213 lines
16 KiB
HTML
213 lines
16 KiB
HTML
|
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source to the Rust file `C:\Users\evilc\.cargo\registry\src\github.com-1ecc6299db9ec823\ucd-util-0.1.5\src\hangul.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>hangul.rs.html -- source</title><link rel="stylesheet" type="text/css" href="../../normalize.css"><link rel="stylesheet" type="text/css" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" type="text/css" href="../../dark.css"><link rel="stylesheet" type="text/css" href="../../light.css" id="themeStyle"><script src="../../storage.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="shortcut icon" href="../../favicon.ico"><style type="text/css">#crate-search{background-image:url("../../down-arrow.svg");}</style></head><body class="rustdoc source"><!--[if lte IE 8]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><div class="sidebar-menu">☰</div><a href='../../ucd_util/index.html'><div class='logo-container'><img src='../../rust-logo.png' alt='logo'></div></a></nav><div class="theme-picker"><button id="theme-picker" aria-label="Pick another theme!"><img src="../../brush.svg" width="18" alt="Pick another theme!"></button><div id="theme-choices"></div></div><script src="../../theme.js"></script><nav class="sub"><form class="search-form js-only"><div class="search-container"><div><select id="crate-search"><option value="All crates">All crates</option></select><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"></div><a id="settings-menu" href="../../settings.html"><img src="../../wheel.svg" width="18" alt="Change settings"></a></div></form></nav><section id="main" class="content"><pre class="line-numbers"><span id="1"> 1</span>
|
|||
|
<span id="2"> 2</span>
|
|||
|
<span id="3"> 3</span>
|
|||
|
<span id="4"> 4</span>
|
|||
|
<span id="5"> 5</span>
|
|||
|
<span id="6"> 6</span>
|
|||
|
<span id="7"> 7</span>
|
|||
|
<span id="8"> 8</span>
|
|||
|
<span id="9"> 9</span>
|
|||
|
<span id="10"> 10</span>
|
|||
|
<span id="11"> 11</span>
|
|||
|
<span id="12"> 12</span>
|
|||
|
<span id="13"> 13</span>
|
|||
|
<span id="14"> 14</span>
|
|||
|
<span id="15"> 15</span>
|
|||
|
<span id="16"> 16</span>
|
|||
|
<span id="17"> 17</span>
|
|||
|
<span id="18"> 18</span>
|
|||
|
<span id="19"> 19</span>
|
|||
|
<span id="20"> 20</span>
|
|||
|
<span id="21"> 21</span>
|
|||
|
<span id="22"> 22</span>
|
|||
|
<span id="23"> 23</span>
|
|||
|
<span id="24"> 24</span>
|
|||
|
<span id="25"> 25</span>
|
|||
|
<span id="26"> 26</span>
|
|||
|
<span id="27"> 27</span>
|
|||
|
<span id="28"> 28</span>
|
|||
|
<span id="29"> 29</span>
|
|||
|
<span id="30"> 30</span>
|
|||
|
<span id="31"> 31</span>
|
|||
|
<span id="32"> 32</span>
|
|||
|
<span id="33"> 33</span>
|
|||
|
<span id="34"> 34</span>
|
|||
|
<span id="35"> 35</span>
|
|||
|
<span id="36"> 36</span>
|
|||
|
<span id="37"> 37</span>
|
|||
|
<span id="38"> 38</span>
|
|||
|
<span id="39"> 39</span>
|
|||
|
<span id="40"> 40</span>
|
|||
|
<span id="41"> 41</span>
|
|||
|
<span id="42"> 42</span>
|
|||
|
<span id="43"> 43</span>
|
|||
|
<span id="44"> 44</span>
|
|||
|
<span id="45"> 45</span>
|
|||
|
<span id="46"> 46</span>
|
|||
|
<span id="47"> 47</span>
|
|||
|
<span id="48"> 48</span>
|
|||
|
<span id="49"> 49</span>
|
|||
|
<span id="50"> 50</span>
|
|||
|
<span id="51"> 51</span>
|
|||
|
<span id="52"> 52</span>
|
|||
|
<span id="53"> 53</span>
|
|||
|
<span id="54"> 54</span>
|
|||
|
<span id="55"> 55</span>
|
|||
|
<span id="56"> 56</span>
|
|||
|
<span id="57"> 57</span>
|
|||
|
<span id="58"> 58</span>
|
|||
|
<span id="59"> 59</span>
|
|||
|
<span id="60"> 60</span>
|
|||
|
<span id="61"> 61</span>
|
|||
|
<span id="62"> 62</span>
|
|||
|
<span id="63"> 63</span>
|
|||
|
<span id="64"> 64</span>
|
|||
|
<span id="65"> 65</span>
|
|||
|
<span id="66"> 66</span>
|
|||
|
<span id="67"> 67</span>
|
|||
|
<span id="68"> 68</span>
|
|||
|
<span id="69"> 69</span>
|
|||
|
<span id="70"> 70</span>
|
|||
|
<span id="71"> 71</span>
|
|||
|
<span id="72"> 72</span>
|
|||
|
<span id="73"> 73</span>
|
|||
|
<span id="74"> 74</span>
|
|||
|
<span id="75"> 75</span>
|
|||
|
<span id="76"> 76</span>
|
|||
|
<span id="77"> 77</span>
|
|||
|
<span id="78"> 78</span>
|
|||
|
<span id="79"> 79</span>
|
|||
|
