| <!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-segmentation-1.10.1/src/sentence.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>sentence.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_segmentation/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_segmentation/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> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| </pre><pre class="rust"><code><span class="comment">// Copyright 2012-2014 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="kw">use </span>core::cmp; |
| <span class="kw">use </span>core::iter::Filter; |
| |
| <span class="comment">// All of the logic for forward iteration over sentences |
| </span><span class="kw">mod </span>fwd { |
| <span class="kw">use </span><span class="kw">crate</span>::tables::sentence::SentenceCat; |
| <span class="kw">use </span>core::cmp; |
| |
| <span class="comment">// Describe a parsed part of source string as described in this table: |
| // https://unicode.org/reports/tr29/#Default_Sentence_Boundaries |
| </span><span class="attribute">#[derive(Clone, Copy, PartialEq, Eq)] |
| </span><span class="kw">enum </span>StatePart { |
| Sot, |
| Eot, |
| Other, |
| CR, |
| LF, |
| Sep, |
| ATerm, |
| UpperLower, |
| ClosePlus, |
| SpPlus, |
| STerm, |
| } |
| |
| <span class="attribute">#[derive(Clone, PartialEq, Eq)] |
| </span><span class="kw">struct </span>SentenceBreaksState(<span class="kw">pub </span>[StatePart; <span class="number">4</span>]); |
| |
| <span class="kw">const </span>INITIAL_STATE: SentenceBreaksState = SentenceBreaksState([ |
| StatePart::Sot, |
| StatePart::Sot, |
| StatePart::Sot, |
| StatePart::Sot, |
| ]); |
| |
| <span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>SentenceBreaks<<span class="lifetime">'a</span>> { |
| <span class="kw">pub </span>string: <span class="kw-2">&</span><span class="lifetime">'a </span>str, |
| pos: usize, |
| state: SentenceBreaksState, |
| } |
| |
| <span class="kw">impl </span>SentenceBreaksState { |
| <span class="comment">// Attempt to advance the internal state by one part |
| // Whitespace and some punctutation will be collapsed |
| </span><span class="kw">fn </span>next(<span class="kw-2">&</span><span class="self">self</span>, cat: SentenceCat) -> SentenceBreaksState { |
| <span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = <span class="self">self</span>; |
| <span class="kw">let </span>parts = <span class="kw">match </span>(parts[<span class="number">3</span>], cat) { |
| (StatePart::ClosePlus, SentenceCat::SC_Close) => parts, |
| (StatePart::SpPlus, SentenceCat::SC_Sp) => parts, |
| <span class="kw">_ </span>=> [ |
| parts[<span class="number">1</span>], |
| parts[<span class="number">2</span>], |
| parts[<span class="number">3</span>], |
| <span class="kw">match </span>cat { |
| SentenceCat::SC_CR => StatePart::CR, |
| SentenceCat::SC_LF => StatePart::LF, |
| SentenceCat::SC_Sep => StatePart::Sep, |
| SentenceCat::SC_ATerm => StatePart::ATerm, |
| SentenceCat::SC_Upper | SentenceCat::SC_Lower => StatePart::UpperLower, |
| SentenceCat::SC_Close => StatePart::ClosePlus, |
| SentenceCat::SC_Sp => StatePart::SpPlus, |
| SentenceCat::SC_STerm => StatePart::STerm, |
| <span class="kw">_ </span>=> StatePart::Other, |
| }, |
| ], |
| }; |
| SentenceBreaksState(parts) |
| } |
| |
| <span class="kw">fn </span>end(<span class="kw-2">&</span><span class="self">self</span>) -> SentenceBreaksState { |
| <span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = <span class="self">self</span>; |
| SentenceBreaksState([parts[<span class="number">1</span>], parts[<span class="number">2</span>], parts[<span class="number">3</span>], StatePart::Eot]) |
| } |
| |
| <span class="comment">// Helper function to check if state head matches a single `StatePart` |
| </span><span class="kw">fn </span>match1(<span class="kw-2">&</span><span class="self">self</span>, part: StatePart) -> bool { |
| <span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = <span class="self">self</span>; |
| part == parts[<span class="number">3</span>] |
| } |
