Improve Dublin Core (#3710)

This fixes #938 - Reading and writing multiple dublinCore entries works: XMPUtilWriter supports mutliple metadata entries in dublinCore and a single entry in the PDDocumentInformation. If you want to test the reading of multiple entries, the PDF file JabRef_multipleMetaEntries.pdf contains three metadata entries in DublinCore for testing locally. - Removed to much code when refactoring the XMPUtil. Non XMP metadata are also relevent, when retrieving org.apache.pdfbox.pdmodel.PDDocumentInformation - Update pdfbox and fontbox from 1.8.13 to 2.0.8 and migritate from jempbox to xmpbox. See pull #1096. - Refactor extraction from DublinCoreSchema - The tests cover the most important use cases, which include reading and writing metadata from pdf files. Both formats, DublinCore and PDMetadata (which are no XMP metadata) are tested. - Separated XMPUtils in a reader and a writer utitlity class. - add meaningful names in DublinCoreExtractor and use StringUtils.isNullOrEmpty - Log exception in XMPUtilShared
JabRef · Feb 20, 2018 · ea8ccb3 · ea8ccb3
1 parent e9e7bcc
commit ea8ccb3
Show file tree

Hide file tree

Showing 39 changed files with 1,389 additions and 3,268 deletions.
diff --git a/build.gradle b/build.gradle
@@ -90,10 +90,9 @@ dependencies {
     compile 'com.jgoodies:jgoodies-common:1.8.1'
     compile 'com.jgoodies:jgoodies-forms:1.9.0'
 
-    // update to 2.0.x is not possible - see https://github.com/JabRef/jabref/pull/1096#issuecomment-208857517
-    compile 'org.apache.pdfbox:pdfbox:1.8.13'
-    compile 'org.apache.pdfbox:fontbox:1.8.13'
-    compile 'org.apache.pdfbox:jempbox:1.8.13'
+    compile 'org.apache.pdfbox:pdfbox:2.0.8'
+    compile 'org.apache.pdfbox:fontbox:2.0.8'
+    compile 'org.apache.pdfbox:xmpbox:2.0.8'
 
     // required for reading write-protected PDFs - see https://github.com/JabRef/jabref/pull/942#issuecomment-209252635
     compile 'org.bouncycastle:bcprov-jdk15on:1.59'
@@ -216,16 +215,6 @@ dependencyUpdates.resolutionStrategy = {
                 selection.reject("Cannot be upgraded to version 2")
             }
         }
-        withModule("org.apache.pdfbox:fontbox") { ComponentSelection selection ->
-            if (selection.candidate.version ==~ /2.*/) {
-                selection.reject("update to 2.0.x is not possible - see https://github.com/JabRef/jabref/pull/1096#issuecomment-208857517")
-            }
-        }
-        withModule("org.apache.pdfbox:pdfbox") { ComponentSelection selection ->
-            if (selection.candidate.version ==~ /2.*/) {
-                selection.reject("update to 2.0.x is not possible - see https://github.com/JabRef/jabref/pull/1096#issuecomment-208857517")
-            }
-        }
         withModule("mysql:mysql-connector-java") { ComponentSelection selection ->
             if (selection.candidate.version ==~ /[6-9].*/) {
                 selection.reject("http://dev.mysql.com/downloads/connector/j/ lists the version 5.* as last stable version.")

diff --git a/src/main/java/org/jabref/cli/XMPUtilMain.java b/src/main/java/org/jabref/cli/XMPUtilMain.java
@@ -1,10 +1,9 @@
 package org.jabref.cli;
 
-import java.io.File;
 import java.io.FileReader;
 import java.io.IOException;
 import java.io.StringWriter;
-import java.nio.charset.StandardCharsets;
+import java.nio.file.Paths;
 import java.util.Collection;
 import java.util.List;
 import java.util.Optional;
@@ -17,14 +16,15 @@
 import org.jabref.logic.importer.ImportFormatPreferences;
 import org.jabref.logic.importer.ParserResult;
 import org.jabref.logic.importer.fileformat.BibtexParser;
-import org.jabref.logic.xmp.XMPPreferences;
-import org.jabref.logic.xmp.XMPUtil;
+import org.jabref.logic.xmp.XmpPreferences;
+import org.jabref.logic.xmp.XmpUtilReader;
+import org.jabref.logic.xmp.XmpUtilWriter;
 import org.jabref.model.database.BibDatabaseMode;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.preferences.JabRefPreferences;
 
-import org.apache.jempbox.impl.XMLUtil;
-import org.apache.jempbox.xmp.XMPMetadata;
+import org.apache.xmpbox.XMPMetadata;
+import org.apache.xmpbox.xml.XmpSerializer;
 
 public class XMPUtilMain {
 
@@ -62,18 +62,16 @@ public static void main(String[] args) throws IOException, TransformerException
             Globals.prefs = JabRefPreferences.getInstance();
         }
 
-        XMPPreferences xmpPreferences = Globals.prefs.getXMPPreferences();
+        XmpPreferences xmpPreferences = Globals.prefs.getXMPPreferences();
         ImportFormatPreferences importFormatPreferences = Globals.prefs.getImportFormatPreferences();
 
-        switch (args.length) {
-        case 0:
+        int argsLength = args.length;
+        if (argsLength == 0) {
             usage();
-            break;
-        case 1:
-
+        } else if (argsLength == 1) {
             if (args[0].endsWith(".pdf")) {
                 // Read from pdf and write as BibTex
-                List<BibEntry> l = XMPUtil.readXMP(new File(args[0]), xmpPreferences);
+                List<BibEntry> l = XmpUtilReader.readXmp(args[0], xmpPreferences);
 
                 BibEntryWriter bibtexEntryWriter = new BibEntryWriter(
                         new LatexFieldFormatter(Globals.prefs.getLatexFieldFormatterPreferences()), false);
@@ -92,63 +90,62 @@ public static void main(String[] args) throws IOException, TransformerException
 
                     if (entries.isEmpty()) {
                         System.err.println("Could not find BibEntry in " + args[0]);
-                    } else {
-                        System.out.println(XMPUtil.toXMP(entries, result.getDatabase(), xmpPreferences));
                     }
                 }
             } else {
                 usage();
             }
-            break;
-        case 2:
+        } else if (argsLength == 2) {
             if ("-x".equals(args[0]) && args[1].endsWith(".pdf")) {
                 // Read from pdf and write as BibTex
-                Optional<XMPMetadata> meta = XMPUtil.readRawXMP(new File(args[1]));
+                List<XMPMetadata> meta = XmpUtilReader.readRawXmp(Paths.get(args[1]));
 
-                if (meta.isPresent()) {
-                    XMLUtil.save(meta.get().getXMPDocument(), System.out, StandardCharsets.UTF_8.name());
+                if (!meta.isEmpty()) {
+                    XmpSerializer serializer = new XmpSerializer();
+                    serializer.serialize(meta.get(0), System.out, true);
                 } else {
                     System.err.println("The given pdf does not contain any XMP-metadata.");
                 }
-                break;
+                return;
             }
 
             if (args[0].endsWith(".bib") && args[1].endsWith(".pdf")) {
-                ParserResult result = new BibtexParser(importFormatPreferences, Globals.getFileUpdateMonitor()).parse(new FileReader(args[0]));
+                try (FileReader reader = new FileReader(args[0])) {
+                    ParserResult result = new BibtexParser(importFormatPreferences, Globals.getFileUpdateMonitor()).parse(reader);
 
-                Collection<BibEntry> entries = result.getDatabase().getEntries();
+                    List<BibEntry> entries = result.getDatabase().getEntries();
 
-                if (entries.isEmpty()) {
-                    System.err.println("Could not find BibEntry in " + args[0]);
-                } else {
-                    XMPUtil.writeXMP(new File(args[1]), entries, result.getDatabase(), false, xmpPreferences);
-                    System.out.println("XMP written.");
+                    if (entries.isEmpty()) {
+                        System.err.println("Could not find BibEntry in " + args[0]);
+                    } else {
+                        XmpUtilWriter.writeXmp(Paths.get(args[1]), entries, result.getDatabase(), xmpPreferences);
+                        System.out.println("XMP written.");
+                    }
                 }
-                break;
+                return;
             }
 
             usage();
-            break;
-        case 3:
+        } else if (argsLength == 3) {
             if (!args[1].endsWith(".bib") && !args[2].endsWith(".pdf")) {
                 usage();
-                break;
+                return;
             }
 
