How to know the Image or Picture Location while parsing MS Word Doc in java using apache poi

Question

HWPFDocument wordDoc = new HWPFDocument(new FileInputStream(fileName));
List picturesList = wordDoc.getPicturesTable().getAllPictures();

Answer 1

You Should add PicturesSourceClass

public class PicturesSource {

private PicturesTable picturesTable;
private Set output = new HashSet();
private Map lookup;
private List nonU1based;
private List all;
private int pn = 0;

public PicturesSource(HWPFDocument doc) {
    picturesTable = doc.getPicturesTable();
    all = picturesTable.getAllPictures();


    lookup = new HashMap();
    for (Picture p : all) {
        lookup.put(p.getStartOffset(), p);
    }


    nonU1based = new ArrayList();
    nonU1based.addAll(all);
    Range r = doc.getRange();
    for (int i = 0; i < r.numCharacterRuns(); i++) {
        CharacterRun cr = r.getCharacterRun(i);
        if (picturesTable.hasPicture(cr)) {
            Picture p = getFor(cr);
            int at = nonU1based.indexOf(p);
            nonU1based.set(at, null);
        }
    }
}


private boolean hasPicture(CharacterRun cr) {
    return picturesTable.hasPicture(cr);
}

private void recordOutput(Picture picture) {
    output.add(picture);
}

private boolean hasOutput(Picture picture) {
    return output.contains(picture);
}

private int pictureNumber(Picture picture) {
    return all.indexOf(picture) + 1;
}

public Picture getFor(CharacterRun cr) {
    return lookup.get(cr.getPicOffset());
}


private Picture nextUnclaimed() {
    Picture p = null;
    while (pn < nonU1based.size()) {
        p = nonU1based.get(pn);
        pn++;
        if (p != null) return p;
    }
    return null;
}

}