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

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


    StringBuffer sb = new StringBuffer();


    for (int x = _textStart; x < _textEnd; x++)
    {
      TextPiece piece = (TextPiece)_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 String getTextFromPieces() {
      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";
        }
        try {
          String text = new String(piece.getRawBytes(), encoding);
          textBuf.append(text);
        } catch(UnsupportedEncodingException e) {
          throw new InternalError("Standard Encoding " + encoding + " not found, JVM broken");
        }
      }

View Full Code Here

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


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

View Full Code Here

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


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


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

View Full Code Here

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


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

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


    List textRuns = cbt.getTextRuns();
    Iterator runIt = textRuns.iterator();
    Iterator textIt = textPieces.iterator();


    TextPiece currentPiece = (TextPiece)textIt.next();
    int currentTextStart = currentPiece.getStart();
    int currentTextEnd = currentPiece.getEnd();


    WordTextBuffer finalTextBuf = new WordTextBuffer();


    // iterate through all text runs extract the text only if they haven't been
    // deleted
    while (runIt.hasNext())
    {
      CHPX chpx = (CHPX)runIt.next();
      boolean deleted = isDeleted(chpx.getGrpprl());
      if (deleted)
      {
        continue;
      }


      int runStart = chpx.getStart();
      int runEnd = chpx.getEnd();


      while (runStart >= currentTextEnd)
      {
        currentPiece = (TextPiece) textIt.next ();
        currentTextStart = currentPiece.getStart ();
        currentTextEnd = currentPiece.getEnd ();
      }


      if (runEnd < currentTextEnd)
      {
        String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
        finalTextBuf.append(str);
      }
      else if (runEnd > currentTextEnd)
      {
        while (runEnd > currentTextEnd)
        {
          String str = currentPiece.substring(runStart - currentTextStart,
                                   currentTextEnd - currentTextStart);
          finalTextBuf.append(str);
          if (textIt.hasNext())
          {
            currentPiece = (TextPiece) textIt.next ();
            currentTextStart = currentPiece.getStart ();
            runStart = currentTextStart;
            currentTextEnd = currentPiece.getEnd ();
          }
          else
          {
            return finalTextBuf.toString();
          }
        }
        String str = currentPiece.substring(0, runEnd - currentTextStart);
        finalTextBuf.append(str);
      }
      else
      {
        String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
        if (textIt.hasNext())
        {
          currentPiece = (TextPiece) textIt.next();
          currentTextStart = currentPiece.getStart();
          currentTextEnd = currentPiece.getEnd();
        }
        finalTextBuf.append(str);
      }
    }
    return finalTextBuf.toString();

View Full Code Here

  public String getTextFromPieces() {
      StringBuffer textBuf = new StringBuffer();
      
      Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
      while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();


        String encoding = "Cp1252";
        if (piece.usesUnicode()) {
          encoding = "UTF-16LE";
        }
        try {
          String text = new String(piece.getRawBytes(), encoding);
          textBuf.append(text);
        } catch(UnsupportedEncodingException e) {
          throw new InternalError("Standard Encoding " + encoding + " not found, JVM broken");
        }
      }

View Full Code Here


    StringBuffer sb = new StringBuffer();


    for (int x = _textStart; x < _textEnd; x++)
    {
      TextPiece piece = (TextPiece)_text.get(x);
      int start = _start > piece.getStart() ? _start - piece.getStart() : 0;
      int end = _end <= piece.getEnd() ? _end - piece.getStart() : piece.getEnd() - piece.getStart();


      if(piece.usesUnicode()) // convert the byte pointers to char pointers
      {
        start/=2;
        end/=2;
      }
      sb.append(piece.getStringBuffer().substring(start, end));
    }
    return sb.toString();
  }

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.