| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/encoding_rs-0.8.32/src/shift_jis.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>shift_jis.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../normalize.css"><link rel="stylesheet" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../ayu.css" disabled><link rel="stylesheet" href="../../dark.css" disabled><link rel="stylesheet" href="../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../storage.js"></script><script defer src="../../source-script.js"></script><script defer src="../../source-files.js"></script><script defer src="../../main.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../encoding_rs/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../encoding_rs/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <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> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| </pre><pre class="rust"><code><span class="comment">// Copyright Mozilla Foundation. See the COPYRIGHT |
| // file at the top-level directory of this distribution. |
| // |
| // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or |
| // https://www.apache.org/licenses/LICENSE-2.0> or the MIT license |
| // <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your |
| // option. This file may not be copied, modified, or distributed |
| // except according to those terms. |
| |
| </span><span class="kw">use super</span>::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::data::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::handles::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::variant::<span class="kw-2">*</span>; |
| <span class="comment">// Rust 1.14.0 requires the following despite the asterisk above. |
| </span><span class="kw">use </span><span class="kw">super</span>::in_inclusive_range; |
| <span class="kw">use </span><span class="kw">super</span>::in_inclusive_range16; |
| |
| <span class="kw">pub struct </span>ShiftJisDecoder { |
| lead: <span class="prelude-ty">Option</span><u8>, |
| } |
| |
| <span class="kw">impl </span>ShiftJisDecoder { |
| <span class="kw">pub fn </span>new() -> VariantDecoder { |
| VariantDecoder::ShiftJis(ShiftJisDecoder { lead: <span class="prelude-val">None </span>}) |
| } |
| |
| <span class="kw">pub fn </span>in_neutral_state(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.lead.is_none() |
| } |
| |
| <span class="kw">fn </span>plus_one_if_lead(<span class="kw-2">&</span><span class="self">self</span>, byte_length: usize) -> <span class="prelude-ty">Option</span><usize> { |
| byte_length.checked_add(<span class="kw">match </span><span class="self">self</span>.lead { |
| <span class="prelude-val">None </span>=> <span class="number">0</span>, |
| <span class="prelude-val">Some</span>(<span class="kw">_</span>) => <span class="number">1</span>, |
| }) |
| } |
| |
| <span class="kw">pub fn </span>max_utf16_buffer_length(<span class="kw-2">&</span><span class="self">self</span>, byte_length: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="self">self</span>.plus_one_if_lead(byte_length) |
| } |
| |
| <span class="kw">pub fn </span>max_utf8_buffer_length_without_replacement(<span class="kw-2">&</span><span class="self">self</span>, byte_length: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="comment">// worst case: 1 to 3 (half-width katakana) |
| </span><span class="self">self</span>.max_utf8_buffer_length(byte_length) |
| } |
| |
| <span class="kw">pub fn </span>max_utf8_buffer_length(<span class="kw-2">&</span><span class="self">self</span>, byte_length: usize) -> <span class="prelude-ty">Option</span><usize> { |
| checked_mul(<span class="number">3</span>, <span class="self">self</span>.plus_one_if_lead(byte_length)) |
| } |
| |
| <span class="macro">ascii_compatible_two_byte_decoder_functions!</span>( |
| { |
| <span class="comment">// If lead is between 0x81 and 0x9F, inclusive, |
| // subtract offset 0x81. Else if lead is |
| // between 0xE0 and 0xFC, inclusive, subtract |
| // offset 0xC1. Else if lead is between |
| // 0xA1 and 0xDF, inclusive, map to half-width |
| // Katakana. Else if lead is 0x80, pass through. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>non_ascii_minus_offset = |
| non_ascii.wrapping_sub(<span class="number">0x81</span>); |
| <span class="kw">if </span>non_ascii_minus_offset > (<span class="number">0x9F </span>- <span class="number">0x81</span>) { |
| <span class="kw">let </span>non_ascii_minus_range_start = non_ascii.wrapping_sub(<span class="number">0xE0</span>); |
| <span class="kw">if </span>non_ascii_minus_range_start > (<span class="number">0xFC </span>- <span class="number">0xE0</span>) { |
| <span class="kw">let </span>non_ascii_minus_half_with_katakana_start = non_ascii.wrapping_sub(<span class="number">0xA1</span>); |
| <span class="kw">if </span>non_ascii_minus_half_with_katakana_start > (<span class="number">0xDF </span>- <span class="number">0xA1</span>) { |
| <span class="kw">if </span>non_ascii == <span class="number">0x80 </span>{ |
| handle.write_mid_bmp(<span class="number">0x80</span>); |
| <span class="comment">// Not caring about optimizing subsequent non-ASCII |
| </span><span class="kw">continue </span><span class="lifetime">'outermost</span>; |
| } |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">0</span>), |
| source.consumed(), |
| handle.written()); |
| } |
| handle.write_upper_bmp(<span class="number">0xFF61 </span>+ u16::from(non_ascii_minus_half_with_katakana_start)); |
| <span class="comment">// Not caring about optimizing subsequent non-ASCII |
| </span><span class="kw">continue </span><span class="lifetime">'outermost</span>; |
| } |
| non_ascii_minus_offset = non_ascii - <span class="number">0xC1</span>; |
| } |
| non_ascii_minus_offset |
| }, |
| { |
| <span class="comment">// If trail is between 0x40 and 0x7E, inclusive, |
| // subtract offset 0x40. Else if trail is |
| // between 0x80 and 0xFC, inclusive, subtract |
| // offset 0x41. |
| // Fast-track Hiragana (60% according to Lunde) |
| // and Katakana (10% acconding to Lunde). |
| // Hiragana doesn't cross 0x7F, but Katakana does. |
| // We can check for Hiragana before normalizing |
| // trail. |
| </span><span class="kw">let </span>trail_minus_hiragana = byte.wrapping_sub(<span class="number">0x9F</span>); |
| <span class="kw">if </span>lead_minus_offset == <span class="number">0x01 </span>&& trail_minus_hiragana < <span class="number">0x53 </span>{ |
| <span class="comment">// Hiragana |
| </span>handle.write_upper_bmp(<span class="number">0x3041 </span>+ u16::from(trail_minus_hiragana)) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>trail_minus_offset = |
| byte.wrapping_sub(<span class="number">0x40</span>); |
| <span class="kw">if </span>trail_minus_offset > (<span class="number">0x7E </span>- <span class="number">0x40</span>) { |
| <span class="kw">let </span>trail_minus_range_start = |
| byte.wrapping_sub(<span class="number">0x80</span>); |
| <span class="kw">if </span>trail_minus_range_start > (<span class="number">0xFC </span>- <span class="number">0x80</span>) { |
| <span class="kw">if </span>byte < <span class="number">0x80 </span>{ |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">0</span>), |
| unread_handle_trail.unread(), |
| handle.written()); |
| } |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">2</span>, <span class="number">0</span>), |
| unread_handle_trail.consumed(), |
| handle.written()); |
| } |
| trail_minus_offset = byte - <span class="number">0x41</span>; |
| } |
