org.sejda.impl.sambox.UnpackTask Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of sejda-sambox Show documentation
Show all versions of sejda-sambox Show documentation
Package containing tasks implemented using sambox.
/*
* Created on 13 dic 2015
* Copyright 2015 by Andrea Vacondio ([email protected]).
* This file is part of Sejda.
*
* Sejda is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Sejda is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with Sejda. If not, see {
private static final Logger LOG = LoggerFactory.getLogger(UnpackTask.class);
private int totalSteps;
private PDDocumentHandler sourceDocumentHandler = null;
private MultipleOutputWriter outputWriter;
private PdfSourceOpener documentLoader;
@Override
public void before(UnpackParameters parameters, TaskExecutionContext executionContext) throws TaskException {
super.before(parameters, executionContext);
totalSteps = parameters.getSourceList().size();
documentLoader = new DefaultPdfSourceOpener(executionContext);
outputWriter = OutputWriters.newMultipleOutputWriter(parameters.getExistingOutputPolicy(), executionContext);
}
@Override
public void execute(UnpackParameters parameters) throws TaskException {
int currentStep = 0;
for (PdfSource source : parameters.getSourceList()) {
currentStep++;
try {
LOG.debug("Opening {}", source);
executionContext().notifiableTaskMetadata().setCurrentSource(source);
sourceDocumentHandler = source.open(documentLoader);
Map names = new HashMap<>();
PDEmbeddedFilesNameTreeNode ef = ofNullable(
sourceDocumentHandler.getUnderlyingPDDocument().getDocumentCatalog().getNames()).map(
PDDocumentNameDictionary::getEmbeddedFiles).orElse(null);
collectNamesVisitingTree(ef, names);
Stream.concat(names.values().stream(),
sourceDocumentHandler.getPages().stream().flatMap(p -> p.getAnnotations().stream())
.filter(a -> a instanceof PDAnnotationFileAttachment)
.map(a -> (PDAnnotationFileAttachment) a).map(PDAnnotationFileAttachment::getFile)
.filter(f -> f instanceof PDComplexFileSpecification)
.map(f -> (PDComplexFileSpecification) f)).forEach(this::unpack);
} finally {
closeQuietly(sourceDocumentHandler);
}
notifyEvent(executionContext().notifiableTaskMetadata()).stepsCompleted(currentStep).outOf(totalSteps);
}
executionContext().notifiableTaskMetadata().clearCurrentSource();
parameters.getOutput().accept(outputWriter);
LOG.debug("Attachments unpacked and written to {}", parameters.getOutput());
}
private void unpack(PDComplexFileSpecification file) {
ofNullable(file.getBestEmbeddedFile()).ifPresent(e -> {
try {
File tmpFile = createTemporaryBuffer();
LOG.debug("Created output temporary buffer {}", tmpFile);
try (InputStream is = e.createInputStream()) {
FileUtils.copyInputStreamToFile(is, tmpFile);
LOG.debug("Attachment '{}' unpacked to temporary buffer", file.getFilename());
}
outputWriter.addOutput(file(tmpFile).name(file.getFilename()));
} catch (IOException | TaskIOException ioe) {
LOG.error("Unable to extract file", ioe);
}
});
}
private void collectNamesVisitingTree(PDNameTreeNode node,
Map names) throws TaskIOException {
try {
if (nonNull(node)) {
Map nodeNames = node.getNames();
if (nodeNames != null) {
names.putAll(nodeNames);
} else {
for (PDNameTreeNode currNode : node.getKids()) {
collectNamesVisitingTree(currNode, names);
}
}
}
} catch (IOException ioe) {
throw new TaskIOException(ioe);
}
}
@Override
public void after() {
closeQuietly(sourceDocumentHandler);
}
}