Rewriting for EPUB

git-svn-id: https://develop.sub.uni-goettingen.de/repos/textgrid/trunk/services/aggregator@13487 7c539038-3410-0410-b1ec-0f2a7bf1c452

pom.xml

@@ -101,7 +101,7 @@
 		<dependency>
 			<groupId>com.google.guava</groupId>
 			<artifactId>guava</artifactId>
-			<version>12.0</version>
+			<version>13.0.1</version>
 		</dependency>
 		<dependency>
 			<groupId>info.textgrid.middleware</groupId>

src/main/java/info/textgrid/services/aggregator/EPUB.java

@@ -6,16 +6,21 @@
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.IoFault;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.MetadataParseFault;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ObjectNotFoundFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ProtocolNotImplementedFault;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.TGCrudService;
+import info.textgrid.utils.linkrewriter.ConfigurableXMLRewriter;
 
 import java.io.File;
+import java.io.FileInputStream;
 import java.io.FileNotFoundException;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.net.URI;
+import java.net.URISyntaxException;
 import java.text.MessageFormat;
 import java.util.Deque;
 import java.util.LinkedList;
+import java.util.Map.Entry;
 import java.util.logging.Logger;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
@@ -27,6 +32,7 @@
 import javax.ws.rs.WebApplicationException;
 import javax.ws.rs.core.Response;
 import javax.ws.rs.core.Response.Status;
+import javax.xml.stream.XMLStreamException;
 import javax.xml.transform.stream.StreamSource;
 
 import net.sf.saxon.s9api.Processor;
@@ -35,6 +41,9 @@
 import net.sf.saxon.s9api.XsltExecutable;
 import net.sf.saxon.s9api.XsltTransformer;
 
+import org.xml.sax.SAXException;
+
+import com.google.common.io.ByteStreams;
 import com.google.common.io.Files;
 
 @Path("/epub")
@@ -51,38 +60,40 @@ public EPUB() {
 		xsltProcessor = new Processor(false);
 		final XsltCompiler xsltCompiler = xsltProcessor.newXsltCompiler();
 		try {
-			teiToEpub = xsltCompiler.compile(new StreamSource("/usr/share/xml/tei/stylesheet/epub/tei-to-epub.xsl"));
+			teiToEpub = xsltCompiler.compile(new StreamSource(
+					"/usr/share/xml/tei/stylesheet/epub/tei-to-epub.xsl"));
 		} catch (final SaxonApiException e) {
 			throw new IllegalStateException(e);
 		}
 	}
 
 	@GET
-	@Path(value="/{object}")
-	@Produces(value="application/epub+zip")
+	@Path(value = "/{object}")
+	@Produces(value = "application/epub+zip")
 	public Response get(@PathParam("object") final URI uri) {
 		logger.fine("EPUB called for root object: " + uri);
 		final TGCrudService crud = repository.getCRUDService();
 		try {
-			final MetadataContainerType container = crud.readMetadata(null, null, uri.toString());
+			final MetadataContainerType container = crud.readMetadata(null,
+					null, uri.toString());
 			final ObjectType rootObject = container.getObject();
-			final String mimeType = rootObject.getGeneric().getProvided().getFormat();
+			final String mimeType = rootObject.getGeneric().getProvided()
+					.getFormat();
 			final boolean aggregation = mimeType.contains("aggregation");
 			if (!aggregation && !mimeType.matches("^text/.*xml.*")) {
 				final String errorMsg = "The EPUB export can only convert aggregations or XML documents to EPUB, however, the document {0} you referred to has the MIME type {1}.";
 				logger.warning("Failing with: " + errorMsg);
-				return Response
-						.status(Status.UNSUPPORTED_MEDIA_TYPE)
+				return Response.status(Status.UNSUPPORTED_MEDIA_TYPE)
 						.entity(MessageFormat.format(errorMsg, uri, mimeType))
-						.type("text/plain")
-						.build();
+						.type("text/plain").build();
 			}
 
 			final File workingDir = Files.createTempDir();
 			logger.fine("Using " + workingDir + " to build the E-Book");
 
 			// First, use the aggregator to create a TEI corpus file to build on
-			final TEICorpusSerializer corpusSerializer = new TEICorpusSerializer(rootObject, true);
+			final TEICorpusSerializer corpusSerializer = new TEICorpusSerializer(
+					rootObject, true);
 			final File corpus = new File(workingDir, "corpus.xml");
 			final FileOutputStream corpusOutput = new FileOutputStream(corpus);
 			corpusSerializer.write(corpusOutput);
@@ -91,22 +102,36 @@ public Response get(@PathParam("object") final URI uri) {
 			// Now, run the EPUB stylesheet
 			// TODO cache the saxon stuff
 			final XsltTransformer transformer = teiToEpub.load();
-			transformer.setDestination(xsltProcessor.newSerializer(new File(workingDir, "output.xml")));
+			transformer.setDestination(xsltProcessor.newSerializer(new File(
+					workingDir, "output.xml")));
 			transformer.setSource(new StreamSource(corpus));
 			transformer.transform();
 
 			// Finally, create the ZIP file.
 			// FIXME first as a file
 			final File zipFile = new File(workingDir, "ebook.epub");
-			final ZipOutputStream zip = new ZipOutputStream(new FileOutputStream(zipFile));
+			final ZipOutputStream zip = new ZipOutputStream(
+					new FileOutputStream(zipFile));
 			try {
 
 				// first entry is the uncompressed mimetype marker
 				new MimeTypeEntry("application/epub+zip").writeTo(zip);
 
-				// now filtered filesystem structure. FIXME add rewriting + images
+				// now filtered filesystem structure. FIXME add rewriting +
+				// images
 				final File mimeTypeFile = new File(workingDir, "mimetype");
 				final URI base = workingDir.toURI();
+				final File opsDir = new File(workingDir, "OPS");
+				final URI ops = opsDir.toURI();
+				final OPFManifest manifest = new OPFManifest(new File(opsDir,
+						"content.opf"));
+				final ConfigurableXMLRewriter xhtmlRewriter = new ConfigurableXMLRewriter(
+						manifest.getImportMapping(), true);
+				xhtmlRewriter.configure(URI.create("internal:html#html"));
+				final ConfigurableXMLRewriter opfRewriter = new ConfigurableXMLRewriter(
+						manifest.getImportMapping(), true);
+				opfRewriter.configure(URI.create("internal:epub#opf"));
+
 				final Deque<File> queue = new LinkedList<File>();
 				queue.push(workingDir);
 				while (!queue.isEmpty()) {
@@ -114,7 +139,8 @@ public Response get(@PathParam("object") final URI uri) {
 
 					for (final File child : directory.listFiles()) {
 						// filter stuff we don't want:
-						if (child.equals(mimeTypeFile) || child.equals(corpus) || child.equals(zipFile))
+						if (child.equals(mimeTypeFile) || child.equals(corpus)
+								|| child.equals(zipFile))
 							continue;
 
 						String name = base.relativize(child.toURI()).getPath();
@@ -125,20 +151,52 @@ public Response get(@PathParam("object") final URI uri) {
 							zip.putNextEntry(new ZipEntry(name));
 						} else {
 							zip.putNextEntry(new ZipEntry(name));
-							Files.copy(child, zip);
+
+							if (Files.getFileExtension(name).equals("html"))
+								xhtmlRewriter.rewrite(
+										new FileInputStream(child), zip);
+							else if (Files.getFileExtension(name).equals("opf"))
+								opfRewriter.rewrite(new FileInputStream(child),
+										zip);
+							else
+								Files.copy(child, zip);
 							zip.closeEntry();
 						}
 					}
 				}
+
+				// now we need to add those files that are referenced by
+				// absolute URI in the manifest
+				for (final Entry<URI, String> externalItem : manifest.externalItems.entrySet()) {
+					final String pseudoFileName = base.relativize(new File(opsDir, manifest.getFileName(externalItem.getKey().toString())).toURI()).getPath();
+					zip.putNextEntry(new ZipEntry(pseudoFileName));
+					ByteStreams.copy(repository.getContent(externalItem.getKey()), zip);
+					zip.closeEntry();
+				}
+			} catch (final SAXException e) {
+				// TODO Auto-generated catch block
+				e.printStackTrace();
+			} catch (final URISyntaxException e) {
+				// TODO Auto-generated catch block
+				e.printStackTrace();
+			} catch (final XMLStreamException e) {
+				// TODO Auto-generated catch block
+				e.printStackTrace();
+			} catch (final ProtocolNotImplementedFault e) {
+				// TODO Auto-generated catch block
+				e.printStackTrace();
 			} finally {
 				zip.close();
 			}
-			return RESTUtils.attachmentResponse(rootObject.getGeneric().getProvided().getTitle().get(0) + ".epub")
-					.type("application/epub+zip")
-					.entity(zipFile)
-					.build();
-
-			//			return Response.ok().type("text/plain").entity("Done, see " + workingDir).build();
+			return RESTUtils
+					.attachmentResponse(
+							rootObject.getGeneric().getProvided().getTitle()
+							.get(0)
+							+ ".epub").type("application/epub+zip")
+							.entity(zipFile).build();
+
+			// return Response.ok().type("text/plain").entity("Done, see " +
+			// workingDir).build();
 		} catch (final ObjectNotFoundFault e) {
 			// TODO Auto-generated catch block
 			e.printStackTrace();
@@ -166,8 +224,6 @@ public Response get(@PathParam("object") final URI uri) {
 		}
 		return Response.noContent().build();
 
-
-
 	}
 
 }

src/main/java/info/textgrid/services/aggregator/ITextGridRep.java

 package info.textgrid.services.aggregator;
 
 import info.textgrid.middleware.tgsearch.client.SearchClient;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.AuthFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.IoFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.MetadataParseFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ObjectNotFoundFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ProtocolNotImplementedFault;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.TGCrudService;
 
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URI;
+
 import javax.ws.rs.WebApplicationException;
 
 public interface ITextGridRep {
@@ -13,5 +22,8 @@ public interface ITextGridRep {
 
 	public String getConfValue(final String key) throws WebApplicationException;
 
+	public abstract InputStream getContent(final URI uri)
+			throws ObjectNotFoundFault, MetadataParseFault, IoFault,
+			ProtocolNotImplementedFault, AuthFault, IOException;
 