| |
| <span class="comment">// Helper function to check if first two `StateParts` in state match |
| // the given two |
| </span><span class="kw">fn </span>match2(<span class="kw-2">&</span><span class="self">self</span>, part1: StatePart, part2: StatePart) -> bool { |
| <span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = <span class="self">self</span>; |
| part1 == parts[<span class="number">2</span>] && part2 == parts[<span class="number">3</span>] |
| } |
| } |
| |
| <span class="comment">// https://unicode.org/reports/tr29/#SB8 |
| // TODO cache this, it is currently quadratic |
| </span><span class="kw">fn </span>match_sb8(state: <span class="kw-2">&</span>SentenceBreaksState, ahead: <span class="kw-2">&</span>str) -> bool { |
| <span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = state; |
| <span class="kw">let </span><span class="kw-2">mut </span>idx = <span class="kw">if </span>parts[<span class="number">3</span>] == StatePart::SpPlus { <span class="number">2 </span>} <span class="kw">else </span>{ <span class="number">3 </span>}; |
| <span class="kw">if </span>parts[idx] == StatePart::ClosePlus { |
| idx -= <span class="number">1 |
| </span>} |
| |
| <span class="kw">if </span>parts[idx] == StatePart::ATerm { |
| <span class="kw">use </span><span class="kw">crate</span>::tables::sentence <span class="kw">as </span>se; |
| |
| <span class="kw">for </span>next_char <span class="kw">in </span>ahead.chars() { |
| <span class="comment">//( ¬(OLetter | Upper | Lower | ParaSep | SATerm) )* Lower |
| </span><span class="kw">match </span>se::sentence_category(next_char).<span class="number">2 </span>{ |
| se::SC_Lower => <span class="kw">return </span><span class="bool-val">true</span>, |
| se::SC_OLetter |
| | se::SC_Upper |
| | se::SC_Sep |
| | se::SC_CR |
| | se::SC_LF |
| | se::SC_STerm |
| | se::SC_ATerm => <span class="kw">return </span><span class="bool-val">false</span>, |
| <span class="kw">_ </span>=> <span class="kw">continue</span>, |
| } |
| } |
| } |
| |
| <span class="bool-val">false |
| </span>} |
| |
| <span class="comment">// https://unicode.org/reports/tr29/#SB8a |
| </span><span class="kw">fn </span>match_sb8a(state: <span class="kw-2">&</span>SentenceBreaksState) -> bool { |
| <span class="comment">// SATerm Close* Sp* |
| </span><span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = state; |
| <span class="kw">let </span><span class="kw-2">mut </span>idx = <span class="kw">if </span>parts[<span class="number">3</span>] == StatePart::SpPlus { <span class="number">2 </span>} <span class="kw">else </span>{ <span class="number">3 </span>}; |
| <span class="kw">if </span>parts[idx] == StatePart::ClosePlus { |
| idx -= <span class="number">1 |
| </span>} |
| parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm |
| } |
| |
| <span class="comment">// https://unicode.org/reports/tr29/#SB9 |
| </span><span class="kw">fn </span>match_sb9(state: <span class="kw-2">&</span>SentenceBreaksState) -> bool { |
| <span class="comment">// SATerm Close* |
| </span><span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = state; |
| <span class="kw">let </span>idx = <span class="kw">if </span>parts[<span class="number">3</span>] == StatePart::ClosePlus { |
| <span class="number">2 |
| </span>} <span class="kw">else </span>{ |
| <span class="number">3 |
| </span>}; |
| parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm |
| } |
| |
| <span class="comment">// https://unicode.org/reports/tr29/#SB11 |
| </span><span class="kw">fn </span>match_sb11(state: <span class="kw-2">&</span>SentenceBreaksState) -> bool { |
| <span class="comment">// SATerm Close* Sp* ParaSep? |
| </span><span class="kw">let </span><span class="kw-2">&</span>SentenceBreaksState(parts) = state; |
| <span class="kw">let </span><span class="kw-2">mut </span>idx = <span class="kw">match </span>parts[<span class="number">3</span>] { |
| StatePart::Sep | StatePart::CR | StatePart::LF => <span class="number">2</span>, |
| <span class="kw">_ </span>=> <span class="number">3</span>, |
| }; |
| |
| <span class="kw">if </span>parts[idx] == StatePart::SpPlus { |
| idx -= <span class="number">1 |
| </span>} |
| <span class="kw">if </span>parts[idx] == StatePart::ClosePlus { |
| idx -= <span class="number">1 |
| </span>} |
| |
| parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>SentenceBreaks<<span class="lifetime">'a</span>> { |
| <span class="comment">// Returns the index of the character which follows a break |
| </span><span class="kw">type </span>Item = usize; |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, <span class="prelude-ty">Option</span><usize>) { |
| <span class="kw">let </span>slen = <span class="self">self</span>.string.len(); |
| <span class="comment">// A sentence could be one character |
| </span>(cmp::min(slen, <span class="number">2</span>), <span class="prelude-val">Some</span>(slen + <span class="number">1</span>)) |
| } |
| |
| <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><usize> { |
| <span class="kw">use </span><span class="kw">crate</span>::tables::sentence <span class="kw">as </span>se; |
| |
| <span class="kw">for </span>next_char <span class="kw">in </span><span class="self">self</span>.string[<span class="self">self</span>.pos..].chars() { |
| <span class="kw">let </span>position_before = <span class="self">self</span>.pos; |
| <span class="kw">let </span>state_before = <span class="self">self</span>.state.clone(); |
| |
| <span class="kw">let </span>next_cat = se::sentence_category(next_char).<span class="number">2</span>; |
| |
| <span class="self">self</span>.pos += next_char.len_utf8(); |
| <span class="self">self</span>.state = <span class="self">self</span>.state.next(next_cat); |
| |
| <span class="kw">match </span>next_cat { |
| <span class="comment">// SB1 https://unicode.org/reports/tr29/#SB1 |
| </span><span class="kw">_ if </span>state_before.match1(StatePart::Sot) => <span class="kw">return </span><span class="prelude-val">Some</span>(position_before), |
| |
| <span class="comment">// SB2 is handled when inner iterator (chars) is finished |
| |
| // SB3 https://unicode.org/reports/tr29/#SB3 |
| </span>SentenceCat::SC_LF <span class="kw">if </span>state_before.match1(StatePart::CR) => <span class="kw">continue</span>, |
| |
| <span class="comment">// SB4 https://unicode.org/reports/tr29/#SB4 |
| </span><span class="kw">_ if </span>state_before.match1(StatePart::Sep) |
| || state_before.match1(StatePart::CR) |
| || state_before.match1(StatePart::LF) => |
| { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(position_before) |
| } |
| |
| <span class="comment">// SB5 https://unicode.org/reports/tr29/#SB5 |
| </span>SentenceCat::SC_Extend | SentenceCat::SC_Format => <span class="self">self</span>.state = state_before, |
| |
| <span class="comment">// SB6 https://unicode.org/reports/tr29/#SB6 |
| </span>SentenceCat::SC_Numeric <span class="kw">if </span>state_before.match1(StatePart::ATerm) => <span class="kw">continue</span>, |
| |
| <span class="comment">// SB7 https://unicode.org/reports/tr29/#SB7 |
| </span>SentenceCat::SC_Upper |
| <span class="kw">if </span>state_before.match2(StatePart::UpperLower, StatePart::ATerm) => |
| { |
| <span class="kw">continue |
| </span>} |
| |
| <span class="comment">// SB8 https://unicode.org/reports/tr29/#SB8 |
| </span><span class="kw">_ if </span>match_sb8(<span class="kw-2">&</span>state_before, <span class="kw-2">&</span><span class="self">self</span>.string[position_before..]) => <span class="kw">continue</span>, |
| |
| <span class="comment">// SB8a https://unicode.org/reports/tr29/#SB8a |
| </span>SentenceCat::SC_SContinue | SentenceCat::SC_STerm | SentenceCat::SC_ATerm |
| <span class="kw">if </span>match_sb8a(<span class="kw-2">&</span>state_before) => |
| { |
| <span class="kw">continue |
| </span>} |
| |
| <span class="comment">// SB9 https://unicode.org/reports/tr29/#SB9 |
| </span>SentenceCat::SC_Close |
| | SentenceCat::SC_Sp |
| | SentenceCat::SC_Sep |
| | SentenceCat::SC_CR |
| | SentenceCat::SC_LF |
| <span class="kw">if </span>match_sb9(<span class="kw-2">&</span>state_before) => |
| { |
| <span class="kw">continue |
| </span>} |
| |
| <span class="comment">// SB10 https://unicode.org/reports/tr29/#SB10 |
| </span>SentenceCat::SC_Sp |
| | SentenceCat::SC_Sep |
| | SentenceCat::SC_CR |
| | SentenceCat::SC_LF |
| <span class="kw">if </span>match_sb8a(<span class="kw-2">&</span>state_before) => |
| { |
| <span class="kw">continue |
| </span>} |
| |
| <span class="comment">// SB11 https://unicode.org/reports/tr29/#SB11 |
| </span><span class="kw">_ if </span>match_sb11(<span class="kw-2">&</span>state_before) => <span class="kw">return </span><span class="prelude-val">Some</span>(position_before), |
| |
| <span class="comment">// SB998 https://unicode.org/reports/tr29/#SB998 |
| </span><span class="kw">_ </span>=> <span class="kw">continue</span>, |
| } |
| } |
| |
| <span class="comment">// SB2 https://unicode.org/reports/tr29/#SB2 |
| </span><span class="kw">if </span><span class="self">self</span>.state.match1(StatePart::Sot) { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else if </span><span class="self">self</span>.state.match1(StatePart::Eot) { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="self">self</span>.state = <span class="self">self</span>.state.end(); |
| <span class="prelude-val">Some</span>(<span class="self">self</span>.pos) |
| } |
| } |
| } |
| |
| <span class="kw">pub fn </span>new_sentence_breaks<<span class="lifetime">'a</span>>(source: <span class="kw-2">&</span><span class="lifetime">'a </span>str) -> SentenceBreaks<<span class="lifetime">'a</span>> { |
| SentenceBreaks { |
| string: source, |
| pos: <span class="number">0</span>, |
| state: INITIAL_STATE, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// An iterator over the substrings of a string which, after splitting the string on |
| /// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries), |
| /// contain any characters with the |
| /// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic) |
| /// property, or with |
| /// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values). |
| /// |
| /// This struct is created by the [`unicode_sentences`] method on the [`UnicodeSegmentation`] |
| /// trait. See its documentation for more. |
| /// |
| /// [`unicode_sentences`]: trait.UnicodeSegmentation.html#tymethod.unicode_sentences |
| /// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>UnicodeSentences<<span class="lifetime">'a</span>> { |
| inner: Filter<USentenceBounds<<span class="lifetime">'a</span>>, <span class="kw">fn</span>(&&str) -> bool>, |
| } |
| |
| <span class="doccomment">/// External iterator for a string's |
| /// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries). |
| /// |
| /// This struct is created by the [`split_sentence_bounds`] method on the [`UnicodeSegmentation`] |
| /// trait. See its documentation for more. |
| /// |
| /// [`split_sentence_bounds`]: trait.UnicodeSegmentation.html#tymethod.split_sentence_bounds |
| /// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>USentenceBounds<<span class="lifetime">'a</span>> { |
| iter: fwd::SentenceBreaks<<span class="lifetime">'a</span>>, |
| sentence_start: <span class="prelude-ty">Option</span><usize>, |
| } |
| |
| <span class="doccomment">/// External iterator for sentence boundaries and byte offsets. |
| /// |
| /// This struct is created by the [`split_sentence_bound_indices`] method on the |
| /// [`UnicodeSegmentation`] trait. See its documentation for more. |
| /// |
| /// [`split_sentence_bound_indices`]: trait.UnicodeSegmentation.html#tymethod.split_sentence_bound_indices |
| /// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>USentenceBoundIndices<<span class="lifetime">'a</span>> { |
| start_offset: usize, |
| iter: USentenceBounds<<span class="lifetime">'a</span>>, |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>new_sentence_bounds<<span class="lifetime">'a</span>>(source: <span class="kw-2">&</span><span class="lifetime">'a </span>str) -> USentenceBounds<<span class="lifetime">'a</span>> { |
| USentenceBounds { |
| iter: fwd::new_sentence_breaks(source), |