| <span class="kw">if </span>lead_minus_offset == <span class="number">0x02 </span>&& |
| trail_minus_offset < <span class="number">0x56 </span>{ |
| <span class="comment">// Katakana |
| </span>handle.write_upper_bmp(<span class="number">0x30A1 </span>+ u16::from(trail_minus_offset)) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>pointer = lead_minus_offset <span class="kw">as </span>usize * |
| <span class="number">188usize </span>+ |
| trail_minus_offset <span class="kw">as </span>usize; |
| <span class="kw">let </span>level1_pointer = pointer.wrapping_sub(<span class="number">1410</span>); |
| <span class="kw">if </span>level1_pointer < JIS0208_LEVEL1_KANJI.len() { |
| handle.write_upper_bmp(JIS0208_LEVEL1_KANJI[level1_pointer]) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>level2_pointer = pointer.wrapping_sub(<span class="number">4418</span>); |
| <span class="kw">if </span>level2_pointer < |
| JIS0208_LEVEL2_AND_ADDITIONAL_KANJI.len() { |
| handle.write_upper_bmp(JIS0208_LEVEL2_AND_ADDITIONAL_KANJI[level2_pointer]) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>upper_ibm_pointer = pointer.wrapping_sub(<span class="number">10744</span>); |
| <span class="kw">if </span>upper_ibm_pointer < IBM_KANJI.len() { |
| handle.write_upper_bmp(IBM_KANJI[upper_ibm_pointer]) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>lower_ibm_pointer = pointer.wrapping_sub(<span class="number">8272</span>); |
| <span class="kw">if </span>lower_ibm_pointer < IBM_KANJI.len() { |
| handle.write_upper_bmp(IBM_KANJI[lower_ibm_pointer]) |
| } <span class="kw">else if </span>in_inclusive_range(pointer, <span class="number">8836</span>, <span class="number">10715</span>) { |
| handle.write_upper_bmp((<span class="number">0xE000 </span>- <span class="number">8836 </span>+ pointer) <span class="kw">as </span>u16) |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(bmp) = jis0208_symbol_decode(pointer) { |
| handle.write_bmp_excl_ascii(bmp) |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(bmp) = jis0208_range_decode(pointer) { |
| handle.write_bmp_excl_ascii(bmp) |
| } <span class="kw">else </span>{ |
| <span class="kw">if </span>byte < <span class="number">0x80 </span>{ |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">0</span>), |
| unread_handle_trail.unread(), |
| handle.written()); |
| } |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">2</span>, <span class="number">0</span>), |
| unread_handle_trail.consumed(), |
| handle.written()); |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| <span class="self">self</span>, |
| non_ascii, |
| byte, |
| lead_minus_offset, |
| unread_handle_trail, |
| source, |
| handle, |
| <span class="lifetime">'outermost</span>, |
| copy_ascii_from_check_space_bmp, |
| check_space_bmp, |
| <span class="bool-val">false</span>); |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"fast-kanji-encode"</span>)] |
| #[inline(always)] |
| </span><span class="kw">fn </span>encode_kanji(bmp: u16) -> <span class="prelude-ty">Option</span><(u8, u8)> { |
| jis0208_kanji_shift_jis_encode(bmp) |
| } |
| |
| <span class="attribute">#[cfg(not(feature = <span class="string">"fast-kanji-encode"</span>))] |
| #[inline(always)] |
| </span><span class="kw">fn </span>encode_kanji(bmp: u16) -> <span class="prelude-ty">Option</span><(u8, u8)> { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>((lead, trail)) = jis0208_level1_kanji_shift_jis_encode(bmp) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((lead, trail)); |
| } |
| <span class="kw">let </span>pointer = <span class="kw">if </span><span class="number">0x4EDD </span>== bmp { |
| <span class="comment">// Ideograph on the symbol row! |
| </span><span class="number">23 |
| </span>} <span class="kw">else if let </span><span class="prelude-val">Some</span>(pos) = jis0208_level2_and_additional_kanji_encode(bmp) { |
| <span class="number">4418 </span>+ pos |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>IBM_KANJI[..], bmp) { |
| <span class="number">10744 </span>+ pos |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| }; |
| <span class="kw">let </span>lead = pointer / <span class="number">188</span>; |
| <span class="kw">let </span>lead_offset = <span class="kw">if </span>lead < <span class="number">0x1F </span>{ <span class="number">0x81usize </span>} <span class="kw">else </span>{ <span class="number">0xC1usize </span>}; |
| <span class="kw">let </span>trail = pointer % <span class="number">188</span>; |
| <span class="kw">let </span>trail_offset = <span class="kw">if </span>trail < <span class="number">0x3F </span>{ <span class="number">0x40usize </span>} <span class="kw">else </span>{ <span class="number">0x41usize </span>}; |
| <span class="prelude-val">Some</span>(((lead + lead_offset) <span class="kw">as </span>u8, (trail + trail_offset) <span class="kw">as </span>u8)) |
| } |
| |
| <span class="kw">pub struct </span>ShiftJisEncoder; |
| |
| <span class="kw">impl </span>ShiftJisEncoder { |
| <span class="kw">pub fn </span>new(encoding: <span class="kw-2">&</span><span class="lifetime">'static </span>Encoding) -> Encoder { |
| Encoder::new(encoding, VariantEncoder::ShiftJis(ShiftJisEncoder)) |
| } |
| |
| <span class="kw">pub fn </span>max_buffer_length_from_utf16_without_replacement( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| u16_length: usize, |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| u16_length.checked_mul(<span class="number">2</span>) |
| } |
| |
| <span class="kw">pub fn </span>max_buffer_length_from_utf8_without_replacement( |
| <span class="kw-2">&</span><span class="self">self</span>, |
| byte_length: usize, |
| ) -> <span class="prelude-ty">Option</span><usize> { |
| byte_length.checked_add(<span class="number">1</span>) |
| } |
| |
| <span class="macro">ascii_compatible_bmp_encoder_functions!</span>( |
| { |
| <span class="comment">// Lunde says 60% Hiragana, 30% Kanji, 10% Katakana |
| </span><span class="kw">let </span>bmp_minus_hiragana = bmp.wrapping_sub(<span class="number">0x3041</span>); |
| <span class="kw">if </span>bmp_minus_hiragana < <span class="number">0x53 </span>{ |
| handle.write_two(<span class="number">0x82</span>, <span class="number">0x9F </span>+ bmp_minus_hiragana <span class="kw">as </span>u8) |
| } <span class="kw">else if </span>in_inclusive_range16(bmp, <span class="number">0x4E00</span>, <span class="number">0x9FA0</span>) { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>((lead, trail)) = encode_kanji(bmp) { |
| handle.write_two(lead, trail) |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span>( |
| EncoderResult::unmappable_from_bmp(bmp), |
| source.consumed(), |
| handle.written(), |
| ); |
| } |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>bmp_minus_katakana = bmp.wrapping_sub(<span class="number">0x30A1</span>); |
| <span class="kw">if </span>bmp_minus_katakana < <span class="number">0x56 </span>{ |
| <span class="kw">let </span>trail_offset = <span class="kw">if </span>bmp_minus_katakana < <span class="number">0x3F </span>{ |
| <span class="number">0x40 |
| </span>} <span class="kw">else </span>{ |
| <span class="number">0x41 |
| </span>}; |
| handle.write_two(<span class="number">0x83</span>, (trail_offset + bmp_minus_katakana) <span class="kw">as </span>u8) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>bmp_minus_space = bmp.wrapping_sub(<span class="number">0x3000</span>); |
| <span class="kw">if </span>bmp_minus_space < <span class="number">3 </span>{ |
| <span class="comment">// fast-track common punctuation |