<span id="80"> 80</span>
|
|||
|
<span id="81"> 81</span>
|
|||
|
<span id="82"> 82</span>
|
|||
|
<span id="83"> 83</span>
|
|||
|
<span id="84"> 84</span>
|
|||
|
<span id="85"> 85</span>
|
|||
|
<span id="86"> 86</span>
|
|||
|
<span id="87"> 87</span>
|
|||
|
<span id="88"> 88</span>
|
|||
|
<span id="89"> 89</span>
|
|||
|
<span id="90"> 90</span>
|
|||
|
<span id="91"> 91</span>
|
|||
|
<span id="92"> 92</span>
|
|||
|
<span id="93"> 93</span>
|
|||
|
<span id="94"> 94</span>
|
|||
|
<span id="95"> 95</span>
|
|||
|
<span id="96"> 96</span>
|
|||
|
<span id="97"> 97</span>
|
|||
|
<span id="98"> 98</span>
|
|||
|
<span id="99"> 99</span>
|
|||
|
<span id="100">100</span>
|
|||
|
<span id="101">101</span>
|
|||
|
<span id="102">102</span>
|
|||
|
<span id="103">103</span>
|
|||
|
<span id="104">104</span>
|
|||
|
<span id="105">105</span>
|
|||
|
</pre><div class="example-wrap"><pre class="rust ">
|
|||
|
<span class="kw">use</span> <span class="ident">unicode_tables</span>::<span class="ident">jamo_short_name</span>::<span class="ident">JAMO_SHORT_NAME</span>;
|
|||
|
|
|||
|
<span class="comment">// This implementation should correspond to the algorithms described in</span>
|
|||
|
<span class="comment">// Unicode 3.12.</span>
|
|||
|
|
|||
|
<span class="doccomment">/// A set of ranges that corresponds to the set of all Hangul syllable</span>
|
|||
|
<span class="doccomment">/// codepoints.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// These ranges are defined in Unicode 4.8 Table 4-13.</span>
|
|||
|
<span class="kw">pub</span> <span class="kw">const</span> <span class="ident">RANGE_HANGUL_SYLLABLE</span>: <span class="kw-2">&</span><span class="lifetime">'static</span> [(<span class="ident">u32</span>, <span class="ident">u32</span>)] <span class="op">=</span> <span class="kw-2">&</span>[
|
|||
|
(<span class="number">0xAC00</span>, <span class="number">0xD7A3</span>),
|
|||
|
];
|
|||
|
|
|||
|
<span class="kw">const</span> <span class="ident">S_BASE</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">0xAC00</span>;
|
|||
|
<span class="kw">const</span> <span class="ident">L_BASE</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">0x1100</span>;
|
|||
|
<span class="kw">const</span> <span class="ident">V_BASE</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">0x1161</span>;
|
|||
|
<span class="kw">const</span> <span class="ident">T_BASE</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">0x11A7</span>;
|
|||
|
<span class="kw">const</span> <span class="ident">T_COUNT</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">28</span>;
|
|||
|
<span class="kw">const</span> <span class="ident">N_COUNT</span>: <span class="ident">u32</span> <span class="op">=</span> <span class="number">588</span>;
|
|||
|
|
|||
|
<span class="doccomment">/// Return the character name of the given precomposed Hangul codepoint.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// If the given codepoint does not correspond to a precomposed Hangul</span>
|
|||
|
<span class="doccomment">/// codepoint in the inclusive range `AC00..D7A3`, then this returns `None`.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// This implements the algorithms described in Unicode 3.12 and Unicode 4.8.</span>
|
|||
|
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">hangul_name</span>(<span class="ident">cp</span>: <span class="ident">u32</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">String</span><span class="op">></span> {
|
|||
|
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">name</span> <span class="op">=</span> <span class="string">"HANGUL SYLLABLE "</span>.<span class="ident">to_string</span>();
|
|||
|
<span class="kw">let</span> (<span class="ident">lpart</span>, <span class="ident">vpart</span>, <span class="ident">tpart</span>) <span class="op">=</span> <span class="kw">match</span> <span class="ident">hangul_full_canonical_decomposition</span>(<span class="ident">cp</span>) {
|
|||
|
<span class="prelude-val">None</span> <span class="op">=></span> <span class="kw">return</span> <span class="prelude-val">None</span>,
|
|||
|
<span class="prelude-val">Some</span>(<span class="ident">triple</span>) <span class="op">=></span> <span class="ident">triple</span>,
|
|||
|
};
|
|||
|
|
|||
