📄 adaptiverevisithostqueue.html
字号:
<a name="424" href="#424">424</a> <strong>return</strong>;<a name="425" href="#425">425</a> }<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>/**<em>*</em></em><a name="430" href="#430">430</a> <em> * Count all entries in both primaryUriDB and processingUriDB.</em><a name="431" href="#431">431</a> <em> * <p></em><a name="432" href="#432">432</a> <em> * This method is needed since BDB does not provide a simple way of counting</em><a name="433" href="#433">433</a> <em> * entries.</em><a name="434" href="#434">434</a> <em> * <p></em><a name="435" href="#435">435</a> <em> * Note: This is an expensive operation, requires a loop through the entire</em><a name="436" href="#436">436</a> <em> * queue!</em><a name="437" href="#437">437</a> <em> * @return the number of distinct CrawlURIs in the HQ.</em><a name="438" href="#438">438</a> <em> * @throws DatabaseException</em><a name="439" href="#439">439</a> <em> */</em><a name="440" href="#440">440</a> <strong>protected</strong> <strong>long</strong> countCrawlURIs() throws DatabaseException{<a name="441" href="#441">441</a> <em class="comment">// TODO: Instead of all this, the value should be simply read from the</em><a name="442" href="#442">442</a> <em class="comment">// database.</em><a name="443" href="#443">443</a> <strong>long</strong> count = 0;<a name="444" href="#444">444</a> <a name="445" href="#445">445</a> DatabaseEntry keyEntry = <strong>new</strong> DatabaseEntry();<a name="446" href="#446">446</a> DatabaseEntry dataEntry = <strong>new</strong> DatabaseEntry(); <a name="447" href="#447">447</a> <a name="448" href="#448">448</a> <em class="comment">// Count URIs in the queue</em><a name="449" href="#449">449</a> Cursor primaryCursor = primaryUriDB.openCursor(<strong>null</strong>,<strong>null</strong>);<a name="450" href="#450">450</a> OperationStatus opStatus = primaryCursor.getFirst(keyEntry,<a name="451" href="#451">451</a> dataEntry,<a name="452" href="#452">452</a> LockMode.DEFAULT);<a name="453" href="#453">453</a> <strong>while</strong>(opStatus == OperationStatus.SUCCESS){<a name="454" href="#454">454</a> count++;<a name="455" href="#455">455</a> opStatus = primaryCursor.getNext(keyEntry,<a name="456" href="#456">456</a> dataEntry,<a name="457" href="#457">457</a> LockMode.DEFAULT);<a name="458" href="#458">458</a> }<a name="459" href="#459">459</a> <a name="460" href="#460">460</a> primaryCursor.close();<a name="461" href="#461">461</a> <a name="462" href="#462">462</a> <em class="comment">// Now count URIs in the processingUriDB</em><a name="463" href="#463">463</a> Cursor processingCursor = processingUriDB.openCursor(<strong>null</strong>,<strong>null</strong>);<a name="464" href="#464">464</a> opStatus = processingCursor.getFirst(keyEntry,<a name="465" href="#465">465</a> dataEntry,<a name="466" href="#466">466</a> LockMode.DEFAULT);<a name="467" href="#467">467</a> <strong>while</strong>(opStatus == OperationStatus.SUCCESS){<a name="468" href="#468">468</a> count++;<a name="469" href="#469">469</a> opStatus = processingCursor.getNext(keyEntry,<a name="470" href="#470">470</a> dataEntry,<a name="471" href="#471">471</a> LockMode.DEFAULT);<a name="472" href="#472">472</a> }<a name="473" href="#473">473</a> <a name="474" href="#474">474</a> processingCursor.close();<a name="475" href="#475">475</a> <strong>return</strong> count;<a name="476" href="#476">476</a> }<a name="477" href="#477">477</a> <a name="478" href="#478">478</a> <em>/**<em>*</em></em><a name="479" href="#479">479</a> <em> * Returns true if this HQ has a CrawlURI matching the uri string currently</em><a name="480" href="#480">480</a> <em> * being processed. False otherwise.</em><a name="481" href="#481">481</a> <em> * </em><a name="482" href="#482">482</a> <em> * @param uri Uri to check</em><a name="483" href="#483">483</a> <em> * @return true if this HQ has a CrawlURI matching the uri string currently</em><a name="484" href="#484">484</a> <em> * being processed. False otherwise.</em><a name="485" href="#485">485</a> <em> * </em><a name="486" href="#486">486</a> <em> * @throws DatabaseException</em><a name="487" href="#487">487</a> <em> */</em><a name="488" href="#488">488</a> <strong>protected</strong> <strong>boolean</strong> inProcessing(String uri) throws DatabaseException{<a name="489" href="#489">489</a> DatabaseEntry keyEntry = <strong>new</strong> DatabaseEntry();<a name="490" href="#490">490</a> DatabaseEntry dataEntry = <strong>new</strong> DatabaseEntry();<a name="491" href="#491">491</a> <a name="492" href="#492">492</a> StringBinding.stringToEntry(uri,keyEntry);<a name="493" href="#493">493</a> <a name="494" href="#494">494</a> OperationStatus opStatus = processingUriDB.get(<strong>null</strong>,<a name="495" href="#495">495</a> keyEntry,<a name="496" href="#496">496</a> dataEntry,<a name="497" href="#497">497</a> LockMode.DEFAULT);<a name="498" href="#498">498</a> <a name="499" href="#499">499</a> <strong>if</strong> (opStatus == OperationStatus.SUCCESS){<a name="500" href="#500">500</a> <strong>return</strong> <strong>true</strong>;<a name="501" href="#501">501</a> }<a name="502" href="#502">502</a> <a name="503" href="#503">503</a> <strong>return</strong> false; <em class="comment">//Not found</em><a name="504" href="#504">504</a> }<a name="505" href="#505">505</a> <a name="506" href="#506">506</a> <em>/**<em>*</em></em><a name="507" href="#507">507</a> <em> * Removes a URI from the list of URIs belonging to this HQ and are </em><a name="508" href="#508">508</a> <em> * currently being processed.</em><a name="509" href="#509">509</a> <em> * <p></em><a name="510" href="#510">510</a> <em> * Returns true if successful, false if the URI was not found.</em><a name="511" href="#511">511</a> <em> * </em><a name="512" href="#512">512</a> <em> * @param uri The URI string of the CrawlURI to delete.</em><a name="513" href="#513">513</a> <em> * </em><a name="514" href="#514">514</a> <em> * @throws DatabaseException</em><a name="515" href="#515">515</a> <em> * @throws IllegalStateException if the URI was not on the list</em><a name="516" href="#516">516</a> <em> */</em><a name="517" href="#517">517</a> <strong>protected</strong> <strong>void</strong> deleteInProcessing(String uri) throws DatabaseException {<a name="518" href="#518">518</a> DatabaseEntry keyEntry = <strong>new</strong> DatabaseEntry();<a name="519" href="#519">519</a> <a name="520" href="#520">520</a> StringBinding.stringToEntry(uri, keyEntry);<a name="521" href="#521">521</a> <a name="522" href="#522">522</a> OperationStatus opStatus = processingUriDB.delete(<strong>null</strong>, keyEntry);<a name="523" href="#523">523</a> <a name="524" href="#524">524</a> <strong>if</strong> (opStatus != OperationStatus.SUCCESS) {<a name="525" href="#525">525</a> <strong>if</strong> (opStatus == OperationStatus.NOTFOUND) {<a name="526" href="#526">526</a> <strong>throw</strong> <strong>new</strong> IllegalStateException(<span class="string">"Trying to deleta a "</span><a name="527" href="#527">527</a> + <span class="string">"non-existant URI from the list of URIs being "</span><a name="528" href="#528">528</a> + <span class="string">"processed. HQ: "</span> + hostName + <span class="string">", CrawlURI: "</span> + uri);<a name="529" href="#529">529</a> }<a name="530" href="#530">530</a> <strong>throw</strong> <strong>new</strong> DatabaseException(<span class="string">"Error occured deleting URI: "</span> + uri<a name="531" href="#531">531</a> + <span class="string">" from HQ "</span> + hostName + <span class="string">" list "</span><a name="532" href="#532">532</a> + <span class="string">"of URIs currently being processed. "</span><a name="533" href="#533">533</a> + opStatus.toString());<a name="534" href="#534">534</a> }<a name="535" href="#535">535</a> }<a name="536" href="#536">536</a> <a name="537" href="#537">537</a> <em>/**<em>*</em></em><a name="538" href="#538">538</a> <em> * Adds a CrawlURI to the list of CrawlURIs belonging to this HQ and are</em><a name="539" href="#539">539</a> <em> * being processed at the moment.</em><a name="540" href="#540">540</a> <em> * </em><a name="541" href="#541">541</a> <em> * @param curi</em><a name="542" href="#542">542</a> <em> * The CrawlURI to add to the list</em><a name="543" href="#543">543</a> <em> * @throws DatabaseException</em><a name="544" href="#544">544</a> <em> * @throws IllegalStateException</em><a name="545" href="#545">545</a> <em> * if the CrawlURI is already in the list of URIs being</em><a name="546" href="#546">546</a> <em> * processed.</em><a name="547" href="#547">547</a> <em> */</em><a name="548" href="#548">548</a> <strong>protected</strong> <strong>void</strong> addInProcessing(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) throws DatabaseException,<a name="549" href="#549">549</a> IllegalStateException {<a name="550" href="#550">550</a> DatabaseEntry keyEntry = <strong>new</strong> DatabaseEntry();<a name="551" href="#551">551</a> DatabaseEntry dataEntry = <strong>new</strong> DatabaseEntry();<a name="552" href="#552">552</a> <a name="553" href="#553">553</a> StringBinding.stringToEntry(curi.toString(), keyEntry);<a name="554" href="#554">554</a> crawlURIBinding.objectToEntry(curi, dataEntry);<a name="555" href="#555">555</a> <a name="556" href="#556">556</a> OperationStatus opStatus = processingUriDB.putNoOverwrite(<strong>null</strong>,<a name="557" href="#557">557</a> keyEntry, dataEntry);<a name="558" href="#558">558</a> <a name="559" href="#559">559</a> <strong>if</strong> (opStatus != OperationStatus.SUCCESS) {<a name="560" href="#560">560</a> <strong>if</strong> (opStatus == OperationStatus.KEYEXIST) {<a name="561" href="#561">561</a> <strong>throw</strong> <strong>new</strong> IllegalStateException(<span class="string">"Can not insert duplicate "</span><a name="562" href="#562">562</a> + <span class="string">"URI into list of URIs being processed. "</span> + <span class="string">"HQ: "</span><a name="563" href="#563">563</a> + hostName + <span class="string">", CrawlURI: "</span> + curi.toString());<a name="564" href="#564">564</a> }<a name="565" href="#565">565</a> <strong>throw</strong> <strong>new</strong> DatabaseException(<span class="string">"Error occured adding CrawlURI: "</span><a name="566" href="#566">566</a> + curi.toString() + <span class="string">" to HQ "</span> + hostName + <span class="string">" list "</span><a name="567" href="#567">567</a> + <span class="string">"of URIs currently being processed. "</span>
⌨️ 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 + -