private void extractEmbeddedDocuments(PDDocument document)
throws IOException, SAXException, TikaException {
PDDocumentNameDictionary namesDictionary =
new PDDocumentNameDictionary(document.getDocumentCatalog());
PDEmbeddedFilesNameTreeNode efTree = namesDictionary.getEmbeddedFiles();
if (efTree == null) {
return;
}
Map<String, PDComplexFileSpecification> embeddedFileNames = efTree.getNames();
// For now, try to get the embeddedFileNames out of embeddedFiles or its kids.
// This code follows: pdfbox/examples/pdmodel/ExtractEmbeddedFiles.java
// If there is a need we could add a fully recursive search to find a non-null
// Map<String, COSObjectable> that contains the doc info.
if (embeddedFileNames != null) {
processEmbeddedDocNames(embeddedFileNames);
} else {
List<PDNameTreeNode<PDComplexFileSpecification>> kids = efTree.getKids();
if (kids == null) {
return;
}
for (PDNameTreeNode<PDComplexFileSpecification> node : kids) {
embeddedFileNames = node.getNames();
if (embeddedFileNames != null) {
processEmbeddedDocNames(embeddedFileNames);
}
}
}
}
