| <!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/git/checkouts/tantivy-65d0bbbddbbd5d02/433372d/src/indexer/segment_writer.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>segment_writer.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/index.html"><div class="logo-container"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy/index.html"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <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> |
| </pre><pre class="rust"><code><span class="kw">use </span>fastfield_codecs::MonotonicallyMappableToU64; |
| <span class="kw">use </span>itertools::Itertools; |
| |
| <span class="kw">use </span><span class="kw">super</span>::doc_id_mapping::{get_doc_id_mapping_from_field, DocIdMapping}; |
| <span class="kw">use </span><span class="kw">super</span>::operation::AddOperation; |
| <span class="kw">use </span><span class="kw">crate</span>::core::Segment; |
| <span class="kw">use </span><span class="kw">crate</span>::fastfield::FastFieldsWriter; |
| <span class="kw">use </span><span class="kw">crate</span>::fieldnorm::{FieldNormReaders, FieldNormsWriter}; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::json_term_writer::index_json_values; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::segment_serializer::SegmentSerializer; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::{ |
| compute_table_size, serialize_postings, IndexingContext, IndexingPosition, |
| PerFieldPostingsWriter, PostingsWriter, |
| }; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{FieldEntry, FieldType, Schema, Term, Value}; |
| <span class="kw">use </span><span class="kw">crate</span>::store::{StoreReader, StoreWriter}; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{FacetTokenizer, PreTokenizedStream, TextAnalyzer, Tokenizer}; |
| <span class="kw">use crate</span>::{DatePrecision, DocId, Document, Opstamp, SegmentComponent}; |
| |
| <span class="doccomment">/// Computes the initial size of the hash table. |
| /// |
| /// Returns the recommended initial table size as a power of 2. |
| /// |
| /// Note this is a very dumb way to compute log2, but it is easier to proofread that way. |
| </span><span class="kw">fn </span>compute_initial_table_size(per_thread_memory_budget: usize) -> <span class="kw">crate</span>::Result<usize> { |
| <span class="kw">let </span>table_memory_upper_bound = per_thread_memory_budget / <span class="number">3</span>; |
| (<span class="number">10</span>..<span class="number">20</span>) <span class="comment">// We cap it at 2^19 = 512K capacity. |
| </span>.map(|power| <span class="number">1 </span><< power) |
| .take_while(|capacity| compute_table_size(<span class="kw-2">*</span>capacity) < table_memory_upper_bound) |
| .last() |
| .ok_or_else(|| { |
| <span class="kw">crate</span>::TantivyError::InvalidArgument(<span class="macro">format!</span>( |
| <span class="string">"per thread memory budget (={per_thread_memory_budget}) is too small. Raise the \ |
| memory budget or lower the number of threads." |
| </span>)) |
| }) |
| } |
| |
| <span class="kw">fn </span>remap_doc_opstamps( |
| opstamps: Vec<Opstamp>, |
| doc_id_mapping_opt: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ) -> Vec<Opstamp> { |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_mapping_opt) = doc_id_mapping_opt { |
| doc_id_mapping_opt |
| .iter_old_doc_ids() |
| .map(|doc| opstamps[doc <span class="kw">as </span>usize]) |
| .collect() |
| } <span class="kw">else </span>{ |
| opstamps |
| } |
| } |
| |
| <span class="doccomment">/// A `SegmentWriter` is in charge of creating segment index from a |
| /// set of documents. |
| /// |
| /// They creates the postings list in anonymous memory. |
| /// The segment is laid on disk when the segment gets `finalized`. |
| </span><span class="kw">pub struct </span>SegmentWriter { |
| <span class="kw">pub</span>(<span class="kw">crate</span>) max_doc: DocId, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) ctx: IndexingContext, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) per_field_postings_writers: PerFieldPostingsWriter, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) segment_serializer: SegmentSerializer, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) fast_field_writers: FastFieldsWriter, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) fieldnorms_writer: FieldNormsWriter, |
| <span class="kw">pub</span>(<span class="kw">crate</span>) doc_opstamps: Vec<Opstamp>, |
| per_field_text_analyzers: Vec<TextAnalyzer>, |
| term_buffer: Term, |
| schema: Schema, |
| } |
| |
| <span class="kw">impl </span>SegmentWriter { |
| <span class="doccomment">/// Creates a new `SegmentWriter` |
| /// |
| /// The arguments are defined as follows |
| /// |
| /// - memory_budget: most of the segment writer data (terms, and postings lists recorders) |
| /// is stored in a memory arena. This makes it possible for the user to define |
| /// the flushing behavior as a memory limit. |
| /// - segment: The segment being written |
| /// - schema |
| </span><span class="kw">pub fn </span>for_segment( |
| memory_budget_in_bytes: usize, |
| segment: Segment, |
| ) -> <span class="kw">crate</span>::Result<SegmentWriter> { |
| <span class="kw">let </span>schema = segment.schema(); |
| <span class="kw">let </span>tokenizer_manager = segment.index().tokenizers().clone(); |
| <span class="kw">let </span>table_size = compute_initial_table_size(memory_budget_in_bytes)<span class="question-mark">?</span>; |
