Example usage for org.apache.poi.xslf.usermodel XSLFSheet getShapes

Introduction

In this page you can find the example usage for org.apache.poi.xslf.usermodel XSLFSheet getShapes.

Prototype

@Override
public List<XSLFShape> getShapes() 

Source Link

Document

Returns an array containing all of the shapes in this sheet

Usage

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

License:Apache License

/**
 * @see org.apache.poi.xslf.extractor.XSLFPowerPointExtractor#getText()
 *///from w w  w. ja v a 2s  .c o  m
protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException, IOException {
    XMLSlideShow slideShow = (XMLSlideShow) extractor.getDocument();

    XSLFSlide[] slides = slideShow.getSlides();
    for (XSLFSlide slide : slides) {
        String slideDesc;

        if (slide.getPackagePart() != null && slide.getPackagePart().getPartName() != null) {
            slideDesc = getJustFileName(slide.getPackagePart().getPartName().toString());
            slideDesc += "_";
        } else {
            slideDesc = null;
        }

        // slide
        extractContent(slide.getShapes(), false, xhtml, slideDesc);

        // slide layout which is the master sheet for this slide
        XSLFSheet slideLayout = slide.getMasterSheet();
        extractContent(slideLayout.getShapes(), true, xhtml, null);

        // slide master which is the master sheet for all text layouts
        XSLFSheet slideMaster = slideLayout.getMasterSheet();
        extractContent(slideMaster.getShapes(), true, xhtml, null);

        // notes (if present)
        XSLFSheet slideNotes = slide.getNotes();
        if (slideNotes != null) {
            extractContent(slideNotes.getShapes(), false, xhtml, slideDesc);
            // master sheet for this notes
            XSLFSheet notesMaster = slideNotes.getMasterSheet();
            extractContent(notesMaster.getShapes(), true, xhtml, null);
        }

        // comments (if present)
        XSLFComments comments = slide.getComments();
        if (comments != null) {
            for (CTComment comment : comments.getCTCommentsList().getCmList()) {
                xhtml.element("p", comment.getText());
            }
        }
    }

    if (Config.inst().getProp(ConfigBool.ENABLE_IMAGE_OCR)) {
        TikaImageHelper helper = new TikaImageHelper(metadata);
        try {
            List<XSLFPictureData> pictures = slideShow.getAllPictures();
            for (XSLFPictureData picture : pictures) {
                ByteArrayInputStream imageData = new ByteArrayInputStream(picture.getData());
                BufferedImage image = ImageIO.read(imageData);
                helper.addImage(image);
                helper.addTextToHandler(xhtml);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (extractor != null) {
                extractor.close();
            }
            if (helper != null) {
                helper.close();
            }
        }
    }
}

---

From source file:org.apache.tika.parser.microsoft.ooxml.XSLFPowerPointExtractorDecorator.java

License:Apache License

/**
 * @see org.apache.poi.xslf.extractor.XSLFPowerPointExtractor#getText()
 *///from w w  w. j  av a 2s  . co  m
protected void buildXHTML(XHTMLContentHandler xhtml) throws SAXException, IOException {
    XMLSlideShow slideShow = (XMLSlideShow) extractor.getDocument();
    XSLFCommentAuthors commentAuthors = slideShow.getCommentAuthors();

    List<XSLFSlide> slides = slideShow.getSlides();
    for (XSLFSlide slide : slides) {
        String slideDesc;
        if (slide.getPackagePart() != null && slide.getPackagePart().getPartName() != null) {
            slideDesc = getJustFileName(slide.getPackagePart().getPartName().toString());
            slideDesc += "_";
        } else {
            slideDesc = null;
        }

        // slide content
        xhtml.startElement("div", "class", "slide-content");
        extractContent(slide.getShapes(), false, xhtml, slideDesc);
        xhtml.endElement("div");

        // slide layout which is the master sheet for this slide
        xhtml.startElement("div", "class", "slide-master-content");
        XSLFSlideLayout slideLayout = slide.getMasterSheet();
        extractContent(slideLayout.getShapes(), true, xhtml, null);
        xhtml.endElement("div");

        // slide master which is the master sheet for all text layouts
        XSLFSheet slideMaster = slideLayout.getMasterSheet();
        extractContent(slideMaster.getShapes(), true, xhtml, null);

        // notes (if present)
        XSLFNotes slideNotes = slide.getNotes();
        if (slideNotes != null) {
            xhtml.startElement("div", "class", "slide-notes");

            extractContent(slideNotes.getShapes(), false, xhtml, slideDesc);

            // master sheet for this notes
            XSLFNotesMaster notesMaster = slideNotes.getMasterSheet();
            extractContent(notesMaster.getShapes(), true, xhtml, null);
            xhtml.endElement("div");
        }

        // comments (if present)
        XSLFComments comments = slide.getComments();
        if (comments != null) {
            StringBuilder authorStringBuilder = new StringBuilder();
            for (int i = 0; i < comments.getNumberOfComments(); i++) {
                authorStringBuilder.setLength(0);
                CTComment comment = comments.getCommentAt(i);
                xhtml.startElement("p", "class", "slide-comment");
                CTCommentAuthor cta = commentAuthors.getAuthorById(comment.getAuthorId());
                if (cta != null) {
                    if (cta.getName() != null) {
                        authorStringBuilder.append(cta.getName());
                    }
                    if (cta.getInitials() != null) {
                        if (authorStringBuilder.length() > 0) {
                            authorStringBuilder.append(" ");
                        }
                        authorStringBuilder.append("(" + cta.getInitials() + ")");
                    }
                    if (comment.getText() != null && authorStringBuilder.length() > 0) {
                        authorStringBuilder.append(" - ");
                    }
                    if (authorStringBuilder.length() > 0) {
                        xhtml.startElement("b");
                        xhtml.characters(authorStringBuilder.toString());
                        xhtml.endElement("b");
                    }
                }
                xhtml.characters(comment.getText());
                xhtml.endElement("p");
            }
        }
    }
}

---