⭐ 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

📄 writerpoolprocessor.html

📁 用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧
💻 HTML
📖 第 1 页 / 共 3 页
字号:
<a name="171" href="#171">171</a>                 WriterPoolMember.DEFAULT_PREFIX));<a name="172" href="#172">172</a>         e = addElementToDefinition(<a name="173" href="#173">173</a>             <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_SUFFIX, <span class="string">"Suffix to tag onto "</span> +<a name="174" href="#174">174</a>                 <span class="string">"files. If value is '${HOSTNAME}', will use hostname for "</span> +<a name="175" href="#175">175</a>                 <span class="string">"suffix. If empty, no suffix will be added."</span>,<a name="176" href="#176">176</a>                 WriterPoolMember.DEFAULT_SUFFIX));<a name="177" href="#177">177</a>         e.setOverrideable(false);<a name="178" href="#178">178</a>         e = addElementToDefinition(<a name="179" href="#179">179</a>             <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_MAX_SIZE_BYTES, <span class="string">"Max size of each file"</span>,<a name="180" href="#180">180</a>                 <strong>new</strong> Integer(DEFAULT_MAX_FILE_SIZE)));<a name="181" href="#181">181</a>         e.setOverrideable(false);<a name="182" href="#182">182</a>         e = addElementToDefinition(<a name="183" href="#183">183</a>             <strong>new</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a>(ATTR_PATH, <span class="string">"Where to files. "</span> +<a name="184" href="#184">184</a>                 <span class="string">"Supply absolute or relative path.  If relative, files "</span> +<a name="185" href="#185">185</a>                 <span class="string">"will be written relative to "</span> +<a name="186" href="#186">186</a>                 <span class="string">"the "</span> + CrawlOrder.ATTR_DISK_PATH + <span class="string">"setting."</span> +<a name="187" href="#187">187</a>                 <span class="string">" If more than one path specified, we'll round-robin"</span> +<a name="188" href="#188">188</a>                 <span class="string">" dropping files to each.  This setting is safe"</span> +<a name="189" href="#189">189</a>                 <span class="string">" to change midcrawl (You can remove and add new dirs"</span> +<a name="190" href="#190">190</a>                 <span class="string">" as the crawler progresses)."</span>, getDefaultPath()));<a name="191" href="#191">191</a>         e.setOverrideable(false);<a name="192" href="#192">192</a>         e = addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_POOL_MAX_ACTIVE,<a name="193" href="#193">193</a>             <span class="string">"Maximum active files in pool. "</span> +<a name="194" href="#194">194</a>             <span class="string">"This setting cannot be varied over the life of a crawl."</span>,<a name="195" href="#195">195</a>             <strong>new</strong> Integer(WriterPool.DEFAULT_MAX_ACTIVE)));<a name="196" href="#196">196</a>         e.setOverrideable(false);<a name="197" href="#197">197</a>         e = addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_POOL_MAX_WAIT,<a name="198" href="#198">198</a>             <span class="string">"Maximum time to wait on pool element"</span> +<a name="199" href="#199">199</a>             <span class="string">" (milliseconds). This setting cannot be varied over the life"</span> +<a name="200" href="#200">200</a>             <span class="string">" of a crawl."</span>,<a name="201" href="#201">201</a>             <strong>new</strong> Integer(WriterPool.DEFAULT_MAXIMUM_WAIT)));<a name="202" href="#202">202</a>         e.setOverrideable(false);<a name="203" href="#203">203</a>         e = addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_MAX_BYTES_WRITTEN,<a name="204" href="#204">204</a>             <span class="string">"Total file bytes to write to disk."