warcreader.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

public void <B>dump</B>(boolean&nbsp;compress)
          throws java.io.IOException,
                 java.text.ParseException</PRE>
<DL>
<DD><B>Description copied from class: <CODE><A HREF="../../../../org/archive/io/ArchiveReader.html#dump(boolean)">ArchiveReader</A></CODE></B></DD>
<DD>Dump this file on STDOUT
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/io/ArchiveReader.html#dump(boolean)">dump</A></CODE> in class <CODE><A HREF="../../../../org/archive/io/ArchiveReader.html" title="class in org.archive.io">ArchiveReader</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE>java.text.ParseException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getDotFileExtension()"><!-- --></A><H3>
getDotFileExtension</H3>
<PRE>
public java.lang.String <B>getDotFileExtension</B>()</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/io/ArchiveReader.html#getDotFileExtension()">getDotFileExtension</A></CODE> in class <CODE><A HREF="../../../../org/archive/io/ArchiveReader.html" title="class in org.archive.io">ArchiveReader</A></CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="getFileExtension()"><!-- --></A><H3>
getFileExtension</H3>
<PRE>
public java.lang.String <B>getFileExtension</B>()</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/io/ArchiveReader.html#getFileExtension()">getFileExtension</A></CODE> in class <CODE><A HREF="../../../../org/archive/io/ArchiveReader.html" title="class in org.archive.io">ArchiveReader</A></CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="output(org.archive.io.warc.WARCReader, java.lang.String)"><!-- --></A><H3>
output</H3>
<PRE>
protected static void <B>output</B>(<A HREF="../../../../org/archive/io/warc/WARCReader.html" title="class in org.archive.io.warc">WARCReader</A>&nbsp;reader,
                             java.lang.String&nbsp;format)
                      throws java.io.IOException,
                             java.text.ParseException</PRE>
<DL>
<DD>Write out the arcfile.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>reader</CODE> - <DD><CODE>format</CODE> - Format to use outputting.
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE>java.text.ParseException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="outputRecord(org.archive.io.warc.WARCReader, java.lang.String)"><!-- --></A><H3>
outputRecord</H3>
<PRE>
protected static void <B>outputRecord</B>(<A HREF="../../../../org/archive/io/warc/WARCReader.html" title="class in org.archive.io.warc">WARCReader</A>&nbsp;r,
                                   java.lang.String&nbsp;format)
                            throws java.io.IOException</PRE>
<DL>
<DD>Output passed record using passed format specifier.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>r</CODE> - ARCReader instance to output.<DD><CODE>format</CODE> - What format to use outputting.
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="createCDXIndexFile(java.lang.String)"><!-- --></A><H3>
createCDXIndexFile</H3>
<PRE>
public static void <B>createCDXIndexFile</B>(java.lang.String&nbsp;urlOrPath)
                               throws java.io.IOException,
                                      java.text.ParseException</PRE>
<DL>
<DD>Generate a CDX index file for an ARC file.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>urlOrPath</CODE> - The ARC file to generate a CDX index for
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE>
<DD><CODE>java.text.ParseException</CODE></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)
                 throws org.apache.commons.cli.ParseException,
                        java.io.IOException,
                        java.text.ParseException</PRE>
<DL>
<DD>Command-line interface to WARCReader.

 Here is the command-line interface:
 <pre>
 usage: java org.archive.io.arc.WARCReader [--offset=#] ARCFILE
  -h,--help      Prints this message and exits.
  -o,--offset    Outputs record at this offset into arc file.</pre>

 <p>Outputs using a pseudo-CDX format as described here:
 <a href="http://www.archive.org/web/researcher/cdx_legend.php">CDX
 Legent</a> and here
 <a href="http://www.archive.org/web/researcher/example_cdx.php">Example</a>.
 Legend used in below is: 'CDX b e a m s c V (or v if uncompressed) n g'.
 Hash is hard-coded straight SHA-1 hash of content.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>args</CODE> - Command-line arguments.
<DT><B>Throws:</B>
<DD><CODE>org.apache.commons.cli.ParseException</CODE> - Failed parse of the command line.
<DD><CODE>java.io.IOException</CODE>
<DD><CODE>java.text.ParseException</CODE></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/WARCReader.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/io/warc/WARCConstants.html" title="interface in org.archive.io.warc"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../../../org/archive/io/warc/WARCReaderFactory.html" title="class in org.archive.io.warc"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../../index.html?org/archive/io/warc/WARCReader.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="WARCReader.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;<A HREF="#nested_classes_inherited_from_class_org.archive.io.ArchiveReader">NESTED</A>&nbsp;|&nbsp;<A HREF="#fields_inherited_from_class_org.archive.io.ArchiveReader">FIELD</A>&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>