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);
}
}
}
}
private void getNamesEmbeddedFiles(List<Object> files, COSDictionary buffer) throws IOException {
PDEmbeddedFilesNameTreeNode root = null;
if (buffer != null) {
root = new PDEmbeddedFilesNameTreeNode(buffer);
}
if (root != null) {
final Set<Map.Entry<String, PDComplexFileSpecification>> entries = root.getNames().entrySet();
for (Map.Entry<String, PDComplexFileSpecification> entry : entries) {
files.add(new PBCosFileSpecification(entry.getValue().getCOSObject()));
}
}
}
/**
* Starts the text extraction.
*
* @param args the commandline arguments.
* @throws IOException if there is an error reading the document or extracting the text.
*/
public void startExtraction(String[] args) throws IOException {
boolean toConsole = false;
boolean toHTML = false;
boolean sort = false;
boolean separateBeads = true;
String password = "";
String encoding = "UTF-8";
String pdfFile = null;
String outputFile = null;
// Defaults to text files
String ext = ".txt";
int startPage = 1;
int endPage = Integer.MAX_VALUE;
for (int i = 0; i < args.length; i++) {
switch (args[i]) {
case PASSWORD:
i++;
if (i >= args.length) {
usage();
}
password = args[i];
break;
case ENCODING:
i++;
if (i >= args.length) {
usage();
}
encoding = args[i];
break;
case START_PAGE:
i++;
if (i >= args.length) {
usage();
}
startPage = Integer.parseInt(args[i]);
break;
case HTML:
toHTML = true;
ext = ".html";
break;
case SORT:
sort = true;
break;
case IGNORE_BEADS:
separateBeads = false;
break;
case DEBUG:
debug = true;
break;
case END_PAGE:
i++;
if (i >= args.length) {
usage();
}
endPage = Integer.parseInt(args[i]);
break;
case CONSOLE:
toConsole = true;
break;
default:
if (pdfFile == null) {
pdfFile = args[i];
} else {
outputFile = args[i];
}
break;
}
}
if (pdfFile == null) {
usage();
} else {
Writer output = null;
PDDocument document = null;
try {
long startTime = startProcessing("Loading PDF " + pdfFile);
if (outputFile == null && pdfFile.length() > 4) {
outputFile = new File(pdfFile.substring(0, pdfFile.length() - 4) + ext).getAbsolutePath();
}
document = PDDocument.load(new File(pdfFile), password);
AccessPermission ap = document.getCurrentAccessPermission();
if (!ap.canExtractContent()) {
throw new IOException("You do not have permission to extract text");
}
stopProcessing("Time for loading: ", startTime);
if (toConsole) {
output = new OutputStreamWriter(System.out, encoding);
} else {
output = new OutputStreamWriter(new FileOutputStream(outputFile), encoding);
}
PDFTextStripper stripper;
if (toHTML) {
stripper = new PDFText2HTML();
} else {
stripper = new PDFTextStripper();
}
stripper.setSortByPosition(sort);
stripper.setShouldSeparateByBeads(separateBeads);
stripper.setStartPage(startPage);
stripper.setEndPage(endPage);
startTime = startProcessing("Starting text extraction");
if (debug) {
System.err.println("Writing to " + outputFile);
}
// Extract text for main document:
stripper.writeText(document, output);
// ... also for any embedded PDFs:
PDDocumentCatalog catalog = document.getDocumentCatalog();
PDDocumentNameDictionary names = catalog.getNames();
if (names != null) {
PDEmbeddedFilesNameTreeNode embeddedFiles = names.getEmbeddedFiles();
if (embeddedFiles != null) {
Map<String, PDComplexFileSpecification> embeddedFileNames = embeddedFiles.getNames();
if (embeddedFileNames != null) {
for (Map.Entry<String, PDComplexFileSpecification> ent :
embeddedFileNames.entrySet()) {
if (debug) {
System.err.println("Processing embedded file " + ent.getKey() + ":");
}
PDComplexFileSpecification spec = ent.getValue();
PDEmbeddedFile file = spec.getEmbeddedFile();
if (file != null && "application/pdf".equals(file.getSubtype())) {
if (debug) {
System.err.println(" is PDF (size=" + file.getSize() + ")");
}
InputStream fis = file.createInputStream();
PDDocument subDoc = null;
try {
subDoc = PDDocument.load(fis);
} finally {
fis.close();
}
try {
stripper.writeText(subDoc, output);
} finally {
IOUtils.closeQuietly(subDoc);
}
}
}
}
}
}
stopProcessing("Time for extraction: ", startTime);
} finally {
IOUtils.closeQuietly(output);
IOUtils.closeQuietly(document);
}
}
}
