pdfparser.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

</DL>
<HR>

<A NAME="encounteredReferences"><!-- --></A><H3>
encounteredReferences</H3>
<PRE>
java.util.ArrayList <B>encounteredReferences</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="documentReader"><!-- --></A><H3>
documentReader</H3>
<PRE>
com.lowagie.text.pdf.PdfReader <B>documentReader</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="document"><!-- --></A><H3>
document</H3>
<PRE>
byte[] <B>document</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="catalog"><!-- --></A><H3>
catalog</H3>
<PRE>
com.lowagie.text.pdf.PdfDictionary <B>catalog</B></PRE>
<DL>
<DL>
</DL>
</DL>

<!-- ========= 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="PDFParser(java.lang.String)"><!-- --></A><H3>
PDFParser</H3>
<PRE>
public <B>PDFParser</B>(java.lang.String&nbsp;doc)
          throws java.io.IOException</PRE>
<DL>
<DL>

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

<A NAME="PDFParser(byte[])"><!-- --></A><H3>
PDFParser</H3>
<PRE>
public <B>PDFParser</B>(byte[]&nbsp;doc)
          throws java.io.IOException</PRE>
<DL>
<DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</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="resetState()"><!-- --></A><H3>
resetState</H3>
<PRE>
protected void <B>resetState</B>()</PRE>
<DL>
<DD>Reinitialize the object as though a new one were created.
<P>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="resetState(byte[])"><!-- --></A><H3>
resetState</H3>
<PRE>
public void <B>resetState</B>(byte[]&nbsp;doc)
                throws java.io.IOException</PRE>
<DL>
<DD>Reset the object and initialize it with a new byte array (the document).
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>doc</CODE> - 
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="resetState(java.lang.String)"><!-- --></A><H3>
resetState</H3>
<PRE>
public void <B>resetState</B>(java.lang.String&nbsp;doc)
                throws java.io.IOException</PRE>
<DL>
<DD>Reinitialize the object as though a new one were created, complete
 with a valid pointer to a document that can be read
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>doc</CODE> - 
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getInFromFile(java.lang.String)"><!-- --></A><H3>
getInFromFile</H3>
<PRE>
protected void <B>getInFromFile</B>(java.lang.String&nbsp;doc)
                      throws java.io.IOException</PRE>
<DL>
<DD>Read a file named 'doc' and store its' bytes for later processing.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>doc</CODE> - 
<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="haveSeen(int, int)"><!-- --></A><H3>
haveSeen</H3>
<PRE>
protected boolean <B>haveSeen</B>(int&nbsp;generation,
                           int&nbsp;id)</PRE>
<DL>
<DD>Indicates, based on a PDFObject's generation/id pair whether
 the parser has already encountered this object (or a reference to it)
 so we don't infinitely loop on circuits within the PDF.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>generation</CODE> - <DD><CODE>id</CODE> - 
<DT><B>Returns:</B><DD>True if already seen.</DL>
</DD>
</DL>
<HR>

<A NAME="markAsSeen(int, int)"><!-- --></A><H3>
markAsSeen</H3>
<PRE>
protected void <B>markAsSeen</B>(int&nbsp;generation,
                          int&nbsp;id)</PRE>
<DL>
<DD>Note that an object (id/generation pair) has been seen by this parser
 so that it can be handled differently when it is encountered again.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>generation</CODE> - <DD><CODE>id</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="getURIs()"><!-- --></A><H3>
getURIs</H3>
<PRE>
public java.util.ArrayList <B>getURIs</B>()</PRE>
<DL>
<DD>Get a list of URIs retrieved from the Pdf during the
 extractURIs operation.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>A list of URIs retrieved from the Pdf during the
 extractURIs operation.</DL>
</DD>
</DL>
<HR>

<A NAME="initialize()"><!-- --></A><H3>
initialize</H3>
<PRE>
protected void <B>initialize</B>()
                   throws java.io.IOException</PRE>
<DL>
<DD>Initialize opens the document for reading.  This is done implicitly
 by the constuctor.  This should only need to be called directly following
 a reset.
<P>
<DD><DL>

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

<A NAME="extractURIs()"><!-- --></A><H3>
extractURIs</H3>
<PRE>
public java.util.ArrayList <B>extractURIs</B>()</PRE>
<DL>
<DD>Extract URIs from all objects found in a Pdf document's catalog.
 Returns an array list representing all URIs found in the document catalog tree.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>URIs from all objects found in a Pdf document's catalog.</DL>
</DD>
</DL>
<HR>

<A NAME="extractURIs(com.lowagie.text.pdf.PdfObject)"><!-- --></A><H3>
extractURIs</H3>
<PRE>
protected void <B>extractURIs</B>(com.lowagie.text.pdf.PdfObject&nbsp;entity)</PRE>
<DL>
<DD>Parse a PdfDictionary, looking for URIs recursively and adding
 them to foundURIs
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>entity</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;argv)</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/PDFParser.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/extractor/Link.html" title="class in org.archive.crawler.extractor"><B>PREV CLASS</B></A>&nbsp;
&nbsp;NEXT CLASS</FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../../index.html?org/archive/crawler/extractor/PDFParser.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="PDFParser.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;<A HREF="#field_summary">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;<A HREF="#field_detail">FIELD</A>&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>