| <!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/unicode-normalization-0.1.22/src/normalize.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>normalize.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="icon" href="https://unicode-rs.github.io/unicode-rs_sm.png"></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="../../unicode_normalization/index.html"><div class="logo-container"> |
| <img src="https://unicode-rs.github.io/unicode-rs_sm.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../unicode_normalization/index.html"> |
| <img src="https://unicode-rs.github.io/unicode-rs_sm.png" 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> |
| </pre><pre class="rust"><code><span class="comment">// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT |
| // file at the top-level directory of this distribution and at |
| // http://rust-lang.org/COPYRIGHT. |
| // |
| // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or |
| // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license |
| // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your |
| // option. This file may not be copied, modified, or distributed |
| // except according to those terms. |
| |
| </span><span class="doccomment">//! Functions for computing canonical and compatible decompositions for Unicode characters. |
| </span><span class="kw">use </span><span class="kw">crate</span>::lookups::{ |
| canonical_fully_decomposed, cjk_compat_variants_fully_decomposed, |
| compatibility_fully_decomposed, composition_table, |
| }; |
| |
| <span class="kw">use </span>core::{char, ops::FnMut}; |
| |
| <span class="doccomment">/// Compute canonical Unicode decomposition for character. |
| /// See [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/) |
| /// for more information. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>decompose_canonical<F>(c: char, emit_char: F) |
| <span class="kw">where |
| </span>F: FnMut(char), |
| { |
| decompose(c, canonical_fully_decomposed, emit_char) |
| } |
| |
| <span class="doccomment">/// Compute canonical or compatible Unicode decomposition for character. |
| /// See [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/) |
| /// for more information. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>decompose_compatible<F: FnMut(char)>(c: char, emit_char: F) { |
| <span class="kw">let </span>decompose_char = |
| |c| compatibility_fully_decomposed(c).or_else(|| canonical_fully_decomposed(c)); |
| decompose(c, decompose_char, emit_char) |
| } |
| |
| <span class="doccomment">/// Compute standard-variation decomposition for character. |
| /// |
| /// [Standardized Variation Sequences] are used instead of the standard canonical |
| /// decompositions, notably for CJK codepoints with singleton canonical decompositions, |
| /// to avoid losing information. See the |
| /// [Unicode Variation Sequence FAQ](http://unicode.org/faq/vs.html) and the |
| /// "Other Enhancements" section of the |
| /// [Unicode 6.3 Release Summary](https://www.unicode.org/versions/Unicode6.3.0/#Summary) |
| /// for more information. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>decompose_cjk_compat_variants<F>(c: char, <span class="kw-2">mut </span>emit_char: F) |
| <span class="kw">where |
| </span>F: FnMut(char), |
| { |
| <span class="comment">// 7-bit ASCII never decomposes |
| </span><span class="kw">if </span>c <= <span class="string">'\x7f' </span>{ |
| emit_char(c); |
| <span class="kw">return</span>; |
| } |
| |
| <span class="comment">// Don't perform decomposition for Hangul |
| |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(decomposed) = cjk_compat_variants_fully_decomposed(c) { |
| <span class="kw">for </span><span class="kw-2">&</span>d <span class="kw">in </span>decomposed { |
| emit_char(d); |
| } |
| <span class="kw">return</span>; |
| } |
| |
| <span class="comment">// Finally bottom out. |
| </span>emit_char(c); |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>decompose<D, F>(c: char, decompose_char: D, <span class="kw-2">mut </span>emit_char: F) |
| <span class="kw">where |
| </span>D: Fn(char) -> <span class="prelude-ty">Option</span><<span class="kw-2">&</span><span class="lifetime">'static </span>[char]>, |
| F: FnMut(char), |
| { |
| <span class="comment">// 7-bit ASCII never decomposes |
| </span><span class="kw">if </span>c <= <span class="string">'\x7f' </span>{ |
| emit_char(c); |
| <span class="kw">return</span>; |
| } |
| |
| <span class="comment">// Perform decomposition for Hangul |
| </span><span class="kw">if </span>is_hangul_syllable(c) { |
| decompose_hangul(c, emit_char); |
| <span class="kw">return</span>; |
| } |
| |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(decomposed) = decompose_char(c) { |
| <span class="kw">for </span><span class="kw-2">&</span>d <span class="kw">in </span>decomposed { |
| emit_char(d); |
| } |
| <span class="kw">return</span>; |
| } |
| |
| <span class="comment">// Finally bottom out. |
| </span>emit_char(c); |
| } |
| |
| <span class="doccomment">/// Compose two characters into a single character, if possible. |
| /// See [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/) |
| /// for more information. |
| </span><span class="kw">pub fn </span>compose(a: char, b: char) -> <span class="prelude-ty">Option</span><char> { |