-            ParserResult result = new BibtexParser(importFormatPreferences, Globals.getFileUpdateMonitor()).parse(new FileReader(args[1]));
+            try (FileReader reader = new FileReader(args[1])) {
+                ParserResult result = new BibtexParser(importFormatPreferences, Globals.getFileUpdateMonitor()).parse(reader);
 
-            Optional<BibEntry> bibEntry = result.getDatabase().getEntryByKey(args[0]);
+                Optional<BibEntry> bibEntry = result.getDatabase().getEntryByKey(args[0]);
 
-            if (bibEntry.isPresent()) {
-                XMPUtil.writeXMP(new File(args[2]), bibEntry.get(), result.getDatabase(), xmpPreferences);
+                if (bibEntry.isPresent()) {
+                    XmpUtilWriter.writeXmp(Paths.get(args[2]), bibEntry.get(), result.getDatabase(), xmpPreferences);
 
-                System.out.println("XMP written.");
-            } else {
-                System.err.println("Could not find BibEntry " + args[0] + " in " + args[0]);
+                    System.out.println("XMP written.");
+                } else {
+                    System.err.println("Could not find BibEntry " + args[0] + " in " + args[0]);
+                }
             }
-            break;
-
-        default:
+        } else {
             usage();
         }
     }
@@ -167,13 +164,13 @@ private static void usage() {
         System.out.println("Read from PDF and print raw XMP:");
         System.out.println("  xmpUtil -x <pdf>");
         System.out
-        .println("Write the entry in <bib> given by <key> to the PDF:");
+                .println("Write the entry in <bib> given by <key> to the PDF:");
         System.out.println("  xmpUtil <key> <bib> <pdf>");
         System.out.println("Write all entries in <bib> to the PDF:");
         System.out.println("  xmpUtil <bib> <pdf>");
         System.out.println("");
         System.out
-        .println("To report bugs visit https://issues.jabref.org");
+                .println("To report bugs visit https://issues.jabref.org");
     }
 
 }
diff --git a/src/main/java/org/jabref/gui/documentviewer/PdfDocumentPageViewModel.java b/src/main/java/org/jabref/gui/documentviewer/PdfDocumentPageViewModel.java
@@ -8,8 +8,11 @@
 import javafx.embed.swing.SwingFXUtils;
 import javafx.scene.image.Image;
 
+import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.rendering.ImageType;
+import org.apache.pdfbox.rendering.PDFRenderer;
 
 /**
  * Represents the view model of a pdf page backed by a {@link PDPage}.
@@ -18,10 +21,12 @@ public class PdfDocumentPageViewModel extends DocumentPageViewModel {
 
     private final PDPage page;
     private final int pageNumber;
+    private final PDDocument document;
 
-    public PdfDocumentPageViewModel(PDPage page, int pageNumber) {
+    public PdfDocumentPageViewModel(PDPage page, int pageNumber, PDDocument document) {
         this.page = Objects.requireNonNull(page);
         this.pageNumber = pageNumber;
+        this.document = document;
     }
 
     // Taken from http://stackoverflow.com/a/9417836/873661
@@ -37,10 +42,12 @@ private static BufferedImage resize(BufferedImage img, int newWidth, int newHeig
     }
 
     @Override
+    // Taken from https://stackoverflow.com/questions/23326562/apache-pdfbox-convert-pdf-to-images
     public Image render(int width, int height) {
+        PDFRenderer renderer = new PDFRenderer(document);
         try {
             int resolution = 96;
-            BufferedImage image = page.convertToImage(BufferedImage.TYPE_INT_RGB, 2 * resolution);
+            BufferedImage image = renderer.renderImageWithDPI(pageNumber, 2 * resolution, ImageType.RGB);
             return SwingFXUtils.toFXImage(resize(image, width, height), null);
         } catch (IOException e) {
             // TODO: LOG

diff --git a/src/main/java/org/jabref/gui/documentviewer/PdfDocumentViewModel.java b/src/main/java/org/jabref/gui/documentviewer/PdfDocumentViewModel.java
@@ -8,7 +8,7 @@
 import javafx.collections.ObservableList;
 
 import org.apache.pdfbox.pdmodel.PDDocument;
-import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.PDPageTree;
 
 public class PdfDocumentViewModel extends DocumentViewModel {
 
@@ -21,13 +21,12 @@ public PdfDocumentViewModel(PDDocument document) {
 
     @Override
     public ObservableList<DocumentPageViewModel> getPages() {
-        @SuppressWarnings("unchecked")
-        List<PDPage> pages = document.getDocumentCatalog().getAllPages();
+        PDPageTree pages = document.getDocumentCatalog().getPages();
 
-        // There is apparently no neat way to get the page number from a PDPage...thus this old-style for loop
         List<PdfDocumentPageViewModel> pdfPages = new ArrayList<>();
-        for (int i = 0; i < pages.size(); i++) {
-            pdfPages.add(new PdfDocumentPageViewModel(pages.get(i), i + 1));
+        // There is apparently no neat way to get the page number from a PDPage...thus this old-style for loop
+        for (int i = 0; i < pages.getCount(); i++) {
+            pdfPages.add(new PdfDocumentPageViewModel(pages.get(i), i + 1, document));
         }
         return FXCollections.observableArrayList(pdfPages);
     }

diff --git a/src/main/java/org/jabref/gui/externalfiles/DroppedFileHandler.java b/src/main/java/org/jabref/gui/externalfiles/DroppedFileHandler.java
@@ -35,7 +35,7 @@
 import org.jabref.gui.util.DefaultTaskExecutor;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.logic.util.io.FileUtil;
-import org.jabref.logic.xmp.XMPUtil;
+import org.jabref.logic.xmp.XmpUtilReader;
 import org.jabref.model.database.BibDatabase;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.FieldName;
@@ -228,7 +228,7 @@ private boolean tryXmpImport(String fileName, ExternalFileType fileType, NamedCo
 
         List<BibEntry> xmpEntriesInFile;
         try {
-            xmpEntriesInFile = XMPUtil.readXMP(fileName, Globals.prefs.getXMPPreferences());
+            xmpEntriesInFile = XmpUtilReader.readXmp(fileName, Globals.prefs.getXMPPreferences());
         } catch (IOException e) {
             LOGGER.warn("Problem reading XMP", e);
             return false;

diff --git a/src/main/java/org/jabref/gui/externalfiles/WriteXMPAction.java b/src/main/java/org/jabref/gui/externalfiles/WriteXMPAction.java
@@ -31,7 +31,7 @@
 import org.jabref.gui.keyboard.KeyBinding;
 import org.jabref.gui.worker.AbstractWorker;
 import org.jabref.logic.l10n.Localization;
-import org.jabref.logic.xmp.XMPUtil;
+import org.jabref.logic.xmp.XmpUtilWriter;
 import org.jabref.model.database.BibDatabase;
 import org.jabref.model.entry.BibEntry;
 
@@ -133,7 +133,7 @@ public void run() {
                 for (Path file : files) {
                     if (Files.exists(file)) {
                         try {
-                            XMPUtil.writeXMP(file.toFile(), entry, database, Globals.prefs.getXMPPreferences());
+                            XmpUtilWriter.writeXmp(file, entry, database, Globals.prefs.getXMPPreferences());
                             SwingUtilities.invokeLater(
                                     () -> optDiag.getProgressArea().append("  " + Localization.lang("OK") + ".\n"));
                             entriesChanged++;

diff --git a/src/main/java/org/jabref/gui/fieldeditors/LinkedFileViewModel.java b/src/main/java/org/jabref/gui/fieldeditors/LinkedFileViewModel.java
@@ -34,7 +34,7 @@
 import org.jabref.logic.cleanup.RenamePdfCleanup;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.logic.util.io.FileUtil;
-import org.jabref.logic.xmp.XMPUtil;
+import org.jabref.logic.xmp.XmpUtilWriter;
 import org.jabref.model.database.BibDatabaseContext;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.LinkedFile;
@@ -331,7 +331,7 @@ public void writeXMPMetadata() {
                 // Localization.lang("PDF does not exist");
             } else {
                 try {
-                    XMPUtil.writeXMP(file.get(), entry, databaseContext.getDatabase(), Globals.prefs.getXMPPreferences());
+                    XmpUtilWriter.writeXmp(file.get(), entry, databaseContext.getDatabase(), Globals.prefs.getXMPPreferences());
                 } catch (IOException | TransformerException ex) {
                     // TODO: Print error message
                     // Localization.lang("Error while writing") + " '" + file.toString() + "': " + ex;