| <!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/stream_safe.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>stream_safe.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> |
| </pre><pre class="rust"><code><span class="kw">use </span><span class="kw">crate</span>::lookups::{ |
| canonical_combining_class, canonical_fully_decomposed, compatibility_fully_decomposed, |
| stream_safe_trailing_nonstarters, |
| }; |
| <span class="kw">use </span><span class="kw">crate</span>::normalize::{hangul_decomposition_length, is_hangul_syllable}; |
| <span class="kw">use </span><span class="kw">crate</span>::tables::stream_safe_leading_nonstarters; |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">const </span>MAX_NONSTARTERS: usize = <span class="number">30</span>; |
| <span class="kw">const </span>COMBINING_GRAPHEME_JOINER: char = <span class="string">'\u{034F}'</span>; |
| |
| <span class="doccomment">/// UAX15-D4: This iterator keeps track of how many non-starters there have been |
| /// since the last starter in *NFKD* and will emit a Combining Grapheme Joiner |
| /// (U+034F) if the count exceeds 30. |
| </span><span class="kw">pub struct </span>StreamSafe<I> { |
| iter: I, |
| nonstarter_count: usize, |
| buffer: <span class="prelude-ty">Option</span><char>, |
| } |
| |
| <span class="kw">impl</span><I> StreamSafe<I> { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>new(iter: I) -> <span class="self">Self </span>{ |
| <span class="self">Self </span>{ |
| iter, |
| nonstarter_count: <span class="number">0</span>, |
| buffer: <span class="prelude-val">None</span>, |
| } |
| } |
| } |
| |
| <span class="kw">impl</span><I: Iterator<Item = char>> Iterator <span class="kw">for </span>StreamSafe<I> { |
| <span class="kw">type </span>Item = char; |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>next(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><char> { |
| <span class="kw">let </span>next_ch = <span class="kw">match </span><span class="self">self</span>.buffer.take().or_else(|| <span class="self">self</span>.iter.next()) { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>(c) => c, |
| }; |
| <span class="kw">let </span>d = classify_nonstarters(next_ch); |
| <span class="kw">if </span><span class="self">self</span>.nonstarter_count + d.leading_nonstarters > MAX_NONSTARTERS { |
| <span class="comment">// Since we're emitting a CGJ, the suffix of the emitted string in NFKD has no trailing |
| // nonstarters, so we can reset the counter to zero. Put `next_ch` back into the |
| // iterator (via `self.buffer`), and we'll reclassify it next iteration. |
| </span><span class="self">self</span>.nonstarter_count = <span class="number">0</span>; |
| <span class="self">self</span>.buffer = <span class="prelude-val">Some</span>(next_ch); |
| <span class="kw">return </span><span class="prelude-val">Some</span>(COMBINING_GRAPHEME_JOINER); |
| } |
| |
| <span class="comment">// Is the character all nonstarters in NFKD? If so, increment our counter of contiguous |
| // nonstarters in NKFD. |
| </span><span class="kw">if </span>d.leading_nonstarters == d.decomposition_len { |
| <span class="self">self</span>.nonstarter_count += d.decomposition_len; |
| } |
| <span class="comment">// Otherwise, reset the counter to the decomposition's number of trailing nonstarters. |
| </span><span class="kw">else </span>{ |
| <span class="self">self</span>.nonstarter_count = d.trailing_nonstarters; |
| } |
| <span class="prelude-val">Some</span>(next_ch) |
| } |
| } |
| |
| <span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">struct </span>Decomposition { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) leading_nonstarters: usize, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) trailing_nonstarters: usize, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) decomposition_len: usize, |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">fn </span>classify_nonstarters(c: char) -> Decomposition { |
| <span class="comment">// As usual, fast path for ASCII (which is always a starter) |
| </span><span class="kw">if </span>c <= <span class="string">'\x7f' </span>{ |
| <span class="kw">return </span>Decomposition { |
| leading_nonstarters: <span class="number">0</span>, |
| trailing_nonstarters: <span class="number">0</span>, |
| decomposition_len: <span class="number">1</span>, |
| }; |
| } |
| <span class="comment">// Next, special case Hangul, since it's not handled by our tables. |
| </span><span class="kw">if </span>is_hangul_syllable(c) { |
| <span class="kw">return </span>Decomposition { |
| leading_nonstarters: <span class="number">0</span>, |
| trailing_nonstarters: <span class="number">0</span>, |
| decomposition_len: hangul_decomposition_length(c), |
| }; |
| } |
| <span class="kw">let </span>decomp = compatibility_fully_decomposed(c).or_else(|| canonical_fully_decomposed(c)); |
| <span class="kw">match </span>decomp { |
| <span class="prelude-val">Some</span>(decomp) => Decomposition { |
| leading_nonstarters: stream_safe_leading_nonstarters(c), |
| trailing_nonstarters: stream_safe_trailing_nonstarters(c), |
| decomposition_len: decomp.len(), |
| }, |
| <span class="prelude-val">None </span>=> { |
| <span class="kw">let </span>is_nonstarter = canonical_combining_class(c) != <span class="number">0</span>; |
| <span class="kw">let </span>nonstarter = <span class="kw">if </span>is_nonstarter { <span class="number">1 </span>} <span class="kw">else </span>{ <span class="number">0 </span>}; |
| Decomposition { |
| leading_nonstarters: nonstarter, |
| trailing_nonstarters: nonstarter, |
| decomposition_len: <span class="number">1</span>, |
| } |
| } |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use super</span>::{classify_nonstarters, StreamSafe}; |
| <span class="kw">use </span><span class="kw">crate</span>::lookups::canonical_combining_class; |
| <span class="kw">use </span><span class="kw">crate</span>::normalize::decompose_compatible; |
| |
| <span class="attribute">#[cfg(not(feature = <span class="string">"std"</span>))] |
| </span><span class="kw">use </span><span class="kw">crate</span>::no_std_prelude::<span class="kw-2">*</span>; |
| |
| <span class="kw">use </span>core::char; |
| |
| <span class="kw">fn </span>stream_safe(s: <span class="kw-2">&</span>str) -> String { |
| StreamSafe::new(s.chars()).collect() |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_simple() { |
| <span class="kw">let </span>technically_okay = <span class="string">"Da\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}ngerzone"</span>; |
| <span class="macro">assert_eq!</span>(stream_safe(technically_okay), technically_okay); |
| |
| <span class="kw">let </span>too_much = <span class="string">"Da\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}\u{032e}ngerzone"</span>; |
| <span class="kw">let </span>fixed_it = <span class="string">"Da\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}\u{034f}\u{032e}ngerzone"</span>; |
| <span class="macro">assert_eq!</span>(stream_safe(too_much), fixed_it); |
| |
| <span class="kw">let </span>woah_nelly = <span class="string">"Da\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}\u{032e}\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}\u{032e}ngerzone"</span>; |
| <span class="kw">let </span>its_cool = <span class="string">"Da\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{031d}\u{034f}\u{032e}\u{0300}\u{0301}\u{0302}\u{0303}\u{0304}\u{0305}\u{0306}\u{0307}\u{0308}\u{0309}\u{030a}\u{030b}\u{030c}\u{030d}\u{030e}\u{030f}\u{0310}\u{0311}\u{0312}\u{0313}\u{0314}\u{0315}\u{0316}\u{0317}\u{0318}\u{0319}\u{031a}\u{031b}\u{031c}\u{034f}\u{031d}\u{032e}ngerzone"</span>; |
| <span class="macro">assert_eq!</span>(stream_safe(woah_nelly), its_cool); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_all_nonstarters() { |
| <span class="kw">let </span>s = <span class="string">"\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}\u{0300}"</span>; |
| <span class="kw">let </span>expected = <span class="string">"\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{034F}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}\u{300}"</span>; |
| <span class="macro">assert_eq!</span>(stream_safe(s), expected); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_classify_nonstarters() { |
| <span class="comment">// Highest character in the `compat_fully_decomp` table is 2FA1D |
| </span><span class="kw">for </span>ch <span class="kw">in </span><span class="number">0</span>..<span class="number">0x2FA1E </span>{ |
| <span class="kw">let </span>ch = <span class="kw">match </span>char::from_u32(ch) { |
| <span class="prelude-val">Some</span>(c) => c, |
| <span class="prelude-val">None </span>=> <span class="kw">continue</span>, |
| }; |
| <span class="kw">let </span>c = classify_nonstarters(ch); |
| <span class="kw">let </span><span class="kw-2">mut </span>s = Vec::new(); |
| decompose_compatible(ch, |c| s.push(c)); |
| |
| <span class="macro">assert_eq!</span>(s.len(), c.decomposition_len); |
| |
| <span class="kw">let </span>num_leading = s |
| .iter() |
| .take_while(|<span class="kw-2">&</span>c| canonical_combining_class(<span class="kw-2">*</span>c) != <span class="number">0</span>) |
| .count(); |
| <span class="kw">let </span>num_trailing = s |
| .iter() |
| .rev() |
| .take_while(|<span class="kw-2">&</span>c| canonical_combining_class(<span class="kw-2">*</span>c) != <span class="number">0</span>) |
| .count(); |
| |
| <span class="macro">assert_eq!</span>(num_leading, c.leading_nonstarters); |
| <span class="macro">assert_eq!</span>(num_trailing, c.trailing_nonstarters); |
| } |
| } |
| } |
| </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> |