workqueuefrontier.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

<CODE>protected abstract &nbsp;<A HREF="../../../../org/archive/crawler/frontier/WorkQueue.html" title="class in org.archive.crawler.frontier">WorkQueue</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#getQueueFor(java.lang.String)">getQueueFor</A></B>(java.lang.String&nbsp;classKey)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return the work queue for the given classKey, or null
 if no such queue exists.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;java.lang.String[]</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#getReports()">getReports</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get an array of report names offered by this Reporter.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#initialize(org.archive.crawler.framework.CrawlController)">initialize</A></B>(<A HREF="../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A>&nbsp;c)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Initializes the Frontier, given the supplied CrawlController.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected abstract &nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#initQueue()">initQueue</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#isEmpty()">isEmpty</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Frontier is empty only if all queues are empty and no URIs are in-process</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#kickUpdate()">kickUpdate</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Accomodate any changes in settings.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#next()">next</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return the next CrawlURI to be processed (and presumably
 visited/fetched) by a a worker thread.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#receive(org.archive.crawler.datamodel.CandidateURI)">receive</A></B>(<A HREF="../../../../org/archive/crawler/datamodel/CandidateURI.html" title="class in org.archive.crawler.datamodel">CandidateURI</A>&nbsp;caUri)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Accept the given CandidateURI for scheduling, as it has
 passed the alreadyIncluded filter.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#reportTo(java.lang.String, java.io.PrintWriter)">reportTo</A></B>(java.lang.String&nbsp;name,
         java.io.PrintWriter&nbsp;writer)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;This method compiles a human readable report on the status of the frontier
 at the time of the call.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#schedule(org.archive.crawler.datamodel.CandidateURI)">schedule</A></B>(<A HREF="../../../../org/archive/crawler/datamodel/CandidateURI.html" title="class in org.archive.crawler.datamodel">CandidateURI</A>&nbsp;caUri)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Arrange for the given CandidateURI to be visited, if it is not
 already scheduled/completed.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#sendToQueue(org.archive.crawler.datamodel.CrawlURI)">sendToQueue</A></B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Send a CrawlURI to the appropriate subqueue.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#singleLineLegend()">singleLineLegend</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return a  legend for the single-line summary report as a String.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#singleLineReportTo(java.io.PrintWriter)">singleLineReportTo</A></B>(java.io.PrintWriter&nbsp;w)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Make a single-line summary report to the passed-in writer</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>(package private) &nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#wakeQueues()">wakeQueues</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Wake any queues sitting in the snoozed queue whose time has come.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected abstract &nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/WorkQueueFrontier.html#workQueueDataOnDisk()">workQueueDataOnDisk</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Returns <code>true</code> if the WorkQueue implementation of this
 Frontier stores its workload on disk instead of relying
 on serialization mechanisms.</TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_org.archive.crawler.frontier.AbstractFrontier"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class org.archive.crawler.frontier.<A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html" title="class in org.archive.crawler.frontier">AbstractFrontier</A></B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE><A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#applySpecialHandling(org.archive.crawler.datamodel.CrawlURI)">applySpecialHandling</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#canonicalize(org.archive.crawler.datamodel.CandidateURI)">canonicalize</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#canonicalize(org.archive.net.UURI)">canonicalize</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlCheckpoint(java.io.File)">crawlCheckpoint</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlEnding(java.lang.String)">crawlEnding</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlPaused(java.lang.String)">crawlPaused</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlPausing(java.lang.String)">crawlPausing</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlResuming(java.lang.String)">crawlResuming</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#crawlStarted(java.lang.String)">crawlStarted</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#decrementQueuedCount(long)">decrementQueuedCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#disregardedUriCount()">disregardedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#doJournalAdded(org.archive.crawler.datamodel.CrawlURI)">doJournalAdded</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#doJournalEmitted(org.archive.crawler.datamodel.CrawlURI)">doJournalEmitted</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#doJournalFinishedFailure(org.archive.crawler.datamodel.CrawlURI)">doJournalFinishedFailure</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#doJournalFinishedSuccess(org.archive.crawler.datamodel.CrawlURI)">doJournalFinishedSuccess</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#doJournalRescheduled(org.archive.crawler.datamodel.CrawlURI)">doJournalRescheduled</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#failedFetchCount()">failedFetchCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#finishedUriCount()">finishedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