⭐ 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

📄 crawluri.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="143" href="#143">143</a> <em>     * Will sometimes be truncated to 48 bits, so behavior</em><a name="144" href="#144">144</a> <em>     * over 281 trillion instantiated CrawlURIs may be </em><a name="145" href="#145">145</a> <em>     * buggy</em><a name="146" href="#146">146</a> <em>     */</em><a name="147" href="#147">147</a>     <strong>protected</strong> <strong>long</strong> ordinal;<a name="148" href="#148">148</a> <a name="149" href="#149">149</a>     <em>/**<em>*</em></em><a name="150" href="#150">150</a> <em>     * Cache of this candidate uuri as a string.</em><a name="151" href="#151">151</a> <em>     *</em><a name="152" href="#152">152</a> <em>     * Profiling shows us spending about 1-2% of total elapsed time in</em><a name="153" href="#153">153</a> <em>     * toString.</em><a name="154" href="#154">154</a> <em>     */</em><a name="155" href="#155">155</a>     <strong>private</strong> String cachedCrawlURIString = <strong>null</strong>;<a name="156" href="#156">156</a>     <a name="157" href="#157">157</a>     <em>/**<em>*</em></em><a name="158" href="#158">158</a> <em>     * Array to hold keys of alist members that persist across URI processings.</em><a name="159" href="#159">159</a> <em>     * Any key mentioned in this list will not be cleared out at the end</em><a name="160" href="#160">160</a> <em>     * of a pass down the processing chain.</em><a name="161" href="#161">161</a> <em>     */</em><a name="162" href="#162">162</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> List alistPersistentMember = <strong>new</strong> CopyOnWriteArrayList(<a name="163" href="#163">163</a>             <strong>new</strong> String [] {A_CREDENTIAL_AVATARS_KEY});<a name="164" href="#164">164</a> <a name="165" href="#165">165</a>     <em>/**<em>*</em></em><a name="166" href="#166">166</a> <em>     * A digest (hash, usually SHA1) of retrieved content-body. </em><a name="167" href="#167">167</a> <em>     * </em><a name="168" href="#168">168</a> <em>     */</em><a name="169" href="#169">169</a>     <strong>private</strong> byte[] contentDigest = <strong>null</strong>;<a name="170" href="#170">170</a>     <strong>private</strong> String contentDigestScheme = <strong>null</strong>;<a name="171" href="#171">171</a> <a name="172" href="#172">172</a> <a name="173" href="#173">173</a>     <em>/**<em>*</em></em><a name="174" href="#174">174</a> <em>     * Create a new instance of CrawlURI from a {@link UURI}.</em><a name="175" href="#175">175</a> <em>     *</em><a name="176" href="#176">176</a> <em>     * @param uuri the UURI to base this CrawlURI on.</em><a name="177" href="#177">177</a> <em>     */</em><a name="178" href="#178">178</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a>(<a href="../../../../org/archive/net/UURI.html">UURI</a> uuri) {<a name="179" href="#179">179</a>         <strong>super</strong>(uuri);<a name="180" href="#180">180</a>     }<a name="181" href="#181">181</a> <a name="182" href="#182">182</a>     <em>/**<em>*</em></em><a name="183" href="#183">183</a> <em>     * Create a new instance of CrawlURI from a {@link CandidateURI}</em><a name="184" href="#184">184</a> <em>     *</em><a name="185" href="#185">185</a> <em>     * @param caUri the CandidateURI to base this CrawlURI on.</em><a name="186" href="#186">186</a> <em>     * @param o Monotonically increasing number within a crawl.</em><a name="187" href="#187">187</a> <em>     */</em><a name="188" href="#188">188</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a>(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> caUri, <strong>long</strong> o) {<a name="189" href="#189">189</a>         <strong>super</strong>(caUri.getUURI(), caUri.getPathFromSeed(), caUri.getVia(),<a name="190" href="#190">190</a>             caUri.getViaContext());<a name="191" href="#191">191</a>         ordinal = o;<a name="192" href="#192">192</a>         setIsSeed(caUri.isSeed());<a name="193" href="#193">193</a>         setSchedulingDirective(caUri.getSchedulingDirective());<a name="194" href="#194">194</a>         setAList(caUri.getAList());<a name="195" href="#195">195</a>     }<a name="196" href="#196">196</a> <a name="197" href="#197">197</a>     <em>/**<em>*</em></em><a name="198" href="#198">198</a> <em>     * Takes a status code and converts it into a human readable string.</em><a name="199" href="#199">199</a> <em>     *</em><a name="200" href="#200">200</a> <em>     * @param code the status code</em><a name="201" href="#201">201</a> <em>     * @return a human readable string declaring what the status code is.</em><a name="202" href="#202">202</a> <em>     */</em><a name="203" href="#203">203</a>     <strong>public</strong> <strong>static</strong> String fetchStatusCodesToString(<strong>int</strong> code){<a name="204" href="#204">204</a>         <strong>switch</strong>(code){<a name="205" href="#205">205</a>             <em class="comment">// DNS</em><a name="206" href="#206">206</a>             <strong>case</strong> S_DNS_SUCCESS : <strong>return</strong> <span class="string">"DNS-1-OK"</span>;<a name="207" href="#207">207</a>             <em class="comment">// HTTP Informational 1xx</em><a name="208" href="#208">208</a>             <strong>case</strong> 100  : <strong>return</strong> <span class="string">"HTTP-100-Info-Continue"</span>;<a name="209" href="#209">209</a>             <strong>case</strong> 101  : <strong>return</strong> <span class="string">"HTTP-101-Info-Switching Protocols"</span>;<a name="210" href="#210">210</a>             <em class="comment">// HTTP Successful 2xx</em><a name="211" href="#211">211</a>             <strong>case</strong> 200  : <strong>return</strong> <span class="string">"HTTP-200-Success-OK"</span>;<a name="212" href="#212">212</a>             <strong>case</strong> 201  : <strong>return</strong> <span class="string">"HTTP-201-Success-Created"</span>;<a name="213" href="#213">213</a>             <strong>case</strong> 202  : <strong>return</strong> <span class="string">"HTTP-202-Success-Accepted"</span>;<a name="214" href="#214">214</a>             <strong>case</strong> 203  : <strong>return</strong> <span class="string">"HTTP-203-Success-Non-Authoritative"</span>;<a name="215" href="#215">215</a>             <strong>case</strong> 204  : <strong>return</strong> <span class="string">"HTTP-204-Success-No Content "</span>;<a name="216" href="#216">216</a>             <strong>case</strong> 205  : <strong>return</strong> <span class="string">"HTTP-205-Success-Reset Content"</span>;<a name="217" href="#217">217</a>             <strong>case</strong> 206  : <strong>return</strong> <span class="string">"HTTP-206-Success-Partial Content"</span>;<a name="218" href="#218">218</a>             <em class="comment">// HTTP Redirection 3xx</em><a name="219" href="#219">219</a>             <strong>case</strong> 300  : <strong>return</strong> <span class="string">"HTTP-300-Redirect-Multiple Choices"</span>;<a name="220" href="#220">220</a>             <strong>case</strong> 301  : <strong>return</strong> <span class="string">"HTTP-301-Redirect-Moved Permanently"</span>;<a name="221" href="#221">221</a>             <strong>case</strong> 302  : <strong>return</strong> <span class="string">"HTTP-302-Redirect-Found"</span>;<a name="222" href="#222">222</a>             <strong>case</strong> 303  : <strong>return</strong> <span class="string">"HTTP-303-Redirect-See Other"</span>;<a name="223" href="#223">223</a>             <strong>case</strong> 304  : <strong>return</strong> <span class="string">"HTTP-304-Redirect-Not Modified"</span>;<a name="224" href="#224">224</a>             <strong>case</strong> 305  : <strong>return</strong> <span class="string">"HTTP-305-Redirect-Use Proxy"</span>;<a name="225" href="#225">225</a>             <strong>case</strong> 307  : <strong>return</strong> <span class="string">"HTTP-307-Redirect-Temporary Redirect"</span>;<a name="226" href="#226">226</a>             <em class="comment">// HTTP Client Error 4xx</em><a name="227" href="#227">227</a>             <strong>case</strong> 400  : <strong>return</strong> <span class="string">"HTTP-400-ClientErr-Bad Request"</span>;<a name="228" href="#228">228</a>             <strong>case</strong> 401  : <strong>return</strong> <span class="string">"HTTP-401-ClientErr-Unauthorized"</span>;<a name="229" href="#229">229</a>             <strong>case</strong> 402  : <strong>return</strong> <span class="string">"HTTP-402-ClientErr-Payment Required"</span>;<a name="230" href="#230">230</a>             <strong>case</strong> 403  : <strong>return</strong> <span class="string">"HTTP-403-ClientErr-Forbidden"</span>;<a name="231" href="#231">231</a>             <strong>case</strong> 404  : <strong>return</strong> <span class="string">"HTTP-404-ClientErr-Not Found"</span>;<a name="232" href="#232">232</a>             <strong>case</strong> 405  : <strong>return</strong> <span class="string">"HTTP-405-ClientErr-Method Not Allowed"</span>;<a name="233" href="#233">233</a>             <strong>case</strong> 407  : <strong>return</strong> <span class="string">"HTTP-406-ClientErr-Not Acceptable"</span>;<a name="234" href="#234">234</a>             <strong>case</strong> 408  : <strong>return</strong> <span class="string">"HTTP-407-ClientErr-Proxy Authentication Required"</span>;<a name="235" href="#235">235</a>             <strong>case</strong> 409  : <strong>return</strong> <span class="string">"HTTP-408-ClientErr-Request Timeout"</span>;<a name="236" href="#236">236</a>             <strong>case</strong> 410  : <strong>return</strong> <span class="string">"HTTP-409-ClientErr-Conflict"</span>;<a name="237" href="#237">237</a>             <strong>case</strong> 406  : <strong>return</strong> <span class="string">"HTTP-410-ClientErr-Gone"</span>;<a name="238" href="#238">238</a>             <strong>case</strong> 411  : <strong>return</strong> <span class="string">"HTTP-411-ClientErr-Length Required"</span>;<a name="239" href="#239">239</a>             <strong>case</strong> 412  : <strong>return</strong> <span class="string">"HTTP-412-ClientErr-Precondition Failed"</span>;<a name="240" href="#240">240</a>             <strong>case</strong> 413  : <strong>return</strong> <span class="string">"HTTP-413-ClientErr-Request Entity Too Large"</span>;<a name="241" href="#241">241</a>             <strong>case</strong> 414  : <strong>return</strong> <span class="string">"HTTP-414-ClientErr-Request-URI Too Long"</span>;<a name="242" href="#242">242</a>             <strong>case</strong> 415  : <strong>return</strong> <span class="string">"HTTP-415-ClientErr-Unsupported Media Type"</span>;<a name="243" href="#243">243</a>             <strong>case</strong> 416  : <strong>return</strong> <span class="string">"HTTP-416-ClientErr-Requested Range Not Satisfiable"</span>;<a name="244" href="#244">244</a>             <strong>case</strong> 417  : <strong>return</strong> <span class="string">"HTTP-417-ClientErr-Expectation Failed"</span>;<a name="245" href="#245">245</a>             <em class="comment">// HTTP Server Error 5xx</em><a name="246" href="#246">246</a>             <strong>case</strong> 500  : <strong>return</strong> <span class="string">"HTTP-500-ServerErr-Internal Server Error"</span>;<a name="247" href="#247">247</a>             <strong>case</strong> 501  : <strong>return</strong> <span class="string">"HTTP-501-ServerErr-Not Implemented"</span>;<a name="248" href="#248">248</a>             <strong>case</strong> 502  : <strong>return</strong> <span class="string">"HTTP-502-ServerErr-Bad Gateway"</span>;<a name="249" href="#249">249</a>             <strong>case</strong> 503  : <strong>return</strong> <span class="string">"HTTP-503-ServerErr-Service Unavailable"</span>;<a name="250" href="#250">250</a>             <strong>case</strong> 504  : <strong>return</strong> <span class="string">"HTTP-504-ServerErr-Gateway Timeout"</span>;<a name="251" href="#251">251</a>             <strong>case</strong> 505  : <strong>return</strong> <span class="string">"HTTP-505-ServerErr-HTTP Version Not Supported"</span>;<a name="252" href="#252">252</a>             <em class="comment">// Heritrix internal codes (all negative numbers</em><a name="253" href="#253">253</a>             <strong>case</strong> S_BLOCKED_BY_USER:<a name="254" href="#254">254</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_BLOCKED_BY_USER + <span class="string">")-Blocked by user"</span>;<a name="255" href="#255">255</a>             <strong>case</strong> S_BLOCKED_BY_CUSTOM_PROCESSOR:<a name="256" href="#256">256</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_BLOCKED_BY_CUSTOM_PROCESSOR +<a name="257" href="#257">257</a>                 <span class="string">")-Blocked by custom prefetch processor"</span>;<a name="258" href="#258">258</a>             <strong>case</strong> S_DELETED_BY_USER:<a name="259" href="#259">259</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_DELETED_BY_USER + <span class="string">")-Deleted by user"</span>;<a name="260" href="#260">260</a>             <strong>case</strong> S_CONNECT_FAILED:<a name="261" href="#261">261</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_CONNECT_FAILED + <span class="string">")-Connection failed"</span>;<a name="262" href="#262">262</a>             <strong>case</strong> S_CONNECT_LOST:<a name="263" href="#263">263</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_CONNECT_LOST + <span class="string">")-Connection lost"</span>;<a name="264" href="#264">264</a>             <strong>case</strong> S_DEEMED_CHAFF:<a name="265" href="#265">265</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_DEEMED_CHAFF + <span class="string">")-Deemed chaff"</span>;<a name="266" href="#266">266</a>             <strong>case</strong> S_DEFERRED:<a name="267" href="#267">267</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_DEFERRED + <span class="string">")-Deferred"</span>;<a name="268" href="#268">268</a>             <strong>case</strong> S_DOMAIN_UNRESOLVABLE:<a name="269" href="#269">269</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_DOMAIN_UNRESOLVABLE<a name="270" href="#270">270</a>                         + <span class="string">")-Domain unresolvable"</span>;<a name="271" href="#271">271</a>             <strong>case</strong> S_OUT_OF_SCOPE:<a name="272" href="#272">272</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_OUT_OF_SCOPE + <span class="string">")-Out of scope"</span>;<a name="273" href="#273">273</a>             <strong>case</strong> S_DOMAIN_PREREQUISITE_FAILURE:<a name="274" href="#274">274</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_DOMAIN_PREREQUISITE_FAILURE<a name="275" href="#275">275</a>                         + <span class="string">")-Domain prerequisite failure"</span>;<a name="276" href="#276">276</a>             <strong>case</strong> S_ROBOTS_PREREQUISITE_FAILURE:<a name="277" href="#277">277</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_ROBOTS_PREREQUISITE_FAILURE<a name="278" href="#278">278</a>                         + <span class="string">")-Robots prerequisite failure"</span>;<a name="279" href="#279">279</a>             <strong>case</strong> S_OTHER_PREREQUISITE_FAILURE:<a name="280" href="#280">280</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_OTHER_PREREQUISITE_FAILURE<a name="281" href="#281">281</a>                         + <span class="string">")-Other prerequisite failure"</span>;<a name="282" href="#282">282</a>             <strong>case</strong> S_PREREQUISITE_UNSCHEDULABLE_FAILURE:<a name="283" href="#283">283</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_PREREQUISITE_UNSCHEDULABLE_FAILURE<a name="284" href="#284">284</a>                         + <span class="string">")-Prerequisite unschedulable failure"</span>;<a name="285" href="#285">285</a>             <strong>case</strong> S_ROBOTS_PRECLUDED:<a name="286" href="#286">286</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_ROBOTS_PRECLUDED + <span class="string">")-Robots precluded"</span>;<a name="287" href="#287">287</a>             <strong>case</strong> S_RUNTIME_EXCEPTION:<a name="288" href="#288">288</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_RUNTIME_EXCEPTION<a name="289" href="#289">289</a>                         + <span class="string">")-Runtime exception"</span>;<a name="290" href="#290">290</a>             <strong>case</strong> S_SERIOUS_ERROR:<a name="291" href="#291">291</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_SERIOUS_ERROR + <span class="string">")-Serious error"</span>;<a name="292" href="#292">292</a>             <strong>case</strong> S_TIMEOUT:<a name="293" href="#293">293</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_TIMEOUT + <span class="string">")-Timeout"</span>;

⌨️ 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 + -