📄 experimentalwarcwritertest.html
字号:
<a name="153" href="#153">153</a> }<a name="154" href="#154">154</a> <a name="155" href="#155">155</a> <em>/**<em>*</em></em><a name="156" href="#156">156</a> <em> * @return Generic HTML Content.</em><a name="157" href="#157">157</a> <em> */</em><a name="158" href="#158">158</a> <strong>protected</strong> <strong>static</strong> String getContent() {<a name="159" href="#159">159</a> <strong>return</strong> getContent(<strong>null</strong>);<a name="160" href="#160">160</a> }<a name="161" href="#161">161</a> <a name="162" href="#162">162</a> <em>/**<em>*</em></em><a name="163" href="#163">163</a> <em> * @return Generic HTML Content with mention of passed <code>indexStr</code></em><a name="164" href="#164">164</a> <em> * in title and body.</em><a name="165" href="#165">165</a> <em> */</em><a name="166" href="#166">166</a> <strong>protected</strong> <strong>static</strong> String getContent(String indexStr) {<a name="167" href="#167">167</a> String page = (indexStr != <strong>null</strong>)? <span class="string">"Page #"</span> + indexStr: <span class="string">"Some Page"</span>;<a name="168" href="#168">168</a> <strong>return</strong> <span class="string">"HTTP/1.1 200 OK\r\n"</span> +<a name="169" href="#169">169</a> <span class="string">"Content-Type: text/html\r\n\r\n"</span> +<a name="170" href="#170">170</a> <span class="string">"<html><head><title>"</span> + page +<a name="171" href="#171">171</a> <span class="string">"</title></head>"</span> +<a name="172" href="#172">172</a> <span class="string">"<body>"</span> + page +<a name="173" href="#173">173</a> <span class="string">"</body></html>"</span>;<a name="174" href="#174">174</a> }<a name="175" href="#175">175</a> <a name="176" href="#176">176</a> <em>/**<em>*</em></em><a name="177" href="#177">177</a> <em> * Write random HTML Record.</em><a name="178" href="#178">178</a> <em> * @param w Where to write.</em><a name="179" href="#179">179</a> <em> * @param index An index to put into content.</em><a name="180" href="#180">180</a> <em> * @return Length of record written.</em><a name="181" href="#181">181</a> <em> * @throws IOException</em><a name="182" href="#182">182</a> <em> */</em><a name="183" href="#183">183</a> <strong>protected</strong> <strong>int</strong> writeRandomHTTPRecord(<a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w, <strong>int</strong> index)<a name="184" href="#184">184</a> throws IOException {<a name="185" href="#185">185</a> ByteArrayOutputStream baos = <strong>new</strong> ByteArrayOutputStream();<a name="186" href="#186">186</a> String indexStr = Integer.toString(index);<a name="187" href="#187">187</a> byte[] record = (getContent(indexStr)).getBytes();<a name="188" href="#188">188</a> <strong>int</strong> recordLength = record.length;<a name="189" href="#189">189</a> baos.write(record);<a name="190" href="#190">190</a> <em class="comment">// Add named fields for ip, checksum, and relate the metadata</em><a name="191" href="#191">191</a> <em class="comment">// and request to the resource field.</em><a name="192" href="#192">192</a> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> r = <strong>new</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a>(1);<a name="193" href="#193">193</a> r.addLabelValue(NAMED_FIELD_IP_LABEL, <span class="string">"127.0.0.1"</span>);<a name="194" href="#194">194</a> w.writeResourceRecord(<a name="195" href="#195">195</a> <span class="string">"http://www.one.net/id="</span> + indexStr,<a name="196" href="#196">196</a> ArchiveUtils.get14DigitDate(),<a name="197" href="#197">197</a> <span class="string">"text/html; charset=UTF-8"</span>,<a name="198" href="#198">198</a> r,<a name="199" href="#199">199</a> <strong>new</strong> ByteArrayInputStream(baos.toByteArray()),<a name="200" href="#200">200</a> recordLength);<a name="201" href="#201">201</a> <strong>return</strong> recordLength;<a name="202" href="#202">202</a> }<a name="203" href="#203">203</a> <a name="204" href="#204">204</a> <em>/**<em>*</em></em><a name="205" href="#205">205</a> <em> * Fill a WARC with HTML Records.</em><a name="206" href="#206">206</a> <em> * @param baseName WARC basename.</em><a name="207" href="#207">207</a> <em> * @param compress Whether to compress or not.</em><a name="208" href="#208">208</a> <em> * @param maxSize Maximum WARC size.</em><a name="209" href="#209">209</a> <em> * @param recordCount How many records.</em><a name="210" href="#210">210</a> <em> * @return The written file.</em><a name="211" href="#211">211</a> <em> * @throws IOException</em><a name="212" href="#212">212</a> <em> */</em><a name="213" href="#213">213</a> <strong>private</strong> File writeRecords(String baseName, <strong>boolean</strong> compress,<a name="214" href="#214">214</a> <strong>int</strong> maxSize, <strong>int</strong> recordCount)<a name="215" href="#215">215</a> throws IOException {<a name="216" href="#216">216</a> cleanUpOldFiles(baseName);<a name="217" href="#217">217</a> File [] files = {getTmpDir()};<a name="218" href="#218">218</a> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w = <strong>new</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a>(SERIAL_NO,<a name="219" href="#219">219</a> Arrays.asList(files), baseName + '-' + PREFIX, <span class="string">""</span>, compress,<a name="220" href="#220">220</a> maxSize, <strong>null</strong>);<a name="221" href="#221">221</a> assertNotNull(w);<a name="222" href="#222">222</a> <strong>for</strong> (<strong>int</strong> i = 0; i < recordCount; i++) {<a name="223" href="#223">223</a> writeRandomHTTPRecord(w, i);<a name="224" href="#224">224</a> }<a name="225" href="#225">225</a> w.close();<a name="226" href="#226">226</a> assertTrue(<span class="string">"Doesn't exist: "</span> + w.getFile().getAbsolutePath(), <a name="227" href="#227">227</a> w.getFile().exists());<a name="228" href="#228">228</a> <strong>return</strong> w.getFile();<a name="229" href="#229">229</a> }<a name="230" href="#230">230</a> <a name="231" href="#231">231</a> <em>/**<em>*</em></em><a name="232" href="#232">232</a> <em> * Run validation of passed file.</em><a name="233" href="#233">233</a> <em> * @param f File to validate.</em><a name="234" href="#234">234</a> <em> * @param recordCount Expected count of records.</em><a name="235" href="#235">235</a> <em> * @throws FileNotFoundException</em><a name="236" href="#236">236</a> <em> * @throws IOException</em><a name="237" href="#237">237</a> <em> */</em><a name="238" href="#238">238</a> <strong>private</strong> <strong>void</strong> validate(File f, <strong>int</strong> recordCount)<a name="239" href="#239">239</a> throws FileNotFoundException, IOException {<a name="240" href="#240">240</a> <a href="../../../../org/archive/io/warc/WARCReader.html">WARCReader</a> reader = WARCReaderFactory.get(f);<a name="241" href="#241">241</a> assertNotNull(reader);<a name="242" href="#242">242</a> List headers = <strong>null</strong>;<a name="243" href="#243">243</a> <strong>if</strong> (recordCount == -1) {<a name="244" href="#244">244</a> headers = reader.validate();<a name="245" href="#245">245</a> } <strong>else</strong> {<a name="246" href="#246">246</a> headers = reader.validate(recordCount);<a name="247" href="#247">247</a> }<a name="248" href="#248">248</a> reader.close();<a name="249" href="#249">249</a> <a name="250" href="#250">250</a> <em class="comment">// Now, run through each of the records doing absolute get going from</em><a name="251" href="#251">251</a> <em class="comment">// the end to start. Reopen the arc so no context between this test</em><a name="252" href="#252">252</a> <em class="comment">// and the previous.</em><a name="253" href="#253">253</a> reader = WARCReaderFactory.get(f);<a name="254" href="#254">254</a> <strong>for</strong> (<strong>int</strong> i = headers.size() - 1; i >= 0; i--) {<a name="255" href="#255">255</a> <a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a> h = (ArchiveRecordHeader)headers.get(i);<a name="256" href="#256">256</a> <a href="../../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> r = reader.get(h.getOffset());<a name="257" href="#257">257</a> String mimeType = r.getHeader().getMimetype();<a name="258" href="#258">258</a> assertTrue(<span class="string">"Record is bogus"</span>,<a name="259" href="#259">259</a> mimeType != <strong>null</strong> && mimeType.length() > 