#getClassKey(org.archive.crawler.datamodel.CandidateURI)">getClassKey</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#getFrontierJournal()">getFrontierJournal</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#getServer(org.archive.crawler.datamodel.CrawlURI)">getServer</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#importRecoverLog(java.lang.String, boolean)">importRecoverLog</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#incrementDisregardedUriCount()">incrementDisregardedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#incrementFailedFetchCount()">incrementFailedFetchCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#incrementQueuedUriCount()">incrementQueuedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#incrementQueuedUriCount(long)">incrementQueuedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#incrementSucceededFetchCount()">incrementSucceededFetchCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#isDisregarded(org.archive.crawler.datamodel.CrawlURI)">isDisregarded</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#loadSeeds()">loadSeeds</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#log(org.archive.crawler.datamodel.CrawlURI)">log</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#logLocalizedErrors(org.archive.crawler.datamodel.CrawlURI)">logLocalizedErrors</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#needsRetrying(org.archive.crawler.datamodel.CrawlURI)">needsRetrying</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#noteAboutToEmit(org.archive.crawler.datamodel.CrawlURI, org.archive.crawler.frontier.WorkQueue)">noteAboutToEmit</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#overMaxRetries(org.archive.crawler.datamodel.CrawlURI)">overMaxRetries</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#pause()">pause</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#politenessDelayFor(org.archive.crawler.datamodel.CrawlURI)">politenessDelayFor</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#preNext(long)">preNext</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#queuedUriCount()">queuedUriCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#reportTo(java.io.PrintWriter)">reportTo</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#retryDelayFor(org.archive.crawler.datamodel.CrawlURI)">retryDelayFor</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#saveIgnoredItems(java.lang.String, java.io.File)">saveIgnoredItems</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#scratchDirFor(java.lang.String)">scratchDirFor</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#singleLineReport()">singleLineReport</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#start()">start</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#succeededFetchCount()">succeededFetchCount</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#terminate()">terminate</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#totalBytesWritten()">totalBytesWritten</A>, <A HREF="../../../../org/archive/crawler/frontier/AbstractFrontier.html#unpause()">unpause</A></CODE></TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_org.archive.crawler.settings.ModuleType"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class org.archive.crawler.settings.<A HREF="../../../../org/archive/crawler/settings/ModuleType.html" title="class in org.archive.crawler.settings">ModuleType</A></B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE><A HREF="../../../../org/archive/crawler/settings/ModuleType.html#addElement(org.archive.crawler.settings.CrawlerSettings, org.archive.crawler.settings.Type)">addElement</A>, <A HREF="../../../../org/archive/crawler/settings/ModuleType.html#listUsedFiles(java.util.List)">listUsedFiles</A></CODE></TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_org.archive.crawler.settings.ComplexType"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class org.archive.crawler.settings.<A HREF="../../../../org/archive/crawler/settings/ComplexType.html" title="class in org.archive.crawler.settings">ComplexType</A></B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE><A HREF="../../../../org/archive/crawler/settings/ComplexType.html#addElementToDefinition(org.archive.crawler.settings.Type)">addElementToDefinition</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#checkValue(org.archive.crawler.settings.CrawlerSettings, java.lang.String, java.lang.Object)">checkValue</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#earlyInitialize(org.archive.crawler.settings.CrawlerSettings)">earlyInitialize</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAbsoluteName()">getAbsoluteName</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttribute(java.lang.Object, java.lang.String)">getAttribute</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttribute(java.lang.String)">getAttribute</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttribute(java.lang.String, org.archive.crawler.datamodel.CrawlURI)">getAttribute</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttributeInfo(org.archive.crawler.settings.CrawlerSettings, java.lang.String)">getAttributeInfo</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttributeInfo(java.lang.String)">getAttributeInfo</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttributeInfoIterator(java.lang.Object)">getAttributeInfoIterator</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getAttributes(java.lang.String[])">getAttributes</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getDataContainerRecursive(org.archive.crawler.settings.ComplexType.Context)">getDataContainerRecursive</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getDataContainerRecursive(org.archive.crawler.settings.ComplexType.Context, java.lang.String)">getDataContainerRecursive</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getDefaultValue()">getDefaultValue</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getDescription()">getDescription</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getElementFromDefinition(java.lang.String)">getElementFromDefinition</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getLegalValues()">getLegalValues</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getLocalAttribute(org.archive.crawler.settings.CrawlerSettings, java.lang.String)">getLocalAttribute</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getMBeanInfo()">getMBeanInfo</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getMBeanInfo(java.lang.Object)">getMBeanInfo</A>, <A HREF="../../../../org/archive/crawler/settings/ComplexType.html#getParent()">getParent</A>, <A HREF="../../../../org/archive/crawler/settings/Comple