| compose_hangul(a, b).or_else(|| composition_table(a, b)) |
| } |
| |
| <span class="comment">// Constants from Unicode 9.0.0 Section 3.12 Conjoining Jamo Behavior |
| // http://www.unicode.org/versions/Unicode9.0.0/ch03.pdf#M9.32468.Heading.310.Combining.Jamo.Behavior |
| </span><span class="kw">const </span>S_BASE: u32 = <span class="number">0xAC00</span>; |
| <span class="kw">const </span>L_BASE: u32 = <span class="number">0x1100</span>; |
| <span class="kw">const </span>V_BASE: u32 = <span class="number">0x1161</span>; |
| <span class="kw">const </span>T_BASE: u32 = <span class="number">0x11A7</span>; |
| <span class="kw">const </span>L_COUNT: u32 = <span class="number">19</span>; |
| <span class="kw">const </span>V_COUNT: u32 = <span class="number">21</span>; |
| <span class="kw">const </span>T_COUNT: u32 = <span class="number">28</span>; |
| <span class="kw">const </span>N_COUNT: u32 = V_COUNT * T_COUNT; |
| <span class="kw">const </span>S_COUNT: u32 = L_COUNT * N_COUNT; |
| |
| <span class="kw">const </span>S_LAST: u32 = S_BASE + S_COUNT - <span class="number">1</span>; |
| <span class="kw">const </span>L_LAST: u32 = L_BASE + L_COUNT - <span class="number">1</span>; |
| <span class="kw">const </span>V_LAST: u32 = V_BASE + V_COUNT - <span class="number">1</span>; |
| <span class="kw">const </span>T_LAST: u32 = T_BASE + T_COUNT - <span class="number">1</span>; |
| |
| <span class="comment">// Composition only occurs for `TPart`s in `U+11A8 ... U+11C2`, |
| // i.e. `T_BASE + 1 ... T_LAST`. |
| </span><span class="kw">const </span>T_FIRST: u32 = T_BASE + <span class="number">1</span>; |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>is_hangul_syllable(c: char) -> bool { |
| (c <span class="kw">as </span>u32) >= S_BASE && (c <span class="kw">as </span>u32) < (S_BASE + S_COUNT) |
| } |
| |
| <span class="comment">// Decompose a precomposed Hangul syllable |
| </span><span class="attribute">#[allow(unsafe_code)] |
| #[inline(always)] |
| </span><span class="kw">fn </span>decompose_hangul<F>(s: char, <span class="kw-2">mut </span>emit_char: F) |
| <span class="kw">where |
| </span>F: FnMut(char), |
| { |
| <span class="kw">let </span>s_index = s <span class="kw">as </span>u32 - S_BASE; |
| <span class="kw">let </span>l_index = s_index / N_COUNT; |
| <span class="kw">unsafe </span>{ |
| emit_char(char::from_u32_unchecked(L_BASE + l_index)); |
| |
| <span class="kw">let </span>v_index = (s_index % N_COUNT) / T_COUNT; |
| emit_char(char::from_u32_unchecked(V_BASE + v_index)); |
| |
| <span class="kw">let </span>t_index = s_index % T_COUNT; |
| <span class="kw">if </span>t_index > <span class="number">0 </span>{ |
| emit_char(char::from_u32_unchecked(T_BASE + t_index)); |
| } |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>hangul_decomposition_length(s: char) -> usize { |
| <span class="kw">let </span>si = s <span class="kw">as </span>u32 - S_BASE; |
| <span class="kw">let </span>ti = si % T_COUNT; |
| <span class="kw">if </span>ti > <span class="number">0 </span>{ |
| <span class="number">3 |
| </span>} <span class="kw">else </span>{ |
| <span class="number">2 |
| </span>} |
| } |
| |
| <span class="comment">// Compose a pair of Hangul Jamo |
| </span><span class="attribute">#[allow(unsafe_code)] |
| #[inline(always)] |
| #[allow(ellipsis_inclusive_range_patterns)] |
| </span><span class="kw">fn </span>compose_hangul(a: char, b: char) -> <span class="prelude-ty">Option</span><char> { |
| <span class="kw">let </span>(a, b) = (a <span class="kw">as </span>u32, b <span class="kw">as </span>u32); |
| <span class="kw">match </span>(a, b) { |
| <span class="comment">// Compose a leading consonant and a vowel together into an LV_Syllable |
| </span>(L_BASE...L_LAST, V_BASE...V_LAST) => { |
| <span class="kw">let </span>l_index = a - L_BASE; |
| <span class="kw">let </span>v_index = b - V_BASE; |
| <span class="kw">let </span>lv_index = l_index * N_COUNT + v_index * T_COUNT; |
| <span class="kw">let </span>s = S_BASE + lv_index; |
| <span class="prelude-val">Some</span>(<span class="kw">unsafe </span>{ char::from_u32_unchecked(s) }) |
| } |
| <span class="comment">// Compose an LV_Syllable and a trailing consonant into an LVT_Syllable |
| </span>(S_BASE...S_LAST, T_FIRST...T_LAST) <span class="kw">if </span>(a - S_BASE) % T_COUNT == <span class="number">0 </span>=> { |
| <span class="prelude-val">Some</span>(<span class="kw">unsafe </span>{ char::from_u32_unchecked(a + (b - T_BASE)) }) |
| } |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span><span class="kw">super</span>::compose_hangul; |
| |
| <span class="comment">// Regression test from a bugfix where we were composing an LV_Syllable with |
| // T_BASE directly. (We should only compose an LV_Syllable with a character |
| // in the range `T_BASE + 1 ... T_LAST`.) |
| </span><span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_hangul_composition() { |
| <span class="macro">assert_eq!</span>(compose_hangul(<span class="string">'\u{c8e0}'</span>, <span class="string">'\u{11a7}'</span>), <span class="prelude-val">None</span>); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="unicode_normalization" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |