statisticstracking.html

来自「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」· HTML 代码 · 共 849 行 · 第 1/3 页

<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;java.util.Iterator</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/StatisticsTracking.html#getSeedRecordsSortedByStatusCode()">getSeedRecordsSortedByStatusCode</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get a SeedRecord iterator for the job being monitored.</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/StatisticsTracking.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;Do initialization.</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/StatisticsTracking.html#noteStart()">noteStart</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Start the tracker's crawl timing.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;double</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/StatisticsTracking.html#processedDocsPerSec()">processedDocsPerSec</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Returns the number of documents that have been processed
 per second over the life of the crawl (as of last snapshot)</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/framework/StatisticsTracking.html#processedKBPerSec()">processedKBPerSec</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Calculates the rate that data, in kb, has been processed
 over the life of the crawl (as of last snapshot.)</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/StatisticsTracking.html#progressStatisticsLegend()">progressStatisticsLegend</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;long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../../org/archive/crawler/framework/StatisticsTracking.html#successfullyFetchedCount()">successfullyFetchedCount</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Number of <i>successfully</i> processed URIs.</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/framework/StatisticsTracking.html#totalBytesWritten()">totalBytesWritten</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Returns the total number of uncompressed bytes written to disk.</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/framework/StatisticsTracking.html#totalCount()">totalCount</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_java.lang.Runnable"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from interface java.lang.Runnable</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>run</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="SEED_DISPOSITION_SUCCESS"><!-- --></A><H3>
SEED_DISPOSITION_SUCCESS</H3>
<PRE>
static final java.lang.String <B>SEED_DISPOSITION_SUCCESS</B></PRE>
<DL>
<DD>Seed successfully crawled
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.StatisticsTracking.SEED_DISPOSITION_SUCCESS">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="SEED_DISPOSITION_FAILURE"><!-- --></A><H3>
SEED_DISPOSITION_FAILURE</H3>
<PRE>
static final java.lang.String <B>SEED_DISPOSITION_FAILURE</B></PRE>
<DL>
<DD>Failed to crawl seed
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.StatisticsTracking.SEED_DISPOSITION_FAILURE">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="SEED_DISPOSITION_RETRY"><!-- --></A><H3>
SEED_DISPOSITION_RETRY</H3>
<PRE>
static final java.lang.String <B>SEED_DISPOSITION_RETRY</B></PRE>
<DL>
<DD>Failed to crawl seed, will retry
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.StatisticsTracking.SEED_DISPOSITION_RETRY">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="SEED_DISPOSITION_DISREGARD"><!-- --></A><H3>
SEED_DISPOSITION_DISREGARD</H3>
<PRE>
static final java.lang.String <B>SEED_DISPOSITION_DISREGARD</B></PRE>
<DL>
<DD>Seed was disregarded
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.StatisticsTracking.SEED_DISPOSITION_DISREGARD">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="SEED_DISPOSITION_NOT_PROCESSED"><!-- --></A><H3>
SEED_DISPOSITION_NOT_PROCESSED</H3>
<PRE>
static final java.lang.String <B>SEED_DISPOSITION_NOT_PROCESSED</B></PRE>
<DL>
<DD>Seed has not been processed
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.StatisticsTracking.SEED_DISPOSITION_NOT_PROCESSED">Constant Field Values</A></DL>
</DL>

<!-- ============ METHOD DETAIL ========== -->

<A NAME="method_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>Method Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="initialize(org.archive.crawler.framework.CrawlController)"><!-- --></A><H3>
initialize</H3>
<PRE>
void <B>initialize</B>(<A HREF="../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A>&nbsp;c)
                throws <A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></PRE>
<DL>
<DD>Do initialization.

 The CrawlController will call this method before calling the start()
 method.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>c</CODE> - The <A HREF="../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework"><CODE>CrawlController</CODE></A> running the crawl
 that this class is to gather statistics on.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html" title="class in org.archive.crawler.framework.exceptions">FatalConfigurationException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="crawlDuration()"><!-- --></A><H3>
crawlDuration</H3>
<PRE>
long <B>crawlDuration</B>()</PRE>
<DL>
<DD>Returns how long the current crawl has been running (excluding any time
 spent paused/suspended/stopped) since it began.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The length of time - in msec - that this crawl has been running.</DL>
</DD>
</DL>
<HR>

<A NAME="noteStart()"><!-- --></A><H3>
noteStart</H3>
<PRE>
void <B>noteStart</B>()</PRE>
<DL>
<DD>Start the tracker's crawl timing.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="totalBytesWritten()"><!-- --></A><H3>
totalBytesWritten</H3>
<PRE>
long <B>totalBytesWritten</B>()</PRE>
<DL>
<DD>Returns the total number of uncompressed bytes written to disk.  This may
 be different from the actual number if you are using compression.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The total number of uncompressed bytes written to disk</DL>
</DD>
</DL>
<HR>

<A NAME="getCrawlerTotalElapsedTime()"><!-- --></A><H3>
getCrawlerTotalElapsedTime</H3>
<PRE>
long <B>getCrawlerTotalElapsedTime</B>()</PRE>
<DL>
<DD>Total amount of time spent actively crawling so far.<p>
 Returns the total amount of time (in milliseconds) that has elapsed from
 the start of the crawl and until the current time or if the crawl has
 ended until the the end of the crawl <b>minus</b> any
 time spent paused.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Total amount of time (in msec.) spent crawling so far.</DL>
</DD>
</DL>
<HR>

<A NAME="currentProcessedDocsPerSec()"><!-- --></A><H3>
currentProcessedDocsPerSec</H3>
<PRE>
double <B>currentProcessedDocsPerSec</B>()</PRE>
<DL>
<DD>Returns an estimate of recent document download rates
 based on a queue of recently seen CrawlURIs (as of last snapshot).
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The rate per second of documents gathered during the last
 snapshot</DL>
</DD>
</DL>
<HR>

<A NAME="processedDocsPerSec()"><!-- --></A><H3>
processedDocsPerSec</H3>
<PRE>