⭐ 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

📄 arcwriterprocessor.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 2 页
字号:
<a name="151" href="#151">151</a>                 InputStream is = curi.getHttpRecorder().getRecordedInput().<a name="152" href="#152">152</a>                  getReplayInputStream();<a name="153" href="#153">153</a>                 write(curi, recordLength, is, getHostAddress(curi));<a name="154" href="#154">154</a>             } <strong>else</strong> {<a name="155" href="#155">155</a>                 logger.info(<span class="string">"This writer does not write out scheme "</span> + scheme +<a name="156" href="#156">156</a>                     <span class="string">" content"</span>);<a name="157" href="#157">157</a>             }<a name="158" href="#158">158</a>         } <strong>catch</strong> (IOException e) {<a name="159" href="#159">159</a>             curi.addLocalizedError(<strong>this</strong>.getName(), e, <span class="string">"WriteRecord: "</span> +<a name="160" href="#160">160</a>                 curi.toString());<a name="161" href="#161">161</a>             logger.log(Level.SEVERE, <span class="string">"Failed write of Record: "</span> +<a name="162" href="#162">162</a>                 curi.toString(), e);<a name="163" href="#163">163</a>         }<a name="164" href="#164">164</a>     }<a name="165" href="#165">165</a>     <a name="166" href="#166">166</a>     <strong>protected</strong> <strong>void</strong> write(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi, <strong>int</strong> recordLength, InputStream in,<a name="167" href="#167">167</a>         String ip)<a name="168" href="#168">168</a>     throws IOException {<a name="169" href="#169">169</a>         <a href="../../../../org/archive/io/WriterPoolMember.html">WriterPoolMember</a> writer = getPool().borrowFile();<a name="170" href="#170">170</a>         <strong>long</strong> position = writer.getPosition();<a name="171" href="#171">171</a>         <em class="comment">// See if we need to open a new file because we've exceeed maxBytes.</em><a name="172" href="#172">172</a>         <em class="comment">// Call to checkFileSize will open new file if we're at maximum for</em><a name="173" href="#173">173</a>         <em class="comment">// current file.</em><a name="174" href="#174">174</a>         writer.checkSize();<a name="175" href="#175">175</a>         <strong>if</strong> (writer.getPosition() != position) {<a name="176" href="#176">176</a>             <em class="comment">// We just closed the file because it was larger than maxBytes.</em><a name="177" href="#177">177</a>             <em class="comment">// Add to the totalBytesWritten the size of the first record</em><a name="178" href="#178">178</a>             <em class="comment">// in the file, if any.</em><a name="179" href="#179">179</a>             setTotalBytesWritten(getTotalBytesWritten() +<a name="180" href="#180">180</a>             	(writer.getPosition() - position));<a name="181" href="#181">181</a>             position = writer.getPosition();<a name="182" href="#182">182</a>         }<a name="183" href="#183">183</a>         <a name="184" href="#184">184</a>         <a href="../../../../org/archive/io/arc/ARCWriter.html">ARCWriter</a> w = (ARCWriter)writer;<a name="185" href="#185">185</a>         <strong>try</strong> {<a name="186" href="#186">186</a>             <strong>if</strong> (in instanceof ReplayInputStream) {<a name="187" href="#187">187</a>                 w.write(curi.toString(), curi.getContentType(),<a name="188" href="#188">188</a>                     ip, curi.getLong(A_FETCH_BEGAN_TIME),<a name="189" href="#189">189</a>                     recordLength, (ReplayInputStream)in);<a name="190" href="#190">190</a>             } <strong>else</strong> {<a name="191" href="#191">191</a>                 w.write(curi.toString(), curi.getContentType(),<a name="192" href="#192">192</a>                     ip, curi.getLong(A_FETCH_BEGAN_TIME),<a name="193" href="#193">193</a>                     recordLength, in);<a name="194" href="#194">194</a>             }<a name="195" href="#195">195</a>         } <strong>catch</strong> (IOException e) {<a name="196" href="#196">196</a>             <em class="comment">// Invalidate this file (It gets a '.invalid' suffix).</em><a name="197" href="#197">197</a>             getPool().invalidateFile(writer);<a name="198" href="#198">198</a>             <em class="comment">// Set the writer to null otherwise the pool accounting</em><a name="199" href="#199">199</a>             <em class="comment">// of how many active writers gets skewed if we subsequently</em><a name="200" href="#200">200</a>             <em class="comment">// do a returnWriter call on this object in the finally block.</em><a name="201" href="#201">201</a>             writer = <strong>null</strong>;<a name="202" href="#202">202</a>             <strong>throw</strong> e;<a name="203" href="#203">203</a>         } <strong>finally</strong> {<a name="204" href="#204">204</a>             <strong>if</strong> (writer != <strong>null</strong>) {<a name="205" href="#205">205</a>             	setTotalBytesWritten(getTotalBytesWritten() +<a name="206" href="#206">206</a>             	     (writer.getPosition() - position));<a name="207" href="#207">207</a>                 getPool().returnFile(writer);<a name="208" href="#208">208</a>             }<a name="209" href="#209">209</a>         }<a name="210" href="#210">210</a>         checkBytesWritten();<a name="211" href="#211">211</a>     }<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>     * Return list of metadatas to add to first arc file metadata record.</em><a name="215" href="#215">215</a> <em>     *</em><a name="216" href="#216">216</a> <em>     * Get xml files from settingshandle.  Currently order file is the</em><a name="217" href="#217">217</a> <em>     * only xml file.  We're NOT adding seeds to meta data.</em><a name="218" href="#218">218</a> <em>     *</em><a name="219" href="#219">219</a> <em>     * @return List of strings and/or files to add to arc file as metadata or</em><a name="220" href="#220">220</a> <em>     * null.</em><a name="221" href="#221">221</a> <em>     */</em><a name="222" href="#222">222</a>     <strong>public</strong> <strong>synchronized</strong> List&lt;String> getMetadata() {<a name="223" href="#223">223</a>         <strong>if</strong> (<strong>this</strong>.cachedMetadata != <strong>null</strong>) {<a name="224" href="#224">224</a>             <strong>return</strong> <strong>this</strong>.cachedMetadata;<a name="225" href="#225">225</a>         }<a name="226" href="#226">226</a>         <strong>return</strong> cacheMetadata();<a name="227" href="#227">227</a>     }<a name="228" href="#228">228</a>     <a name="229" href="#229">229</a>     <strong>protected</strong> <strong>synchronized</strong> List&lt;String> cacheMetadata() {<a name="230" href="#230">230</a>         <strong>if</strong> (<strong>this</strong>.cachedMetadata != <strong>null</strong>) {<a name="231" href="#231">231</a>             <strong>return</strong> <strong>this</strong>.cachedMetadata;<a name="232" href="#232">232</a>         }<a name="233" href="#233">233</a>         <a name="234" href="#234">234</a>         List&lt;String> result = <strong>null</strong>;<a name="235" href="#235">235</a>         <strong>if</strong> (!XMLSettingsHandler.<strong>class</strong>.isInstance(getSettingsHandler())) {<a name="236" href="#236">236</a>             logger.warning(<span class="string">"Expected xml settings handler (No arcmetadata)."</span>);<a name="237" href="#237">237</a>             <em class="comment">// Early return</em><a name="238" href="#238">238</a>             <strong>return</strong> result;<a name="239" href="#239">239</a>         }<a name="240" href="#240">240</a>         <a name="241" href="#241">241</a>         <a href="../../../../org/archive/crawler/settings/XMLSettingsHandler.html">XMLSettingsHandler</a> xsh = (XMLSettingsHandler)getSettingsHandler();<a name="242" href="#242">242</a>         File orderFile = xsh.getOrderFile();<a name="243" href="#243">243</a>         <strong>if</strong> (!orderFile.exists() || !orderFile.canRead()) {<a name="244" href="#244">244</a>                 logger.severe(<span class="string">"File "</span> + orderFile.getAbsolutePath() +<a name="245" href="#245">245</a>                     <span class="string">" is does not exist or is not readable."</span>);<a name="246" href="#246">246</a>         } <strong>else</strong> {<a name="247" href="#247">247</a>             result = <strong>new</strong> ArrayList&lt;String>(1);<a name="248" href="#248">248</a>             result.add(getMetadataBody(orderFile));<a name="249" href="#249">249</a>         }<a name="250" href="#250">250</a>         <strong>this</strong>.cachedMetadata = result;<a name="251" href="#251">251</a>         <strong>return</strong> <strong>this</strong>.cachedMetadata;<a name="252" href="#252">252</a>     }<a name="253" href="#253">253</a> <a name="254" href="#254">254</a>     <em>/**<em>*</em></em><a name="255" href="#255">255</a> <em>     * Write the arc metadata body content.</em><a name="256" href="#256">256</a> <em>     *</em><a name="257" href="#257">257</a> <em>     * Its based on the order xml file but into this base we'll add other info</em><a name="258" href="#258">258</a> <em>     * such as machine ip.</em><a name="259" href="#259">259</a> <em>     *</em><a name="260" href="#260">260</a> <em>     * @param orderFile Order file.</em><a name="261" href="#261">261</a> <em>     *</em><a name="262" href="#262">262</a> <em>     * @return String that holds the arc metaheader body.</em><a name="263" href="#263">263</a> <em>     */</em><a name="264" href="#264">264</a>     <strong>protected</strong> String getMetadataBody(File orderFile) {<a name="265" href="#265">265</a>         String result = <strong>null</strong>;<a name="266" href="#266">266</a>         TransformerFactory factory = TransformerFactory.newInstance();<a name="267" href="#267">267</a>         Templates templates = <strong>null</strong>;<a name="268" href="#268">268</a>         Transformer xformer = <strong>null</strong>;<a name="269" href="#269">269</a>         <strong>try</strong> {<a name="270" href="#270">270</a>             templates = factory.<strong>new</strong>Templates(<strong>new</strong> StreamSource(<a name="271" href="#271">271</a>                 <strong>this</strong>.getClass().getResourceAsStream(<span class="string">"/arcMetaheaderBody.xsl"</span>)));<a name="272" href="#272">272</a>             xformer = templates.newTransformer();<a name="273" href="#273">273</a>             <em class="comment">// Below parameter names must match what is in the stylesheet.</em><a name="274" href="#274">274</a>             xformer.setParameter(<span class="string">"software"</span>, <span class="string">"Heritrix "</span> +<a name="275" href="#275">275</a>                 Heritrix.getVersion() + <span class="string">" http://crawler.archive.org"</span>);<a name="276" href="#276">276</a>             xformer.setParameter(<span class="string">"ip"</span>,<a name="277" href="#277">277</a>                 InetAddress.getLocalHost().getHostAddress());<a name="278" href="#278">278</a>             xformer.setParameter(<span class="string">"hostname"</span>,<a name="279" href="#279">279</a>                 InetAddress.getLocalHost().getHostName());<a name="280" href="#280">280</a>             StreamSource source = <strong>new</strong> StreamSource(<a name="281" href="#281">281</a>                 <strong>new</strong> FileInputStream(orderFile));<a name="282" href="#282">282</a>             StringWriter writer = <strong>new</strong> StringWriter();<a name="283" href="#283">283</a>             StreamResult target = <strong>new</strong> StreamResult(writer);<a name="284" href="#284">284</a>             xformer.transform(source, target);<a name="285" href="#285">285</a>             result= writer.toString();<a name="286" href="#286">286</a>         } <strong>catch</strong> (TransformerConfigurationException e) {<a name="287" href="#287">287</a>             logger.severe(<span class="string">"Failed transform "</span> + e);<a name="288" href="#288">288</a>         } <strong>catch</strong> (FileNotFoundException e) {<a name="289" href="#289">289</a>             logger.severe(<span class="string">"Failed transform, file not found "</span> + e);<a name="290" href="#290">290</a>         } <strong>catch</strong> (UnknownHostException e) {<a name="291" href="#291">291</a>             logger.severe(<span class="string">"Failed transform, unknown host "</span> + e);<a name="292" href="#292">292</a>         } <strong>catch</strong>(TransformerException e) {<a name="293" href="#293">293</a>             SourceLocator locator = e.getLocator();<a name="294" href="#294">294</a>             <strong>int</strong> col = locator.getColumnNumber();<a name="295" href="#295">295</a>             <strong>int</strong> line = locator.getLineNumber();<a name="296" href="#296">296</a>             String publicId = locator.getPublicId();<a name="297" href="#297">297</a>             String systemId = locator.getSystemId();<a name="298" href="#298">298</a>             logger.severe(<span class="string">"Transform error "</span> + e + <span class="string">", col "</span> + col + <span class="string">", line "</span> +<a name="299" href="#299">299</a>                 line + <span class="string">", publicId "</span> + publicId + <span class="string">", systemId "</span> + systemId);<a name="300" href="#300">300</a>         }<a name="301" href="#301">301</a> <a name="302" href="#302">302</a>         <strong>return</strong> result;<a name="303" href="#303">303</a>     }<a name="304" href="#304">304</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>

⌨️ 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 + -