| </span>handle.write_two(<span class="number">0x81</span>, <span class="number">0x40 </span>+ bmp_minus_space <span class="kw">as </span>u8) |
| } <span class="kw">else if </span>bmp == <span class="number">0xA5 </span>{ |
| handle.write_one(<span class="number">0x5Cu8</span>) |
| } <span class="kw">else if </span>bmp == <span class="number">0x80 </span>{ |
| handle.write_one(<span class="number">0x80u8</span>) |
| } <span class="kw">else if </span>bmp == <span class="number">0x203E </span>{ |
| handle.write_one(<span class="number">0x7Eu8</span>) |
| } <span class="kw">else if </span>in_inclusive_range16(bmp, <span class="number">0xFF61</span>, <span class="number">0xFF9F</span>) { |
| handle.write_one((bmp - (<span class="number">0xFF61 </span>- <span class="number">0xA1</span>)) <span class="kw">as </span>u8) |
| } <span class="kw">else if </span>bmp == <span class="number">0x2212 </span>{ |
| handle.write_two(<span class="number">0x81u8</span>, <span class="number">0x7Cu8</span>) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>bmp_minus_roman = bmp.wrapping_sub(<span class="number">0x2170</span>); |
| <span class="kw">let </span>pointer = <span class="kw">if </span>bmp_minus_roman <= (<span class="number">0x2179 </span>- <span class="number">0x2170</span>) { |
| <span class="number">10716 </span>+ bmp_minus_roman <span class="kw">as </span>usize |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(pointer) = jis0208_range_encode(bmp) { |
| pointer |
| } <span class="kw">else if </span>in_inclusive_range16(bmp, <span class="number">0xFA0E</span>, <span class="number">0xFA2D</span>) |
| || bmp == <span class="number">0xF929 |
| </span>|| bmp == <span class="number">0xF9DC |
| </span>{ |
| <span class="comment">// Guaranteed to be found in IBM_KANJI |
| </span><span class="kw">let </span>pos = position(<span class="kw-2">&</span>IBM_KANJI[..], bmp).unwrap(); |
| <span class="number">10744 </span>+ pos |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(pointer) = jis0208_symbol_encode(bmp) { |
| pointer |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span>( |
| EncoderResult::unmappable_from_bmp(bmp), |
| source.consumed(), |
| handle.written(), |
| ); |
| }; |
| <span class="kw">let </span>lead = pointer / <span class="number">188</span>; |
| <span class="kw">let </span>lead_offset = <span class="kw">if </span>lead < <span class="number">0x1F </span>{ <span class="number">0x81usize </span>} <span class="kw">else </span>{ <span class="number">0xC1usize </span>}; |
| <span class="kw">let </span>trail = pointer % <span class="number">188</span>; |
| <span class="kw">let </span>trail_offset = <span class="kw">if </span>trail < <span class="number">0x3F </span>{ <span class="number">0x40usize </span>} <span class="kw">else </span>{ <span class="number">0x41usize </span>}; |
| handle.write_two((lead + lead_offset) <span class="kw">as </span>u8, (trail + trail_offset) <span class="kw">as </span>u8) |
| } |
| } |
| } |
| }, |
| bmp, |
| <span class="self">self</span>, |
| source, |
| handle, |
| copy_ascii_to_check_space_two, |
| check_space_two, |
| <span class="bool-val">false |
| </span>); |
| } |
| |
| <span class="comment">// Any copyright to the test code below this comment is dedicated to the |
| // Public Domain. http://creativecommons.org/publicdomain/zero/1.0/ |
| |
| </span><span class="attribute">#[cfg(all(test, feature = <span class="string">"alloc"</span>))] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span><span class="kw">super</span>::<span class="kw">super</span>::testing::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">super</span>::<span class="kw">super</span>::<span class="kw-2">*</span>; |
| |
| <span class="kw">fn </span>decode_shift_jis(bytes: <span class="kw-2">&</span>[u8], expect: <span class="kw-2">&</span>str) { |
| decode(SHIFT_JIS, bytes, expect); |
| } |
| |
| <span class="kw">fn </span>encode_shift_jis(string: <span class="kw-2">&</span>str, expect: <span class="kw-2">&</span>[u8]) { |
| encode(SHIFT_JIS, string, expect); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_shift_jis_decode() { |
| <span class="comment">// Empty |
| </span>decode_shift_jis(<span class="string">b""</span>, <span class="kw-2">&</span><span class="string">""</span>); |
| |
| <span class="comment">// ASCII |
| </span>decode_shift_jis(<span class="string">b"\x61\x62"</span>, <span class="string">"\u{0061}\u{0062}"</span>); |
| |
| <span class="comment">// Half-width |
| </span>decode_shift_jis(<span class="string">b"\xA1"</span>, <span class="string">"\u{FF61}"</span>); |
| decode_shift_jis(<span class="string">b"\xDF"</span>, <span class="string">"\u{FF9F}"</span>); |
| decode_shift_jis(<span class="string">b"\xA0"</span>, <span class="string">"\u{FFFD}"</span>); |
| decode_shift_jis(<span class="string">b"\xE0"</span>, <span class="string">"\u{FFFD}"</span>); |
| decode_shift_jis(<span class="string">b"\xA0+"</span>, <span class="string">"\u{FFFD}+"</span>); |
| decode_shift_jis(<span class="string">b"\xE0+"</span>, <span class="string">"\u{FFFD}+"</span>); |
| |
| <span class="comment">// EUDC |
| </span>decode_shift_jis(<span class="string">b"\xF0\x40"</span>, <span class="string">"\u{E000}"</span>); |
| decode_shift_jis(<span class="string">b"\xF9\xFC"</span>, <span class="string">"\u{E757}"</span>); |
| decode_shift_jis(<span class="string">b"\xEF\xFC"</span>, <span class="string">"\u{FFFD}"</span>); |
| decode_shift_jis(<span class="string">b"\xFA\x40"</span>, <span class="string">"\u{2170}"</span>); |
| |
| <span class="comment">// JIS 0208 |
| </span>decode_shift_jis(<span class="string">b"\x81\x40"</span>, <span class="string">"\u{3000}"</span>); |
| decode_shift_jis(<span class="string">b"\x81\x3F"</span>, <span class="string">"\u{FFFD}?"</span>); |
| decode_shift_jis(<span class="string">b"\xEE\xFC"</span>, <span class="string">"\u{FF02}"</span>); |
| decode_shift_jis(<span class="string">b"\xEE\xFD"</span>, <span class="string">"\u{FFFD}"</span>); |
| decode_shift_jis(<span class="string">b"\xFA\x40"</span>, <span class="string">"\u{2170}"</span>); |
| decode_shift_jis(<span class="string">b"\xFA\x3F"</span>, <span class="string">"\u{FFFD}?"</span>); |
| decode_shift_jis(<span class="string">b"\xFC\x4B"</span>, <span class="string">"\u{9ED1}"</span>); |
| decode_shift_jis(<span class="string">b"\xFC\x4C"</span>, <span class="string">"\u{FFFD}L"</span>); |
| <span class="comment">// |
| </span>} |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_shift_jis_encode() { |
| <span class="comment">// Empty |
| </span>encode_shift_jis(<span class="string">""</span>, <span class="string">b""</span>); |
| |
| <span class="comment">// ASCII |
| </span>encode_shift_jis(<span class="string">"\u{0061}\u{0062}"</span>, <span class="string">b"\x61\x62"</span>); |
| |
| <span class="comment">// Exceptional code points |
| </span>encode_shift_jis(<span class="string">"\u{0080}"</span>, <span class="string">b"\x80"</span>); |
| encode_shift_jis(<span class="string">"\u{00A5}"</span>, <span class="string">b"\x5C"</span>); |
| encode_shift_jis(<span class="string">"\u{203E}"</span>, <span class="string">b"\x7E"</span>); |
| encode_shift_jis(<span class="string">"\u{2212}"</span>, <span class="string">b"\x81\x7C"</span>); |
| |
| <span class="comment">// Half-width |
| </span>encode_shift_jis(<span class="string">"\u{FF61}"</span>, <span class="string">b"\xA1"</span>); |
| encode_shift_jis(<span class="string">"\u{FF9F}"</span>, <span class="string">b"\xDF"</span>); |
| |
| <span class="comment">// EUDC |
| </span>encode_shift_jis(<span class="string">"\u{E000}"</span>, <span class="string">b"&#57344;"</span>); |
| encode_shift_jis(<span class="string">"\u{E757}"</span>, <span class="string">b"&#59223;"</span>); |
| |
| <span class="comment">// JIS 0212 |
| </span>encode_shift_jis(<span class="string">"\u{02D8}"</span>, <span class="string">b"&#728;"</span>); |
| |
| <span class="comment">// JIS 0208 |
| </span>encode_shift_jis(<span class="string">"\u{3000}"</span>, <span class="string">b"\x81\x40"</span>); |
| encode_shift_jis(<span class="string">"\u{FF02}"</span>, <span class="string">b"\xFA\x57"</span>); |
| encode_shift_jis(<span class="string">"\u{2170}"</span>, <span class="string">b"\xFA\x40"</span>); |
| encode_shift_jis(<span class="string">"\u{9ED1}"</span>, <span class="string">b"\xFC\x4B"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg_attr(miri, ignore)] </span><span class="comment">// Miri is too slow |
| </span><span class="kw">fn </span>test_shift_jis_decode_all() { |
| <span class="kw">let </span>input = <span class="macro">include_bytes!</span>(<span class="string">"test_data/shift_jis_in.txt"</span>); |
| <span class="kw">let </span>expectation = <span class="macro">include_str!</span>(<span class="string">"test_data/shift_jis_in_ref.txt"</span>); |
| <span class="kw">let </span>(cow, had_errors) = SHIFT_JIS.decode_without_bom_handling(input); |
| <span class="macro">assert!</span>(had_errors, <span class="string">"Should have had errors."</span>); |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>cow[..], expectation); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg_attr(miri, ignore)] </span><span class="comment">// Miri is too slow |
| </span><span class="kw">fn </span>test_shift_jis_encode_all() { |
| <span class="kw">let </span>input = <span class="macro">include_str!</span>(<span class="string">"test_data/shift_jis_out.txt"</span>); |
| <span class="kw">let </span>expectation = <span class="macro">include_bytes!</span>(<span class="string">"test_data/shift_jis_out_ref.txt"</span>); |
| <span class="kw">let </span>(cow, encoding, had_errors) = SHIFT_JIS.encode(input); |
| <span class="macro">assert!</span>(!had_errors, <span class="string">"Should not have had errors."</span>); |
| <span class="macro">assert_eq!</span>(encoding, SHIFT_JIS); |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>cow[..], <span class="kw-2">&</span>expectation[..]); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_shift_jis_half_width_katakana_length() { |
| <span class="kw">let </span><span class="kw-2">mut </span>output = [<span class="number">0u8</span>; <span class="number">20</span>]; |
| <span class="kw">let </span><span class="kw-2">mut </span>decoder = SHIFT_JIS.new_decoder(); |
| { |
| <span class="kw">let </span>needed = decoder |
| .max_utf8_buffer_length_without_replacement(<span class="number">1</span>) |
| .unwrap(); |
| <span class="kw">let </span>(result, read, written) = |
| decoder.decode_to_utf8_without_replacement(<span class="string">b"\xA1"</span>, <span class="kw-2">&mut </span>output[..needed], <span class="bool-val">true</span>); |
| <span class="macro">assert_eq!</span>(result, DecoderResult::InputEmpty); |
| <span class="macro">assert_eq!</span>(read, <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(written, <span class="number">3</span>); |
| <span class="macro">assert_eq!</span>(output[<span class="number">0</span>], <span class="number">0xEF</span>); |
| <span class="macro">assert_eq!</span>(output[<span class="number">1</span>], <span class="number">0xBD</span>); |
| <span class="macro">assert_eq!</span>(output[<span class="number">2</span>], <span class="number">0xA1</span>); |
| } |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="encoding_rs" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |