Examples of org.apache.poi.hwpf.usermodel.Range

org.apache.poi.hwpf.usermodel.Range
This class is the central class of the HWPF object model. All properties that apply to a range of characters in a Word document extend this class. It is possible to insert text and/or properties at the beginning or end of a range. Ranges are only valid if there hasn't been an insert in a prior Range since the Range's creation. Once an element (text, paragraph, etc.) has been inserted into a Range, subsequent Ranges become unstable. @author Ryan Ackley

        int previous = range.getStartOffset();
        for ( Structure structure : structures )
        {
            if ( structure.start != previous )
            {
                Range subrange = new Range( previous, structure.start, range )
                {
                    @Override
                    public String toString()
                    {
                        return "BetweenStructuresSubrange " + super.toString();
                    }
                };
                processCharacters( wordDocument, currentTableLevel, subrange,
                        block );
            }


            if ( structure.structure instanceof Bookmark )
            {
                // other bookmarks with same boundaries
                List<Bookmark> bookmarks = new LinkedList<Bookmark>();
                for ( Bookmark bookmark : ( (HWPFDocument) wordDocument )
                        .getBookmarks()
                        .getBookmarksStartedBetween( structure.start,
                                structure.start + 1 ).values().iterator()
                        .next() )
                {
                    if ( bookmark.getStart() == structure.start
                            && bookmark.getEnd() == structure.end )
                    {
                        bookmarks.add( bookmark );
                    }
                }


                bookmarkStack.addAll( bookmarks );
                try
                {
                    int end = Math.min( range.getEndOffset(), structure.end );
                    Range subrange = new Range( structure.start, end, range )
                    {
                        @Override
                        public String toString()
                        {
                            return "BookmarksSubrange " + super.toString();
                        }
                    };


                    processBookmarks( wordDocument, block, subrange,
                            currentTableLevel, bookmarks );
                }
                finally
                {
                    bookmarkStack.removeAll( bookmarks );
                }
            }
            else if ( structure.structure instanceof Field )
            {
                Field field = (Field) structure.structure;
                processField( (HWPFDocument) wordDocument, range,
                        currentTableLevel, field, block );
            }
            else if ( structure.structure instanceof DeadFieldBoundaries )
            {
                DeadFieldBoundaries boundaries = (DeadFieldBoundaries) structure.structure;
                processDeadField( wordDocument, block, range,
                        currentTableLevel, boundaries.beginMark,
                        boundaries.separatorMark, boundaries.endMark );
            }
            else
            {
                throw new UnsupportedOperationException( "NYI: "
                        + structure.structure.getClass() );
            }


            previous = Math.min( range.getEndOffset(), structure.end );
        }


        if ( previous != range.getStartOffset() )
        {
            if ( previous > range.getEndOffset() )
            {
                logger.log( POILogger.WARN, "Latest structure in ", range,
                        " ended at #" + previous, " after range boundaries [",
                        range.getStartOffset() + "; " + range.getEndOffset(),
                        ")" );
                return true;
            }


            if ( previous < range.getEndOffset() )
            {
                Range subrange = new Range( previous, range.getEndOffset(),
                        range )
                {
                    @Override
                    public String toString()
                    {

View Full Code Here

            Element currentBlock, Range range, int currentTableLevel,
            int beginMark, int separatorMark, int endMark )
    {
        if ( beginMark + 1 < separatorMark && separatorMark + 1 < endMark )
        {
            Range formulaRange = new Range( range.getCharacterRun(
                    beginMark + 1 ).getStartOffset(), range.getCharacterRun(
                    separatorMark - 1 ).getEndOffset(), range )
            {
                @Override
                public String toString()
                {
                    return "Dead field formula subrange: " + super.toString();
                }
            };
            Range valueRange = new Range( range.getCharacterRun(
                    separatorMark + 1 ).getStartOffset(), range
                    .getCharacterRun( endMark - 1 ).getEndOffset(), range )
            {
                @Override
                public String toString()
                {
                    return "Dead field value subrange: " + super.toString();
                }
            };
            String formula = formulaRange.text();
            final Matcher matcher = PATTERN_HYPERLINK_LOCAL.matcher( formula );
            if ( matcher.matches() )
            {
                String localref = matcher.group( 1 );
                processPageref( wordDocument, currentBlock, valueRange,
                        currentTableLevel, localref );
                return;
            }
        }


        StringBuilder debug = new StringBuilder( "Unsupported field type: \n" );
        for ( int i = beginMark; i <= endMark; i++ )
        {
            debug.append( "\t" );
            debug.append( range.getCharacterRun( i ) );
            debug.append( "\n" );
        }
        logger.log( POILogger.WARN, debug );


        Range deadFieldValueSubrage = new Range( range.getCharacterRun(
                separatorMark ).getStartOffset() + 1, range.getCharacterRun(
                endMark ).getStartOffset(), range )
        {
            @Override
            public String toString()

View Full Code Here

            logger.log( POILogger.WARN,
                    "Unable to process document summary information: ", exc,
                    exc );
        }


        final Range docRange = wordDocument.getRange();


        if ( docRange.numSections() == 1 )
        {
            processSingleSection( wordDocument, docRange.getSection( 0 ) );
            afterProcess();
            return;
        }


        processDocumentPart( wordDocument, docRange );

View Full Code Here

    {
        switch ( field.getType() )
        {
        case 37: // page reference
        {
            final Range firstSubrange = field.firstSubrange( parentRange );
            if ( firstSubrange != null )
            {
                String formula = firstSubrange.text();
                Matcher matcher = PATTERN_PAGEREF.matcher( formula );
                if ( matcher.find() )
                {
                    String pageref = matcher.group( 1 );
                    processPageref( wordDocument, currentBlock,
                            field.secondSubrange( parentRange ),
                            currentTableLevel, pageref );
                    return;
                }
            }
            break;
        }
        case 58: // Embedded Object
        {
            if ( !field.hasSeparator() )
            {
                logger.log( POILogger.WARN, parentRange + " contains " + field
                        + " with 'Embedded Object' but without separator mark" );
                return;
            }


            CharacterRun separator = field
                    .getMarkSeparatorCharacterRun( parentRange );


            if ( separator.isOle2() )
            {
                // the only supported so far
                boolean processed = processOle2( wordDocument, separator,
                        currentBlock );


                // if we didn't output OLE - output field value
                if ( !processed )
                {
                    processCharacters( wordDocument, currentTableLevel,
                            field.secondSubrange( parentRange ), currentBlock );
                }


                return;
            }


            break;
        }
        case 88: // hyperlink
        {
            final Range firstSubrange = field.firstSubrange( parentRange );
            if ( firstSubrange != null )
            {
                String formula = firstSubrange.text();
                Matcher matcher = PATTERN_HYPERLINK_EXTERNAL.matcher( formula );
                if ( matcher.matches() )
                {
                    String hyperlink = matcher.group( 1 );
                    processHyperlink( wordDocument, currentBlock,
                            field.secondSubrange( parentRange ),
                            currentTableLevel, hyperlink );
                    return;
                }
                matcher.usePattern( PATTERN_HYPERLINK_LOCAL );
                if ( matcher.matches() )
                {
                    String hyperlink = matcher.group( 1 );
                    Range textRange = null;
                    String text = matcher.group( 2 );
                    if ( AbstractWordUtils.isNotEmpty( text ) )
                    {
                        textRange = new Range( firstSubrange.getStartOffset()
                                + matcher.start( 2 ),
                                firstSubrange.getStartOffset()
                                        + matcher.end( 2 ), firstSubrange )
                        {
                            @Override

View Full Code Here

            int noteIndex = footnotes
                    .getNoteIndexByAnchorPosition( characterRun
                            .getStartOffset() );
            if ( noteIndex != -1 )
            {
                Range footnoteRange = doc.getFootnoteRange();
                int rangeStartOffset = footnoteRange.getStartOffset();
                int noteTextStartOffset = footnotes
                        .getNoteTextStartOffset( noteIndex );
                int noteTextEndOffset = footnotes
                        .getNoteTextEndOffset( noteIndex );


                Range noteTextRange = new Range( rangeStartOffset
                        + noteTextStartOffset, rangeStartOffset
                        + noteTextEndOffset, doc );


                processFootnoteAutonumbered( doc, noteIndex, block,
                        noteTextRange );
                return;
            }
        }
        {
            Notes endnotes = doc.getEndnotes();
            int noteIndex = endnotes.getNoteIndexByAnchorPosition( characterRun
                    .getStartOffset() );
            if ( noteIndex != -1 )
            {
                Range endnoteRange = doc.getEndnoteRange();
                int rangeStartOffset = endnoteRange.getStartOffset();
                int noteTextStartOffset = endnotes
                        .getNoteTextStartOffset( noteIndex );
                int noteTextEndOffset = endnotes
                        .getNoteTextEndOffset( noteIndex );


                Range noteTextRange = new Range( rangeStartOffset
                        + noteTextStartOffset, rangeStartOffset
                        + noteTextEndOffset, doc );


                processEndnoteAutonumbered( doc, noteIndex, block,
                        noteTextRange );

View Full Code Here

                }
            }


            if ( true )
            {
                String text = new Range( chpx.getStart(), chpx.getEnd(),
                        _doc.getOverallRange() )
                {
                    public String toString()
                    {
                        return "CHPX range (" + super.toString() + ")";

View Full Code Here

        }
    }


    public void dumpParagraphsDom( boolean withText )
    {
        Range range = _doc.getOverallRange();
        for ( int p = 0; p < range.numParagraphs(); p++ )
        {
            Paragraph paragraph = range.getParagraph( p );
            System.out.println( p + ":\t" + paragraph.toString() );


            if ( withText )
                System.out.println( paragraph.text() );
        }

View Full Code Here

   * @return a list of Picture objects found in current document
   */
  public List<Picture> getAllPictures() {
    ArrayList<Picture> pictures = new ArrayList<Picture>();


    Range range = _document.getOverallRange();
    for (int i = 0; i < range.numCharacterRuns(); i++) {
      CharacterRun run = range.getCharacterRun(i);


        if (run==null) {
            continue;
        }

View Full Code Here

  public String[] getParagraphText() {
      String[] ret;


      // Extract using the model code
      try {
          Range r = doc.getRange();


          ret = WordExtractor.getParagraphText(r);
      } catch (Exception e) {
            // Something's up with turning the text pieces into paragraphs
            // Fall back to ripping out the text pieces

View Full Code Here

        //  placed or referenced from an anchor
        PicturesTable pictureTable = document.getPicturesTable();
        PicturesSource pictures = new PicturesSource(document);
        
        // Do the main paragraph text
        Range r = document.getRange();
        for(int i=0; i<r.numParagraphs(); i++) {
           Paragraph p = r.getParagraph(i);
           i += handleParagraph(p, 0, r, document, pictures, pictureTable, xhtml);
        }


        // Do everything else
        for (String paragraph : wordExtractor.getFootnoteText()) {

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.poi.hwpf.usermodel.Range

org.apache.poi.hslf.examples.DataExtraction

org.apache.poi.hwpf.converter.AbstractWordConverter

org.apache.poi.hwpf.converter.AbstractWordUtilsTest

org.apache.poi.hwpf.dev.HWPFLister

org.apache.poi.hwpf.extractor.TestDifferentRoutes

org.apache.poi.hwpf.extractor.Word6Extractor

org.apache.poi.hwpf.extractor.WordExtractor

org.apache.poi.hwpf.HWPFDocument

org.apache.poi.hwpf.HWPFOldDocument

org.apache.poi.hwpf.model.CHPX

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.