| <!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/gb18030.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>gb18030.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> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| <span id="568">568</span> |
| <span id="569">569</span> |
| <span id="570">570</span> |
| <span id="571">571</span> |
| <span id="572">572</span> |
| <span id="573">573</span> |
| <span id="574">574</span> |
| <span id="575">575</span> |
| <span id="576">576</span> |
| <span id="577">577</span> |
| <span id="578">578</span> |
| <span id="579">579</span> |
| <span id="580">580</span> |
| <span id="581">581</span> |
| <span id="582">582</span> |
| <span id="583">583</span> |
| <span id="584">584</span> |
| <span id="585">585</span> |
| <span id="586">586</span> |
| <span id="587">587</span> |
| <span id="588">588</span> |
| <span id="589">589</span> |
| <span id="590">590</span> |
| <span id="591">591</span> |
| <span id="592">592</span> |
| <span id="593">593</span> |
| <span id="594">594</span> |
| <span id="595">595</span> |
| <span id="596">596</span> |
| <span id="597">597</span> |
| <span id="598">598</span> |
| <span id="599">599</span> |
| <span id="600">600</span> |
| <span id="601">601</span> |
| <span id="602">602</span> |
| <span id="603">603</span> |
| <span id="604">604</span> |
| <span id="605">605</span> |
| <span id="606">606</span> |
| <span id="607">607</span> |
| <span id="608">608</span> |
| <span id="609">609</span> |
| <span id="610">610</span> |
| <span id="611">611</span> |
| <span id="612">612</span> |
| <span id="613">613</span> |
| <span id="614">614</span> |
| <span id="615">615</span> |
| <span id="616">616</span> |
| <span id="617">617</span> |
| <span id="618">618</span> |
| <span id="619">619</span> |
| <span id="620">620</span> |
| <span id="621">621</span> |
| <span id="622">622</span> |
| <span id="623">623</span> |
| <span id="624">624</span> |
| <span id="625">625</span> |
| <span id="626">626</span> |
| <span id="627">627</span> |
| <span id="628">628</span> |
| <span id="629">629</span> |
| <span id="630">630</span> |
| <span id="631">631</span> |
| <span id="632">632</span> |
| <span id="633">633</span> |
| <span id="634">634</span> |
| <span id="635">635</span> |
| <span id="636">636</span> |
| <span id="637">637</span> |
| <span id="638">638</span> |
| <span id="639">639</span> |
| <span id="640">640</span> |
| <span id="641">641</span> |
| <span id="642">642</span> |
| <span id="643">643</span> |
| <span id="644">644</span> |
| <span id="645">645</span> |
| <span id="646">646</span> |
| <span id="647">647</span> |
| <span id="648">648</span> |
| <span id="649">649</span> |
| <span id="650">650</span> |
| <span id="651">651</span> |
| <span id="652">652</span> |
| <span id="653">653</span> |
| <span id="654">654</span> |
| <span id="655">655</span> |
| <span id="656">656</span> |
| <span id="657">657</span> |
| <span id="658">658</span> |
| <span id="659">659</span> |
| <span id="660">660</span> |
| <span id="661">661</span> |
| <span id="662">662</span> |
| <span id="663">663</span> |
| <span id="664">664</span> |
| <span id="665">665</span> |
| <span id="666">666</span> |
| <span id="667">667</span> |
| <span id="668">668</span> |
| <span id="669">669</span> |
| <span id="670">670</span> |
| <span id="671">671</span> |
| <span id="672">672</span> |
| <span id="673">673</span> |
| <span id="674">674</span> |
| <span id="675">675</span> |
| <span id="676">676</span> |
| <span id="677">677</span> |
| <span id="678">678</span> |
| <span id="679">679</span> |
| <span id="680">680</span> |
| <span id="681">681</span> |
| <span id="682">682</span> |
| <span id="683">683</span> |
| <span id="684">684</span> |
| <span id="685">685</span> |
| <span id="686">686</span> |
| <span id="687">687</span> |
| <span id="688">688</span> |
| <span id="689">689</span> |
| <span id="690">690</span> |
| <span id="691">691</span> |
| <span id="692">692</span> |
| <span id="693">693</span> |
| <span id="694">694</span> |
| <span id="695">695</span> |
| <span id="696">696</span> |
| <span id="697">697</span> |
| <span id="698">698</span> |
| <span id="699">699</span> |
| <span id="700">700</span> |
| <span id="701">701</span> |
| <span id="702">702</span> |
| <span id="703">703</span> |
| <span id="704">704</span> |
| <span id="705">705</span> |
| <span id="706">706</span> |
| <span id="707">707</span> |
| <span id="708">708</span> |
| <span id="709">709</span> |
| <span id="710">710</span> |
| <span id="711">711</span> |
| <span id="712">712</span> |
| <span id="713">713</span> |
| <span id="714">714</span> |
| <span id="715">715</span> |
| <span id="716">716</span> |
| <span id="717">717</span> |
| <span id="718">718</span> |
| <span id="719">719</span> |
| <span id="720">720</span> |
| <span id="721">721</span> |
| <span id="722">722</span> |
| <span id="723">723</span> |
| <span id="724">724</span> |
| <span id="725">725</span> |
| <span id="726">726</span> |
| <span id="727">727</span> |
| <span id="728">728</span> |
| <span id="729">729</span> |
| <span id="730">730</span> |
| <span id="731">731</span> |
| <span id="732">732</span> |
| <span id="733">733</span> |
| <span id="734">734</span> |
| <span id="735">735</span> |
| <span id="736">736</span> |
| <span id="737">737</span> |
| <span id="738">738</span> |
| <span id="739">739</span> |
| <span id="740">740</span> |
| <span id="741">741</span> |
| <span id="742">742</span> |
| <span id="743">743</span> |
| <span id="744">744</span> |
| <span id="745">745</span> |
| <span id="746">746</span> |
| <span id="747">747</span> |
| <span id="748">748</span> |
| <span id="749">749</span> |
| <span id="750">750</span> |
| <span id="751">751</span> |
| <span id="752">752</span> |
| <span id="753">753</span> |
| <span id="754">754</span> |
| <span id="755">755</span> |
| <span id="756">756</span> |
| <span id="757">757</span> |
| <span id="758">758</span> |
| <span id="759">759</span> |
| <span id="760">760</span> |
| <span id="761">761</span> |
| <span id="762">762</span> |
| <span id="763">763</span> |
| <span id="764">764</span> |
| <span id="765">765</span> |
| <span id="766">766</span> |
