| <!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 `src/lib.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>lib.rs - 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="../../light.css" id="themeStyle"><link rel="stylesheet" type="text/css" href="../../dark.css" disabled ><link rel="stylesheet" type="text/css" href="../../ayu.css" disabled ><script id="default-settings"></script><script src="../../storage.js"></script><script src="../../crates.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="shortcut icon" href="https://unicode-rs.github.io/unicode-rs_sm.png"><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" role="button">☰</div><a href='../../unicode_segmentation/index.html'><div class='logo-container'><img src='https://unicode-rs.github.io/unicode-rs_sm.png' alt='logo'></div></a></nav><div class="theme-picker"><button id="theme-picker" aria-label="Pick another theme!" aria-haspopup="menu"><img src="../../brush.svg" width="18" height="18" alt="Pick another theme!"></button><div id="theme-choices" role="menu"></div></div><script src="../../theme.js"></script><nav class="sub"><form class="search-form"><div class="search-container"><div><select id="crate-search"><option value="All crates">All crates</option></select><input class="search-input" name="search" disabled autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"></div><button type="button" class="help-button">?</button> |
| <a id="settings-menu" href="../../settings.html"><img src="../../wheel.svg" width="18" height="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> |
| <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> |
| </pre><div class="example-wrap"><pre class="rust "> |
| <span class="comment">// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT</span> |
| <span class="comment">// file at the top-level directory of this distribution and at</span> |
| <span class="comment">// http://rust-lang.org/COPYRIGHT.</span> |
| <span class="comment">//</span> |
| <span class="comment">// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> |
| <span class="comment">// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> |
| <span class="comment">// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your</span> |
| <span class="comment">// option. This file may not be copied, modified, or distributed</span> |
| <span class="comment">// except according to those terms.</span> |
| |
| <span class="doccomment">//! Iterators which split strings on Grapheme Cluster, Word or Sentence boundaries, according</span> |
| <span class="doccomment">//! to the [Unicode Standard Annex #29](http://www.unicode.org/reports/tr29/) rules.</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! ```rust</span> |
| <span class="doccomment">//! extern crate unicode_segmentation;</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! use unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! fn main() {</span> |
| <span class="doccomment">//! let s = "a̐éö̲\r\n";</span> |
| <span class="doccomment">//! let g = UnicodeSegmentation::graphemes(s, true).collect::<Vec<&str>>();</span> |
| <span class="doccomment">//! let b: &[_] = &["a̐", "é", "ö̲", "\r\n"];</span> |
| <span class="doccomment">//! assert_eq!(g, b);</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! let s = "The quick (\"brown\") fox can't jump 32.3 feet, right?";</span> |
| <span class="doccomment">//! let w = s.unicode_words().collect::<Vec<&str>>();</span> |
| <span class="doccomment">//! let b: &[_] = &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"];</span> |
| <span class="doccomment">//! assert_eq!(w, b);</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! let s = "The quick (\"brown\") fox";</span> |
| <span class="doccomment">//! let w = s.split_word_bounds().collect::<Vec<&str>>();</span> |
| <span class="doccomment">//! let b: &[_] = &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", " ", "fox"];</span> |
| <span class="doccomment">//! assert_eq!(w, b);</span> |
| <span class="doccomment">//! }</span> |
| <span class="doccomment">//! ```</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! # no_std</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! unicode-segmentation does not depend on libstd, so it can be used in crates</span> |
| <span class="doccomment">//! with the `#![no_std]` attribute.</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! # crates.io</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! You can use this package in your project by adding the following</span> |
| <span class="doccomment">//! to your `Cargo.toml`:</span> |
| <span class="doccomment">//!</span> |
| <span class="doccomment">//! ```toml</span> |
| <span class="doccomment">//! [dependencies]</span> |
| <span class="doccomment">//! unicode-segmentation = "1.7.1"</span> |
| <span class="doccomment">//! ```</span> |
| |
| <span class="attribute">#![<span class="ident">deny</span>(<span class="ident">missing_docs</span>, <span class="ident">unsafe_code</span>)]</span> |
| <span class="attribute">#![<span class="ident">doc</span>(<span class="ident">html_logo_url</span> <span class="op">=</span> <span class="string">"https://unicode-rs.github.io/unicode-rs_sm.png"</span>, |
| <span class="ident">html_favicon_url</span> <span class="op">=</span> <span class="string">"https://unicode-rs.github.io/unicode-rs_sm.png"</span>)]</span> |
| |
| <span class="attribute">#![<span class="ident">no_std</span>]</span> |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span> |
| <span class="attribute">#[<span class="ident">macro_use</span>]</span> |
| <span class="kw">extern</span> <span class="kw">crate</span> <span class="ident">std</span>; |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span> |
| <span class="attribute">#[<span class="ident">macro_use</span>]</span> |
| <span class="kw">extern</span> <span class="kw">crate</span> <span class="ident">quickcheck</span>; |
| |
| <span class="kw">pub</span> <span class="kw">use</span> <span class="ident">grapheme</span>::{<span class="ident">Graphemes</span>, <span class="ident">GraphemeIndices</span>}; |
| <span class="kw">pub</span> <span class="kw">use</span> <span class="ident">grapheme</span>::{<span class="ident">GraphemeCursor</span>, <span class="ident">GraphemeIncomplete</span>}; |
| <span class="kw">pub</span> <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">UNICODE_VERSION</span>; |
| <span class="kw">pub</span> <span class="kw">use</span> <span class="ident">word</span>::{<span class="ident">UWordBounds</span>, <span class="ident">UWordBoundIndices</span>, <span class="ident">UnicodeWords</span>, <span class="ident">UnicodeWordIndices</span>}; |
| <span class="kw">pub</span> <span class="kw">use</span> <span class="ident">sentence</span>::{<span class="ident">USentenceBounds</span>, <span class="ident">USentenceBoundIndices</span>, <span class="ident">UnicodeSentences</span>}; |
| |
| <span class="kw">mod</span> <span class="ident">grapheme</span>; |
| <span class="kw">mod</span> <span class="ident">tables</span>; |
| <span class="kw">mod</span> <span class="ident">word</span>; |
| <span class="kw">mod</span> <span class="ident">sentence</span>; |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span> |
| <span class="kw">mod</span> <span class="ident">test</span>; |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span> |
| <span class="kw">mod</span> <span class="ident">testdata</span>; |
| |
| <span class="doccomment">/// Methods for segmenting strings according to</span> |
| <span class="doccomment">/// [Unicode Standard Annex #29](http://www.unicode.org/reports/tr29/).</span> |
| <span class="kw">pub</span> <span class="kw">trait</span> <span class="ident">UnicodeSegmentation</span> { |
| <span class="doccomment">/// Returns an iterator over the [grapheme clusters][graphemes] of `self`.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// [graphemes]: http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// If `is_extended` is true, the iterator is over the</span> |
| <span class="doccomment">/// *extended grapheme clusters*;</span> |
| <span class="doccomment">/// otherwise, the iterator is over the *legacy grapheme clusters*.</span> |
| <span class="doccomment">/// [UAX#29](http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries)</span> |
| <span class="doccomment">/// recommends extended grapheme cluster boundaries for general processing.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Examples</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let gr1 = UnicodeSegmentation::graphemes("a\u{310}e\u{301}o\u{308}\u{332}", true)</span> |
| <span class="doccomment">/// .collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["a\u{310}", "e\u{301}", "o\u{308}\u{332}"];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&gr1[..], b);</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// let gr2 = UnicodeSegmentation::graphemes("a\r\nb🇷🇺🇸🇹", true).collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["a", "\r\n", "b", "🇷🇺", "🇸🇹"];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&gr2[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">graphemes</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>, <span class="ident">is_extended</span>: <span class="ident">bool</span>) <span class="op">-</span><span class="op">></span> <span class="ident">Graphemes</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over the grapheme clusters of `self` and their</span> |
| <span class="doccomment">/// byte offsets. See `graphemes()` for more information.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Examples</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let gr_inds = UnicodeSegmentation::grapheme_indices("a̐éö̲\r\n", true)</span> |
| <span class="doccomment">/// .collect::<Vec<(usize, &str)>>();</span> |
| <span class="doccomment">/// let b: &[_] = &[(0, "a̐"), (3, "é"), (6, "ö̲"), (11, "\r\n")];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&gr_inds[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">grapheme_indices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>, <span class="ident">is_extended</span>: <span class="ident">bool</span>) <span class="op">-</span><span class="op">></span> <span class="ident">GraphemeIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over the words of `self`, separated on</span> |
| <span class="doccomment">/// [UAX#29 word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// Here, "words" are just those substrings which, after splitting on</span> |
| <span class="doccomment">/// UAX#29 word boundaries, contain any alphanumeric characters. That is, the</span> |
| <span class="doccomment">/// substring must contain at least one character with the</span> |
| <span class="doccomment">/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)</span> |
| <span class="doccomment">/// property, or with</span> |
| <span class="doccomment">/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let uws = "The quick (\"brown\") fox can't jump 32.3 feet, right?";</span> |
| <span class="doccomment">/// let uw1 = uws.unicode_words().collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&uw1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">unicode_words</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeWords</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over the words of `self`, separated on</span> |
| <span class="doccomment">/// [UAX#29 word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries), and their</span> |
| <span class="doccomment">/// offsets.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// Here, "words" are just those substrings which, after splitting on</span> |
| <span class="doccomment">/// UAX#29 word boundaries, contain any alphanumeric characters. That is, the</span> |
| <span class="doccomment">/// substring must contain at least one character with the</span> |
| <span class="doccomment">/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)</span> |
| <span class="doccomment">/// property, or with</span> |
| <span class="doccomment">/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let uwis = "The quick (\"brown\") fox can't jump 32.3 feet, right?";</span> |
| <span class="doccomment">/// let uwi1 = uwis.unicode_word_indices().collect::<Vec<(usize, &str)>>();</span> |
| <span class="doccomment">/// let b: &[_] = &[(0, "The"), (4, "quick"), (12, "brown"), (20, "fox"), (24, "can't"),</span> |
| <span class="doccomment">/// (30, "jump"), (35, "32.3"), (40, "feet"), (46, "right")];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&uwi1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">unicode_word_indices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeWordIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over substrings of `self` separated on</span> |
| <span class="doccomment">/// [UAX#29 word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// The concatenation of the substrings returned by this function is just the original string.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let swu1 = "The quick (\"brown\") fox".split_word_bounds().collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", " ", "fox"];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&swu1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">split_word_bounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over substrings of `self`, split on UAX#29 word boundaries,</span> |
| <span class="doccomment">/// and their offsets. See `split_word_bounds()` for more information.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let swi1 = "Brr, it's 29.3°F!".split_word_bound_indices().collect::<Vec<(usize, &str)>>();</span> |
| <span class="doccomment">/// let b: &[_] = &[(0, "Brr"), (3, ","), (4, " "), (5, "it's"), (9, " "), (10, "29.3"),</span> |
| <span class="doccomment">/// (14, "°"), (16, "F"), (17, "!")];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&swi1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">split_word_bound_indices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UWordBoundIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over substrings of `self` separated on</span> |
| <span class="doccomment">/// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// Here, "sentences" are just those substrings which, after splitting on</span> |
| <span class="doccomment">/// UAX#29 sentence boundaries, contain any alphanumeric characters. That is, the</span> |
| <span class="doccomment">/// substring must contain at least one character with the</span> |
| <span class="doccomment">/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)</span> |
| <span class="doccomment">/// property, or with</span> |
| <span class="doccomment">/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let uss = "Mr. Fox jumped. [...] The dog was too lazy.";</span> |
| <span class="doccomment">/// let us1 = uss.unicode_sentences().collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["Mr. ", "Fox jumped. ", "The dog was too lazy."];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&us1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">unicode_sentences</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeSentences</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over substrings of `self` separated on</span> |
| <span class="doccomment">/// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// The concatenation of the substrings returned by this function is just the original string.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let ssbs = "Mr. Fox jumped. [...] The dog was too lazy.";</span> |
| <span class="doccomment">/// let ssb1 = ssbs.split_sentence_bounds().collect::<Vec<&str>>();</span> |
| <span class="doccomment">/// let b: &[_] = &["Mr. ", "Fox jumped. ", "[...] ", "The dog was too lazy."];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&ssb1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">split_sentence_bounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">USentenceBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| |
| <span class="doccomment">/// Returns an iterator over substrings of `self`, split on UAX#29 sentence boundaries,</span> |
| <span class="doccomment">/// and their offsets. See `split_sentence_bounds()` for more information.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// # Example</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```</span> |
| <span class="doccomment">/// # use self::unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let ssis = "Mr. Fox jumped. [...] The dog was too lazy.";</span> |
| <span class="doccomment">/// let ssi1 = ssis.split_sentence_bound_indices().collect::<Vec<(usize, &str)>>();</span> |
| <span class="doccomment">/// let b: &[_] = &[(0, "Mr. "), (4, "Fox jumped. "), (16, "[...] "),</span> |
| <span class="doccomment">/// (22, "The dog was too lazy.")];</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// assert_eq!(&ssi1[..], b);</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">fn</span> <span class="ident">split_sentence_bound_indices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>(<span class="kw-2">&</span><span class="lifetime">'a</span> <span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">USentenceBoundIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>; |
| } |
| |
| <span class="kw">impl</span> <span class="ident">UnicodeSegmentation</span> <span class="kw">for</span> <span class="ident">str</span> { |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">graphemes</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">is_extended</span>: <span class="ident">bool</span>) <span class="op">-</span><span class="op">></span> <span class="ident">Graphemes</span> { |
| <span class="ident">grapheme</span>::<span class="ident">new_graphemes</span>(<span class="self">self</span>, <span class="ident">is_extended</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">grapheme_indices</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">is_extended</span>: <span class="ident">bool</span>) <span class="op">-</span><span class="op">></span> <span class="ident">GraphemeIndices</span> { |
| <span class="ident">grapheme</span>::<span class="ident">new_grapheme_indices</span>(<span class="self">self</span>, <span class="ident">is_extended</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">unicode_words</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeWords</span> { |
| <span class="ident">word</span>::<span class="ident">new_unicode_words</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">unicode_word_indices</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeWordIndices</span> { |
| <span class="ident">word</span>::<span class="ident">new_unicode_word_indices</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">split_word_bounds</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UWordBounds</span> { |
| <span class="ident">word</span>::<span class="ident">new_word_bounds</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">split_word_bound_indices</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UWordBoundIndices</span> { |
| <span class="ident">word</span>::<span class="ident">new_word_bound_indices</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">unicode_sentences</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">UnicodeSentences</span> { |
| <span class="ident">sentence</span>::<span class="ident">new_unicode_sentences</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">split_sentence_bounds</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">USentenceBounds</span> { |
| <span class="ident">sentence</span>::<span class="ident">new_sentence_bounds</span>(<span class="self">self</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">split_sentence_bound_indices</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">USentenceBoundIndices</span> { |
| <span class="ident">sentence</span>::<span class="ident">new_sentence_bound_indices</span>(<span class="self">self</span>) |
| } |
| } |
| </pre></div> |
| </section><section id="search" class="content hidden"></section><section class="footer"></section><div id="rustdoc-vars" data-root-path="../../" data-current-crate="unicode_segmentation" data-search-js="../../search-index.js"></div> |
| <script src="../../main.js"></script><script src="../../source-script.js"></script><script src="../../source-files.js"></script></body></html> |