|
<span class="ident">name</span>.<span class="ident">push_str</span>(<span class="ident">jamo_short_name</span>(<span class="ident">lpart</span>));
|
|||
|
<span class="ident">name</span>.<span class="ident">push_str</span>(<span class="ident">jamo_short_name</span>(<span class="ident">vpart</span>));
|
|||
|
<span class="ident">name</span>.<span class="ident">push_str</span>(<span class="ident">tpart</span>.<span class="ident">map_or</span>(<span class="string">""</span>, <span class="ident">jamo_short_name</span>));
|
|||
|
<span class="prelude-val">Some</span>(<span class="ident">name</span>)
|
|||
|
}
|
|||
|
|
|||
|
<span class="doccomment">/// Return the full canonical decomposition of the given precomposed Hangul</span>
|
|||
|
<span class="doccomment">/// codepoint.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// If the decomposition does not have any trailing consonant, then the third</span>
|
|||
|
<span class="doccomment">/// part of the tuple returned is `None`.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// If the given codepoint does not correspond to a precomposed Hangul</span>
|
|||
|
<span class="doccomment">/// codepoint in the inclusive range `AC00..D7A3`, then this returns `None`.</span>
|
|||
|
<span class="doccomment">///</span>
|
|||
|
<span class="doccomment">/// This implements the algorithms described in Unicode 3.12 and Unicode 4.8.</span>
|
|||
|
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">hangul_full_canonical_decomposition</span>(
|
|||
|
<span class="ident">cp</span>: <span class="ident">u32</span>,
|
|||
|
) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span>(<span class="ident">u32</span>, <span class="ident">u32</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">u32</span><span class="op">></span>)<span class="op">></span> {
|
|||
|
<span class="kw">if</span> <span class="op">!</span>(<span class="number">0xAC00</span> <span class="op"><=</span> <span class="ident">cp</span> <span class="op">&&</span> <span class="ident">cp</span> <span class="op"><=</span> <span class="number">0xD7A3</span>) {
|
|||
|
<span class="kw">return</span> <span class="prelude-val">None</span>;
|
|||
|
}
|
|||
|
|
|||
|
<span class="kw">let</span> <span class="ident">s_index</span> <span class="op">=</span> <span class="ident">cp</span> <span class="op">-</span> <span class="ident">S_BASE</span>;
|
|||
|
<span class="kw">let</span> <span class="ident">l_index</span> <span class="op">=</span> <span class="ident">s_index</span> <span class="op">/</span> <span class="ident">N_COUNT</span>;
|
|||
|
<span class="kw">let</span> <span class="ident">v_index</span> <span class="op">=</span> (<span class="ident">s_index</span> <span class="op">%</span> <span class="ident">N_COUNT</span>) <span class="op">/</span> <span class="ident">T_COUNT</span>;
|
|||
|
<span class="kw">let</span> <span class="ident">t_index</span> <span class="op">=</span> <span class="ident">s_index</span> <span class="op">%</span> <span class="ident">T_COUNT</span>;
|
|||
|
|
|||
|
<span class="kw">let</span> <span class="ident">l_part</span> <span class="op">=</span> <span class="ident">L_BASE</span> <span class="op">+</span> <span class="ident">l_index</span>;
|
|||
|
<span class="kw">let</span> <span class="ident">v_part</span> <span class="op">=</span> <span class="ident">V_BASE</span> <span class="op">+</span> <span class="ident">v_index</span>;
|
|||
|
<span class="kw">let</span> <span class="ident">t_part</span> <span class="op">=</span>
|
|||
|
<span class="kw">if</span> <span class="ident">t_index</span> <span class="op">==</span> <span class="number">0</span> {
|
|||
|
<span class="prelude-val">None</span>
|
|||
|
} <span class="kw">else</span> {
|
|||
|
<span class="prelude-val">Some</span>(<span class="ident">T_BASE</span> <span class="op">+</span> <span class="ident">t_index</span>)
|
|||
|
};
|
|||
|
<span class="prelude-val">Some</span>((<span class="ident">l_part</span>, <span class="ident">v_part</span>, <span class="ident">t_part</span>))
|
|||
|
}
|
|||
|
|
|||
|
<span class="kw">fn</span> <span class="ident">jamo_short_name</span>(<span class="ident">cp</span>: <span class="ident">u32</span>) <span class="op">-></span> <span class="kw-2">&</span><span class="lifetime">'static</span> <span class="ident">str</span> {
