?? experimentalwarcwriterprocessor.html
字號:
<a name="322" href="#322">322</a> w.writeResponseRecord(curi.toString(), timestamp, mimetype, baseid,<a name="323" href="#323">323</a> namedFields, ris,<a name="324" href="#324">324</a> curi.getHttpRecorder().getRecordedInput().getSize());<a name="325" href="#325">325</a> } <strong>finally</strong> {<a name="326" href="#326">326</a> <strong>if</strong> (ris != <strong>null</strong>) {<a name="327" href="#327">327</a> ris.close();<a name="328" href="#328">328</a> }<a name="329" href="#329">329</a> }<a name="330" href="#330">330</a> <strong>return</strong> baseid;<a name="331" href="#331">331</a> }<a name="332" href="#332">332</a> <a name="333" href="#333">333</a> <strong>protected</strong> URI writeRevisitDigest(<strong>final</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w,<a name="334" href="#334">334</a> <strong>final</strong> String timestamp, <strong>final</strong> String mimetype,<a name="335" href="#335">335</a> <strong>final</strong> URI baseid, <strong>final</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi,<a name="336" href="#336">336</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields) <a name="337" href="#337">337</a> throws IOException {<a name="338" href="#338">338</a> <strong>long</strong> revisedLength = curi.getHttpRecorder().getRecordedInput().getContentBegin();<a name="339" href="#339">339</a> revisedLength = revisedLength > 0 <a name="340" href="#340">340</a> ? revisedLength <a name="341" href="#341">341</a> : curi.getHttpRecorder().getRecordedInput().getSize();<a name="342" href="#342">342</a> namedFields.addLabelValue(<a name="343" href="#343">343</a> HEADER_KEY_PROFILE, PROFILE_REVISIT_IDENTICAL_DIGEST);<a name="344" href="#344">344</a> namedFields.addLabelValue(<a name="345" href="#345">345</a> HEADER_KEY_TRUNCATED, NAMED_FIELD_TRUNCATED_VALUE_LEN);<a name="346" href="#346">346</a> <a href="../../../../org/archive/io/ReplayInputStream.html">ReplayInputStream</a> ris =<a name="347" href="#347">347</a> curi.getHttpRecorder().getRecordedInput().getReplayInputStream();<a name="348" href="#348">348</a> <strong>try</strong> {<a name="349" href="#349">349</a> w.writeRevisitRecord(curi.toString(), timestamp, mimetype, baseid,<a name="350" href="#350">350</a> namedFields, ris, revisedLength);<a name="351" href="#351">351</a> } <strong>finally</strong> {<a name="352" href="#352">352</a> <strong>if</strong> (ris != <strong>null</strong>) {<a name="353" href="#353">353</a> ris.close();<a name="354" href="#354">354</a> }<a name="355" href="#355">355</a> }<a name="356" href="#356">356</a> <strong>return</strong> baseid;<a name="357" href="#357">357</a> }<a name="358" href="#358">358</a> <a name="359" href="#359">359</a> <strong>protected</strong> URI writeRevisitNotModified(<strong>final</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w,<a name="360" href="#360">360</a> <strong>final</strong> String timestamp, <a name="361" href="#361">361</a> <strong>final</strong> URI baseid, <strong>final</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi,<a name="362" href="#362">362</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields) <a name="363" href="#363">363</a> throws IOException {<a name="364" href="#364">364</a> namedFields.addLabelValue(<a name="365" href="#365">365</a> HEADER_KEY_PROFILE, PROFILE_REVISIT_NOT_MODIFIED);<a name="366" href="#366">366</a> <em class="comment">// save just enough context to understand basis of not-modified</em><a name="367" href="#367">367</a> <strong>if</strong>(curi.containsKey(A_HTTP_TRANSACTION)) {<a name="368" href="#368">368</a> <a href="../../../../org/apache/commons/httpclient/HttpMethodBase.html">HttpMethodBase</a> method = <a name="369" href="#369">369</a> (<a href="../../../../org/apache/commons/httpclient/HttpMethodBase.html">HttpMethodBase</a>) curi.getObject(A_HTTP_TRANSACTION);<a name="370" href="#370">370</a> saveHeader(A_ETAG_HEADER,method,namedFields,HEADER_KEY_ETAG);<a name="371" href="#371">371</a> saveHeader(A_LAST_MODIFIED_HEADER,method,namedFields,<a name="372" href="#372">372</a> HEADER_KEY_LAST_MODIFIED);<a name="373" href="#373">373</a> }<a name="374" href="#374">374</a> <em class="comment">// truncate to zero-length (all necessary info is above)</em><a name="375" href="#375">375</a> namedFields.addLabelValue(HEADER_KEY_TRUNCATED,<a name="376" href="#376">376</a> NAMED_FIELD_TRUNCATED_VALUE_LEN);<a name="377" href="#377">377</a> <a href="../../../../org/archive/io/ReplayInputStream.html">ReplayInputStream</a> ris =<a name="378" href="#378">378</a> curi.getHttpRecorder().getRecordedInput().getReplayInputStream();<a name="379" href="#379">379</a> <strong>try</strong> {<a name="380" href="#380">380</a> w.writeRevisitRecord(curi.toString(), timestamp, <strong>null</strong>, baseid,<a name="381" href="#381">381</a> namedFields, ris, 0);<a name="382" href="#382">382</a> } <strong>finally</strong> {<a name="383" href="#383">383</a> <strong>if</strong> (ris != <strong>null</strong>) {<a name="384" href="#384">384</a> ris.close();<a name="385" href="#385">385</a> }<a name="386" href="#386">386</a> }<a name="387" href="#387">387</a> <strong>return</strong> baseid;<a name="388" href="#388">388</a> }<a name="389" href="#389">389</a> <a name="390" href="#390">390</a> <em>/**<em>*</em></em><a name="391" href="#391">391</a> <em> * Save a header from the given HTTP operation into the </em><a name="392" href="#392">392</a> <em> * provider headers under a new name</em><a name="393" href="#393">393</a> <em> * </em><a name="394" href="#394">394</a> <em> * @param origName header name to get if present</em><a name="395" href="#395">395</a> <em> * @param method http operation containing headers</em><a name="396" href="#396">396</a> <em> */</em><a name="397" href="#397">397</a> <strong>protected</strong> <strong>void</strong> saveHeader(String origName, <a href="../../../../org/apache/commons/httpclient/HttpMethodBase.html">HttpMethodBase</a> method, <a name="398" href="#398">398</a> ANVLRecord headers, String newName) {<a name="399" href="#399">399</a> Header header = method.getResponseHeader(origName);<a name="400" href="#400">400</a> <strong>if</strong>(header!=<strong>null</strong>) {<a name="401" href="#401">401</a> headers.addLabelValue(newName, header.getValue());<a name="402" href="#402">402</a> }<a name="403" href="#403">403</a> }<a name="404" href="#404">404</a> <a name="405" href="#405">405</a> <strong>protected</strong> URI writeMetadata(<strong>final</strong> <a href="../../../../org/archive/io/warc/ExperimentalWARCWriter.html">ExperimentalWARCWriter</a> w,<a name="406" href="#406">406</a> <strong>final</strong> String timestamp,<a name="407" href="#407">407</a> <strong>final</strong> URI baseid, <strong>final</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi,<a name="408" href="#408">408</a> <strong>final</strong> <a href="../../../../org/archive/util/anvl/ANVLRecord.html">ANVLRecord</a> namedFields) <a name="409" href="#409">409</a> throws IOException {<a name="410" href="#410">410</a> <strong>final</strong> URI uid = qualifyRecordID(baseid, TYPE, METADATA);<a name="411" href="#411">411</a> <em class="comment">// Get some metadata from the curi.</em><a name="412" href="#412">412</a> <em class="comment">// TODO: Get all curi metadata.</em><a name="413" href="#413">413</a> <em class="comment">// TODO: Use other than ANVL (or rename ANVL as NameValue or use</em><a name="414" href="#414">414</a> <em class="comment">// RFC822 (commons-httpclient?).</em><a name="415" href="#415">415</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>();<a name="416" href="#416">416</a> <strong>if</strong> (curi.isSeed()) {<a name="417" href="#417">417</a> r.addLabel(<span class="string">"seed"</span>);<a name="418" href="#418">418</a> } <strong>else</strong> {<a name="419" href="#419">419</a> <strong>if</strong> (curi.forceFetch()) {<a name="420" href="#420">420</a> r.addLabel(<span class="string">"force-fetch"</span>);<a name="421" href="#421">421</a> }<a name="422" href="#422">422</a> r.addLabelValue(<span class="string">"via"</span>, curi.flattenVia());<a name="423" href="#423">423</a> r.addLabelValue(<span class="string">"pathFromSeed"</span>, curi.getPathFromSeed());<a name="424" href="#424">424</a> <strong>if</strong> (curi.containsKey(A_SOURCE_TAG)) {<a name="425" href="#425">425</a> r.addLabelValue(<span class="string">"sourceTag"</span>, curi.getString(A_SOURCE_TAG));<a name="426" href="#426">426</a> }<a name="427" href="#427">427</a> }<a name="428" href="#428">428</a> <a name="429" href="#429">429</a> <em class="comment">// Add outlinks though they are effectively useless without anchor text.</em><a name="430" href="#430">430</a> Collection<Link> links = curi.getOutLinks();<a name="431" href="#431">431</a> <strong>if</strong> (links != <strong>null</strong> && links.size() > 0) {<a name="432" href="#432">432</a> <strong>for</strong> (Link link: links) {<a name="433" href="#433">433</a> r.addLabelValue(<span class="string">"outlink"</span>, link.toString());<a name="434" href="#434">434</a> }<a name="435" href="#435">435</a> }<a name="436" href="#436">436</a> <a name="437" href="#437">437</a> <em class="comment">// TODO: Other curi fields to write to metadata.</em><a name="438" href="#438">438</a> <em class="comment">// </em><a name="439" href="#439">439</a> <em class="comment">// Credentials</em><a name="440" href="#440">440</a> <em class="comment">// </em><a name="441" href="#441">441</a> <em class="comment">// fetch-began-time: 1154569278774</em><a name="442" href="#442">442</a> <em class="comment">// fetch-completed-time: 1154569281816</em><a name="443" href="#443">443</a> <em class="comment">//</em><a name="444" href="#444">444</a> <em class="comment">// Annotations.</em><a name="445" href="#445">445</a> <a name="446" href="#446">446</a> byte [] b = r.getUTF8Bytes();<a name="447" href="#447">447</a> w.writeMetadataRecord(curi.toString(), timestamp, ANVLRecord.MIMETYPE,<a name="448" href="#448">448</a> uid, namedFields, <strong>new</strong> ByteArrayInputStream(b), b.length);<a name="449" href="#449">449</a> <strong>return</strong> uid;<a name="450" href="#450">450</a> }<a name="451" href="#451">451</a> <a name="452" href="#452">452</a> <strong>protected</strong> URI getRecordID() throws IOException {<a name="453" href="#453">453</a> URI result;<a name="454" href="#454">454</a> <strong>try</strong> {<a name="455" href="#455">455</a> result = GeneratorFactory.getFactory().getRecordID();<a name="456" href="#456">456</a> } <strong>catch</strong> (URISyntaxException e) {<a name="457" href="#457">457</a> <strong>throw</strong> <strong>new</strong> IOException(e.toString());<a name="458" href="#458">458</a> }<a name="459" href="#459">459</a> <strong>return</strong> result;<a name="460" href="#460">460</a> }<a name="461" href="#461">461</a> <a name="462" href="#462">462</a> <strong>protected</strong> URI qualifyRecordID(<strong>final</strong> URI base, <strong>final</strong> String key,<a name="463" href="#463">463</a> <strong>final</strong> String value)<a name="464" href="#464">464</a> throws IOException {<a name="465" href="#465">465</a> URI result;<a name="466" href="#466">466</a> Map<String, String> qualifiers = <strong>new</strong> HashMap<String, String>(1);<a name="467" href="#467">467</a> qualifiers.put(key, value);<a name="468" href="#468">468</a> <strong>try</strong> {<a name="469" href="#469">469</a> result = GeneratorFactory.getFactory().<a name="470" href="#470">470</a> qualifyRecordID(base, qualifiers);<a name="471" href="#471">471</a> } <strong>catch</strong> (URISyntaxException e) {<a name="472" href="#472">472</a> <strong>throw</strong> <strong>new</strong> IOException(e.toString());<a name="473" href="#473">473</a> }<a name="474" href="#474">474</a> <strong>return</strong> result;<a name="475" href="#475">475</a> } <a name="476" href="#476">476</a> <a name="477" href="#477">477</a> @Override<a name="478" href="#478">478</a> <strong>protected</strong> String getFirstrecordStylesheet() {<a name="479" href="#479">479</a> <strong>return</strong> <span class="string">"/warcinfobody.xsl"</span>;<a name="480" href="#480">480</a> }<a name="481" href="#481">481</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>
?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -