recoverylogmapper.html

一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫

<A NAME="RecoveryLogMapper(java.lang.String)"><!-- --></A><H3>
RecoveryLogMapper</H3>
<PRE>
public <B>RecoveryLogMapper</B>(java.lang.String&nbsp;recoverLogFileName)
                  throws java.io.FileNotFoundException,
                         java.io.IOException,
                         <A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></PRE>
<DL>
<DD>Normal constructor - if encounter not-found seeds while loading
 recoverLogFileName, will throw throw SeedUrlNotFoundException.
 Use <A HREF="../../../../org/archive/crawler/util/RecoveryLogMapper.html#RecoveryLogMapper(java.lang.String)"><CODE>RecoveryLogMapper(String)</CODE></A> if you want to just log
 such cases and keep going.  (Those should not happen if the
 recover log is written correctly, but we see them in pratice.)
<P>
<DL>
<DT><B>Parameters:</B><DD><CODE>recoverLogFileName</CODE> - 
<DT><B>Throws:</B>
<DD><CODE>java.io.FileNotFoundException</CODE>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE><A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></CODE></DL>
</DL>
<HR>

<A NAME="RecoveryLogMapper(java.lang.String, java.lang.String)"><!-- --></A><H3>
RecoveryLogMapper</H3>
<PRE>
public <B>RecoveryLogMapper</B>(java.lang.String&nbsp;recoverLogFileName,
                         java.lang.String&nbsp;seedNotFoundLogFileName)
                  throws java.io.FileNotFoundException,
                         java.io.IOException,
                         <A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></PRE>
<DL>
<DD>Constructor to use if you want to allow not-found seeds, logging
 them to seedNotFoundLogFileName.  In contrast, <A HREF="../../../../org/archive/crawler/util/RecoveryLogMapper.html#RecoveryLogMapper(java.lang.String)"><CODE>RecoveryLogMapper(String)</CODE></A> will throw SeedUrlNotFoundException
 when a seed isn't found.
<P>
<DL>
<DT><B>Parameters:</B><DD><CODE>recoverLogFileName</CODE> - <DD><CODE>seedNotFoundLogFileName</CODE> - 
<DT><B>Throws:</B>
<DD><CODE>java.io.FileNotFoundException</CODE>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE><A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></CODE></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="load(java.lang.String)"><!-- --></A><H3>
load</H3>
<PRE>
protected void <B>load</B>(java.lang.String&nbsp;recoverLogFileName)
             throws java.io.FileNotFoundException,
                    java.io.IOException,
                    <A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></PRE>
<DL>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.FileNotFoundException</CODE>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE><A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getSeedForUrl(java.lang.String)"><!-- --></A><H3>
getSeedForUrl</H3>
<PRE>
public java.lang.String <B>getSeedForUrl</B>(java.lang.String&nbsp;urlString)</PRE>
<DL>
<DD>Returns seed for urlString (null if seed not found).
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>urlString</CODE> - 
<DT><B>Returns:</B><DD>Seed.</DL>
</DD>
</DL>
<HR>

<A NAME="getSeedUrlToDiscoveredUrlsMap()"><!-- --></A><H3>
getSeedUrlToDiscoveredUrlsMap</H3>
<PRE>
public java.util.Map <B>getSeedUrlToDiscoveredUrlsMap</B>()</PRE>
<DL>
<DD><DL>

<DT><B>Returns:</B><DD>Returns the seedUrlToDiscoveredUrlsMap.</DL>
</DD>
</DL>
<HR>

<A NAME="getSuccessfullyCrawledUrls()"><!-- --></A><H3>
getSuccessfullyCrawledUrls</H3>
<PRE>
public java.util.Set <B>getSuccessfullyCrawledUrls</B>()</PRE>
<DL>
<DD><DL>

<DT><B>Returns:</B><DD>Returns the successfullyCrawledUrls.</DL>
</DD>
</DL>
<HR>

<A NAME="getLogger()"><!-- --></A><H3>
getLogger</H3>
<PRE>
public static java.util.logging.Logger <B>getLogger</B>()</PRE>
<DL>
<DD><DL>

<DT><B>Returns:</B><DD>Returns the logger.</DL>
</DD>
</DL>
<HR>

<A NAME="getIteratorOfURLsSuccessfullyCrawledFromSeedUrl(java.lang.String)"><!-- --></A><H3>
getIteratorOfURLsSuccessfullyCrawledFromSeedUrl</H3>
<PRE>
public java.util.Iterator <B>getIteratorOfURLsSuccessfullyCrawledFromSeedUrl</B>(java.lang.String&nbsp;seedUrlString)
                                                                   throws <A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></PRE>
<DL>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util">SeedUrlNotFoundException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getSeedCollection()"><!-- --></A><H3>
getSeedCollection</H3>
<PRE>
public java.util.Collection <B>getSeedCollection</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="main(java.lang.String[])"><!-- --></A><H3>
main</H3>
<PRE>
public static void <B>main</B>(java.lang.String[]&nbsp;args)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
</DL>
<!-- ========= END OF CLASS DATA ========= -->
<HR>


<!-- ======= START OF BOTTOM NAVBAR ====== -->
<A NAME="navbar_bottom"><!-- --></A>
<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
<TR>
<TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
<A NAME="navbar_bottom_firstrow"><!-- --></A>
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
  <TR ALIGN="center" VALIGN="top">
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="class-use/RecoveryLogMapper.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
  </TR>
</TABLE>
</TD>
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
</EM>
</TD>
</TR>

<TR>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
&nbsp;<A HREF="../../../../org/archive/crawler/util/NoopUriUniqFilter.html" title="class in org.archive.crawler.util"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../../../org/archive/crawler/util/SeedUrlNotFoundException.html" title="class in org.archive.crawler.util"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../../index.html?org/archive/crawler/util/RecoveryLogMapper.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="RecoveryLogMapper.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
&nbsp;<SCRIPT type="text/javascript">
  <!--
  if(window==top) {
    document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>');
  }
  //-->
</SCRIPT>
<NOSCRIPT>
  <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>
</NOSCRIPT>


</FONT></TD>
</TR>
<TR>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
</TR>
</TABLE>
<A NAME="skip-navbar_bottom"></A>
<!-- ======== END OF BOTTOM NAVBAR ======= -->

<HR>
Copyright &copy; 2003-2006 Internet Archive. All Rights Reserved.
</BODY>
</HTML>