|
|||
|
<span class="kw">let</span> <span class="ident">i</span> <span class="op">=</span> <span class="ident">JAMO_SHORT_NAME</span>.<span class="ident">binary_search_by_key</span>(<span class="kw-2">&</span><span class="ident">cp</span>, <span class="op">|</span><span class="ident">p</span><span class="op">|</span> <span class="ident">p</span>.<span class="number">0</span>).<span class="ident">unwrap</span>();
|
|||
|
<span class="ident">JAMO_SHORT_NAME</span>[<span class="ident">i</span>].<span class="number">1</span>
|
|||
|
}
|
|||
|
|
|||
|
<span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span>
|
|||
|
<span class="kw">mod</span> <span class="ident">tests</span> {
|
|||
|
<span class="kw">use</span> <span class="kw">super</span>::{<span class="ident">hangul_name</span>, <span class="ident">hangul_full_canonical_decomposition</span>};
|
|||
|
|
|||
|
<span class="attribute">#[<span class="ident">test</span>]</span>
|
|||
|
<span class="kw">fn</span> <span class="ident">canon_decomp</span>() {
|
|||
|
<span class="macro">assert_eq</span><span class="macro">!</span>(
|
|||
|
<span class="ident">hangul_full_canonical_decomposition</span>(<span class="number">0xD4DB</span>),
|
|||
|
<span class="prelude-val">Some</span>((<span class="number">0x1111</span>, <span class="number">0x1171</span>, <span class="prelude-val">Some</span>(<span class="number">0x11B6</span>))));
|
|||
|
}
|
|||
|
|
|||
|
<span class="attribute">#[<span class="ident">test</span>]</span>
|
|||
|
<span class="kw">fn</span> <span class="ident">name</span>() {
|
|||
|
<span class="macro">assert_eq</span><span class="macro">!</span>(<span class="ident">hangul_name</span>(<span class="number">0xD4DB</span>).<span class="ident">unwrap</span>(), <span class="string">"HANGUL SYLLABLE PWILH"</span>);
|
|||
|
}
|
|||
|
|
|||
|
<span class="attribute">#[<span class="ident">test</span>]</span>
|
|||
|
<span class="kw">fn</span> <span class="ident">all</span>() {
|
|||
|
<span class="kw">for</span> <span class="ident">cp</span> <span class="kw">in</span> <span class="number">0xAC00</span>..(<span class="number">0xD7A3</span> <span class="op">+</span> <span class="number">1</span>) {
|
|||
|
<span class="ident">hangul_name</span>(<span class="ident">cp</span>).<span class="ident">unwrap</span>();
|
|||
|
}
|
|||
|
}
|
|||
|
|
|||
|
<span class="attribute">#[<span class="ident">test</span>]</span>
|
|||
|
<span class="kw">fn</span> <span class="ident">invalid</span>() {
|
|||
|
<span class="macro">assert</span><span class="macro">!</span>(<span class="ident">hangul_name</span>(<span class="number">0</span>).<span class="ident">is_none</span>());
|
|||
|
}
|
|||
|
}
|
|||
|
</pre></div>
|
|||
|
</section><section id="search" class="content hidden"></section><section class="footer"></section><aside id="help" class="hidden"><div><h1 class="hidden">Help</h1><div class="shortcuts"><h2>Keyboard Shortcuts</h2><dl><dt><kbd>?</kbd></dt><dd>Show this help dialog</dd><dt><kbd>S</kbd></dt><dd>Focus the search field</dd><dt><kbd>↑</kbd></dt><dd>Move up in search results</dd><dt><kbd>↓</kbd></dt><dd>Move down in search results</dd><dt><kbd>↹</kbd></dt><dd>Switch tab</dd><dt><kbd>⏎</kbd></dt><dd>Go to active search result</dd><dt><kbd>+</kbd></dt><dd>Expand all sections</dd><dt><kbd>-</kbd></dt><dd>Collapse all sections</dd></dl></div><div class="infos"><h2>Search Tricks</h2><p>Prefix searches with a type followed by a colon (e.g., <code>fn:</code>) to restrict the search to a given type.</p><p>Accepted types are: <code>fn</code>, <code>mod</code>, <code>struct</code>, <code>enum</code>, <code>trait</code>, <code>type</code>, <code>macro</code>, and <code>const</code>.</p><p>Search functions by type signature (e.g., <code>vec -> usize</code> or <code>* -> vec</code>)</p><p>Search multiple things at once by splitting your query with comma (e.g., <code>str,u8</code> or <code>String,struct:Vec,test</code>)</p></div></div></aside><script>window.rootPath = "../../";window.currentCrate = "ucd_util";</script><script src="../../aliases.js"></script><script src="../../main.js"></script><script src="../../source-script.js"></script><script src="../../source-files.js"></script><script defer src="../../search-index.js"></script></body></html>
|