⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 adaptiverevisitqueuelist.html

📁 一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫
💻 HTML
📖 第 1 页 / 共 3 页
字号:
<a name="308" href="#308">308</a>         Iterator it = hostQueues.keySet().iterator();<a name="309" href="#309">309</a>         <strong>long</strong> count = 0;<a name="310" href="#310">310</a>         <strong>while</strong>(it.hasNext()){<a name="311" href="#311">311</a>             AdaptiveRevisitHostQueueWrapper wrapper =<a name="312" href="#312">312</a>                 (AdaptiveRevisitHostQueueWrapper)it.next();<a name="313" href="#313">313</a>             count += wrapper.hq.getSize();<a name="314" href="#314">314</a>         }<a name="315" href="#315">315</a>         <strong>return</strong> count;<a name="316" href="#316">316</a>     }<a name="317" href="#317">317</a>         <a name="318" href="#318">318</a>     <em>/**<em>*</em></em><a name="319" href="#319">319</a> <em>     * This class wraps an AdaptiveRevisitHostQueue with a fixed value for next</em><a name="320" href="#320">320</a> <em>     * ready time.</em><a name="321" href="#321">321</a> <em>     * This is done to facilitate sorting by making sure that the value does </em><a name="322" href="#322">322</a> <em>     * not change while the HQ is in the sorted list. With this wrapper, it</em><a name="323" href="#323">323</a> <em>     * is possible to remove it from the sorted list, then update the time of</em><a name="324" href="#324">324</a> <em>     * next ready, and then readd (resort) it. </em><a name="325" href="#325">325</a> <em>     *</em><a name="326" href="#326">326</a> <em>     * @author Kristinn Sigurdsson</em><a name="327" href="#327">327</a> <em>     */</em><a name="328" href="#328">328</a>     <strong>private</strong> <strong>class</strong> AdaptiveRevisitHostQueueWrapper implements Comparable{<a name="329" href="#329">329</a>         <strong>long</strong> nextReadyTime;<a name="330" href="#330">330</a>         <a href="../../../../org/archive/crawler/frontier/AdaptiveRevisitHostQueue.html">AdaptiveRevisitHostQueue</a> hq;<a name="331" href="#331">331</a>         <a name="332" href="#332">332</a>         <strong>public</strong> AdaptiveRevisitHostQueueWrapper(<a href="../../../../org/archive/crawler/frontier/AdaptiveRevisitHostQueue.html">AdaptiveRevisitHostQueue</a> hq){<a name="333" href="#333">333</a>             nextReadyTime = hq.getNextReadyTime();<a name="334" href="#334">334</a>             <strong>this</strong>.hq = hq;<a name="335" href="#335">335</a>         }<a name="336" href="#336">336</a>         <a name="337" href="#337">337</a>         <em>/**<em>*</em></em><a name="338" href="#338">338</a> <em>         * Compares the this ARHQWrapper to the supplied one.</em><a name="339" href="#339">339</a> <em>         * </em><a name="340" href="#340">340</a> <em>         * @param obj the HQ to compare to. If this object is not an instance</em><a name="341" href="#341">341</a> <em>         *             of ARHostQueueWrapper then the method will throw a </em><a name="342" href="#342">342</a> <em>         *             ClassCastException.</em><a name="343" href="#343">343</a> <em>         * @return a value less than 0 if this HQWrappers time of next ready</em><a name="344" href="#344">344</a> <em>         *         value is less than the argument HQWrappers's; and a value </em><a name="345" href="#345">345</a> <em>         *         greater than 0 if this value is greater. If the time of</em><a name="346" href="#346">346</a> <em>         *         next ready is equal, the hostName strings will be compared</em><a name="347" href="#347">347</a> <em>         *         and that result returned.</em><a name="348" href="#348">348</a> <em>         */</em><a name="349" href="#349">349</a>         <strong>public</strong> <strong>int</strong> compareTo(Object obj){<a name="350" href="#350">350</a>             AdaptiveRevisitHostQueueWrapper comp =<a name="351" href="#351">351</a>                 (AdaptiveRevisitHostQueueWrapper)obj;<a name="352" href="#352">352</a> <a name="353" href="#353">353</a>             <strong>long</strong> compTime = comp.nextReadyTime;<a name="354" href="#354">354</a>             <a name="355" href="#355">355</a>             <strong>if</strong>(nextReadyTime>compTime){<a name="356" href="#356">356</a>                 <strong>return</strong> 1;<a name="357" href="#357">357</a>             } <strong>else</strong> <strong>if</strong>(nextReadyTime&lt;compTime){<a name="358" href="#358">358</a>                 <strong>return</strong> -1;<a name="359" href="#359">359</a>             } <strong>else</strong> {<a name="360" href="#360">360</a>                 <em class="comment">// Equal time. Use hostnames</em><a name="361" href="#361">361</a>                 <strong>return</strong> hq.getHostName().compareTo(comp.hq.getHostName());<a name="362" href="#362">362</a>             }<a name="363" href="#363">363</a>         }<a name="364" href="#364">364</a>     }<a name="365" href="#365">365</a>     <a name="366" href="#366">366</a>     <em>/**<em>*</em></em><a name="367" href="#367">367</a> <em>     * Closes all HQs and the Environment. </em><a name="368" href="#368">368</a> <em>     */</em><a name="369" href="#369">369</a>     <strong>public</strong> <strong>void</strong> close(){<a name="370" href="#370">370</a>         Iterator it = sortedHostQueues.iterator();<a name="371" href="#371">371</a>         <strong>while</strong>(it.hasNext()){<a name="372" href="#372">372</a>             <a href="../../../../org/archive/crawler/frontier/AdaptiveRevisitHostQueue.html">AdaptiveRevisitHostQueue</a> hq =<a name="373" href="#373">373</a>                 ((AdaptiveRevisitHostQueueWrapper)it.next()).hq;<a name="374" href="#374">374</a>             <strong>try</strong> {<a name="375" href="#375">375</a>                 hq.close();<a name="376" href="#376">376</a>             } <strong>catch</strong> (IOException e) {<a name="377" href="#377">377</a>                 logger.severe(<span class="string">"IOException while closing "</span> + hq.getHostName() +<a name="378" href="#378">378</a>                         <span class="string">"\n"</span> + e.getMessage());<a name="379" href="#379">379</a>             }<a name="380" href="#380">380</a>         }<a name="381" href="#381">381</a>         <strong>try</strong> {<a name="382" href="#382">382</a>             hostNamesDB.close();<a name="383" href="#383">383</a>         } <strong>catch</strong> (DatabaseException e) {<a name="384" href="#384">384</a>             logger.severe(<span class="string">"IOException while closing hostNamesDB"</span> +<a name="385" href="#385">385</a>                     <span class="string">"\n"</span> + e.getMessage());<a name="386" href="#386">386</a>         }<a name="387" href="#387">387</a>     }<a name="388" href="#388">388</a>     <a name="389" href="#389">389</a>     <em class="comment">//</em><a name="390" href="#390">390</a>     <em class="comment">// Reporter implementation</em><a name="391" href="#391">391</a>     <em class="comment">//</em><a name="392" href="#392">392</a>     <a name="393" href="#393">393</a>     <strong>public</strong> String[] getReports() {<a name="394" href="#394">394</a>         <em class="comment">// none but default for now</em><a name="395" href="#395">395</a>         <strong>return</strong> <strong>new</strong> String[] {};<a name="396" href="#396">396</a>     }<a name="397" href="#397">397</a>     <a name="398" href="#398">398</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="399" href="#399">399</a> <em class="comment">     * @see org.archive.util.Reporter#singleLineReport()</em><a name="400" href="#400">400</a> <em class="comment">     */</em><a name="401" href="#401">401</a>     <strong>public</strong> String singleLineReport() {<a name="402" href="#402">402</a>         <strong>return</strong> ArchiveUtils.singleLineReport(<strong>this</strong>);<a name="403" href="#403">403</a>     }<a name="404" href="#404">404</a> <a name="405" href="#405">405</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="406" href="#406">406</a> <em class="comment">     * @see org.archive.util.Reporter#reportTo(java.io.Writer)</em><a name="407" href="#407">407</a> <em class="comment">     */</em><a name="408" href="#408">408</a>     <strong>public</strong> <strong>void</strong> reportTo(PrintWriter writer) {<a name="409" href="#409">409</a>         Iterator it = sortedHostQueues.iterator();<a name="410" href="#410">410</a>         <strong>while</strong>(it.hasNext()){<a name="411" href="#411">411</a>             AdaptiveRevisitHostQueueWrapper wrapper =<a name="412" href="#412">412</a>                 (AdaptiveRevisitHostQueueWrapper)it.next();<a name="413" href="#413">413</a>           <a name="414" href="#414">414</a>             writer.print(wrapper.hq.report(10));<a name="415" href="#415">415</a>             writer.print(<span class="string">"\n\n"</span>);<a name="416" href="#416">416</a>         }<a name="417" href="#417">417</a>     }<a name="418" href="#418">418</a>     <a name="419" href="#419">419</a>     <strong>public</strong> <strong>void</strong> reportTo(String name, PrintWriter writer) {<a name="420" href="#420">420</a>         <strong>if</strong>(name==<strong>null</strong> || hostQueues.containsKey(name)==false){<a name="421" href="#421">421</a>         	reportTo(writer);<a name="422" href="#422">422</a>         } <strong>else</strong> {<a name="423" href="#423">423</a> 	    	AdaptiveRevisitHostQueueWrapper wrapper =<a name="424" href="#424">424</a> 	                (AdaptiveRevisitHostQueueWrapper)hostQueues.get(name);<a name="425" href="#425">425</a> 	          <a name="426" href="#426">426</a> 	        writer.print(wrapper.hq.report(0));<a name="427" href="#427">427</a> 	        writer.print(<span class="string">"\n\n"</span>);<a name="428" href="#428">428</a>         }<a name="429" href="#429">429</a>     }<a name="430" href="#430">430</a>     <a name="431" href="#431">431</a>     <strong>public</strong> <strong>void</strong> singleLineReportTo(PrintWriter writer) {<a name="432" href="#432">432</a>         Iterator it = sortedHostQueues.iterator();<a name="433" href="#433">433</a>         <strong>int</strong> total = 0;<a name="434" href="#434">434</a>         <strong>int</strong> ready = 0;<a name="435" href="#435">435</a>         <strong>int</strong> snoozed = 0;<a name="436" href="#436">436</a>         <strong>int</strong> empty = 0;<a name="437" href="#437">437</a>         <strong>int</strong> busy = 0;<a name="438" href="#438">438</a>         <strong>while</strong>(it.hasNext()){<a name="439" href="#439">439</a>             AdaptiveRevisitHostQueueWrapper wrapper =<a name="440" href="#440">440</a>                 (AdaptiveRevisitHostQueueWrapper)it.next();<a name="441" href="#441">441</a>             total++;<a name="442" href="#442">442</a>             <strong>switch</strong>(wrapper.hq.getState()){<a name="443" href="#443">443</a>                 <strong>case</strong> AdaptiveRevisitHostQueue.HQSTATE_BUSY : busy++; <strong>break</strong>;<a name="444" href="#444">444</a>                 <strong>case</strong> AdaptiveRevisitHostQueue.HQSTATE_EMPTY : empty++; <strong>break</strong>;<a name="445" href="#445">445</a>                 <strong>case</strong> AdaptiveRevisitHostQueue.HQSTATE_READY : ready++; <strong>break</strong>;<a name="446" href="#446">446</a>                 <strong>case</strong> AdaptiveRevisitHostQueue.HQSTATE_SNOOZED : snoozed++; <strong>break</strong>;<a name="447" href="#447">447</a>             }<a name="448" href="#448">448</a>         }<a name="449" href="#449">449</a>         writer.print(total + <span class="string">" queues: "</span> + ready + <span class="string">" ready, "</span> + snoozed + <a name="450" href="#450">450</a>             <span class="string">" snoozed, "</span> + busy + <span class="string">" busy, and "</span> + empty + <span class="string">" empty"</span>);<a name="451" href="#451">451</a>     }<a name="452" href="#452">452</a>     <a name="453" href="#453">453</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="454" href="#454">454</a> <em class="comment">     * @see org.archive.util.Reporter#singleLineLegend()</em><a name="455" href="#455">455</a> <em class="comment">     */</em><a name="456" href="#456">456</a>     <strong>public</strong> String singleLineLegend() {<a name="457" href="#457">457</a>         <strong>return</strong> <span class="string">"total ready snoozed busy empty"</span>;<a name="458" href="#458">458</a>     }<a name="459" href="#459">459</a> <a name="460" href="#460">460</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -