crawlcontroller.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

&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Request a checkpoint.</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/framework/CrawlController.html#requestCrawlPause()">requestCrawlPause</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Stop the crawl temporarly.</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/framework/CrawlController.html#requestCrawlResume()">requestCrawlResume</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Resume crawl from paused state</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/framework/CrawlController.html#requestCrawlStart()">requestCrawlStart</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Operator requested crawl begin</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/framework/CrawlController.html#requestCrawlStop()">requestCrawlStop</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Operator requested for crawl to stop.</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/framework/CrawlController.html#requestCrawlStop(java.lang.String)">requestCrawlStop</A></B>(java.lang.String&nbsp;message)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Operator requested for crawl to stop.</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/framework/CrawlController.html#restoreStatisticsTracker(org.archive.crawler.settings.MapType, java.lang.String)">restoreStatisticsTracker</A></B>(<A HREF="../../../../org/archive/crawler/settings/MapType.html" title="class in org.archive.crawler.settings">MapType</A>&nbsp;loggers,
                         java.lang.String&nbsp;replaceName)</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/framework/CrawlController.html#rotateLogFiles(java.lang.String)">rotateLogFiles</A></B>(java.lang.String&nbsp;generationSuffix)</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/framework/CrawlController.html#runFrontierRecover(java.lang.String)">runFrontierRecover</A></B>(java.lang.String&nbsp;recoverPath)</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/framework/CrawlController.html#sendCheckpointEvent(java.io.File)">sendCheckpointEvent</A></B>(java.io.File&nbsp;checkpointDir)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Send the checkpoint event.</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/framework/CrawlController.html#sendCrawlStateChangeEvent(java.lang.Object, java.lang.String)">sendCrawlStateChangeEvent</A></B>(java.lang.Object&nbsp;newState,
                          java.lang.String&nbsp;message)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Send crawl change event to all listeners.</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/framework/CrawlController.html#setBdbjeBkgrdThreads(com.sleepycat.je.EnvironmentConfig, java.util.List, java.lang.String)">setBdbjeBkgrdThreads</A></B>(com.sleepycat.je.EnvironmentConfig&nbsp;config,
                     java.util.List&nbsp;threads,
                     java.lang.String&nbsp;setting)</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;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/CrawlController.html#setOrder(org.archive.crawler.datamodel.CrawlOrder)">setOrder</A></B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlOrder.html" title="class in org.archive.crawler.datamodel">CrawlOrder</A>&nbsp;o)</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/framework/CrawlController.html#setupCheckpointRecover()">setupCheckpointRecover</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Does setup of checkpoint recover.</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/framework/CrawlController.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;java.lang.String</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/CrawlController.html#singleLineReport()">singleLineReport</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return a short 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/framework/CrawlController.html#singleLineReportTo(java.io.PrintWriter)">singleLineReportTo</A></B>(java.io.PrintWriter&nbsp;writer)</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>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/CrawlController.html#singleThreadMode()">singleThreadMode</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Go to single thread mode, where only one ToeThread may
 proceed at a time.</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/framework/CrawlController.html#toeEnded()">toeEnded</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Note that a ToeThread ended, possibly completing the crawl-stop.</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/framework/CrawlController.html#toePaused()">toePaused</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Note that a ToeThread reached paused condition, possibly
 completing the crawl-pause.</TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
</TR>
</TABLE>
&nbsp;
<P>

<!-- ============ FIELD DETAIL =========== -->

<A NAME="field_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Field Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="MANIFEST_CONFIG_FILE"><!-- --></A><H3>
MANIFEST_CONFIG_FILE</H3>
<PRE>
public static final char <B>MANIFEST_CONFIG_FILE</B></PRE>
<DL>
<DD>abbrieviation label for config files in manifest
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.MANIFEST_CONFIG_FILE">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="MANIFEST_REPORT_FILE"><!-- --></A><H3>
MANIFEST_REPORT_FILE</H3>
<PRE>
public static final char <B>MANIFEST_REPORT_FILE</B></PRE>
<DL>
<DD>abbrieviation label for report files in manifest
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.MANIFEST_REPORT_FILE">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="MANIFEST_LOG_FILE"><!-- --></A><H3>
MANIFEST_LOG_FILE</H3>
<PRE>
public static final char <B>MANIFEST_LOG_FILE</B></PRE>
<DL>
<DD>abbrieviation label for log files in manifest
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.MANIFEST_LOG_FILE">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="CURRENT_LOG_SUFFIX"><!-- --></A><H3>
CURRENT_LOG_SUFFIX</H3>
<PRE>
public static final java.lang.String <B>CURRENT_LOG_SUFFIX</B></PRE>
<DL>
<DD>suffix to use on active logs
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.CURRENT_LOG_SUFFIX">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="uriProcessing"><!-- --></A><H3>
uriProcessing</H3>
<PRE>
public transient java.util.logging.Logger <B>uriProcessing</B></PRE>
<DL>
<DD>Crawl progress logger.

 No exceptions.  Logs summary result of each url processing.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="runtimeErrors"><!-- --></A><H3>
runtimeErrors</H3>
<PRE>
public transient java.util.logging.Logger <B>runtimeErrors</B></PRE>
<DL>
<DD>This logger contains unexpected runtime errors.

 Would contain errors trying to set up a job or failures inside
 processors that they are not prepared to recover from.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="localErrors"><!-- --></A><H3>
localErrors</H3>
<PRE>
public transient java.util.logging.Logger <B>localErrors</B></PRE>
<DL>
<DD>This logger is for job-scoped logging, specifically errors which
 happen and are handled within a particular processor.

 Examples would be socket timeouts, exceptions thrown by extractors, etc.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="uriErrors"><!-- --></A><H3>
uriErrors</H3>
<PRE>
public transient java.util.logging.Logger <B>uriErrors</B></PRE>
<DL>
<DD>Special log for URI format problems, wherever they may occur.
<P>