 }
\ No newline at end of file

src/main/java/info/textgrid/services/aggregator/OPFManifest.java

+package info.textgrid.services.aggregator;
+
+import info.textgrid._import.ImportObject;
+import info.textgrid._import.RewriteMethod;
+import info.textgrid.utils.linkrewriter.ImportMapping;
+
+import java.io.File;
+import java.io.IOException;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.util.Map;
+import java.util.Map.Entry;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.ParserConfigurationException;
+
+import org.w3c.dom.Document;
+import org.w3c.dom.Element;
+import org.w3c.dom.NodeList;
+import org.xml.sax.SAXException;
+
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.ImmutableSortedMap;
+import com.google.common.collect.Maps;
+
+public class OPFManifest {
+	public static final String OPF_NS = "http://www.idpf.org/2007/opf";
+	public final ImmutableMap<URI, String> externalItems;
+	public static final ImmutableMap<String, String> EXTENSION = ImmutableMap
+			.of("image/jpeg", ".jpg", "image/png", ".png", "text/html", ".html");
+	private ImportMapping importMapping;
+
+	public OPFManifest(final File opfFile) throws SAXException, IOException,
+	URISyntaxException {
+		final DocumentBuilderFactory factory = DocumentBuilderFactory
+				.newInstance();
+		factory.setNamespaceAware(true);
+		DocumentBuilder builder;
+		try {
+			builder = factory.newDocumentBuilder();
+			final Document document = builder.parse(opfFile);
+			final NodeList itemList = document.getElementsByTagNameNS(OPF_NS,
+					"item");
+
+			final Map<URI, String> map = Maps.newLinkedHashMap();
+			for (int i = 0; i < itemList.getLength(); i++) {
+				final Element item = (Element) itemList.item(i);
+				final URI uri = new URI(item.getAttribute("href"));
+				if (uri.isAbsolute() && !map.containsKey(uri))
+					map.put(uri, item.getAttribute("media-type"));
+			}
+			externalItems = ImmutableSortedMap.copyOf(map);
+		} catch (final ParserConfigurationException e) {
+			throw new IllegalStateException(e);
+		}
+
+	}
+
+	public ImportMapping getImportMapping() {
+		if (importMapping == null) {
+			importMapping = new ImportMapping();
+			for (final Entry<URI, String> entry : externalItems.entrySet()) {
+				final String fileName = entry.getKey().getSchemeSpecificPart()
+						.concat(EXTENSION.get(entry.getValue()));
+				final ImportObject io = new ImportObject();
+				io.setTextgridUri(entry.getKey().toString());
+				io.setLocalData(fileName);
+				if (entry.getValue().equals("application/xhtml+xml")) {
+					io.setRewriteMethod(RewriteMethod.XML);
+					io.setRewriteConfig("internal:html#html");
+				}
+				importMapping.add(io);
+			}
+		};
+		return importMapping;
+	}
+
+	public String getFileName(final String uri) {
+		return getImportMapping().getImportObjectForTextGridURI(uri).getLocalData();
+	}
+
+}

src/main/java/info/textgrid/services/aggregator/TextGridRepProvider.java

@@ -3,17 +3,27 @@
 import info.textgrid.middleware.confclient.ConfservClient;
 import info.textgrid.middleware.confclient.ConfservClientConstants;
 import info.textgrid.middleware.tgsearch.client.SearchClient;
+import info.textgrid.namespaces.metadata.core._2010.MetadataContainerType;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.AuthFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.IoFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.MetadataParseFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ObjectNotFoundFault;
+import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.ProtocolNotImplementedFault;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.TGCrudService;
 import info.textgrid.namespaces.middleware.tgcrud.services.tgcrudservice.TGCrudService_Service;
 
 import java.io.IOException;
+import java.io.InputStream;
+import java.net.URI;
 import java.net.URL;
 import java.util.HashMap;
 import java.util.Map;
 
+import javax.activation.DataHandler;
 import javax.ws.rs.WebApplicationException;
 import javax.xml.stream.XMLStreamException;
 import javax.xml.ws.BindingProvider;
+import javax.xml.ws.Holder;
 import javax.xml.ws.soap.MTOMFeature;
 
 import org.codehaus.jettison.json.JSONException;
@@ -57,6 +67,15 @@ public TGCrudService getCRUDService() {
 		return crud;
 	}
 
+	@Override
+	public InputStream getContent(final URI uri) throws ObjectNotFoundFault, MetadataParseFault, IoFault, ProtocolNotImplementedFault, AuthFault, IOException {
+		final TGCrudService crudService = getCRUDService();
+		final Holder<MetadataContainerType> mdHolder = new Holder<MetadataContainerType>();
+		final Holder<DataHandler> dHolder = new Holder<DataHandler>();
+		crudService.read(null, null, uri.toString(), mdHolder, dHolder);
+		return dHolder.value.getInputStream();
+	}
+
 	@Override
 	public SearchClient getPublicSearchClient() {
 		if (publicSearchClient == null)

src/test/java/info/textgrid/services/aggregator/EPUBTest.java

+package info.textgrid.services.aggregator;
+
+import java.net.URI;
+
+import javax.ws.rs.core.Response;
+
+import org.junit.Test;
+
+public class EPUBTest {
+
+	@Test
+	public void testGet() {
+		final EPUB epub = new EPUB();
+		final Response response = epub.get(URI.create("textgrid:jfst.0"));
+	}
+
+}