| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/tantivy-fst-0.4.0/src/raw/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../tantivy_fst/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy_fst/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <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> |
| <span id="650">650</span> |
| <span id="651">651</span> |
| <span id="652">652</span> |
| <span id="653">653</span> |
| <span id="654">654</span> |
| <span id="655">655</span> |
| <span id="656">656</span> |
| <span id="657">657</span> |
| <span id="658">658</span> |
| <span id="659">659</span> |
| <span id="660">660</span> |
| <span id="661">661</span> |
| <span id="662">662</span> |
| <span id="663">663</span> |
| <span id="664">664</span> |
| <span id="665">665</span> |
| <span id="666">666</span> |
| <span id="667">667</span> |
| <span id="668">668</span> |
| <span id="669">669</span> |
| <span id="670">670</span> |
| <span id="671">671</span> |
| <span id="672">672</span> |
| <span id="673">673</span> |
| <span id="674">674</span> |
| <span id="675">675</span> |
| <span id="676">676</span> |
| <span id="677">677</span> |
| <span id="678">678</span> |
| <span id="679">679</span> |
| <span id="680">680</span> |
| <span id="681">681</span> |
| <span id="682">682</span> |
| <span id="683">683</span> |
| <span id="684">684</span> |
| <span id="685">685</span> |
| <span id="686">686</span> |
| <span id="687">687</span> |
| <span id="688">688</span> |
| <span id="689">689</span> |
| <span id="690">690</span> |
| <span id="691">691</span> |
| <span id="692">692</span> |
| <span id="693">693</span> |
| <span id="694">694</span> |
| <span id="695">695</span> |
| <span id="696">696</span> |
| <span id="697">697</span> |
| <span id="698">698</span> |
| <span id="699">699</span> |
| <span id="700">700</span> |
| <span id="701">701</span> |
| <span id="702">702</span> |
| <span id="703">703</span> |
| <span id="704">704</span> |
| <span id="705">705</span> |
| <span id="706">706</span> |
| <span id="707">707</span> |
| <span id="708">708</span> |
| <span id="709">709</span> |
| <span id="710">710</span> |
| <span id="711">711</span> |
| <span id="712">712</span> |
| <span id="713">713</span> |
| <span id="714">714</span> |
| <span id="715">715</span> |
| <span id="716">716</span> |
| <span id="717">717</span> |
| <span id="718">718</span> |
| <span id="719">719</span> |
| <span id="720">720</span> |
| <span id="721">721</span> |
| <span id="722">722</span> |
| <span id="723">723</span> |
| <span id="724">724</span> |
| <span id="725">725</span> |
| <span id="726">726</span> |
| <span id="727">727</span> |
| <span id="728">728</span> |
| <span id="729">729</span> |
| <span id="730">730</span> |
| <span id="731">731</span> |
| <span id="732">732</span> |
| <span id="733">733</span> |
| <span id="734">734</span> |
| <span id="735">735</span> |
| <span id="736">736</span> |
| <span id="737">737</span> |
| <span id="738">738</span> |
| <span id="739">739</span> |
| <span id="740">740</span> |
| <span id="741">741</span> |
| <span id="742">742</span> |
| <span id="743">743</span> |
| <span id="744">744</span> |
| <span id="745">745</span> |
| <span id="746">746</span> |
| <span id="747">747</span> |
| <span id="748">748</span> |
| <span id="749">749</span> |
| <span id="750">750</span> |
| <span id="751">751</span> |
| <span id="752">752</span> |
| <span id="753">753</span> |
| <span id="754">754</span> |
| <span id="755">755</span> |
| <span id="756">756</span> |
| <span id="757">757</span> |
| <span id="758">758</span> |
| <span id="759">759</span> |
| <span id="760">760</span> |
| <span id="761">761</span> |
| <span id="762">762</span> |
| <span id="763">763</span> |
| <span id="764">764</span> |
| <span id="765">765</span> |
| <span id="766">766</span> |
| <span id="767">767</span> |
| <span id="768">768</span> |
| <span id="769">769</span> |
| <span id="770">770</span> |
| <span id="771">771</span> |
| <span id="772">772</span> |
| <span id="773">773</span> |
| <span id="774">774</span> |
| <span id="775">775</span> |
| <span id="776">776</span> |
| <span id="777">777</span> |
| <span id="778">778</span> |
| <span id="779">779</span> |
| <span id="780">780</span> |
| <span id="781">781</span> |
| <span id="782">782</span> |
| <span id="783">783</span> |
| <span id="784">784</span> |
| <span id="785">785</span> |
| <span id="786">786</span> |
| <span id="787">787</span> |
| <span id="788">788</span> |
| <span id="789">789</span> |
| <span id="790">790</span> |
| <span id="791">791</span> |
| <span id="792">792</span> |
| <span id="793">793</span> |
| <span id="794">794</span> |
| <span id="795">795</span> |
| <span id="796">796</span> |
| <span id="797">797</span> |
| <span id="798">798</span> |
| <span id="799">799</span> |
| <span id="800">800</span> |
| <span id="801">801</span> |
| <span id="802">802</span> |
| <span id="803">803</span> |
| <span id="804">804</span> |
| <span id="805">805</span> |
| <span id="806">806</span> |
| <span id="807">807</span> |
| <span id="808">808</span> |
| <span id="809">809</span> |
| <span id="810">810</span> |
| <span id="811">811</span> |
| <span id="812">812</span> |
| <span id="813">813</span> |
| <span id="814">814</span> |
| <span id="815">815</span> |
| <span id="816">816</span> |
| <span id="817">817</span> |
| <span id="818">818</span> |
| <span id="819">819</span> |
| <span id="820">820</span> |
| <span id="821">821</span> |
| <span id="822">822</span> |
| <span id="823">823</span> |
| <span id="824">824</span> |
| <span id="825">825</span> |
| <span id="826">826</span> |
| <span id="827">827</span> |
| <span id="828">828</span> |
| <span id="829">829</span> |
| <span id="830">830</span> |
| <span id="831">831</span> |
| <span id="832">832</span> |
| <span id="833">833</span> |
| <span id="834">834</span> |
| <span id="835">835</span> |
| <span id="836">836</span> |
| <span id="837">837</span> |
| <span id="838">838</span> |
| <span id="839">839</span> |
| <span id="840">840</span> |
| <span id="841">841</span> |
| <span id="842">842</span> |
| <span id="843">843</span> |
| <span id="844">844</span> |
| <span id="845">845</span> |
| <span id="846">846</span> |
| <span id="847">847</span> |
| <span id="848">848</span> |
| <span id="849">849</span> |
| <span id="850">850</span> |
| <span id="851">851</span> |
| <span id="852">852</span> |
| <span id="853">853</span> |
| <span id="854">854</span> |
| <span id="855">855</span> |
| <span id="856">856</span> |
| <span id="857">857</span> |
| <span id="858">858</span> |
| <span id="859">859</span> |
| <span id="860">860</span> |
| <span id="861">861</span> |
| <span id="862">862</span> |
| <span id="863">863</span> |
| <span id="864">864</span> |
| <span id="865">865</span> |
| <span id="866">866</span> |
| <span id="867">867</span> |
| <span id="868">868</span> |
| <span id="869">869</span> |
| <span id="870">870</span> |
| <span id="871">871</span> |
| <span id="872">872</span> |
| <span id="873">873</span> |
| <span id="874">874</span> |
| <span id="875">875</span> |
| <span id="876">876</span> |
| <span id="877">877</span> |
| <span id="878">878</span> |
| <span id="879">879</span> |
| <span id="880">880</span> |
| <span id="881">881</span> |
| <span id="882">882</span> |
| <span id="883">883</span> |
| <span id="884">884</span> |
| <span id="885">885</span> |
| <span id="886">886</span> |
| <span id="887">887</span> |
| <span id="888">888</span> |
| <span id="889">889</span> |
| <span id="890">890</span> |
| <span id="891">891</span> |
| <span id="892">892</span> |
| <span id="893">893</span> |
| <span id="894">894</span> |
| <span id="895">895</span> |
| <span id="896">896</span> |
| <span id="897">897</span> |
| <span id="898">898</span> |
| <span id="899">899</span> |
| <span id="900">900</span> |
| <span id="901">901</span> |
| <span id="902">902</span> |
| <span id="903">903</span> |
| <span id="904">904</span> |
| <span id="905">905</span> |
| <span id="906">906</span> |
| <span id="907">907</span> |
| <span id="908">908</span> |
| <span id="909">909</span> |
| <span id="910">910</span> |
| <span id="911">911</span> |
| <span id="912">912</span> |
| <span id="913">913</span> |
| <span id="914">914</span> |
| <span id="915">915</span> |
| <span id="916">916</span> |
| <span id="917">917</span> |
| <span id="918">918</span> |
| <span id="919">919</span> |
| <span id="920">920</span> |
| <span id="921">921</span> |
| <span id="922">922</span> |
| <span id="923">923</span> |
| <span id="924">924</span> |
| <span id="925">925</span> |
| <span id="926">926</span> |
| <span id="927">927</span> |
| <span id="928">928</span> |
| <span id="929">929</span> |
| <span id="930">930</span> |
| <span id="931">931</span> |
| <span id="932">932</span> |
| <span id="933">933</span> |
| <span id="934">934</span> |
| <span id="935">935</span> |
| <span id="936">936</span> |
| <span id="937">937</span> |
| <span id="938">938</span> |
| <span id="939">939</span> |
| <span id="940">940</span> |
| <span id="941">941</span> |
| <span id="942">942</span> |
| <span id="943">943</span> |
| <span id="944">944</span> |
| <span id="945">945</span> |
| <span id="946">946</span> |
| <span id="947">947</span> |
| <span id="948">948</span> |
| <span id="949">949</span> |
| <span id="950">950</span> |
| <span id="951">951</span> |
| <span id="952">952</span> |
| <span id="953">953</span> |
| <span id="954">954</span> |
| <span id="955">955</span> |
| <span id="956">956</span> |
| <span id="957">957</span> |
| <span id="958">958</span> |
| <span id="959">959</span> |
| <span id="960">960</span> |
| <span id="961">961</span> |
| <span id="962">962</span> |
| <span id="963">963</span> |
| <span id="964">964</span> |
| <span id="965">965</span> |
| <span id="966">966</span> |
| <span id="967">967</span> |
| <span id="968">968</span> |
| <span id="969">969</span> |
| <span id="970">970</span> |
| <span id="971">971</span> |
| <span id="972">972</span> |
| <span id="973">973</span> |
| <span id="974">974</span> |
| <span id="975">975</span> |
| <span id="976">976</span> |
| <span id="977">977</span> |
| <span id="978">978</span> |
| <span id="979">979</span> |
| <span id="980">980</span> |
| <span id="981">981</span> |
| <span id="982">982</span> |
| <span id="983">983</span> |
| <span id="984">984</span> |
| <span id="985">985</span> |
| <span id="986">986</span> |
| <span id="987">987</span> |
| <span id="988">988</span> |
| <span id="989">989</span> |
| <span id="990">990</span> |
| <span id="991">991</span> |
| <span id="992">992</span> |
| <span id="993">993</span> |
| <span id="994">994</span> |
| <span id="995">995</span> |
| <span id="996">996</span> |
| <span id="997">997</span> |
| <span id="998">998</span> |
| <span id="999">999</span> |
| <span id="1000">1000</span> |
| <span id="1001">1001</span> |
| <span id="1002">1002</span> |
| <span id="1003">1003</span> |
| <span id="1004">1004</span> |
| <span id="1005">1005</span> |
| <span id="1006">1006</span> |
| <span id="1007">1007</span> |
| <span id="1008">1008</span> |
| <span id="1009">1009</span> |
| <span id="1010">1010</span> |
| <span id="1011">1011</span> |
| <span id="1012">1012</span> |
| <span id="1013">1013</span> |
| <span id="1014">1014</span> |
| <span id="1015">1015</span> |
| <span id="1016">1016</span> |
| <span id="1017">1017</span> |
| <span id="1018">1018</span> |
| <span id="1019">1019</span> |
| <span id="1020">1020</span> |
| <span id="1021">1021</span> |
| <span id="1022">1022</span> |
| <span id="1023">1023</span> |
| <span id="1024">1024</span> |
| <span id="1025">1025</span> |
| <span id="1026">1026</span> |
| <span id="1027">1027</span> |
| <span id="1028">1028</span> |
| <span id="1029">1029</span> |
| <span id="1030">1030</span> |
| <span id="1031">1031</span> |
| <span id="1032">1032</span> |
| <span id="1033">1033</span> |
| <span id="1034">1034</span> |
| <span id="1035">1035</span> |
| <span id="1036">1036</span> |
| <span id="1037">1037</span> |
| <span id="1038">1038</span> |
| <span id="1039">1039</span> |
| <span id="1040">1040</span> |
| <span id="1041">1041</span> |
| <span id="1042">1042</span> |
| <span id="1043">1043</span> |
| <span id="1044">1044</span> |
| <span id="1045">1045</span> |
| <span id="1046">1046</span> |
| <span id="1047">1047</span> |
| <span id="1048">1048</span> |
| <span id="1049">1049</span> |
| <span id="1050">1050</span> |
| <span id="1051">1051</span> |
| <span id="1052">1052</span> |
| <span id="1053">1053</span> |
| <span id="1054">1054</span> |
| <span id="1055">1055</span> |
| <span id="1056">1056</span> |
| <span id="1057">1057</span> |
| <span id="1058">1058</span> |
| <span id="1059">1059</span> |
| <span id="1060">1060</span> |
| <span id="1061">1061</span> |
| <span id="1062">1062</span> |
| <span id="1063">1063</span> |
| <span id="1064">1064</span> |
| <span id="1065">1065</span> |
| <span id="1066">1066</span> |
| <span id="1067">1067</span> |
| <span id="1068">1068</span> |
| <span id="1069">1069</span> |
| <span id="1070">1070</span> |
| <span id="1071">1071</span> |
| <span id="1072">1072</span> |
| <span id="1073">1073</span> |
| <span id="1074">1074</span> |
| <span id="1075">1075</span> |
| <span id="1076">1076</span> |
| <span id="1077">1077</span> |
| <span id="1078">1078</span> |
| <span id="1079">1079</span> |
| <span id="1080">1080</span> |
| <span id="1081">1081</span> |
| <span id="1082">1082</span> |
| <span id="1083">1083</span> |
| <span id="1084">1084</span> |
| <span id="1085">1085</span> |
| <span id="1086">1086</span> |
| <span id="1087">1087</span> |
| <span id="1088">1088</span> |
| <span id="1089">1089</span> |
| <span id="1090">1090</span> |
| <span id="1091">1091</span> |
| <span id="1092">1092</span> |
| <span id="1093">1093</span> |
| <span id="1094">1094</span> |
| <span id="1095">1095</span> |
| <span id="1096">1096</span> |
| <span id="1097">1097</span> |
| <span id="1098">1098</span> |
| <span id="1099">1099</span> |
| <span id="1100">1100</span> |
| <span id="1101">1101</span> |
| <span id="1102">1102</span> |
| <span id="1103">1103</span> |
| <span id="1104">1104</span> |
| <span id="1105">1105</span> |
| <span id="1106">1106</span> |
| <span id="1107">1107</span> |
| <span id="1108">1108</span> |
| <span id="1109">1109</span> |
| <span id="1110">1110</span> |
| <span id="1111">1111</span> |
| <span id="1112">1112</span> |
| <span id="1113">1113</span> |
| <span id="1114">1114</span> |
| <span id="1115">1115</span> |
| <span id="1116">1116</span> |
| <span id="1117">1117</span> |
| <span id="1118">1118</span> |
| <span id="1119">1119</span> |
| <span id="1120">1120</span> |
| <span id="1121">1121</span> |
| <span id="1122">1122</span> |
| <span id="1123">1123</span> |
| <span id="1124">1124</span> |
| <span id="1125">1125</span> |
| <span id="1126">1126</span> |
| <span id="1127">1127</span> |
| <span id="1128">1128</span> |
| <span id="1129">1129</span> |
| <span id="1130">1130</span> |
| <span id="1131">1131</span> |
| <span id="1132">1132</span> |
| <span id="1133">1133</span> |
| <span id="1134">1134</span> |
| <span id="1135">1135</span> |
| <span id="1136">1136</span> |
| <span id="1137">1137</span> |
| <span id="1138">1138</span> |
| <span id="1139">1139</span> |
| <span id="1140">1140</span> |
| <span id="1141">1141</span> |
| <span id="1142">1142</span> |
| <span id="1143">1143</span> |
| <span id="1144">1144</span> |
| <span id="1145">1145</span> |
| <span id="1146">1146</span> |
| <span id="1147">1147</span> |
| <span id="1148">1148</span> |
| <span id="1149">1149</span> |
| <span id="1150">1150</span> |
| <span id="1151">1151</span> |
| <span id="1152">1152</span> |
| <span id="1153">1153</span> |
| <span id="1154">1154</span> |
| <span id="1155">1155</span> |
| <span id="1156">1156</span> |
| <span id="1157">1157</span> |
| <span id="1158">1158</span> |
| <span id="1159">1159</span> |
| <span id="1160">1160</span> |
| <span id="1161">1161</span> |
| <span id="1162">1162</span> |
| <span id="1163">1163</span> |
| <span id="1164">1164</span> |
| <span id="1165">1165</span> |
| <span id="1166">1166</span> |
| <span id="1167">1167</span> |
| <span id="1168">1168</span> |
| <span id="1169">1169</span> |
| <span id="1170">1170</span> |
| <span id="1171">1171</span> |
| <span id="1172">1172</span> |
| <span id="1173">1173</span> |
| <span id="1174">1174</span> |
| <span id="1175">1175</span> |
| <span id="1176">1176</span> |
| <span id="1177">1177</span> |
| <span id="1178">1178</span> |
| <span id="1179">1179</span> |
| <span id="1180">1180</span> |
| <span id="1181">1181</span> |
| <span id="1182">1182</span> |
| <span id="1183">1183</span> |
| <span id="1184">1184</span> |
| <span id="1185">1185</span> |
| <span id="1186">1186</span> |
| <span id="1187">1187</span> |
| <span id="1188">1188</span> |
| <span id="1189">1189</span> |
| <span id="1190">1190</span> |
| <span id="1191">1191</span> |
| <span id="1192">1192</span> |
| <span id="1193">1193</span> |
| <span id="1194">1194</span> |
| <span id="1195">1195</span> |
| <span id="1196">1196</span> |
| <span id="1197">1197</span> |
| <span id="1198">1198</span> |
| <span id="1199">1199</span> |
| <span id="1200">1200</span> |
| <span id="1201">1201</span> |
| <span id="1202">1202</span> |
| <span id="1203">1203</span> |
| <span id="1204">1204</span> |
| <span id="1205">1205</span> |
| <span id="1206">1206</span> |
| <span id="1207">1207</span> |
| <span id="1208">1208</span> |
| <span id="1209">1209</span> |
| <span id="1210">1210</span> |
| <span id="1211">1211</span> |
| <span id="1212">1212</span> |
| <span id="1213">1213</span> |
| <span id="1214">1214</span> |
| <span id="1215">1215</span> |
| <span id="1216">1216</span> |
| <span id="1217">1217</span> |
| <span id="1218">1218</span> |
| <span id="1219">1219</span> |
| <span id="1220">1220</span> |
| <span id="1221">1221</span> |
| <span id="1222">1222</span> |
| <span id="1223">1223</span> |
| <span id="1224">1224</span> |
| <span id="1225">1225</span> |
| <span id="1226">1226</span> |
| <span id="1227">1227</span> |
| <span id="1228">1228</span> |
| <span id="1229">1229</span> |
| <span id="1230">1230</span> |
| <span id="1231">1231</span> |
| <span id="1232">1232</span> |
| <span id="1233">1233</span> |
| <span id="1234">1234</span> |
| <span id="1235">1235</span> |
| <span id="1236">1236</span> |
| <span id="1237">1237</span> |
| <span id="1238">1238</span> |
| <span id="1239">1239</span> |
| <span id="1240">1240</span> |
| <span id="1241">1241</span> |
| <span id="1242">1242</span> |
| <span id="1243">1243</span> |
| <span id="1244">1244</span> |
| <span id="1245">1245</span> |
| <span id="1246">1246</span> |
| <span id="1247">1247</span> |
| <span id="1248">1248</span> |
| <span id="1249">1249</span> |
| <span id="1250">1250</span> |
| <span id="1251">1251</span> |
| <span id="1252">1252</span> |
| <span id="1253">1253</span> |
| <span id="1254">1254</span> |
| <span id="1255">1255</span> |
| <span id="1256">1256</span> |
| <span id="1257">1257</span> |
| <span id="1258">1258</span> |
| <span id="1259">1259</span> |
| <span id="1260">1260</span> |
| <span id="1261">1261</span> |
| <span id="1262">1262</span> |
| <span id="1263">1263</span> |
| <span id="1264">1264</span> |
| <span id="1265">1265</span> |
| <span id="1266">1266</span> |
| <span id="1267">1267</span> |
| <span id="1268">1268</span> |
| <span id="1269">1269</span> |
| <span id="1270">1270</span> |
| <span id="1271">1271</span> |
| <span id="1272">1272</span> |
| <span id="1273">1273</span> |
| <span id="1274">1274</span> |
| <span id="1275">1275</span> |
| <span id="1276">1276</span> |
| <span id="1277">1277</span> |
| <span id="1278">1278</span> |
| <span id="1279">1279</span> |
| <span id="1280">1280</span> |
| <span id="1281">1281</span> |
| <span id="1282">1282</span> |
| <span id="1283">1283</span> |
| <span id="1284">1284</span> |
| <span id="1285">1285</span> |
| <span id="1286">1286</span> |
| <span id="1287">1287</span> |
| <span id="1288">1288</span> |
| <span id="1289">1289</span> |
| <span id="1290">1290</span> |
| <span id="1291">1291</span> |
| <span id="1292">1292</span> |
| <span id="1293">1293</span> |
| <span id="1294">1294</span> |
| <span id="1295">1295</span> |
| <span id="1296">1296</span> |
| <span id="1297">1297</span> |
| <span id="1298">1298</span> |
| <span id="1299">1299</span> |
| <span id="1300">1300</span> |
| <span id="1301">1301</span> |
| <span id="1302">1302</span> |
| <span id="1303">1303</span> |
| <span id="1304">1304</span> |
| <span id="1305">1305</span> |
| <span id="1306">1306</span> |
| <span id="1307">1307</span> |
| <span id="1308">1308</span> |
| <span id="1309">1309</span> |
| <span id="1310">1310</span> |
| <span id="1311">1311</span> |
| <span id="1312">1312</span> |
| <span id="1313">1313</span> |
| <span id="1314">1314</span> |
| <span id="1315">1315</span> |
| <span id="1316">1316</span> |
| <span id="1317">1317</span> |
| <span id="1318">1318</span> |
| <span id="1319">1319</span> |
| <span id="1320">1320</span> |
| <span id="1321">1321</span> |
| <span id="1322">1322</span> |
| <span id="1323">1323</span> |
| <span id="1324">1324</span> |
| </pre><pre class="rust"><code><span class="doccomment">/*! |
| Operations on raw finite state transducers. |
| |
| This sub-module exposes the guts of a finite state transducer. Many parts of |
| it, such as construction and traversal, are mirrored in the `set` and `map` |
| sub-modules. Other parts of it, such as direct access to nodes and transitions |
| in the transducer, do not have any analog. |
| |
| # Overview of types |
| |
| `Fst` is a read only interface to pre-constructed finite state transducers. |
| `Node` is a read only interface to a single node in a transducer. `Builder` is |
| used to create new finite state transducers. (Once a transducer is created, it |
| can never be modified.) `Stream` is a stream of all inputs and outputs in a |
| transducer. `StreamBuilder` builds range queries. `OpBuilder` collects streams |
| and executes set operations like `union` or `intersection` on them with the |
| option of specifying a merge strategy for output values. |
| |
| Most of the rest of the types are streams from set operations. |
| */ |
| </span><span class="kw">use </span>std::fmt; |
| <span class="kw">use </span>std::ops::Deref; |
| <span class="kw">use </span>std::{cmp, mem}; |
| |
| <span class="kw">use </span>byteorder::{LittleEndian, ReadBytesExt}; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::automaton::{AlwaysMatch, Automaton}; |
| <span class="kw">use </span><span class="kw">crate</span>::error::Result; |
| <span class="kw">use </span><span class="kw">crate</span>::stream::{IntoStreamer, Streamer}; |
| |
| <span class="kw">pub use </span><span class="self">self</span>::build::Builder; |
| <span class="kw">pub use </span><span class="self">self</span>::error::Error; |
| <span class="kw">use </span><span class="self">self</span>::node::node_new; |
| <span class="kw">pub use </span><span class="self">self</span>::node::{Node, Transitions}; |
| <span class="kw">pub use </span><span class="self">self</span>::ops::{ |
| Chain, Difference, IndexedValue, Intersection, OpBuilder, SymmetricDifference, Union, |
| }; |
| |
| <span class="kw">mod </span>build; |
| <span class="kw">mod </span>common_inputs; |
| <span class="kw">mod </span>counting_writer; |
| <span class="kw">mod </span>error; |
| <span class="kw">mod </span>node; |
| <span class="kw">mod </span>ops; |
| <span class="kw">mod </span>pack; |
| <span class="kw">mod </span>registry; |
| <span class="kw">mod </span>registry_minimal; |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests; |
| |
| <span class="doccomment">/// The API version of this crate. |
| /// |
| /// This version number is written to every finite state transducer created by |
| /// this crate. When a finite state transducer is read, its version number is |
| /// checked against this value. |
| /// |
| /// Currently, any version mismatch results in an error. Fixing this requires |
| /// regenerating the finite state transducer or switching to a version of this |
| /// crate that is compatible with the serialized transducer. This particular |
| /// behavior may be relaxed in future versions. |
| </span><span class="kw">pub const </span>VERSION: u64 = <span class="number">2</span>; |
| |
| <span class="doccomment">/// A sentinel value used to indicate an empty final state. |
| </span><span class="kw">const </span>EMPTY_ADDRESS: CompiledAddr = <span class="number">0</span>; |
| |
| <span class="doccomment">/// A sentinel value used to indicate an invalid state. |
| /// |
| /// This is never the address of a node in a serialized transducer. |
| </span><span class="kw">const </span>NONE_ADDRESS: CompiledAddr = <span class="number">1</span>; |
| |
| <span class="doccomment">/// Default capacity for the key buffer of a stream. |
| </span><span class="kw">const </span>KEY_BUFFER_CAPACITY: usize = <span class="number">128</span>; |
| |
| <span class="doccomment">/// FstType is a convention used to indicate the type of the underlying |
| /// transducer. |
| /// |
| /// This crate reserves the range 0-255 (inclusive) but currently leaves the |
| /// meaning of 0-255 unspecified. |
| </span><span class="kw">pub type </span>FstType = u64; |
| |
| <span class="doccomment">/// CompiledAddr is the type used to address nodes in a finite state |
| /// transducer. |
| /// |
| /// It is most useful as a pointer to nodes. It can be used in the `Fst::node` |
| /// method to resolve the pointer. |
| </span><span class="kw">pub type </span>CompiledAddr = usize; |
| |
| <span class="doccomment">/// An acyclic deterministic finite state transducer. |
| /// |
| /// # How does it work? |
| /// |
| /// The short answer: it's just like a prefix trie, which compresses keys |
| /// based only on their prefixes, except that a automaton/transducer also |
| /// compresses suffixes. |
| /// |
| /// The longer answer is that keys in an automaton are stored only in the |
| /// transitions from one state to another. A key can be acquired by tracing |
| /// a path from the root of the automaton to any match state. The inputs along |
| /// each transition are concatenated. Once a match state is reached, the |
| /// concatenation of inputs up until that point corresponds to a single key. |
| /// |
| /// But why is it called a transducer instead of an automaton? A finite state |
| /// transducer is just like a finite state automaton, except that it has output |
| /// transitions in addition to input transitions. Namely, the value associated |
| /// with any particular key is determined by summing the outputs along every |
| /// input transition that leads to the key's corresponding match state. |
| /// |
| /// This is best demonstrated with a couple images. First, let's ignore the |
| /// "transducer" aspect and focus on a plain automaton. |
| /// |
| /// Consider that your keys are abbreviations of some of the months in the |
| /// Gregorian calendar: |
| /// |
| /// ```ignore |
| /// jan |
| /// feb |
| /// mar |
| /// apr |
| /// may |
| /// jun |
| /// jul |
| /// ``` |
| /// |
| /// The corresponding automaton that stores all of these as keys looks like |
| /// this: |
| /// |
| /// ![finite state automaton](http://burntsushi.net/stuff/months-set.png) |
| /// |
| /// Notice here how the prefix and suffix of `jan` and `jun` are shared. |
| /// Similarly, the prefixes of `jun` and `jul` are shared and the prefixes |
| /// of `mar` and `may` are shared. |
| /// |
| /// All of the keys from this automaton can be enumerated in lexicographic |
| /// order by following every transition from each node in lexicographic |
| /// order. Since it is acyclic, the procedure will terminate. |
| /// |
| /// A key can be found by tracing it through the transitions in the automaton. |
| /// For example, the key `aug` is known not to be in the automaton by only |
| /// visiting the root state (because there is no `a` transition). For another |
| /// example, the key `jax` is known not to be in the set only after moving |
| /// through the transitions for `j` and `a`. Namely, after those transitions |
| /// are followed, there are no transitions for `x`. |
| /// |
| /// Notice here that looking up a key is proportional the length of the key |
| /// itself. Namely, lookup time is not affected by the number of keys in the |
| /// automaton! |
| /// |
| /// Additionally, notice that the automaton exploits the fact that many keys |
| /// share common prefixes and suffixes. For example, `jun` and `jul` are |
| /// represented with no more states than would be required to represent either |
| /// one on its own. Instead, the only change is a single extra transition. This |
| /// is a form of compression and is key to how the automatons produced by this |
| /// crate are so small. |
| /// |
| /// Let's move on to finite state transducers. Consider the same set of keys |
| /// as above, but let's assign their numeric month values: |
| /// |
| /// ```ignore |
| /// jan,1 |
| /// feb,2 |
| /// mar,3 |
| /// apr,4 |
| /// may,5 |
| /// jun,6 |
| /// jul,7 |
| /// ``` |
| /// |
| /// The corresponding transducer looks very similar to the automaton above, |
| /// except outputs have been added to some of the transitions: |
| /// |
| /// ![finite state transducer](http://burntsushi.net/stuff/months-map.png) |
| /// |
| /// All of the operations with a transducer are the same as described above |
| /// for automatons. Additionally, the same compression techniques are used: |
| /// common prefixes and suffixes in keys are exploited. |
| /// |
| /// The key difference is that some transitions have been given an output. |
| /// As one follows input transitions, one must sum the outputs as they |
| /// are seen. (A transition with no output represents the additive identity, |
| /// or `0` in this case.) For example, when looking up `feb`, the transition |
| /// `f` has output `2`, the transition `e` has output `0`, and the transition |
| /// `b` also has output `0`. The sum of these is `2`, which is exactly the |
| /// value we associated with `feb`. |
| /// |
| /// For another more interesting example, consider `jul`. The `j` transition |
| /// has output `1`, the `u` transition has output `5` and the `l` transition |
| /// has output `1`. Summing these together gets us `7`, which is again the |
| /// correct value associated with `jul`. Notice that if we instead looked up |
| /// the `jun` key, then the `n` transition would be followed instead of the |
| /// `l` transition, which has no output. Therefore, the `jun` key equals |
| /// `1+5+0=6`. |
| /// |
| /// The trick to transducers is that there exists a unique path through the |
| /// transducer for every key, and its outputs are stored appropriately along |
| /// this path such that the correct value is returned when they are all summed |
| /// together. This process also enables the data that makes up each value to be |
| /// shared across many values in the transducer in exactly the same way that |
| /// keys are shared. This is yet another form of compression! |
| /// |
| /// # Bonus: a billion strings |
| /// |
| /// The amount of compression one can get from automata can be absolutely |
| /// ridiuclous. Consider the particular case of storing all billion strings |
| /// in the range `0000000001-1000000000`, e.g., |
| /// |
| /// ```ignore |
| /// 0000000001 |
| /// 0000000002 |
| /// ... |
| /// 0000000100 |
| /// 0000000101 |
| /// ... |
| /// 0999999999 |
| /// 1000000000 |
| /// ``` |
| /// |
| /// The corresponding automaton looks like this: |
| /// |
| /// ![finite state automaton - one billion strings] |
| /// (http://burntsushi.net/stuff/one-billion.png) |
| /// |
| /// Indeed, the on disk size of this automaton is a mere **251 bytes**. |
| /// |
| /// Of course, this is a bit of a pathological best case, but it does serve |
| /// to show how good compression can be in the optimal case. |
| /// |
| /// Also, check out the |
| /// [corresponding transducer](http://burntsushi.net/stuff/one-billion-map.svg) |
| /// that maps each string to its integer value. It's a bit bigger, but still |
| /// only takes up **896 bytes** of space on disk. This demonstrates that |
| /// output values are also compressible. |
| /// |
| /// # Does this crate produce minimal transducers? |
| /// |
| /// For any non-trivial sized set of keys, it is unlikely that this crate will |
| /// produce a minimal transducer. As far as this author knows, guaranteeing a |
| /// minimal transducer requires working memory proportional to the number of |
| /// states. This can be quite costly and is anathema to the main design goal of |
| /// this crate: provide the ability to work with gigantic sets of strings with |
| /// constant memory overhead. |
| /// |
| /// Instead, construction of a finite state transducer uses a cache of |
| /// states. More frequently used states are cached and reused, which provides |
| /// reasonably good compression ratios. (No comprehensive benchmarks exist to |
| /// back up this claim.) |
| /// |
| /// It is possible that this crate may expose a way to guarantee minimal |
| /// construction of transducers at the expense of exorbitant memory |
| /// requirements. |
| /// |
| /// # Bibliography |
| /// |
| /// I initially got the idea to use finite state tranducers to represent |
| /// ordered sets/maps from |
| /// [Michael |
| /// McCandless'](http://blog.mikemccandless.com/2010/12/using-finite-state-transducers-in.html) |
| /// work on incorporating transducers in Lucene. |
| /// |
| /// However, my work would also not have been possible without the hard work |
| /// of many academics, especially |
| /// [Jan Daciuk](http://galaxy.eti.pg.gda.pl/katedry/kiw/pracownicy/Jan.Daciuk/personal/). |
| /// |
| /// * [Incremental construction of minimal acyclic finite-state automata](http://www.mitpressjournals.org/doi/pdfplus/10.1162/089120100561601) |
| /// (Section 3 provides a decent overview of the algorithm used to construct |
| /// transducers in this crate, assuming all outputs are `0`.) |
| /// * [Direct Construction of Minimal Acyclic Subsequential Transducers](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.24.3698&rep=rep1&type=pdf) |
| /// (The whole thing. The proof is dense but illuminating. The algorithm at |
| /// the end is the money shot, namely, it incorporates output values.) |
| /// * [Experiments with Automata Compression](http://www.researchgate.net/profile/Jii_Dvorsky/publication/221568039_Word_Random_Access_Compression/links/0c96052c095630d5b3000000.pdf#page=116), [Smaller Representation of Finite State Automata](http://www.cs.put.poznan.pl/dweiss/site/publications/download/fsacomp.pdf) |
| /// (various compression techniques for representing states/transitions) |
| /// * [Jan Daciuk's dissertation](http://www.pg.gda.pl/~jandac/thesis.ps.gz) |
| /// (excellent for in depth overview) |
| /// * [Comparison of Construction Algorithms for Minimal, Acyclic, Deterministic, Finite-State Automata from Sets of Strings](http://www.cs.mun.ca/~harold/Courses/Old/CS4750/Diary/q3p2qx4lv71m5vew.pdf) |
| /// (excellent for surface level overview) |
| </span><span class="kw">pub struct </span>Fst<Data = Vec<u8>> { |
| meta: FstMeta, |
| data: Data, |
| } |
| |
| <span class="kw">struct </span>FstMeta { |
| version: u64, |
| root_addr: CompiledAddr, |
| ty: FstType, |
| len: usize, |
| } |
| |
| <span class="kw">impl </span>FstMeta { |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>root<<span class="lifetime">'f</span>>(<span class="kw-2">&</span><span class="self">self</span>, data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8]) -> Node<<span class="lifetime">'f</span>> { |
| <span class="self">self</span>.node(<span class="self">self</span>.root_addr, data) |
| } |
| |
| <span class="attribute">#[inline(always)] |
| </span><span class="kw">fn </span>node<<span class="lifetime">'f</span>>(<span class="kw-2">&</span><span class="self">self</span>, addr: CompiledAddr, data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8]) -> Node<<span class="lifetime">'f</span>> { |
| node_new(<span class="self">self</span>.version, addr, data) |
| } |
| |
| <span class="kw">fn </span>empty_final_output(<span class="kw-2">&</span><span class="self">self</span>, data: <span class="kw-2">&</span>[u8]) -> <span class="prelude-ty">Option</span><Output> { |
| <span class="kw">let </span>root = <span class="self">self</span>.root(data); |
| <span class="kw">if </span>root.is_final() { |
| <span class="prelude-val">Some</span>(root.final_output()) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl</span><Data: Deref<Target = [u8]>> Fst<Data> { |
| <span class="doccomment">/// Open a `Fst` from a given data. |
| </span><span class="kw">pub fn </span>new(data: Data) -> <span class="prelude-ty">Result</span><Fst<Data>> { |
| <span class="kw">if </span>data.len() < <span class="number">32 </span>{ |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Format.into()); |
| } |
| <span class="comment">// The read_u64 unwraps below are OK because they can never fail. |
| // They can only fail when there is an IO error or if there is an |
| // unexpected EOF. However, we are reading from a byte slice (no |
| // IO errors possible) and we've confirmed the byte slice is at least |
| // N bytes (no unexpected EOF). |
| </span><span class="kw">let </span>version = (<span class="kw-2">&*</span>data).read_u64::<LittleEndian>().unwrap(); |
| <span class="kw">if </span>version == <span class="number">0 </span>|| version > VERSION { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Version { |
| expected: VERSION, |
| got: version, |
| } |
| .into()); |
| } |
| <span class="kw">let </span>ty = (<span class="kw-2">&</span>data[<span class="number">8</span>..]).read_u64::<LittleEndian>().unwrap(); |
| <span class="kw">let </span>root_addr = { |
| <span class="kw">let </span><span class="kw-2">mut </span>last = <span class="kw-2">&</span>data[data.len() - <span class="number">8</span>..]; |
| u64_to_usize(last.read_u64::<LittleEndian>().unwrap()) |
| }; |
| <span class="kw">let </span>len = { |
| <span class="kw">let </span><span class="kw-2">mut </span>last2 = <span class="kw-2">&</span>data[data.len() - <span class="number">16</span>..]; |
| u64_to_usize(last2.read_u64::<LittleEndian>().unwrap()) |
| }; |
| <span class="comment">// The root node is always the last node written, so its address should |
| // be near the end. After the root node is written, we still have to |
| // write the root *address* and the number of keys in the FST. |
| // That's 16 bytes. The extra byte comes from the fact that the root |
| // address points to the last byte in the root node, rather than the |
| // byte immediately following the root node. |
| // |
| // If this check passes, it is still possible that the FST is invalid |
| // but probably unlikely. If this check reports a false positive, then |
| // the program will probably panic. In the worst case, the FST will |
| // operate but be subtly wrong. (This would require the bytes to be in |
| // a format expected by an FST, which is incredibly unlikely.) |
| // |
| // The special check for EMPTY_ADDRESS is needed since an empty FST |
| // has a root node that is empty and final, which means it has the |
| // special address `0`. In that case, the FST is the smallest it can |
| // be: the version, type, root address and number of nodes. That's |
| // 32 bytes (8 byte u64 each). |
| // |
| // This is essentially our own little checksum. |
| </span><span class="kw">if </span>(root_addr == EMPTY_ADDRESS && data.len() != <span class="number">32</span>) && root_addr + <span class="number">17 </span>!= data.len() { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::Format.into()); |
| } |
| <span class="prelude-val">Ok</span>(Fst { |
| data, |
| meta: FstMeta { |
| version, |
| root_addr, |
| ty, |
| len, |
| }, |
| }) |
| } |
| |
| <span class="doccomment">/// Retrieves the value associated with a key. |
| /// |
| /// If the key does not exist, then `None` is returned. |
| </span><span class="attribute">#[inline(never)] |
| </span><span class="kw">pub fn </span>get<B: AsRef<[u8]>>(<span class="kw-2">&</span><span class="self">self</span>, key: B) -> <span class="prelude-ty">Option</span><Output> { |
| <span class="kw">let </span><span class="kw-2">mut </span>node = <span class="self">self</span>.root(); |
| <span class="kw">let </span><span class="kw-2">mut </span>out = Output::zero(); |
| <span class="kw">for </span><span class="kw-2">&</span>b <span class="kw">in </span>key.as_ref() { |
| node = <span class="kw">match </span>node.find_input(b) { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="prelude-val">None</span>, |
| <span class="prelude-val">Some</span>(i) => { |
| <span class="kw">let </span>t = node.transition(i); |
| out = out.cat(t.out); |
| <span class="self">self</span>.node(t.addr) |
| } |
| } |
| } |
| <span class="kw">if </span>!node.is_final() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else </span>{ |
| <span class="prelude-val">Some</span>(out.cat(node.final_output())) |
| } |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the given key is in this FST. |
| </span><span class="kw">pub fn </span>contains_key<B: AsRef<[u8]>>(<span class="kw-2">&</span><span class="self">self</span>, key: B) -> bool { |
| <span class="kw">let </span><span class="kw-2">mut </span>node = <span class="self">self</span>.root(); |
| <span class="kw">for </span><span class="kw-2">&</span>b <span class="kw">in </span>key.as_ref() { |
| node = <span class="kw">match </span>node.find_input(b) { |
| <span class="prelude-val">None </span>=> <span class="kw">return </span><span class="bool-val">false</span>, |
| <span class="prelude-val">Some</span>(i) => <span class="self">self</span>.node(node.transition_addr(i)), |
| } |
| } |
| node.is_final() |
| } |
| |
| <span class="doccomment">/// Return a lexicographically ordered stream of all key-value pairs in |
| /// this fst. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>stream(<span class="kw-2">&</span><span class="self">self</span>) -> Stream { |
| <span class="self">self</span>.stream_builder(AlwaysMatch).into_stream() |
| } |
| |
| <span class="kw">fn </span>stream_builder<A: Automaton>(<span class="kw-2">&</span><span class="self">self</span>, aut: A) -> StreamBuilder<A> { |
| StreamBuilder::new(<span class="kw-2">&</span><span class="self">self</span>.meta, <span class="kw-2">&</span><span class="self">self</span>.data, aut) |
| } |
| |
| <span class="doccomment">/// Return a builder for range queries. |
| /// |
| /// A range query returns a subset of key-value pairs in this fst in a |
| /// range given in lexicographic order. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>range(<span class="kw-2">&</span><span class="self">self</span>) -> StreamBuilder { |
| <span class="self">self</span>.stream_builder(AlwaysMatch) |
| } |
| |
| <span class="doccomment">/// Executes an automaton on the keys of this map. |
| </span><span class="kw">pub fn </span>search<A: Automaton>(<span class="kw-2">&</span><span class="self">self</span>, aut: A) -> StreamBuilder<A> { |
| <span class="self">self</span>.stream_builder(aut) |
| } |
| |
| <span class="doccomment">/// Returns the number of keys in this fst. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>len(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.meta.len |
| } |
| |
| <span class="doccomment">/// Returns true if and only if this fst has no keys. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="self">self</span>.len() == <span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Returns the number of bytes used by this fst. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>size(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.data.len() |
| } |
| |
| <span class="doccomment">/// Creates a new fst operation with this fst added to it. |
| /// |
| /// The `OpBuilder` type can be used to add additional fst streams |
| /// and perform set operations like union, intersection, difference and |
| /// symmetric difference on the keys of the fst. These set operations also |
| /// allow one to specify how conflicting values are merged in the stream. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>op(<span class="kw-2">&</span><span class="self">self</span>) -> OpBuilder { |
| OpBuilder::default().add(<span class="self">self</span>) |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the `self` fst is disjoint with the fst |
| /// `stream`. |
| /// |
| /// `stream` must be a lexicographically ordered sequence of byte strings |
| /// with associated values. |
| </span><span class="kw">pub fn </span>is_disjoint<<span class="lifetime">'f</span>, I, S>(<span class="kw-2">&</span><span class="self">self</span>, stream: I) -> bool |
| <span class="kw">where |
| </span>I: <span class="kw">for</span><<span class="lifetime">'a</span>> IntoStreamer<<span class="lifetime">'a</span>, Into = S, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| S: <span class="lifetime">'f </span>+ <span class="kw">for</span><<span class="lifetime">'a</span>> Streamer<<span class="lifetime">'a</span>, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| { |
| <span class="self">self</span>.op().add(stream).intersection().next().is_none() |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the `self` fst is a subset of the fst |
| /// `stream`. |
| /// |
| /// `stream` must be a lexicographically ordered sequence of byte strings |
| /// with associated values. |
| </span><span class="kw">pub fn </span>is_subset<<span class="lifetime">'f</span>, I, S>(<span class="kw-2">&</span><span class="self">self</span>, stream: I) -> bool |
| <span class="kw">where |
| </span>I: <span class="kw">for</span><<span class="lifetime">'a</span>> IntoStreamer<<span class="lifetime">'a</span>, Into = S, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| S: <span class="lifetime">'f </span>+ <span class="kw">for</span><<span class="lifetime">'a</span>> Streamer<<span class="lifetime">'a</span>, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>op = <span class="self">self</span>.op().add(stream).intersection(); |
| <span class="kw">let </span><span class="kw-2">mut </span>count = <span class="number">0</span>; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(<span class="kw">_</span>) = op.next() { |
| count += <span class="number">1</span>; |
| } |
| count == <span class="self">self</span>.len() |
| } |
| |
| <span class="doccomment">/// Returns true if and only if the `self` fst is a superset of the fst |
| /// `stream`. |
| /// |
| /// `stream` must be a lexicographically ordered sequence of byte strings |
| /// with associated values. |
| </span><span class="kw">pub fn </span>is_superset<<span class="lifetime">'f</span>, I, S>(<span class="kw-2">&</span><span class="self">self</span>, stream: I) -> bool |
| <span class="kw">where |
| </span>I: <span class="kw">for</span><<span class="lifetime">'a</span>> IntoStreamer<<span class="lifetime">'a</span>, Into = S, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| S: <span class="lifetime">'f </span>+ <span class="kw">for</span><<span class="lifetime">'a</span>> Streamer<<span class="lifetime">'a</span>, Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output)>, |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>op = <span class="self">self</span>.op().add(stream).union(); |
| <span class="kw">let </span><span class="kw-2">mut </span>count = <span class="number">0</span>; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(<span class="kw">_</span>) = op.next() { |
| count += <span class="number">1</span>; |
| } |
| count == <span class="self">self</span>.len() |
| } |
| |
| <span class="doccomment">/// Returns the underlying type of this fst. |
| /// |
| /// FstType is a convention used to indicate the type of the underlying |
| /// transducer. |
| /// |
| /// This crate reserves the range 0-255 (inclusive) but currently leaves |
| /// the meaning of 0-255 unspecified. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>fst_type(<span class="kw-2">&</span><span class="self">self</span>) -> FstType { |
| <span class="self">self</span>.meta.ty |
| } |
| |
| <span class="doccomment">/// Returns the root node of this fst. |
| </span><span class="attribute">#[inline(always)] |
| </span><span class="kw">pub fn </span>root(<span class="kw-2">&</span><span class="self">self</span>) -> Node { |
| <span class="self">self</span>.meta.root(<span class="self">self</span>.data.deref()) |
| } |
| |
| <span class="doccomment">/// Returns the node at the given address. |
| /// |
| /// Node addresses can be obtained by reading transitions on `Node` values. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>node(<span class="kw-2">&</span><span class="self">self</span>, addr: CompiledAddr) -> Node { |
| <span class="self">self</span>.meta.node(addr, <span class="self">self</span>.data.deref()) |
| } |
| |
| <span class="doccomment">/// Returns a copy of the binary contents of this FST. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>to_vec(<span class="kw-2">&</span><span class="self">self</span>) -> Vec<u8> { |
| <span class="self">self</span>.data.to_vec() |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, <span class="lifetime">'f</span>, Data> IntoStreamer<<span class="lifetime">'a</span>> <span class="kw">for </span><span class="kw-2">&</span><span class="lifetime">'f </span>Fst<Data> |
| <span class="kw">where |
| </span>Data: Deref<Target = [u8]>, |
| { |
| <span class="kw">type </span>Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output); |
| <span class="kw">type </span>Into = Stream<<span class="lifetime">'f</span>>; |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>into_stream(<span class="self">self</span>) -> <span class="self">Self</span>::Into { |
| <span class="self">self</span>.stream() |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing range queries on streams. |
| /// |
| /// Once all bounds are set, one should call `into_stream` to get a |
| /// `Stream`. |
| /// |
| /// Bounds are not additive. That is, if `ge` is called twice on the same |
| /// builder, then the second setting wins. |
| /// |
| /// The `A` type parameter corresponds to an optional automaton to filter |
| /// the stream. By default, no filtering is done. |
| /// |
| /// The `'f` lifetime parameter refers to the lifetime of the underlying fst. |
| </span><span class="kw">pub struct </span>StreamBuilder<<span class="lifetime">'f</span>, A = AlwaysMatch> { |
| meta: <span class="kw-2">&</span><span class="lifetime">'f </span>FstMeta, |
| data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8], |
| aut: A, |
| min: Bound, |
| max: Bound, |
| backward: bool, |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'f</span>, A: Automaton> StreamBuilder<<span class="lifetime">'f</span>, A> { |
| <span class="kw">fn </span>new(meta: <span class="kw-2">&</span><span class="lifetime">'f </span>FstMeta, data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8], aut: A) -> <span class="self">Self </span>{ |
| StreamBuilder { |
| meta, |
| data, |
| aut, |
| min: Bound::Unbounded, |
| max: Bound::Unbounded, |
| backward: <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Specify a greater-than-or-equal-to bound. |
| </span><span class="kw">pub fn </span>ge<T: AsRef<[u8]>>(<span class="kw-2">mut </span><span class="self">self</span>, bound: T) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.min = Bound::Included(bound.as_ref().to_owned()); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Specify a greater-than bound. |
| </span><span class="kw">pub fn </span>gt<T: AsRef<[u8]>>(<span class="kw-2">mut </span><span class="self">self</span>, bound: T) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.min = Bound::Excluded(bound.as_ref().to_owned()); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Specify a less-than-or-equal-to bound. |
| </span><span class="kw">pub fn </span>le<T: AsRef<[u8]>>(<span class="kw-2">mut </span><span class="self">self</span>, bound: T) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.max = Bound::Included(bound.as_ref().to_owned()); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Specify a less-than bound. |
| </span><span class="kw">pub fn </span>lt<T: AsRef<[u8]>>(<span class="kw-2">mut </span><span class="self">self</span>, bound: T) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.max = Bound::Excluded(bound.as_ref().to_owned()); |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Sets the `StreamBuilder` to stream the `(key, value)` backward. |
| </span><span class="kw">pub fn </span>backward(<span class="kw-2">mut </span><span class="self">self</span>) -> <span class="self">Self </span>{ |
| <span class="self">self</span>.backward = <span class="bool-val">true</span>; |
| <span class="self">self |
| </span>} |
| |
| <span class="doccomment">/// Return this builder and gives the automaton states |
| /// along with the results. |
| </span><span class="kw">pub fn </span>with_state(<span class="self">self</span>) -> StreamWithStateBuilder<<span class="lifetime">'f</span>, A> { |
| StreamWithStateBuilder(<span class="self">self</span>) |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, <span class="lifetime">'f</span>, A: Automaton> IntoStreamer<<span class="lifetime">'a</span>> <span class="kw">for </span>StreamBuilder<<span class="lifetime">'f</span>, A> { |
| <span class="kw">type </span>Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output); |
| <span class="kw">type </span>Into = Stream<<span class="lifetime">'f</span>, A>; |
| |
| <span class="kw">fn </span>into_stream(<span class="self">self</span>) -> Stream<<span class="lifetime">'f</span>, A> { |
| Stream::new( |
| <span class="self">self</span>.meta, |
| <span class="self">self</span>.data, |
| <span class="self">self</span>.aut, |
| <span class="self">self</span>.min, |
| <span class="self">self</span>.max, |
| <span class="self">self</span>.backward, |
| ) |
| } |
| } |
| |
| <span class="doccomment">/// A builder for constructing range queries of streams |
| /// that returns results along with automaton states. |
| /// |
| /// Once all bounds are set, one should call `into_stream` to get a |
| /// `StreamWithState`. |
| /// |
| /// Bounds are not additive. That is, if `ge` is called twice on the same |
| /// builder, then the second setting wins. |
| /// |
| /// The `A` type parameter corresponds to an optional automaton to filter |
| /// the stream. By default, no filtering is done. |
| /// |
| /// The `'f` lifetime parameter refers to the lifetime of the underlying fst. |
| </span><span class="kw">pub struct </span>StreamWithStateBuilder<<span class="lifetime">'f</span>, A = AlwaysMatch>(StreamBuilder<<span class="lifetime">'f</span>, A>); |
| |
| <span class="kw">impl</span><<span class="lifetime">'a</span>, <span class="lifetime">'f</span>, A: <span class="lifetime">'a </span>+ Automaton> IntoStreamer<<span class="lifetime">'a</span>> <span class="kw">for </span>StreamWithStateBuilder<<span class="lifetime">'f</span>, A> |
| <span class="kw">where |
| </span>A::State: Clone, |
| { |
| <span class="kw">type </span>Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output, A::State); |
| <span class="kw">type </span>Into = StreamWithState<<span class="lifetime">'f</span>, A>; |
| |
| <span class="kw">fn </span>into_stream(<span class="self">self</span>) -> StreamWithState<<span class="lifetime">'f</span>, A> { |
| StreamWithState::new( |
| <span class="self">self</span>.<span class="number">0</span>.meta, |
| <span class="self">self</span>.<span class="number">0</span>.data, |
| <span class="self">self</span>.<span class="number">0</span>.aut, |
| <span class="self">self</span>.<span class="number">0</span>.min, |
| <span class="self">self</span>.<span class="number">0</span>.max, |
| <span class="self">self</span>.<span class="number">0</span>.backward, |
| ) |
| } |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">enum </span>Bound { |
| Included(Vec<u8>), |
| Excluded(Vec<u8>), |
| Unbounded, |
| } |
| |
| <span class="kw">impl </span>Bound { |
| <span class="kw">fn </span>exceeded_by(<span class="kw-2">&</span><span class="self">self</span>, inp: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Bound::Included(<span class="kw-2">ref </span>v) => inp > v, |
| Bound::Excluded(<span class="kw-2">ref </span>v) => inp >= v, |
| Bound::Unbounded => <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>subceeded_by(<span class="kw-2">&</span><span class="self">self</span>, inp: <span class="kw-2">&</span>[u8]) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Bound::Included(<span class="kw-2">ref </span>v) => inp < v, |
| Bound::Excluded(<span class="kw-2">ref </span>v) => inp <= v, |
| Bound::Unbounded => <span class="bool-val">false</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>is_empty(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Bound::Included(<span class="kw-2">ref </span>v) => v.is_empty(), |
| Bound::Excluded(<span class="kw-2">ref </span>v) => v.is_empty(), |
| Bound::Unbounded => <span class="bool-val">true</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>is_inclusive(<span class="kw-2">&</span><span class="self">self</span>) -> bool { |
| <span class="kw">match </span><span class="kw-2">*</span><span class="self">self </span>{ |
| Bound::Excluded(<span class="kw">_</span>) => <span class="bool-val">false</span>, |
| <span class="kw">_ </span>=> <span class="bool-val">true</span>, |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Stream of `key, value` not exposing the state of the automaton. |
| </span><span class="kw">pub struct </span>Stream<<span class="lifetime">'f</span>, A = AlwaysMatch>(StreamWithState<<span class="lifetime">'f</span>, A>) |
| <span class="kw">where |
| </span>A: Automaton; |
| |
| <span class="kw">impl</span><<span class="lifetime">'f</span>, A: Automaton> Stream<<span class="lifetime">'f</span>, A> { |
| <span class="kw">fn </span>new( |
| meta: <span class="kw-2">&</span><span class="lifetime">'f </span>FstMeta, |
| data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8], |
| aut: A, |
| min: Bound, |
| max: Bound, |
| backward: bool, |
| ) -> <span class="self">Self </span>{ |
| <span class="self">Self</span>(StreamWithState::new(meta, data, aut, min, max, backward)) |
| } |
| |
| <span class="doccomment">/// Convert this stream into a vector of byte strings and outputs. |
| /// |
| /// Note that this creates a new allocation for every key in the stream. |
| </span><span class="kw">pub fn </span>into_byte_vec(<span class="kw-2">mut </span><span class="self">self</span>) -> Vec<(Vec<u8>, u64)> { |
| <span class="kw">let </span><span class="kw-2">mut </span>vs = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>((k, v)) = <span class="self">self</span>.next() { |
| vs.push((k.to_vec(), v.value())); |
| } |
| vs |
| } |
| |
| <span class="doccomment">/// Convert this stream into a vector of Unicode strings and outputs. |
| /// |
| /// If any key is not valid UTF-8, then iteration on the stream is stopped |
| /// and a UTF-8 decoding error is returned. |
| /// |
| /// Note that this creates a new allocation for every key in the stream. |
| </span><span class="kw">pub fn </span>into_str_vec(<span class="kw-2">mut </span><span class="self">self</span>) -> <span class="prelude-ty">Result</span><Vec<(String, u64)>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>vs = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>((k, v)) = <span class="self">self</span>.next() { |
| <span class="kw">let </span>k = String::from_utf8(k.to_vec()).map_err(Error::from)<span class="question-mark">?</span>; |
| vs.push((k, v.value())); |
| } |
| <span class="prelude-val">Ok</span>(vs) |
| } |
| |
| <span class="doccomment">/// Convert this stream into a vector of byte strings. |
| /// |
| /// Note that this creates a new allocation for every key in the stream. |
| </span><span class="kw">pub fn </span>into_byte_keys(<span class="kw-2">mut </span><span class="self">self</span>) -> Vec<Vec<u8>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>vs = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>((k, <span class="kw">_</span>)) = <span class="self">self</span>.next() { |
| vs.push(k.to_vec()); |
| } |
| vs |
| } |
| |
| <span class="doccomment">/// Convert this stream into a vector of Unicode strings. |
| /// |
| /// If any key is not valid UTF-8, then iteration on the stream is stopped |
| /// and a UTF-8 decoding error is returned. |
| /// |
| /// Note that this creates a new allocation for every key in the stream. |
| </span><span class="kw">pub fn </span>into_str_keys(<span class="kw-2">mut </span><span class="self">self</span>) -> <span class="prelude-ty">Result</span><Vec<String>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>vs = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>((k, <span class="kw">_</span>)) = <span class="self">self</span>.next() { |
| <span class="kw">let </span>k = String::from_utf8(k.to_vec()).map_err(Error::from)<span class="question-mark">?</span>; |
| vs.push(k); |
| } |
| <span class="prelude-val">Ok</span>(vs) |
| } |
| |
| <span class="doccomment">/// Convert this stream into a vector of outputs. |
| </span><span class="kw">pub fn </span>into_values(<span class="kw-2">mut </span><span class="self">self</span>) -> Vec<u64> { |
| <span class="kw">let </span><span class="kw-2">mut </span>vs = <span class="macro">vec!</span>[]; |
| <span class="kw">while let </span><span class="prelude-val">Some</span>((<span class="kw">_</span>, v)) = <span class="self">self</span>.next() { |
| vs.push(v.value()); |
| } |
| vs |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'f</span>, <span class="lifetime">'a</span>, A: Automaton> Streamer<<span class="lifetime">'a</span>> <span class="kw">for </span>Stream<<span class="lifetime">'f</span>, A> { |
| <span class="kw">type </span>Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output); |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>::Item> { |
| <span class="self">self</span>.<span class="number">0</span>.next(|<span class="kw">_</span>| ()).map(|(key, out, <span class="kw">_</span>)| (key, out)) |
| } |
| } |
| |
| <span class="doccomment">/// A lexicographically ordered stream from an fst |
| /// of key-value pairs along with the state of the automaton. |
| /// |
| /// The `A` type parameter corresponds to an optional automaton to filter |
| /// the stream. By default, no filtering is done. |
| /// |
| /// The `'f` lifetime parameter refers to the lifetime of the underlying fst. |
| </span><span class="attribute">#[derive(Clone)] |
| </span><span class="kw">pub struct </span>StreamWithState<<span class="lifetime">'f</span>, A = AlwaysMatch> |
| <span class="kw">where |
| </span>A: Automaton, |
| { |
| fst: <span class="kw-2">&</span><span class="lifetime">'f </span>FstMeta, |
| data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8], |
| aut: A, |
| inp: Buffer, |
| empty_output: <span class="prelude-ty">Option</span><Output>, |
| stack: Vec<StreamState<<span class="lifetime">'f</span>, A::State>>, |
| end_at: Bound, |
| min: Bound, |
| max: Bound, |
| reversed: bool, |
| } |
| |
| <span class="attribute">#[derive(Clone, Debug)] |
| </span><span class="kw">struct </span>StreamState<<span class="lifetime">'f</span>, S> { |
| node: Node<<span class="lifetime">'f</span>>, |
| trans: usize, |
| out: Output, |
| aut_state: S, |
| done: bool, <span class="comment">// ('done' = true) means that there are no unexplored transitions in the current state. |
| // 'trans' value should be ignored when done is true. |
| </span>} |
| |
| <span class="kw">impl</span><<span class="lifetime">'f</span>, A: Automaton> StreamWithState<<span class="lifetime">'f</span>, A> { |
| <span class="kw">fn </span>new( |
| fst: <span class="kw-2">&</span><span class="lifetime">'f </span>FstMeta, |
| data: <span class="kw-2">&</span><span class="lifetime">'f </span>[u8], |
| aut: A, |
| min: Bound, |
| max: Bound, |
| backward: bool, |
| ) -> <span class="self">Self </span>{ |
| <span class="kw">let </span>min_2 = min.clone(); |
| <span class="kw">let </span>max_2 = max.clone(); |
| <span class="kw">let </span>end_at: Bound = <span class="kw">if </span>!backward { max.clone() } <span class="kw">else </span>{ min.clone() }; |
| <span class="kw">let </span><span class="kw-2">mut </span>stream = StreamWithState { |
| fst, |
| data, |
| aut, |
| inp: Buffer::new(), |
| empty_output: <span class="prelude-val">None</span>, |
| stack: <span class="macro">vec!</span>[], |
| end_at, |
| min: min_2, |
| max: max_2, |
| reversed: backward, |
| }; |
| stream.seek(<span class="kw-2">&</span>min, <span class="kw-2">&</span>max); |
| stream |
| } |
| |
| <span class="doccomment">/// Seeks the underlying stream such that the next key to be read is the |
| /// smallest key in the underlying fst that satisfies the given minimum |
| /// bound. |
| /// |
| /// This theoretically should be straight-forward, but we need to make |
| /// sure our stack is correct, which includes accounting for automaton |
| /// states. |
| </span><span class="kw">fn </span>seek(<span class="kw-2">&mut </span><span class="self">self</span>, min: <span class="kw-2">&</span>Bound, max: <span class="kw-2">&</span>Bound) { |
| <span class="kw">let </span>start_bound = <span class="kw">if </span><span class="self">self</span>.reversed { <span class="kw-2">&</span>max } <span class="kw">else </span>{ <span class="kw-2">&</span>min }; |
| <span class="kw">if </span>min.is_empty() && min.is_inclusive() { |
| <span class="self">self</span>.empty_output = <span class="self">self</span>.resolve_empty_output(min, max); |
| } |
| <span class="kw">if </span>start_bound.is_empty() { |
| <span class="self">self</span>.stack.clear(); |
| <span class="kw">let </span>node = <span class="self">self</span>.fst.root(<span class="self">self</span>.data); |
| <span class="kw">let </span>transition = <span class="self">self</span>.starting_transition(<span class="kw-2">&</span>node); |
| <span class="self">self</span>.stack = <span class="macro">vec!</span>[StreamState { |
| node, |
| trans: transition.unwrap_or_default(), |
| out: Output::zero(), |
| aut_state: <span class="self">self</span>.aut.start(), |
| done: transition.is_none(), |
| }]; |
| <span class="kw">return</span>; |
| } |
| <span class="kw">let </span>(key, inclusive) = <span class="kw">match </span>start_bound { |
| Bound::Excluded(<span class="kw-2">ref </span>start_bound) => (start_bound, <span class="bool-val">false</span>), |
| Bound::Included(<span class="kw-2">ref </span>start_bound) => (start_bound, <span class="bool-val">true</span>), |
| Bound::Unbounded => <span class="macro">unreachable!</span>(), |
| }; |
| <span class="comment">// At this point, we need to find the starting location of `min` in |
| // the FST. However, as we search, we need to maintain a stack of |
| // reader states so that the reader can pick up where we left off. |
| // N.B. We do not necessarily need to stop in a final state, unlike |
| // the one-off `find` method. For the example, the given bound might |
| // not actually exist in the FST. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>node = <span class="self">self</span>.fst.root(<span class="self">self</span>.data); |
| <span class="kw">let </span><span class="kw-2">mut </span>out = Output::zero(); |
| <span class="kw">let </span><span class="kw-2">mut </span>aut_state = <span class="self">self</span>.aut.start(); |
| <span class="kw">for </span><span class="kw-2">&</span>b <span class="kw">in </span>key { |
| <span class="kw">match </span>node.find_input(b) { |
| <span class="prelude-val">Some</span>(i) => { |
| <span class="kw">let </span>t = node.transition(i); |
| <span class="kw">let </span>prev_state = aut_state; |
| aut_state = <span class="self">self</span>.aut.accept(<span class="kw-2">&</span>prev_state, b); |
| <span class="self">self</span>.inp.push(b); |
| <span class="kw">let </span>transition = <span class="self">self</span>.next_transition(<span class="kw-2">&</span>node, i); |
| <span class="self">self</span>.stack.push(StreamState { |
| node, |
| trans: transition.unwrap_or_default(), |
| out, |
| aut_state: prev_state, |
| done: transition.is_none(), |
| }); |
| out = out.cat(t.out); |
| node = <span class="self">self</span>.fst.node(t.addr, <span class="self">self</span>.data); |
| } |
| <span class="prelude-val">None </span>=> { |
| <span class="comment">// This is a little tricky. We're in this case if the |
| // given bound is not a prefix of any key in the FST. |
| // Since this is a minimum bound, we need to find the |
| // first transition in this node that proceeds the current |
| // input byte. |
| </span><span class="kw">let </span>trans = <span class="self">self</span>.transition_within_bound(<span class="kw-2">&</span>node, b); |
| <span class="self">self</span>.stack.push(StreamState { |
| node, |
| trans: trans.unwrap_or_default(), |
| out, |
| aut_state, |
| done: trans.is_none(), |
| }); |
| <span class="kw">return</span>; |
| } |
| } |
| } |
| <span class="kw">if </span><span class="self">self</span>.stack.is_empty() { |
| <span class="kw">return</span>; |
| } |
| <span class="kw">let </span>last = <span class="self">self</span>.stack.len() - <span class="number">1</span>; |
| <span class="kw">let </span>state = <span class="kw-2">&</span><span class="self">self</span>.stack[last]; |
| <span class="kw">let </span>transition = <span class="kw">if </span>!state.done { |
| <span class="self">self</span>.previous_transition(<span class="kw-2">&</span>state.node, state.trans) |
| } <span class="kw">else </span>{ |
| <span class="self">self</span>.last_transition(<span class="kw-2">&</span>state.node) |
| }; |
| <span class="kw">if </span>inclusive { |
| <span class="self">self</span>.stack[last].trans = transition.unwrap_or_default(); |
| <span class="self">self</span>.stack[last].done = transition.is_none(); |
| <span class="self">self</span>.inp.pop(); |
| } <span class="kw">else </span>{ |
| <span class="kw">let </span>next_node = <span class="self">self</span>.fst.node( |
| state.node.transition(transition.unwrap_or_default()).addr, |
| <span class="self">self</span>.data, |
| ); |
| <span class="kw">let </span>starting_transition = <span class="self">self</span>.starting_transition(<span class="kw-2">&</span>next_node); |
| <span class="self">self</span>.stack.push(StreamState { |
| node: next_node, |
| trans: starting_transition.unwrap_or_default(), |
| out, |
| aut_state, |
| done: starting_transition.is_none(), |
| }); |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>next<F, T>(<span class="kw-2">&mut </span><span class="self">self</span>, transform: F) -> <span class="prelude-ty">Option</span><(<span class="kw-2">&</span>[u8], Output, T)> |
| <span class="kw">where |
| </span>F: Fn(<span class="kw-2">&</span>A::State) -> T, |
| { |
| <span class="kw">if </span>!<span class="self">self</span>.reversed { |
| <span class="comment">// Inorder empty output (will be first). |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(out) = <span class="self">self</span>.empty_output.take() { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="kw-2">&</span>[], out, transform(<span class="kw-2">&</span><span class="self">self</span>.aut.start()))); |
| } |
| } |
| <span class="kw">while let </span><span class="prelude-val">Some</span>(state) = <span class="self">self</span>.stack.pop() { |
| <span class="kw">if </span>state.done || !<span class="self">self</span>.aut.can_match(<span class="kw-2">&</span>state.aut_state) { |
| <span class="kw">if </span>state.node.addr() != <span class="self">self</span>.fst.root_addr { |
| <span class="comment">// Reversed return next logic. |
| // If the stack is empty the value should not be returned. |
| </span><span class="kw">if </span><span class="self">self</span>.reversed && !<span class="self">self</span>.stack.is_empty() && state.node.is_final() { |
| <span class="kw">let </span>out_of_bounds = |
| <span class="self">self</span>.min.subceeded_by(<span class="kw-2">&</span><span class="self">self</span>.inp) || <span class="self">self</span>.max.exceeded_by(<span class="kw-2">&</span><span class="self">self</span>.inp); |
| <span class="kw">if </span>!out_of_bounds && <span class="self">self</span>.aut.is_match(<span class="kw-2">&</span>state.aut_state) { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="kw-2">&</span><span class="self">self</span>.inp.pop(), state.out, transform(<span class="kw-2">&</span>state.aut_state))); |
| } |
| } |
| <span class="self">self</span>.inp.pop(); |
| } |
| <span class="kw">continue</span>; |
| } |
| <span class="kw">let </span>trans = state.node.transition(state.trans); |
| <span class="kw">let </span>out = state.out.cat(trans.out); |
| <span class="kw">let </span>next_state = <span class="self">self</span>.aut.accept(<span class="kw-2">&</span>state.aut_state, trans.inp); |
| <span class="kw">let </span>is_match = <span class="self">self</span>.aut.is_match(<span class="kw-2">&</span>next_state); |
| <span class="kw">let </span>next_node = <span class="self">self</span>.fst.node(trans.addr, <span class="self">self</span>.data); |
| <span class="self">self</span>.inp.push(trans.inp); |
| <span class="kw">let </span>current_transition = <span class="self">self</span>.next_transition(<span class="kw-2">&</span>state.node, state.trans); |
| <span class="self">self</span>.stack.push(StreamState { |
| trans: current_transition.unwrap_or_default(), |
| done: current_transition.is_none(), |
| ..state |
| }); |
| <span class="kw">let </span>ns = transform(<span class="kw-2">&</span>next_state); |
| <span class="kw">let </span>next_transition = <span class="self">self</span>.starting_transition(<span class="kw-2">&</span>next_node); |
| <span class="self">self</span>.stack.push(StreamState { |
| node: next_node, |
| trans: next_transition.unwrap_or_default(), |
| out, |
| aut_state: next_state, |
| done: next_transition.is_none(), |
| }); |
| <span class="comment">// Inorder return next logic. |
| </span><span class="kw">if </span>!<span class="self">self</span>.reversed { |
| <span class="kw">if </span><span class="self">self</span>.end_at.exceeded_by(<span class="kw-2">&</span><span class="self">self</span>.inp) { |
| <span class="comment">// We are done, forever. |
| </span><span class="self">self</span>.stack.clear(); |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } <span class="kw">else if </span>!<span class="self">self</span>.reversed && next_node.is_final() && is_match { |
| <span class="kw">return </span><span class="prelude-val">Some</span>((<span class="kw-2">&</span><span class="self">self</span>.inp, out.cat(next_node.final_output()), ns)); |
| } |
| } |
| } |
| <span class="comment">// If we are streaming backward, we still need to return the empty output, if empty is |
| // part of our fst, matches the range and the automaton |
| </span><span class="self">self</span>.empty_output |
| .take() |
| .map(|out| (<span class="kw-2">&</span>[][..], out, transform(<span class="kw-2">&</span><span class="self">self</span>.aut.start()))) |
| } |
| |
| <span class="comment">// The first transition that is in a bound for a given node. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>transition_within_bound(<span class="kw-2">&</span><span class="self">self</span>, node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>, bound: u8) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">let </span><span class="kw-2">mut </span>trans; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(t) = <span class="self">self</span>.starting_transition(<span class="kw-2">&</span>node) { |
| trans = t; |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">loop </span>{ |
| <span class="kw">let </span>transition = node.transition(trans); |
| <span class="kw">if </span>(!<span class="self">self</span>.reversed && transition.inp > bound) |
| || (<span class="self">self</span>.reversed && transition.inp < bound) |
| { |
| <span class="kw">return </span><span class="prelude-val">Some</span>(trans); |
| } <span class="kw">else if let </span><span class="prelude-val">Some</span>(t) = <span class="self">self</span>.next_transition(<span class="kw-2">&</span>node, trans) { |
| trans = t; |
| } <span class="kw">else </span>{ |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| } |
| } |
| |
| <span class="doccomment">/// Resolves value of the empty output. Will be none if the empty output should not be returned. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>resolve_empty_output(<span class="kw-2">&mut </span><span class="self">self</span>, min: <span class="kw-2">&</span>Bound, max: <span class="kw-2">&</span>Bound) -> <span class="prelude-ty">Option</span><Output> { |
| <span class="kw">if </span>min.subceeded_by(<span class="kw-2">&</span>[]) || max.exceeded_by(<span class="kw-2">&</span>[]) { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="kw">let </span>start = <span class="self">self</span>.aut.start(); |
| <span class="kw">if </span>!<span class="self">self</span>.aut.is_match(<span class="kw-2">&</span>start) { |
| <span class="kw">return </span><span class="prelude-val">None</span>; |
| } |
| <span class="self">self</span>.fst.empty_final_output(<span class="self">self</span>.data) |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>starting_transition(<span class="kw-2">&</span><span class="self">self</span>, node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span>node.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else if </span>!<span class="self">self</span>.reversed { |
| <span class="prelude-val">Some</span>(<span class="number">0</span>) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Some</span>(node.len() - <span class="number">1</span>) |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>last_transition(<span class="kw-2">&</span><span class="self">self</span>, node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span>node.is_empty() { |
| <span class="prelude-val">None |
| </span>} <span class="kw">else if </span><span class="self">self</span>.reversed { |
| <span class="prelude-val">Some</span>(<span class="number">0</span>) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">Some</span>(node.len() - <span class="number">1</span>) |
| } |
| } |
| |
| <span class="doccomment">/// Returns the next transition. |
| /// |
| /// The concept of `next` transition is dependent on whether the stream is in reverse mode or |
| /// not. If all the transitions of this node have been emitted, this method returns None. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>next_transition(<span class="kw-2">&</span><span class="self">self</span>, node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>, current_transition: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span><span class="self">self</span>.reversed { |
| <span class="self">Self</span>::backward_transition(node, current_transition) |
| } <span class="kw">else </span>{ |
| <span class="self">Self</span>::forward_transition(node, current_transition) |
| } |
| } |
| |
| <span class="doccomment">/// See `StreamWithState::next_transition`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>previous_transition(<span class="kw-2">&</span><span class="self">self</span>, node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>, current_transition: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span><span class="self">self</span>.reversed { |
| <span class="self">Self</span>::forward_transition(node, current_transition) |
| } <span class="kw">else </span>{ |
| <span class="self">Self</span>::backward_transition(node, current_transition) |
| } |
| } |
| |
| <span class="doccomment">/// Returns the next logical transition. |
| /// |
| /// This is independent from whether the stream is in backward mode or not. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>forward_transition(node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>, current_transition: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span>current_transition + <span class="number">1 </span>< node.len() { |
| <span class="prelude-val">Some</span>(current_transition + <span class="number">1</span>) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| |
| <span class="doccomment">/// See [Stream::forward_transition]. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">fn </span>backward_transition(node: <span class="kw-2">&</span>Node<<span class="lifetime">'f</span>>, current_transition: usize) -> <span class="prelude-ty">Option</span><usize> { |
| <span class="kw">if </span>current_transition > <span class="number">0 </span>&& !node.is_empty() { |
| <span class="prelude-val">Some</span>(current_transition - <span class="number">1</span>) |
| } <span class="kw">else </span>{ |
| <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl</span><<span class="lifetime">'f</span>, <span class="lifetime">'a</span>, A: <span class="lifetime">'a </span>+ Automaton> Streamer<<span class="lifetime">'a</span>> <span class="kw">for </span>StreamWithState<<span class="lifetime">'f</span>, A> |
| <span class="kw">where |
| </span>A::State: Clone, |
| { |
| <span class="kw">type </span>Item = (<span class="kw-2">&</span><span class="lifetime">'a </span>[u8], Output, A::State); |
| |
| <span class="kw">fn </span>next(<span class="kw-2">&</span><span class="lifetime">'a </span><span class="kw-2">mut </span><span class="self">self</span>) -> <span class="prelude-ty">Option</span><<span class="self">Self</span>::Item> { |
| <span class="self">self</span>.next(Clone::clone) |
| } |
| } |
| |
| <span class="doccomment">/// An output is a value that is associated with a key in a finite state |
| /// transducer. |
| /// |
| /// Note that outputs must satisfy an algebra. Namely, it must have an additive |
| /// identity and the following binary operations defined: `prefix`, |
| /// `concatenation` and `subtraction`. `prefix` and `concatenation` are |
| /// commutative while `subtraction` is not. `subtraction` is only defined on |
| /// pairs of operands where the first operand is greater than or equal to the |
| /// second operand. |
| /// |
| /// Currently, output values must be `u64`. However, in theory, an output value |
| /// can be anything that satisfies the above algebra. Future versions of this |
| /// crate may make outputs generic on this algebra. |
| </span><span class="attribute">#[derive(Copy, Clone, Debug, Hash, Eq, Ord, PartialEq, PartialOrd)] |
| </span><span class="kw">pub struct </span>Output(u64); |
| |
| <span class="attribute">#[derive(Clone)] |
| </span><span class="kw">struct </span>Buffer { |
| buf: Box<[u8]>, |
| len: usize, |
| } |
| |
| <span class="kw">impl </span>Buffer { |
| <span class="kw">fn </span>new() -> <span class="self">Self </span>{ |
| Buffer { |
| buf: <span class="macro">vec!</span>[<span class="number">0u8</span>; KEY_BUFFER_CAPACITY].into_boxed_slice(), |
| len: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="kw">fn </span>capacity(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.buf.len() |
| } |
| |
| <span class="kw">fn </span>double_cap(<span class="kw-2">&mut </span><span class="self">self</span>) { |
| <span class="kw">let </span>old_cap = <span class="self">self</span>.capacity(); |
| <span class="kw">let </span>new_cap = old_cap * <span class="number">2</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>new_buf = <span class="macro">vec!</span>[<span class="number">0u8</span>; new_cap].into_boxed_slice(); |
| new_buf[..old_cap].copy_from_slice(<span class="kw-2">&</span><span class="self">self</span>.buf[..old_cap]); |
| mem::replace(<span class="kw-2">&mut </span><span class="self">self</span>.buf, new_buf); |
| } |
| |
| <span class="kw">fn </span>push(<span class="kw-2">&mut </span><span class="self">self</span>, b: u8) { |
| <span class="kw">if </span><span class="self">self</span>.capacity() <= <span class="self">self</span>.len { |
| <span class="self">self</span>.double_cap(); |
| } |
| <span class="self">self</span>.buf[<span class="self">self</span>.len] = b; |
| <span class="self">self</span>.len += <span class="number">1</span>; |
| } |
| |
| <span class="comment">// Pops one byte and returns the entire chain before the byte was popped. |
| </span><span class="kw">fn </span>pop(<span class="kw-2">&mut </span><span class="self">self</span>) -> <span class="kw-2">&</span>[u8] { |
| <span class="kw">let </span>len = <span class="self">self</span>.len; |
| <span class="self">self</span>.len = len - <span class="number">1</span>; |
| <span class="kw-2">&</span><span class="self">self</span>.buf[..len] |
| } |
| } |
| |
| <span class="kw">impl </span>Deref <span class="kw">for </span>Buffer { |
| <span class="kw">type </span>Target = [u8]; |
| |
| <span class="kw">fn </span>deref(<span class="kw-2">&</span><span class="self">self</span>) -> <span class="kw-2">&</span>[u8] { |
| <span class="kw-2">&</span><span class="self">self</span>.buf[..<span class="self">self</span>.len] |
| } |
| } |
| |
| <span class="kw">impl </span>Output { |
| <span class="doccomment">/// Create a new output from a `u64`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>new(v: u64) -> Output { |
| Output(v) |
| } |
| |
| <span class="doccomment">/// Create a zero output. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>zero() -> Output { |
| Output(<span class="number">0</span>) |
| } |
| |
| <span class="doccomment">/// Retrieve the value inside this output. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>value(<span class="self">self</span>) -> u64 { |
| <span class="self">self</span>.<span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Returns true if this is a zero output. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>is_zero(<span class="self">self</span>) -> bool { |
| <span class="self">self</span>.<span class="number">0 </span>== <span class="number">0 |
| </span>} |
| |
| <span class="doccomment">/// Returns the prefix of this output and `o`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>prefix(<span class="self">self</span>, o: Output) -> Output { |
| Output(cmp::min(<span class="self">self</span>.<span class="number">0</span>, o.<span class="number">0</span>)) |
| } |
| |
| <span class="doccomment">/// Returns the concatenation of this output and `o`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>cat(<span class="self">self</span>, o: Output) -> Output { |
| Output(<span class="self">self</span>.<span class="number">0 </span>+ o.<span class="number">0</span>) |
| } |
| |
| <span class="doccomment">/// Returns the subtraction of `o` from this output. |
| /// |
| /// This function panics if `self > o`. |
| </span><span class="attribute">#[inline] |
| </span><span class="kw">pub fn </span>sub(<span class="self">self</span>, o: Output) -> Output { |
| Output( |
| <span class="self">self</span>.<span class="number">0 |
| </span>.checked_sub(o.<span class="number">0</span>) |
| .expect(<span class="string">"BUG: underflow subtraction not allowed"</span>), |
| ) |
| } |
| } |
| |
| <span class="doccomment">/// A transition from one note to another. |
| </span><span class="attribute">#[derive(Copy, Clone, Hash, Eq, PartialEq)] |
| </span><span class="kw">pub struct </span>Transition { |
| <span class="doccomment">/// The byte input associated with this transition. |
| </span><span class="kw">pub </span>inp: u8, |
| <span class="doccomment">/// The output associated with this transition. |
| </span><span class="kw">pub </span>out: Output, |
| <span class="doccomment">/// The address of the node that this transition points to. |
| </span><span class="kw">pub </span>addr: CompiledAddr, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>Transition { |
| <span class="attribute">#[inline] |
| </span><span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| Transition { |
| inp: <span class="number">0</span>, |
| out: Output::zero(), |
| addr: NONE_ADDRESS, |
| } |
| } |
| } |
| |
| <span class="kw">impl </span>fmt::Debug <span class="kw">for </span>Transition { |
| <span class="kw">fn </span>fmt(<span class="kw-2">&</span><span class="self">self</span>, f: <span class="kw-2">&mut </span>fmt::Formatter) -> fmt::Result { |
| <span class="kw">if </span><span class="self">self</span>.out.is_zero() { |
| <span class="macro">write!</span>(f, <span class="string">"{} -> {}"</span>, <span class="self">self</span>.inp <span class="kw">as </span>char, <span class="self">self</span>.addr) |
| } <span class="kw">else </span>{ |
| <span class="macro">write!</span>( |
| f, |
| <span class="string">"({}, {}) -> {}"</span>, |
| <span class="self">self</span>.inp <span class="kw">as </span>char, |
| <span class="self">self</span>.out.value(), |
| <span class="self">self</span>.addr |
| ) |
| } |
| } |
| } |
| |
| <span class="attribute">#[inline] |
| #[cfg(target_pointer_width = <span class="string">"64"</span>)] |
| </span><span class="kw">fn </span>u64_to_usize(n: u64) -> usize { |
| n <span class="kw">as </span>usize |
| } |
| |
| <span class="attribute">#[inline] |
| #[cfg(not(target_pointer_width = <span class="string">"64"</span>))] |
| </span><span class="kw">fn </span>u64_to_usize(n: u64) -> usize { |
| <span class="kw">if </span>n > ::std::usize::MAX <span class="kw">as </span>u64 { |
| <span class="macro">panic!</span>( |
| <span class="string">"\ |
| Cannot convert node address {} to a pointer sized variable. If this FST |
| is very large and was generated on a system with a larger pointer size |
| than this system, then it is not possible to read this FST on this |
| system."</span>, |
| n |
| ); |
| } |
| n <span class="kw">as </span>usize |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy_fst" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |