How to get the shapes in a docx drawing using XWPF (Apache POI) - apache-poi

Question

I have a docx document with text and some shapes. I am able to get the drawings, but when I get a drawing, how can I get the Shapes in this drawing? For example I have the following code to parse my document:
try (FileInputStream fis = new FileInputStream(file)) {
document = new XWPFDocument(fis);
parseDocument(document);
}
The parseDocument(XWPFDocument document) method has the following code (I used the answer to the following question: How to get the drawings from the apache POI XWPFDocument?):
public void parseDocument(XWPFDocument document) throws Exception {
Iterator<XWPFParagraph> it = document.getParagraphs().iterator();
while (it.hasNext()) {
XWPFParagraph paragraph = it.next();
List<XWPFRun> runs = paragraph.getRuns();
Iterator<XWPFRun> it2 = runs.iterator();
while (it2.hasNext()) {
XWPFRun run = it2.next();
List<CTDrawing> drawings = getAllDrawings(run);
if (!drawings.isEmpty()) {
System.out.println("Found " + drawings.size() + " drawings");
Iterator<CTDrawing> it3 = drawings.iterator();
while (it3.hasNext()) {
CTDrawing drawing = it3.next();
visitDrawing(drawing);
}
}
}
}
}
private void visitDrawing(CTDrawing drawing) {
List<CTInline> inlines = drawing.getInlineList();
Iterator<CTInline> it = inlines.iterator();
while (it.hasNext()) {
CTInline inline = it.next();
CTGraphicalObject graphic = inline.getGraphic();
if (graphic != null) {
CTGraphicalObjectData graphicData = graphic.getGraphicData();
if (graphicData != null) {
XmlCursor c = graphicData.newCursor();
c.selectPath("./*");
while (c.toNextSelection()) {
XmlObject o = c.getObject();
System.out.println(o);
}
}
}
}
List<CTAnchor> anchors = drawing.getAnchorList();
Iterator<CTAnchor> it2 = anchors.iterator();
while (it2.hasNext()) {
CTAnchor anchor = it2.next();
CTGraphicalObject graphic = anchor.getGraphic();
if (graphic != null) {
CTGraphicalObjectData graphicData = graphic.getGraphicData();
if (graphicData != null) {
XmlCursor c = graphicData.newCursor();
c.selectPath("./*");
while (c.toNextSelection()) {
XmlObject o = c.getObject();
System.out.println(o);
}
}
}
}
}
private static List<CTDrawing> getAllDrawings(XWPFRun run) throws Exception {
CTR ctR = run.getCTR();
XmlCursor cursor = ctR.newCursor();
cursor.selectPath("declare namespace w='http://schemas.openxmlformats.org/wordprocessingml/2006/main' .//*/w:drawing");
List<CTDrawing> drawings = new ArrayList<>();
while (cursor.hasNextSelection()) {
cursor.toNextSelection();
XmlObject obj = cursor.getObject();
CTDrawing drawing = CTDrawing.Factory.parse(obj.newInputStream());
drawings.add(drawing);
}
return drawings;
}
With both the inline and anchor drawings, the XmlObject element contains the shapes I can see it is the case in very simple exampleswhen I look at the printed content), but how do I get these shapes when I have the object?