public WordDocument(String fileName) throws IOException 
{
  	this(new FileInputStream(fileName));
}

Constructs a Word document from fileName. Parses the document and places all the important stuff into data structures.

Parameters:

fileName - The name of the file to read.

Throws:

IOException - if there is a problem while parsing the document.

 public WordDocument(InputStream inputStream) throws IOException 
{
        //do Ole stuff
        istream = inputStream;
        filesystem = new POIFSFileSystem(istream);
        //get important stuff from the Header block and parse all the
        //data structures
        readFIB();
        //get the SEPS for the main document text
        ArrayList sections = findProperties(_fcMin, _fcMin + _ccpText, _sectionTable.root);
        //iterate through sections, paragraphs, and character runs doing what
        //you will with the data.
        int size = sections.size();
        for(int x = 0; x <  size; x++)
        {
          SepxNode node = (SepxNode)sections.get(x);
          int start = node.getStart();
          int end = node.getEnd();
          SEP sep = (SEP)StyleSheet.uncompressProperty(node.getSepx(), new SEP(), _styleSheet);
          writeSection(Math.max(_fcMin, start), Math.min(_fcMin + _ccpText, end), sep, _text, _paragraphTable, _characterTable, _styleSheet);
        }
        //finish
        istream.close();
}

 public  void closeDoc() 
{
    _headerBuffer.append("< /fo:layout-master-set >");
    _bodyBuffer.append("< /fo:root >");
    //_headerBuffer.append();
    //test code
    try
    {
      OutputStreamWriter test = new OutputStreamWriter(new FileOutputStream(_outName), "8859_1");
      test.write(_headerBuffer.toString());
      test.write(_bodyBuffer.toString());
      test.flush();
      test.close();
    }
    catch(Throwable t)
    {
      t.printStackTrace();
    }
}

 public static  void main(String[] args) 
{
                           
      /*try
      {
        WordDocument file = new WordDocument(args[0], "r");
        Writer out = new BufferedWriter(new FileWriter(args[1]));
        file.writeAllText(out);
        out.flush();
        out.close();
      }
      catch(Throwable t)
      {
        t.printStackTrace();
      }*/
      try
      {
          _outName = args[1];
          WordDocument file = new WordDocument(args[0]);
          file.closeDoc();
      }
      catch(Exception e)
      {
          e.printStackTrace();
      }
      System.exit(0);
}

right now this function takes one parameter: a Word file, and outputs an XSL-FO document at c:\test.xml (this is hardcoded)

 public  void openDoc() 
{
    _headerBuffer.append("< ?xml version=\"1.0\" encoding=\"iso-8859-1\"? >\r\n");
    _headerBuffer.append("< fo:root xmlns:fo=\"http://www.w3.org/1999/XSL/Format\" >\r\n");
    _headerBuffer.append("< fo:layout-master-set >\r\n");
}

 public  void writeAllText(Writer out) throws IOException 
{
    int textStart = Utils.convertBytesToInt(_header, 0x18);
    int textEnd = Utils.convertBytesToInt(_header, 0x1c);
    ArrayList textPieces = findProperties(textStart, textEnd, _text.root);
    int size = textPieces.size();
    for(int x = 0; x <  size; x++)
    {
      TextPiece nextPiece = (TextPiece)textPieces.get(x);
      int start = nextPiece.getStart();
      int end = nextPiece.getEnd();
      boolean unicode = nextPiece.usesUnicode();
      int add = 1;
      if(unicode)
      {
        add = 2;
        char ch;
        for(int y = start; y <  end; y += add)
        {
	  ch = (char)Utils.convertBytesToShort(_header, y);
	  out.write(ch);
        }
      }
      else
      {
	String sText = new String(_header, start, end-start);
	out.write(sText);
      }
    }
}

Spits out the document text

 public  void writeSection(int start,
    int end,
    SEP sep,
    BTreeSet text,
    BTreeSet paragraphTable,
    BTreeSet characterTable,
    StyleSheet stylesheet) 
{
    HeaderFooter titleHeader = findSectionHdrFtr(HeaderFooter.HEADER_FIRST, _sectionCounter);
    HeaderFooter titleFooter = findSectionHdrFtr(HeaderFooter.FOOTER_FIRST, _sectionCounter);
    HeaderFooter oddHeader = findSectionHdrFtr(HeaderFooter.HEADER_ODD, _sectionCounter);
    HeaderFooter evenHeader = findSectionHdrFtr(HeaderFooter.HEADER_EVEN, _sectionCounter);
    HeaderFooter oddFooter = findSectionHdrFtr(HeaderFooter.FOOTER_ODD, _sectionCounter);
    HeaderFooter evenFooter = findSectionHdrFtr(HeaderFooter.FOOTER_EVEN, _sectionCounter);
    String titlePage = null;
    String evenPage = null;
    String oddPage = null;
    String regPage = null;
    String sequenceName = null;
    /*if(sep._fTitlePage)
    {
      titlePage = createPageMaster(sep, "first", _sectionCounter, createRegion("before", "title-header"), createRegion("after", "title-footer"));
      if(!titleHeader.isEmpty())
      {
        addStaticContent("title-header" + _sectionCounter, titleHeader);
      }
      if(!titleFooter.isEmpty())
      {
        addStaticContent("title-footer" + _sectionCounter, titleFooter);
      }
    }*/
    if(_docProps._fFacingPages)
    {
      if(sep._fTitlePage)
      {
        String before = createRegion(true, titleHeader, sep, "title-header" + _sectionCounter);
        String after = createRegion(false, titleFooter, sep, "title-footer" + _sectionCounter);
        titlePage = createPageMaster(sep, "first", _sectionCounter, before, after);
      }
      String before = createRegion(true, evenHeader, sep, "even-header" + _sectionCounter);
      String after = createRegion(false, evenFooter, sep, "even-footer" + _sectionCounter);
      evenPage = createPageMaster(sep, "even", _sectionCounter, before, after);
      before = createRegion(true, oddHeader, sep, "odd-header" + _sectionCounter);
      after = createRegion(false, oddFooter, sep, "odd-footer" + _sectionCounter);
      oddPage = createPageMaster(sep, "odd", _sectionCounter, before, after);
      sequenceName = createEvenOddPageSequence(titlePage, evenPage, oddPage, _sectionCounter);
      openPage(sequenceName, "reference");
      if(sep._fTitlePage)
      {
        if(!titleHeader.isEmpty())
        {
          addStaticContent("title-header" + _sectionCounter, titleHeader);
        }
        if(!titleFooter.isEmpty())
        {
          addStaticContent("title-footer" + _sectionCounter, titleFooter);
        }
      }
      //handle the headers and footers for odd and even pages
      if(!oddHeader.isEmpty())
      {
        addStaticContent("odd-header" + _sectionCounter, oddHeader);
      }
      if(!oddFooter.isEmpty())
      {
        addStaticContent("odd-footer" + _sectionCounter, oddFooter);
      }
      if(!evenHeader.isEmpty())
      {
        addStaticContent("even-header" + _sectionCounter, evenHeader);
      }
      if(!evenFooter.isEmpty())
      {
        addStaticContent("even-footer" + _sectionCounter, evenFooter);
      }
      openFlow();
      addBlockContent(start, end, text, paragraphTable, characterTable);
      closeFlow();
      closePage();
    }
    else
    {
      /*if(sep._fTitlePage)
      {
        String before = createRegion(true, titleHeader, sep);
        String after = createRegion(false, titleFooter, sep);
        titlePage = createPageMaster(sep, "first", _sectionCounter, before, after);
      }*/
      String before = createRegion(true, oddHeader, sep, null);
      String after = createRegion(false, oddFooter, sep, null);
      regPage = createPageMaster(sep, "page", _sectionCounter, before, after);
      if(sep._fTitlePage)
      {
        before = createRegion(true, titleHeader, sep, "title-header" + _sectionCounter);
        after = createRegion(false, titleFooter, sep, "title-footer" + _sectionCounter);
        titlePage = createPageMaster(sep, "first", _sectionCounter, before, after);
        sequenceName = createPageSequence(titlePage, regPage, _sectionCounter);
        openPage(sequenceName, "reference");
        if(!titleHeader.isEmpty())
        {
          addStaticContent("title-header" + _sectionCounter, titleHeader);
        }
        if(!titleFooter.isEmpty())
        {
          addStaticContent("title-footer" + _sectionCounter, titleFooter);
        }
      }
      else
      {
        openPage(regPage, "name");
      }
      if(!oddHeader.isEmpty())
      {
        addStaticContent("xsl-region-before", oddHeader);
      }
      if(!oddFooter.isEmpty())
      {
        addStaticContent("xsl-region-after", oddFooter);
      }
      openFlow();
      addBlockContent(start, end, text, paragraphTable, characterTable);
      closeFlow();
      closePage();
    }
    _sectionCounter++;
}