⭐ 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

📄 crawljob.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="128" href="#128">128</a>     <em>/**<em>*</em></em><a name="129" href="#129">129</a> <em>     * Eclipse generated serial number.</em><a name="130" href="#130">130</a> <em>     */</em><a name="131" href="#131">131</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>long</strong> serialVersionUID = 3411161000452525856L;<a name="132" href="#132">132</a>     <a name="133" href="#133">133</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Logger logger =<a name="134" href="#134">134</a>         Logger.getLogger(CrawlJob.<strong>class</strong>.getName());<a name="135" href="#135">135</a>     <em class="comment">/*</em><a name="136" href="#136">136</a> <em class="comment">     * Possible values for Priority</em><a name="137" href="#137">137</a> <em class="comment">     */</em><a name="138" href="#138">138</a>     <em>/**<em>* lowest */</em></em><a name="139" href="#139">139</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PRIORITY_MINIMAL = 0;<a name="140" href="#140">140</a>     <em>/**<em>* low */</em></em><a name="141" href="#141">141</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PRIORITY_LOW = 1;<a name="142" href="#142">142</a>     <em>/**<em>* average */</em></em><a name="143" href="#143">143</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PRIORITY_AVERAGE = 2;<a name="144" href="#144">144</a>     <em>/**<em>* high */</em></em><a name="145" href="#145">145</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PRIORITY_HIGH = 3;<a name="146" href="#146">146</a>     <em>/**<em>* highest */</em></em><a name="147" href="#147">147</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PRIORITY_CRITICAL = 4;<a name="148" href="#148">148</a> <a name="149" href="#149">149</a>     <em class="comment">/*</em><a name="150" href="#150">150</a> <em class="comment">     * Possible states for a Job.</em><a name="151" href="#151">151</a> <em class="comment">     */</em><a name="152" href="#152">152</a>     <em>/**<em>* Inital value. May not be ready to run/incomplete. */</em></em><a name="153" href="#153">153</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_CREATED = <span class="string">"Created"</span>;<a name="154" href="#154">154</a>     <em>/**<em>* Job has been successfully submitted to a <a href="../../../../org/archive/crawler/admin/CrawlJobHandler.html">CrawlJobHandler</a> */</em></em><a name="155" href="#155">155</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_PENDING = <span class="string">"Pending"</span>;<a name="156" href="#156">156</a>     <em>/**<em>* Job is being crawled */</em></em><a name="157" href="#157">157</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_RUNNING = <span class="string">"Running"</span>;<a name="158" href="#158">158</a>     <em>/**<em>* Job was deleted by user, will not be displayed in UI. */</em></em><a name="159" href="#159">159</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_DELETED = <span class="string">"Deleted"</span>;<a name="160" href="#160">160</a>     <em>/**<em>* Job was terminted by user input while crawling */</em></em><a name="161" href="#161">161</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_ABORTED = <span class="string">"Finished - Ended by operator"</span>;<a name="162" href="#162">162</a>     <em>/**<em>* Something went very wrong */</em></em><a name="163" href="#163">163</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_FINISHED_ABNORMAL =<a name="164" href="#164">164</a>         <span class="string">"Finished - Abnormal exit from crawling"</span>;<a name="165" href="#165">165</a>     <em>/**<em>* Job finished normally having completed its crawl. */</em></em><a name="166" href="#166">166</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_FINISHED = <span class="string">"Finished"</span>;<a name="167" href="#167">167</a>     <em>/**<em>* Job finished normally when the specified timelimit was hit. */</em></em><a name="168" href="#168">168</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_FINISHED_TIME_LIMIT =<a name="169" href="#169">169</a>         <span class="string">"Finished - Timelimit hit"</span>;<a name="170" href="#170">170</a>     <em>/**<em>* Job finished normally when the specifed amount of </em></em><a name="171" href="#171">171</a> <em>     * data (MB) had been downloaded */</em><a name="172" href="#172">172</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_FINISHED_DATA_LIMIT =<a name="173" href="#173">173</a>         <span class="string">"Finished - Maximum amount of data limit hit"</span>;<a name="174" href="#174">174</a>     <em>/**<em>* Job finished normally when the specified number of documents had been</em></em><a name="175" href="#175">175</a> <em>     * fetched.