adaptiverevisitfrontier.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

<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/AdaptiveRevisitFrontier.html#finished(org.archive.crawler.datamodel.CrawlURI)">finished</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;Report a URI being processed as having finished processing.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#finishedUriCount()">finishedUriCount</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Number of URIs that have <i>finished</i> processing.</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/AdaptiveRevisitFrontier.html#getClassKey(org.archive.crawler.datamodel.CandidateURI)">getClassKey</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;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;<A HREF="../../../../org/archive/crawler/frontier/FrontierJournal.html" title="interface in org.archive.crawler.frontier">FrontierJournal</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getFrontierJournal()">getFrontierJournal</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;<A HREF="../../../../org/archive/crawler/framework/Frontier.FrontierGroup.html" title="interface in org.archive.crawler.framework">Frontier.FrontierGroup</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getGroup(org.archive.crawler.datamodel.CrawlURI)">getGroup</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;Get the 'frontier group' (usually queue) for the given 
 CrawlURI.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;<A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitHostQueue.html" title="class in org.archive.crawler.frontier">AdaptiveRevisitHostQueue</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getHQ(org.archive.crawler.datamodel.CrawlURI)">getHQ</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;Get the AdaptiveRevisitHostQueue for the given CrawlURI, creating
 it if necessary.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;<A HREF="../../../../org/archive/crawler/framework/FrontierMarker.html" title="interface in org.archive.crawler.framework">FrontierMarker</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getInitialMarker(java.lang.String, boolean)">getInitialMarker</A></B>(java.lang.String&nbsp;regexpr,
                 boolean&nbsp;inCacheOnly)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get a <code>URIFrontierMarker</code> initialized with the given
 regular expression at the 'start' of the Frontier.</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/AdaptiveRevisitFrontier.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>protected &nbsp;<A HREF="../../../../org/archive/crawler/datamodel/CrawlServer.html" title="class in org.archive.crawler.datamodel">CrawlServer</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getServer(org.archive.crawler.datamodel.CrawlURI)">getServer</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;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;java.util.ArrayList</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#getURIsList(org.archive.crawler.framework.FrontierMarker, int, boolean)">getURIsList</A></B>(<A HREF="../../../../org/archive/crawler/framework/FrontierMarker.html" title="interface in org.archive.crawler.framework">FrontierMarker</A>&nbsp;marker,
            int&nbsp;numberOfMatches,
            boolean&nbsp;verbose)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Returns a list of all uncrawled URIs starting from a specified marker
 until <code>numberOfMatches</code> is reached.</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/AdaptiveRevisitFrontier.html#importRecoverLog(java.lang.String)">importRecoverLog</A></B>(java.lang.String&nbsp;pathToLog)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Method is not supported by this Frontier implementation..</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/AdaptiveRevisitFrontier.html#importRecoverLog(java.lang.String, boolean)">importRecoverLog</A></B>(java.lang.String&nbsp;pathToLog,
                 boolean&nbsp;retainFailures)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;This method is not supported by this Frontier implementation</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/AdaptiveRevisitFrontier.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;Initialize the Frontier.</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/AdaptiveRevisitFrontier.html#innerFinished(org.archive.crawler.datamodel.CrawlURI)">innerFinished</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;&nbsp;</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/AdaptiveRevisitFrontier.html#innerSchedule(org.archive.crawler.datamodel.CandidateURI)">innerSchedule</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;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#isDisregarded(org.archive.crawler.datamodel.CrawlURI)">isDisregarded</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;&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/AdaptiveRevisitFrontier.html#isEmpty()">isEmpty</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Returns true if the frontier contains no more URIs to crawl.</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/AdaptiveRevisitFrontier.html#kickUpdate()">kickUpdate</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Notify Frontier that it should consider updating configuration
 info that may have changed in external files.</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/AdaptiveRevisitFrontier.html#loadSeeds()">loadSeeds</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Loads the seeds</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#needsPromptRetry(org.archive.crawler.datamodel.CrawlURI)">needsPromptRetry</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;Checks if a recently completed CrawlURI that did not finish successfully
 needs to be retried immediately (processed again as soon as politeness
 allows.)</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/frontier/AdaptiveRevisitFrontier.html#needsRetrying(org.archive.crawler.datamodel.CrawlURI)">needsRetrying</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;Checks if a recently completed CrawlURI that did not finish successfully
 needs to be retried (processed again after some time elapses)</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">