</span> +<a name="205" href="#205">205</a>             <span class="string">" Once the size of all files on disk has exceeded this "</span> +<a name="206" href="#206">206</a>             <span class="string">"limit, this processor will stop the crawler. "</span> +<a name="207" href="#207">207</a>             <span class="string">"A value of zero means no upper limit."</span>, <strong>new</strong> Long(0)));<a name="208" href="#208">208</a>         e.setOverrideable(false);<a name="209" href="#209">209</a>         e.setExpertSetting(<strong>true</strong>);<a name="210" href="#210">210</a>     }<a name="211" href="#211">211</a>     <a name="212" href="#212">212</a>     <strong>protected</strong> String [] getDefaultPath() {<a name="213" href="#213">213</a>     	<strong>return</strong> DEFAULT_PATH;<a name="214" href="#214">214</a> 	}<a name="215" href="#215">215</a> <a name="216" href="#216">216</a>     <strong>public</strong> <strong>synchronized</strong> <strong>void</strong> initialTasks() {<a name="217" href="#217">217</a>         <em class="comment">// Add this class to crawl state listeners and setup pool.</em><a name="218" href="#218">218</a>         getSettingsHandler().getOrder().getController().<a name="219" href="#219">219</a>             addCrawlStatusListener(<strong>this</strong>);<a name="220" href="#220">220</a>         setupPool(<strong>new</strong> AtomicInteger());<a name="221" href="#221">221</a>         <em class="comment">// Run checkpoint recovery code.</em><a name="222" href="#222">222</a>         <strong>if</strong> (getSettingsHandler().getOrder().getController().<a name="223" href="#223">223</a>         		isCheckpointRecover()) {<a name="224" href="#224">224</a>         	checkpointRecover();<a name="225" href="#225">225</a>         }<a name="226" href="#226">226</a>     }<a name="227" href="#227">227</a>     <a name="228" href="#228">228</a>     <strong>protected</strong> AtomicInteger getSerialNo() {<a name="229" href="#229">229</a>         <strong>return</strong> ((WriterPool)getPool()).getSerialNo();<a name="230" href="#230">230</a>     }<a name="231" href="#231">231</a> <a name="232" href="#232">232</a>     <em>/**<em>*</em></em><a name="233" href="#233">233</a> <em>     * Set up pool of files.</em><a name="234" href="#234">234</a> <em>     */</em><a name="235" href="#235">235</a>     <strong>protected</strong> <strong>abstract</strong> <strong>void</strong> setupPool(<strong>final</strong> AtomicInteger serialNo);<a name="236" href="#236">236</a> <a name="237" href="#237">237</a>     <em>/**<em>*</em></em><a name="238" href="#238">238</a> <em>     * Writes a CrawlURI and its associated data to store file.</em><a name="239" href="#239">239</a> <em>     *</em><a name="240" href="#240">240</a> <em>     * Currently this method understands the following uri types: dns, http, </em><a name="241" href="#241">241</a> <em>     * and https.</em><a name="242" href="#242">242</a> <em>     *</em><a name="243" href="#243">243</a> <em>     * @param curi CrawlURI to process.</em><a name="244" href="#244">244</a> <em>     */</em><a name="245" href="#245">245</a>     <strong>protected</strong> <strong>abstract</strong> <strong>void</strong> innerProcess(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi);<a name="246" href="#246">246</a>     <a name="247" href="#247">247</a>     <strong>protected</strong> <strong>void</strong> checkBytesWritten() {<a name="248" href="#248">248</a>         <strong>long</strong> max = getMaxToWrite();<a name="249" href="#249">249</a>         <strong>if</strong> (max &lt;= 0) {<a name="250" href="#250">250</a>             <strong>return</strong>;<a name="251" href="#251">251</a>         }<a name="252" href="#252">252</a>         <strong>if</strong> (max &lt;= <strong>this</strong>.totalBytesWritten) {<a name="253" href="#253">253</a>             getController().requestCrawlStop(<span class="string">"Finished - Maximum