| <span class="kw">let </span>segment_serializer = SegmentSerializer::for_segment(segment, <span class="bool-val">false</span>)<span class="question-mark">?</span>; |
| <span class="kw">let </span>per_field_postings_writers = PerFieldPostingsWriter::for_schema(<span class="kw-2">&</span>schema); |
| <span class="kw">let </span>per_field_text_analyzers = schema |
| .fields() |
| .map(|(<span class="kw">_</span>, field_entry): (<span class="kw">_</span>, <span class="kw-2">&</span>FieldEntry)| { |
| <span class="kw">let </span>text_options = <span class="kw">match </span>field_entry.field_type() { |
| FieldType::Str(<span class="kw-2">ref </span>text_options) => text_options.get_indexing_options(), |
| FieldType::JsonObject(<span class="kw-2">ref </span>json_object_options) => { |
| json_object_options.get_text_indexing_options() |
| } |
| <span class="kw">_ </span>=> <span class="prelude-val">None</span>, |
| }; |
| text_options |
| .and_then(|text_index_option| { |
| <span class="kw">let </span>tokenizer_name = <span class="kw-2">&</span>text_index_option.tokenizer(); |
| tokenizer_manager.get(tokenizer_name) |
| }) |
| .unwrap_or_default() |
| }) |
| .collect(); |
| <span class="prelude-val">Ok</span>(SegmentWriter { |
| max_doc: <span class="number">0</span>, |
| ctx: IndexingContext::new(table_size), |
| per_field_postings_writers, |
| fieldnorms_writer: FieldNormsWriter::for_schema(<span class="kw-2">&</span>schema), |
| segment_serializer, |
| fast_field_writers: FastFieldsWriter::from_schema(<span class="kw-2">&</span>schema), |
| doc_opstamps: Vec::with_capacity(<span class="number">1_000</span>), |
| per_field_text_analyzers, |
| term_buffer: Term::with_capacity(<span class="number">16</span>), |
| schema, |
| }) |
| } |
| |
| <span class="doccomment">/// Lay on disk the current content of the `SegmentWriter` |
| /// |
| /// Finalize consumes the `SegmentWriter`, so that it cannot |
| /// be used afterwards. |
| </span><span class="kw">pub fn </span>finalize(<span class="kw-2">mut </span><span class="self">self</span>) -> <span class="kw">crate</span>::Result<Vec<u64>> { |
| <span class="self">self</span>.fieldnorms_writer.fill_up_to_max_doc(<span class="self">self</span>.max_doc); |
| <span class="kw">let </span>mapping: <span class="prelude-ty">Option</span><DocIdMapping> = <span class="self">self |
| </span>.segment_serializer |
| .segment() |
| .index() |
| .settings() |
| .sort_by_field |
| .clone() |
| .map(|sort_by_field| get_doc_id_mapping_from_field(sort_by_field, <span class="kw-2">&</span><span class="self">self</span>)) |
| .transpose()<span class="question-mark">?</span>; |
| remap_and_write( |
| <span class="kw-2">&</span><span class="self">self</span>.per_field_postings_writers, |
| <span class="self">self</span>.ctx, |
| <span class="self">self</span>.fast_field_writers, |
| <span class="kw-2">&</span><span class="self">self</span>.fieldnorms_writer, |
| <span class="kw-2">&</span><span class="self">self</span>.schema, |
| <span class="self">self</span>.segment_serializer, |
| mapping.as_ref(), |
| )<span class="question-mark">?</span>; |
| <span class="kw">let </span>doc_opstamps = remap_doc_opstamps(<span class="self">self</span>.doc_opstamps, mapping.as_ref()); |
| <span class="prelude-val">Ok</span>(doc_opstamps) |
| } |
| |
| <span class="kw">pub fn </span>mem_usage(<span class="kw-2">&</span><span class="self">self</span>) -> usize { |
| <span class="self">self</span>.ctx.mem_usage() |
| + <span class="self">self</span>.fieldnorms_writer.mem_usage() |
| + <span class="self">self</span>.fast_field_writers.mem_usage() |
| + <span class="self">self</span>.segment_serializer.mem_usage() |
| } |
| |
| <span class="kw">fn </span>index_document(<span class="kw-2">&mut </span><span class="self">self</span>, doc: <span class="kw-2">&</span>Document) -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span>doc_id = <span class="self">self</span>.max_doc; |
| <span class="kw">let </span>vals_grouped_by_field = doc |
| .field_values() |
| .iter() |
| .sorted_by_key(|el| el.field()) |
| .group_by(|el| el.field()); |
| <span class="kw">for </span>(field, field_values) <span class="kw">in </span><span class="kw-2">&</span>vals_grouped_by_field { |
| <span class="kw">let </span>values = field_values.map(|field_value| field_value.value()); |
| <span class="kw">let </span>field_entry = <span class="self">self</span>.schema.get_field_entry(field); |
| <span class="kw">let </span>make_schema_error = || { |
| <span class="kw">crate</span>::TantivyError::SchemaError(<span class="macro">format!</span>( |
| <span class="string">"Expected a {:?} for field {:?}"</span>, |
| field_entry.field_type().value_type(), |
| field_entry.name() |
| )) |
| }; |
| <span class="kw">if </span>!field_entry.is_indexed() { |
| <span class="kw">continue</span>; |
| } |
| |
| <span class="kw">let </span>(term_buffer, ctx) = (<span class="kw-2">&mut </span><span class="self">self</span>.term_buffer, <span class="kw-2">&mut </span><span class="self">self</span>.ctx); |
| <span class="kw">let </span>postings_writer: <span class="kw-2">&mut </span><span class="kw">dyn </span>PostingsWriter = |
| <span class="self">self</span>.per_field_postings_writers.get_for_field_mut(field); |
| term_buffer.clear_with_field_and_type(field_entry.field_type().value_type(), field); |
| |
| <span class="kw">match </span>field_entry.field_type() { |
| FieldType::Facet(<span class="kw">_</span>) => { |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span>facet = value.as_facet().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| <span class="kw">let </span>facet_str = facet.encoded_str(); |
| <span class="kw">let </span><span class="kw-2">mut </span>unordered_term_id_opt = <span class="prelude-val">None</span>; |
| FacetTokenizer |
| .token_stream(facet_str) |
| .process(<span class="kw-2">&mut </span>|token| { |
| term_buffer.set_text(<span class="kw-2">&</span>token.text); |
| <span class="kw">let </span>unordered_term_id = |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| <span class="comment">// TODO pass indexing context directly in subscribe function |
| </span>unordered_term_id_opt = <span class="prelude-val">Some</span>(unordered_term_id); |
| }); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(unordered_term_id) = unordered_term_id_opt { |
| <span class="self">self</span>.fast_field_writers |
| .get_term_id_writer_mut(field) |
| .expect(<span class="string">"writer for facet missing"</span>) |
| .add_val(unordered_term_id); |
| } |
| } |
| } |
| FieldType::Str(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>indexing_position = IndexingPosition::default(); |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| <span class="kw">let </span><span class="kw-2">mut </span>token_stream = <span class="kw">match </span>value { |
| Value::PreTokStr(tok_str) => { |
| PreTokenizedStream::from(tok_str.clone()).into() |
| } |
| Value::Str(<span class="kw-2">ref </span>text) => { |
| <span class="kw">let </span>text_analyzer = |
| <span class="kw-2">&</span><span class="self">self</span>.per_field_text_analyzers[field.field_id() <span class="kw">as </span>usize]; |
| text_analyzer.token_stream(text) |
| } |
| <span class="kw">_ </span>=> { |
| <span class="kw">continue</span>; |
| } |
| }; |
| |
| <span class="macro">assert!</span>(term_buffer.is_empty()); |
| postings_writer.index_text( |
| doc_id, |
| <span class="kw-2">&mut *</span>token_stream, |
| term_buffer, |
| ctx, |
| <span class="kw-2">&mut </span>indexing_position, |
| <span class="self">self</span>.fast_field_writers.get_term_id_writer_mut(field), |
| ); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer |
| .record(doc_id, field, indexing_position.num_tokens); |
| } |
| } |
| FieldType::U64(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>u64_val = value.as_u64().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_u64(u64_val); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::Date(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>date_val = value.as_date().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_u64(date_val.truncate(DatePrecision::Seconds).to_u64()); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::I64(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>i64_val = value.as_i64().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_i64(i64_val); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::F64(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>f64_val = value.as_f64().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_f64(f64_val); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::Bool(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>bool_val = value.as_bool().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_bool(bool_val); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::Bytes(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>bytes = value.as_bytes().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_bytes(bytes); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| FieldType::JsonObject(json_options) => { |
| <span class="kw">let </span>text_analyzer = <span class="kw-2">&</span><span class="self">self</span>.per_field_text_analyzers[field.field_id() <span class="kw">as </span>usize]; |
| <span class="kw">let </span>json_values_it = |
| values.map(|value| value.as_json().ok_or_else(make_schema_error)); |
| index_json_values( |
| doc_id, |
| json_values_it, |
| text_analyzer, |
| json_options.is_expand_dots_enabled(), |
| term_buffer, |
| postings_writer, |
| ctx, |
| )<span class="question-mark">?</span>; |
| } |
| FieldType::IpAddr(<span class="kw">_</span>) => { |
| <span class="kw">let </span><span class="kw-2">mut </span>num_vals = <span class="number">0</span>; |
| <span class="kw">for </span>value <span class="kw">in </span>values { |
| num_vals += <span class="number">1</span>; |
| <span class="kw">let </span>ip_addr = value.as_ip_addr().ok_or_else(make_schema_error)<span class="question-mark">?</span>; |
| term_buffer.set_ip_addr(ip_addr); |
| postings_writer.subscribe(doc_id, <span class="number">0u32</span>, term_buffer, ctx); |
| } |
| <span class="kw">if </span>field_entry.has_fieldnorms() { |
| <span class="self">self</span>.fieldnorms_writer.record(doc_id, field, num_vals); |
| } |
| } |
| } |
| } |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Indexes a new document |
| /// |
| /// As a user, you should rather use `IndexWriter`'s add_document. |
| </span><span class="kw">pub fn </span>add_document(<span class="kw-2">&mut </span><span class="self">self</span>, add_operation: AddOperation) -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span>doc = add_operation.document; |
| <span class="self">self</span>.doc_opstamps.push(add_operation.opstamp); |
| <span class="self">self</span>.fast_field_writers.add_document(<span class="kw-2">&</span>doc)<span class="question-mark">?</span>; |
