use of org.apache.poi.hslf.usermodel.HSLFShape in project poi by apache.
the class TestBackground method readBackground.
/**
* Read fill information from an reference ppt file
*/
@Test
public void readBackground() throws IOException {
HSLFSlideShow ppt = HSLFTestDataSamples.getSlideShow("backgrounds.ppt");
HSLFFill fill;
HSLFShape shape;
List<HSLFSlide> slide = ppt.getSlides();
fill = slide.get(0).getBackground().getFill();
assertEquals(HSLFFill.FILL_PICTURE, fill.getFillType());
shape = slide.get(0).getShapes().get(0);
assertEquals(HSLFFill.FILL_SOLID, shape.getFill().getFillType());
fill = slide.get(1).getBackground().getFill();
assertEquals(HSLFFill.FILL_PATTERN, fill.getFillType());
shape = slide.get(1).getShapes().get(0);
assertEquals(HSLFFill.FILL_BACKGROUND, shape.getFill().getFillType());
fill = slide.get(2).getBackground().getFill();
assertEquals(HSLFFill.FILL_TEXTURE, fill.getFillType());
shape = slide.get(2).getShapes().get(0);
assertEquals(HSLFFill.FILL_PICTURE, shape.getFill().getFillType());
fill = slide.get(3).getBackground().getFill();
assertEquals(HSLFFill.FILL_SHADE_CENTER, fill.getFillType());
shape = slide.get(3).getShapes().get(0);
assertEquals(HSLFFill.FILL_SHADE, shape.getFill().getFillType());
ppt.close();
}
use of org.apache.poi.hslf.usermodel.HSLFShape in project poi by apache.
the class Hyperlinks method main.
public static void main(String[] args) throws Exception {
for (int i = 0; i < args.length; i++) {
FileInputStream is = new FileInputStream(args[i]);
HSLFSlideShow ppt = new HSLFSlideShow(is);
is.close();
for (HSLFSlide slide : ppt.getSlides()) {
System.out.println("\nslide " + slide.getSlideNumber());
// read hyperlinks from the slide's text runs
System.out.println("- reading hyperlinks from the text runs");
for (List<HSLFTextParagraph> paras : slide.getTextParagraphs()) {
for (HSLFTextParagraph para : paras) {
for (HSLFTextRun run : para) {
HSLFHyperlink link = run.getHyperlink();
if (link != null) {
System.out.println(toStr(link, run.getRawText()));
}
}
}
}
// in PowerPoint you can assign a hyperlink to a shape without text,
// for example to a Line object. The code below demonstrates how to
// read such hyperlinks
System.out.println("- reading hyperlinks from the slide's shapes");
for (HSLFShape sh : slide.getShapes()) {
if (sh instanceof HSLFSimpleShape) {
HSLFHyperlink link = ((HSLFSimpleShape) sh).getHyperlink();
if (link != null) {
System.out.println(toStr(link, null));
}
}
}
}
ppt.close();
}
}
use of org.apache.poi.hslf.usermodel.HSLFShape in project tika by apache.
the class HSLFExtractor method parse.
protected void parse(DirectoryNode root, XHTMLContentHandler xhtml) throws IOException, SAXException, TikaException {
HSLFSlideShow ss = new HSLFSlideShow(root);
List<HSLFSlide> _slides = ss.getSlides();
xhtml.startElement("div", "class", "slideShow");
/* Iterate over slides and extract text */
for (HSLFSlide slide : _slides) {
xhtml.startElement("div", "class", "slide");
// Slide header, if present
HeadersFooters hf = slide.getHeadersFooters();
if (hf != null && hf.isHeaderVisible() && hf.getHeaderText() != null) {
xhtml.startElement("p", "class", "slide-header");
xhtml.characters(hf.getHeaderText());
xhtml.endElement("p");
}
// Slide master, if present
extractMaster(xhtml, slide.getMasterSheet());
// Slide text
{
xhtml.startElement("div", "class", "slide-content");
textRunsToText(xhtml, slide.getTextParagraphs());
xhtml.endElement("div");
}
// Table text
for (HSLFShape shape : slide.getShapes()) {
if (shape instanceof HSLFTable) {
extractTableText(xhtml, (HSLFTable) shape);
}
}
// Slide footer, if present
if (hf != null && hf.isFooterVisible() && hf.getFooterText() != null) {
xhtml.startElement("p", "class", "slide-footer");
xhtml.characters(hf.getFooterText());
xhtml.endElement("p");
}
// Comments, if present
StringBuilder authorStringBuilder = new StringBuilder();
for (Comment comment : slide.getComments()) {
authorStringBuilder.setLength(0);
xhtml.startElement("p", "class", "slide-comment");
if (comment.getAuthor() != null) {
authorStringBuilder.append(comment.getAuthor());
}
if (comment.getAuthorInitials() != null) {
if (authorStringBuilder.length() > 0) {
authorStringBuilder.append(" ");
}
authorStringBuilder.append("(" + comment.getAuthorInitials() + ")");
}
if (authorStringBuilder.length() > 0) {
if (comment.getText() != null) {
authorStringBuilder.append(" - ");
}
xhtml.startElement("b");
xhtml.characters(authorStringBuilder.toString());
xhtml.endElement("b");
}
if (comment.getText() != null) {
xhtml.characters(comment.getText());
}
xhtml.endElement("p");
}
// Now any embedded resources
handleSlideEmbeddedResources(slide, xhtml);
// Find the Notes for this slide and extract inline
HSLFNotes notes = slide.getNotes();
if (notes != null) {
xhtml.startElement("div", "class", "slide-notes");
textRunsToText(xhtml, notes.getTextParagraphs());
xhtml.endElement("div");
}
// Slide complete
xhtml.endElement("div");
}
// All slides done
xhtml.endElement("div");
/* notes */
xhtml.startElement("div", "class", "slide-notes");
HashSet<Integer> seenNotes = new HashSet<>();
HeadersFooters hf = ss.getNotesHeadersFooters();
for (HSLFSlide slide : _slides) {
HSLFNotes notes = slide.getNotes();
if (notes == null) {
continue;
}
Integer id = notes._getSheetNumber();
if (seenNotes.contains(id)) {
continue;
}
seenNotes.add(id);
// Repeat the Notes header, if set
if (hf != null && hf.isHeaderVisible() && hf.getHeaderText() != null) {
xhtml.startElement("p", "class", "slide-note-header");
xhtml.characters(hf.getHeaderText());
xhtml.endElement("p");
}
// Notes text
textRunsToText(xhtml, notes.getTextParagraphs());
// Repeat the notes footer, if set
if (hf != null && hf.isFooterVisible() && hf.getFooterText() != null) {
xhtml.startElement("p", "class", "slide-note-footer");
xhtml.characters(hf.getFooterText());
xhtml.endElement("p");
}
}
handleSlideEmbeddedPictures(ss, xhtml);
xhtml.endElement("div");
}
use of org.apache.poi.hslf.usermodel.HSLFShape in project tika by apache.
the class HSLFExtractor method extractMaster.
private void extractMaster(XHTMLContentHandler xhtml, HSLFMasterSheet master) throws SAXException {
if (master == null) {
return;
}
List<HSLFShape> shapes = master.getShapes();
if (shapes == null || shapes.isEmpty()) {
return;
}
xhtml.startElement("div", "class", "slide-master-content");
for (HSLFShape shape : shapes) {
if (shape != null && !HSLFMasterSheet.isPlaceholder(shape)) {
if (shape instanceof HSLFTextShape) {
HSLFTextShape tsh = (HSLFTextShape) shape;
String text = tsh.getText();
if (text != null) {
xhtml.element("p", text);
}
}
}
}
xhtml.endElement("div");
}
use of org.apache.poi.hslf.usermodel.HSLFShape in project tika by apache.
the class HSLFExtractor method handleSlideEmbeddedResources.
private void handleSlideEmbeddedResources(HSLFSlide slide, XHTMLContentHandler xhtml) throws TikaException, SAXException, IOException {
List<HSLFShape> shapes;
try {
shapes = slide.getShapes();
} catch (NullPointerException e) {
// Sometimes HSLF hits problems
// Please open POI bugs for any you come across!
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
return;
}
for (HSLFShape shape : shapes) {
if (shape instanceof OLEShape) {
OLEShape oleShape = (OLEShape) shape;
HSLFObjectData data = null;
try {
data = oleShape.getObjectData();
} catch (NullPointerException e) {
/* getObjectData throws NPE some times. */
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
continue;
}
if (data != null) {
String objID = Integer.toString(oleShape.getObjectID());
// Embedded Object: add a <div
// class="embedded" id="X"/> so consumer can see where
// in the main text each embedded document
// occurred:
AttributesImpl attributes = new AttributesImpl();
attributes.addAttribute("", "class", "class", "CDATA", "embedded");
attributes.addAttribute("", "id", "id", "CDATA", objID);
xhtml.startElement("div", attributes);
xhtml.endElement("div");
InputStream dataStream = null;
try {
dataStream = data.getData();
} catch (Exception e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
continue;
}
try (TikaInputStream stream = TikaInputStream.get(dataStream)) {
String mediaType = null;
if ("Excel.Chart.8".equals(oleShape.getProgID())) {
mediaType = "application/vnd.ms-excel";
} else {
MediaType mt = getTikaConfig().getDetector().detect(stream, new Metadata());
mediaType = mt.toString();
}
if (mediaType.equals("application/x-tika-msoffice-embedded; format=comp_obj")) {
try (NPOIFSFileSystem npoifs = new NPOIFSFileSystem(new CloseShieldInputStream(stream))) {
handleEmbeddedOfficeDoc(npoifs.getRoot(), objID, xhtml);
}
} else {
handleEmbeddedResource(stream, objID, objID, mediaType, xhtml, false);
}
} catch (IOException e) {
EmbeddedDocumentUtil.recordEmbeddedStreamException(e, parentMetadata);
}
}
}
}
}
Aggregations