| sentence_start: <span class="prelude-val">None</span>, |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>new_sentence_bound_indices<<span class="lifetime">'a</span>>(source: <span class="kw-2">&</span><span class="lifetime">'a </span>str) -> USentenceBoundIndices<<span class="lifetime">'a</span>> { |
| USentenceBoundIndices { |
| start_offset: source.as_ptr() <span class="kw">as </span>usize, |
| iter: new_sentence_bounds(source), |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>new_unicode_sentences<<span class="lifetime">'b</span>>(s: <span class="kw-2">&</span><span class="lifetime">'b </span>str) -> UnicodeSentences<<span class="lifetime">'b</span>> { |
| <span class="kw">use </span><span class="kw">super</span>::UnicodeSegmentation; |
| <span class="kw">use </span><span class="kw">crate</span>::tables::util::is_alphanumeric; |
| |
| <span class="kw">fn </span>has_alphanumeric(s: &&str) -> bool { |
| s.chars().any(|c| is_alphanumeric(c)) |
| } |
| <span class="kw">let </span>has_alphanumeric: <span class="kw">fn</span>(&&str) -> bool = has_alphanumeric; <span class="comment">// coerce to fn pointer |
| |
| </span>UnicodeSentences { |
| inner: s.split_sentence_bounds().filter(has_alphanumeric), |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>UnicodeSentences<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = <span class="kw-2">&</span><span class="lifetime">'a </span>str; |
| |
| <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><<span class="kw-2">&</span><span class="lifetime">'a </span>str> { |
| <span class="self">self</span>.inner.next() |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>USentenceBounds<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = <span class="kw-2">&</span><span class="lifetime">'a </span>str; |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, <span class="prelude-ty">Option</span><usize>) { |
| <span class="kw">let </span>(lower, upper) = <span class="self">self</span>.iter.size_hint(); |
| (cmp::max(<span class="number">0</span>, lower - <span class="number">1</span>), upper.map(|u| cmp::max(<span class="number">0</span>, u - <span class="number">1</span>))) |
| } |
| |
| <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><<span class="kw-2">&</span><span class="lifetime">'a </span>str> { |
| <span class="kw">if </span><span class="self">self</span>.sentence_start == <span class="prelude-val">None </span>{ |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(start_pos) = <span class="self">self</span>.iter.next() { |
| <span class="self">self</span>.sentence_start = <span class="prelude-val">Some</span>(start_pos) |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| } |
| |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(break_pos) = <span class="self">self</span>.iter.next() { |
| <span class="kw">let </span>start_pos = <span class="self">self</span>.sentence_start.unwrap(); |
| <span class="kw">let </span>sentence = <span class="kw-2">&</span><span class="self">self</span>.iter.string[start_pos..break_pos]; |
| <span class="self">self</span>.sentence_start = <span class="prelude-val">Some</span>(break_pos); |
| <span class="prelude-val">Some</span>(sentence) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>> Iterator <span class="kw">for </span>USentenceBoundIndices<<span class="lifetime">'a</span>> { |
| <span class="kw">type </span>Item = (usize, <span class="kw-2">&</span><span class="lifetime">'a </span>str); |
| |
| <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><(usize, <span class="kw-2">&</span><span class="lifetime">'a </span>str)> { |
| <span class="self">self</span>.iter |
| .next() |
| .map(|s| (s.as_ptr() <span class="kw">as </span>usize - <span class="self">self</span>.start_offset, s)) |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>size_hint(<span class="kw-2">&</span><span class="self">self</span>) -> (usize, <span class="prelude-ty">Option</span><usize>) { |
| <span class="self">self</span>.iter.size_hint() |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="unicode_segmentation" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |