📄 bdbmultipleworkqueues.html
字号:
<a name="421" href="#421">421</a> <em> * @throws DatabaseException</em><a name="422" href="#422">422</a> <em> */</em><a name="423" href="#423">423</a> <strong>public</strong> <strong>void</strong> delete(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> item) throws DatabaseException {<a name="424" href="#424">424</a> OperationStatus status;<a name="425" href="#425">425</a> status = pendingUrisDB.delete(<strong>null</strong>, (DatabaseEntry) item.getHolderKey());<a name="426" href="#426">426</a> <strong>if</strong> (status != OperationStatus.SUCCESS) {<a name="427" href="#427">427</a> LOGGER.severe(<span class="string">"expected item not present: "</span><a name="428" href="#428">428</a> + item<a name="429" href="#429">429</a> + <span class="string">"("</span><a name="430" href="#430">430</a> + (<strong>new</strong> BigInteger(((DatabaseEntry) item.getHolderKey())<a name="431" href="#431">431</a> .getData())).toString(16) + <span class="string">")"</span>);<a name="432" href="#432">432</a> }<a name="433" href="#433">433</a> <a name="434" href="#434">434</a> }<a name="435" href="#435">435</a> <a name="436" href="#436">436</a> <em>/**<em>*</em></em><a name="437" href="#437">437</a> <em> * Method used by BdbFrontier during checkpointing.</em><a name="438" href="#438">438</a> <em> * <p>The backing bdbje database has been marked deferred write so we save</em><a name="439" href="#439">439</a> <em> * on writes to disk. Means no guarantees disk will have whats in memory</em><a name="440" href="#440">440</a> <em> * unless a sync is called (Calling sync on the bdbje Environment is not</em><a name="441" href="#441">441</a> <em> * sufficent).</em><a name="442" href="#442">442</a> <em> * <p>Package access only because only Frontiers of this package would ever</em><a name="443" href="#443">443</a> <em> * need access.</em><a name="444" href="#444">444</a> <em> * @see <a href="<a href="http://www.sleepycat.com/jedocs/GettingStartedGuide/DB.html" target="alexandria_uri">http://www.sleepycat.com/jedocs/GettingStartedGuide/DB.html</a>">Deferred Write Databases</a></em><a name="445" href="#445">445</a> <em> */</em><a name="446" href="#446">446</a> <strong>void</strong> sync() {<a name="447" href="#447">447</a> <strong>if</strong> (<strong>this</strong>.pendingUrisDB == <strong>null</strong>) {<a name="448" href="#448">448</a> <strong>return</strong>;<a name="449" href="#449">449</a> }<a name="450" href="#450">450</a> <strong>try</strong> {<a name="451" href="#451">451</a> <strong>this</strong>.pendingUrisDB.sync();<a name="452" href="#452">452</a> } <strong>catch</strong> (DatabaseException e) {<a name="453" href="#453">453</a> e.printStackTrace();<a name="454" href="#454">454</a> }<a name="455" href="#455">455</a> }<a name="456" href="#456">456</a> <a name="457" href="#457">457</a> <em>/**<em>*</em></em><a name="458" href="#458">458</a> <em> * clean up </em><a name="459" href="#459">459</a> <em> *</em><a name="460" href="#460">460</a> <em> */</em><a name="461" href="#461">461</a> <strong>public</strong> <strong>void</strong> close() {<a name="462" href="#462">462</a> <strong>try</strong> {<a name="463" href="#463">463</a> <strong>this</strong>.pendingUrisDB.close();<a name="464" href="#464">464</a> } <strong>catch</strong> (DatabaseException e) {<a name="465" href="#465">465</a> e.printStackTrace();<a name="466" href="#466">466</a> }<a name="467" href="#467">467</a> }<a name="468" href="#468">468</a> <a name="469" href="#469">469</a> <em>/**<em>*</em></em><a name="470" href="#470">470</a> <em> * Marker for remembering a position within the BdbMultipleWorkQueues.</em><a name="471" href="#471">471</a> <em> * </em><a name="472" href="#472">472</a> <em> * @author gojomo</em><a name="473" href="#473">473</a> <em> */</em><a name="474" href="#474">474</a> <strong>public</strong> <strong>class</strong> BdbFrontierMarker implements <a href="../../../../org/archive/crawler/framework/FrontierMarker.html">FrontierMarker</a> {<a name="475" href="#475">475</a> DatabaseEntry startKey;<a name="476" href="#476">476</a> Pattern pattern; <a name="477" href="#477">477</a> <strong>int</strong> nextItemNumber;<a name="478" href="#478">478</a> <a name="479" href="#479">479</a> <em>/**<em>*</em></em><a name="480" href="#480">480</a> <em> * Create a marker pointed at the given start location.</em><a name="481" href="#481">481</a> <em> * </em><a name="482" href="#482">482</a> <em> * @param startKey</em><a name="483" href="#483">483</a> <em> * @param regexpr</em><a name="484" href="#484">484</a> <em> */</em><a name="485" href="#485">485</a> <strong>public</strong> BdbFrontierMarker(DatabaseEntry startKey, String regexpr) {<a name="486" href="#486">486</a> <strong>this</strong>.startKey = startKey;<a name="487" href="#487">487</a> pattern = Pattern.compile(regexpr);<a name="488" href="#488">488</a> nextItemNumber = 1;<a name="489" href="#489">489</a> }<a name="490" href="#490">490</a> <a name="491" href="#491">491</a> <em>/**<em>*</em></em><a name="492" href="#492">492</a> <em> * @param curi</em><a name="493" href="#493">493</a> <em> * @return whether the marker accepts the given CrawlURI</em><a name="494" href="#494">494</a> <em> */</em><a name="495" href="#495">495</a> <strong>public</strong> <strong>boolean</strong> accepts(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="496" href="#496">496</a> <strong>boolean</strong> retVal = pattern.matcher(curi.toString()).matches();<a name="497" href="#497">497</a> <strong>if</strong>(retVal==<strong>true</strong>) {<a name="498" href="#498">498</a> nextItemNumber++;<a name="499" href="#499">499</a> }<a name="500" href="#500">500</a> <strong>return</strong> retVal;<a name="501" href="#501">501</a> }<a name="502" href="#502">502</a> <a name="503" href="#503">503</a> <em>/**<em>*</em></em><a name="504" href="#504">504</a> <em> * @param key position for marker</em><a name="505" href="#505">505</a> <em> */</em><a name="506" href="#506">506</a> <strong>public</strong> <strong>void</strong> setStartKey(DatabaseEntry key) {<a name="507" href="#507">507</a> startKey = key;<a name="508" href="#508">508</a> }<a name="509" href="#509">509</a> <a name="510" href="#510">510</a> <em>/**<em>*</em></em><a name="511" href="#511">511</a> <em> * @return startKey</em><a name="512" href="#512">512</a> <em> */</em><a name="513" href="#513">513</a> <strong>public</strong> DatabaseEntry getStartKey() {<a name="514" href="#514">514</a> <strong>return</strong> startKey;<a name="515" href="#515">515</a> }<a name="516" href="#516">516</a> <a name="517" href="#517">517</a> <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="518" href="#518">518</a> <em class="comment"> * @see org.archive.crawler.framework.FrontierMarker#getMatchExpression()</em><a name="519" href="#519">519</a> <em class="comment"> */</em><a name="520" href="#520">520</a> <strong>public</strong> String getMatchExpression() {<a name="521" href="#521">521</a> <strong>return</strong> pattern.pattern();<a name="522" href="#522">522</a> }<a name="523" href="#523">523</a> <a name="524" href="#524">524</a> <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="525" href="#525">525</a> <em class="comment"> * @see org.archive.crawler.framework.FrontierMarker#getNextItemNumber()</em><a name="526" href="#526">526</a> <em class="comment"> */</em><a name="527" href="#527">527</a> <strong>public</strong> <strong>long</strong> getNextItemNumber() {<a name="528" href="#528">528</a> <strong>return</strong> nextItemNumber;<a name="529" href="#529">529</a> }<a name="530" href="#530">530</a> <a name="531" href="#531">531</a> <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="532" href="#532">532</a> <em class="comment"> * @see org.archive.crawler.framework.FrontierMarker#hasNext()</em><a name="533" href="#533">533</a> <em class="comment"> */</em><a name="534" href="#534">534</a> <strong>public</strong> <strong>boolean</strong> hasNext() {<a name="535" href="#535">535</a> <em class="comment">// as long as any startKey is stated, consider as having next</em><a name="536" href="#536">536</a> <strong>return</strong> startKey != <strong>null</strong>;<a name="537" href="#537">537</a> }<a name="538" href="#538">538</a> }<a name="539" href="#539">539</a> <a name="540" href="#540">540</a> <em>/**<em>*</em></em><a name="541" href="#541">541</a> <em> * Add a dummy 'cap' entry at the given insertion key. Prevents</em><a name="542" href="#542">542</a> <em> * 'seeks' to queue heads from holding lock on last item of </em><a name="543" href="#543">543</a> <em> * 'preceding' queue. See:</em><a name="544" href="#544">544</a> <em> * <a href="http://sourceforge.net/tracker/index.php?func=detail&aid=1262665&group_id=73833&atid=539102" target="alexandria_uri">http://sourceforge.net/tracker/index.php?func=detail&aid=1262665&group_id=73833&atid=539102</a></em><a name="545" href="#545">545</a> <em> * </em><a name="546" href="#546">546</a> <em> * @param origin key at which to insert the cap</em><a name="547" href="#547">547</a> <em> */</em><a name="548" href="#548">548</a> <strong>public</strong> <strong>void</strong> addCap(byte[] origin) {<a name="549" href="#549">549</a> <strong>try</strong> {<a name="550" href="#550">550</a> pendingUrisDB.put(<strong>null</strong>, <strong>new</strong> DatabaseEntry(origin),<a name="551" href="#551">551</a> <strong>new</strong> DatabaseEntry(<strong>new</strong> byte[0]));<a name="552" href="#552">552</a> } <strong>catch</strong> (DatabaseException e) {<a name="553" href="#553">553</a> <strong>throw</strong> <strong>new</strong> RuntimeException(e);<a name="554" href="#554">554</a> }<a name="555" href="#555">555</a> }<a name="556" href="#556">556</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 + -