experimentalwarcwriter.html
来自「网络爬虫开源代码」· HTML 代码 · 共 454 行 · 第 1/3 页
HTML
454 行
<a name="296" href="#296">296</a> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> record = <strong>new</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a>(2);<a name="297" href="#297">297</a> record.addLabelValue(HEADER_KEY_FILENAME, filename);<a name="298" href="#298">298</a> <strong>if</strong> (description != <strong>null</strong> && description.length() > 0) {<a name="299" href="#299">299</a> record.addLabelValue(CONTENT_DESCRIPTION, description);<a name="300" href="#300">300</a> }<a name="301" href="#301">301</a> <em class="comment">// Add warcinfo body.</em><a name="302" href="#302">302</a> byte [] warcinfoBody = <strong>null</strong>;<a name="303" href="#303">303</a> <strong>if</strong> (<strong>this</strong>.fileMetadata == <strong>null</strong>) {<a name="304" href="#304">304</a> <em class="comment">// TODO: What to write into a warcinfo? What to associate?</em><a name="305" href="#305">305</a> warcinfoBody = <span class="string">"TODO: Unimplemented"</span>.getBytes();<a name="306" href="#306">306</a> } <strong>else</strong> {<a name="307" href="#307">307</a> ByteArrayOutputStream baos = <strong>new</strong> ByteArrayOutputStream();<a name="308" href="#308">308</a> <strong>for</strong> (<strong>final</strong> Iterator i = <strong>this</strong>.fileMetadata.iterator();<a name="309" href="#309">309</a> i.hasNext();) {<a name="310" href="#310">310</a> baos.write(i.next().toString().getBytes(UTF8Bytes.UTF8));<a name="311" href="#311">311</a> }<a name="312" href="#312">312</a> warcinfoBody = baos.toByteArray();<a name="313" href="#313">313</a> }<a name="314" href="#314">314</a> URI uri = writeWarcinfoRecord(<span class="string">"text/xml"</span>, record,<a name="315" href="#315">315</a> <strong>new</strong> ByteArrayInputStream(warcinfoBody), warcinfoBody.length);<a name="316" href="#316">316</a> <em class="comment">// TODO: If at start of file, and we're writing compressed,</em><a name="317" href="#317">317</a> <em class="comment">// write out our distinctive GZIP extensions.</em><a name="318" href="#318">318</a> <strong>return</strong> uri;<a name="319" href="#319">319</a> }<a name="320" href="#320">320</a> <a name="321" href="#321">321</a> <em>/**<em>*</em></em><a name="322" href="#322">322</a> <em> * Write a warcinfo to current file.</em><a name="323" href="#323">323</a> <em> * TODO: Write crawl metadata or pointers to crawl description.</em><a name="324" href="#324">324</a> <em> * @param mimetype Mimetype of the <code>fileMetadata</code> block.</em><a name="325" href="#325">325</a> <em> * @param namedFields Named fields. Pass <code>null</code> if none.</em><a name="326" href="#326">326</a> <em> * @param fileMetadata Metadata about this WARC as RDF, ANVL, etc.</em><a name="327" href="#327">327</a> <em> * @param fileMetadataLength Length of <code>fileMetadata</code>.</em><a name="328" href="#328">328</a> <em> * @throws IOException</em><a name="329" href="#329">329</a> <em> * @return Generated record-id made with</em><a name="330" href="#330">330</a> <em> * <a href="<a href="http://en.wikipedia.org/wiki/Data:_URL" target="alexandria_uri">http://en.wikipedia.org/wiki/Data:_URL</a>">data: scheme</a> and</em><a name="331" href="#331">331</a> <em> * the current filename.</em><a name="332" href="#332">332</a> <em> */</em><a name="333" href="#333">333</a> <strong>public</strong> URI writeWarcinfoRecord(<strong>final</strong> String mimetype,<a name="334" href="#334">334</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream fileMetadata,<a name="335" href="#335">335</a> <strong>final</strong> <strong>long</strong> fileMetadataLength)<a name="336" href="#336">336</a> throws IOException {<a name="337" href="#337">337</a> <strong>final</strong> URI recordid = generateRecordId(TYPE, WARCINFO);<a name="338" href="#338">338</a> writeWarcinfoRecord(ArchiveUtils.getLog14Date(), mimetype, recordid,<a name="339" href="#339">339</a> namedFields, fileMetadata, fileMetadataLength);<a name="340" href="#340">340</a> <strong>return</strong> recordid;<a name="341" href="#341">341</a> }<a name="342" href="#342">342</a> <a name="343" href="#343">343</a> <em>/**<em>*</em></em><a name="344" href="#344">344</a> <em> * Write a <code>warcinfo</code> to current file.</em><a name="345" href="#345">345</a> <em> * The <code>warcinfo</code> type uses its <code>recordId</code> as its URL.</em><a name="346" href="#346">346</a> <em> * @param recordId URI to use for this warcinfo.</em><a name="347" href="#347">347</a> <em> * @param create14DigitDate Record creation date as 14 digit date.</em><a name="348" href="#348">348</a> <em> * @param mimetype Mimetype of the <code>fileMetadata</code>.</em><a name="349" href="#349">349</a> <em> * @param namedFields Named fields.</em><a name="350" href="#350">350</a> <em> * @param fileMetadata Metadata about this WARC as RDF, ANVL, etc.</em><a name="351" href="#351">351</a> <em> * @param fileMetadataLength Length of <code>fileMetadata</code>.</em><a name="352" href="#352">352</a> <em> * @throws IOException</em><a name="353" href="#353">353</a> <em> */</em><a name="354" href="#354">354</a> <strong>public</strong> <strong>void</strong> writeWarcinfoRecord(<strong>final</strong> String create14DigitDate,<a name="355" href="#355">355</a> <strong>final</strong> String mimetype, <strong>final</strong> URI recordId, <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields,<a name="356" href="#356">356</a> <strong>final</strong> InputStream fileMetadata, <strong>final</strong> <strong>long</strong> fileMetadataLength)<a name="357" href="#357">357</a> throws IOException {<a name="358" href="#358">358</a> writeRecord(WARCINFO, <strong>null</strong>, create14DigitDate, mimetype,<a name="359" href="#359">359</a> recordId, namedFields, fileMetadata, fileMetadataLength);<a name="360" href="#360">360</a> }<a name="361" href="#361">361</a> <a name="362" href="#362">362</a> <strong>public</strong> <strong>void</strong> writeRequestRecord(<strong>final</strong> String url,<a name="363" href="#363">363</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="364" href="#364">364</a> <strong>final</strong> URI recordId,<a name="365" href="#365">365</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream request,<a name="366" href="#366">366</a> <strong>final</strong> <strong>long</strong> requestLength)<a name="367" href="#367">367</a> throws IOException {<a name="368" href="#368">368</a> writeRecord(REQUEST, url, create14DigitDate,<a name="369" href="#369">369</a> mimetype, recordId, namedFields, request,<a name="370" href="#370">370</a> requestLength);<a name="371" href="#371">371</a> }<a name="372" href="#372">372</a> <a name="373" href="#373">373</a> <strong>public</strong> <strong>void</strong> writeResourceRecord(<strong>final</strong> String url,<a name="374" href="#374">374</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="375" href="#375">375</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream response,<a name="376" href="#376">376</a> <strong>final</strong> <strong>long</strong> responseLength)<a name="377" href="#377">377</a> throws IOException {<a name="378" href="#378">378</a> writeResourceRecord(url, create14DigitDate, mimetype, getRecordID(),<a name="379" href="#379">379</a> namedFields, response, responseLength);<a name="380" href="#380">380</a> }<a name="381" href="#381">381</a> <a name="382" href="#382">382</a> <strong>public</strong> <strong>void</strong> writeResourceRecord(<strong>final</strong> String url,<a name="383" href="#383">383</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="384" href="#384">384</a> <strong>final</strong> URI recordId,<a name="385" href="#385">385</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream response,<a name="386" href="#386">386</a> <strong>final</strong> <strong>long</strong> responseLength)<a name="387" href="#387">387</a> throws IOException {<a name="388" href="#388">388</a> writeRecord(RESOURCE, url, create14DigitDate,<a name="389" href="#389">389</a> mimetype, recordId, namedFields, response,<a name="390" href="#390">390</a> responseLength);<a name="391" href="#391">391</a> }<a name="392" href="#392">392</a> <a name="393" href="#393">393</a> <strong>public</strong> <strong>void</strong> writeResponseRecord(<strong>final</strong> String url,<a name="394" href="#394">394</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="395" href="#395">395</a> <strong>final</strong> URI recordId,<a name="396" href="#396">396</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream response,<a name="397" href="#397">397</a> <strong>final</strong> <strong>long</strong> responseLength)<a name="398" href="#398">398</a> throws IOException {<a name="399" href="#399">399</a> writeRecord(RESPONSE, url, create14DigitDate,<a name="400" href="#400">400</a> mimetype, recordId, namedFields, response,<a name="401" href="#401">401</a> responseLength);<a name="402" href="#402">402</a> }<a name="403" href="#403">403</a> <a name="404" href="#404">404</a> <strong>public</strong> <strong>void</strong> writeRevisitRecord(<strong>final</strong> String url,<a name="405" href="#405">405</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="406" href="#406">406</a> <strong>final</strong> URI recordId,<a name="407" href="#407">407</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream response,<a name="408" href="#408">408</a> <strong>final</strong> <strong>long</strong> responseLength)<a name="409" href="#409">409</a> throws IOException {<a name="410" href="#410">410</a> writeRecord(REVISIT, url, create14DigitDate,<a name="411" href="#411">411</a> mimetype, recordId, namedFields, response,<a name="412" href="#412">412</a> responseLength);<a name="413" href="#413">413</a> }<a name="414" href="#414">414</a> <a name="415" href="#415">415</a> <strong>public</strong> <strong>void</strong> writeMetadataRecord(<strong>final</strong> String url,<a name="416" href="#416">416</a> <strong>final</strong> String create14DigitDate, <strong>final</strong> String mimetype,<a name="417" href="#417">417</a> <strong>final</strong> URI recordId,<a name="418" href="#418">418</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields, <strong>final</strong> InputStream metadata,<a name="419" href="#419">419</a> <strong>final</strong> <strong>long</strong> metadataLength)<a name="420" href="#420">420</a> throws IOException {<a name="421" href="#421">421</a> writeRecord(METADATA, url, create14DigitDate,<a name="422" href="#422">422</a> mimetype, recordId, namedFields, metadata,<a name="423" href="#423">423</a> metadataLength);<a name="424" href="#424">424</a> }<a name="425" href="#425">425</a> <a name="426" href="#426">426</a> <em>/**<em>*</em></em><a name="427" href="#427">427</a> <em> * Convenience method for getting Record-Ids.</em><a name="428" href="#428">428</a> <em> * @return A record ID.</em><a name="429" href="#429">429</a> <em> * @throws IOException</em><a name="430" href="#430">430</a> <em> */</em><a name="431" href="#431">431</a> <strong>public</strong> <strong>static</strong> URI getRecordID() throws IOException {<a name="432" href="#432">432</a> URI result;<a name="433" href="#433">433</a> <strong>try</strong> {<a name="434" href="#434">434</a> result = GeneratorFactory.getFactory().getRecordID();<a name="435" href="#435">435</a> } <strong>catch</strong> (URISyntaxException e) {<a name="436" href="#436">436</a> <strong>throw</strong> <strong>new</strong> IOException(e.toString());<a name="437" href="#437">437</a> }<a name="438" href="#438">438</a> <strong>return</strong> result;<a name="439" href="#439">439</a> }<a name="440" href="#440">440</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
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?