">map</span>(<span class="op">|</span>_<span class="op">|</span> <span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_utf16_tuple_unchecked</span>(<span class="ident">utf16</span>) } ) |
| } |
| |
| <span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">from_utf16_tuple_unchecked</span>(<span class="ident">utf16</span>: (<span class="ident">u16</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u16</span><span class="op">></span>)) <span class="op">-></span> <span class="self">Self</span> { |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">c</span> <span class="op">=</span> <span class="ident">utf16</span>.<span class="number">0</span> <span class="kw">as</span> <span class="ident">u32</span>; |
| <span class="kw">if</span> <span class="kw">let</span> <span class="prelude-val">Some</span>(<span class="ident">second</span>) <span class="op">=</span> <span class="ident">utf16</span>.<span class="number">1</span> { |
| <span class="kw">let</span> <span class="ident">high</span> <span class="op">=</span> (<span class="ident">c</span><span class="op">-</span><span class="number">0x_d8_00</span>) <span class="op"><<</span> <span class="number">10</span>; |
| <span class="kw">let</span> <span class="ident">low</span> <span class="op">=</span> <span class="ident">second</span> <span class="kw">as</span> <span class="ident">u32</span> <span class="op">-</span> <span class="number">0x_dc_00</span>; |
| <span class="ident">c</span> <span class="op">=</span> <span class="ident">high</span> <span class="op">|</span> <span class="ident">low</span>; |
| <span class="ident">c</span> <span class="op">+=</span> <span class="number">0x_01_00_00</span>; |
| } |
| <span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_u32_unchecked</span>(<span class="ident">c</span>) } |
| } |
| |
| |
| <span class="kw">fn</span> <span class="ident">from_u32_detailed</span>(<span class="ident">c</span>: <span class="ident">u32</span>) <span class="op">-></span> <span class="prelude-ty">Result</span><span class="op"><</span><span class="self">Self</span>,<span class="ident">InvalidCodePoint</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">errors</span>::<span class="ident">InvalidCodePoint</span>::<span class="kw-2">*</span>; |
| <span class="kw">match</span> <span class="ident">c</span> { |
| <span class="comment">// reserved for UTF-16 surrogate pairs</span> |
| <span class="number">0xd8_00</span>...<span class="number">0xdf_ff</span> <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">Utf16Reserved</span>), |
| <span class="comment">// too big</span> |
| <span class="number">0x11_00_00</span>...<span class="ident">u32</span>::<span class="ident">MAX</span> <span class="op">=></span> <span class="prelude-val">Err</span>(<span class="ident">TooHigh</span>), |
| _ <span class="op">=></span> <span class="prelude-val">Ok</span>(<span class="kw">unsafe</span>{ <span class="ident">char</span>::<span class="ident">from_u32_unchecked</span>(<span class="ident">c</span>) }), |
| } |
| } |
| } |
| |
| |
| <span class="comment">// If all the data bits in the first byte are zero, the sequence might be longer than necessary</span> |
| <span class="comment">// When you go up one byte, you gain 6-1 data bits, so if the five first are zero it's too long.</span> |
| <span class="comment">// The first byte has 3 + (4-len) data bits, which we know are zero.</span> |
| <span class="comment">// The first two bits in the second byte are 10, which gets shifted out.</span> |
| <span class="kw">fn</span> <span class="ident">overlong</span>(<span class="ident">first</span>: <span class="ident">u8</span>, <span class="ident">second</span>: <span class="ident">u8</span>) <span class="op">-></span> <span class="ident">bool</span> { |
| <span class="kw">let</span> <span class="ident">both</span> <span class="op">=</span> ((<span class="ident">first</span> <span class="kw">as</span> <span class="ident">u16</span>) <span class="op"><<</span> <span class="number">8</span>) <span class="op">|</span> (<span class="ident">second</span> <span class="op"><<</span> <span class="number">2</span>) <span class="kw">as</span> <span class="ident">u16</span>; |
| <span class="kw">let</span> <span class="ident">both</span> <span class="op">=</span> <span class="ident">both</span> <span class="op"><<</span> <span class="number">1</span><span class="op">+</span><span class="ident">both</span>.<span class="ident">not</span>().<span class="ident">leading_zeros</span>(); |
| <span class="ident">both</span>.<span class="ident">leading_zeros</span>() <span class="op">>=</span> <span class="number">5</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>?</dt> |
| <dd>Show this help dialog</dd> |
| <dt>S</dt> |
| <dd>Focus the search field</dd> |
| <dt>⇤</dt> |
| <dd>Move up in search results</dd> |
| <dt>⇥</dt> |
| <dd>Move down in search results</dd> |
| <dt>⏎</dt> |
| <dd>Go to active search result</dd> |
| <dt>+</dt> |
| <dd>Collapse/expand 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> |
| </div> |
| </div> |
| </aside> |
| |
| |
| |
| <script> |
| window.rootPath = "../../"; |
| window.currentCrate = "encode_unicode"; |
| </script> |
| <script src="../../main.js"></script> |
| <script defer src="../../search-index.js"></script> |
| </body> |
| </html> |
