org.sejda.impl.sambox.SetMetadataTask 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.
/*
* Copyright 2015 by Edi Weissmann ([email protected])
*
* This file is part of the Sejda source code
*
* This program 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.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see {
private static final Logger LOG = LoggerFactory.getLogger(SetMetadataTask.class);
private PDDocumentHandler documentHandler = null;
private MultipleOutputWriter outputWriter;
private PdfSourceOpener documentLoader;
@Override
public void before(SetMetadataParameters parameters, TaskExecutionContext executionContext) throws TaskException {
super.before(parameters, executionContext);
documentLoader = new DefaultPdfSourceOpener();
outputWriter = OutputWriters.newMultipleOutputWriter(parameters.getExistingOutputPolicy(), executionContext);
}
@Override
public void execute(SetMetadataParameters parameters) throws TaskException {
int totalSteps = parameters.getSourceList().size();
for (int sourceIndex = 0; sourceIndex < parameters.getSourceList().size(); sourceIndex++) {
PdfSource source = parameters.getSourceList().get(sourceIndex);
int fileNumber = executionContext().incrementAndGetOutputDocumentsCounter();
try {
LOG.debug("Opening {}", source);
documentHandler = source.open(documentLoader);
documentHandler.setUpdateProducerModifiedDate(parameters.isUpdateProducerModifiedDate());
if(parameters.isUpdateProducerModifiedDate()) {
documentHandler.setCreatorOnPDDocument();
}
File tmpFile = createTemporaryBuffer(parameters.getOutput());
PDDocument doc = documentHandler.getUnderlyingPDDocument();
doc.setOnBeforeWriteAction(new PDDocument.OnBeforeWrite() {
@Override
public void onBeforeWrite() throws IOException {
LOG.debug("Setting metadata on temporary document.");
PDDocumentInformation actualMeta = documentHandler.getUnderlyingPDDocument().getDocumentInformation();
for (Entry meta : parameters.getMetadata().entrySet()) {
LOG.trace("'{}' -> '{}'", meta.getKey(), meta.getValue());
actualMeta.setCustomMetadataValue(meta.getKey(), meta.getValue());
}
for (String keyToRemove : parameters.getToRemove()) {
LOG.trace("Removing '{}'", keyToRemove);
actualMeta.removeMetadataField(keyToRemove);
}
PDDocumentCatalog catalog = documentHandler.getUnderlyingPDDocument().getDocumentCatalog();
if(catalog.getMetadata() != null) {
LOG.debug("Document has XMP metadata stream");
updateXmpMetadata(catalog, actualMeta);
}
}
});
documentHandler.setVersionOnPDDocument(parameters.getVersion());
documentHandler.setCompress(parameters.isCompress());
documentHandler.savePDDocument(tmpFile, parameters.getOutput().getEncryptionAtRestPolicy());
String outName = ofNullable(parameters.getSpecificResultFilename(fileNumber)).orElseGet(() -> {
return nameGenerator(parameters.getOutputPrefix())
.generate(nameRequest().originalName(source.getName()).fileNumber(fileNumber));
});
outputWriter.addOutput(file(tmpFile).name(outName));
} finally {
closeQuietly(documentHandler);
}
notifyEvent(executionContext().notifiableTaskMetadata()).stepsCompleted(fileNumber).outOf(totalSteps);
}
parameters.getOutput().accept(outputWriter);
LOG.debug("Metadata set and written to {}", parameters.getOutput());
}
private void setDate(String path, Document document, Calendar calendar) throws XPathExpressionException {
SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ssZ");
dateFormat.setTimeZone(TimeZone.getTimeZone("UTC"));
XPath xPath = XPathFactory.newInstance().newXPath();
Node node = (Node) xPath.compile(path).evaluate(document, XPathConstants.NODE);
if(node != null) {
String value = "";
if(calendar != null) {
value = dateFormat.format(calendar.getTime());
}
node.setTextContent(value);
}
}
private void setText(String path, Document document, String value) throws XPathExpressionException {
XPath xPath = XPathFactory.newInstance().newXPath();
Node node = (Node) xPath.compile(path).evaluate(document, XPathConstants.NODE);
if(node != null) {
if(value == null) {
value = "";
}
node.setTextContent(value);
}
}
private void updateXmpMetadata(PDDocumentCatalog catalog, PDDocumentInformation metadata) {
try {
DocumentBuilderFactory f = DocumentBuilderFactory.newInstance();
f.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, true);
DocumentBuilder b = f.newDocumentBuilder();
Document document = b.parse(catalog.getMetadata().createInputStream());
setDate("//*[name()='xmp:CreateDate']", document, metadata.getCreationDate());
setDate("//*[name()='xmp:ModifyDate']", document, metadata.getModificationDate());
setText("//*[name()='pdf:Producer']", document, metadata.getProducer());
setText("//*[name()='xmp:CreatorTool']", document, metadata.getCreator());
setText("//*[name()='pdf:Keywords']", document, metadata.getKeywords());
// TODO: update title, description
Calendar nowCalendar = Calendar.getInstance();
nowCalendar.setTime(new Date());
setDate("//*[name()='xmp:MetadataDate']", document, nowCalendar);
// write the DOM object to the file
TransformerFactory transformerFactory = TransformerFactory.newInstance();
Transformer transformer = transformerFactory.newTransformer();
StringWriter writer = new StringWriter();
DOMSource domSource = new DOMSource(document);
StreamResult streamResult = new StreamResult(writer);
transformer.transform(domSource, streamResult);
String updatedXml = writer.getBuffer().toString();
catalog.setMetadata(new PDMetadata(new ByteArrayInputStream(updatedXml.getBytes(StandardCharsets.UTF_8))));
} catch (SAXParseException ex) {
LOG.warn("Failed to parse XMP metadata, skipping update", ex);
} catch (Exception ex) {
throw new RuntimeException("Failed to update XMP metadata", ex);
}
}
@Override
public void after() {
closeQuietly(documentHandler);
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy