| <!DOCTYPE html> |
| <html lang="en"> |
| <head> |
| <meta charset="utf-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| <meta name="generator" content="rustdoc"> |
| <meta name="description" content="Source to the Rust file `/home/travis/.cargo/registry/src/github.com-1ecc6299db9ec823/unicode-segmentation-1.2.0/src/word.rs`."> |
| <meta name="keywords" content="rust, rustlang, rust-lang"> |
| |
| <title>word.rs.html -- source</title> |
| |
| <link rel="stylesheet" type="text/css" href="../../normalize.css"> |
| <link rel="stylesheet" type="text/css" href="../../rustdoc.css"> |
| <link rel="stylesheet" type="text/css" href="../../main.css"> |
| |
| |
| <link rel="shortcut icon" href="https://unicode-rs.github.io/unicode-rs_sm.png"> |
| |
| </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"> |
| <a href='../../unicode_segmentation/index.html'><img src='https://unicode-rs.github.io/unicode-rs_sm.png' alt='logo' width='100'></a> |
| |
| </nav> |
| |
| <nav class="sub"> |
| <form class="search-form js-only"> |
| <div class="search-container"> |
| <input class="search-input" name="search" |
| autocomplete="off" |
| placeholder="Click or press ‘S’ to search, ‘?’ for more options…" |
| type="search"> |
| </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> |
| <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> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| <span id="430">430</span> |
| <span id="431">431</span> |
| <span id="432">432</span> |
| <span id="433">433</span> |
| <span id="434">434</span> |
| <span id="435">435</span> |
| <span id="436">436</span> |
| <span id="437">437</span> |
| <span id="438">438</span> |
| <span id="439">439</span> |
| <span id="440">440</span> |
| <span id="441">441</span> |
| <span id="442">442</span> |
| <span id="443">443</span> |
| <span id="444">444</span> |
| <span id="445">445</span> |
| <span id="446">446</span> |
| <span id="447">447</span> |
| <span id="448">448</span> |
| <span id="449">449</span> |
| <span id="450">450</span> |
| <span id="451">451</span> |
| <span id="452">452</span> |
| <span id="453">453</span> |
| <span id="454">454</span> |
| <span id="455">455</span> |
| <span id="456">456</span> |
| <span id="457">457</span> |
| <span id="458">458</span> |
| <span id="459">459</span> |
| <span id="460">460</span> |
| <span id="461">461</span> |
| <span id="462">462</span> |
| <span id="463">463</span> |
| <span id="464">464</span> |
| <span id="465">465</span> |
| <span id="466">466</span> |
| <span id="467">467</span> |
| <span id="468">468</span> |
| <span id="469">469</span> |
| <span id="470">470</span> |
| <span id="471">471</span> |
| <span id="472">472</span> |
| <span id="473">473</span> |
| <span id="474">474</span> |
| <span id="475">475</span> |
| <span id="476">476</span> |
| <span id="477">477</span> |
| <span id="478">478</span> |
| <span id="479">479</span> |
| <span id="480">480</span> |
| <span id="481">481</span> |
| <span id="482">482</span> |
| <span id="483">483</span> |
| <span id="484">484</span> |
| <span id="485">485</span> |
| <span id="486">486</span> |
| <span id="487">487</span> |
| <span id="488">488</span> |
| <span id="489">489</span> |
| <span id="490">490</span> |
| <span id="491">491</span> |
| <span id="492">492</span> |
| <span id="493">493</span> |
| <span id="494">494</span> |
| <span id="495">495</span> |
| <span id="496">496</span> |
| <span id="497">497</span> |
| <span id="498">498</span> |
| <span id="499">499</span> |
| <span id="500">500</span> |
| <span id="501">501</span> |
| <span id="502">502</span> |
| <span id="503">503</span> |
| <span id="504">504</span> |
| <span id="505">505</span> |
| <span id="506">506</span> |
| <span id="507">507</span> |
| <span id="508">508</span> |
| <span id="509">509</span> |
| <span id="510">510</span> |
| <span id="511">511</span> |
| <span id="512">512</span> |
| <span id="513">513</span> |
| <span id="514">514</span> |
| <span id="515">515</span> |
| <span id="516">516</span> |
| <span id="517">517</span> |
| <span id="518">518</span> |
| <span id="519">519</span> |
| <span id="520">520</span> |
| <span id="521">521</span> |
| <span id="522">522</span> |
| <span id="523">523</span> |
| <span id="524">524</span> |
| <span id="525">525</span> |
| <span id="526">526</span> |
| <span id="527">527</span> |
| <span id="528">528</span> |
| <span id="529">529</span> |
| <span id="530">530</span> |
| <span id="531">531</span> |
| <span id="532">532</span> |
| <span id="533">533</span> |
| <span id="534">534</span> |
| <span id="535">535</span> |
| <span id="536">536</span> |
| <span id="537">537</span> |
| <span id="538">538</span> |
| <span id="539">539</span> |
| <span id="540">540</span> |
| <span id="541">541</span> |
| <span id="542">542</span> |
| <span id="543">543</span> |
| <span id="544">544</span> |
| <span id="545">545</span> |
| <span id="546">546</span> |
| <span id="547">547</span> |
| <span id="548">548</span> |
| <span id="549">549</span> |
| <span id="550">550</span> |
| <span id="551">551</span> |
| <span id="552">552</span> |
| <span id="553">553</span> |
| <span id="554">554</span> |
| <span id="555">555</span> |
| <span id="556">556</span> |
| <span id="557">557</span> |
| <span id="558">558</span> |
| <span id="559">559</span> |
| <span id="560">560</span> |
| <span id="561">561</span> |
| <span id="562">562</span> |
| <span id="563">563</span> |
| <span id="564">564</span> |
| <span id="565">565</span> |
| <span id="566">566</span> |
| <span id="567">567</span> |
| <span id="568">568</span> |
| <span id="569">569</span> |
| <span id="570">570</span> |
| <span id="571">571</span> |
| <span id="572">572</span> |
| <span id="573">573</span> |
| <span id="574">574</span> |
| <span id="575">575</span> |
| <span id="576">576</span> |
| <span id="577">577</span> |
| <span id="578">578</span> |
| <span id="579">579</span> |
| <span id="580">580</span> |
| <span id="581">581</span> |
| <span id="582">582</span> |
| <span id="583">583</span> |
| <span id="584">584</span> |
| <span id="585">585</span> |
| <span id="586">586</span> |
| <span id="587">587</span> |
| <span id="588">588</span> |
| <span id="589">589</span> |
| <span id="590">590</span> |
| <span id="591">591</span> |
| <span id="592">592</span> |
| <span id="593">593</span> |
| <span id="594">594</span> |
| <span id="595">595</span> |
| <span id="596">596</span> |
| <span id="597">597</span> |
| <span id="598">598</span> |
| <span id="599">599</span> |
| <span id="600">600</span> |
| <span id="601">601</span> |
| <span id="602">602</span> |
| <span id="603">603</span> |
| <span id="604">604</span> |
| <span id="605">605</span> |
| <span id="606">606</span> |
| <span id="607">607</span> |
| <span id="608">608</span> |
| <span id="609">609</span> |
| <span id="610">610</span> |
| <span id="611">611</span> |
| <span id="612">612</span> |
| <span id="613">613</span> |
| <span id="614">614</span> |
| <span id="615">615</span> |
| <span id="616">616</span> |
| <span id="617">617</span> |
| <span id="618">618</span> |
| <span id="619">619</span> |
| <span id="620">620</span> |
| <span id="621">621</span> |
| <span id="622">622</span> |
| <span id="623">623</span> |
| <span id="624">624</span> |
| <span id="625">625</span> |
| <span id="626">626</span> |
| <span id="627">627</span> |
| <span id="628">628</span> |
| <span id="629">629</span> |
| <span id="630">630</span> |
| <span id="631">631</span> |
| <span id="632">632</span> |
| <span id="633">633</span> |
| <span id="634">634</span> |
| <span id="635">635</span> |
| <span id="636">636</span> |
| <span id="637">637</span> |
| <span id="638">638</span> |
| <span id="639">639</span> |
| <span id="640">640</span> |
| <span id="641">641</span> |
| <span id="642">642</span> |
| <span id="643">643</span> |
| <span id="644">644</span> |
| <span id="645">645</span> |
| <span id="646">646</span> |
| <span id="647">647</span> |
| <span id="648">648</span> |
| <span id="649">649</span> |
| </pre><pre class="rust "> |
| <span class="comment">// Copyright 2012-2014 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="kw">use</span> <span class="ident">core</span>::<span class="ident">cmp</span>; |
| <span class="kw">use</span> <span class="ident">core</span>::<span class="ident">iter</span>::<span class="ident">Filter</span>; |
| |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">word</span>::<span class="ident">WordCat</span>; |
| |
| <span class="doccomment">/// An iterator over the substrings of a string which, after splitting the string on</span> |
| <span class="doccomment">/// [word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries),</span> |
| <span class="doccomment">/// contain any characters 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="kw">pub</span> <span class="kw">struct</span> <span class="ident">UnicodeWords</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="ident">inner</span>: <span class="ident">Filter</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="kw">fn</span>(<span class="op">&&</span><span class="ident">str</span>) <span class="op">-></span> <span class="ident">bool</span><span class="op">></span>, |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">Iterator</span> <span class="kw">for</span> <span class="ident">UnicodeWords</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="kw">type</span> <span class="ident">Item</span> <span class="op">=</span> <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>; |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span><span class="op">></span> { <span class="self">self</span>.<span class="ident">inner</span>.<span class="ident">next</span>() } |
| } |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">DoubleEndedIterator</span> <span class="kw">for</span> <span class="ident">UnicodeWords</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next_back</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span><span class="op">></span> { <span class="self">self</span>.<span class="ident">inner</span>.<span class="ident">next_back</span>() } |
| } |
| |
| <span class="doccomment">/// External iterator for a string's</span> |
| <span class="doccomment">/// [word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries).</span> |
| <span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>)]</span> |
| <span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="ident">string</span>: <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>, |
| <span class="ident">cat</span>: <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">WordCat</span><span class="op">></span>, |
| <span class="ident">catb</span>: <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">WordCat</span><span class="op">></span>, |
| } |
| |
| <span class="doccomment">/// External iterator for word boundaries and byte offsets.</span> |
| <span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>)]</span> |
| <span class="kw">pub</span> <span class="kw">struct</span> <span class="ident">UWordBoundIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="ident">start_offset</span>: <span class="ident">usize</span>, |
| <span class="ident">iter</span>: <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span>, |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</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="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="doccomment">/// View the underlying data (the part yet to be iterated) as a slice of the original string.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```rust</span> |
| <span class="doccomment">/// # use unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let mut iter = "Hello world".split_word_bound_indices();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), "Hello world");</span> |
| <span class="doccomment">/// iter.next();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), " world");</span> |
| <span class="doccomment">/// iter.next();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), "world");</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">as_str</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span> { |
| <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">as_str</span>() |
| } |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">Iterator</span> <span class="kw">for</span> <span class="ident">UWordBoundIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="kw">type</span> <span class="ident">Item</span> <span class="op">=</span> (<span class="ident">usize</span>, <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span>(<span class="ident">usize</span>, <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>)<span class="op">></span> { |
| <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">next</span>().<span class="ident">map</span>(<span class="op">|</span><span class="ident">s</span><span class="op">|</span> (<span class="ident">s</span>.<span class="ident">as_ptr</span>() <span class="kw">as</span> <span class="ident">usize</span> <span class="op">-</span> <span class="self">self</span>.<span class="ident">start_offset</span>, <span class="ident">s</span>)) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">size_hint</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> (<span class="ident">usize</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>) { |
| <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">size_hint</span>() |
| } |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">DoubleEndedIterator</span> <span class="kw">for</span> <span class="ident">UWordBoundIndices</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next_back</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span>(<span class="ident">usize</span>, <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>)<span class="op">></span> { |
| <span class="self">self</span>.<span class="ident">iter</span>.<span class="ident">next_back</span>().<span class="ident">map</span>(<span class="op">|</span><span class="ident">s</span><span class="op">|</span> (<span class="ident">s</span>.<span class="ident">as_ptr</span>() <span class="kw">as</span> <span class="ident">usize</span> <span class="op">-</span> <span class="self">self</span>.<span class="ident">start_offset</span>, <span class="ident">s</span>)) |
| } |
| } |
| |
| <span class="comment">// state machine for word boundary rules</span> |
| <span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>,<span class="ident">Copy</span>,<span class="ident">PartialEq</span>,<span class="ident">Eq</span>,<span class="ident">Debug</span>)]</span> |
| <span class="kw">enum</span> <span class="ident">UWordBoundsState</span> { |
| <span class="ident">Start</span>, |
| <span class="ident">Letter</span>, |
| <span class="ident">HLetter</span>, |
| <span class="ident">Numeric</span>, |
| <span class="ident">Katakana</span>, |
| <span class="ident">ExtendNumLet</span>, |
| <span class="ident">Regional</span>(<span class="ident">RegionalState</span>), |
| <span class="ident">FormatExtend</span>(<span class="ident">FormatExtendType</span>), |
| <span class="ident">Zwj</span>, |
| <span class="ident">Emoji</span>, |
| } |
| |
| <span class="comment">// subtypes for FormatExtend state in UWordBoundsState</span> |
| <span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>,<span class="ident">Copy</span>,<span class="ident">PartialEq</span>,<span class="ident">Eq</span>,<span class="ident">Debug</span>)]</span> |
| <span class="kw">enum</span> <span class="ident">FormatExtendType</span> { |
| <span class="ident">AcceptAny</span>, |
| <span class="ident">AcceptNone</span>, |
| <span class="ident">RequireLetter</span>, |
| <span class="ident">RequireHLetter</span>, |
| <span class="ident">AcceptQLetter</span>, |
| <span class="ident">RequireNumeric</span>, |
| } |
| |
| <span class="attribute">#[<span class="ident">derive</span>(<span class="ident">Clone</span>,<span class="ident">Copy</span>,<span class="ident">PartialEq</span>,<span class="ident">Eq</span>,<span class="ident">Debug</span>)]</span> |
| <span class="kw">enum</span> <span class="ident">RegionalState</span> { |
| <span class="ident">Half</span>, |
| <span class="ident">Full</span>, |
| <span class="ident">Unknown</span>, |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">Iterator</span> <span class="kw">for</span> <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="kw">type</span> <span class="ident">Item</span> <span class="op">=</span> <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span>; |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">size_hint</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> (<span class="ident">usize</span>, <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span>) { |
| <span class="kw">let</span> <span class="ident">slen</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">len</span>(); |
| (<span class="ident">cmp</span>::<span class="ident">min</span>(<span class="ident">slen</span>, <span class="number">1</span>), <span class="prelude-val">Some</span>(<span class="ident">slen</span>)) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="self">self</span>::<span class="ident">UWordBoundsState</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="self">self</span>::<span class="ident">FormatExtendType</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">word</span> <span class="kw">as</span> <span class="ident">wd</span>; |
| <span class="kw">if</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">len</span>() <span class="op">==</span> <span class="number">0</span> { |
| <span class="kw">return</span> <span class="prelude-val">None</span>; |
| } |
| |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">idx</span> <span class="op">=</span> <span class="number">0</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">saveidx</span> <span class="op">=</span> <span class="number">0</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="ident">Start</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">cat</span> <span class="op">=</span> <span class="ident">wd</span>::<span class="ident">WC_Any</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">savecat</span> <span class="op">=</span> <span class="ident">wd</span>::<span class="ident">WC_Any</span>; |
| |
| <span class="comment">// Whether or not the previous category was ZWJ</span> |
| <span class="comment">// ZWJs get collapsed, so this handles precedence of WB3c over WB4</span> |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">prev_zwj</span>; |
| <span class="kw">for</span> (<span class="ident">curr</span>, <span class="ident">ch</span>) <span class="kw">in</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">char_indices</span>() { |
| <span class="ident">idx</span> <span class="op">=</span> <span class="ident">curr</span>; |
| <span class="ident">prev_zwj</span> <span class="op">=</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span>; |
| <span class="comment">// if there's a category cached, grab it</span> |
| <span class="ident">cat</span> <span class="op">=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">cat</span> { |
| <span class="prelude-val">None</span> <span class="op">=></span> <span class="ident">wd</span>::<span class="ident">word_category</span>(<span class="ident">ch</span>), |
| _ <span class="op">=></span> <span class="self">self</span>.<span class="ident">cat</span>.<span class="ident">take</span>().<span class="ident">unwrap</span>() |
| }; |
| <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| |
| <span class="comment">// handle rule WB4</span> |
| <span class="comment">// just skip all format, extend, and zwj chars</span> |
| <span class="comment">// note that Start is a special case: if there's a bunch of Format | Extend</span> |
| <span class="comment">// characters at the beginning of a block of text, dump them out as one unit.</span> |
| <span class="comment">//</span> |
| <span class="comment">// (This is not obvious from the wording of UAX#29, but if you look at the</span> |
| <span class="comment">// test cases http://www.unicode.org/Public/UNIDATA/auxiliary/WordBreakTest.txt</span> |
| <span class="comment">// then the "correct" interpretation of WB4 becomes apparent.)</span> |
| <span class="kw">if</span> <span class="ident">state</span> <span class="op">!=</span> <span class="ident">Start</span> { |
| <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Extend</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Format</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">=></span> { |
| <span class="kw">continue</span> |
| } |
| _ <span class="op">=></span> {} |
| } |
| } |
| |
| <span class="comment">// rule WB3c</span> |
| <span class="comment">// WB4 makes all ZWJs collapse into the previous state</span> |
| <span class="comment">// but you can still be in a Zwj state if you started with Zwj</span> |
| <span class="comment">//</span> |
| <span class="comment">// This means that Zwj + Extend will collapse into Zwj, which is wrong,</span> |
| <span class="comment">// since Extend has a boundary with following EBG/GAZ chars but ZWJ doesn't,</span> |
| <span class="comment">// and that rule (WB3c) has higher priority</span> |
| <span class="comment">//</span> |
| <span class="comment">// Additionally, Emoji_Base+ZWJ+(EBG/GAZ) will collapse into Emoji_Base+EBG/GAZ</span> |
| <span class="comment">// which won't have a boundary even though EB+ZWJ+GAZ should have a boundary.</span> |
| <span class="comment">//</span> |
| <span class="comment">// Thus, we separately keep track of whether or not the last character</span> |
| <span class="comment">// was a ZWJ. This is an additional bit of state tracked outside of the</span> |
| <span class="comment">// state enum; the state enum represents the last non-zwj state encountered.</span> |
| <span class="comment">// When prev_zwj is true, for the purposes of WB3c, we are in the Zwj state,</span> |
| <span class="comment">// however we are in the previous state for the purposes of all other rules.</span> |
| <span class="kw">if</span> <span class="ident">prev_zwj</span> { |
| <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Glue_After_Zwj</span> <span class="op">=></span> <span class="kw">continue</span>, |
| <span class="ident">wd</span>::<span class="ident">WC_E_Base_GAZ</span> <span class="op">=></span> { |
| <span class="ident">state</span> <span class="op">=</span> <span class="ident">Emoji</span>; |
| <span class="kw">continue</span>; |
| }, |
| _ <span class="op">=></span> () |
| } |
| } |
| <span class="comment">// Don't use `continue` in this match without updating `cat`</span> |
| <span class="ident">state</span> <span class="op">=</span> <span class="kw">match</span> <span class="ident">state</span> { |
| <span class="ident">Start</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_CR</span> <span class="op">=></span> { |
| <span class="ident">idx</span> <span class="op">+=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">get_next_cat</span>(<span class="ident">idx</span>) { |
| <span class="prelude-val">Some</span>(<span class="ident">ncat</span>) <span class="kw">if</span> <span class="ident">ncat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_LF</span> <span class="op">=></span> <span class="number">1</span>, <span class="comment">// rule WB3</span> |
| _ <span class="op">=></span> <span class="number">0</span> |
| }; |
| <span class="kw">break</span>; <span class="comment">// rule WB3a</span> |
| }, |
| <span class="ident">Start</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB5, WB6, WB9, WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB5, WB6, WB7a, WB7b, WB9, WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB8, WB10, WB12, WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13, WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a, WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Regional_Indicator</span> <span class="op">=></span> <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Half</span>), <span class="comment">// rule WB13c</span> |
| <span class="ident">wd</span>::<span class="ident">WC_LF</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Newline</span> <span class="op">=></span> <span class="kw">break</span>, <span class="comment">// rule WB3a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">=></span> <span class="ident">Zwj</span>, <span class="comment">// rule WB3c</span> |
| <span class="ident">wd</span>::<span class="ident">WC_E_Base</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_E_Base_GAZ</span> <span class="op">=></span> <span class="ident">Emoji</span>, <span class="comment">// rule WB14</span> |
| _ <span class="op">=></span> { |
| <span class="kw">if</span> <span class="kw">let</span> <span class="prelude-val">Some</span>(<span class="ident">ncat</span>) <span class="op">=</span> <span class="self">self</span>.<span class="ident">get_next_cat</span>(<span class="ident">idx</span>) { <span class="comment">// rule WB4</span> |
| <span class="kw">if</span> <span class="ident">ncat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Format</span> <span class="op">||</span> <span class="ident">ncat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Extend</span> <span class="op">||</span> <span class="ident">ncat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> { |
| <span class="ident">state</span> <span class="op">=</span> <span class="ident">FormatExtend</span>(<span class="ident">AcceptNone</span>); |
| <span class="self">self</span>.<span class="ident">cat</span> <span class="op">=</span> <span class="prelude-val">Some</span>(<span class="ident">ncat</span>); |
| <span class="kw">continue</span>; |
| } |
| } |
| <span class="kw">break</span>; <span class="comment">// rule WB999</span> |
| } |
| }, |
| <span class="ident">Zwj</span> <span class="op">=></span> { |
| <span class="comment">// We already handle WB3c above. At this point,</span> |
| <span class="comment">// the current category is not GAZ or EBG,</span> |
| <span class="comment">// or the previous character was not actually a ZWJ</span> |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| <span class="ident">Letter</span> <span class="op">|</span> <span class="ident">HLetter</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB5</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB5</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB9</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Double_Quote</span> <span class="kw">if</span> <span class="ident">state</span> <span class="op">==</span> <span class="ident">HLetter</span> <span class="op">=></span> { |
| <span class="ident">savecat</span> <span class="op">=</span> <span class="ident">cat</span>; |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireHLetter</span>) <span class="comment">// rule WB7b</span> |
| }, |
| <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="kw">if</span> <span class="ident">state</span> <span class="op">==</span> <span class="ident">HLetter</span> <span class="op">=></span> { |
| <span class="ident">FormatExtend</span>(<span class="ident">AcceptQLetter</span>) <span class="comment">// rule WB7a</span> |
| }, |
| <span class="ident">wd</span>::<span class="ident">WC_MidLetter</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_MidNumLet</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="op">=></span> { |
| <span class="ident">savecat</span> <span class="op">=</span> <span class="ident">cat</span>; |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireLetter</span>) <span class="comment">// rule WB6</span> |
| }, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Numeric</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB8</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB10</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB10</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_MidNum</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_MidNumLet</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="op">=></span> { |
| <span class="ident">savecat</span> <span class="op">=</span> <span class="ident">cat</span>; |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireNumeric</span>) <span class="comment">// rule WB12</span> |
| }, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Katakana</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">ExtendNumLet</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13b</span> |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Full</span>) <span class="op">=></span> { |
| <span class="comment">// if it reaches here we've gone too far,</span> |
| <span class="comment">// a full flag can only compose with ZWJ/Extend/Format</span> |
| <span class="comment">// proceeding it.</span> |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Half</span>) <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Regional_Indicator</span> <span class="op">=></span> <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Full</span>), <span class="comment">// rule WB13c</span> |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Regional</span>(_) <span class="op">=></span> <span class="macro">unreachable</span><span class="macro">!</span>(<span class="string">"RegionalState::Unknown should not occur on forward iteration"</span>), |
| <span class="ident">Emoji</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { <span class="comment">// rule WB14</span> |
| <span class="ident">wd</span>::<span class="ident">WC_E_Modifier</span> <span class="op">=></span> <span class="ident">state</span>, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">FormatExtend</span>(<span class="ident">t</span>) <span class="op">=></span> <span class="kw">match</span> <span class="ident">t</span> { <span class="comment">// handle FormatExtends depending on what type</span> |
| <span class="ident">RequireNumeric</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB11</span> |
| <span class="ident">RequireLetter</span> <span class="op">|</span> <span class="ident">AcceptQLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB7</span> |
| <span class="ident">RequireLetter</span> <span class="op">|</span> <span class="ident">AcceptQLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// WB7a</span> |
| <span class="ident">RequireHLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB7b</span> |
| <span class="ident">AcceptNone</span> <span class="op">|</span> <span class="ident">AcceptQLetter</span> <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; <span class="comment">// emit all the Format|Extend characters</span> |
| <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| }, |
| _ <span class="op">=></span> <span class="kw">break</span> <span class="comment">// rewind (in if statement below)</span> |
| } |
| } |
| } |
| |
| <span class="kw">if</span> <span class="kw">let</span> <span class="ident">FormatExtend</span>(<span class="ident">t</span>) <span class="op">=</span> <span class="ident">state</span> { |
| <span class="comment">// we were looking for something and didn't find it; we have to back up</span> |
| <span class="kw">if</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireLetter</span> <span class="op">||</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireHLetter</span> <span class="op">||</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireNumeric</span> { |
| <span class="ident">idx</span> <span class="op">=</span> <span class="ident">saveidx</span>; |
| <span class="ident">cat</span> <span class="op">=</span> <span class="ident">savecat</span>; |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| } |
| } |
| |
| <span class="self">self</span>.<span class="ident">cat</span> <span class="op">=</span> <span class="kw">if</span> <span class="ident">take_curr</span> { |
| <span class="ident">idx</span> <span class="op">=</span> <span class="ident">idx</span> <span class="op">+</span> <span class="self">self</span>.<span class="ident">string</span>[<span class="ident">idx</span>..].<span class="ident">chars</span>().<span class="ident">next</span>().<span class="ident">unwrap</span>().<span class="ident">len_utf8</span>(); |
| <span class="prelude-val">None</span> |
| } <span class="kw">else</span> <span class="kw">if</span> <span class="ident">take_cat</span> { |
| <span class="prelude-val">Some</span>(<span class="ident">cat</span>) |
| } <span class="kw">else</span> { |
| <span class="prelude-val">None</span> |
| }; |
| |
| <span class="kw">let</span> <span class="ident">retstr</span> <span class="op">=</span> <span class="kw-2">&</span><span class="self">self</span>.<span class="ident">string</span>[..<span class="ident">idx</span>]; |
| <span class="self">self</span>.<span class="ident">string</span> <span class="op">=</span> <span class="kw-2">&</span><span class="self">self</span>.<span class="ident">string</span>[<span class="ident">idx</span>..]; |
| <span class="prelude-val">Some</span>(<span class="ident">retstr</span>) |
| } |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> <span class="ident">DoubleEndedIterator</span> <span class="kw">for</span> <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'a</span><span class="op">></span> { |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">next_back</span>(<span class="kw-2">&</span><span class="kw-2">mut</span> <span class="self">self</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="self">self</span>::<span class="ident">UWordBoundsState</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="self">self</span>::<span class="ident">FormatExtendType</span>::<span class="kw-2">*</span>; |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">word</span> <span class="kw">as</span> <span class="ident">wd</span>; |
| <span class="kw">if</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">len</span>() <span class="op">==</span> <span class="number">0</span> { |
| <span class="kw">return</span> <span class="prelude-val">None</span>; |
| } |
| |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">idx</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">len</span>(); |
| <span class="ident">idx</span> <span class="op">-=</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">chars</span>().<span class="ident">next_back</span>().<span class="ident">unwrap</span>().<span class="ident">len_utf8</span>(); |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">previdx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="ident">Start</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">savestate</span> <span class="op">=</span> <span class="ident">Start</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">cat</span> <span class="op">=</span> <span class="ident">wd</span>::<span class="ident">WC_Any</span>; |
| |
| <span class="kw">for</span> (<span class="ident">curr</span>, <span class="ident">ch</span>) <span class="kw">in</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">char_indices</span>().<span class="ident">rev</span>() { |
| <span class="ident">previdx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="ident">idx</span> <span class="op">=</span> <span class="ident">curr</span>; |
| |
| <span class="comment">// if there's a category cached, grab it</span> |
| <span class="ident">cat</span> <span class="op">=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">catb</span> { |
| <span class="prelude-val">None</span> <span class="op">=></span> <span class="ident">wd</span>::<span class="ident">word_category</span>(<span class="ident">ch</span>), |
| _ <span class="op">=></span> <span class="self">self</span>.<span class="ident">catb</span>.<span class="ident">take</span>().<span class="ident">unwrap</span>() |
| }; |
| <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">true</span>; |
| |
| <span class="comment">// backward iterator over word boundaries. Mostly the same as the forward</span> |
| <span class="comment">// iterator, with two weirdnesses:</span> |
| <span class="comment">// (1) If we encounter a single quote in the Start state, we have to check for a</span> |
| <span class="comment">// Hebrew Letter immediately before it.</span> |
| <span class="comment">// (2) Format and Extend char handling takes some gymnastics.</span> |
| |
| <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Extend</span> |
| <span class="op">||</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Format</span> |
| <span class="op">||</span> (<span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">&&</span> <span class="ident">state</span> <span class="op">!=</span> <span class="ident">Zwj</span>) { <span class="comment">// WB3c has more priority so we should not</span> |
| <span class="comment">// fold in that case</span> |
| <span class="kw">if</span> <span class="kw">match</span> <span class="ident">state</span> { |
| <span class="ident">FormatExtend</span>(_) <span class="op">|</span> <span class="ident">Start</span> <span class="op">=></span> <span class="bool-val">false</span>, |
| _ <span class="op">=></span> <span class="bool-val">true</span> |
| } { |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">previdx</span>; |
| <span class="ident">savestate</span> <span class="op">=</span> <span class="ident">state</span>; |
| <span class="ident">state</span> <span class="op">=</span> <span class="ident">FormatExtend</span>(<span class="ident">AcceptNone</span>); |
| } |
| |
| <span class="kw">if</span> <span class="ident">state</span> <span class="op">!=</span> <span class="ident">Start</span> { |
| <span class="kw">continue</span>; |
| } |
| } <span class="kw">else</span> <span class="kw">if</span> <span class="ident">state</span> <span class="op">==</span> <span class="ident">FormatExtend</span>(<span class="ident">AcceptNone</span>) { |
| <span class="comment">// finished a scan of some Format|Extend chars, restore previous state</span> |
| <span class="ident">state</span> <span class="op">=</span> <span class="ident">savestate</span>; |
| <span class="ident">previdx</span> <span class="op">=</span> <span class="ident">saveidx</span>; |
| <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| } |
| |
| <span class="comment">// Don't use `continue` in this match without updating `catb`</span> |
| <span class="ident">state</span> <span class="op">=</span> <span class="kw">match</span> <span class="ident">state</span> { |
| <span class="ident">Start</span> <span class="op">|</span> <span class="ident">FormatExtend</span>(<span class="ident">AcceptAny</span>) <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB5, WB7, WB10, WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB5, WB7, WB7c, WB10, WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB8, WB9, WB11, WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13, WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Regional_Indicator</span> <span class="op">=></span> <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Unknown</span>), <span class="comment">// rule WB13c</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Glue_After_Zwj</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_E_Base_GAZ</span> <span class="op">=></span> <span class="ident">Zwj</span>, <span class="comment">// rule WB3c</span> |
| <span class="comment">// rule WB4:</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Extend</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Format</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">=></span> <span class="ident">FormatExtend</span>(<span class="ident">AcceptAny</span>), |
| <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="op">=></span> { |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">idx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">AcceptQLetter</span>) <span class="comment">// rule WB7a</span> |
| }, |
| <span class="ident">wd</span>::<span class="ident">WC_E_Modifier</span> <span class="op">=></span> <span class="ident">Emoji</span>, <span class="comment">// rule WB14</span> |
| <span class="ident">wd</span>::<span class="ident">WC_CR</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_LF</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Newline</span> <span class="op">=></span> { |
| <span class="kw">if</span> <span class="ident">state</span> <span class="op">==</span> <span class="ident">Start</span> { |
| <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_LF</span> { |
| <span class="ident">idx</span> <span class="op">-=</span> <span class="kw">match</span> <span class="self">self</span>.<span class="ident">get_prev_cat</span>(<span class="ident">idx</span>) { |
| <span class="prelude-val">Some</span>(<span class="ident">pcat</span>) <span class="kw">if</span> <span class="ident">pcat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_CR</span> <span class="op">=></span> <span class="number">1</span>, <span class="comment">// rule WB3</span> |
| _ <span class="op">=></span> <span class="number">0</span> |
| }; |
| } |
| } <span class="kw">else</span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| } |
| <span class="kw">break</span>; <span class="comment">// rule WB3a</span> |
| }, |
| _ <span class="op">=></span> <span class="kw">break</span> <span class="comment">// rule WB999</span> |
| }, |
| <span class="ident">Zwj</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { <span class="comment">// rule WB3c</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">=></span> { |
| <span class="ident">FormatExtend</span>(<span class="ident">AcceptAny</span>) |
| } |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Letter</span> <span class="op">|</span> <span class="ident">HLetter</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB5</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB5</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB10</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Double_Quote</span> <span class="kw">if</span> <span class="ident">state</span> <span class="op">==</span> <span class="ident">HLetter</span> <span class="op">=></span> { |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">previdx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireHLetter</span>) <span class="comment">// rule WB7c</span> |
| }, |
| <span class="ident">wd</span>::<span class="ident">WC_MidLetter</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_MidNumLet</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="op">=></span> { |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">previdx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireLetter</span>) <span class="comment">// rule WB7</span> |
| }, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Numeric</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB8</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB9</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB9</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13b</span> |
| <span class="ident">wd</span>::<span class="ident">WC_MidNum</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_MidNumLet</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_Single_Quote</span> <span class="op">=></span> { |
| <span class="ident">saveidx</span> <span class="op">=</span> <span class="ident">previdx</span>; |
| <span class="ident">FormatExtend</span>(<span class="ident">RequireNumeric</span>) <span class="comment">// rule WB11</span> |
| }, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Katakana</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13b</span> |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">ExtendNumLet</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="ident">wd</span>::<span class="ident">WC_ExtendNumLet</span> <span class="op">=></span> <span class="ident">ExtendNumLet</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB13a</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Katakana</span> <span class="op">=></span> <span class="ident">Katakana</span>, <span class="comment">// rule WB13a</span> |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Regional</span>(<span class="kw-2">mut</span> <span class="ident">regional_state</span>) <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { |
| <span class="comment">// rule WB13c</span> |
| <span class="ident">wd</span>::<span class="ident">WC_Regional_Indicator</span> <span class="op">=></span> { |
| <span class="kw">if</span> <span class="ident">regional_state</span> <span class="op">==</span> <span class="ident">RegionalState</span>::<span class="ident">Unknown</span> { |
| <span class="kw">let</span> <span class="ident">count</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">string</span>[..<span class="ident">previdx</span>] |
| .<span class="ident">chars</span>().<span class="ident">rev</span>() |
| .<span class="ident">map</span>(<span class="op">|</span><span class="ident">c</span><span class="op">|</span> <span class="ident">wd</span>::<span class="ident">word_category</span>(<span class="ident">c</span>)) |
| .<span class="ident">filter</span>(<span class="op">|</span><span class="kw-2">&</span><span class="ident">c</span><span class="op">|</span> <span class="op">!</span> (<span class="ident">c</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ZWJ</span> <span class="op">||</span> <span class="ident">c</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Extend</span> <span class="op">||</span> <span class="ident">c</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Format</span>)) |
| .<span class="ident">take_while</span>(<span class="op">|</span><span class="kw-2">&</span><span class="ident">c</span><span class="op">|</span> <span class="ident">c</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Regional_Indicator</span>) |
| .<span class="ident">count</span>(); |
| <span class="ident">regional_state</span> <span class="op">=</span> <span class="kw">if</span> <span class="ident">count</span> <span class="op">%</span> <span class="number">2</span> <span class="op">==</span> <span class="number">0</span> { |
| <span class="ident">RegionalState</span>::<span class="ident">Full</span> |
| } <span class="kw">else</span> { |
| <span class="ident">RegionalState</span>::<span class="ident">Half</span> |
| }; |
| } |
| <span class="kw">if</span> <span class="ident">regional_state</span> <span class="op">==</span> <span class="ident">RegionalState</span>::<span class="ident">Full</span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } <span class="kw">else</span> { |
| <span class="ident">Regional</span>(<span class="ident">RegionalState</span>::<span class="ident">Full</span>) |
| } |
| } |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">Emoji</span> <span class="op">=></span> <span class="kw">match</span> <span class="ident">cat</span> { <span class="comment">// rule WB14</span> |
| <span class="ident">wd</span>::<span class="ident">WC_E_Base</span> <span class="op">|</span> <span class="ident">wd</span>::<span class="ident">WC_E_Base_GAZ</span> <span class="op">=></span> { |
| <span class="ident">Zwj</span> |
| }, |
| _ <span class="op">=></span> { |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="kw">break</span>; |
| } |
| }, |
| <span class="ident">FormatExtend</span>(<span class="ident">t</span>) <span class="op">=></span> <span class="kw">match</span> <span class="ident">t</span> { |
| <span class="ident">RequireNumeric</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Numeric</span> <span class="op">=></span> <span class="ident">Numeric</span>, <span class="comment">// rule WB12</span> |
| <span class="ident">RequireLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_ALetter</span> <span class="op">=></span> <span class="ident">Letter</span>, <span class="comment">// rule WB6</span> |
| <span class="ident">RequireLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB6</span> |
| <span class="ident">AcceptQLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB7a</span> |
| <span class="ident">RequireHLetter</span> <span class="kw">if</span> <span class="ident">cat</span> <span class="op">==</span> <span class="ident">wd</span>::<span class="ident">WC_Hebrew_Letter</span> <span class="op">=></span> <span class="ident">HLetter</span>, <span class="comment">// rule WB7b</span> |
| _ <span class="op">=></span> <span class="kw">break</span> <span class="comment">// backtrack will happens</span> |
| } |
| } |
| } |
| |
| <span class="kw">if</span> <span class="kw">let</span> <span class="ident">FormatExtend</span>(<span class="ident">t</span>) <span class="op">=</span> <span class="ident">state</span> { |
| <span class="comment">// if we required something but didn't find it, backtrack</span> |
| <span class="kw">if</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireLetter</span> <span class="op">||</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireHLetter</span> <span class="op">||</span> |
| <span class="ident">t</span> <span class="op">==</span> <span class="ident">RequireNumeric</span> <span class="op">||</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">AcceptNone</span> <span class="op">||</span> <span class="ident">t</span> <span class="op">==</span> <span class="ident">AcceptQLetter</span> { |
| <span class="ident">previdx</span> <span class="op">=</span> <span class="ident">saveidx</span>; |
| <span class="ident">take_cat</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| <span class="ident">take_curr</span> <span class="op">=</span> <span class="bool-val">false</span>; |
| } |
| } |
| |
| <span class="self">self</span>.<span class="ident">catb</span> <span class="op">=</span> <span class="kw">if</span> <span class="ident">take_curr</span> { |
| <span class="prelude-val">None</span> |
| } <span class="kw">else</span> { |
| <span class="ident">idx</span> <span class="op">=</span> <span class="ident">previdx</span>; |
| <span class="kw">if</span> <span class="ident">take_cat</span> { |
| <span class="prelude-val">Some</span>(<span class="ident">cat</span>) |
| } <span class="kw">else</span> { |
| <span class="prelude-val">None</span> |
| } |
| }; |
| |
| <span class="kw">let</span> <span class="ident">retstr</span> <span class="op">=</span> <span class="kw-2">&</span><span class="self">self</span>.<span class="ident">string</span>[<span class="ident">idx</span>..]; |
| <span class="self">self</span>.<span class="ident">string</span> <span class="op">=</span> <span class="kw-2">&</span><span class="self">self</span>.<span class="ident">string</span>[..<span class="ident">idx</span>]; |
| <span class="prelude-val">Some</span>(<span class="ident">retstr</span>) |
| } |
| } |
| |
| <span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</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="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="doccomment">/// View the underlying data (the part yet to be iterated) as a slice of the original string.</span> |
| <span class="doccomment">///</span> |
| <span class="doccomment">/// ```rust</span> |
| <span class="doccomment">/// # use unicode_segmentation::UnicodeSegmentation;</span> |
| <span class="doccomment">/// let mut iter = "Hello world".split_word_bounds();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), "Hello world");</span> |
| <span class="doccomment">/// iter.next();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), " world");</span> |
| <span class="doccomment">/// iter.next();</span> |
| <span class="doccomment">/// assert_eq!(iter.as_str(), "world");</span> |
| <span class="doccomment">/// ```</span> |
| <span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">as_str</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-></span> <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">str</span> { |
| <span class="self">self</span>.<span class="ident">string</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">get_next_cat</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">idx</span>: <span class="ident">usize</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">WordCat</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">word</span> <span class="kw">as</span> <span class="ident">wd</span>; |
| <span class="kw">let</span> <span class="ident">nidx</span> <span class="op">=</span> <span class="ident">idx</span> <span class="op">+</span> <span class="self">self</span>.<span class="ident">string</span>[<span class="ident">idx</span>..].<span class="ident">chars</span>().<span class="ident">next</span>().<span class="ident">unwrap</span>().<span class="ident">len_utf8</span>(); |
| <span class="kw">if</span> <span class="ident">nidx</span> <span class="op"><</span> <span class="self">self</span>.<span class="ident">string</span>.<span class="ident">len</span>() { |
| <span class="kw">let</span> <span class="ident">nch</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">string</span>[<span class="ident">nidx</span>..].<span class="ident">chars</span>().<span class="ident">next</span>().<span class="ident">unwrap</span>(); |
| <span class="prelude-val">Some</span>(<span class="ident">wd</span>::<span class="ident">word_category</span>(<span class="ident">nch</span>)) |
| } <span class="kw">else</span> { |
| <span class="prelude-val">None</span> |
| } |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">get_prev_cat</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">idx</span>: <span class="ident">usize</span>) <span class="op">-></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">WordCat</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">word</span> <span class="kw">as</span> <span class="ident">wd</span>; |
| <span class="kw">if</span> <span class="ident">idx</span> <span class="op">></span> <span class="number">0</span> { |
| <span class="kw">let</span> <span class="ident">nch</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">string</span>[..<span class="ident">idx</span>].<span class="ident">chars</span>().<span class="ident">next_back</span>().<span class="ident">unwrap</span>(); |
| <span class="prelude-val">Some</span>(<span class="ident">wd</span>::<span class="ident">word_category</span>(<span class="ident">nch</span>)) |
| } <span class="kw">else</span> { |
| <span class="prelude-val">None</span> |
| } |
| } |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">new_word_bounds</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span>(<span class="ident">s</span>: <span class="kw-2">&</span><span class="lifetime">'b</span> <span class="ident">str</span>) <span class="op">-></span> <span class="ident">UWordBounds</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span> { |
| <span class="ident">UWordBounds</span> { <span class="ident">string</span>: <span class="ident">s</span>, <span class="ident">cat</span>: <span class="prelude-val">None</span>, <span class="ident">catb</span>: <span class="prelude-val">None</span> } |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">new_word_bound_indices</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span>(<span class="ident">s</span>: <span class="kw-2">&</span><span class="lifetime">'b</span> <span class="ident">str</span>) <span class="op">-></span> <span class="ident">UWordBoundIndices</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span> { |
| <span class="ident">UWordBoundIndices</span> { <span class="ident">start_offset</span>: <span class="ident">s</span>.<span class="ident">as_ptr</span>() <span class="kw">as</span> <span class="ident">usize</span>, <span class="ident">iter</span>: <span class="ident">new_word_bounds</span>(<span class="ident">s</span>) } |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">new_unicode_words</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span>(<span class="ident">s</span>: <span class="kw-2">&</span><span class="lifetime">'b</span> <span class="ident">str</span>) <span class="op">-></span> <span class="ident">UnicodeWords</span><span class="op"><</span><span class="lifetime">'b</span><span class="op">></span> { |
| <span class="kw">use</span> <span class="kw">super</span>::<span class="ident">UnicodeSegmentation</span>; |
| <span class="kw">use</span> <span class="ident">tables</span>::<span class="ident">util</span>::<span class="ident">is_alphanumeric</span>; |
| |
| <span class="kw">fn</span> <span class="ident">has_alphanumeric</span>(<span class="ident">s</span>: <span class="op">&&</span><span class="ident">str</span>) <span class="op">-></span> <span class="ident">bool</span> { <span class="ident">s</span>.<span class="ident">chars</span>().<span class="ident">any</span>(<span class="op">|</span><span class="ident">c</span><span class="op">|</span> <span class="ident">is_alphanumeric</span>(<span class="ident">c</span>)) } |
| <span class="kw">let</span> <span class="ident">has_alphanumeric</span>: <span class="kw">fn</span>(<span class="op">&&</span><span class="ident">str</span>) <span class="op">-></span> <span class="ident">bool</span> <span class="op">=</span> <span class="ident">has_alphanumeric</span>; <span class="comment">// coerce to fn pointer</span> |
| |
| <span class="ident">UnicodeWords</span> { <span class="ident">inner</span>: <span class="ident">s</span>.<span class="ident">split_word_bounds</span>().<span class="ident">filter</span>(<span class="ident">has_alphanumeric</span>) } |
| } |
| </pre> |
| </section> |
| <section id='search' class="content hidden"></section> |
| |
| <section class="footer"></section> |
| |
| <aside id="help" class="hidden"> |
| <div> |
| <h1 class="hidden">Help</h1> |
| |
| <div class="shortcuts"> |
| <h2>Keyboard Shortcuts</h2> |
| |
| <dl> |
| <dt>?</dt> |
| <dd>Show this help dialog</dd> |
| <dt>S</dt> |
| <dd>Focus the search field</dd> |
| <dt>⇤</dt> |
| <dd>Move up in search results</dd> |
| <dt>⇥</dt> |
| <dd>Move down in search results</dd> |
| <dt>⏎</dt> |
| <dd>Go to active search result</dd> |
| <dt>+</dt> |
| <dd>Collapse/expand all sections</dd> |
| </dl> |
| </div> |
| |
| <div class="infos"> |
| <h2>Search Tricks</h2> |
| |
| <p> |
| Prefix searches with a type followed by a colon (e.g. |
| <code>fn:</code>) to restrict the search to a given type. |
| </p> |
| |
| <p> |
| Accepted types are: <code>fn</code>, <code>mod</code>, |
| <code>struct</code>, <code>enum</code>, |
| <code>trait</code>, <code>type</code>, <code>macro</code>, |
| and <code>const</code>. |
| </p> |
| |
| <p> |
| Search functions by type signature (e.g. |
| <code>vec -> usize</code> or <code>* -> vec</code>) |
| </p> |
| </div> |
| </div> |
| </aside> |
| |
| |
| |
| <script> |
| window.rootPath = "../../"; |
| window.currentCrate = "unicode_segmentation"; |
| </script> |
| <script src="../../main.js"></script> |
| <script defer src="../../search-index.js"></script> |
| </body> |
| </html> |