?? candidateuri.html
字號:
<a name="173" href="#173">173</a> <strong>this</strong>.uuri = u;<a name="174" href="#174">174</a> <strong>this</strong>.pathFromSeed = pathFromSeed;<a name="175" href="#175">175</a> <strong>this</strong>.via = via;<a name="176" href="#176">176</a> <strong>this</strong>.viaContext = viaContext;<a name="177" href="#177">177</a> }<a name="178" href="#178">178</a> <a name="179" href="#179">179</a> <em>/**<em>*</em></em><a name="180" href="#180">180</a> <em> * Set the <tt>isSeed</tt> attribute of this URI.</em><a name="181" href="#181">181</a> <em> * @param b Is this URI a seed, true or false.</em><a name="182" href="#182">182</a> <em> */</em><a name="183" href="#183">183</a> <strong>public</strong> <strong>void</strong> setIsSeed(<strong>boolean</strong> b) {<a name="184" href="#184">184</a> <strong>this</strong>.isSeed = b;<a name="185" href="#185">185</a> <strong>if</strong> (<strong>this</strong>.isSeed) {<a name="186" href="#186">186</a> <strong>if</strong>(pathFromSeed==<strong>null</strong>) {<a name="187" href="#187">187</a> <strong>this</strong>.pathFromSeed = <span class="string">""</span>;<a name="188" href="#188">188</a> }<a name="189" href="#189">189</a> <em class="comment">// seeds created on redirect must have a via to be recognized; don't clear</em><a name="190" href="#190">190</a> <em class="comment">// setVia(null);</em><a name="191" href="#191">191</a> }<a name="192" href="#192">192</a> }<a name="193" href="#193">193</a> <a name="194" href="#194">194</a> <em>/**<em>*</em></em><a name="195" href="#195">195</a> <em> * @return UURI</em><a name="196" href="#196">196</a> <em> */</em><a name="197" href="#197">197</a> <strong>public</strong> <a href="../../../../org/archive/net/UURI.html">UURI</a> getUURI() {<a name="198" href="#198">198</a> <strong>return</strong> <strong>this</strong>.uuri;<a name="199" href="#199">199</a> }<a name="200" href="#200">200</a> <a name="201" href="#201">201</a> <em>/**<em>*</em></em><a name="202" href="#202">202</a> <em> * @return Whether seeded.</em><a name="203" href="#203">203</a> <em> */</em><a name="204" href="#204">204</a> <strong>public</strong> <strong>boolean</strong> isSeed() {<a name="205" href="#205">205</a> <strong>return</strong> <strong>this</strong>.isSeed;<a name="206" href="#206">206</a> }<a name="207" href="#207">207</a> <a name="208" href="#208">208</a> <em>/**<em>*</em></em><a name="209" href="#209">209</a> <em> * @return path (hop-types) from seed</em><a name="210" href="#210">210</a> <em> */</em><a name="211" href="#211">211</a> <strong>public</strong> String getPathFromSeed() {<a name="212" href="#212">212</a> <strong>return</strong> <strong>this</strong>.pathFromSeed;<a name="213" href="#213">213</a> }<a name="214" href="#214">214</a> <a name="215" href="#215">215</a> <em>/**<em>*</em></em><a name="216" href="#216">216</a> <em> * @return URI via which this one was discovered</em><a name="217" href="#217">217</a> <em> */</em><a name="218" href="#218">218</a> <strong>public</strong> <a href="../../../../org/archive/net/UURI.html">UURI</a> getVia() {<a name="219" href="#219">219</a> <strong>return</strong> <strong>this</strong>.via;<a name="220" href="#220">220</a> }<a name="221" href="#221">221</a> <a name="222" href="#222">222</a> <em>/**<em>*</em></em><a name="223" href="#223">223</a> <em> * @return CharSequence context in which this one was discovered</em><a name="224" href="#224">224</a> <em> */</em><a name="225" href="#225">225</a> <strong>public</strong> CharSequence getViaContext() {<a name="226" href="#226">226</a> <strong>return</strong> <strong>this</strong>.viaContext;<a name="227" href="#227">227</a> }<a name="228" href="#228">228</a> <a name="229" href="#229">229</a> <em>/**<em>*</em></em><a name="230" href="#230">230</a> <em> * @param string</em><a name="231" href="#231">231</a> <em> */</em><a name="232" href="#232">232</a> <strong>protected</strong> <strong>void</strong> setPathFromSeed(String string) {<a name="233" href="#233">233</a> pathFromSeed = string;<a name="234" href="#234">234</a> }<a name="235" href="#235">235</a> <a name="236" href="#236">236</a> <em>/**<em>*</em></em><a name="237" href="#237">237</a> <em> * Called when making a copy of another CandidateURI.</em><a name="238" href="#238">238</a> <em> * @param alist AList to use.</em><a name="239" href="#239">239</a> <em> */</em><a name="240" href="#240">240</a> <strong>protected</strong> <strong>void</strong> setAList(<a href="../../../../st/ata/util/AList.html">AList</a> alist) {<a name="241" href="#241">241</a> <strong>this</strong>.alist = alist;<a name="242" href="#242">242</a> }<a name="243" href="#243">243</a> <a name="244" href="#244">244</a> <strong>public</strong> <strong>void</strong> setVia(<a href="../../../../org/archive/net/UURI.html">UURI</a> via) {<a name="245" href="#245">245</a> <strong>this</strong>.via = via;<a name="246" href="#246">246</a> }<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> * @return This candidate URI as a string wrapped with 'CandidateURI(' +</em><a name="250" href="#250">250</a> <em> * ')'.</em><a name="251" href="#251">251</a> <em> */</em><a name="252" href="#252">252</a> <strong>public</strong> <strong>synchronized</strong> String getCandidateURIString() {<a name="253" href="#253">253</a> <strong>if</strong> (<strong>this</strong>.cachedCandidateURIString == <strong>null</strong>) {<a name="254" href="#254">254</a> <strong>this</strong>.cachedCandidateURIString =<a name="255" href="#255">255</a> <span class="string">"CandidateURI("</span> + toString() + <span class="string">")"</span>;<a name="256" href="#256">256</a> }<a name="257" href="#257">257</a> <strong>return</strong> <strong>this</strong>.cachedCandidateURIString;<a name="258" href="#258">258</a> }<a name="259" href="#259">259</a> <a name="260" href="#260">260</a> <em>/**<em>*</em></em><a name="261" href="#261">261</a> <em> * Method returns string version of this URI's referral URI.</em><a name="262" href="#262">262</a> <em> * @return String version of referral URI</em><a name="263" href="#263">263</a> <em> */</em><a name="264" href="#264">264</a> <strong>public</strong> String flattenVia() {<a name="265" href="#265">265</a> <strong>return</strong> (via == <strong>null</strong>)? <span class="string">""</span>: via.toString();<a name="266" href="#266">266</a> }<a name="267" href="#267">267</a> <a name="268" href="#268">268</a> <em>/**<em>*</em></em><a name="269" href="#269">269</a> <em> * @return The UURI this CandidateURI wraps as a string </em><a name="270" href="#270">270</a> <em> * (We used return what {@link #getCandidateURIString()}</em><a name="271" href="#271">271</a> <em> * returns on a toString -- use that method if you still need</em><a name="272" href="#272">272</a> <em> * this functionality).</em><a name="273" href="#273">273</a> <em> * @see #getCandidateURIString()</em><a name="274" href="#274">274</a> <em> */</em><a name="275" href="#275">275</a> <strong>public</strong> String toString() {<a name="276" href="#276">276</a> <strong>return</strong> getURIString();<a name="277" href="#277">277</a> }<a name="278" href="#278">278</a> <a name="279" href="#279">279</a> <em>/**<em>*</em></em><a name="280" href="#280">280</a> <em> * @return URI String</em><a name="281" href="#281">281</a> <em> * @deprecated Use {@link #toString()}.</em><a name="282" href="#282">282</a> <em> */</em><a name="283" href="#283">283</a> <strong>public</strong> String getURIString() {<a name="284" href="#284">284</a> <strong>return</strong> getUURI().toString();<a name="285" href="#285">285</a> }<a name="286" href="#286">286</a> <a name="287" href="#287">287</a> <em>/**<em>*</em></em><a name="288" href="#288">288</a> <em> * Compares the domain of this CandidateURI with that of another</em><a name="289" href="#289">289</a> <em> * CandidateURI</em><a name="290" href="#290">290</a> <em> *</em><a name="291" href="#291">291</a> <em> * @param other The other CandidateURI</em><a name="292" href="#292">292</a> <em> *</em><a name="293" href="#293">293</a> <em> * @return True if both are in the same domain, false otherwise.