0);<a name="260" href="#260">260</a> }<a name="261" href="#261">261</a> reader.close();<a name="262" href="#262">262</a> <a name="263" href="#263">263</a> assertTrue(<span class="string">"Metadatas not equal"</span>, headers.size() == recordCount);<a name="264" href="#264">264</a> <strong>for</strong> (Iterator i = headers.iterator(); i.hasNext();) {<a name="265" href="#265">265</a> <a href="../../../../org/archive/io/ArchiveRecordHeader.html">ArchiveRecordHeader</a> r = (ArchiveRecordHeader)i.next();<a name="266" href="#266">266</a> assertTrue(<span class="string">"Record is empty"</span>, r.getLength() > 0);<a name="267" href="#267">267</a> }<a name="268" href="#268">268</a> }<a name="269" href="#269">269</a> <a name="270" href="#270">270</a> <strong>public</strong> <strong>void</strong> testWriteRecords() throws IOException {<a name="271" href="#271">271</a> <strong>final</strong> <strong>int</strong> recordCount = 2;<a name="272" href="#272">272</a> File f = writeRecords(<span class="string">"writeRecord"</span>, false, DEFAULT_MAX_WARC_FILE_SIZE,<a name="273" href="#273">273</a> recordCount);<a name="274" href="#274">274</a> validate(f, recordCount + 1); <em class="comment">// Header record.</em><a name="275" href="#275">275</a> }<a name="276" href="#276">276</a> <a name="277" href="#277">277</a> <strong>public</strong> <strong>void</strong> testRandomAccess() throws IOException {<a name="278" href="#278">278</a> <strong>final</strong> <strong>int</strong> recordCount = 3;<a name="279" href="#279">279</a> File f = writeRecords(<span class="string">"writeRecord"</span>, <strong>true</strong>, DEFAULT_MAX_WARC_FILE_SIZE,<a name="280" href="#280">280</a> recordCount);<a name="281" href="#281">281</a> <a href="../../../../org/archive/io/warc/WARCReader.html">WARCReader</a> reader = WARCReaderFactory.get(f);<a name="282" href="#282">282</a> <em class="comment">// Get to second record. Get its offset for later use.</em><a name="283" href="#283">283</a> <strong>boolean</strong> readFirst = false;<a name="284" href="#284">284</a> String url = <strong>null</strong>;<a name="285" href="#285">285</a> <strong>long</strong> offset = -1;<a name="286" href="#286">286</a> <strong>long</strong> totalRecords = 0;<a name="287" href="#287">287</a> <strong>boolean</strong> readSecond = false;<a name="288" href="#288">288</a> <strong>for</strong> (<strong>final</strong> Iterator i = reader.iterator(); i.hasNext();<a name="289" href="#289">289</a> totalRecords++) {<a name="290" href="#290">290</a> <a href="../../../../org/archive/io/warc/WARCRecord.html">WARCRecord</a> ar = (WARCRecord)i.next();<a name="291" href="#291">291</a> <strong>if</strong> (!readFirst) {<a name="292" href="#292">292</a> readFirst = <strong>true</strong>;<a name="293" href="#293">293</a> <strong>continue</strong>;<a name="294" href="#294">294</a> }<a name="295" href="#295">295</a> <strong>if</strong> (!readSecond) {<a name="296" href="#296">296</a> url = ar.getHeader().getUrl();<a name="297" href="#297">297</a> offset = ar.getHeader().getOffset();<a name="298" href="#298">298</a> readSecond = <strong>true</strong>;<a name="299" href="#299">299</a> }<a name="300" href="#300">300</a> }<a name="301" href="#301">301</a> <a name="302" href="#302">302</a> reader = WARCReaderFactory.get(f, offset);<a name="303" href="#303">303</a> <a href="../../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> ar = reader.get();<a name="304" href="#304">304</a> assertEquals(ar.getHeader().getUrl(), url);<a name="305" href="#305">305</a> ar.close();<a name="306" href="#306">306</a> <a name="307" href="#307">307</a> <em class="comment">// Get reader again. See how iterator works with offset</em><a name="308" href="#308">308</a> reader = WARCReaderFactory.get(f, offset);<a name="309" href="#309">309</a> <strong>int</strong> count = 0;<a name="310" href="#310">310</a> <strong>for</strong> (<strong>final</strong> Iterator i = reader.iterator(); i.hasNext(); i.next()) {<a name="311" href="#311">311</a> count++;<a name="312" href="#312">312</a> }<a name="313" href="#313">313</a> reader.close();
⌨️ 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 + -