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(executionContext);
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);
executionContext().notifiableTaskMetadata().setCurrentSource(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(() -> {
LOG.debug("Setting metadata on temporary document.");
PDDocument doc1 = documentHandler.getUnderlyingPDDocument();
PDDocumentCatalog catalog = doc1.getDocumentCatalog();
if (parameters.isRemoveAllMetadata()) {
doc1.setDocumentInformation(new PDDocumentInformation());
catalog.setMetadata(null);
return;
}
PDDocumentInformation actualMeta = doc1.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);
}
if (catalog.getMetadata() != null) {
LOG.debug("Document has XMP metadata stream");
try {
updateXmpMetadata(catalog, actualMeta);
} catch (RuntimeException ex) {
if(exceptionStackContains("Namespace for prefix 'xmp' has not been declared", ex)) {
// try to fix the metadata and retry
fixMissingXmpNamespace(catalog);
updateXmpMetadata(catalog, actualMeta);
} else {
throw ex;
}
}
}
});
documentHandler.setVersionOnPDDocument(parameters.getVersion());
documentHandler.setCompress(parameters.isCompress());
documentHandler.savePDDocument(tmpFile, parameters.getOutput().getEncryptionAtRestPolicy());
String outName = ofNullable(parameters.getSpecificResultFilename(fileNumber)).orElseGet(
() -> 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);
}
executionContext().notifiableTaskMetadata().clearCurrentSource();
parameters.getOutput().accept(outputWriter);
LOG.debug("Metadata set and written to {}", parameters.getOutput());
}
private XPathFactory newXPathFactory() {
try {
XPathFactory f = XPathFactory.newInstance();
f.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, true);
return f;
} catch (XPathFactoryConfigurationException e) {
throw new RuntimeException(e);
}
}
private void updateDateNode(String tagName, Document document, Calendar calendar) throws XPathExpressionException {
SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ssZ");
dateFormat.setTimeZone(TimeZone.getTimeZone("UTC"));
String value = "";
if(calendar != null) {
value = dateFormat.format(calendar.getTime());
}
updateTextNode(tagName, document, value);
}
private void updateTextNode(String tagName, Document document, String value) throws XPathExpressionException {
XPath xPath = newXPathFactory().newXPath();
Node node = (Node) xPath.compile("//*[name()='" + tagName + "']").evaluate(document, XPathConstants.NODE);
if(value == null) {
value = "";
}
if(node != null) {
node.setTextContent(value);
}
}
private boolean exceptionStackContains(String msg, Throwable ex) {
if (ex != null && ex.getMessage() != null && ex.getMessage().contains(msg)){
return true;
}
if (ex != null && ex.getCause() != null) {
return exceptionStackContains(msg, ex.getCause());
}
return false;
}
private void deleteAttr(String path, String attrName, Document document) throws XPathExpressionException {
XPath xPath = newXPathFactory().newXPath();
Node node = (Node) xPath.compile(path).evaluate(document, XPathConstants.NODE);
if(node != null && node.getAttributes().getNamedItem(attrName) != null) {
node.getAttributes().removeNamedItem(attrName);
}
}
private void fixMissingXmpNamespace(PDDocumentCatalog catalog) throws IOException {
try(InputStream is = catalog.getMetadata().createInputStream()) {
String metadataAsString = new String(is.readAllBytes(), StandardCharsets.UTF_8);
if (!metadataAsString.contains("xmlns:xmp=\"http://ns.adobe.com/xap/1.0/\"")) {
LOG.warn("Metadata seems to be missing xmlns:xmp namespace definition, adding it");
metadataAsString = metadataAsString.replaceAll(" © 2015 - 2025 Weber Informatics LLC | Privacy Policy