</em><a name="294" href="#294">294</a> <em> * @throws URIException</em><a name="295" href="#295">295</a> <em> */</em><a name="296" href="#296">296</a> <strong>public</strong> <strong>boolean</strong> sameDomainAs(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> other) throws URIException {<a name="297" href="#297">297</a> String domain = getUURI().getHost();<a name="298" href="#298">298</a> <strong>if</strong> (domain == <strong>null</strong>) {<a name="299" href="#299">299</a> <strong>return</strong> false;<a name="300" href="#300">300</a> }<a name="301" href="#301">301</a> <strong>while</strong>(domain.lastIndexOf('.') > domain.indexOf('.')) {<a name="302" href="#302">302</a> <em class="comment">// While has more than one dot, lop off first segment</em><a name="303" href="#303">303</a> domain = domain.substring(domain.indexOf('.') + 1);<a name="304" href="#304">304</a> }<a name="305" href="#305">305</a> <strong>if</strong>(other.getUURI().getHost() == <strong>null</strong>) {<a name="306" href="#306">306</a> <strong>return</strong> false;<a name="307" href="#307">307</a> }<a name="308" href="#308">308</a> <strong>return</strong> other.getUURI().getHost().endsWith(domain);<a name="309" href="#309">309</a> }<a name="310" href="#310">310</a> <a name="311" href="#311">311</a> <em>/**<em>*</em></em><a name="312" href="#312">312</a> <em> * If this method returns true, this URI should be fetched even though</em><a name="313" href="#313">313</a> <em> * it already has been crawled. This also implies</em><a name="314" href="#314">314</a> <em> * that this URI will be scheduled for crawl before any other waiting</em><a name="315" href="#315">315</a> <em> * URIs for the same host.</em><a name="316" href="#316">316</a> <em> *</em><a name="317" href="#317">317</a> <em> * This value is used to refetch any expired robots.txt or dns-lookups.</em><a name="318" href="#318">318</a> <em> *</em><a name="319" href="#319">319</a> <em> * @return true if crawling of this URI should be forced</em><a name="320" href="#320">320</a> <em> */</em><a name="321" href="#321">321</a> <strong>public</strong> <strong>boolean</strong> forceFetch() {<a name="322" href="#322">322</a> <strong>return</strong> forceRevisit;<a name="323" href="#323">323</a> }<a name="324" href="#324">324</a> <a name="325" href="#325">325</a> <em>/**<em>*</em></em><a name="326" href="#326">326</a> <em> * Method to signal that this URI should be fetched even though</em><a name="327" href="#327">327</a> <em> * it already has been crawled. Setting this to true also implies</em><a name="328" href="#328">328</a> <em> * that this URI will be scheduled for crawl before any other waiting</em><a name="329" href="#329">329</a> <em> * URIs for the same host.</em><a name="330" href="#330">330</a> <em> *</em><a name="331" href="#331">331</a> <em> * This value is used to refetch any expired robots.txt or dns-lookups.</em><a name="332" href="#332">332</a> <em> *</em><a name="333" href="#333">333</a> <em> * @param b set to true to enforce the crawling of this URI</em><a name="334" href="#334">334</a> <em> */</em><a name="335" href="#335">335</a> <strong>public</strong> <strong>void</strong> setForceFetch(<strong>boolean</strong> b) {<a name="336" href="#336">336</a> forceRevisit = b;<a name="337" href="#337">337</a> }<a name="338" href="#338">338</a> <a name="339" href="#339">339</a> <em>/**<em>*</em></em><a name="340" href="#340">340</a> <em> * @return Returns the schedulingDirective.</em><a name="341" href="#341">341</a> <em> */</em><a name="342" href="#342">342</a> <strong>public</strong> <strong>int</strong> getSchedulingDirective() {<a name="343" href="#343">343</a> <strong>return</strong> schedulingDirective;<a name="344" href="#344">344</a> }<a name="345" href="#345">345</a> <em>/**<em>* </em></em><a name="346" href="#346">346</a> <em> * @param schedulingDirective The schedulingDirective to set.</em><a name="347" href="#347">347</a> <em> */</em><a name="348" href="#348">348</a> <strong>public</strong> <strong>void</strong> setSchedulingDirective(<strong>int</strong> schedulingDirective) {<a name="349" href="#349">349</a> <strong>this</strong>.schedulingDirective = schedulingDirective;<a name="350" href="#350">350</a> }<a name="351" href="#351">351</a> <a name="352" href="#352">352</a> <a name="353" href="#353">353</a> <em>/**<em>*</em></em>
?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -