Examples of org.apache.poi.hwpf.model.TextPiece

org.apache.poi.hwpf.model.TextPiece
Lightweight representation of a text piece. @author Ryan Ackley

    Iterator<TextPiece> textIt = textPieces.iterator();


    int length = 0;
    while(textIt.hasNext())
    {
      TextPiece tp = textIt.next();
      length += tp.characterLength();
    }
    return length;
  }

View Full Code Here

  public void testExtractFromTextPieces() throws Exception {
    StringBuffer textBuf = new StringBuffer();


    Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
    while (textPieces.hasNext()) {
      TextPiece piece = (TextPiece) textPieces.next();


      String encoding = "Cp1252";
      if (piece.isUnicode()) {
        encoding = "UTF-16LE";
      }
      String text = new String(piece.getRawBytes(), encoding);
      textBuf.append(text);
    }


    StringBuffer exp = new StringBuffer();
    for (int i = 0; i < p_text.length; i++) {

View Full Code Here

        }
        if ( !preserveTextTable )
        {
            _cft = new ComplexFileTable();
            _tpt = _cft.getTextPieceTable();
            final TextPiece textPiece = new SinglentonTextPiece( _text );
            _tpt.add( textPiece );
            _text = textPiece.getStringBuilder();
        }


        // Read FSPA and Escher information
        // _fspa = new FSPATable(_tableStream, _fib.getFcPlcspaMom(),
        // _fib.getLcbPlcspaMom(), getTextTable().getTextPieces());

View Full Code Here

            // Generate a single Text Piece Table, with a single Text Piece
            //  which covers all the (8 bit only) text in the file
            tpt = new TextPieceTable();
            byte[] textData = new byte[_fib.getFibBase().getFcMac()-_fib.getFibBase().getFcMin()];
            System.arraycopy(_mainStream, _fib.getFibBase().getFcMin(), textData, 0, textData.length);
            TextPiece tp = new TextPiece(
                    0, textData.length, textData, pd
            );
            tpt.add(tp);
            
            text.append(tp.getStringBuilder());
        }
        
        _text = tpt.getText();


        // Now we can fetch the character and paragraph properties

View Full Code Here

  public boolean usesUnicode() {


    initText();


    for (int i = _textStart; i < _textEnd; i++) {
      TextPiece piece = _text.get(i);
      if (piece.isUnicode())
        return true;
    }


    return false;
  }

View Full Code Here

    initText();


    StringBuffer sb = new StringBuffer();


    for (int x = _textStart; x < _textEnd; x++) {
      TextPiece piece = _text.get(x);


      // Figure out where in this piece the text
      // we're after lives
      int rStart = 0;
      int rEnd = piece.characterLength();
      if (_start > piece.getStart()) {
        rStart = _start - piece.getStart();
      }
      if (_end < piece.getEnd()) {
        rEnd -= (piece.getEnd() - _end);
      }


      // Luckily TextPieces work in characters, so we don't
      // need to worry about unicode here
      sb.append(piece.substring(rStart, rEnd));
    }
    return sb.toString();
  }

View Full Code Here

  public CharacterRun insertBefore(String text)
  // throws UnsupportedEncodingException
  {
    initAll();


    TextPiece tp = _text.get(_textStart);
    StringBuffer sb = tp.getStringBuffer();


    // Since this is the first item in our list, it is safe to assume that
    // _start >= tp.getStart()
    int insertIndex = _start - tp.getStart();
    sb.insert(insertIndex, text);


    int adjustedLength = _doc.getTextTable().adjustForInsert(_textStart, text.length());
    _doc.getCharacterTable().adjustForInsert(_charStart, adjustedLength);
    _doc.getParagraphTable().adjustForInsert(_parStart, adjustedLength);

View Full Code Here

   */
  public CharacterRun insertAfter(String text) {
    initAll();


    int listIndex = _textEnd - 1;
    TextPiece tp = _text.get(listIndex);
    StringBuffer sb = tp.getStringBuffer();


    int insertIndex = _end - tp.getStart();


    if (tp.getStringBuffer().charAt(_end - 1) == '\r' && text.charAt(0) != '\u0007') {
      insertIndex--;
    }
    sb.insert(insertIndex, text);
    int adjustedLength = _doc.getTextTable().adjustForInsert(listIndex, text.length());
    _doc.getCharacterTable().adjustForInsert(_charEnd - 1, adjustedLength);

View Full Code Here

      // System.err.println("Section " + x + " is now " + sepx.getStart()
      // + " -> " + sepx.getEnd());
    }


    for (int x = _textStart; x < numTextPieces; x++) {
      TextPiece piece = _text.get(x);
      piece.adjustForDelete(_start, _end - _start);
    }


    // update the FIB.CCPText + friends field
    adjustFIB(-(_end - _start));
  }

View Full Code Here

            // Generate a single Text Piece Table, with a single Text Piece
            //  which covers all the (8 bit only) text in the file
            tpt = new TextPieceTable();
            byte[] textData = new byte[_fib.getFcMac()-_fib.getFcMin()];
            System.arraycopy(_mainStream, _fib.getFcMin(), textData, 0, textData.length);
            TextPiece tp = new TextPiece(
                    0, textData.length, textData, pd, 0
            );
            tpt.add(tp);
            
            text.append(tp.getStringBuffer());
        }
        
        // Now we can fetch the character and paragraph properties
        _cbt = new OldCHPBinTable(
                _mainStream, chpTableOffset, chpTableSize,

View Full Code Here

0 1 2 3 4 5 6 7 8

TOP

Related Classes of org.apache.poi.hwpf.model.TextPiece

org.apache.nutch.parse.msword.WordExtractor

org.apache.poi.hwpf.extractor.TestDifferentRoutes

org.apache.poi.hwpf.extractor.WordExtractor

org.apache.poi.hwpf.HWPFDocument

org.apache.poi.hwpf.HWPFOldDocument

org.apache.poi.hwpf.usermodel.Range

org.apache.tika.parser.microsoft.WordParser

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.