| <span id="767">767</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_range16; |
| <span class="kw">use </span><span class="kw">super</span>::in_range16; |
| |
| <span class="kw">enum </span>Gb18030Pending { |
| <span class="prelude-val">None</span>, |
| One(u8), |
| Two(u8, u8), |
| Three(u8, u8, u8), |
| } |
| |
| <span class="kw">impl </span>Gb18030Pending { |
| <span class="kw">fn </span>is_none(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Gb18030Pending::None => <span class="bool-val">true</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>count(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Gb18030Pending::None => <span class="number">0</span>, |
| Gb18030Pending::One(<span class="kw">_</span>) => <span class="number">1</span>, |
| Gb18030Pending::Two(<span class="kw">_</span>, <span class="kw">_</span>) => <span class="number">2</span>, |
| Gb18030Pending::Three(<span class="kw">_</span>, <span class="kw">_</span>, <span class="kw">_</span>) => <span class="number">3</span>, |
| } |
| } |
| } |
| |
| <span class="kw">pub struct </span>Gb18030Decoder { |
| first: <span class="prelude-ty">Option</span><u8>, |
| second: <span class="prelude-ty">Option</span><u8>, |
| third: <span class="prelude-ty">Option</span><u8>, |
| pending: Gb18030Pending, |
| pending_ascii: <span class="prelude-ty">Option</span><u8>, |
| } |
| |
| <span class="kw">impl </span>Gb18030Decoder { |
| <span class="kw">pub fn </span>new() -> VariantDecoder { |
| VariantDecoder::Gb18030(Gb18030Decoder { |
| first: <span class="prelude-val">None</span>, |
| second: <span class="prelude-val">None</span>, |
| third: <span class="prelude-val">None</span>, |
| pending: Gb18030Pending::None, |
| pending_ascii: <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>.first.is_none() |
| && <span class="self">self</span>.second.is_none() |
| && <span class="self">self</span>.third.is_none() |
| && <span class="self">self</span>.pending.is_none() |
| && <span class="self">self</span>.pending_ascii.is_none() |
| } |
| |
| <span class="kw">fn </span>extra_from_state(<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="self">self</span>.pending.count() |
| + <span class="kw">match </span><span class="self">self</span>.first { |
| <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">match </span><span class="self">self</span>.second { |
| <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">match </span><span class="self">self</span>.third { |
| <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">match </span><span class="self">self</span>.pending_ascii { |
| <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="comment">// ASCII: 1 to 1 (worst case) |
| // gbk: 2 to 1 |
| // ranges: 4 to 1 or 4 to 2 |
| </span>checked_add(<span class="number">1</span>, <span class="self">self</span>.extra_from_state(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">// ASCII: 1 to 1 |
| // gbk: 2 to 2 or 2 to 3 |
| // ranges: 4 to 2, 4 to 3 or 4 to 4 |
| // 0x80: 1 to 3 (worst case) |
| </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_add(<span class="number">1</span>, checked_mul(<span class="number">3</span>, <span class="self">self</span>.extra_from_state(byte_length))) |
| } |
| |
| <span class="macro">gb18030_decoder_functions!</span>( |
| { |
| <span class="comment">// If first is between 0x81 and 0xFE, inclusive, |
| // subtract offset 0x81. |
| </span><span class="kw">let </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">0xFE </span>- <span class="number">0x81</span>) { |
| <span class="kw">if </span>non_ascii == <span class="number">0x80 </span>{ |
| handle.write_upper_bmp(<span class="number">0x20ACu16</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()); |
| } |
| non_ascii_minus_offset |
| }, |
| { |
| <span class="comment">// Two-byte (or error) |
| </span><span class="kw">if </span>first_minus_offset >= <span class="number">0x20 </span>{ |
| <span class="comment">// Not the gbk ideograph range above GB2312 |
| </span><span class="kw">let </span>trail_minus_offset = second.wrapping_sub(<span class="number">0xA1</span>); |
| <span class="kw">if </span>trail_minus_offset <= (<span class="number">0xFE </span>- <span class="number">0xA1</span>) { |
| <span class="comment">// GB2312 |
| </span><span class="kw">let </span>hanzi_lead = first_minus_offset.wrapping_sub(<span class="number">0x2F</span>); |
| <span class="kw">if </span>hanzi_lead < (<span class="number">0x77 </span>- <span class="number">0x2F</span>) { |
| <span class="comment">// Level 1 Hanzi, Level 2 Hanzi |
| // or one of the 5 PUA code |
| // points in between. |
| </span><span class="kw">let </span>hanzi_pointer = mul_94(hanzi_lead) + trail_minus_offset <span class="kw">as </span>usize; |
| <span class="kw">let </span>upper_bmp = GB2312_HANZI[hanzi_pointer]; |
| handle.write_upper_bmp(upper_bmp) |
| } <span class="kw">else if </span>first_minus_offset == <span class="number">0x20 </span>{ |
| <span class="comment">// Symbols (starting with ideographic space) |
| </span><span class="kw">let </span>bmp = GB2312_SYMBOLS[trail_minus_offset <span class="kw">as </span>usize]; |
| handle.write_bmp_excl_ascii(bmp) |
| } <span class="kw">else if </span>first_minus_offset == <span class="number">0x25 </span>&& ((trail_minus_offset.wrapping_sub(<span class="number">63</span>) <span class="kw">as </span>usize) < GB2312_SYMBOLS_AFTER_GREEK.len()) { |
| handle.write_bmp_excl_ascii(GB2312_SYMBOLS_AFTER_GREEK[trail_minus_offset.wrapping_sub(<span class="number">63</span>) <span class="kw">as </span>usize]) |
| } <span class="kw">else if </span>first_minus_offset == <span class="number">0x27 </span>&& (trail_minus_offset <span class="kw">as </span>usize) < GB2312_PINYIN.len() { |
| handle.write_bmp_excl_ascii(GB2312_PINYIN[trail_minus_offset <span class="kw">as </span>usize]) |
| } <span class="kw">else if </span>first_minus_offset > <span class="number">0x76 </span>{ |
| <span class="comment">// Bottom PUA |
| </span><span class="kw">let </span>pua = (<span class="number">0xE234 </span>+ mul_94(first_minus_offset - <span class="number">0x77</span>) + trail_minus_offset <span class="kw">as </span>usize) <span class="kw">as </span>u16; |
| handle.write_upper_bmp(pua) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>bmp = gb2312_other_decode((mul_94(first_minus_offset - <span class="number">0x21</span>) + (trail_minus_offset <span class="kw">as </span>usize)) <span class="kw">as </span>u16); |
| handle.write_bmp_excl_ascii(bmp) |
| } |
| } <span class="kw">else </span>{ |
| <span class="comment">// gbk range on the left |
| </span><span class="kw">let </span><span class="kw-2">mut </span>trail_minus_offset = second.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 = second.wrapping_sub(<span class="number">0x80</span>); |
| <span class="kw">if </span>trail_minus_range_start > (<span class="number">0xA0 </span>- <span class="number">0x80</span>) { |
| <span class="kw">if </span>second < <span class="number">0x80 </span>{ |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">0</span>), |
| unread_handle_second.unread(), |
| handle.written()); |
| } |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">2</span>, <span class="number">0</span>), |
| unread_handle_second.consumed(), |
| handle.written()); |
| } |
| trail_minus_offset = second - <span class="number">0x41</span>; |
| } |
| <span class="comment">// Zero-base lead |
| </span><span class="kw">let </span>left_lead = first_minus_offset - <span class="number">0x20</span>; |
| <span class="kw">let </span>left_pointer = left_lead <span class="kw">as </span>usize * (<span class="number">190 </span>- <span class="number">94</span>) + |
| trail_minus_offset <span class="kw">as </span>usize; |
| <span class="kw">let </span>gbk_left_ideograph_pointer = left_pointer.wrapping_sub((<span class="number">0x29 </span>- <span class="number">0x20</span>) * (<span class="number">190 </span>- <span class="number">94</span>)); |
| <span class="kw">if </span>gbk_left_ideograph_pointer < (((<span class="number">0x7D </span>- <span class="number">0x29</span>) * (<span class="number">190 </span>- <span class="number">94</span>)) - <span class="number">5</span>) { |
| <span class="kw">let </span>upper_bmp = gbk_left_ideograph_decode(gbk_left_ideograph_pointer <span class="kw">as </span>u16); |
| handle.write_upper_bmp(upper_bmp) |
| } <span class="kw">else if </span>left_pointer < ((<span class="number">0x29 </span>- <span class="number">0x20</span>) * (<span class="number">190 </span>- <span class="number">94</span>)) { |
| <span class="kw">let </span>bmp = gbk_other_decode(left_pointer <span class="kw">as </span>u16); |
| handle.write_bmp_excl_ascii(bmp) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>bottom_pointer = left_pointer - (((<span class="number">0x7D </span>- <span class="number">0x20</span>) * (<span class="number">190 </span>- <span class="number">94</span>)) - <span class="number">5</span>); |
| <span class="kw">let </span>upper_bmp = GBK_BOTTOM[bottom_pointer]; |
| handle.write_upper_bmp(upper_bmp) |
| } |
| } |
| } <span class="kw">else </span>{ |
| <span class="comment">// gbk ideograph range above GB2312 |
| </span><span class="kw">let </span><span class="kw-2">mut </span>trail_minus_offset = second.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 = second.wrapping_sub(<span class="number">0x80</span>); |
| <span class="kw">if </span>trail_minus_range_start > (<span class="number">0xFE </span>- <span class="number">0x80</span>) { |
| <span class="kw">if </span>second < <span class="number">0x80 </span>{ |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">0</span>), |
| unread_handle_second.unread(), |
| handle.written()); |
| } |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">2</span>, <span class="number">0</span>), |
| unread_handle_second.consumed(), |
| handle.written()); |
| } |
| trail_minus_offset = second - <span class="number">0x41</span>; |
| } |
| <span class="kw">let </span>pointer = first_minus_offset <span class="kw">as </span>usize * <span class="number">190usize </span>+ |
| trail_minus_offset <span class="kw">as </span>usize; |
| <span class="kw">let </span>upper_bmp = gbk_top_ideograph_decode(pointer <span class="kw">as </span>u16); |
| handle.write_upper_bmp(upper_bmp) |
| } |
| }, |
| { |
| <span class="comment">// If third is between 0x81 and 0xFE, inclusive, |
| // subtract offset 0x81. |
| </span><span class="kw">let </span>third_minus_offset = third.wrapping_sub(<span class="number">0x81</span>); |
| <span class="kw">if </span>third_minus_offset > (<span class="number">0xFE </span>- <span class="number">0x81</span>) { |
| <span class="comment">// We have an error. Let's inline what's going |
| // to happen when `second` is |
| // reprocessed. (`third` gets unread.) |
| // `second` is guaranteed ASCII, so let's |
| // put it in `pending_ascii`. Recompute |
| // `second` from `second_minus_offset`. |
| </span><span class="self">self</span>.pending_ascii = <span class="prelude-val">Some</span>(second_minus_offset + <span class="number">0x30</span>); |
| <span class="comment">// Now unread `third` and designate the previous |
| // `first` as being in error. |
| </span><span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">1</span>), |
| unread_handle_third.unread(), |
| handle.written()); |
| } |
| third_minus_offset |
| }, |
| { |
| <span class="comment">// If fourth is between 0x30 and 0x39, inclusive, |
| // subtract offset 0x30. |
| // |
| // If we have an error, we'll inline what's going |
| // to happen when `second` and `third` are |
| // reprocessed. (`fourth` gets unread.) |
| // `second` is guaranteed ASCII, so let's |
| // put it in `pending_ascii`. Recompute |
| // `second` from `second_minus_offset` to |
| // make this block reusable when `second` |
| // is not in scope. |
| // |
| // `third` is guaranteed to be in the range |
| // that makes it become the new `self.first`. |
| // |
| // `fourth` gets unread and the previous |
| // `first` gets designates as being in error. |
| </span><span class="kw">let </span>fourth_minus_offset = fourth.wrapping_sub(<span class="number">0x30</span>); |
| <span class="kw">if </span>fourth_minus_offset > (<span class="number">0x39 </span>- <span class="number">0x30</span>) { |
| <span class="self">self</span>.pending_ascii = <span class="prelude-val">Some</span>(second_minus_offset + <span class="number">0x30</span>); |
| <span class="self">self</span>.pending = Gb18030Pending::One(third_minus_offset); |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">1</span>, <span class="number">2</span>), |
| unread_handle_fourth.unread(), |
| handle.written()); |
| } |
| <span class="kw">let </span>pointer = (first_minus_offset <span class="kw">as </span>usize * (<span class="number">10 </span>* <span class="number">126 </span>* <span class="number">10</span>)) + |
| (second_minus_offset <span class="kw">as </span>usize * (<span class="number">10 </span>* <span class="number">126</span>)) + |
| (third_minus_offset <span class="kw">as </span>usize * <span class="number">10</span>) + |
| fourth_minus_offset <span class="kw">as </span>usize; |
| <span class="kw">if </span>pointer <= <span class="number">39419 </span>{ |
| <span class="comment">// BMP |
| </span><span class="kw">if </span>pointer == <span class="number">7457 </span>{ |
| handle.write_upper_bmp(<span class="number">0xE7C7</span>) |
| } <span class="kw">else </span>{ |
| handle.write_bmp_excl_ascii(gb18030_range_decode(pointer <span class="kw">as </span>u16)) |
| } |
| } <span class="kw">else if </span>pointer >= <span class="number">189_000 </span>&& pointer <= <span class="number">1_237_575 </span>{ |
| <span class="comment">// Astral |
| </span>handle.write_astral((pointer - (<span class="number">189_000usize </span>- <span class="number">0x1_0000usize</span>)) <span class="kw">as </span>u32) |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span>(DecoderResult::Malformed(<span class="number">4</span>, <span class="number">0</span>), |
| unread_handle_fourth.consumed(), |
| handle.written()); |
| } |
| }, |
| <span class="self">self</span>, |
| non_ascii, |
| first_minus_offset, |
| second, |
| second_minus_offset, |
| unread_handle_second, |
| third, |
| third_minus_offset, |
| unread_handle_third, |
| fourth, |
| fourth_minus_offset, |
| unread_handle_fourth, |
| source, |
| handle, |
| <span class="lifetime">'outermost</span>); |
| } |
| |
| <span class="comment">// XXX Experiment with inline directives |
| </span><span class="kw">fn </span>gbk_encode_non_unified(bmp: u16) -> <span class="prelude-ty">Option</span><(usize, usize)> { |
| <span class="comment">// Try ideographic punctuation first as it's the most likely case. |
| // Throwing in the check for full-width currencies and tilde is probably |
| // more size-efficient here than elsewhere. |
| </span><span class="kw">if </span>in_inclusive_range16(bmp, <span class="number">0x2014</span>, <span class="number">0x3017</span>) || in_inclusive_range16(bmp, <span class="number">0xFF04</span>, <span class="number">0xFFE1</span>) { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>GB2312_SYMBOLS[..], bmp) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA1</span>, pos + <span class="number">0xA1</span>)); |
| } |
| } |
| <span class="comment">// Ext A |
| </span><span class="kw">if </span>in_range16(bmp, <span class="number">0x3400</span>, <span class="number">0x4E00</span>) { |
| <span class="kw">return </span>position(<span class="kw-2">&</span>GBK_BOTTOM[<span class="number">21</span>..<span class="number">100</span>], bmp).map(|pos| { |
| ( |
| <span class="number">0xFE</span>, |
| pos + <span class="kw">if </span>pos < (<span class="number">0x3F </span>- <span class="number">16</span>) { |
| <span class="number">0x40 </span>+ <span class="number">16 |
| </span>} <span class="kw">else </span>{ |
| <span class="number">0x41 </span>+ <span class="number">16 |
| </span>}, |
| ) |
| }); |
| } |
| <span class="comment">// Compatibility ideographs |
| </span><span class="kw">if </span>in_range16(bmp, <span class="number">0xF900</span>, <span class="number">0xFB00</span>) { |
| <span class="kw">return </span>position(<span class="kw-2">&</span>GBK_BOTTOM[<span class="number">0</span>..<span class="number">21</span>], bmp).map(|pos| { |
| <span class="kw">if </span>pos < <span class="number">5 </span>{ |
| <span class="comment">// end of second to last row |
| </span>(<span class="number">0xFD</span>, pos + (<span class="number">190 </span>- <span class="number">94 </span>- <span class="number">5 </span>+ <span class="number">0x41</span>)) |
| } <span class="kw">else </span>{ |
| <span class="comment">// last row |
| </span>(<span class="number">0xFE</span>, pos + (<span class="number">0x40 </span>- <span class="number">5</span>)) |
| } |
| }); |
| } |
| <span class="comment">// Handle everything below U+02CA, which is in GBK_OTHER. |
| </span><span class="kw">if </span>bmp < <span class="number">0x02CA </span>{ |
| <span class="kw">if </span>in_range16(bmp, <span class="number">0x00E0</span>, <span class="number">0x0262</span>) && bmp != <span class="number">0x00F7 </span>{ |
| <span class="comment">// Pinyin except U+1E3F |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>GB2312_PINYIN[..], bmp) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA8</span>, pos + <span class="number">0xA1</span>)); |
| } |
| } <span class="kw">else if </span>in_inclusive_range16(bmp, <span class="number">0x00A4</span>, <span class="number">0x00F7</span>) |
| || in_inclusive_range16(bmp, <span class="number">0x02C7</span>, <span class="number">0x02C9</span>) |
| { |
| <span class="comment">// Diacritics and Latin 1 symbols |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>GB2312_SYMBOLS[<span class="number">3</span>..(<span class="number">0xAC </span>- <span class="number">0x60</span>)], bmp) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA1</span>, pos + <span class="number">0xA1 </span>+ <span class="number">3</span>)); |
| } |
| } |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">if </span>bmp >= <span class="number">0xE794 </span>{ |
| <span class="comment">// Various brackets, all in PUA or full-width regions |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>GB2312_SYMBOLS_AFTER_GREEK[..], bmp) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA6</span>, pos + (<span class="number">0x9F </span>- <span class="number">0x60 </span>+ <span class="number">0xA1</span>))); |
| } |
| } <span class="kw">else if </span>bmp == <span class="number">0x1E3F </span>{ |
| <span class="comment">// The one Pinyin placed elsewhere on the BMP |
| </span><span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA8</span>, <span class="number">0x7B </span>- <span class="number">0x60 </span>+ <span class="number">0xA1</span>)); |
| } <span class="kw">else if </span>in_range16(bmp, <span class="number">0xA000</span>, <span class="number">0xD800</span>) { |
| <span class="comment">// Since Korean has usage in China, let's spend a branch to fast-track |
| // Hangul. |
| </span><span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="comment">// GB2312 other (except bottom PUA and PUA between Hanzi levels). |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(other_pointer) = gb2312_other_encode(bmp) { |
| <span class="kw">let </span>other_lead = other_pointer <span class="kw">as </span>usize / <span class="number">94</span>; |
| <span class="kw">let </span>other_trail = other_pointer <span class="kw">as </span>usize % <span class="number">94</span>; |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xA2 </span>+ other_lead, <span class="number">0xA1 </span>+ other_trail)); |
| } |
| <span class="comment">// At this point, we've handled all mappable characters above U+02D9 but |
| // below U+2010. Let's check for that range in order to let lower BMP |
| // characters used for minority languages in China avoid the subsequent |
| // search that deals mainly with various symbols. |
| </span><span class="kw">if </span>in_range16(bmp, <span class="number">0x02DA</span>, <span class="number">0x2010</span>) { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="comment">// GBK other (except radicals and PUA in GBK_BOTTOM). |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(other_pointer) = gbk_other_encode(bmp) { |
| <span class="kw">let </span>other_lead = other_pointer <span class="kw">as </span>usize / (<span class="number">190 </span>- <span class="number">94</span>); |
| <span class="kw">let </span>other_trail = other_pointer <span class="kw">as </span>usize % (<span class="number">190 </span>- <span class="number">94</span>); |
| <span class="kw">let </span>offset = <span class="kw">if </span>other_trail < <span class="number">0x3F </span>{ <span class="number">0x40 </span>} <span class="kw">else </span>{ <span class="number">0x41 </span>}; |
| <span class="kw">return </span><span class="prelude-val">Some</span>((other_lead + (<span class="number">0x81 </span>+ <span class="number">0x20</span>), other_trail + offset)); |
| } |
| <span class="comment">// CJK Radicals Supplement or PUA in GBK_BOTTOM |
| </span><span class="kw">if </span>in_inclusive_range16(bmp, <span class="number">0x2E81</span>, <span class="number">0x2ECA</span>) || in_inclusive_range16(bmp, <span class="number">0xE816</span>, <span class="number">0xE864</span>) { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(pos) = position(<span class="kw-2">&</span>GBK_BOTTOM[<span class="number">21</span>..], bmp) { |
| <span class="kw">let </span>trail = pos + <span class="number">16</span>; |
| <span class="kw">let </span>offset = <span class="kw">if </span>trail < <span class="number">0x3F </span>{ <span class="number">0x40 </span>} <span class="kw">else </span>{ <span class="number">0x41 </span>}; |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0xFE</span>, trail + offset)); |
| } |
| } |
| <span class="comment">// GB2312 bottom PUA |
| </span><span class="kw">let </span>bmp_minus_gb2312_bottom_pua = bmp.wrapping_sub(<span class="number">0xE234</span>); |
| <span class="kw">if </span>bmp_minus_gb2312_bottom_pua <= (<span class="number">0xE4C5 </span>- <span class="number">0xE234</span>) { |
| <span class="kw">let </span>pua_lead = bmp_minus_gb2312_bottom_pua <span class="kw">as </span>usize / <span class="number">94</span>; |
| <span class="kw">let </span>pua_trail = bmp_minus_gb2312_bottom_pua <span class="kw">as </span>usize % <span class="number">94</span>; |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0x81 </span>+ <span class="number">0x77 </span>+ pua_lead, <span class="number">0xA1 </span>+ pua_trail)); |
| } |
| <span class="comment">// PUA between Hanzi Levels |
| </span><span class="kw">let </span>bmp_minus_pua_between_hanzi = bmp.wrapping_sub(<span class="number">0xE810</span>); |
| <span class="kw">if </span>bmp_minus_pua_between_hanzi < <span class="number">5 </span>{ |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="number">0x81 </span>+ <span class="number">0x56</span>, <span class="number">0xFF </span>- <span class="number">5 </span>+ bmp_minus_pua_between_hanzi <span class="kw">as </span>usize)); |
| } |
| <span class="prelude-val">None |
| </span>} |
| |
| <span class="attribute">#[cfg(not(feature = <span class="string">"fast-gb-hanzi-encode"</span>))] |
| #[inline(always)] |
| </span><span class="kw">fn </span>encode_hanzi(bmp: u16, <span class="kw">_</span>: u16) -> (u8, u8) { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>((lead, trail)) = gb2312_level1_hanzi_encode(bmp) { |
| (lead, trail) |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(hanzi_pointer) = gb2312_level2_hanzi_encode(bmp) { |
| <span class="kw">let </span>hanzi_lead = (hanzi_pointer / <span class="number">94</span>) + (<span class="number">0xD8</span>); |
| <span class="kw">let </span>hanzi_trail = (hanzi_pointer % <span class="number">94</span>) + <span class="number">0xA1</span>; |
| (hanzi_lead <span class="kw">as </span>u8, hanzi_trail <span class="kw">as </span>u8) |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>(lead, gbk_trail) = <span class="kw">if </span>bmp < <span class="number">0x72DC </span>{ |
| <span class="comment">// Above GB2312 |
| </span><span class="kw">let </span>pointer = gbk_top_ideograph_encode(bmp) <span class="kw">as </span>usize; |
| <span class="kw">let </span>lead = (pointer / <span class="number">190</span>) + <span class="number">0x81</span>; |
| <span class="kw">let </span>gbk_trail = pointer % <span class="number">190</span>; |
| (lead, gbk_trail) |
| } <span class="kw">else </span>{ |
| <span class="comment">// To the left of GB2312 |
| </span><span class="kw">let </span>gbk_left_ideograph_pointer = gbk_left_ideograph_encode(bmp) <span class="kw">as </span>usize; |
| <span class="kw">let </span>lead = (gbk_left_ideograph_pointer / (<span class="number">190 </span>- <span class="number">94</span>)) + (<span class="number">0x81 </span>+ <span class="number">0x29</span>); |
| <span class="kw">let </span>gbk_trail = gbk_left_ideograph_pointer % (<span class="number">190 </span>- <span class="number">94</span>); |
| (lead, gbk_trail) |
| }; |
| <span class="kw">let </span>offset = <span class="kw">if </span>gbk_trail < <span class="number">0x3F </span>{ <span class="number">0x40 </span>} <span class="kw">else </span>{ <span class="number">0x41 </span>}; |
| (lead <span class="kw">as </span>u8, (gbk_trail + offset) <span class="kw">as </span>u8) |
| } |
| } |
| |
| <span class="attribute">#[cfg(feature = <span class="string">"fast-gb-hanzi-encode"</span>)] |
| #[inline(always)] |
| </span><span class="kw">fn </span>encode_hanzi(<span class="kw">_</span>: u16, bmp_minus_unified_start: u16) -> (u8, u8) { |
| gbk_hanzi_encode(bmp_minus_unified_start) |
| } |
| |
| <span class="kw">pub struct </span>Gb18030Encoder { |
| extended: bool, |
| } |
| |
| <span class="kw">impl </span>Gb18030Encoder { |
| <span class="kw">pub fn </span>new(encoding: <span class="kw-2">&</span><span class="lifetime">'static </span>Encoding, extended_range: bool) -> Encoder { |
| Encoder::new( |
| encoding, |
| VariantEncoder::Gb18030(Gb18030Encoder { |
| extended: extended_range, |
| }), |
| ) |
| } |
| |
| <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> { |
| <span class="kw">if </span><span class="self">self</span>.extended { |
| u16_length.checked_mul(<span class="number">4</span>) |
| } <span class="kw">else </span>{ |
| <span class="comment">// Need to add, because space check is done with the four-byte |
| // assumption. |
| </span>checked_add(<span class="number">2</span>, 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> { |
| <span class="kw">if </span><span class="self">self</span>.extended { |
| <span class="comment">// 1 to 1 |
| // 2 to 2 |
| // 3 to 2 |
| // 2 to 4 (worst) |
| // 3 to 4 |
| // 4 to 4 |
| </span>checked_add(<span class="number">2</span>, byte_length.checked_mul(<span class="number">2</span>)) |
| } <span class="kw">else </span>{ |
| <span class="comment">// 1 to 1 |
| // 2 to 2 |
| // 3 to 2 |
| // Need to add, because space check is done with the four-byte |
| // assumption. |
| </span>byte_length.checked_add(<span class="number">3</span>) |
| } |
| } |
| |
| <span class="macro">ascii_compatible_encoder_functions!</span>( |
| { |
| <span class="kw">let </span>bmp_minus_unified_start = bmp.wrapping_sub(<span class="number">0x4E00</span>); |
| <span class="kw">if </span>bmp_minus_unified_start < (<span class="number">0x9FA6 </span>- <span class="number">0x4E00</span>) { |
| <span class="comment">// CJK Unified Ideographs |
| // Can't fail now, since all are |
| // mapped. |
| </span><span class="kw">let </span>(lead, trail) = encode_hanzi(bmp, bmp_minus_unified_start); |
| handle.write_two(lead, trail) |
| } <span class="kw">else if </span>bmp == <span class="number">0xE5E5 </span>{ |
| <span class="comment">// It's not optimal to check for the unmappable |
| // and for euro at this stage, but getting |
| // the out of the way makes the rest of the |
| // code less messy. |
| </span><span class="kw">return </span>( |
| EncoderResult::unmappable_from_bmp(bmp), |
| source.consumed(), |
| handle.written(), |
| ); |
| } <span class="kw">else if </span>bmp == <span class="number">0x20AC </span>&& !<span class="self">self</span>.extended { |
| handle.write_one(<span class="number">0x80u8</span>) |
| } <span class="kw">else </span>{ |
| <span class="kw">match </span>gbk_encode_non_unified(bmp) { |
| <span class="prelude-val">Some</span>((lead, trail)) => handle.write_two(lead <span class="kw">as </span>u8, trail <span class="kw">as </span>u8), |
| <span class="prelude-val">None </span>=> { |
| <span class="kw">if </span>!<span class="self">self</span>.extended { |
| <span class="kw">return </span>( |
| EncoderResult::unmappable_from_bmp(bmp), |
| source.consumed(), |
| handle.written(), |
| ); |
| } |
| <span class="kw">let </span>range_pointer = gb18030_range_encode(bmp); |
| <span class="kw">let </span>first = range_pointer / (<span class="number">10 </span>* <span class="number">126 </span>* <span class="number">10</span>); |
| <span class="kw">let </span>rem_first = range_pointer % (<span class="number">10 </span>* <span class="number">126 </span>* <span class="number">10</span>); |
| <span class="kw">let </span>second = rem_first / (<span class="number">10 </span>* <span class="number">126</span>); |
| <span class="kw">let </span>rem_second = rem_first % (<span class="number">10 </span>* <span class="number">126</span>); |
| <span class="kw">let </span>third = rem_second / <span class="number">10</span>; |
| <span class="kw">let </span>fourth = rem_second % <span class="number">10</span>; |
| handle.write_four( |
| (first + <span class="number">0x81</span>) <span class="kw">as </span>u8, |
| (second + <span class="number">0x30</span>) <span class="kw">as </span>u8, |
| (third + <span class="number">0x81</span>) <span class="kw">as </span>u8, |
| (fourth + <span class="number">0x30</span>) <span class="kw">as </span>u8, |
| ) |
| } |
| } |
| } |
| }, |
| { |
| <span class="kw">if </span>!<span class="self">self</span>.extended { |
| <span class="kw">return </span>( |
| EncoderResult::Unmappable(astral), |
| source.consumed(), |
| handle.written(), |
| ); |
| } |
| <span class="kw">let </span>range_pointer = astral <span class="kw">as </span>usize + (<span class="number">189_000usize </span>- <span class="number">0x1_0000usize</span>); |
| <span class="kw">let </span>first = range_pointer / (<span class="number">10 </span>* <span class="number">126 </span>* <span class="number">10</span>); |
| <span class="kw">let </span>rem_first = range_pointer % (<span class="number">10 </span>* <span class="number">126 </span>* <span class="number">10</span>); |
| <span class="kw">let </span>second = rem_first / (<span class="number">10 </span>* <span class="number">126</span>); |
| <span class="kw">let </span>rem_second = rem_first % (<span class="number">10 </span>* <span class="number">126</span>); |
| <span class="kw">let </span>third = rem_second / <span class="number">10</span>; |
| <span class="kw">let </span>fourth = rem_second % <span class="number">10</span>; |
| handle.write_four( |
| (first + <span class="number">0x81</span>) <span class="kw">as </span>u8, |
| (second + <span class="number">0x30</span>) <span class="kw">as </span>u8, |
| (third + <span class="number">0x81</span>) <span class="kw">as </span>u8, |
| (fourth + <span class="number">0x30</span>) <span class="kw">as </span>u8, |
| ) |
| }, |
| bmp, |
| astral, |
| <span class="self">self</span>, |
| source, |
| handle, |
| copy_ascii_to_check_space_four, |
| check_space_four, |
| <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_gb18030(bytes: <span class="kw-2">&</span>[u8], expect: <span class="kw-2">&</span>str) { |
| decode(GB18030, bytes, expect); |
| } |
| |
| <span class="kw">fn </span>encode_gb18030(string: <span class="kw-2">&</span>str, expect: <span class="kw-2">&</span>[u8]) { |
| encode(GB18030, string, expect); |
| } |
| |
| <span class="kw">fn </span>encode_gbk(string: <span class="kw-2">&</span>str, expect: <span class="kw-2">&</span>[u8]) { |
| encode(GBK, string, expect); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_gb18030_decode() { |
| <span class="comment">// Empty |
| </span>decode_gb18030(<span class="string">b""</span>, <span class="kw-2">&</span><span class="string">""</span>); |
| |
| <span class="comment">// ASCII |
| </span>decode_gb18030(<span class="string">b"\x61\x62"</span>, <span class="string">"\u{0061}\u{0062}"</span>); |
| |
| <span class="comment">// euro |
| </span>decode_gb18030(<span class="string">b"\x80"</span>, <span class="string">"\u{20AC}"</span>); |
| decode_gb18030(<span class="string">b"\xA2\xE3"</span>, <span class="string">"\u{20AC}"</span>); |
| |
| <span class="comment">// two bytes |
| </span>decode_gb18030(<span class="string">b"\x81\x40"</span>, <span class="string">"\u{4E02}"</span>); |
| decode_gb18030(<span class="string">b"\x81\x7E"</span>, <span class="string">"\u{4E8A}"</span>); |
| decode_gb18030(<span class="string">b"\x81\x7F"</span>, <span class="string">"\u{FFFD}\u{007F}"</span>); |
| decode_gb18030(<span class="string">b"\x81\x80"</span>, <span class="string">"\u{4E90}"</span>); |
| decode_gb18030(<span class="string">b"\x81\xFE"</span>, <span class="string">"\u{4FA2}"</span>); |
| decode_gb18030(<span class="string">b"\xFE\x40"</span>, <span class="string">"\u{FA0C}"</span>); |
| decode_gb18030(<span class="string">b"\xFE\x7E"</span>, <span class="string">"\u{E843}"</span>); |
| decode_gb18030(<span class="string">b"\xFE\x7F"</span>, <span class="string">"\u{FFFD}\u{007F}"</span>); |
| decode_gb18030(<span class="string">b"\xFE\x80"</span>, <span class="string">"\u{4723}"</span>); |
| decode_gb18030(<span class="string">b"\xFE\xFE"</span>, <span class="string">"\u{E4C5}"</span>); |
| |
| <span class="comment">// The difference from the original GB18030 |
| </span>decode_gb18030(<span class="string">b"\xA3\xA0"</span>, <span class="string">"\u{3000}"</span>); |
| decode_gb18030(<span class="string">b"\xA1\xA1"</span>, <span class="string">"\u{3000}"</span>); |
| |
| <span class="comment">// 0xFF |
| </span>decode_gb18030(<span class="string">b"\xFF\x40"</span>, <span class="string">"\u{FFFD}\u{0040}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\xFF\x9A\x33"</span>, <span class="string">"\u{FFFD}\u{FFFD}"</span>); <span class="comment">// not \u{FFFD}\u{FFFD}\u{0033} ! |
| </span>decode_gb18030(<span class="string">b"\xFF\x32\x9A\x33"</span>, <span class="string">"\u{FFFD}\u{0032}\u{FFFD}"</span>); <span class="comment">// not \u{FFFD}\u{0032}\u{FFFD}\u{0033} ! |
| </span>decode_gb18030(<span class="string">b"\xFF\x40\x00"</span>, <span class="string">"\u{FFFD}\u{0040}\u{0000}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\xFF\x9A\x33\x00"</span>, <span class="string">"\u{FFFD}\u{FFFD}\u{0033}\u{0000}"</span>); |
| decode_gb18030( |
| <span class="string">b"\xFF\x32\x9A\x33\x00"</span>, |
| <span class="string">"\u{FFFD}\u{0032}\u{FFFD}\u{0033}\u{0000}"</span>, |
| ); |
| |
| <span class="comment">// Four bytes |
| </span>decode_gb18030(<span class="string">b"\x81\x30\x81\x30"</span>, <span class="string">"\u{0080}"</span>); |
| decode_gb18030(<span class="string">b"\x81\x35\xF4\x37"</span>, <span class="string">"\u{E7C7}"</span>); |
| decode_gb18030(<span class="string">b"\x81\x37\xA3\x30"</span>, <span class="string">"\u{2603}"</span>); |
| decode_gb18030(<span class="string">b"\x94\x39\xDA\x33"</span>, <span class="string">"\u{1F4A9}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\x32\x9A\x35"</span>, <span class="string">"\u{10FFFF}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\x32\x9A\x36\x81\x30"</span>, <span class="string">"\u{FFFD}\u{FFFD}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\x32\x9A\x36\x81\x40"</span>, <span class="string">"\u{FFFD}\u{4E02}"</span>); |
| decode_gb18030(<span class="string">b"\xE3\x32\x9A"</span>, <span class="string">"\u{FFFD}"</span>); <span class="comment">// not \u{FFFD}\u{0032}\u{FFFD} ! |
| </span>decode_gb18030(<span class="string">b"\xE3\x32\x9A\x00"</span>, <span class="string">"\u{FFFD}\u{0032}\u{FFFD}\u{0000}"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_gb18030_encode() { |
| <span class="comment">// Empty |
| </span>encode_gb18030(<span class="string">""</span>, <span class="string">b""</span>); |
| |
| <span class="comment">// ASCII |
| </span>encode_gb18030(<span class="string">"\u{0061}\u{0062}"</span>, <span class="string">b"\x61\x62"</span>); |
| |
| <span class="comment">// euro |
| </span>encode_gb18030(<span class="string">"\u{20AC}"</span>, <span class="string">b"\xA2\xE3"</span>); |
| |
| <span class="comment">// two bytes |
| </span>encode_gb18030(<span class="string">"\u{4E02}"</span>, <span class="string">b"\x81\x40"</span>); |
| encode_gb18030(<span class="string">"\u{4E8A}"</span>, <span class="string">b"\x81\x7E"</span>); |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(miri) { |
| <span class="comment">// Miri is too slow |
| </span>encode_gb18030(<span class="string">"\u{4E90}"</span>, <span class="string">b"\x81\x80"</span>); |
| encode_gb18030(<span class="string">"\u{4FA2}"</span>, <span class="string">b"\x81\xFE"</span>); |
| encode_gb18030(<span class="string">"\u{FA0C}"</span>, <span class="string">b"\xFE\x40"</span>); |
| encode_gb18030(<span class="string">"\u{E843}"</span>, <span class="string">b"\xFE\x7E"</span>); |
| encode_gb18030(<span class="string">"\u{4723}"</span>, <span class="string">b"\xFE\x80"</span>); |
| encode_gb18030(<span class="string">"\u{E4C5}"</span>, <span class="string">b"\xFE\xFE"</span>); |
| } |
| |
| <span class="comment">// The difference from the original GB18030 |
| </span>encode_gb18030(<span class="string">"\u{E5E5}"</span>, <span class="string">b"&#58853;"</span>); |
| encode_gb18030(<span class="string">"\u{3000}"</span>, <span class="string">b"\xA1\xA1"</span>); |
| |
| <span class="comment">// Four bytes |
| </span>encode_gb18030(<span class="string">"\u{0080}"</span>, <span class="string">b"\x81\x30\x81\x30"</span>); |
| encode_gb18030(<span class="string">"\u{E7C7}"</span>, <span class="string">b"\x81\x35\xF4\x37"</span>); |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(miri) { |
| <span class="comment">// Miri is too slow |
| </span>encode_gb18030(<span class="string">"\u{2603}"</span>, <span class="string">b"\x81\x37\xA3\x30"</span>); |
| encode_gb18030(<span class="string">"\u{1F4A9}"</span>, <span class="string">b"\x94\x39\xDA\x33"</span>); |
| encode_gb18030(<span class="string">"\u{10FFFF}"</span>, <span class="string">b"\xE3\x32\x9A\x35"</span>); |
| } |
| |
| <span class="comment">// Edge cases |
| </span>encode_gb18030(<span class="string">"\u{00F7}"</span>, <span class="string">b"\xA1\xC2"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_gbk_encode() { |
| <span class="comment">// Empty |
| </span>encode_gbk(<span class="string">""</span>, <span class="string">b""</span>); |
| |
| <span class="comment">// ASCII |
| </span>encode_gbk(<span class="string">"\u{0061}\u{0062}"</span>, <span class="string">b"\x61\x62"</span>); |
| |
| <span class="comment">// euro |
| </span>encode_gbk(<span class="string">"\u{20AC}"</span>, <span class="string">b"\x80"</span>); |
| |
| <span class="comment">// two bytes |
| </span>encode_gbk(<span class="string">"\u{4E02}"</span>, <span class="string">b"\x81\x40"</span>); |
| encode_gbk(<span class="string">"\u{4E8A}"</span>, <span class="string">b"\x81\x7E"</span>); |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(miri) { |
| <span class="comment">// Miri is too slow |
| </span>encode_gbk(<span class="string">"\u{4E90}"</span>, <span class="string">b"\x81\x80"</span>); |
| encode_gbk(<span class="string">"\u{4FA2}"</span>, <span class="string">b"\x81\xFE"</span>); |
| encode_gbk(<span class="string">"\u{FA0C}"</span>, <span class="string">b"\xFE\x40"</span>); |
| encode_gbk(<span class="string">"\u{E843}"</span>, <span class="string">b"\xFE\x7E"</span>); |
| encode_gbk(<span class="string">"\u{4723}"</span>, <span class="string">b"\xFE\x80"</span>); |
| encode_gbk(<span class="string">"\u{E4C5}"</span>, <span class="string">b"\xFE\xFE"</span>); |
| } |
| |
| <span class="comment">// The difference from the original gb18030 |
| </span>encode_gbk(<span class="string">"\u{E5E5}"</span>, <span class="string">b"&#58853;"</span>); |
| encode_gbk(<span class="string">"\u{3000}"</span>, <span class="string">b"\xA1\xA1"</span>); |
| |
| <span class="comment">// Four bytes |
| </span>encode_gbk(<span class="string">"\u{0080}"</span>, <span class="string">b"&#128;"</span>); |
| encode_gbk(<span class="string">"\u{E7C7}"</span>, <span class="string">b"&#59335;"</span>); |
| <span class="kw">if </span>!<span class="macro">cfg!</span>(miri) { |
| <span class="comment">// Miri is too slow |
| </span>encode_gbk(<span class="string">"\u{2603}"</span>, <span class="string">b"&#9731;"</span>); |
| encode_gbk(<span class="string">"\u{1F4A9}"</span>, <span class="string">b"&#128169;"</span>); |
| encode_gbk(<span class="string">"\u{10FFFF}"</span>, <span class="string">b"&#1114111;"</span>); |
| } |
| |
| <span class="comment">// Edge cases |
| </span>encode_gbk(<span class="string">"\u{00F7}"</span>, <span class="string">b"\xA1\xC2"</span>); |
| } |
| |
| <span class="attribute">#[test] |
| #[cfg_attr(miri, ignore)] </span><span class="comment">// Miri is too slow |
| </span><span class="kw">fn </span>test_gb18030_decode_all() { |
| <span class="kw">let </span>input = <span class="macro">include_bytes!</span>(<span class="string">"test_data/gb18030_in.txt"</span>); |
| <span class="kw">let </span>expectation = <span class="macro">include_str!</span>(<span class="string">"test_data/gb18030_in_ref.txt"</span>); |
| <span class="kw">let </span>(cow, had_errors) = GB18030.decode_without_bom_handling(input); |
| <span class="macro">assert!</span>(!had_errors, <span class="string">"Should not 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_gb18030_encode_all() { |
| <span class="kw">let </span>input = <span class="macro">include_str!</span>(<span class="string">"test_data/gb18030_out.txt"</span>); |
| <span class="kw">let </span>expectation = <span class="macro">include_bytes!</span>(<span class="string">"test_data/gb18030_out_ref.txt"</span>); |
| <span class="kw">let </span>(cow, encoding, had_errors) = GB18030.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, GB18030); |
| <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_gb18030_encode_from_utf16_max_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>encoder = GB18030.new_encoder(); |
| { |
| <span class="kw">let </span>needed = encoder |
| .max_buffer_length_from_utf16_without_replacement(<span class="number">1</span>) |
| .unwrap(); |
| <span class="kw">let </span>(result, read, written) = encoder.encode_from_utf16_without_replacement( |
| <span class="kw-2">&</span>[<span class="number">0x3000</span>], |
| <span class="kw-2">&mut </span>output[..needed], |
| <span class="bool-val">true</span>, |
| ); |
| <span class="macro">assert_eq!</span>(result, EncoderResult::InputEmpty); |
| <span class="macro">assert_eq!</span>(read, <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(written, <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(output[<span class="number">0</span>], <span class="number">0xA1</span>); |
| <span class="macro">assert_eq!</span>(output[<span class="number">1</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> |