frontier.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

<a name="152" href="#152">152</a>     <em>/**<em>*</em></em>
<a name="153" href="#153">153</a> <em>     * Returns true if the frontier contains no more URIs to crawl.</em>
<a name="154" href="#154">154</a> <em>     *</em>
<a name="155" href="#155">155</a> <em>     * &lt;p>That is to say that there are no more URIs either currently availible</em>
<a name="156" href="#156">156</a> <em>     * (ready to be emitted), URIs belonging to deferred hosts or pending URIs</em>
<a name="157" href="#157">157</a> <em>     * in the Frontier. Thus this method may return false even if there is no</em>
<a name="158" href="#158">158</a> <em>     * currently availible URI.</em>
<a name="159" href="#159">159</a> <em>     *</em>
<a name="160" href="#160">160</a> <em>     * @return true if the frontier contains no more URIs to crawl.</em>
<a name="161" href="#161">161</a> <em>     */</em>
<a name="162" href="#162">162</a>     <strong>boolean</strong> isEmpty();
<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>     * Schedules a CandidateURI.</em>
<a name="166" href="#166">166</a> <em>     *</em>
<a name="167" href="#167">167</a> <em>     * &lt;p>This method accepts one URI and schedules it immediately. This has</em>
<a name="168" href="#168">168</a> <em>     * nothing to do with the priority of the URI being scheduled. Only that</em>
<a name="169" href="#169">169</a> <em>     * it will be placed in it's respective queue at once. For priority</em>
<a name="170" href="#170">170</a> <em>     * scheduling see {@link CandidateURI#setSchedulingDirective(int)}</em>
<a name="171" href="#171">171</a> <em>     *</em>
<a name="172" href="#172">172</a> <em>     * &lt;p>This method should be synchronized in all implementing classes.</em>
<a name="173" href="#173">173</a> <em>     *</em>
<a name="174" href="#174">174</a> <em>     * @param caURI The URI to schedule.</em>
<a name="175" href="#175">175</a> <em>     *</em>
<a name="176" href="#176">176</a> <em>     * @see CandidateURI#setSchedulingDirective(int)</em>
<a name="177" href="#177">177</a> <em>     */</em>
<a name="178" href="#178">178</a>     <strong>public</strong> <strong>void</strong> schedule(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> caURI);
<a name="179" href="#179">179</a> 
<a name="180" href="#180">180</a>     <em>/**<em>*</em></em>
<a name="181" href="#181">181</a> <em>     * Report a URI being processed as having finished processing.</em>
<a name="182" href="#182">182</a> <em>     *</em>
<a name="183" href="#183">183</a> <em>     * &lt;p>ToeThreads will invoke this method once they have completed work on</em>
<a name="184" href="#184">184</a> <em>     * their assigned URI.</em>
<a name="185" href="#185">185</a> <em>     *</em>
<a name="186" href="#186">186</a> <em>     * &lt;p>This method is synchronized.</em>
<a name="187" href="#187">187</a> <em>     *</em>
<a name="188" href="#188">188</a> <em>     * @param cURI The URI that has finished processing.</em>
<a name="189" href="#189">189</a> <em>     */</em>
<a name="190" href="#190">190</a>     <strong>public</strong> <strong>void</strong> finished(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> cURI);
<a name="191" href="#191">191</a> 
<a name="192" href="#192">192</a>     <em>/**<em>*</em></em>
<a name="193" href="#193">193</a> <em>     * Number of &lt;i>discovered&lt;/i> URIs.</em>
<a name="194" href="#194">194</a> <em>     *</em>
<a name="195" href="#195">195</a> <em>     * &lt;p>That is any URI that has been confirmed be within 'scope'</em>
<a name="196" href="#196">196</a> <em>     * (i.e. the Frontier decides that it should be processed). This</em>
<a name="197" href="#197">197</a> <em>     * includes those that have been processed, are being processed</em>
<a name="198" href="#198">198</a> <em>     * and have finished processing. Does not include URIs that have</em>
<a name="199" href="#199">199</a> <em>     * been 'forgotten' (deemed out of scope when trying to fetch,</em>
<a name="200" href="#200">200</a> <em>     * most likely due to operator changing scope definition).</em>
<a name="201" href="#201">201</a> <em>     *</em>
<a name="202" href="#202">202</a> <em>     * &lt;p>&lt;b>Note:&lt;/b> This only counts discovered URIs. Since the same</em>
<a name="203" href="#203">203</a> <em>     * URI can (at least in most frontiers) be fetched multiple times, this</em>
<a name="204" href="#204">204</a> <em>     * number may be somewhat lower then the combined &lt;i>queued&lt;/i>,</em>
<a name="205" href="#205">205</a> <em>     * &lt;i>in process&lt;/i> and &lt;i>finished&lt;/i> items combined due to duplicate</em>
<a name="206" href="#206">206</a> <em>     * URIs being queued and processed. This variance is likely to be especially</em>
<a name="207" href="#207">207</a> <em>     * high in Frontiers implementing 'revist' strategies.</em>
<a name="208" href="#208">208</a> <em>     *</em>
<a name="209" href="#209">209</a> <em>     * @return Number of discovered URIs.</em>
<a name="210" href="#210">210</a> <em>     */</em>
<a name="211" href="#211">211</a>     <strong>public</strong> <strong>long</strong> discoveredUriCount();
<a name="212" href="#212">212</a> 
<a name="213" href="#213">213</a>     <em>/**<em>*</em></em>
<a name="214" href="#214">214</a> <em>     * Number of URIs &lt;i>queued&lt;/i> up and waiting for processing.</em>
<a name="215" href="#215">215</a> <em>     *</em>
<a name="216" href="#216">216</a> <em>     * &lt;p>This includes any URIs that failed but will be retried. Basically this</em>
<a name="217" href="#217">217</a> <em>     * is any &lt;i>discovered&lt;/i> URI that has not either been processed or is</em>
<a name="218" href="#218">218</a> <em>     * being processed. The same discovered URI can be queued multiple times.</em>
<a name="219" href="#219">219</a> <em>     *</em>
<a name="220" href="#220">220</a> <em>     * @return Number of queued URIs.</em>
<a name="221" href="#221">221</a> <em>     */</em>
<a name="222" href="#222">222</a>     <strong>public</strong> <strong>long</strong> queuedUriCount();
<a name="223" href="#223">223</a> 
<a name="224" href="#224">224</a>     <strong>public</strong> <strong>long</strong> deepestUri(); <em class="comment">// aka longest queue</em>
<a name="225" href="#225">225</a>     <strong>public</strong> <strong>long</strong> averageDepth(); <em class="comment">// aka average queue length</em>
<a name="226" href="#226">226</a>     <strong>public</strong> <strong>float</strong> congestionRatio(); <em class="comment">// multiple of threads needed for max progress</em>
<a name="227" href="#227">227</a>     
<a name="228" href="#228">228</a>     <em>/**<em>*</em></em>
<a name="229" href="#229">229</a> <em>     * Number of URIs that have &lt;i>finished&lt;/i> processing.</em>
<a name="230" href="#230">230</a> <em>     *</em>
<a name="231" href="#231">231</a> <em>     * &lt;p>Includes both those that were processed successfully and failed to be</em>
<a name="232" href="#232">232</a> <em>     * processed (excluding those that failed but will be retried). Does not</em>
<a name="233" href="#233">233</a> <em>     * include those URIs that have been 'forgotten' (deemed out of scope when</em>
<a name="234" href="#234">234</a> <em>     * trying to fetch, most likely due to operator changing scope definition).</em>
<a name="235" href="#235">235</a> <em>     *</em>
<a name="236" href="#236">236</a> <em>     * @return Number of finished URIs.</em>
<a name="237" href="#237">237</a> <em>     */</em>
<a name="238" href="#238">238</a>     <strong>public</strong> <strong>long</strong> finishedUriCount();
<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>     * Number of &lt;i>successfully&lt;/i> processed URIs.</em>
<a name="242" href="#242">242</a> <em>     *</em>
<a name="243" href="#243">243</a> <em>     * &lt;p>Any URI that was processed successfully. This includes URIs that</em>
<a name="244" href="#244">244</a> <em>     * returned 404s and other error codes that do not originate within the</em>
<a name="245" href="#245">245</a> <em>     * crawler.</em>
<a name="246" href="#246">246</a> <em>     *</em>
<a name="247" href="#247">247</a> <em>     * @return Number of &lt;i>successfully&lt;/i> processed URIs.</em>
<a name="248" href="#248">248</a> <em>     */</em>
<a name="249" href="#249">249</a>     <strong>public</strong> <strong>long</strong> succeededFetchCount();
<a name="250" href="#250">250</a> 
<a name="251" href="#251">251</a>     <em>/**<em>*</em></em>
<a name="252" href="#252">252</a> <em>     * Number of URIs that &lt;i>failed&lt;/i> to process.</em>
<a name="253" href="#253">253</a> <em>     *</em>
<a name="254" href="#254">254</a> <em>     * &lt;p>URIs that could not be processed because of some error or failure in</em>
<a name="255" href="#255">255</a> <em>     * the processing chain. Can include failure to acquire prerequisites, to</em>
<a name="256" href="#256">256</a> <em>     * establish a connection with the host and any number of other problems.</em>
<a name="257" href="#257">257</a> <em>     * Does not count those that will be retried, only those that have</em>
<a name="258" href="#258">258</a> <em>     * permenantly failed.</em>
<a name="259" href="#259">259</a> <em>     *</em>
<a name="260" href="#260">260</a> <em>     * @return Number of URIs that failed to process.</em>
<a name="261" href="#261">261</a> <em>     */</em>
<a name="262" href="#262">262</a>     <strong>public</strong> <strong>long</strong> failedFetchCount();
<a name="263" href="#263">263</a> 
<a name="264" href="#264">264</a>     <em>/**<em>*</em></em>
<a name="265" href="#265">265</a> <em>     * Number of URIs that were scheduled at one point but have been</em>
<a name="266" href="#266">266</a> <em>     * &lt;i>disregarded&lt;/i>.</em>
<a name="267" href="#267">267</a> <em>     *</em>
<a name="268" href="#268">268</a> <em>     * &lt;p>Counts any URI that is scheduled only to be disregarded</em>
<a name="269" href="#269">269</a> <em>     * because it is determined to lie outside the scope of the crawl. Most</em>
<a name="270" href="#270">270</a> <em>     * commonly this will be due to robots.txt exclusions.</em>
<a name="271" href="#271">271</a> <em>     *</em>
<a name="272" href="#272">272</a> <em>     * @return The number of URIs that have been disregarded.</em>
<a name="273" href="#273">273</a> <em>     */</em>
<a name="274" href="#274">274</a>     <strong>public</strong> <strong>long</strong> disregardedUriCount();
<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>     * Total number of bytes contained in all URIs that have been processed.</em>
<a name="278" href="#278">278</a> <em>     *</em>
<a name="279" href="#279">279</a> <em>     * @return The total amounts of bytes in all processed URIs.</em>
<a name="280" href="#280">280</a> <em>     */</em>
<a name="281" href="#281">281</a>     <strong>public</strong> <strong>long</strong> totalBytesWritten();
<a name="282" href="#282">282</a> 
<a name="283" href="#283">283</a>     <em>/**<em>*</em></em>
<a name="284" href="#284">284</a> <em>     * Recover earlier state by reading a recovery log.</em>
<a name="285" href="#285">285</a> <em>     *</em>
<a name="286" href="#286">286</a> <em>     * &lt;p>Some Frontiers are able to write detailed logs that can be loaded</em>
<a name="287" href="#287">287</a> <em>     * after a system crash to recover the state of the Frontier prior to the</em>
<a name="288" href="#288">288</a> <em>     * crash. This method is the one used to achive this.</em>
<a name="289" href="#289">289</a> <em>     *</em>
<a name="290" href="#290">290</a> <em>     * @param pathToLog The name (with full path) of the recover log.</em>
<a name="291" href="#291">291</a> <em>     * @param retainFailures If true, failures in log should count as </em>
<a name="292" href="#292">292</a> <em>     * having been included. (If false, failures will be ignored, meaning</em>
<a name="293" href="#293">293</a> <em>     * the corresponding URIs will be retried in the recovered crawl.)</em>
<a name="294" href="#294">294</a> <em>     * @throws IOException If problems occur reading the recover log.</em>
<a name="295" href="#295">295</a> <em>     */</em>
<a name="296" href="#296">296</a>     <strong>public</strong> <strong>void</strong> importRecoverLog(String pathToLog, <strong>boolean</strong> retainFailures)
<a name="297" href="#297">297</a> 			throws IOException;
<a name="298" href="#298">298</a> 
<a name="299" href="#299">299</a>     <em>/**<em>*</em></em>
<a name="300" href="#300">300</a> <em>     * Get a &lt;code>URIFrontierMarker&lt;/code> initialized with the given</em>
<a name="301" href="#301">301</a> <em>     * regular expression at the 'start' of the Frontier.</em>
<a name="302" href="#302">302</a> <em>     * @param regexpr The regular expression that URIs within the frontier must</em>
<a name="303" href="#303">303</a> <em>     *                match to be considered within the scope of this marker</em>
<a name="304" href="#304">304</a> <em>     * @param inCacheOnly If set to true, only those URIs within the frontier</em>
<a name="305" href="#305">305</a> <em>     *                that are stored in cache (usually this means in memory</em>
<a name="306" href="#306">306</a> <em>     *                rather then on disk, but that is an implementation</em>
<a name="307" href="#307">307</a> <em>     *                detail) will be considered. Others will be entierly</em>
<a name="308" href="#308">308</a> <em>     *                ignored, as if they dont exist. This is usefull for quick</em>
<a name="309" href="#309">309</a> <em>     *                peeks at the top of the URI list.</em>
<a name="310" href="#310">310</a> <em>     * @return A URIFrontierMarker that is set for the 'start' of the frontier's</em>
<a name="311" href="#311">311</a> <em>     *                URI list.</em>