📄 warc2arc.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><!--NewPage--><HTML><HEAD><!-- Generated by javadoc (build 1.5.0_06) on Wed Sep 27 16:03:13 PDT 2006 --><TITLE>Warc2Arc (Heritrix 1.10.1)</TITLE><META NAME="keywords" CONTENT="org.archive.io.Warc2Arc class"><LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style"><SCRIPT type="text/javascript">function windowTitle(){ parent.document.title="Warc2Arc (Heritrix 1.10.1)";}</SCRIPT><NOSCRIPT></NOSCRIPT></HEAD><BODY BGCOLOR="white" onload="windowTitle();"><!-- ========= START OF TOP NAVBAR ======= --><A NAME="navbar_top"><!-- --></A><A HREF="#skip-navbar_top" 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_top_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> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/Warc2Arc.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../org/archive/io/UTF8Bytes.html" title="interface in org.archive.io"><B>PREV CLASS</B></A> <A HREF="../../../org/archive/io/WriterPool.html" title="class in org.archive.io"><B>NEXT CLASS</B></A></FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../index.html?org/archive/io/Warc2Arc.html" target="_top"><B>FRAMES</B></A> <A HREF="Warc2Arc.html" target="_top"><B>NO FRAMES</B></A> <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: NESTED | FIELD | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: FIELD | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_top"></A><!-- ========= END OF TOP NAVBAR ========= --><HR><!-- ======== START OF CLASS DATA ======== --><H2><FONT SIZE="-1">org.archive.io</FONT><BR>Class Warc2Arc</H2><PRE>java.lang.Object <IMG SRC="../../../resources/inherit.gif" ALT="extended by "><B>org.archive.io.Warc2Arc</B></PRE><HR><DL><DT><PRE>public class <B>Warc2Arc</B><DT>extends java.lang.Object</DL></PRE><P>Convert WARCs to (sortof) ARCs. WARCs can be 1Gig in size, that is, 10x default ARC size. Script takes directory as output and will write multiple ARCs for a single large WARC. Only writes resource records of type <code>text/dns</code> or <code>application/http; msgtype=response</code>. All others -- metadata, request -- are skipped.<P><P><DL><DT><B>Version:</B></DT> <DD>$Date: 2006/09/02 02:58:28 $ $Revision: 1.3 $</DD><DT><B>Author:</B></DT> <DD>stack</DD></DL><HR><P><!-- ======== CONSTRUCTOR SUMMARY ======== --><A NAME="constructor_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Constructor Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#Warc2Arc()">Warc2Arc</A></B>()</CODE><BR> </TD></TR></TABLE> <!-- ========== METHOD SUMMARY =========== --><A NAME="method_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Method Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#isARCType(java.lang.String)">isARCType</A></B>(java.lang.String mimetype)</CODE><BR> </TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#main(java.lang.String[])">main</A></B>(java.lang.String[] args)</CODE><BR> Command-line interface to Arc2Warc.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>(package private) static java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#parseRevision(java.lang.String)">parseRevision</A></B>(java.lang.String version)</CODE><BR> </TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#transform(java.io.File, java.io.File, java.lang.String, java.lang.String, boolean)">transform</A></B>(java.io.File warc, java.io.File dir, java.lang.String prefix, java.lang.String suffix, boolean force)</CODE><BR> </TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>protected void</CODE></FONT></TD><TD><CODE><B><A HREF="../../../org/archive/io/Warc2Arc.html#transform(org.archive.io.warc.WARCReader, org.archive.io.arc.ARCWriter)">transform</A></B>(<A HREF="../../../org/archive/io/warc/WARCReader.html" title="class in org.archive.io.warc">WARCReader</A> reader, <A HREF="../../../org/archive/io/arc/ARCWriter.html" title="class in org.archive.io.arc">ARCWriter</A> writer)</CODE><BR> </TD></TR></TABLE> <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> <P><!-- ========= CONSTRUCTOR DETAIL ======== --><A NAME="constructor_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>Constructor Detail</B></FONT></TH></TR></TABLE><A NAME="Warc2Arc()"><!-- --></A><H3>Warc2Arc</H3><PRE>public <B>Warc2Arc</B>()</PRE><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="parseRevision(java.lang.String)"><!-- --></A><H3>parseRevision</H3><PRE>static java.lang.String <B>parseRevision</B>(java.lang.String version)</PRE><DL><DD><DL></DL></DD></DL><HR><A NAME="transform(java.io.File, java.io.File, java.lang.String, java.lang.String, boolean)"><!-- --></A><H3>transform</H3><PRE>public void <B>transform</B>(java.io.File warc, java.io.File dir, java.lang.String prefix, java.lang.String suffix, boolean force) throws java.io.IOException, java.text.ParseException</PRE><DL><DD><DL><DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE><DD><CODE>java.text.ParseException</CODE></DL></DD></DL><HR><A NAME="transform(org.archive.io.warc.WARCReader, org.archive.io.arc.ARCWriter)"><!-- --></A><H3>transform</H3><PRE>protected void <B>transform</B>(<A HREF="../../../org/archive/io/warc/WARCReader.html" title="class in org.archive.io.warc">WARCReader</A> reader, <A HREF="../../../org/archive/io/arc/ARCWriter.html" title="class in org.archive.io.arc">ARCWriter</A> writer) throws java.io.IOException, java.text.ParseException</PRE><DL><DD><DL><DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE><DD><CODE>java.text.ParseException</CODE></DL></DD></DL><HR><A NAME="isARCType(java.lang.String)"><!-- --></A><H3>isARCType</H3><PRE>protected boolean <B>isARCType</B>(java.lang.String mimetype)</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[] args) throws org.apache.commons.cli.ParseException, java.io.IOException, java.text.ParseException</PRE><DL><DD>Command-line interface to Arc2Warc.<P><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> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/Warc2Arc.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../org/archive/io/UTF8Bytes.html" title="interface in org.archive.io"><B>PREV CLASS</B></A> <A HREF="../../../org/archive/io/WriterPool.html" title="class in org.archive.io"><B>NEXT CLASS</B></A></FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../index.html?org/archive/io/Warc2Arc.html" target="_top"><B>FRAMES</B></A> <A HREF="Warc2Arc.html" target="_top"><B>NO FRAMES</B></A> <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: NESTED | FIELD | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: FIELD | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_bottom"></A><!-- ======== END OF BOTTOM NAVBAR ======= --><HR>Copyright © 2003-2006 Internet Archive. All Rights Reserved.</BODY></HTML>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -