⭐ 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

📄 experimentalwarcwritertest.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 3 页
字号:
<a name="314" href="#314">314</a>         assertEquals(totalRecords - 1, count);<a name="315" href="#315">315</a>     }<a name="316" href="#316">316</a>     <a name="317" href="#317">317</a>     <strong>public</strong> <strong>void</strong> testWriteRecordCompressed() throws IOException {<a name="318" href="#318">318</a>         <strong>final</strong> <strong>int</strong> recordCount = 2;<a name="319" href="#319">319</a>         File arcFile = writeRecords(<span class="string">"writeRecordCompressed"</span>, <strong>true</strong>,<a name="320" href="#320">320</a>             DEFAULT_MAX_WARC_FILE_SIZE, recordCount);<a name="321" href="#321">321</a>         validate(arcFile, recordCount + 1 <em class="comment">/*<em class="comment">Header record*/</em>);</em><a name="322" href="#322">322</a>     }<a name="323" href="#323">323</a>     <a name="324" href="#324">324</a>     <strong>protected</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> createWARCWriter(String NAME,<a name="325" href="#325">325</a>             <strong>boolean</strong> compress) {<a name="326" href="#326">326</a>         File [] files = {getTmpDir()};<a name="327" href="#327">327</a>         <strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a>(SERIAL_NO,<a name="328" href="#328">328</a>         	Arrays.asList(files), NAME, <span class="string">""</span>,<a name="329" href="#329">329</a>             compress, DEFAULT_MAX_WARC_FILE_SIZE, <strong>null</strong>);<a name="330" href="#330">330</a>     }<a name="331" href="#331">331</a>     <a name="332" href="#332">332</a>     <strong>protected</strong> <strong>static</strong> ByteArrayOutputStream getBaos(String str)<a name="333" href="#333">333</a>     throws IOException {<a name="334" href="#334">334</a>         ByteArrayOutputStream baos = <strong>new</strong> ByteArrayOutputStream();<a name="335" href="#335">335</a>         baos.write(str.getBytes());<a name="336" href="#336">336</a>         <strong>return</strong> baos;<a name="337" href="#337">337</a>     }<a name="338" href="#338">338</a>     <a name="339" href="#339">339</a>     <strong>protected</strong> <strong>static</strong> <strong>void</strong> writeRecord(<a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w, String url,<a name="340" href="#340">340</a>         String mimetype, <strong>int</strong> len, ByteArrayOutputStream baos)<a name="341" href="#341">341</a>     throws IOException {<a name="342" href="#342">342</a>         w.writeResourceRecord(url,<a name="343" href="#343">343</a>             ArchiveUtils.get14DigitDate(),<a name="344" href="#344">344</a>             mimetype,<a name="345" href="#345">345</a>             <strong>null</strong>,<a name="346" href="#346">346</a>             <strong>new</strong> ByteArrayInputStream(baos.toByteArray()),<a name="347" href="#347">347</a>             len);<a name="348" href="#348">348</a>     }<a name="349" href="#349">349</a>     <a name="350" href="#350">350</a>     <strong>protected</strong> <strong>int</strong> iterateRecords(<a href="../../../../org/archive/io/warc/WARCReader.html">WARCReader</a> r)<a name="351" href="#351">351</a>     throws IOException {<a name="352" href="#352">352</a>         <strong>int</strong> count = 0;<a name="353" href="#353">353</a>         <strong>for</strong> (Iterator&lt;ArchiveRecord> i = r.iterator(); i.hasNext();) {<a name="354" href="#354">354</a>             <a href="../../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> ar = i.next();<a name="355" href="#355">355</a>             ar.close();<a name="356" href="#356">356</a>             <strong>if</strong> (count != 0) {<a name="357" href="#357">357</a>                 assertTrue(<span class="string">"Unexpected URL "</span> + ar.getHeader().getUrl(),<a name="358" href="#358">358</a>                     ar.getHeader().getUrl().equals(SOME_URL));<a name="359" href="#359">359</a>             }<a name="360" href="#360">360</a>             count++;<a name="361" href="#361">361</a>         }<a name="362" href="#362">362</a>         <strong>return</strong> count;<a name="363" href="#363">363</a>     }<a name="364" href="#364">364</a>     <a name="365" href="#365">365</a>     <strong>protected</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> createWithOneRecord(String name,<a name="366" href="#366">366</a>         <strong>boolean</strong> compressed)<a name="367" href="#367">367</a>     throws IOException {<a name="368" href="#368">368</a>         <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> writer = createWARCWriter(name, compressed);<a name="369" href="#369">369</a>         String content = getContent();<a name="370" href="#370">370</a>         writeRecord(writer, SOME_URL, <span class="string">"text/html"</span>,<a name="371" href="#371">371</a>             content.length(), getBaos(content));<a name="372" href="#372">372</a>         <strong>return</strong> writer;<a name="373" href="#373">373</a>     }<a name="374" href="#374">374</a>     <a name="375" href="#375">375</a>     <strong>public</strong> <strong>void</strong> testSpaceInURL() {<a name="376" href="#376">376</a>         String eMessage = <strong>null</strong>;<a name="377" href="#377">377</a>         <strong>try</strong> {<a name="378" href="#378">378</a>             holeyUrl(<span class="string">"testSpaceInURL-"</span> + PREFIX, false, <span class="string">" "</span>);<a name="379" href="#379">379</a>         } <strong>catch</strong> (IOException e) {<a name="380" href="#380">380</a>             eMessage = e.getMessage();<a name="381" href="#381">381</a>         }<a name="382" href="#382">382</a>         assertTrue(<span class="string">"Didn't get expected exception: "</span> + eMessage,<a name="383" href="#383">383</a>             eMessage.startsWith(<span class="string">"Contains disallowed"</span>));<a name="384" href="#384">384</a>     }<a name="385" href="#385">385</a> <a name="386" href="#386">386</a>     <strong>public</strong> <strong>void</strong> testTabInURL() {<a name="387" href="#387">387</a>         String eMessage = <strong>null</strong>;<a name="388" href="#388">388</a>         <strong>try</strong> {<a name="389" href="#389">389</a>             holeyUrl(<span class="string">"testTabInURL-"</span> + PREFIX, false, <span class="string">"\t"</span>);<a name="390" href="#390">390</a>         } <strong>catch</strong> (IOException e) {<a name="391" href="#391">391</a>             eMessage = e.getMessage();<a name="392" href="#392">392</a>         }<a name="393" href="#393">393</a>         assertTrue(<span class="string">"Didn't get expected exception: "</span> + eMessage,<a name="394" href="#394">394</a>             eMessage.startsWith(<span class="string">"Contains illegal"</span>));<a name="395" href="#395">395</a>     }<a name="396" href="#396">396</a>     <a name="397" href="#397">397</a>     <strong>protected</strong> <strong>void</strong> holeyUrl(String name, <strong>boolean</strong> compress, String urlInsert)<a name="398" href="#398">398</a>     throws IOException {<a name="399" href="#399">399</a>         <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> writer = createWithOneRecord(name, compress);<a name="400" href="#400">400</a>         <em class="comment">// Add some bytes on the end to mess up the record.</em><a name="401" href="#401">401</a>         String content = getContent();<a name="402" href="#402">402</a>         ByteArrayOutputStream baos = getBaos(content);<a name="403" href="#403">403</a>         writeRecord(writer, SOME_URL + urlInsert + <span class="string">"/index.html"</span>, <span class="string">"text/html"</span>,<a name="404" href="#404">404</a>             content.length(), baos);<a name="405" href="#405">405</a>         writer.close();<a name="406" href="#406">406</a>     }<a name="407" href="#407">407</a>     <a name="408" href="#408">408</a>     <em>/**<em>*</em></em><a name="409" href="#409">409</a> <em>     * Write an arc file for other tests to use.</em><a name="410" href="#410">410</a> <em>     * @param arcdir Directory to write to.</em><a name="411" href="#411">411</a> <em>     * @param compress True if file should be compressed.</em><a name="412" href="#412">412</a> <em>     * @return ARC written.</em><a name="413" href="#413">413</a> <em>     * @throws IOException </em><a name="414" href="#414">414</a> <em>     */</em><a name="415" href="#415">415</a>     <strong>public</strong> <strong>static</strong> File createWARCFile(File arcdir, <strong>boolean</strong> compress)<a name="416" href="#416">416</a>     throws IOException {<a name="417" href="#417">417</a>         File [] files = {arcdir};<a name="418" href="#418">418</a>         <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> writer =<a name="419" href="#419">419</a>             <strong>new</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a>(SERIAL_NO, Arrays.asList(files),<a name="420" href="#420">420</a>             <span class="string">"test"</span>, <span class="string">""</span>, compress, DEFAULT_MAX_WARC_FILE_SIZE, <strong>null</strong>);<a name="421" href="#421">421</a>         String content = getContent();<a name="422" href="#422">422</a>         writeRecord(writer, SOME_URL, <span class="string">"text/html"</span>, content.length(),<a name="423" href="#423">423</a>             getBaos(content));<a name="424" href="#424">424</a>         writer.close();<a name="425" href="#425">425</a>         <strong>return</strong> writer.getFile();<a name="426" href="#426">426</a>     }<a name="427" href="#427">427</a>     <a name="428" href="#428">428</a> <em class="comment">//    public void testSpeed() throws IOException {</em><a name="429" href="#429">429</a> <em class="comment">//        ARCWriter writer = createArcWithOneRecord("speed", true);</em><a name="430" href="#430">430</a> <em class="comment">//        // Add a record with a length that is too long.</em><a name="431" href="#431">431</a> <em class="comment">//        String content = getContent();</em><a name="432" href="#432">432</a> <em class="comment">//        final int count = 100000;</em><a name="433" href="#433">433</a> <em class="comment">//        logger.info("Starting speed write of " + count + " records.");</em><a name="434" href="#434">434</a> <em class="comment">//        for (int i = 0; i &lt; count; i++) {</em><a name="435" href="#435">435</a> <em class="comment">//            writeRecord(writer, SOME_URL, "text/html", content.length(),</em><a name="436" href="#436">436</a> <em class="comment">//                    getBaos(content));</em><a name="437" href="#437">437</a> <em class="comment">//        }</em><a name="438" href="#438">438</a> <em class="comment">//        writer.close();</em><a name="439" href="#439">439</a> <em class="comment">//        logger.info("Finished speed write test.");</em><a name="440" href="#440">440</a> <em class="comment">//    }</em><a name="441" href="#441">441</a>     <a name="442" href="#442">442</a>     <strong>public</strong> <strong>void</strong> testArcRecordOffsetReads() throws Exception {<a name="443" href="#443">443</a>     	<em class="comment">// Get an ARC with one record.</em><a name="444" href="#444">444</a> 		WriterPoolMember w =<a name="445" href="#445">445</a> 			createWithOneRecord(<span class="string">"testArcRecordInBufferStream"</span>, <strong>true</strong>);<a name="446" href="#446">446</a> 		w.close();<a name="447" href="#447">447</a> 		<em class="comment">// Get reader on said ARC.</em><a name="448" href="#448">448</a> 		WARCReader r = WARCReaderFactory.get(w.getFile());<a name="449" href="#449">449</a> 		<strong>final</strong> Iterator&lt;ArchiveRecord> i = r.iterator();<a name="450" href="#450">450</a> 		<em class="comment">// Skip first ARC meta record.</em><a name="451" href="#451">451</a> 		ArchiveRecord ar = i.next();<a name="452" href="#452">452</a> 		i.hasNext();<a name="453" href="#453">453</a> 		<em class="comment">// Now we're at first and only record in ARC.</em><a name="454" href="#454">454</a> 		ar = (WARCRecord) i.next();<a name="455" href="#455">455</a> 		<em class="comment">// Now try getting some random set of bytes out of it </em><a name="456" href="#456">456</a> 		<em class="comment">// at an odd offset (used to fail because we were</em><a name="457" href="#457">457</a> 		<em class="comment">// doing bad math to find where in buffer to read).</em><a name="458" href="#458">458</a> 		<strong>final</strong> byte[] buffer = <strong>new</strong> byte[17];<a name="459" href="#459">459</a> 		<strong>final</strong> <strong>int</strong> maxRead = 4;<a name="460" href="#460">460</a> 		<strong>int</strong> totalRead = 0;<a name="461" href="#461">461</a> 		<strong>while</strong> (totalRead &lt; maxRead) {<a name="462" href="#462">462</a> 			totalRead = totalRead<a name="463" href="#463">463</a> 			    + ar.read(buffer, 13 + totalRead, maxRead - totalRead);<a name="464" href="#464">464</a> 			assertTrue(totalRead > 0);<a name="465" href="#465">465</a> 		}<a name="466" href="#466">466</a> 	}<a name="467" href="#467">467</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 + -