📄 abstracttracker.html
字号:
<a name="171" href="#171">171</a> <em> * A method for logging current crawler state.</em><a name="172" href="#172">172</a> <em> *</em><a name="173" href="#173">173</a> <em> * This method will be called by run() at intervals specified in</em><a name="174" href="#174">174</a> <em> * the crawl order file. It is also invoked when pausing or</em><a name="175" href="#175">175</a> <em> * stopping a crawl to capture the state at that point. Default behavior is</em><a name="176" href="#176">176</a> <em> * call to {@link CrawlController#logProgressStatistics} so CrawlController</em><a name="177" href="#177">177</a> <em> * can act on progress statistics event.</em><a name="178" href="#178">178</a> <em> * <p></em><a name="179" href="#179">179</a> <em> * It is recommended that for implementations of this method it be</em><a name="180" href="#180">180</a> <em> * carefully considered if it should be synchronized in whole or in</em><a name="181" href="#181">181</a> <em> * part</em><a name="182" href="#182">182</a> <em> * @param e Progress statistics event.</em><a name="183" href="#183">183</a> <em> */</em><a name="184" href="#184">184</a> <strong>protected</strong> <strong>synchronized</strong> <strong>void</strong> progressStatisticsEvent(<strong>final</strong> EventObject e) {<a name="185" href="#185">185</a> <strong>this</strong>.controller.progressStatisticsEvent(e);<a name="186" href="#186">186</a> }<a name="187" href="#187">187</a> <a name="188" href="#188">188</a> <em>/**<em>*</em></em><a name="189" href="#189">189</a> <em> * Get the starting time of the crawl (as given by</em><a name="190" href="#190">190</a> <em> * <code>System.currentTimeMillis()</code> when the crawl started).</em><a name="191" href="#191">191</a> <em> * @return time fo the crawl's start</em><a name="192" href="#192">192</a> <em> */</em><a name="193" href="#193">193</a> <strong>public</strong> <strong>long</strong> getCrawlStartTime() {<a name="194" href="#194">194</a> <strong>return</strong> <strong>this</strong>.crawlerStartTime;<a name="195" href="#195">195</a> }<a name="196" href="#196">196</a> <a name="197" href="#197">197</a> <em>/**<em>*</em></em><a name="198" href="#198">198</a> <em> * If crawl has ended it will return the time it ended (given by</em><a name="199" href="#199">199</a> <em> * <code>System.currentTimeMillis()</code> at that time).</em><a name="200" href="#200">200</a> <em> * <br></em><a name="201" href="#201">201</a> <em> * If crawl is still going on it will return the same as</em><a name="202" href="#202">202</a> <em> * <code>System.currentTimeMillis()</code> at the time of the call.</em><a name="203" href="#203">203</a> <em> * @return The time of the crawl ending or the current time if the crawl has</em><a name="204" href="#204">204</a> <em> * not ended.</em><a name="205" href="#205">205</a> <em> */</em><a name="206" href="#206">206</a> <strong>public</strong> <strong>long</strong> getCrawlEndTime() {<a name="207" href="#207">207</a> <strong>return</strong> (<strong>this</strong>.crawlerEndTime == -1)?<a name="208" href="#208">208</a> System.currentTimeMillis(): <strong>this</strong>.crawlerEndTime;<a name="209" href="#209">209</a> }<a name="210" href="#210">210</a> <a name="211" href="#211">211</a> <em>/**<em>*</em></em><a name="212" href="#212">212</a> <em> * Returns the number of milliseconds that the crawl spent paused or</em><a name="213" href="#213">213</a> <em> * otherwise in a nonactive state.</em><a name="214" href="#214">214</a> <em> * @return the number of msec. that the crawl was paused or otherwise</em><a name="215" href="#215">215</a> <em> * suspended.</em><a name="216" href="#216">216</a> <em> */</em><a name="217" href="#217">217</a> <strong>public</strong> <strong>long</strong> getCrawlTotalPauseTime() {<a name="218" href="#218">218</a> <strong>return</strong> <strong>this</strong>.crawlerTotalPausedTime;<a name="219" href="#219">219</a> }<a name="220" href="#220">220</a> <a name="221" href="#221">221</a> <em>/**<em>*</em></em><a name="222" href="#222">222</a> <em> * Get the time when the the crawl was last paused/suspended (as given by</em><a name="223" href="#223">223</a> <em> * <code>System.currentTimeMillis()</code> at that time). Will be 0 if the</em><a name="224" href="#224">224</a> <em> * crawl is not currently paused.</em><a name="225" href="#225">225</a> <em> * @return time of the crawl's last pause/suspend or 0 if the crawl is not</em><a name="226" href="#226">226</a> <em> * currently paused.</em><a name="227" href="#227">227</a> <em> */</em><a name="228" href="#228">228</a> <strong>public</strong> <strong>long</strong> getCrawlPauseStartedTime() {<a name="229" href="#229">229</a> <strong>return</strong> <strong>this</strong>.crawlerPauseStarted;<a name="230" href="#230">230</a> }<a name="231" href="#231">231</a> <a name="232" href="#232">232</a> <strong>public</strong> <strong>long</strong> getCrawlerTotalElapsedTime() {<a name="233" href="#233">233</a> <strong>if</strong> (getCrawlStartTime() == 0) {<a name="234" href="#234">234</a> <em class="comment">// if no start time set yet, consider elapsed time zero</em><a name="235" href="#235">235</a> <strong>return</strong> 0;<a name="236" href="#236">236</a> }<a name="237" href="#237">237</a> <a name="238" href="#238">238</a> <strong>return</strong> (getCrawlPauseStartedTime() != 0)?<a name="239" href="#239">239</a> <em class="comment">// Are currently paused, calculate time up to last pause</em><a name="240" href="#240">240</a> (getCrawlPauseStartedTime() - getCrawlTotalPauseTime() -<a name="241" href="#241">241</a> getCrawlStartTime()):<a name="242" href="#242">242</a> <em class="comment">// Not paused, calculate total time.</em><a name="243" href="#243">243</a> (getCrawlEndTime() - getCrawlTotalPauseTime() - getCrawlStartTime());<a name="244" href="#244">244</a> }<a name="245" href="#245">245</a> <a name="246" href="#246">246</a> <em>/**<em>*</em></em><a name="247" href="#247">247</a> <em> * The number of seconds to wait between writing snapshot data to log file.</em><a name="248" href="#248">248</a> <em> * @return the number of seconds to wait between writing snapshot data to</em><a name="249" href="#249">249</a> <em> * log file.</em><a name="250" href="#250">250</a> <em> */</em><a name="251" href="#251">251</a> <strong>protected</strong> <strong>int</strong> getLogWriteInterval() {<a name="252" href="#252">252</a> <strong>int</strong> logInterval;<a name="253" href="#253">253</a> <strong>try</strong> {<a name="254" href="#254">254</a> logInterval =<a name="255" href="#255">255</a> ((Integer) getAttribute(<strong>null</strong>, ATTR_STATS_INTERVAL)).intValue();<a name="256" href="#256">256</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="257" href="#257">257</a> logInterval = 10;<a name="258" href="#258">258</a> }<a name="259" href="#259">259</a> <strong>return</strong> logInterval;<a name="260" href="#260">260</a> }<a name="261" href="#261">261</a> <a name="262" href="#262">262</a> <em>/**<em>*</em></em><a name="263" href="#263">263</a> <em> * @see org.archive.crawler.event.CrawlStatusListener#crawlPausing(java.lang.String)</em><a name="264" href="#264">264</a> <em> */</em><a name="265" href="#265">265</a> <strong>public</strong> <strong>void</strong> crawlPausing(String statusMessage) {<a name="266" href="#266">266</a> logNote(<span class="string">"CRAWL WAITING - "</span> + statusMessage);<a name="267" href="#267">267</a> }<a name="268" href="#268">268</a> <a name="269" href="#269">269</a> <strong>protected</strong> <strong>void</strong> logNote(<strong>final</strong> String note) {<a name="270" href="#270">270</a> <strong>this</strong>.controller.logProgressStatistics(<strong>new</strong> <a href="../../../../org/archive/util/PaddingStringBuffer.html">PaddingStringBuffer</a>()<a name="271" href="#271">271</a> .append(ArchiveUtils.TIMESTAMP14.format(<strong>new</strong> Date()))<a name="272" href="#272">272</a> .append(<span class="string">" "</span>)<a name="273" href="#273">273</a> .append(note)<a name="274" href="#274">274</a> .toString());<a name="275" href="#275">275</a> }<a name="276" href="#276">276</a> <a name="277" href="#277">277</a> <strong>public</strong> <strong>void</strong> crawlPaused(String statusMessage) {<a name="278" href="#278">278</a> crawlerPauseStarted = System.currentTimeMillis();<a name="279" href="#279">279</a> progressStatisticsEvent(<strong>new</strong> EventObject(<strong>this</strong>));<a name="280" href="#280">280</a> logNote(<span class="string">"CRAWL PAUSED - "</span> + statusMessage);<a name="281" href="#281">281</a> }<a name="282" href="#282">282</a> <a name="283" href="#283">283</a> <strong>public</strong> <strong>void</strong> crawlResuming(String statusMessage) {<a name="284" href="#284">284</a> tallyCurrentPause();<a name="285" href="#285">285</a> logNote(<span class="string">"CRAWL RESUMED - "</span> + statusMessage);<a name="286" href="#286">286</a> lastLogPointTime = System.currentTimeMillis();<a name="287" href="#287">287</a> }<a name="288" href="#288">288</a> <a name="289" href="#289">289</a> <em>/**<em>*</em></em><a name="290" href="#290">290</a> <em> * For a current pause (if any), add paused time to total and reset</em><a name="291" href="#291">291</a> <em> */</em><a name="292" href="#292">292</a> <strong>protected</strong> <strong>void</strong> tallyCurrentPause() {<a name="293" href="#293">293</a> <strong>if</strong> (<strong>this</strong>.crawlerPauseStarted > 0) {<a name="294" href="#294">294</a> <em class="comment">// Ok, we managed to actually pause before resuming.</em><a name="295" href="#295">295</a> <strong>this</strong>.crawlerTotalPausedTime<a name="296" href="#296">296</a> += (System.currentTimeMillis() - <strong>this</strong>.crawlerPauseStarted);<a name="297" href="#297">297</a> }<a name="298" href="#298">298</a> <strong>this</strong>.crawlerPauseStarted = 0;<a name="299" href="#299">299</a> }<a name="300" href="#300">300</a> <a name="301" href="#301">301</a> <strong>public</strong> <strong>void</strong> crawlEnding(String sExitMessage) {<a name="302" href="#302">302</a> logNote(<span class="string">"CRAWL ENDING - "</span> + sExitMessage);<a name="303" href="#303">303</a> }<a name="304" href="#304">304</a> <a name="305" href="#305">305</a> <em>/**<em>*</em></em><a name="306" href="#306">306</a> <em> * @see org.archive.crawler.event.CrawlStatusListener#crawlEnded(java.lang.String)</em><a name="307" href="#307">307</a> <em> */</em><a name="308" href="#308">308</a> <strong>public</strong> <strong>void</strong> crawlEnded(String sExitMessage) {<a name="309" href="#309">309</a> <em class="comment">// Note the time when the crawl stops.</em><a name="310" href="#310">310</a> crawlerEndTime = System.currentTimeMillis();<a name="311" href="#311">311</a> progressStatisticsEvent(<strong>new</strong> EventObject(<strong>this</strong>));<a name="312" href="#312">312</a> logNote(<span class="string">"CRAWL ENDED - "</span> + sExitMessage);<a name="313" href="#313">313</a> shouldrun = false;<a name="314" href="#314">314</a> dumpReports();<a name="315" href="#315">315</a> finalCleanup();<a name="316" href="#316">316</a> }<a name="317" href="#317">317</a> <a name="318" href="#318">318</a> <strong>public</strong> <strong>void</strong> crawlStarted(String message) {<a name="319" href="#319">319</a> tallyCurrentPause();<a name="320" href="#320">320</a> noteStart();<a name="321" href="#321">321</a> }<a name="322" href="#322">322</a> <a name="323" href="#323">323</a> <em>/**<em>*</em></em><a name="324" href="#324">324</a> <em> * Dump reports, if any, on request or at crawl end. </em><a name="325" href="#325">325</a> <em> */</em><a name="326" href="#326">326</a> <strong>protected</strong> <strong>void</strong> dumpReports() {<a name="327" href="#327">327</a> <em class="comment">// by default do nothing; subclasses may override</em><a name="328" href="#328">328</a> }<a name="329" href="#329">329</a> <a name="330" href="#330">330</a> <em>/**<em>*</em></em><a name="331" href="#331">331</a> <em> * Cleanup resources used, at crawl end. </em><a name="332" href="#332">332</a> <em> */</em><a name="333" href="#333">333</a> <strong>protected</strong> <strong>void</strong> finalCleanup() {<a name="334" href="#334">334</a> controller = <strong>null</strong>; <em class="comment">// Facilitate GC.</em><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> * @see org.archive.crawler.framework.StatisticsTracking#crawlDuration()</em><a name="339" href="#339">339</a> <em> */</em><a name="340" href="#340">340</a> <strong>public</strong> <strong>long</strong> crawlDuration() {<a name="341" href="#341">341</a> <strong>return</strong> getCrawlerTotalElapsedTime();<a name="342" href="#342">342</a> }<a name="343" href="#343">343</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 + -