</em><a name="176" href="#176">176</a> <em>     */</em><a name="177" href="#177">177</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_FINISHED_DOCUMENT_LIMIT =<a name="178" href="#178">178</a>         <span class="string">"Finished - Maximum number of documents limit hit"</span>;<a name="179" href="#179">179</a>     <em>/**<em>* Job is going to be temporarly stopped after active threads are finished. */</em></em><a name="180" href="#180">180</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_WAITING_FOR_PAUSE = <span class="string">"Pausing - "</span> +<a name="181" href="#181">181</a>         <span class="string">"Waiting for threads to finish"</span>;<a name="182" href="#182">182</a>     <em>/**<em>* Job was temporarly stopped. State is kept so it can be resumed */</em></em><a name="183" href="#183">183</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_PAUSED = <span class="string">"Paused"</span>;<a name="184" href="#184">184</a>     <em>/**<em>*</em></em><a name="185" href="#185">185</a> <em>     * Job is being checkpointed.  When finished checkpointing, job is set</em><a name="186" href="#186">186</a> <em>     * back to STATUS_PAUSED (Job must be first paused before checkpointing</em><a name="187" href="#187">187</a> <em>     * will run).</em><a name="188" href="#188">188</a> <em>     */</em><a name="189" href="#189">189</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_CHECKPOINTING = <span class="string">"Checkpointing"</span>;<a name="190" href="#190">190</a>     <em>/**<em>* Job could not be launced due to an <a href="../../../../org/archive/crawler/framework/exceptions/InitializationException.html">InitializationException</a> */</em></em><a name="191" href="#191">191</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_MISCONFIGURED = <span class="string">"Could not launch job "</span> +<a name="192" href="#192">192</a>         <span class="string">"- Fatal InitializationException"</span>;<a name="193" href="#193">193</a>     <em>/**<em>* Job is actually a profile */</em></em><a name="194" href="#194">194</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_PROFILE = <span class="string">"Profile"</span>;<a name="195" href="#195">195</a>     <a name="196" href="#196">196</a>     <strong>public</strong> <strong>static</strong> <strong>final</strong> String STATUS_PREPARING = <span class="string">"Preparing"</span>;<a name="197" href="#197">197</a> <a name="198" href="#198">198</a>     <em class="comment">// Class variables</em><a name="199" href="#199">199</a>     <strong>private</strong> String UID;       <em class="comment">//A UID issued by the CrawlJobHandler.</em><a name="200" href="#200">200</a>     <strong>private</strong> String name;<a name="201" href="#201">201</a>     <strong>private</strong> String status;<a name="202" href="#202">202</a>     <strong>private</strong> <strong>boolean</strong> isReadOnly = false;<a name="203" href="#203">203</a>     <strong>private</strong> <strong>boolean</strong> isNew = <strong>true</strong>;<a name="204" href="#204">204</a>     <strong>private</strong> <strong>boolean</strong> isProfile = false;<a name="205" href="#205">205</a>     <strong>private</strong> <strong>boolean</strong> isRunning = false;<a name="206" href="#206">206</a>     <strong>private</strong> <strong>int</strong> priority;<a name="207" href="#207">207</a>     <strong>private</strong> <strong>int</strong> numberOfJournalEntries = 0;<a name="208" href="#208">208</a>     <a name="209" href="#209">209</a>     <strong>private</strong> String statisticsFileSave = <span class="string">""</span>;<a name="210" href="#210">210</a> <a name="211" href="#211">211</a>     <strong>private</strong> String errorMessage = <strong>null</strong>;<a name="212" href="#212">212</a> <a name="213" href="#213">213</a>     <strong>private</strong> File jobDir = <strong>null</strong>;<a name="214" href="#214">214</a> <a name="215" href="#215">215</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/admin/CrawlJobErrorHandler.html">CrawlJobErrorHandler</a> errorHandler = <strong>null</strong>;<a name="216" href="#216">216</a> <a name="217" href="#217">217</a>     <strong>protected</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/settings/XMLSettingsHandler.html">XMLSettingsHandler</a> settingsHandler;<a name="218" href="#218">218</a>     <a name="219" href="#219">219</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/crawler/framework/CrawlController.html">CrawlController</a> controller = <strong>null</strong>;<a name="220" href="#220">220</a>     <a name="221" href="#221">221</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String RECOVERY_JOURNAL_STYLE = <span class="string">"recoveryJournal"</span>;<a name="222" href="#222">222</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String CRAWL_LOG_STYLE = <span class="string">"crawlLog"</span>;<a name="223" href="#223">223</a>     <a name="224" href="#224">224</a>     <em class="comment">// OpenMBean support.</em><a name="225" href="#225">225</a> <a name="226" href="#226">226</a>     <em>/**<em>*</em></em><a name="227" href="#227">227</a> <em>     * Server we registered with. Maybe null.</em><a name="228" href="#228">228</a> <em>     */</em><a name="229" href="#229">229</a>     <strong>private</strong> <strong>transient</strong> MBeanServer mbeanServer = <strong>null</strong>;<a name="230" href="#230">230</a>     <strong>private</strong> <strong>transient</strong> ObjectName mbeanName = <strong>null</strong>;<a name="231" href="#231">231</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String CRAWLJOB_JMXMBEAN_TYPE =<a name="232" href="#232">232</a>         JmxUtils.SERVICE + <span class="string">".Job"</span>;<a name="233" href="#233">233</a>     <strong>private</strong> <strong>transient</strong> <a href="../../../../org/archive/util/JEMBeanHelper.html">JEMBeanHelper</a> bdbjeMBeanHelper = <strong>null</strong>;<a name="234" href="#234">234</a>     <strong>private</strong> <strong>transient</strong> List bdbjeAttributeNameList = <strong>null</strong>;<a name="235" href="#235">235</a>     <strong>private</strong> <strong>transient</strong> List bdbjeOperationsNameList = <strong>null</strong>;<a name="236" href="#236">236</a>     <a name="237" href="#237">237</a>     <a name="238" href="#238">238</a>     <em>/**<em>*</em></em><a name="239" href="#239">239</a> <em>     * The MBean we've registered ourselves with (May be null</em><a name="240" href="#240">240</a> <em>     * throughout life of Heritrix).</em><a name="241" href="#241">241</a> <em>     */</em><a name="242" href="#242">242</a>     <strong>private</strong> <strong>transient</strong> OpenMBeanInfoSupport openMBeanInfo;<a name="243" href="#243">243</a>     <a name="244" href="#244">244</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String NAME_ATTR = <span class="string">"Name"</span>;<a name="245" href="#245">245</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String UID_ATTR = <span class="string">"UID"</span>;<a name="246" href="#246">246</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String STATUS_ATTR = <span class="string">"Status"</span>;<a name="247" href="#247">247</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String FRONTIER_SHORT_REPORT_ATTR =<a name="248" href="#248">248</a>         <span class="string">"FrontierShortReport"</span>;<a name="249" href="#249">249</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String THREADS_SHORT_REPORT_ATTR =<a name="250" href="#250">250</a>         <span class="string">"ThreadsShortReport"</span>;<a name="251" href="#251">251</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String TOTAL_DATA_ATTR = <span class="string">"TotalData"</span>;<a name="252" href="#252">252</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String CRAWL_TIME_ATTR = <span class="string">"CrawlTime"</span>;<a name="253" href="#253">253</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String DOC_RATE_ATTR = <span class="string">"DocRate"</span>;<a name="254" href="#254">254</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String CURRENT_DOC_RATE_ATTR = <span class="string">"CurrentDocRate"</span>;<a name="255" href="#255">255</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String KB_RATE_ATTR = <span class="string">"KbRate"</span>;<a name="256" href="#256">256</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String CURRENT_KB_RATE_ATTR = <span class="string">"CurrentKbRate"</span>;<a name="257" href="#257">257</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String THREAD_COUNT_ATTR = <span class="string">"ThreadCount"</span>;<a name="258" href="#258">258</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String DOWNLOAD_COUNT_ATTR = <span class="string">"DownloadedCount"</span>;<a name="259" href="#259">259</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String DISCOVERED_COUNT_ATTR = <span class="string">"DiscoveredCount"</span>;<a name="260" href="#260">260</a>     <strong>private</strong> <strong>final</strong> <strong>static</strong> String [] ATTRIBUTE_ARRAY = {NAME_ATTR, UID_ATTR,<a name="261" href="#261">261</a>         STATUS_ATTR, FRONTIER_SHORT_REPORT_ATTR, THREADS_SHORT_REPORT_ATTR,<a name="262" href="#262">262</a>         TOTAL_DATA_ATTR, CRAWL_TIME_ATTR, DOC_RATE_ATTR,<a name="263" href="#263">263</a>         CURRENT_DOC_RATE_ATTR, KB_RATE_ATTR, CURRENT_KB_RATE_ATTR,

⌨️ 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 + -