| <span class="self">self</span>.index_document(<span class="kw-2">&</span>doc)<span class="question-mark">?</span>; |
| <span class="kw">let </span>doc_writer = <span class="self">self</span>.segment_serializer.get_store_writer(); |
| doc_writer.store(<span class="kw-2">&</span>doc, <span class="kw-2">&</span><span class="self">self</span>.schema)<span class="question-mark">?</span>; |
| <span class="self">self</span>.max_doc += <span class="number">1</span>; |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="doccomment">/// Max doc is |
| /// - the number of documents in the segment assuming there is no deletes |
| /// - the maximum document id (including deleted documents) + 1 |
| /// |
| /// Currently, **tantivy** does not handle deletes anyway, |
| /// so `max_doc == num_docs` |
| </span><span class="kw">pub fn </span>max_doc(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.max_doc |
| } |
| |
| <span class="doccomment">/// Number of documents in the index. |
| /// Deleted documents are not counted. |
| /// |
| /// Currently, **tantivy** does not handle deletes anyway, |
| /// so `max_doc == num_docs` |
| </span><span class="attribute">#[allow(dead_code)] |
| </span><span class="kw">pub fn </span>num_docs(<span class="kw-2">&</span><span class="self">self</span>) -> u32 { |
| <span class="self">self</span>.max_doc |
| } |
| } |
| |
| <span class="doccomment">/// This method is used as a trick to workaround the borrow checker |
| /// Writes a view of a segment by pushing information |
| /// to the `SegmentSerializer`. |
| /// |
| /// `doc_id_map` is used to map to the new doc_id order. |
| </span><span class="kw">fn </span>remap_and_write( |
| per_field_postings_writers: <span class="kw-2">&</span>PerFieldPostingsWriter, |
| ctx: IndexingContext, |
| fast_field_writers: FastFieldsWriter, |
| fieldnorms_writer: <span class="kw-2">&</span>FieldNormsWriter, |
| schema: <span class="kw-2">&</span>Schema, |
| <span class="kw-2">mut </span>serializer: SegmentSerializer, |
| doc_id_map: <span class="prelude-ty">Option</span><<span class="kw-2">&</span>DocIdMapping>, |
| ) -> <span class="kw">crate</span>::Result<()> { |
| <span class="macro">debug!</span>(<span class="string">"remap-and-write"</span>); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() { |
| fieldnorms_writer.serialize(fieldnorms_serializer, doc_id_map)<span class="question-mark">?</span>; |
| } |
| <span class="kw">let </span>fieldnorm_data = serializer |
| .segment() |
| .open_read(SegmentComponent::FieldNorms)<span class="question-mark">?</span>; |
| <span class="kw">let </span>fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)<span class="question-mark">?</span>; |
| <span class="kw">let </span>term_ord_map = serialize_postings( |
| ctx, |
| per_field_postings_writers, |
| fieldnorm_readers, |
| doc_id_map, |
| schema, |
| serializer.get_postings_serializer(), |
| )<span class="question-mark">?</span>; |
| <span class="macro">debug!</span>(<span class="string">"fastfield-serialize"</span>); |
| fast_field_writers.serialize( |
| serializer.get_fast_field_serializer(), |
| <span class="kw-2">&</span>term_ord_map, |
| doc_id_map, |
| )<span class="question-mark">?</span>; |
| |
| <span class="comment">// finalize temp docstore and create version, which reflects the doc_id_map |
| </span><span class="kw">if let </span><span class="prelude-val">Some</span>(doc_id_map) = doc_id_map { |
| <span class="macro">debug!</span>(<span class="string">"resort-docstore"</span>); |
| <span class="kw">let </span>store_write = serializer |
| .segment_mut() |
| .open_write(SegmentComponent::Store)<span class="question-mark">?</span>; |
| <span class="kw">let </span>settings = serializer.segment().index().settings(); |
| <span class="kw">let </span>store_writer = StoreWriter::new( |
| store_write, |
| settings.docstore_compression, |
| settings.docstore_blocksize, |
| settings.docstore_compress_dedicated_thread, |
| )<span class="question-mark">?</span>; |
| <span class="kw">let </span>old_store_writer = std::mem::replace(<span class="kw-2">&mut </span>serializer.store_writer, store_writer); |
| old_store_writer.close()<span class="question-mark">?</span>; |
| <span class="kw">let </span>store_read = StoreReader::open( |
| serializer |
| .segment() |
| .open_read(SegmentComponent::TempStore)<span class="question-mark">?</span>, |
| <span class="number">1</span>, <span class="comment">/* The docstore is configured to have one doc per block, and each doc is accessed |
| * only once: we don't need caching. */ |
| </span>)<span class="question-mark">?</span>; |
| <span class="kw">for </span>old_doc_id <span class="kw">in </span>doc_id_map.iter_old_doc_ids() { |
| <span class="kw">let </span>doc_bytes = store_read.get_document_bytes(old_doc_id)<span class="question-mark">?</span>; |
| serializer.get_store_writer().store_bytes(<span class="kw-2">&</span>doc_bytes)<span class="question-mark">?</span>; |
| } |
| } |
| |
| <span class="macro">debug!</span>(<span class="string">"serializer-close"</span>); |
| serializer.close()<span class="question-mark">?</span>; |
| |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span>std::path::Path; |
| |
| <span class="kw">use </span><span class="kw">super</span>::compute_initial_table_size; |
| <span class="kw">use </span><span class="kw">crate</span>::collector::Count; |
| <span class="kw">use </span><span class="kw">crate</span>::directory::RamDirectory; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::json_term_writer::JsonTermWriter; |
| <span class="kw">use </span><span class="kw">crate</span>::postings::TermInfo; |
| <span class="kw">use </span><span class="kw">crate</span>::query::PhraseQuery; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::{IndexRecordOption, Schema, Type, STORED, STRING, TEXT}; |
| <span class="kw">use </span><span class="kw">crate</span>::store::{Compressor, StoreReader, StoreWriter}; |
| <span class="kw">use </span><span class="kw">crate</span>::time::format_description::well_known::Rfc3339; |
| <span class="kw">use </span><span class="kw">crate</span>::time::OffsetDateTime; |
| <span class="kw">use </span><span class="kw">crate</span>::tokenizer::{PreTokenizedString, Token}; |
| <span class="kw">use crate</span>::{ |
| DateTime, Directory, DocAddress, DocSet, Document, Index, Postings, Term, TERMINATED, |
| }; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_hashmap_size() { |
| <span class="macro">assert_eq!</span>(compute_initial_table_size(<span class="number">100_000</span>).unwrap(), <span class="number">1 </span><< <span class="number">11</span>); |
| <span class="macro">assert_eq!</span>(compute_initial_table_size(<span class="number">1_000_000</span>).unwrap(), <span class="number">1 </span><< <span class="number">14</span>); |
| <span class="macro">assert_eq!</span>(compute_initial_table_size(<span class="number">10_000_000</span>).unwrap(), <span class="number">1 </span><< <span class="number">17</span>); |
| <span class="macro">assert_eq!</span>(compute_initial_table_size(<span class="number">1_000_000_000</span>).unwrap(), <span class="number">1 </span><< <span class="number">19</span>); |
| <span class="macro">assert_eq!</span>(compute_initial_table_size(<span class="number">4_000_000_000</span>).unwrap(), <span class="number">1 </span><< <span class="number">19</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_prepare_for_store() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>text_field = schema_builder.add_text_field(<span class="string">"title"</span>, TEXT | STORED); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc = Document::default(); |
| <span class="kw">let </span>pre_tokenized_text = PreTokenizedString { |
| text: String::from(<span class="string">"A"</span>), |
| tokens: <span class="macro">vec!</span>[Token { |
| offset_from: <span class="number">0</span>, |
| offset_to: <span class="number">1</span>, |
| position: <span class="number">0</span>, |
| text: String::from(<span class="string">"A"</span>), |
| position_length: <span class="number">1</span>, |
| }], |
| }; |
| |
| doc.add_pre_tokenized_text(text_field, pre_tokenized_text); |
| doc.add_text(text_field, <span class="string">"title"</span>); |
| |
| <span class="kw">let </span>path = Path::new(<span class="string">"store"</span>); |
| <span class="kw">let </span>directory = RamDirectory::create(); |
| <span class="kw">let </span>store_wrt = directory.open_write(path).unwrap(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>store_writer = StoreWriter::new(store_wrt, Compressor::None, <span class="number">0</span>, <span class="bool-val">false</span>).unwrap(); |
| store_writer.store(<span class="kw-2">&</span>doc, <span class="kw-2">&</span>schema).unwrap(); |
| store_writer.close().unwrap(); |
| |
| <span class="kw">let </span>reader = StoreReader::open(directory.open_read(path).unwrap(), <span class="number">0</span>).unwrap(); |
| <span class="kw">let </span>doc = reader.get(<span class="number">0</span>).unwrap(); |
| |
| <span class="macro">assert_eq!</span>(doc.field_values().len(), <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(doc.field_values()[<span class="number">0</span>].value().as_text(), <span class="prelude-val">Some</span>(<span class="string">"A"</span>)); |
| <span class="macro">assert_eq!</span>(doc.field_values()[<span class="number">1</span>].value().as_text(), <span class="prelude-val">Some</span>(<span class="string">"title"</span>)); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_json_indexing() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>json_field = schema_builder.add_json_field(<span class="string">"json"</span>, STORED | TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>json_val: serde_json::Map<String, serde_json::Value> = serde_json::from_str( |
| <span class="string">r#"{ |
| "toto": "titi", |
| "float": -0.2, |
| "bool": true, |
| "unsigned": 1, |
| "signed": -2, |
| "complexobject": { |
| "field.with.dot": 1 |
| }, |
| "date": "1985-04-12T23:20:50.52Z", |
| "my_arr": [2, 3, {"my_key": "two tokens"}, 4] |
| }"#</span>, |
| ) |
| .unwrap(); |
| <span class="kw">let </span>doc = <span class="macro">doc!</span>(json_field=>json_val.clone()); |
| <span class="kw">let </span>index = Index::create_in_ram(schema.clone()); |
| <span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests().unwrap(); |
| writer.add_document(doc).unwrap(); |
| writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>doc = searcher |
| .doc(DocAddress { |
| segment_ord: <span class="number">0u32</span>, |
| doc_id: <span class="number">0u32</span>, |
| }) |
| .unwrap(); |
| <span class="kw">let </span>serdeser_json_val = serde_json::from_str::<serde_json::Map<String, serde_json::Value>>( |
| <span class="kw-2">&</span>schema.to_json(<span class="kw-2">&</span>doc), |
| ) |
| .unwrap() |
| .get(<span class="string">"json"</span>) |
| .unwrap()[<span class="number">0</span>] |
| .as_object() |
| .unwrap() |
| .clone(); |
| <span class="macro">assert_eq!</span>(json_val, serdeser_json_val); |
| <span class="kw">let </span>segment_reader = searcher.segment_reader(<span class="number">0u32</span>); |
| <span class="kw">let </span>inv_idx = segment_reader.inverted_index(json_field).unwrap(); |
| <span class="kw">let </span>term_dict = inv_idx.terms(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>term = Term::with_type_and_field(Type::Json, json_field); |
| <span class="kw">let </span><span class="kw-2">mut </span>term_stream = term_dict.stream().unwrap(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>json_term_writer = JsonTermWriter::wrap(<span class="kw-2">&mut </span>term, <span class="bool-val">false</span>); |
| |
| json_term_writer.push_path_segment(<span class="string">"bool"</span>); |
| json_term_writer.set_fast_value(<span class="bool-val">true</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"complexobject"</span>); |
| json_term_writer.push_path_segment(<span class="string">"field.with.dot"</span>); |
| json_term_writer.set_fast_value(<span class="number">1u64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"date"</span>); |
| json_term_writer.set_fast_value(DateTime::from_utc( |
| OffsetDateTime::parse(<span class="string">"1985-04-12T23:20:50.52Z"</span>, <span class="kw-2">&</span>Rfc3339).unwrap(), |
| )); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"float"</span>); |
| json_term_writer.set_fast_value(-<span class="number">0.2f64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"my_arr"</span>); |
| json_term_writer.set_fast_value(<span class="number">2u64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.set_fast_value(<span class="number">3u64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.set_fast_value(<span class="number">4u64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.push_path_segment(<span class="string">"my_key"</span>); |
| json_term_writer.set_str(<span class="string">"tokens"</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.set_str(<span class="string">"two"</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"signed"</span>); |
| json_term_writer.set_fast_value(-<span class="number">2i64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"toto"</span>); |
| json_term_writer.set_str(<span class="string">"titi"</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| |
| json_term_writer.pop_path_segment(); |
| json_term_writer.push_path_segment(<span class="string">"unsigned"</span>); |
| json_term_writer.set_fast_value(<span class="number">1u64</span>); |
| <span class="macro">assert!</span>(term_stream.advance()); |
| <span class="macro">assert_eq!</span>(term_stream.key(), json_term_writer.term().value_bytes()); |
| <span class="macro">assert!</span>(!term_stream.advance()); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_json_tokenized_with_position() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>json_field = schema_builder.add_json_field(<span class="string">"json"</span>, STORED | TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc = Document::default(); |
| <span class="kw">let </span>json_val: serde_json::Map<String, serde_json::Value> = |
| serde_json::from_str(<span class="string">r#"{"mykey": "repeated token token"}"#</span>).unwrap(); |
| doc.add_json_object(json_field, json_val); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests().unwrap(); |
| writer.add_document(doc).unwrap(); |
| writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>segment_reader = searcher.segment_reader(<span class="number">0u32</span>); |
| <span class="kw">let </span>inv_index = segment_reader.inverted_index(json_field).unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>term = Term::with_type_and_field(Type::Json, json_field); |
| <span class="kw">let </span><span class="kw-2">mut </span>json_term_writer = JsonTermWriter::wrap(<span class="kw-2">&mut </span>term, <span class="bool-val">false</span>); |
| json_term_writer.push_path_segment(<span class="string">"mykey"</span>); |
| json_term_writer.set_str(<span class="string">"token"</span>); |
| <span class="kw">let </span>term_info = inv_index |
| .get_term_info(json_term_writer.term()) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>( |
| term_info, |
| TermInfo { |
| doc_freq: <span class="number">1</span>, |
| postings_range: <span class="number">2</span>..<span class="number">4</span>, |
| positions_range: <span class="number">2</span>..<span class="number">5 |
| </span>} |
| ); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = inv_index |
| .read_postings(<span class="kw-2">&</span>term, IndexRecordOption::WithFreqsAndPositions) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>(postings.doc(), <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(postings.term_freq(), <span class="number">2</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| postings.positions(<span class="kw-2">&mut </span>positions); |
| <span class="macro">assert_eq!</span>(<span class="kw-2">&</span>positions[..], <span class="kw-2">&</span>[<span class="number">1</span>, <span class="number">2</span>]); |
| <span class="macro">assert_eq!</span>(postings.advance(), TERMINATED); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_json_raw_no_position() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>json_field = schema_builder.add_json_field(<span class="string">"json"</span>, STRING); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>json_val: serde_json::Map<String, serde_json::Value> = |