bytes ("</span> +<a name="254" href="#254">254</a>                 Long.toString(max) + <span class="string">") written"</span>);<a name="255" href="#255">255</a>         }<a name="256" href="#256">256</a>     }<a name="257" href="#257">257</a>     <a name="258" href="#258">258</a>     <strong>protected</strong> String getHostAddress(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="259" href="#259">259</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlHost.html">CrawlHost</a> h = getController().getServerCache().getHostFor(curi);<a name="260" href="#260">260</a>         <strong>if</strong> (h == <strong>null</strong>) {<a name="261" href="#261">261</a>             <strong>throw</strong> <strong>new</strong> NullPointerException(<span class="string">"Crawlhost is null for "</span> +<a name="262" href="#262">262</a>                 curi + <span class="string">" "</span> + curi.getVia());<a name="263" href="#263">263</a>         }<a name="264" href="#264">264</a>         InetAddress a = h.getIP();<a name="265" href="#265">265</a>         <strong>if</strong> (a == <strong>null</strong>) {<a name="266" href="#266">266</a>             <strong>throw</strong> <strong>new</strong> NullPointerException(<span class="string">"Address is null for "</span> +<a name="267" href="#267">267</a>                 curi + <span class="string">" "</span> + curi.getVia() + <span class="string">". Address "</span> +<a name="268" href="#268">268</a>                 ((h.getIpFetched() == CrawlHost.IP_NEVER_LOOKED_UP)?<a name="269" href="#269">269</a>                      <span class="string">"was never looked up."</span>:<a name="270" href="#270">270</a>                      (System.currentTimeMillis() - h.getIpFetched()) +<a name="271" href="#271">271</a>                          <span class="string">" ms ago."</span>));<a name="272" href="#272">272</a>         }<a name="273" href="#273">273</a>         <strong>return</strong> h.getIP().getHostAddress();<a name="274" href="#274">274</a>     }<a name="275" href="#275">275</a>     <a name="276" href="#276">276</a>     <em>/**<em>*</em></em><a name="277" href="#277">277</a> <em>     * Version of getAttributes that catches and logs exceptions</em><a name="278" href="#278">278</a> <em>     * and returns null if failure to fetch the attribute.</em><a name="279" href="#279">279</a> <em>     * @param name Attribute name.</em><a name="280" href="#280">280</a> <em>     * @return Attribute or null.</em><a name="281" href="#281">281</a> <em>     */</em><a name="282" href="#282">282</a>     <strong>public</strong> Object getAttributeUnchecked(String name) {<a name="283" href="#283">283</a>         Object result = <strong>null</strong>;<a name="284" href="#284">284</a>         <strong>try</strong> {<a name="285" href="#285">285</a>             result = <strong>super</strong>.getAttribute(name);<a name="286" href="#286">286</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="287" href="#287">287</a>             logger.warning(e.getLocalizedMessage());<a name="288" href="#288">288</a>         } <strong>catch</strong> (MBeanException e) {<a name="289" href="#289">289</a>             logger.warning(e.getLocalizedMessage());<a name="290" href="#290">290</a>         } <strong>catch</strong> (ReflectionException e) {<a name="291" href="#291">291</a>             logger.warning(e.getLocalizedMessage());<a name="292" href="#292">292</a>         }<a name="293" href="#293">293</a>         <strong>return</strong> result;<a name="294" href="#294">294</a>     }<a name="295" href="#295">295</a> <a name="296" href="#296">296</a>    <em>/**<em>*</em></em><a name="297" href="#297">297</a> <em>    * Max size we want files to be (bytes).</em><a name="298" href="#298">298</a> <em>    *</em><a name="299" href="#299">299</a> <em>    * Default is ARCConstants.DEFAULT_MAX_ARC_FILE_SIZE.  Note that ARC</em><a name="300" href="#300">300</a> <em>    * files will usually be bigger than maxSize; they'll be maxSize + length</em><a name="301" href="#301">301</a> <em>    * to next boundary.</em><a name="302" href="#302">302</a> <em>    * @return ARC maximum size.</em><a name="303" href="#303">303</a> <em>    */</em><a name="304" href="#304">304</a>     <strong>public</strong> <strong>int</strong> getMaxSize() {<a name="305" href="#305">305</a>         Object obj = getAttributeUnchecked(ATTR_MAX_SIZE_BYTES);<a name="306" href="#306">306</a>         <strong>return</strong> (obj == <strong>null</strong>)? DEFAULT_MAX_FILE_SIZE: ((Integer)obj).intValue();<a name="307" href="#307">307</a>     }<a name="308" href="#308">308</a> <a name="309" href="#309">309</a>     <strong>public</strong> String getPrefix() {<a name="310" href="#310">310</a>         Object obj = getAttributeUnchecked(ATTR_PREFIX);<a name="311" href="#311">311</a>         <strong>return</strong> (obj == <strong>null</strong>)? WriterPoolMember.DEFAULT_PREFIX: (String)obj;<a name="312" href="#312">312</a>     }<a name="313" href="#313">313</a> <a name="314" href="#314">314</a>     <strong>public</strong> List getOutputDirs() {<a name="315" href="#315">315</a>         Object obj = getAttributeUnchecked(ATTR_PATH);<a name="316" href="#316">316</a>         List list = (obj == <strong>null</strong>)? Arrays.asList(DEFAULT_PATH): (StringList)obj;<a name="317" href="#317">317</a>         ArrayList&lt;File> results = <strong>new</strong> ArrayList&lt;File>();<a name="318" href="#318">318</a>         <strong>for</strong> (Iterator i = list.iterator(); i.hasNext();) {<a name="319" href="#319">319</a>             String path = (String)i.next();<a name="320" href="#320">320</a>             File f = <strong>new</strong> File(path);<a name="321" href="#321">321</a>             <strong>if</strong> (!f.isAbsolute()) {<a name="322" href="#322">322</a>                 f = <strong>new</strong> File(getController().getDisk(), path);<a name="323" href="#323">323</a>             }<a name="324" href="#324">324</a>             <strong>if</strong> (!f.exists()) {<a name="325" href="#325">325</a>                 <strong>try</strong> {<a name="326" href="#326">326</a>                     f.mkdirs();<a name="327" href="#327">327</a>                 } <strong>catch</strong> (Exception e) {<a name="328" href="#328">328</a>                     e.printStackTrace();<a name="329" href="#329">329</a>                     <strong>continue</strong>;<a name="330" href="#330">330</a>                 }<a name="331" href="#331">331</a>             }<a name="332" href="#332">332</a>             results.add(f);<a name="333" href="#333">333</a>         }<a name="334" href="#334">334</a>         <strong>return</strong> results;<a name="335" href="#335">335</a>     }<a name="336" href="#336">336</a>     <a name="337" href="#337">337</a>     <strong>public</strong> <strong>boolean</strong> isCompressed() {<a name="338" href="#338">338</a>         Object obj = getAttributeUnchecked(ATTR_COMPRESS);<a name="339" href="#339">339</a>         <strong>return</strong> (obj == <strong>null</strong>)? DEFAULT_COMPRESS:<a name="340" href="#340">340</a>             ((Boolean)obj).booleanValue();<a name="341" href="#341">341</a>     }<a name="342" href="#342">342</a> <a name="343" href="#343">343</a>     <em>/**<em>*</em></em><a name="344" href="#344">344</a> <em>     * @return Returns the poolMaximumActive.</em><a name="345" href="#345">345</a> <em>     */</em><a name="346" href="#346">346</a>     <strong>public</strong> <strong>int</strong> getPoolMaximumActive() {<a name="347" href="#347">347</a>         Object obj = getAttributeUnchecked(ATTR_POOL_MAX_ACTIVE);<a name="348" href="#348">348</a>         <strong>return</strong> (obj == <strong>null</strong>)? WriterPool.DEFAULT_MAX_ACTIVE:<a name="349" href="#349">349</a>             ((Integer)obj).intValue();

⌨️ 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 + -