dspace-api: Update syntax for pdfbox 3.0.x

Author: alanorth

dspace-api/src/main/java/org/dspace/app/mediafilter/ImageMagickThumbnailFilter.java

@@ -14,7 +14,7 @@
 import java.util.regex.Pattern;
 import java.util.regex.PatternSyntaxException;
 
-import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
 import org.dspace.content.Bitstream;
@@ -153,8 +153,8 @@ public File getImageFile(File f, boolean verbose)
         // the CropBox is missing or empty because pdfbox will set it to the
         // same size as the MediaBox if it doesn't exist. Also note that we
         // only need to check the first page, since that's what we use for
-        // generating the thumbnail (PDDocument uses a zero-based index).
-        PDPage pdfPage = PDDocument.load(f).getPage(0);
+        // generating the thumbnail (PDPage uses a zero-based index).
+        PDPage pdfPage = Loader.loadPDF(f).getPage(0);
         PDRectangle pdfPageMediaBox = pdfPage.getMediaBox();
         PDRectangle pdfPageCropBox = pdfPage.getCropBox();
 

dspace-api/src/main/java/org/dspace/app/mediafilter/PDFBoxThumbnail.java

@@ -11,6 +11,8 @@
 import java.io.InputStream;
 
 import org.apache.logging.log4j.Logger;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;
 import org.apache.pdfbox.rendering.PDFRenderer;
@@ -71,7 +73,7 @@ public InputStream getDestinationStream(Item currentItem, InputStream source, bo
         BufferedImage buf;
 
         // Render the page image.
-        try ( PDDocument doc = PDDocument.load(source); ) {
+        try ( PDDocument doc = Loader.loadPDF(new RandomAccessReadBuffer(source)); ) {
             PDFRenderer renderer = new PDFRenderer(doc);
             buf = renderer.renderImage(0);
         } catch (InvalidPasswordException ex) {

dspace-api/src/main/java/org/dspace/content/packager/PDFPackager.java

@@ -19,11 +19,11 @@
 
 import org.apache.commons.lang3.ArrayUtils;
 import org.apache.logging.log4j.Logger;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.cos.COSDocument;
 import org.apache.pdfbox.io.MemoryUsageSetting;
-import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.io.ScratchFile;
-import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDDocumentInformation;
 import org.dspace.authorize.AuthorizeException;
@@ -331,19 +331,24 @@ private void crosswalkPDF(Context context, Item item, InputStream metadata)
         COSDocument cos = null;
 
         try {
-            ScratchFile scratchFile = null;
+            PDDocument document = null;
+
             try {
-                long useRAM = Runtime.getRuntime().freeMemory() * 80 / 100; // use up to 80% of JVM free memory
-                scratchFile = new ScratchFile(
-                    MemoryUsageSetting.setupMixed(useRAM)); // then fallback to temp file (unlimited size)
+                // Use up to 80% of JVM free memory and fall back to a temp file (unlimited size)
+                long useRAM = Runtime.getRuntime().freeMemory() * 80 / 100;
+                document = Loader.loadPDF(
+                        new RandomAccessReadBuffer(metadata),
+                        () -> new ScratchFile(MemoryUsageSetting.setupMixed(useRAM)));
             } catch (IOException ioe) {
                 log.warn("Error initializing scratch file: " + ioe.getMessage());
             }
 
-            PDFParser parser = new PDFParser(new RandomAccessBufferedFileInputStream(metadata), scratchFile);
-            parser.parse();
-            cos = parser.getDocument();
+            // sanity check: loaded PDF document must not be null.
+            if (document == null) {
+                throw new MetadataValidationException("The provided stream could not be parsed into a PDF document.");
+            }
 
+            cos = document.getDocument();
             // sanity check: PDFBox breaks on encrypted documents, so give up.
             if (cos.getEncryptionDictionary() != null) {
                 throw new MetadataValidationException("This packager cannot accept an encrypted PDF document.");

dspace-api/src/main/java/org/dspace/disseminate/CitationDocumentServiceImpl.java

@@ -20,6 +20,8 @@
 import org.apache.commons.lang3.tuple.Pair;
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.dspace.authorize.AuthorizeException;
@@ -264,7 +266,7 @@ public Pair<byte[], Long> makeCitedDocument(Context context, Bitstream bitstream
 
     private PDDocument loadDocumentFromDB(Context context, Bitstream bitstream) {
         try (var inputStream = bitstreamService.retrieve(context, bitstream)) {
-            return PDDocument.load(inputStream);
+            return Loader.loadPDF(new RandomAccessReadBuffer(inputStream));
         } catch (IOException | SQLException | AuthorizeException e) {
             throw new RuntimeException(e);
         }
@@ -307,4 +309,4 @@ private void addCoverPageToDocument(PDDocument document, PDDocument sourceDocume
             }
         }
     }
-}
+}

dspace-api/src/main/java/org/dspace/disseminate/PdfGenerator.java

@@ -15,6 +15,7 @@
 import java.util.Map;
 import java.util.stream.Collectors;
 
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.thymeleaf.TemplateEngine;
 import org.thymeleaf.context.Context;
@@ -84,7 +85,7 @@ public void generateToFile(String html, File toFile) {
     public PDDocument generate(String html) {
         try (var out = new ByteArrayOutputStream()) {
             generate(html, out);
-            return PDDocument.load(out.toByteArray());
+            return Loader.loadPDF(out.toByteArray());
         } catch (IOException e) {
             throw new RuntimeException(e);
         }

dspace-api/src/main/java/org/dspace/importer/external/epo/service/EpoImportMetadataSourceServiceImpl.java

@@ -29,9 +29,9 @@
 import org.apache.commons.lang3.StringUtils;
 import org.apache.http.HttpException;
 import org.apache.http.client.utils.URIBuilder;
+import org.apache.jena.ext.xerces.impl.dv.util.Base64;
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
-import org.apache.xerces.impl.dv.util.Base64;
 import org.dspace.app.util.XMLUtils;
 import org.dspace.content.Item;
 import org.dspace.importer.external.datamodel.ImportRecord;

dspace-server-webapp/src/test/java/org/dspace/app/rest/BitstreamRestControllerIT.java

@@ -62,6 +62,8 @@
 import org.apache.commons.io.IOUtils;
 import org.apache.commons.lang3.CharEncoding;
 import org.apache.commons.lang3.StringUtils;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
 import org.apache.solr.client.solrj.SolrServerException;
@@ -1007,7 +1009,7 @@ private String extractPDFText(byte[] content) throws IOException {
 
         try (ByteArrayInputStream source = new ByteArrayInputStream(content);
              Writer writer = new StringWriter();
-             PDDocument pdfDoc = PDDocument.load(source)) {
+             PDDocument pdfDoc = Loader.loadPDF(new RandomAccessReadBuffer(source))) {
 
             pts.writeText(pdfDoc, writer);
             return writer.toString();
@@ -1016,7 +1018,7 @@ private String extractPDFText(byte[] content) throws IOException {
 
     private int getNumberOfPdfPages(byte[] content) throws IOException {
         try (ByteArrayInputStream source = new ByteArrayInputStream(content);
-             PDDocument pdfDoc = PDDocument.load(source)) {
+            PDDocument pdfDoc = Loader.loadPDF(new RandomAccessReadBuffer(source))) {
             return pdfDoc.getNumberOfPages();
         }
     }