| serde_json::from_str(<span class="string">r#"{"mykey": "two tokens"}"#</span>).unwrap(); |
| <span class="kw">let </span>doc = <span class="macro">doc!</span>(json_field=>json_val); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests().unwrap(); |
| writer.add_document(doc).unwrap(); |
| writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>segment_reader = searcher.segment_reader(<span class="number">0u32</span>); |
| <span class="kw">let </span>inv_index = segment_reader.inverted_index(json_field).unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>term = Term::with_type_and_field(Type::Json, json_field); |
| <span class="kw">let </span><span class="kw-2">mut </span>json_term_writer = JsonTermWriter::wrap(<span class="kw-2">&mut </span>term, <span class="bool-val">false</span>); |
| json_term_writer.push_path_segment(<span class="string">"mykey"</span>); |
| json_term_writer.set_str(<span class="string">"two tokens"</span>); |
| <span class="kw">let </span>term_info = inv_index |
| .get_term_info(json_term_writer.term()) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>( |
| term_info, |
| TermInfo { |
| doc_freq: <span class="number">1</span>, |
| postings_range: <span class="number">0</span>..<span class="number">1</span>, |
| positions_range: <span class="number">0</span>..<span class="number">0 |
| </span>} |
| ); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = inv_index |
| .read_postings(<span class="kw-2">&</span>term, IndexRecordOption::WithFreqs) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>(postings.doc(), <span class="number">0</span>); |
| <span class="macro">assert_eq!</span>(postings.term_freq(), <span class="number">1</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| postings.positions(<span class="kw-2">&mut </span>positions); |
| <span class="macro">assert_eq!</span>(postings.advance(), TERMINATED); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_position_overlapping_path() { |
| <span class="comment">// This test checks that we do not end up detecting phrase query due |
| // to several string literal in the same json object being overlapping. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>json_field = schema_builder.add_json_field(<span class="string">"json"</span>, TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>json_val: serde_json::Map<String, serde_json::Value> = serde_json::from_str( |
| <span class="string">r#"{"mykey": [{"field": "hello happy tax payer"}, {"field": "nothello"}]}"#</span>, |
| ) |
| .unwrap(); |
| <span class="kw">let </span>doc = <span class="macro">doc!</span>(json_field=>json_val); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>writer = index.writer_for_tests().unwrap(); |
| writer.add_document(doc).unwrap(); |
| writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span><span class="kw-2">mut </span>term = Term::with_type_and_field(Type::Json, json_field); |
| <span class="kw">let </span><span class="kw-2">mut </span>json_term_writer = JsonTermWriter::wrap(<span class="kw-2">&mut </span>term, <span class="bool-val">false</span>); |
| json_term_writer.push_path_segment(<span class="string">"mykey"</span>); |
| json_term_writer.push_path_segment(<span class="string">"field"</span>); |
| json_term_writer.set_str(<span class="string">"hello"</span>); |
| <span class="kw">let </span>hello_term = json_term_writer.term().clone(); |
| json_term_writer.set_str(<span class="string">"nothello"</span>); |
| <span class="kw">let </span>nothello_term = json_term_writer.term().clone(); |
| json_term_writer.set_str(<span class="string">"happy"</span>); |
| <span class="kw">let </span>happy_term = json_term_writer.term().clone(); |
| <span class="kw">let </span>phrase_query = PhraseQuery::new(<span class="macro">vec!</span>[hello_term, happy_term.clone()]); |
| <span class="macro">assert_eq!</span>(searcher.search(<span class="kw-2">&</span>phrase_query, <span class="kw-2">&</span>Count).unwrap(), <span class="number">1</span>); |
| <span class="kw">let </span>phrase_query = PhraseQuery::new(<span class="macro">vec!</span>[nothello_term, happy_term]); |
| <span class="macro">assert_eq!</span>(searcher.search(<span class="kw-2">&</span>phrase_query, <span class="kw-2">&</span>Count).unwrap(), <span class="number">0</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_bug_regression_1629_position_when_array_with_a_field_value_that_does_not_contain_any_token( |
| ) { |
| <span class="comment">// We experienced a bug where we would have a position underflow when computing position |
| // delta in an horrible corner case. |
| // |
| // See the commit with this unit test if you want the details. |
| </span><span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>text = schema_builder.add_text_field(<span class="string">"text"</span>, TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span>doc = schema |
| .parse_document(<span class="string">r#"{"text": [ "bbb", "aaa", "", "aaa"]}"#</span>) |
| .unwrap(); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests().unwrap(); |
| index_writer.add_document(doc).unwrap(); |
| <span class="comment">// On debug this did panic on the underflow |
| </span>index_writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>seg_reader = searcher.segment_reader(<span class="number">0</span>); |
| <span class="kw">let </span>inv_index = seg_reader.inverted_index(text).unwrap(); |
| <span class="kw">let </span>term = Term::from_field_text(text, <span class="string">"aaa"</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = inv_index |
| .read_postings(<span class="kw-2">&</span>term, IndexRecordOption::WithFreqsAndPositions) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>(postings.doc(), <span class="number">0u32</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| postings.positions(<span class="kw-2">&mut </span>positions); |
| <span class="comment">// On release this was [2, 1]. (< note the decreasing values) |
| </span><span class="macro">assert_eq!</span>(positions, <span class="kw-2">&</span>[<span class="number">2</span>, <span class="number">5</span>]); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_multiple_field_value_and_long_tokens() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>text = schema_builder.add_text_field(<span class="string">"text"</span>, TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc = Document::default(); |
| <span class="comment">// This is a bit of a contrived example. |
| </span><span class="kw">let </span>tokens = PreTokenizedString { |
| text: <span class="string">"roller-coaster"</span>.to_string(), |
| tokens: <span class="macro">vec!</span>[Token { |
| offset_from: <span class="number">0</span>, |
| offset_to: <span class="number">14</span>, |
| position: <span class="number">0</span>, |
| text: <span class="string">"rollercoaster"</span>.to_string(), |
| position_length: <span class="number">2</span>, |
| }], |
| }; |
| doc.add_pre_tokenized_text(text, tokens.clone()); |
| doc.add_pre_tokenized_text(text, tokens); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests().unwrap(); |
| index_writer.add_document(doc).unwrap(); |
| index_writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>seg_reader = searcher.segment_reader(<span class="number">0</span>); |
| <span class="kw">let </span>inv_index = seg_reader.inverted_index(text).unwrap(); |
| <span class="kw">let </span>term = Term::from_field_text(text, <span class="string">"rollercoaster"</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = inv_index |
| .read_postings(<span class="kw-2">&</span>term, IndexRecordOption::WithFreqsAndPositions) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>(postings.doc(), <span class="number">0u32</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| postings.positions(<span class="kw-2">&mut </span>positions); |
| <span class="macro">assert_eq!</span>(positions, <span class="kw-2">&</span>[<span class="number">0</span>, <span class="number">3</span>]); <span class="comment">//< as opposed to 0, 2 if we had a position length of 1. |
| </span>} |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_last_token_not_ending_last() { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = Schema::builder(); |
| <span class="kw">let </span>text = schema_builder.add_text_field(<span class="string">"text"</span>, TEXT); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| <span class="kw">let </span><span class="kw-2">mut </span>doc = Document::default(); |
| <span class="comment">// This is a bit of a contrived example. |
| </span><span class="kw">let </span>tokens = PreTokenizedString { |
| text: <span class="string">"contrived-example"</span>.to_string(), <span class="comment">//< I can't think of a use case where this corner case happens in real life. |
| </span>tokens: <span class="macro">vec!</span>[Token { <span class="comment">// Not the last token, yet ends after the last token. |
| </span>offset_from: <span class="number">0</span>, |
| offset_to: <span class="number">14</span>, |
| position: <span class="number">0</span>, |
| text: <span class="string">"long_token"</span>.to_string(), |
| position_length: <span class="number">3</span>, |
| }, |
| Token { |
| offset_from: <span class="number">0</span>, |
| offset_to: <span class="number">14</span>, |
| position: <span class="number">1</span>, |
| text: <span class="string">"short"</span>.to_string(), |
| position_length: <span class="number">1</span>, |
| }], |
| }; |
| doc.add_pre_tokenized_text(text, tokens); |
| doc.add_text(text, <span class="string">"hello"</span>); |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests().unwrap(); |
| index_writer.add_document(doc).unwrap(); |
| index_writer.commit().unwrap(); |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>seg_reader = searcher.segment_reader(<span class="number">0</span>); |
| <span class="kw">let </span>inv_index = seg_reader.inverted_index(text).unwrap(); |
| <span class="kw">let </span>term = Term::from_field_text(text, <span class="string">"hello"</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>postings = inv_index |
| .read_postings(<span class="kw-2">&</span>term, IndexRecordOption::WithFreqsAndPositions) |
| .unwrap() |
| .unwrap(); |
| <span class="macro">assert_eq!</span>(postings.doc(), <span class="number">0u32</span>); |
| <span class="kw">let </span><span class="kw-2">mut </span>positions = Vec::new(); |
| postings.positions(<span class="kw-2">&mut </span>positions); |
| <span class="macro">assert_eq!</span>(positions, <span class="kw-2">&</span>[<span class="number">4</span>]); <span class="comment">//< as opposed to 3 if we had a position length of 1. |
| </span>} |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
