Merge branch '9481-pdf-codebook' into develop

Author: lubitchv

pom.xml

@@ -456,6 +456,12 @@
             <artifactId>commons-compress</artifactId>
             <!-- no version here as managed by <dependencyManagement> above! -->
         </dependency>
+        <!-- https://mvnrepository.com/artifact/org.apache.xmlgraphics/fop -->
+        <dependency>
+            <groupId>org.apache.xmlgraphics</groupId>
+            <artifactId>fop</artifactId>
+            <version>2.8</version>
+        </dependency>
         <dependency>
             <groupId>org.duracloud</groupId>
             <artifactId>common</artifactId>

src/main/java/edu/harvard/iq/dataverse/api/Datasets.java

@@ -272,7 +272,7 @@ public Response getDataset(@Context ContainerRequestContext crc, @PathParam("id"
 
     @GET
     @Path("/export")
-    @Produces({"application/xml", "application/json", "application/html" })
+    @Produces({"application/xml", "application/json", "application/html", "*/*" })
     public Response exportDataset(@QueryParam("persistentId") String persistentId, @QueryParam("exporter") String exporter, @Context UriInfo uriInfo, @Context HttpHeaders headers, @Context HttpServletResponse response) {
 
         try {

src/main/java/edu/harvard/iq/dataverse/export/PdfCodeBookExporter.java

@@ -0,0 +1,83 @@
+
+
+package edu.harvard.iq.dataverse.export;
+
+import com.google.auto.service.AutoService;
+import edu.harvard.iq.dataverse.Dataset;
+import edu.harvard.iq.dataverse.DatasetVersion;
+        import edu.harvard.iq.dataverse.export.ddi.DdiExportUtil;
+        import io.gdcc.spi.export.ExportDataProvider;
+        import io.gdcc.spi.export.ExportException;
+        import io.gdcc.spi.export.Exporter;
+        import edu.harvard.iq.dataverse.util.BundleUtil;
+
+        import javax.json.JsonObject;
+        import javax.ws.rs.core.MediaType;
+        import javax.xml.stream.XMLStreamException;
+        import java.io.File;
+        import java.io.IOException;
+        import java.io.InputStream;
+        import java.io.OutputStream;
+        import java.nio.file.Path;
+        import java.nio.file.Paths;
+        import java.util.Locale;
+        import java.util.Optional;
+
+@AutoService(Exporter.class)
+public class PdfCodeBookExporter implements Exporter {
+
+    @Override
+    public String getFormatName() {
+        return "pdf";
+    }
+
+    @Override
+    public String getDisplayName(Locale locale) {
+        String displayName = BundleUtil.getStringFromBundle("dataset.exportBtn.itemLabel.pdf", locale);
+        return Optional.ofNullable(displayName).orElse("DDI pdf codebook");
+    }
+
+    @Override
+    public void exportDataset(ExportDataProvider dataProvider, OutputStream outputStream) throws ExportException {
+        Optional<InputStream> ddiInputStreamOptional = dataProvider.getPrerequisiteInputStream();
+        if (ddiInputStreamOptional.isPresent()) {
+            try (InputStream ddiInputStream = ddiInputStreamOptional.get()) {
+                DdiExportUtil.datasetPdfDDI(ddiInputStream, outputStream);
+            } catch (IOException e) {
+                throw new ExportException("Cannot open export_ddi cached file");
+            } catch (XMLStreamException xse) {
+                throw new ExportException("Caught XMLStreamException performing DDI export");
+            }
+        } else {
+            throw new ExportException("No prerequisite input stream found");
+        }
+    }
+
+    @Override
+    public Boolean isHarvestable() {
+        // No, we don't want this format to be harvested!
+        // For datasets with tabular data the <data> portions of the DDIs
+        // become huge and expensive to parse; even as they don't contain any
+        // metadata useful to remote harvesters. -- L.A. 4.5
+        return false;
+    }
+
+    @Override
+    public Boolean isAvailableToUsers() {
+        return true;
+    }
+
+    @Override
+    public  Optional<String> getPrerequisiteFormatName() {
+        //This exporter relies on being able to get the output of the ddi exporter
+        return Optional.of("ddi");
+    }
+
+    @Override
+    public String  getMediaType() {
+        return MediaType.WILDCARD;
+    };
+}
+
+
+

src/main/java/edu/harvard/iq/dataverse/export/ddi/DdiExportUtil.java

@@ -27,6 +27,7 @@
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.io.OutputStream;
+import java.net.URL;
 import java.nio.file.Files;
 import java.nio.file.Paths;
 import java.time.LocalDate;
@@ -62,6 +63,21 @@
 import javax.xml.transform.stream.StreamResult;
 import java.io.InputStream;
 
+
+import java.io.OutputStream;
+import javax.xml.transform.Result;
+import javax.xml.transform.Source;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.sax.SAXResult;
+import javax.xml.transform.stream.StreamSource;
+
+import org.apache.fop.apps.FOUserAgent;
+import org.apache.fop.apps.Fop;
+import org.apache.fop.apps.FopFactory;
+import org.apache.fop.apps.MimeConstants;
+
+
 public class DdiExportUtil {
 
     private static final Logger logger = Logger.getLogger(DdiExportUtil.class.getCanonicalName());
@@ -2090,6 +2106,40 @@ private static boolean checkParentElement(XMLStreamWriter xmlw, String elementNa
         return true;
     }
 
+    public static void datasetPdfDDI(InputStream datafile, OutputStream outputStream) throws XMLStreamException {
+        try {
+            InputStream  styleSheetInput = DdiExportUtil.class.getClassLoader().getResourceAsStream("edu/harvard/iq/dataverse/ddi-to-fo.xsl");
+
+            final FopFactory fopFactory = FopFactory.newInstance(new File(".").toURI());
+            FOUserAgent foUserAgent = fopFactory.newFOUserAgent();
+
+            try {
+                Fop fop = fopFactory.newFop(MimeConstants.MIME_PDF, foUserAgent, outputStream);
+                // Setup XSLT
+                TransformerFactory factory = TransformerFactory.newInstance();
+                Transformer transformer = factory.newTransformer(new StreamSource(styleSheetInput));
+
+                // Set the value of a <param> in the stylesheet
+                transformer.setParameter("versionParam", "2.0");
+
+                // Setup input for XSLT transformation
+                Source src = new StreamSource(datafile);
+
+                // Resulting SAX events (the generated FO) must be piped through to FOP
+                Result res = new SAXResult(fop.getDefaultHandler());
+
+                // Start XSLT transformation and FOP processing
+                transformer.transform(src, res);
+
+            } catch (Exception e) {
+                logger.severe(e.getMessage());
+            }
+        }  catch (Exception e) {
+            logger.info("Second try");
+            logger.severe(e.getMessage());
+        }
+    }
+
     public static void datasetHtmlDDI(InputStream datafile, OutputStream outputStream) throws XMLStreamException {
         DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
 

src/main/java/propertyFiles/Bundle.properties

@@ -1401,6 +1401,7 @@ dataset.exportBtn.itemLabel.json=JSON
 dataset.exportBtn.itemLabel.oai_ore=OAI_ORE
 dataset.exportBtn.itemLabel.dataciteOpenAIRE=OpenAIRE
 dataset.exportBtn.itemLabel.html=DDI HTML Codebook
+dataset.exportBtn.itemLabel.pdf=DDI PDF Codebook
 license.custom=Custom Dataset Terms
 license.custom.description=Custom terms specific to this dataset
 metrics.title=Metrics