Example usage for org.apache.poi.hwpf.usermodel CharacterRun isBold

List of usage examples for org.apache.poi.hwpf.usermodel CharacterRun isBold

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.hwpf.usermodel.*
  5. CharacterRun
  6. isBold

Introduction

In this page you can find the example usage for org.apache.poi.hwpf.usermodel CharacterRun isBold.

Prototype

public boolean isBold()

Source Link

Usage

From source file:com.example.minireader.WordViewActivity.java

License:Apache License

/**html*/
public void writeParagraphContent(Paragraph paragraph) {
    Paragraph p = paragraph;//from   w  ww  .java2  s.  c om
    int pnumCharacterRuns = p.numCharacterRuns();

    for (int j = 0; j < pnumCharacterRuns; j++) {

        CharacterRun run = p.getCharacterRun(j);

        if (run.getPicOffset() == 0 || run.getPicOffset() >= 1000) {
            if (presentPicture < pictures.size()) {
                //
                writePicture();
            }
        } else {
            try {
                String text = run.text();
                if (text.length() >= 2 && pnumCharacterRuns < 2) {
                    //
                    output.write(text.getBytes());
                } else {
                    //
                    int size = run.getFontSize();
                    int color = run.getColor();
                    String fontSizeBegin = "<font size=\"" + decideSize(size) + "\">";
                    String fontColorBegin = "<font color=\"" + decideColor(color) + "\">";
                    String fontEnd = "</font>";
                    String boldBegin = "<b>";
                    String boldEnd = "</b>";
                    String islaBegin = "<i>";
                    String islaEnd = "</i>";

                    output.write(fontSizeBegin.getBytes());
                    output.write(fontColorBegin.getBytes());

                    if (run.isBold()) {
                        output.write(boldBegin.getBytes());
                    }
                    if (run.isItalic()) {
                        output.write(islaBegin.getBytes());
                    }

                    output.write(text.getBytes());

                    if (run.isBold()) {
                        output.write(boldEnd.getBytes());
                    }
                    if (run.isItalic()) {
                        output.write(islaEnd.getBytes());
                    }
                    output.write(fontEnd.getBytes());
                    output.write(fontEnd.getBytes());
                }
            } catch (Exception e) {
                System.out.println("Write File Exception");
            }
        }
    }
}

From source file:mj.ocraptor.extraction.tika.parser.microsoft.WordExtractor.java

License:Apache License

private void handleCharacterRun(CharacterRun cr, boolean skipStyling, XHTMLContentHandler xhtml)
        throws SAXException {
    // Skip trailing newlines
    if (!isRendered(cr) || cr.text().equals("\r"))
        return;/*from w w  w  .j  ava2  s .  com*/

    if (!skipStyling) {
        if (cr.isBold() != curBold) {
            // Enforce nesting -- must close s and i tags
            if (curStrikeThrough) {
                xhtml.endElement("s");
                curStrikeThrough = false;
            }
            if (curItalic) {
                xhtml.endElement("i");
                curItalic = false;
            }
            if (cr.isBold()) {
                xhtml.startElement("b");
            } else {
                xhtml.endElement("b");
            }
            curBold = cr.isBold();
        }

        if (cr.isItalic() != curItalic) {
            // Enforce nesting -- must close s tag
            if (curStrikeThrough) {
                xhtml.endElement("s");
                curStrikeThrough = false;
            }
            if (cr.isItalic()) {
                xhtml.startElement("i");
            } else {
                xhtml.endElement("i");
            }
            curItalic = cr.isItalic();
        }

        if (cr.isStrikeThrough() != curStrikeThrough) {
            if (cr.isStrikeThrough()) {
                xhtml.startElement("s");
            } else {
                xhtml.endElement("s");
            }
            curStrikeThrough = cr.isStrikeThrough();
        }
    }

    // Clean up the text
    String text = cr.text();
    text = text.replace('\r', '\n');
    if (text.endsWith("\u0007")) {
        // Strip the table cell end marker
        text = text.substring(0, text.length() - 1);
    }

    // Copied from POI's
    // org/apache/poi/hwpf/converter/AbstractWordConverter.processCharacters:

    // line tabulator as break line
    text = text.replace((char) 0x000b, '\n');

    // Non-breaking hyphens are returned as char 30
    text = text.replace((char) 30, UNICODECHAR_NONBREAKING_HYPHEN);

    // Non-required hyphens to zero-width space
    text = text.replace((char) 31, UNICODECHAR_ZERO_WIDTH_SPACE);

    // TODO: mj
    xhtml.characters(text);
}

From source file:org.apache.tika.parser.microsoft.WordExtractor.java

License:Apache License

private void handleCharacterRun(CharacterRun cr, boolean skipStyling, XHTMLContentHandler xhtml)
        throws SAXException {
    // Skip trailing newlines
    if (!isRendered(cr) || cr.text().equals("\r"))
        return;//from   ww w .java 2s . c o  m

    if (!skipStyling) {
        if (cr.isBold() != curBold) {
            // Enforce nesting -- must close s and i tags
            if (curStrikeThrough) {
                xhtml.endElement("s");
                curStrikeThrough = false;
            }
            if (curItalic) {
                xhtml.endElement("i");
                curItalic = false;
            }
            if (cr.isBold()) {
                xhtml.startElement("b");
            } else {
                xhtml.endElement("b");
            }
            curBold = cr.isBold();
        }

        if (cr.isItalic() != curItalic) {
            // Enforce nesting -- must close s tag
            if (curStrikeThrough) {
                xhtml.endElement("s");
                curStrikeThrough = false;
            }
            if (cr.isItalic()) {
                xhtml.startElement("i");
            } else {
                xhtml.endElement("i");
            }
            curItalic = cr.isItalic();
        }

        if (cr.isStrikeThrough() != curStrikeThrough) {
            if (cr.isStrikeThrough()) {
                xhtml.startElement("s");
            } else {
                xhtml.endElement("s");
            }
            curStrikeThrough = cr.isStrikeThrough();
        }
    }

    // Clean up the text
    String text = cr.text();
    text = text.replace('\r', '\n');
    if (text.endsWith("\u0007")) {
        // Strip the table cell end marker
        text = text.substring(0, text.length() - 1);
    }

    // Copied from POI's org/apache/poi/hwpf/converter/AbstractWordConverter.processCharacters:

    // Non-breaking hyphens are returned as char 30
    text = text.replace((char) 30, UNICODECHAR_NONBREAKING_HYPHEN);

    // Non-required hyphens to zero-width space
    text = text.replace((char) 31, UNICODECHAR_ZERO_WIDTH_SPACE);

    // Control characters as line break
    text = text.replaceAll("[\u0000-\u001f]", "\n");
    xhtml.characters(text);
}

From source file:org.docx4j.convert.in.Doc.java

License:Apache License

private static org.docx4j.wml.P handleP(WordprocessingMLPackage wordMLPackage, HWPFDocument doc, Paragraph p,
        org.apache.poi.hwpf.model.StyleSheet stylesheet, MainDocumentPart documentPart,
        org.docx4j.wml.ObjectFactory factory) {

    org.docx4j.wml.P wmlP = null;//from   ww  w.  j av  a 2 s.  c  o m

    if (p.getStyleIndex() > 0) {
        log.debug("Styled paragraph, with index: " + p.getStyleIndex());
        String styleName = stylesheet.getStyleDescription(p.getStyleIndex()).getName();

        log.debug(styleName);

        wmlP = documentPart.createStyledParagraphOfText(stripSpace(styleName), null);

    } else {
        wmlP = documentPart.createParagraphOfText(null);
    }

    // LineSpacingDescriptor lsd = p.getLineSpacing();
    // if (lsd==null || lsd.isEmpty()) {
    // // do nothing
    // } else {
    // PPr pPr = wmlP.getPPr();
    // if (pPr==null) {
    // pPr = Context.getWmlObjectFactory().createPPr();
    // wmlP.setPPr(pPr);
    // }
    // Spacing spacing =
    // Context.getWmlObjectFactory().createPPrBaseSpacing();
    // spacing.setLine(lsd._dyaLine); // not visible
    // spacing.setLineRule(STLineSpacingRule.AUTO);
    // pPr.setSpacing(spacing);
    // }

    for (int z = 0; z < p.numCharacterRuns(); z++) {
        // character run
        CharacterRun run = p.getCharacterRun(z);

        // No character styles defined in there??

        org.docx4j.wml.RPr rPr = null;

        if (run.isBold()) {

            // TODO - HIGH PRIORITY- handle other run properties
            // esp underline, font size
            if (rPr == null) {
                rPr = factory.createRPr();
            }

            org.docx4j.wml.BooleanDefaultTrue boldOn = factory.createBooleanDefaultTrue();
            boldOn.setVal(Boolean.TRUE);

            rPr.setB(boldOn);

        }

        //Process image
        if (doc instanceof HWPFDocument && ((HWPFDocument) doc).getPicturesTable().hasPicture(run)) {

            Picture picture = doc.getPicturesTable().extractPicture(run, true);
            Inline inline;
            try {
                BinaryPartAbstractImage imagePart = BinaryPartAbstractImage.createImagePart(wordMLPackage,
                        picture.getContent());

                long cx = UnitsOfMeasurement
                        .twipToEMU(Math.round((double) imagePart.getImageInfo().getSize().getWidthMpt()
                                * ((double) picture.getHorizontalScalingFactor() * 0.00001d)))
                        * 2L;
                long cy = UnitsOfMeasurement
                        .twipToEMU(Math.round((double) imagePart.getImageInfo().getSize().getHeightMpt()
                                * ((double) picture.getVerticalScalingFactor() * 0.00001d)))
                        * 2L;

                inline = imagePart.createImageInline(null, "", ID1++, ID2++, cx, cy, false);

                org.docx4j.wml.R imgrun = factory.createR();
                org.docx4j.wml.Drawing drawing = factory.createDrawing();
                imgrun.getContent().add(drawing);
                drawing.getAnchorOrInline().add(inline);
                wmlP.getContent().add(imgrun);
            } catch (Exception e1) {
                // TODO Auto-generated catch block
                e1.printStackTrace();
            }

        } else {
            // character run text
            String text = run.text();

            // show us the text
            log.debug("Processing: " + text);

            String cleansed = stripNonValidXMLCharacters(text);
            // Necessary to avoid org.xml.sax.SAXParseException: An invalid
            // XML character
            // (Unicode: 0xb) was found in the element content of the
            // document.
            // when trying to open the resulting docx.
            // ie JAXB happily writes (marshals) it, but doesn't want to
            // unmarshall.

            if (!text.equals(cleansed)) {
                log.warn("Cleansed..");
            }

            org.docx4j.wml.Text t = factory.createText();
            t.setValue(cleansed);

            org.docx4j.wml.R wmlRun = factory.createR();

            if (rPr != null) {
                wmlRun.setRPr(rPr);
            }
            wmlRun.getRunContent().add(t);
            wmlP.getParagraphContent().add(wmlRun);
        }
    }

    System.out.println(XmlUtils.marshaltoString(wmlP, true, true));

    return wmlP;

}