⭐ 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

📄 crawlcontroller.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 5 页
字号:
<a name="134" href="#134">134</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String LOGNAME_RUNTIME_ERRORS = <span class="string">"runtime-errors"</span>;<a name="135" href="#135">135</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String LOGNAME_LOCAL_ERRORS = <span class="string">"local-errors"</span>;<a name="136" href="#136">136</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String LOGNAME_CRAWL = <span class="string">"crawl"</span>;<a name="137" href="#137">137</a> <a name="138" href="#138">138</a>     <em class="comment">// key subcomponents which define and implement a crawl in progress</em><a name="139" href="#139">139</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlOrder.html">CrawlOrder</a> order;<a name="140" href="#140">140</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/framework/CrawlScope.html">CrawlScope</a> scope;<a name="141" href="#141">141</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/framework/ProcessorChainList.html">ProcessorChainList</a> processorChains;<a name="142" href="#142">142</a>     <a name="143" href="#143">143</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/framework/Frontier.html">Frontier</a> frontier;<a name="144" href="#144">144</a> <a name="145" href="#145">145</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/framework/ToePool.html">ToePool</a> toePool;<a name="146" href="#146">146</a>     <a name="147" href="#147">147</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/datamodel/ServerCache.html">ServerCache</a> serverCache;<a name="148" href="#148">148</a>     <a name="149" href="#149">149</a>     <em class="comment">// This gets passed into the initialize method.</em><a name="150" href="#150">150</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/settings/SettingsHandler.html">SettingsHandler</a> settingsHandler;<a name="151" href="#151">151</a> <a name="152" href="#152">152</a> <a name="153" href="#153">153</a>     <em class="comment">// Used to enable/disable single-threaded operation after OOM</em><a name="154" href="#154">154</a>     <strong>private</strong> <strong>volatile</strong> <strong>transient</strong> <strong>boolean</strong> singleThreadMode = false; <a name="155" href="#155">155</a>     <strong>private</strong> <strong>transient</strong> ReentrantLock singleThreadLock = <strong>null</strong>;<a name="156" href="#156">156</a> <a name="157" href="#157">157</a>     <em class="comment">// emergency reserve of memory to allow some progress/reporting after OOM</em><a name="158" href="#158">158</a>     <strong>private</strong> <strong>transient</strong> LinkedList reserveMemory;<a name="159" href="#159">159</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> RESERVE_BLOCKS = 1;<a name="160" href="#160">160</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> RESERVE_BLOCK_SIZE = 6*2^20; <em class="comment">// 6MB</em><a name="161" href="#161">161</a> <a name="162" href="#162">162</a>     <em class="comment">// crawl state: as requested or actual</em><a name="163" href="#163">163</a>     <a name="164" href="#164">164</a>     <em>/**<em>*</em></em><a name="165" href="#165">165</a> <em>     * Crawl exit status.</em><a name="166" href="#166">166</a> <em>     */</em><a name="167" href="#167">167</a>     <strong>private</strong> <strong>transient</strong> String sExit;<a name="168" href="#168">168</a> <a name="169" href="#169">169</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object NASCENT = <span class="string">"NASCENT"</span>.intern();<a name="170" href="#170">170</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object RUNNING = <span class="string">"RUNNING"</span>.intern();<a name="171" href="#171">171</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object PAUSED = <span class="string">"PAUSED"</span>.intern();<a name="172" href="#172">172</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object PAUSING = <span class="string">"PAUSING"</span>.intern();<a name="173" href="#173">173</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object CHECKPOINTING = <span class="string">"CHECKPOINTING"</span>.intern();<a name="174" href="#174">174</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object STOPPING = <span class="string">"STOPPING"</span>.intern();<a name="175" href="#175">175</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object FINISHED = <span class="string">"FINISHED"</span>.intern();<a name="176" href="#176">176</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object STARTED = <span class="string">"STARTED"</span>.intern();<a name="177" href="#177">177</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Object PREPARING = <span class="string">"PREPARING"</span>.intern();<a name="178" href="#178">178</a> <a name="179" href="#179">179</a>     <strong>transient</strong> <strong>private</strong> Object state = NASCENT;<a name="180" href="#180">180</a> <a name="181" href="#181">181</a>     <em class="comment">// disk paths</em><a name="182" href="#182">182</a>     <strong>private</strong> <strong>transient</strong> File disk;        <em class="comment">// overall disk path</em><a name="183" href="#183">183</a>     <strong>private</strong> <strong>transient</strong> File logsDisk;    <em class="comment">// for log files</em><a name="184" href="#184">184</a>     <a name="185" href="#185">185</a>     <em>/**<em>*</em></em><a name="186" href="#186">186</a> <em>     * For temp files representing state of crawler (eg queues)</em><a name="187" href="#187">187</a> <em>     */</em><a name="188" href="#188">188</a>     <strong>private</strong> <strong>transient</strong> File stateDisk;<a name="189" href="#189">189</a>     <a name="190" href="#190">190</a>     <em>/**<em>*</em></em><a name="191" href="#191">191</a> <em>     * For discardable temp files (eg fetch buffers).</em><a name="192" href="#192">192</a> <em>     */</em><a name="193" href="#193">193</a>     <strong>private</strong> <strong>transient</strong> File scratchDisk;<a name="194" href="#194">194</a> <a name="195" href="#195">195</a>     <em>/**<em>*</em></em><a name="196" href="#196">196</a> <em>     * Directory that holds checkpoint.</em><a name="197" href="#197">197</a> <em>     */</em><a name="198" href="#198">198</a>     <strong>private</strong> <strong>transient</strong> File checkpointsDisk;<a name="199" href="#199">199</a>     <a name="200" href="#200">200</a>     <em>/**<em>*</em></em><a name="201" href="#201">201</a> <em>     * Checkpointer.</em><a name="202" href="#202">202</a> <em>     * Knows if checkpoint in progress and what name of checkpoint is.  Also runs</em><a name="203" href="#203">203</a> <em>     * checkpoints.</em><a name="204" href="#204">204</a> <em>     */</em><a name="205" href="#205">205</a>     <strong>private</strong> <a href="../../../../org/archive/crawler/framework/Checkpointer.html">Checkpointer</a> checkpointer;<a name="206" href="#206">206</a>     <a name="207" href="#207">207</a>     <em>/**<em>*</em></em><a name="208" href="#208">208</a> <em>     * Gets set to checkpoint we're in recovering if in checkpoint recover</em><a name="209" href="#209">209</a> <em>     * mode.  Gets setup by {@link #getCheckpointRecover()}.</em><a name="210" href="#210">210</a> <em>     */</em><a name="211" href="#211">211</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/datamodel/Checkpoint.html">Checkpoint</a> checkpointRecover = <strong>null</strong>;<a name="212" href="#212">212</a> <a name="213" href="#213">213</a>     <em class="comment">// crawl limits</em><a name="214" href="#214">214</a>     <strong>private</strong> <strong>long</strong> maxBytes;<a name="215" href="#215">215</a>     <strong>private</strong> <strong>long</strong> maxDocument;<a name="216" href="#216">216</a>     <strong>private</strong> <strong>long</strong> maxTime;<a name="217" href="#217">217</a> <a name="218" href="#218">218</a>     <em>/**<em>*</em></em><a name="219" href="#219">219</a> <em>     * A manifest of all files used/created during this crawl. Written to file</em><a name="220" href="#220">220</a> <em>     * at the end of the crawl (the absolutely last thing done).</em><a name="221" href="#221">221</a> <em>     */</em><a name="222" href="#222">222</a>     <strong>private</strong> StringBuffer manifest;<a name="223" href="#223">223</a> <a name="224" href="#224">224</a>     <em>/**<em>*</em></em><a name="225" href="#225">225</a> <em>     * Record of fileHandlers established for loggers,</em><a name="226" href="#226">226</a> <em>     * assisting file rotation.</em><a name="227" href="#227">227</a> <em>     */</em><a name="228" href="#228">228</a>     <strong>transient</strong> <strong>private</strong> Map fileHandlers;<a name="229" href="#229">229</a> <a name="230" href="#230">230</a>     <em>/**<em>* suffix to use on active logs */</em></em><a name="231" href="#231">231</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String CURRENT_LOG_SUFFIX = <span class="string">".log"</span>;<a name="232" href="#232">232</a> <a name="233" href="#233">233</a>     <em>/**<em>*</em></em><a name="234" href="#234">234</a> <em>     * Crawl progress logger.</em><a name="235" href="#235">235</a> <em>     *</em><a name="236" href="#236">236</a> <em>     * No exceptions.  Logs summary result of each url processing.</em><a name="237" href="#237">237</a> <em>     */</em><a name="238" href="#238">238</a>     <strong>public</strong> <strong>transient</strong> Logger uriProcessing;<a name="239" href="#239">239</a> <a name="240" href="#240">240</a>     <em>/**<em>*</em></em><a name="241" href="#241">241</a> <em>     * This logger contains unexpected runtime errors.</em><a name="242" href="#242">242</a> <em>     *</em><a name="243" href="#243">243</a> <em>     * Would contain errors trying to set up a job or failures inside</em><a name="244" href="#244">244</a> <em>     * processors that they are not prepared to recover from.</em><a name="245" href="#245">245</a> <em>     */</em><a name="246" href="#246">246</a>     <strong>public</strong> <strong>transient</strong> Logger runtimeErrors;<a name="247" href="#247">247</a> <a name="248" href="#248">248</a>     <em>/**<em>*</em></em><a name="249" href="#249">249</a> <em>     * This logger is for job-scoped logging, specifically errors which</em><a name="250" href="#250">250</a> <em>     * happen and are handled within a particular processor.</em><a name="251" href="#251">251</a> <em>     *</em><a name="252" href="#252">252</a> <em>     * Examples would be socket timeouts, exceptions thrown by extractors, etc.</em><a name="253" href="#253">253</a> <em>     */</em><a name="254" href="#254">254</a>     <strong>public</strong> <strong>transient</strong> Logger localErrors;<a name="255" href="#255">255</a> <a name="256" href="#256">256</a>     <em>/**<em>*</em></em><a name="257" href="#257">257</a> <em>     * Special log for URI format problems, wherever they may occur.</em><a name="258" href="#258">258</a> <em>     */</em><a name="259" href="#259">259</a>     <strong>public</strong> <strong>transient</strong> Logger uriErrors;<a name="260" href="#260">260</a> <a name="261" href="#261">261</a>     <em>/**<em>*</em></em><a name="262" href="#262">262</a> <em>     * Statistics tracker writes here at regular intervals.</em><a name="263" href="#263">263</a> <em>     */</em><a name="264" href="#264">264</a>     <strong>private</strong> <strong>transient</strong> Logger progressStats;<a name="265" href="#265">265</a> <a name="266" href="#266">266</a>     <em>/**<em>*</em></em><a name="267" href="#267">267</a> <em>     * Logger to hold job summary report.</em><a name="268" href="#268">268</a> <em>     *</em><a name="269" href="#269">269</a> <em>     * Large state reports made at infrequent intervals (e.g. job ending) go</em><a name="270" href="#270">270</a> <em>     * here.</em><a name="271" href="#271">271</a> <em>     */</em><a name="272" href="#272">272</a>     <strong>public</strong> <strong>transient</strong> Logger reports;<a name="273" href="#273">273</a> <a name="274" href="#274">274</a>     <strong>protected</strong> <a href="../../../../org/archive/crawler/framework/StatisticsTracking.html">StatisticsTracking</a> statistics = <strong>null</strong>;<a name="275" href="#275">275</a> 

⌨️ 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 + -